diff options
Diffstat (limited to 'drivers/misc')
90 files changed, 14448 insertions, 828 deletions
diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig index 8dacd4c9ee87..6cb388e8fb7d 100644 --- a/drivers/misc/Kconfig +++ b/drivers/misc/Kconfig @@ -381,19 +381,6 @@ config HMC6352 This driver provides support for the Honeywell HMC6352 compass, providing configuration and heading data via sysfs. -config EP93XX_PWM - tristate "EP93xx PWM support" - depends on ARCH_EP93XX - help - This option enables device driver support for the PWM channels - on the Cirrus EP93xx processors. The EP9307 chip only has one - PWM channel all the others have two, the second channel is an - alternate function of the EGPIO14 pin. A sysfs interface is - provided to control the PWM channels. - - To compile this driver as a module, choose M here: the module will - be called ep93xx_pwm. - config DS1682 tristate "Dallas DS1682 Total Elapsed Time Recorder with Alarm" depends on I2C @@ -537,4 +524,6 @@ source "drivers/misc/carma/Kconfig" source "drivers/misc/altera-stapl/Kconfig" source "drivers/misc/mei/Kconfig" source "drivers/misc/vmw_vmci/Kconfig" +source "drivers/misc/mic/Kconfig" +source "drivers/misc/genwqe/Kconfig" endmenu diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile index c235d5b68311..99b9424ce31d 100644 --- a/drivers/misc/Makefile +++ b/drivers/misc/Makefile @@ -33,7 +33,6 @@ obj-$(CONFIG_APDS9802ALS) += apds9802als.o obj-$(CONFIG_ISL29003) += isl29003.o obj-$(CONFIG_ISL29020) += isl29020.o obj-$(CONFIG_SENSORS_TSL2550) += tsl2550.o -obj-$(CONFIG_EP93XX_PWM) += ep93xx_pwm.o obj-$(CONFIG_DS1682) += ds1682.o obj-$(CONFIG_TI_DAC7512) += ti_dac7512.o obj-$(CONFIG_C2PORT) += c2port/ @@ -53,3 +52,5 @@ obj-$(CONFIG_INTEL_MEI) += mei/ obj-$(CONFIG_VMWARE_VMCI) += vmw_vmci/ obj-$(CONFIG_LATTICE_ECP3_CONFIG) += lattice-ecp3-config.o obj-$(CONFIG_SRAM) += sram.o +obj-y += mic/ +obj-$(CONFIG_GENWQE) += genwqe/ diff --git a/drivers/misc/ad525x_dpot.c b/drivers/misc/ad525x_dpot.c index 0daadcf1ed7a..d3eee113baeb 100644 --- a/drivers/misc/ad525x_dpot.c +++ b/drivers/misc/ad525x_dpot.c @@ -641,7 +641,7 @@ static const struct attribute_group ad525x_group_commands = { .attrs = ad525x_attributes_commands, }; -int ad_dpot_add_files(struct device *dev, +static int ad_dpot_add_files(struct device *dev, unsigned features, unsigned rdac) { int err = sysfs_create_file(&dev->kobj, @@ -666,7 +666,7 @@ int ad_dpot_add_files(struct device *dev, return err; } -inline void ad_dpot_remove_files(struct device *dev, +static inline void ad_dpot_remove_files(struct device *dev, unsigned features, unsigned rdac) { sysfs_remove_file(&dev->kobj, diff --git a/drivers/misc/arm-charlcd.c b/drivers/misc/arm-charlcd.c index 1256a4bf1c04..b7ebf8021d99 100644 --- a/drivers/misc/arm-charlcd.c +++ b/drivers/misc/arm-charlcd.c @@ -297,7 +297,7 @@ static int __init charlcd_probe(struct platform_device *pdev) lcd->irq = platform_get_irq(pdev, 0); /* If no IRQ is supplied, we'll survive without it */ if (lcd->irq >= 0) { - if (request_irq(lcd->irq, charlcd_interrupt, IRQF_DISABLED, + if (request_irq(lcd->irq, charlcd_interrupt, 0, DRIVERNAME, lcd)) { ret = -EIO; goto out_no_irq; diff --git a/drivers/misc/atmel_pwm.c b/drivers/misc/atmel_pwm.c index 494d0500bda6..a6dc56e1bc58 100644 --- a/drivers/misc/atmel_pwm.c +++ b/drivers/misc/atmel_pwm.c @@ -90,8 +90,10 @@ int pwm_channel_alloc(int index, struct pwm_channel *ch) unsigned long flags; int status = 0; - /* insist on PWM init, with this signal pinned out */ - if (!pwm || !(pwm->mask & 1 << index)) + if (!pwm) + return -EPROBE_DEFER; + + if (!(pwm->mask & 1 << index)) return -ENODEV; if (index < 0 || index >= PWM_NCHAN || !ch) diff --git a/drivers/misc/bh1780gli.c b/drivers/misc/bh1780gli.c index 057580e026c0..48ea33d15a79 100644 --- a/drivers/misc/bh1780gli.c +++ b/drivers/misc/bh1780gli.c @@ -23,6 +23,7 @@ #include <linux/platform_device.h> #include <linux/delay.h> #include <linux/module.h> +#include <linux/of.h> #define BH1780_REG_CONTROL 0x80 #define BH1780_REG_PARTID 0x8A @@ -244,6 +245,15 @@ static const struct i2c_device_id bh1780_id[] = { { }, }; +#ifdef CONFIG_OF +static const struct of_device_id of_bh1780_match[] = { + { .compatible = "rohm,bh1780gli", }, + {}, +}; + +MODULE_DEVICE_TABLE(of, of_bh1780_match); +#endif + static struct i2c_driver bh1780_driver = { .probe = bh1780_probe, .remove = bh1780_remove, @@ -251,6 +261,7 @@ static struct i2c_driver bh1780_driver = { .driver = { .name = "bh1780", .pm = &bh1780_pm, + .of_match_table = of_match_ptr(of_bh1780_match), }, }; diff --git a/drivers/misc/bmp085-i2c.c b/drivers/misc/bmp085-i2c.c index 3abfcecf8424..a7c16295b816 100644 --- a/drivers/misc/bmp085-i2c.c +++ b/drivers/misc/bmp085-i2c.c @@ -49,7 +49,7 @@ static int bmp085_i2c_probe(struct i2c_client *client, return err; } - return bmp085_probe(&client->dev, regmap); + return bmp085_probe(&client->dev, regmap, client->irq); } static int bmp085_i2c_remove(struct i2c_client *client) diff --git a/drivers/misc/bmp085-spi.c b/drivers/misc/bmp085-spi.c index d6a52659cf24..864ecac32373 100644 --- a/drivers/misc/bmp085-spi.c +++ b/drivers/misc/bmp085-spi.c @@ -41,7 +41,7 @@ static int bmp085_spi_probe(struct spi_device *client) return err; } - return bmp085_probe(&client->dev, regmap); + return bmp085_probe(&client->dev, regmap, client->irq); } static int bmp085_spi_remove(struct spi_device *client) diff --git a/drivers/misc/bmp085.c b/drivers/misc/bmp085.c index 849e2fed4da2..820e53d0048f 100644 --- a/drivers/misc/bmp085.c +++ b/drivers/misc/bmp085.c @@ -49,9 +49,11 @@ #include <linux/device.h> #include <linux/init.h> #include <linux/slab.h> -#include <linux/delay.h> #include <linux/of.h> #include "bmp085.h" +#include <linux/interrupt.h> +#include <linux/completion.h> +#include <linux/gpio.h> #define BMP085_CHIP_ID 0x55 #define BMP085_CALIBRATION_DATA_START 0xAA @@ -84,8 +86,19 @@ struct bmp085_data { unsigned long last_temp_measurement; u8 chip_id; s32 b6; /* calculated temperature correction coefficient */ + int irq; + struct completion done; }; +static irqreturn_t bmp085_eoc_isr(int irq, void *devid) +{ + struct bmp085_data *data = devid; + + complete(&data->done); + + return IRQ_HANDLED; +} + static s32 bmp085_read_calibration_data(struct bmp085_data *data) { u16 tmp[BMP085_CALIBRATION_DATA_LENGTH]; @@ -116,6 +129,9 @@ static s32 bmp085_update_raw_temperature(struct bmp085_data *data) s32 status; mutex_lock(&data->lock); + + init_completion(&data->done); + status = regmap_write(data->regmap, BMP085_CTRL_REG, BMP085_TEMP_MEASUREMENT); if (status < 0) { @@ -123,7 +139,8 @@ static s32 bmp085_update_raw_temperature(struct bmp085_data *data) "Error while requesting temperature measurement.\n"); goto exit; } - msleep(BMP085_TEMP_CONVERSION_TIME); + wait_for_completion_timeout(&data->done, 1 + msecs_to_jiffies( + BMP085_TEMP_CONVERSION_TIME)); status = regmap_bulk_read(data->regmap, BMP085_CONVERSION_REGISTER_MSB, &tmp, sizeof(tmp)); @@ -147,6 +164,9 @@ static s32 bmp085_update_raw_pressure(struct bmp085_data *data) s32 status; mutex_lock(&data->lock); + + init_completion(&data->done); + status = regmap_write(data->regmap, BMP085_CTRL_REG, BMP085_PRESSURE_MEASUREMENT + (data->oversampling_setting << 6)); @@ -157,8 +177,8 @@ static s32 bmp085_update_raw_pressure(struct bmp085_data *data) } /* wait for the end of conversion */ - msleep(2+(3 << data->oversampling_setting)); - + wait_for_completion_timeout(&data->done, 1 + msecs_to_jiffies( + 2+(3 << data->oversampling_setting))); /* copy data into a u32 (4 bytes), but skip the first byte. */ status = regmap_bulk_read(data->regmap, BMP085_CONVERSION_REGISTER_MSB, ((u8 *)&tmp)+1, 3); @@ -374,7 +394,7 @@ int bmp085_detect(struct device *dev) } EXPORT_SYMBOL_GPL(bmp085_detect); -static void __init bmp085_get_of_properties(struct bmp085_data *data) +static void bmp085_get_of_properties(struct bmp085_data *data) { #ifdef CONFIG_OF struct device_node *np = data->dev->of_node; @@ -420,7 +440,7 @@ struct regmap_config bmp085_regmap_config = { }; EXPORT_SYMBOL_GPL(bmp085_regmap_config); -int bmp085_probe(struct device *dev, struct regmap *regmap) +int bmp085_probe(struct device *dev, struct regmap *regmap, int irq) { struct bmp085_data *data; int err = 0; @@ -434,6 +454,15 @@ int bmp085_probe(struct device *dev, struct regmap *regmap) dev_set_drvdata(dev, data); data->dev = dev; data->regmap = regmap; + data->irq = irq; + + if (data->irq > 0) { + err = devm_request_irq(dev, data->irq, bmp085_eoc_isr, + IRQF_TRIGGER_RISING, "bmp085", + data); + if (err < 0) + goto exit_free; + } /* Initialize the BMP085 chip */ err = bmp085_init_client(data); diff --git a/drivers/misc/bmp085.h b/drivers/misc/bmp085.h index 2b8f615bca92..8b8e3b1f5ca5 100644 --- a/drivers/misc/bmp085.h +++ b/drivers/misc/bmp085.h @@ -26,7 +26,7 @@ extern struct regmap_config bmp085_regmap_config; -int bmp085_probe(struct device *dev, struct regmap *regmap); +int bmp085_probe(struct device *dev, struct regmap *regmap, int irq); int bmp085_remove(struct device *dev); int bmp085_detect(struct device *dev); diff --git a/drivers/misc/carma/carma-fpga-program.c b/drivers/misc/carma/carma-fpga-program.c index c6bd7e84de24..7be89832db19 100644 --- a/drivers/misc/carma/carma-fpga-program.c +++ b/drivers/misc/carma/carma-fpga-program.c @@ -10,6 +10,8 @@ */ #include <linux/dma-mapping.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> #include <linux/of_platform.h> #include <linux/completion.h> #include <linux/miscdevice.h> diff --git a/drivers/misc/carma/carma-fpga.c b/drivers/misc/carma/carma-fpga.c index 7b56563f8b74..9e2b985293fc 100644 --- a/drivers/misc/carma/carma-fpga.c +++ b/drivers/misc/carma/carma-fpga.c @@ -88,6 +88,8 @@ * interrupt source to the GPIO pin. Tada, we hid the interrupt. :) */ +#include <linux/of_address.h> +#include <linux/of_irq.h> #include <linux/of_platform.h> #include <linux/dma-mapping.h> #include <linux/miscdevice.h> @@ -631,8 +633,7 @@ static int data_submit_dma(struct fpga_device *priv, struct data_buf *buf) struct dma_async_tx_descriptor *tx; dma_cookie_t cookie; dma_addr_t dst, src; - unsigned long dma_flags = DMA_COMPL_SKIP_DEST_UNMAP | - DMA_COMPL_SKIP_SRC_UNMAP; + unsigned long dma_flags = 0; dst_sg = buf->vb.sglist; dst_nents = buf->vb.sglen; diff --git a/drivers/misc/cb710/core.c b/drivers/misc/cb710/core.c index 2e50f811ff59..fb397e7d1cce 100644 --- a/drivers/misc/cb710/core.c +++ b/drivers/misc/cb710/core.c @@ -176,7 +176,7 @@ static int cb710_suspend(struct pci_dev *pdev, pm_message_t state) { struct cb710_chip *chip = pci_get_drvdata(pdev); - free_irq(pdev->irq, chip); + devm_free_irq(&pdev->dev, pdev->irq, chip); pci_save_state(pdev); pci_disable_device(pdev); if (state.event & PM_EVENT_SLEEP) diff --git a/drivers/misc/eeprom/Kconfig b/drivers/misc/eeprom/Kconfig index 04f2e1fa9dd1..9536852fd4c6 100644 --- a/drivers/misc/eeprom/Kconfig +++ b/drivers/misc/eeprom/Kconfig @@ -96,4 +96,17 @@ config EEPROM_DIGSY_MTC_CFG If unsure, say N. +config EEPROM_SUNXI_SID + tristate "Allwinner sunxi security ID support" + depends on ARCH_SUNXI && SYSFS + help + This is a driver for the 'security ID' available on various Allwinner + devices. + + Due to the potential risks involved with changing e-fuses, + this driver is read-only. + + This driver can also be built as a module. If so, the module + will be called sunxi_sid. + endmenu diff --git a/drivers/misc/eeprom/Makefile b/drivers/misc/eeprom/Makefile index fc1e81d29267..9507aec95e94 100644 --- a/drivers/misc/eeprom/Makefile +++ b/drivers/misc/eeprom/Makefile @@ -4,4 +4,5 @@ obj-$(CONFIG_EEPROM_LEGACY) += eeprom.o obj-$(CONFIG_EEPROM_MAX6875) += max6875.o obj-$(CONFIG_EEPROM_93CX6) += eeprom_93cx6.o obj-$(CONFIG_EEPROM_93XX46) += eeprom_93xx46.o +obj-$(CONFIG_EEPROM_SUNXI_SID) += sunxi_sid.o obj-$(CONFIG_EEPROM_DIGSY_MTC_CFG) += digsy_mtc_eeprom.o diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c index 5d4fd69d04ca..d87f77f790d6 100644 --- a/drivers/misc/eeprom/at24.c +++ b/drivers/misc/eeprom/at24.c @@ -22,7 +22,7 @@ #include <linux/jiffies.h> #include <linux/of.h> #include <linux/i2c.h> -#include <linux/i2c/at24.h> +#include <linux/platform_data/at24.h> /* * I2C EEPROMs from most vendors are inexpensive and mostly interchangeable. @@ -428,6 +428,9 @@ static ssize_t at24_bin_write(struct file *filp, struct kobject *kobj, { struct at24_data *at24; + if (unlikely(off >= attr->size)) + return -EFBIG; + at24 = dev_get_drvdata(container_of(kobj, struct device, kobj)); return at24_write(at24, buf, off, count); } diff --git a/drivers/misc/eeprom/at25.c b/drivers/misc/eeprom/at25.c index 840b3594a5ae..4f3bca1003a1 100644 --- a/drivers/misc/eeprom/at25.c +++ b/drivers/misc/eeprom/at25.c @@ -462,10 +462,17 @@ static int at25_remove(struct spi_device *spi) /*-------------------------------------------------------------------------*/ +static const struct of_device_id at25_of_match[] = { + { .compatible = "atmel,at25", }, + { } +}; +MODULE_DEVICE_TABLE(of, at25_of_match); + static struct spi_driver at25_driver = { .driver = { .name = "at25", .owner = THIS_MODULE, + .of_match_table = at25_of_match, }, .probe = at25_probe, .remove = at25_remove, diff --git a/drivers/misc/eeprom/eeprom_93xx46.c b/drivers/misc/eeprom/eeprom_93xx46.c index 94cfc1212577..78e55b501c94 100644 --- a/drivers/misc/eeprom/eeprom_93xx46.c +++ b/drivers/misc/eeprom/eeprom_93xx46.c @@ -202,7 +202,7 @@ eeprom_93xx46_bin_write(struct file *filp, struct kobject *kobj, edev = dev_get_drvdata(dev); if (unlikely(off >= edev->bin.size)) - return 0; + return -EFBIG; if ((off + count) > edev->bin.size) count = edev->bin.size - off; if (unlikely(!count)) @@ -378,7 +378,6 @@ static int eeprom_93xx46_remove(struct spi_device *spi) device_remove_file(&spi->dev, &dev_attr_erase); sysfs_remove_bin_file(&spi->dev.kobj, &edev->bin); - spi_set_drvdata(spi, NULL); kfree(edev); return 0; } diff --git a/drivers/misc/eeprom/sunxi_sid.c b/drivers/misc/eeprom/sunxi_sid.c new file mode 100644 index 000000000000..9c34e5704304 --- /dev/null +++ b/drivers/misc/eeprom/sunxi_sid.c @@ -0,0 +1,158 @@ +/* + * Copyright (c) 2013 Oliver Schinagl <oliver@schinagl.nl> + * http://www.linux-sunxi.org + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * This driver exposes the Allwinner security ID, efuses exported in byte- + * sized chunks. + */ + +#include <linux/compiler.h> +#include <linux/device.h> +#include <linux/err.h> +#include <linux/export.h> +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/io.h> +#include <linux/kernel.h> +#include <linux/kobject.h> +#include <linux/module.h> +#include <linux/of_device.h> +#include <linux/platform_device.h> +#include <linux/random.h> +#include <linux/slab.h> +#include <linux/stat.h> +#include <linux/sysfs.h> +#include <linux/types.h> + +#define DRV_NAME "sunxi-sid" + +struct sunxi_sid_data { + void __iomem *reg_base; + unsigned int keysize; +}; + +/* We read the entire key, due to a 32 bit read alignment requirement. Since we + * want to return the requested byte, this results in somewhat slower code and + * uses 4 times more reads as needed but keeps code simpler. Since the SID is + * only very rarely probed, this is not really an issue. + */ +static u8 sunxi_sid_read_byte(const struct sunxi_sid_data *sid_data, + const unsigned int offset) +{ + u32 sid_key; + + if (offset >= sid_data->keysize) + return 0; + + sid_key = ioread32be(sid_data->reg_base + round_down(offset, 4)); + sid_key >>= (offset % 4) * 8; + + return sid_key; /* Only return the last byte */ +} + +static ssize_t sid_read(struct file *fd, struct kobject *kobj, + struct bin_attribute *attr, char *buf, + loff_t pos, size_t size) +{ + struct platform_device *pdev; + struct sunxi_sid_data *sid_data; + int i; + + pdev = to_platform_device(kobj_to_dev(kobj)); + sid_data = platform_get_drvdata(pdev); + + if (pos < 0 || pos >= sid_data->keysize) + return 0; + if (size > sid_data->keysize - pos) + size = sid_data->keysize - pos; + + for (i = 0; i < size; i++) + buf[i] = sunxi_sid_read_byte(sid_data, pos + i); + + return i; +} + +static struct bin_attribute sid_bin_attr = { + .attr = { .name = "eeprom", .mode = S_IRUGO, }, + .read = sid_read, +}; + +static int sunxi_sid_remove(struct platform_device *pdev) +{ + device_remove_bin_file(&pdev->dev, &sid_bin_attr); + dev_dbg(&pdev->dev, "driver unloaded\n"); + + return 0; +} + +static const struct of_device_id sunxi_sid_of_match[] = { + { .compatible = "allwinner,sun4i-sid", .data = (void *)16}, + { .compatible = "allwinner,sun7i-a20-sid", .data = (void *)512}, + {/* sentinel */}, +}; +MODULE_DEVICE_TABLE(of, sunxi_sid_of_match); + +static int sunxi_sid_probe(struct platform_device *pdev) +{ + struct sunxi_sid_data *sid_data; + struct resource *res; + const struct of_device_id *of_dev_id; + u8 *entropy; + unsigned int i; + + sid_data = devm_kzalloc(&pdev->dev, sizeof(struct sunxi_sid_data), + GFP_KERNEL); + if (!sid_data) + return -ENOMEM; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + sid_data->reg_base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(sid_data->reg_base)) + return PTR_ERR(sid_data->reg_base); + + of_dev_id = of_match_device(sunxi_sid_of_match, &pdev->dev); + if (!of_dev_id) + return -ENODEV; + sid_data->keysize = (int)of_dev_id->data; + + platform_set_drvdata(pdev, sid_data); + + sid_bin_attr.size = sid_data->keysize; + if (device_create_bin_file(&pdev->dev, &sid_bin_attr)) + return -ENODEV; + + entropy = kzalloc(sizeof(u8) * sid_data->keysize, GFP_KERNEL); + for (i = 0; i < sid_data->keysize; i++) + entropy[i] = sunxi_sid_read_byte(sid_data, i); + add_device_randomness(entropy, sid_data->keysize); + kfree(entropy); + + dev_dbg(&pdev->dev, "loaded\n"); + + return 0; +} + +static struct platform_driver sunxi_sid_driver = { + .probe = sunxi_sid_probe, + .remove = sunxi_sid_remove, + .driver = { + .name = DRV_NAME, + .owner = THIS_MODULE, + .of_match_table = sunxi_sid_of_match, + }, +}; +module_platform_driver(sunxi_sid_driver); + +MODULE_AUTHOR("Oliver Schinagl <oliver@schinagl.nl>"); +MODULE_DESCRIPTION("Allwinner sunxi security id driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/misc/enclosure.c b/drivers/misc/enclosure.c index 0e8df41aaf14..2cf2bbc0b927 100644 --- a/drivers/misc/enclosure.c +++ b/drivers/misc/enclosure.c @@ -198,6 +198,13 @@ static void enclosure_remove_links(struct enclosure_component *cdev) { char name[ENCLOSURE_NAME_SIZE]; + /* + * In odd circumstances, like multipath devices, something else may + * already have removed the links, so check for this condition first. + */ + if (!cdev->dev->kobj.sd) + return; + enclosure_link_name(cdev, name); sysfs_remove_link(&cdev->dev->kobj, name); sysfs_remove_link(&cdev->cdev.kobj, "device"); diff --git a/drivers/misc/ep93xx_pwm.c b/drivers/misc/ep93xx_pwm.c deleted file mode 100644 index cdb67a9c1959..000000000000 --- a/drivers/misc/ep93xx_pwm.c +++ /dev/null @@ -1,286 +0,0 @@ -/* - * Simple PWM driver for EP93XX - * - * (c) Copyright 2009 Matthieu Crapet <mcrapet@gmail.com> - * (c) Copyright 2009 H Hartley Sweeten <hsweeten@visionengravers.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - * EP9307 has only one channel: - * - PWMOUT - * - * EP9301/02/12/15 have two channels: - * - PWMOUT - * - PWMOUT1 (alternate function for EGPIO14) - */ - -#include <linux/module.h> -#include <linux/platform_device.h> -#include <linux/slab.h> -#include <linux/clk.h> -#include <linux/err.h> -#include <linux/io.h> - -#include <mach/platform.h> - -#define EP93XX_PWMx_TERM_COUNT 0x00 -#define EP93XX_PWMx_DUTY_CYCLE 0x04 -#define EP93XX_PWMx_ENABLE 0x08 -#define EP93XX_PWMx_INVERT 0x0C - -#define EP93XX_PWM_MAX_COUNT 0xFFFF - -struct ep93xx_pwm { - void __iomem *mmio_base; - struct clk *clk; - u32 duty_percent; -}; - -/* - * /sys/devices/platform/ep93xx-pwm.N - * /min_freq read-only minimum pwm output frequency - * /max_req read-only maximum pwm output frequency - * /freq read-write pwm output frequency (0 = disable output) - * /duty_percent read-write pwm duty cycle percent (1..99) - * /invert read-write invert pwm output - */ - -static ssize_t ep93xx_pwm_get_min_freq(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct platform_device *pdev = to_platform_device(dev); - struct ep93xx_pwm *pwm = platform_get_drvdata(pdev); - unsigned long rate = clk_get_rate(pwm->clk); - - return sprintf(buf, "%ld\n", rate / (EP93XX_PWM_MAX_COUNT + 1)); -} - -static ssize_t ep93xx_pwm_get_max_freq(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct platform_device *pdev = to_platform_device(dev); - struct ep93xx_pwm *pwm = platform_get_drvdata(pdev); - unsigned long rate = clk_get_rate(pwm->clk); - - return sprintf(buf, "%ld\n", rate / 2); -} - -static ssize_t ep93xx_pwm_get_freq(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct platform_device *pdev = to_platform_device(dev); - struct ep93xx_pwm *pwm = platform_get_drvdata(pdev); - - if (readl(pwm->mmio_base + EP93XX_PWMx_ENABLE) & 0x1) { - unsigned long rate = clk_get_rate(pwm->clk); - u16 term = readl(pwm->mmio_base + EP93XX_PWMx_TERM_COUNT); - - return sprintf(buf, "%ld\n", rate / (term + 1)); - } else { - return sprintf(buf, "disabled\n"); - } -} - -static ssize_t ep93xx_pwm_set_freq(struct device *dev, - struct device_attribute *attr, const char *buf, size_t count) -{ - struct platform_device *pdev = to_platform_device(dev); - struct ep93xx_pwm *pwm = platform_get_drvdata(pdev); - long val; - int err; - - err = kstrtol(buf, 10, &val); - if (err) - return -EINVAL; - - if (val == 0) { - writel(0x0, pwm->mmio_base + EP93XX_PWMx_ENABLE); - } else if (val <= (clk_get_rate(pwm->clk) / 2)) { - u32 term, duty; - - val = (clk_get_rate(pwm->clk) / val) - 1; - if (val > EP93XX_PWM_MAX_COUNT) - val = EP93XX_PWM_MAX_COUNT; - if (val < 1) - val = 1; - - term = readl(pwm->mmio_base + EP93XX_PWMx_TERM_COUNT); - duty = ((val + 1) * pwm->duty_percent / 100) - 1; - - /* If pwm is running, order is important */ - if (val > term) { - writel(val, pwm->mmio_base + EP93XX_PWMx_TERM_COUNT); - writel(duty, pwm->mmio_base + EP93XX_PWMx_DUTY_CYCLE); - } else { - writel(duty, pwm->mmio_base + EP93XX_PWMx_DUTY_CYCLE); - writel(val, pwm->mmio_base + EP93XX_PWMx_TERM_COUNT); - } - - if (!readl(pwm->mmio_base + EP93XX_PWMx_ENABLE) & 0x1) - writel(0x1, pwm->mmio_base + EP93XX_PWMx_ENABLE); - } else { - return -EINVAL; - } - - return count; -} - -static ssize_t ep93xx_pwm_get_duty_percent(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct platform_device *pdev = to_platform_device(dev); - struct ep93xx_pwm *pwm = platform_get_drvdata(pdev); - - return sprintf(buf, "%d\n", pwm->duty_percent); -} - -static ssize_t ep93xx_pwm_set_duty_percent(struct device *dev, - struct device_attribute *attr, const char *buf, size_t count) -{ - struct platform_device *pdev = to_platform_device(dev); - struct ep93xx_pwm *pwm = platform_get_drvdata(pdev); - long val; - int err; - - err = kstrtol(buf, 10, &val); - if (err) - return -EINVAL; - - if (val > 0 && val < 100) { - u32 term = readl(pwm->mmio_base + EP93XX_PWMx_TERM_COUNT); - u32 duty = ((term + 1) * val / 100) - 1; - - writel(duty, pwm->mmio_base + EP93XX_PWMx_DUTY_CYCLE); - pwm->duty_percent = val; - return count; - } - - return -EINVAL; -} - -static ssize_t ep93xx_pwm_get_invert(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct platform_device *pdev = to_platform_device(dev); - struct ep93xx_pwm *pwm = platform_get_drvdata(pdev); - int inverted = readl(pwm->mmio_base + EP93XX_PWMx_INVERT) & 0x1; - - return sprintf(buf, "%d\n", inverted); -} - -static ssize_t ep93xx_pwm_set_invert(struct device *dev, - struct device_attribute *attr, const char *buf, size_t count) -{ - struct platform_device *pdev = to_platform_device(dev); - struct ep93xx_pwm *pwm = platform_get_drvdata(pdev); - long val; - int err; - - err = kstrtol(buf, 10, &val); - if (err) - return -EINVAL; - - if (val == 0) - writel(0x0, pwm->mmio_base + EP93XX_PWMx_INVERT); - else if (val == 1) - writel(0x1, pwm->mmio_base + EP93XX_PWMx_INVERT); - else - return -EINVAL; - - return count; -} - -static DEVICE_ATTR(min_freq, S_IRUGO, ep93xx_pwm_get_min_freq, NULL); -static DEVICE_ATTR(max_freq, S_IRUGO, ep93xx_pwm_get_max_freq, NULL); -static DEVICE_ATTR(freq, S_IWUSR | S_IRUGO, - ep93xx_pwm_get_freq, ep93xx_pwm_set_freq); -static DEVICE_ATTR(duty_percent, S_IWUSR | S_IRUGO, - ep93xx_pwm_get_duty_percent, ep93xx_pwm_set_duty_percent); -static DEVICE_ATTR(invert, S_IWUSR | S_IRUGO, - ep93xx_pwm_get_invert, ep93xx_pwm_set_invert); - -static struct attribute *ep93xx_pwm_attrs[] = { - &dev_attr_min_freq.attr, - &dev_attr_max_freq.attr, - &dev_attr_freq.attr, - &dev_attr_duty_percent.attr, - &dev_attr_invert.attr, - NULL -}; - -static const struct attribute_group ep93xx_pwm_sysfs_files = { - .attrs = ep93xx_pwm_attrs, -}; - -static int ep93xx_pwm_probe(struct platform_device *pdev) -{ - struct ep93xx_pwm *pwm; - struct resource *res; - int ret; - - pwm = devm_kzalloc(&pdev->dev, sizeof(*pwm), GFP_KERNEL); - if (!pwm) - return -ENOMEM; - - pwm->clk = devm_clk_get(&pdev->dev, "pwm_clk"); - if (IS_ERR(pwm->clk)) - return PTR_ERR(pwm->clk); - - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - pwm->mmio_base = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(pwm->mmio_base)) - return PTR_ERR(pwm->mmio_base); - - ret = ep93xx_pwm_acquire_gpio(pdev); - if (ret) - return ret; - - ret = sysfs_create_group(&pdev->dev.kobj, &ep93xx_pwm_sysfs_files); - if (ret) { - ep93xx_pwm_release_gpio(pdev); - return ret; - } - - pwm->duty_percent = 50; - - /* disable pwm at startup. Avoids zero value. */ - writel(0x0, pwm->mmio_base + EP93XX_PWMx_ENABLE); - writel(EP93XX_PWM_MAX_COUNT, pwm->mmio_base + EP93XX_PWMx_TERM_COUNT); - writel(EP93XX_PWM_MAX_COUNT/2, pwm->mmio_base + EP93XX_PWMx_DUTY_CYCLE); - - clk_enable(pwm->clk); - - platform_set_drvdata(pdev, pwm); - return 0; -} - -static int ep93xx_pwm_remove(struct platform_device *pdev) -{ - struct ep93xx_pwm *pwm = platform_get_drvdata(pdev); - - writel(0x0, pwm->mmio_base + EP93XX_PWMx_ENABLE); - clk_disable(pwm->clk); - sysfs_remove_group(&pdev->dev.kobj, &ep93xx_pwm_sysfs_files); - ep93xx_pwm_release_gpio(pdev); - - return 0; -} - -static struct platform_driver ep93xx_pwm_driver = { - .driver = { - .name = "ep93xx-pwm", - .owner = THIS_MODULE, - }, - .probe = ep93xx_pwm_probe, - .remove = ep93xx_pwm_remove, -}; -module_platform_driver(ep93xx_pwm_driver); - -MODULE_AUTHOR("Matthieu Crapet <mcrapet@gmail.com>, " - "H Hartley Sweeten <hsweeten@visionengravers.com>"); -MODULE_DESCRIPTION("EP93xx PWM driver"); -MODULE_LICENSE("GPL"); -MODULE_ALIAS("platform:ep93xx-pwm"); diff --git a/drivers/misc/fsa9480.c b/drivers/misc/fsa9480.c index a725c79c35f5..71d2793b372c 100644 --- a/drivers/misc/fsa9480.c +++ b/drivers/misc/fsa9480.c @@ -396,7 +396,7 @@ static int fsa9480_irq_init(struct fsa9480_usbsw *usbsw) IRQF_TRIGGER_FALLING | IRQF_ONESHOT, "fsa9480 micro USB", usbsw); if (ret) { - dev_err(&client->dev, "failed to reqeust IRQ\n"); + dev_err(&client->dev, "failed to request IRQ\n"); return ret; } diff --git a/drivers/misc/genwqe/Kconfig b/drivers/misc/genwqe/Kconfig new file mode 100644 index 000000000000..6069d8cd79d7 --- /dev/null +++ b/drivers/misc/genwqe/Kconfig @@ -0,0 +1,13 @@ +# +# IBM Accelerator Family 'GenWQE' +# + +menuconfig GENWQE + tristate "GenWQE PCIe Accelerator" + depends on PCI && 64BIT + select CRC_ITU_T + default n + help + Enables PCIe card driver for IBM GenWQE accelerators. + The user-space interface is described in + include/linux/genwqe/genwqe_card.h. diff --git a/drivers/misc/genwqe/Makefile b/drivers/misc/genwqe/Makefile new file mode 100644 index 000000000000..98a2b4f0b18b --- /dev/null +++ b/drivers/misc/genwqe/Makefile @@ -0,0 +1,7 @@ +# +# Makefile for GenWQE driver +# + +obj-$(CONFIG_GENWQE) := genwqe_card.o +genwqe_card-objs := card_base.o card_dev.o card_ddcb.o card_sysfs.o \ + card_debugfs.o card_utils.o diff --git a/drivers/misc/genwqe/card_base.c b/drivers/misc/genwqe/card_base.c new file mode 100644 index 000000000000..74d51c9bb858 --- /dev/null +++ b/drivers/misc/genwqe/card_base.c @@ -0,0 +1,1205 @@ +/** + * IBM Accelerator Family 'GenWQE' + * + * (C) Copyright IBM Corp. 2013 + * + * Author: Frank Haverkamp <haver@linux.vnet.ibm.com> + * Author: Joerg-Stephan Vogt <jsvogt@de.ibm.com> + * Author: Michael Jung <mijung@de.ibm.com> + * Author: Michael Ruettger <michael@ibmra.de> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +/* + * Module initialization and PCIe setup. Card health monitoring and + * recovery functionality. Character device creation and deletion are + * controlled from here. + */ + +#include <linux/module.h> +#include <linux/types.h> +#include <linux/pci.h> +#include <linux/err.h> +#include <linux/aer.h> +#include <linux/string.h> +#include <linux/sched.h> +#include <linux/wait.h> +#include <linux/delay.h> +#include <linux/dma-mapping.h> +#include <linux/module.h> +#include <linux/notifier.h> +#include <linux/device.h> +#include <linux/log2.h> +#include <linux/genwqe/genwqe_card.h> + +#include "card_base.h" +#include "card_ddcb.h" + +MODULE_AUTHOR("Frank Haverkamp <haver@linux.vnet.ibm.com>"); +MODULE_AUTHOR("Michael Ruettger <michael@ibmra.de>"); +MODULE_AUTHOR("Joerg-Stephan Vogt <jsvogt@de.ibm.com>"); +MODULE_AUTHOR("Michal Jung <mijung@de.ibm.com>"); + +MODULE_DESCRIPTION("GenWQE Card"); +MODULE_VERSION(DRV_VERS_STRING); +MODULE_LICENSE("GPL"); + +static char genwqe_driver_name[] = GENWQE_DEVNAME; +static struct class *class_genwqe; +static struct dentry *debugfs_genwqe; +static struct genwqe_dev *genwqe_devices[GENWQE_CARD_NO_MAX]; + +/* PCI structure for identifying device by PCI vendor and device ID */ +static DEFINE_PCI_DEVICE_TABLE(genwqe_device_table) = { + { .vendor = PCI_VENDOR_ID_IBM, + .device = PCI_DEVICE_GENWQE, + .subvendor = PCI_SUBVENDOR_ID_IBM, + .subdevice = PCI_SUBSYSTEM_ID_GENWQE5, + .class = (PCI_CLASSCODE_GENWQE5 << 8), + .class_mask = ~0, + .driver_data = 0 }, + + /* Initial SR-IOV bring-up image */ + { .vendor = PCI_VENDOR_ID_IBM, + .device = PCI_DEVICE_GENWQE, + .subvendor = PCI_SUBVENDOR_ID_IBM_SRIOV, + .subdevice = PCI_SUBSYSTEM_ID_GENWQE5_SRIOV, + .class = (PCI_CLASSCODE_GENWQE5_SRIOV << 8), + .class_mask = ~0, + .driver_data = 0 }, + + { .vendor = PCI_VENDOR_ID_IBM, /* VF Vendor ID */ + .device = 0x0000, /* VF Device ID */ + .subvendor = PCI_SUBVENDOR_ID_IBM_SRIOV, + .subdevice = PCI_SUBSYSTEM_ID_GENWQE5_SRIOV, + .class = (PCI_CLASSCODE_GENWQE5_SRIOV << 8), + .class_mask = ~0, + .driver_data = 0 }, + + /* Fixed up image */ + { .vendor = PCI_VENDOR_ID_IBM, + .device = PCI_DEVICE_GENWQE, + .subvendor = PCI_SUBVENDOR_ID_IBM_SRIOV, + .subdevice = PCI_SUBSYSTEM_ID_GENWQE5, + .class = (PCI_CLASSCODE_GENWQE5_SRIOV << 8), + .class_mask = ~0, + .driver_data = 0 }, + + { .vendor = PCI_VENDOR_ID_IBM, /* VF Vendor ID */ + .device = 0x0000, /* VF Device ID */ + .subvendor = PCI_SUBVENDOR_ID_IBM_SRIOV, + .subdevice = PCI_SUBSYSTEM_ID_GENWQE5, + .class = (PCI_CLASSCODE_GENWQE5_SRIOV << 8), + .class_mask = ~0, + .driver_data = 0 }, + + /* Even one more ... */ + { .vendor = PCI_VENDOR_ID_IBM, + .device = PCI_DEVICE_GENWQE, + .subvendor = PCI_SUBVENDOR_ID_IBM, + .subdevice = PCI_SUBSYSTEM_ID_GENWQE5_NEW, + .class = (PCI_CLASSCODE_GENWQE5 << 8), + .class_mask = ~0, + .driver_data = 0 }, + + { 0, } /* 0 terminated list. */ +}; + +MODULE_DEVICE_TABLE(pci, genwqe_device_table); + +/** + * genwqe_dev_alloc() - Create and prepare a new card descriptor + * + * Return: Pointer to card descriptor, or ERR_PTR(err) on error + */ +static struct genwqe_dev *genwqe_dev_alloc(void) +{ + unsigned int i = 0, j; + struct genwqe_dev *cd; + + for (i = 0; i < GENWQE_CARD_NO_MAX; i++) { + if (genwqe_devices[i] == NULL) + break; + } + if (i >= GENWQE_CARD_NO_MAX) + return ERR_PTR(-ENODEV); + + cd = kzalloc(sizeof(struct genwqe_dev), GFP_KERNEL); + if (!cd) + return ERR_PTR(-ENOMEM); + + cd->card_idx = i; + cd->class_genwqe = class_genwqe; + cd->debugfs_genwqe = debugfs_genwqe; + + init_waitqueue_head(&cd->queue_waitq); + + spin_lock_init(&cd->file_lock); + INIT_LIST_HEAD(&cd->file_list); + + cd->card_state = GENWQE_CARD_UNUSED; + spin_lock_init(&cd->print_lock); + + cd->ddcb_software_timeout = genwqe_ddcb_software_timeout; + cd->kill_timeout = genwqe_kill_timeout; + + for (j = 0; j < GENWQE_MAX_VFS; j++) + cd->vf_jobtimeout_msec[j] = genwqe_vf_jobtimeout_msec; + + genwqe_devices[i] = cd; + return cd; +} + +static void genwqe_dev_free(struct genwqe_dev *cd) +{ + if (!cd) + return; + + genwqe_devices[cd->card_idx] = NULL; + kfree(cd); +} + +/** + * genwqe_bus_reset() - Card recovery + * + * pci_reset_function() will recover the device and ensure that the + * registers are accessible again when it completes with success. If + * not, the card will stay dead and registers will be unaccessible + * still. + */ +static int genwqe_bus_reset(struct genwqe_dev *cd) +{ + int bars, rc = 0; + struct pci_dev *pci_dev = cd->pci_dev; + void __iomem *mmio; + + if (cd->err_inject & GENWQE_INJECT_BUS_RESET_FAILURE) + return -EIO; + + mmio = cd->mmio; + cd->mmio = NULL; + pci_iounmap(pci_dev, mmio); + + bars = pci_select_bars(pci_dev, IORESOURCE_MEM); + pci_release_selected_regions(pci_dev, bars); + + /* + * Firmware/BIOS might change memory mapping during bus reset. + * Settings like enable bus-mastering, ... are backuped and + * restored by the pci_reset_function(). + */ + dev_dbg(&pci_dev->dev, "[%s] pci_reset function ...\n", __func__); + rc = pci_reset_function(pci_dev); + if (rc) { + dev_err(&pci_dev->dev, + "[%s] err: failed reset func (rc %d)\n", __func__, rc); + return rc; + } + dev_dbg(&pci_dev->dev, "[%s] done with rc=%d\n", __func__, rc); + + /* + * Here is the right spot to clear the register read + * failure. pci_bus_reset() does this job in real systems. + */ + cd->err_inject &= ~(GENWQE_INJECT_HARDWARE_FAILURE | + GENWQE_INJECT_GFIR_FATAL | + GENWQE_INJECT_GFIR_INFO); + + rc = pci_request_selected_regions(pci_dev, bars, genwqe_driver_name); + if (rc) { + dev_err(&pci_dev->dev, + "[%s] err: request bars failed (%d)\n", __func__, rc); + return -EIO; + } + + cd->mmio = pci_iomap(pci_dev, 0, 0); + if (cd->mmio == NULL) { + dev_err(&pci_dev->dev, + "[%s] err: mapping BAR0 failed\n", __func__); + return -ENOMEM; + } + return 0; +} + +/* + * Hardware circumvention section. Certain bitstreams in our test-lab + * had different kinds of problems. Here is where we adjust those + * bitstreams to function will with this version of our device driver. + * + * Thise circumventions are applied to the physical function only. + * The magical numbers below are identifying development/manufacturing + * versions of the bitstream used on the card. + * + * Turn off error reporting for old/manufacturing images. + */ + +bool genwqe_need_err_masking(struct genwqe_dev *cd) +{ + return (cd->slu_unitcfg & 0xFFFF0ull) < 0x32170ull; +} + +static void genwqe_tweak_hardware(struct genwqe_dev *cd) +{ + struct pci_dev *pci_dev = cd->pci_dev; + + /* Mask FIRs for development images */ + if (((cd->slu_unitcfg & 0xFFFF0ull) >= 0x32000ull) && + ((cd->slu_unitcfg & 0xFFFF0ull) <= 0x33250ull)) { + dev_warn(&pci_dev->dev, + "FIRs masked due to bitstream %016llx.%016llx\n", + cd->slu_unitcfg, cd->app_unitcfg); + + __genwqe_writeq(cd, IO_APP_SEC_LEM_DEBUG_OVR, + 0xFFFFFFFFFFFFFFFFull); + + __genwqe_writeq(cd, IO_APP_ERR_ACT_MASK, + 0x0000000000000000ull); + } +} + +/** + * genwqe_recovery_on_fatal_gfir_required() - Version depended actions + * + * Bitstreams older than 2013-02-17 have a bug where fatal GFIRs must + * be ignored. This is e.g. true for the bitstream we gave to the card + * manufacturer, but also for some old bitstreams we released to our + * test-lab. + */ +int genwqe_recovery_on_fatal_gfir_required(struct genwqe_dev *cd) +{ + return (cd->slu_unitcfg & 0xFFFF0ull) >= 0x32170ull; +} + +int genwqe_flash_readback_fails(struct genwqe_dev *cd) +{ + return (cd->slu_unitcfg & 0xFFFF0ull) < 0x32170ull; +} + +/** + * genwqe_T_psec() - Calculate PF/VF timeout register content + * + * Note: From a design perspective it turned out to be a bad idea to + * use codes here to specifiy the frequency/speed values. An old + * driver cannot understand new codes and is therefore always a + * problem. Better is to measure out the value or put the + * speed/frequency directly into a register which is always a valid + * value for old as well as for new software. + */ +/* T = 1/f */ +static int genwqe_T_psec(struct genwqe_dev *cd) +{ + u16 speed; /* 1/f -> 250, 200, 166, 175 */ + static const int T[] = { 4000, 5000, 6000, 5714 }; + + speed = (u16)((cd->slu_unitcfg >> 28) & 0x0full); + if (speed >= ARRAY_SIZE(T)) + return -1; /* illegal value */ + + return T[speed]; +} + +/** + * genwqe_setup_pf_jtimer() - Setup PF hardware timeouts for DDCB execution + * + * Do this _after_ card_reset() is called. Otherwise the values will + * vanish. The settings need to be done when the queues are inactive. + * + * The max. timeout value is 2^(10+x) * T (6ns for 166MHz) * 15/16. + * The min. timeout value is 2^(10+x) * T (6ns for 166MHz) * 14/16. + */ +static bool genwqe_setup_pf_jtimer(struct genwqe_dev *cd) +{ + u32 T = genwqe_T_psec(cd); + u64 x; + + if (genwqe_pf_jobtimeout_msec == 0) + return false; + + /* PF: large value needed, flash update 2sec per block */ + x = ilog2(genwqe_pf_jobtimeout_msec * + 16000000000uL/(T * 15)) - 10; + + genwqe_write_vreg(cd, IO_SLC_VF_APPJOB_TIMEOUT, + 0xff00 | (x & 0xff), 0); + return true; +} + +/** + * genwqe_setup_vf_jtimer() - Setup VF hardware timeouts for DDCB execution + */ +static bool genwqe_setup_vf_jtimer(struct genwqe_dev *cd) +{ + struct pci_dev *pci_dev = cd->pci_dev; + unsigned int vf; + u32 T = genwqe_T_psec(cd); + u64 x; + + for (vf = 0; vf < pci_sriov_get_totalvfs(pci_dev); vf++) { + + if (cd->vf_jobtimeout_msec[vf] == 0) + continue; + + x = ilog2(cd->vf_jobtimeout_msec[vf] * + 16000000000uL/(T * 15)) - 10; + + genwqe_write_vreg(cd, IO_SLC_VF_APPJOB_TIMEOUT, + 0xff00 | (x & 0xff), vf + 1); + } + return true; +} + +static int genwqe_ffdc_buffs_alloc(struct genwqe_dev *cd) +{ + unsigned int type, e = 0; + + for (type = 0; type < GENWQE_DBG_UNITS; type++) { + switch (type) { + case GENWQE_DBG_UNIT0: + e = genwqe_ffdc_buff_size(cd, 0); + break; + case GENWQE_DBG_UNIT1: + e = genwqe_ffdc_buff_size(cd, 1); + break; + case GENWQE_DBG_UNIT2: + e = genwqe_ffdc_buff_size(cd, 2); + break; + case GENWQE_DBG_REGS: + e = GENWQE_FFDC_REGS; + break; + } + + /* currently support only the debug units mentioned here */ + cd->ffdc[type].entries = e; + cd->ffdc[type].regs = kmalloc(e * sizeof(struct genwqe_reg), + GFP_KERNEL); + /* + * regs == NULL is ok, the using code treats this as no regs, + * Printing warning is ok in this case. + */ + } + return 0; +} + +static void genwqe_ffdc_buffs_free(struct genwqe_dev *cd) +{ + unsigned int type; + + for (type = 0; type < GENWQE_DBG_UNITS; type++) { + kfree(cd->ffdc[type].regs); + cd->ffdc[type].regs = NULL; + } +} + +static int genwqe_read_ids(struct genwqe_dev *cd) +{ + int err = 0; + int slu_id; + struct pci_dev *pci_dev = cd->pci_dev; + + cd->slu_unitcfg = __genwqe_readq(cd, IO_SLU_UNITCFG); + if (cd->slu_unitcfg == IO_ILLEGAL_VALUE) { + dev_err(&pci_dev->dev, + "err: SLUID=%016llx\n", cd->slu_unitcfg); + err = -EIO; + goto out_err; + } + + slu_id = genwqe_get_slu_id(cd); + if (slu_id < GENWQE_SLU_ARCH_REQ || slu_id == 0xff) { + dev_err(&pci_dev->dev, + "err: incompatible SLU Architecture %u\n", slu_id); + err = -ENOENT; + goto out_err; + } + + cd->app_unitcfg = __genwqe_readq(cd, IO_APP_UNITCFG); + if (cd->app_unitcfg == IO_ILLEGAL_VALUE) { + dev_err(&pci_dev->dev, + "err: APPID=%016llx\n", cd->app_unitcfg); + err = -EIO; + goto out_err; + } + genwqe_read_app_id(cd, cd->app_name, sizeof(cd->app_name)); + + /* + * Is access to all registers possible? If we are a VF the + * answer is obvious. If we run fully virtualized, we need to + * check if we can access all registers. If we do not have + * full access we will cause an UR and some informational FIRs + * in the PF, but that should not harm. + */ + if (pci_dev->is_virtfn) + cd->is_privileged = 0; + else + cd->is_privileged = (__genwqe_readq(cd, IO_SLU_BITSTREAM) + != IO_ILLEGAL_VALUE); + + out_err: + return err; +} + +static int genwqe_start(struct genwqe_dev *cd) +{ + int err; + struct pci_dev *pci_dev = cd->pci_dev; + + err = genwqe_read_ids(cd); + if (err) + return err; + + if (genwqe_is_privileged(cd)) { + /* do this after the tweaks. alloc fail is acceptable */ + genwqe_ffdc_buffs_alloc(cd); + genwqe_stop_traps(cd); + + /* Collect registers e.g. FIRs, UNITIDs, traces ... */ + genwqe_read_ffdc_regs(cd, cd->ffdc[GENWQE_DBG_REGS].regs, + cd->ffdc[GENWQE_DBG_REGS].entries, 0); + + genwqe_ffdc_buff_read(cd, GENWQE_DBG_UNIT0, + cd->ffdc[GENWQE_DBG_UNIT0].regs, + cd->ffdc[GENWQE_DBG_UNIT0].entries); + + genwqe_ffdc_buff_read(cd, GENWQE_DBG_UNIT1, + cd->ffdc[GENWQE_DBG_UNIT1].regs, + cd->ffdc[GENWQE_DBG_UNIT1].entries); + + genwqe_ffdc_buff_read(cd, GENWQE_DBG_UNIT2, + cd->ffdc[GENWQE_DBG_UNIT2].regs, + cd->ffdc[GENWQE_DBG_UNIT2].entries); + + genwqe_start_traps(cd); + + if (cd->card_state == GENWQE_CARD_FATAL_ERROR) { + dev_warn(&pci_dev->dev, + "[%s] chip reload/recovery!\n", __func__); + + /* + * Stealth Mode: Reload chip on either hot + * reset or PERST. + */ + cd->softreset = 0x7Cull; + __genwqe_writeq(cd, IO_SLC_CFGREG_SOFTRESET, + cd->softreset); + + err = genwqe_bus_reset(cd); + if (err != 0) { + dev_err(&pci_dev->dev, + "[%s] err: bus reset failed!\n", + __func__); + goto out; + } + + /* + * Re-read the IDs because + * it could happen that the bitstream load + * failed! + */ + err = genwqe_read_ids(cd); + if (err) + goto out; + } + } + + err = genwqe_setup_service_layer(cd); /* does a reset to the card */ + if (err != 0) { + dev_err(&pci_dev->dev, + "[%s] err: could not setup servicelayer!\n", __func__); + err = -ENODEV; + goto out; + } + + if (genwqe_is_privileged(cd)) { /* code is running _after_ reset */ + genwqe_tweak_hardware(cd); + + genwqe_setup_pf_jtimer(cd); + genwqe_setup_vf_jtimer(cd); + } + + err = genwqe_device_create(cd); + if (err < 0) { + dev_err(&pci_dev->dev, + "err: chdev init failed! (err=%d)\n", err); + goto out_release_service_layer; + } + return 0; + + out_release_service_layer: + genwqe_release_service_layer(cd); + out: + if (genwqe_is_privileged(cd)) + genwqe_ffdc_buffs_free(cd); + return -EIO; +} + +/** + * genwqe_stop() - Stop card operation + * + * Recovery notes: + * As long as genwqe_thread runs we might access registers during + * error data capture. Same is with the genwqe_health_thread. + * When genwqe_bus_reset() fails this function might called two times: + * first by the genwqe_health_thread() and later by genwqe_remove() to + * unbind the device. We must be able to survive that. + * + * This function must be robust enough to be called twice. + */ +static int genwqe_stop(struct genwqe_dev *cd) +{ + genwqe_finish_queue(cd); /* no register access */ + genwqe_device_remove(cd); /* device removed, procs killed */ + genwqe_release_service_layer(cd); /* here genwqe_thread is stopped */ + + if (genwqe_is_privileged(cd)) { + pci_disable_sriov(cd->pci_dev); /* access pci config space */ + genwqe_ffdc_buffs_free(cd); + } + + return 0; +} + +/** + * genwqe_recover_card() - Try to recover the card if it is possible + * + * If fatal_err is set no register access is possible anymore. It is + * likely that genwqe_start fails in that situation. Proper error + * handling is required in this case. + * + * genwqe_bus_reset() will cause the pci code to call genwqe_remove() + * and later genwqe_probe() for all virtual functions. + */ +static int genwqe_recover_card(struct genwqe_dev *cd, int fatal_err) +{ + int rc; + struct pci_dev *pci_dev = cd->pci_dev; + + genwqe_stop(cd); + + /* + * Make sure chip is not reloaded to maintain FFDC. Write SLU + * Reset Register, CPLDReset field to 0. + */ + if (!fatal_err) { + cd->softreset = 0x70ull; + __genwqe_writeq(cd, IO_SLC_CFGREG_SOFTRESET, cd->softreset); + } + + rc = genwqe_bus_reset(cd); + if (rc != 0) { + dev_err(&pci_dev->dev, + "[%s] err: card recovery impossible!\n", __func__); + return rc; + } + + rc = genwqe_start(cd); + if (rc < 0) { + dev_err(&pci_dev->dev, + "[%s] err: failed to launch device!\n", __func__); + return rc; + } + return 0; +} + +static int genwqe_health_check_cond(struct genwqe_dev *cd, u64 *gfir) +{ + *gfir = __genwqe_readq(cd, IO_SLC_CFGREG_GFIR); + return (*gfir & GFIR_ERR_TRIGGER) && + genwqe_recovery_on_fatal_gfir_required(cd); +} + +/** + * genwqe_fir_checking() - Check the fault isolation registers of the card + * + * If this code works ok, can be tried out with help of the genwqe_poke tool: + * sudo ./tools/genwqe_poke 0x8 0xfefefefefef + * + * Now the relevant FIRs/sFIRs should be printed out and the driver should + * invoke recovery (devices are removed and readded). + */ +static u64 genwqe_fir_checking(struct genwqe_dev *cd) +{ + int j, iterations = 0; + u64 mask, fir, fec, uid, gfir, gfir_masked, sfir, sfec; + u32 fir_addr, fir_clr_addr, fec_addr, sfir_addr, sfec_addr; + struct pci_dev *pci_dev = cd->pci_dev; + + healthMonitor: + iterations++; + if (iterations > 16) { + dev_err(&pci_dev->dev, "* exit looping after %d times\n", + iterations); + goto fatal_error; + } + + gfir = __genwqe_readq(cd, IO_SLC_CFGREG_GFIR); + if (gfir != 0x0) + dev_err(&pci_dev->dev, "* 0x%08x 0x%016llx\n", + IO_SLC_CFGREG_GFIR, gfir); + if (gfir == IO_ILLEGAL_VALUE) + goto fatal_error; + + /* + * Avoid printing when to GFIR bit is on prevents contignous + * printout e.g. for the following bug: + * FIR set without a 2ndary FIR/FIR cannot be cleared + * Comment out the following if to get the prints: + */ + if (gfir == 0) + return 0; + + gfir_masked = gfir & GFIR_ERR_TRIGGER; /* fatal errors */ + + for (uid = 0; uid < GENWQE_MAX_UNITS; uid++) { /* 0..2 in zEDC */ + + /* read the primary FIR (pfir) */ + fir_addr = (uid << 24) + 0x08; + fir = __genwqe_readq(cd, fir_addr); + if (fir == 0x0) + continue; /* no error in this unit */ + + dev_err(&pci_dev->dev, "* 0x%08x 0x%016llx\n", fir_addr, fir); + if (fir == IO_ILLEGAL_VALUE) + goto fatal_error; + + /* read primary FEC */ + fec_addr = (uid << 24) + 0x18; + fec = __genwqe_readq(cd, fec_addr); + + dev_err(&pci_dev->dev, "* 0x%08x 0x%016llx\n", fec_addr, fec); + if (fec == IO_ILLEGAL_VALUE) + goto fatal_error; + + for (j = 0, mask = 1ULL; j < 64; j++, mask <<= 1) { + + /* secondary fir empty, skip it */ + if ((fir & mask) == 0x0) + continue; + + sfir_addr = (uid << 24) + 0x100 + 0x08 * j; + sfir = __genwqe_readq(cd, sfir_addr); + + if (sfir == IO_ILLEGAL_VALUE) + goto fatal_error; + dev_err(&pci_dev->dev, + "* 0x%08x 0x%016llx\n", sfir_addr, sfir); + + sfec_addr = (uid << 24) + 0x300 + 0x08 * j; + sfec = __genwqe_readq(cd, sfec_addr); + + if (sfec == IO_ILLEGAL_VALUE) + goto fatal_error; + dev_err(&pci_dev->dev, + "* 0x%08x 0x%016llx\n", sfec_addr, sfec); + + gfir = __genwqe_readq(cd, IO_SLC_CFGREG_GFIR); + if (gfir == IO_ILLEGAL_VALUE) + goto fatal_error; + + /* gfir turned on during routine! get out and + start over. */ + if ((gfir_masked == 0x0) && + (gfir & GFIR_ERR_TRIGGER)) { + goto healthMonitor; + } + + /* do not clear if we entered with a fatal gfir */ + if (gfir_masked == 0x0) { + + /* NEW clear by mask the logged bits */ + sfir_addr = (uid << 24) + 0x100 + 0x08 * j; + __genwqe_writeq(cd, sfir_addr, sfir); + + dev_dbg(&pci_dev->dev, + "[HM] Clearing 2ndary FIR 0x%08x " + "with 0x%016llx\n", sfir_addr, sfir); + + /* + * note, these cannot be error-Firs + * since gfir_masked is 0 after sfir + * was read. Also, it is safe to do + * this write if sfir=0. Still need to + * clear the primary. This just means + * there is no secondary FIR. + */ + + /* clear by mask the logged bit. */ + fir_clr_addr = (uid << 24) + 0x10; + __genwqe_writeq(cd, fir_clr_addr, mask); + + dev_dbg(&pci_dev->dev, + "[HM] Clearing primary FIR 0x%08x " + "with 0x%016llx\n", fir_clr_addr, + mask); + } + } + } + gfir = __genwqe_readq(cd, IO_SLC_CFGREG_GFIR); + if (gfir == IO_ILLEGAL_VALUE) + goto fatal_error; + + if ((gfir_masked == 0x0) && (gfir & GFIR_ERR_TRIGGER)) { + /* + * Check once more that it didn't go on after all the + * FIRS were cleared. + */ + dev_dbg(&pci_dev->dev, "ACK! Another FIR! Recursing %d!\n", + iterations); + goto healthMonitor; + } + return gfir_masked; + + fatal_error: + return IO_ILLEGAL_VALUE; +} + +/** + * genwqe_health_thread() - Health checking thread + * + * This thread is only started for the PF of the card. + * + * This thread monitors the health of the card. A critical situation + * is when we read registers which contain -1 (IO_ILLEGAL_VALUE). In + * this case we need to be recovered from outside. Writing to + * registers will very likely not work either. + * + * This thread must only exit if kthread_should_stop() becomes true. + * + * Condition for the health-thread to trigger: + * a) when a kthread_stop() request comes in or + * b) a critical GFIR occured + * + * Informational GFIRs are checked and potentially printed in + * health_check_interval seconds. + */ +static int genwqe_health_thread(void *data) +{ + int rc, should_stop = 0; + struct genwqe_dev *cd = data; + struct pci_dev *pci_dev = cd->pci_dev; + u64 gfir, gfir_masked, slu_unitcfg, app_unitcfg; + + while (!kthread_should_stop()) { + rc = wait_event_interruptible_timeout(cd->health_waitq, + (genwqe_health_check_cond(cd, &gfir) || + (should_stop = kthread_should_stop())), + genwqe_health_check_interval * HZ); + + if (should_stop) + break; + + if (gfir == IO_ILLEGAL_VALUE) { + dev_err(&pci_dev->dev, + "[%s] GFIR=%016llx\n", __func__, gfir); + goto fatal_error; + } + + slu_unitcfg = __genwqe_readq(cd, IO_SLU_UNITCFG); + if (slu_unitcfg == IO_ILLEGAL_VALUE) { + dev_err(&pci_dev->dev, + "[%s] SLU_UNITCFG=%016llx\n", + __func__, slu_unitcfg); + goto fatal_error; + } + + app_unitcfg = __genwqe_readq(cd, IO_APP_UNITCFG); + if (app_unitcfg == IO_ILLEGAL_VALUE) { + dev_err(&pci_dev->dev, + "[%s] APP_UNITCFG=%016llx\n", + __func__, app_unitcfg); + goto fatal_error; + } + + gfir = __genwqe_readq(cd, IO_SLC_CFGREG_GFIR); + if (gfir == IO_ILLEGAL_VALUE) { + dev_err(&pci_dev->dev, + "[%s] %s: GFIR=%016llx\n", __func__, + (gfir & GFIR_ERR_TRIGGER) ? "err" : "info", + gfir); + goto fatal_error; + } + + gfir_masked = genwqe_fir_checking(cd); + if (gfir_masked == IO_ILLEGAL_VALUE) + goto fatal_error; + + /* + * GFIR ErrorTrigger bits set => reset the card! + * Never do this for old/manufacturing images! + */ + if ((gfir_masked) && !cd->skip_recovery && + genwqe_recovery_on_fatal_gfir_required(cd)) { + + cd->card_state = GENWQE_CARD_FATAL_ERROR; + + rc = genwqe_recover_card(cd, 0); + if (rc < 0) { + /* FIXME Card is unusable and needs unbind! */ + goto fatal_error; + } + } + + cd->last_gfir = gfir; + cond_resched(); + } + + return 0; + + fatal_error: + dev_err(&pci_dev->dev, + "[%s] card unusable. Please trigger unbind!\n", __func__); + + /* Bring down logical devices to inform user space via udev remove. */ + cd->card_state = GENWQE_CARD_FATAL_ERROR; + genwqe_stop(cd); + + /* genwqe_bus_reset failed(). Now wait for genwqe_remove(). */ + while (!kthread_should_stop()) + cond_resched(); + + return -EIO; +} + +static int genwqe_health_check_start(struct genwqe_dev *cd) +{ + int rc; + + if (genwqe_health_check_interval <= 0) + return 0; /* valid for disabling the service */ + + /* moved before request_irq() */ + /* init_waitqueue_head(&cd->health_waitq); */ + + cd->health_thread = kthread_run(genwqe_health_thread, cd, + GENWQE_DEVNAME "%d_health", + cd->card_idx); + if (IS_ERR(cd->health_thread)) { + rc = PTR_ERR(cd->health_thread); + cd->health_thread = NULL; + return rc; + } + return 0; +} + +static int genwqe_health_thread_running(struct genwqe_dev *cd) +{ + return cd->health_thread != NULL; +} + +static int genwqe_health_check_stop(struct genwqe_dev *cd) +{ + int rc; + + if (!genwqe_health_thread_running(cd)) + return -EIO; + + rc = kthread_stop(cd->health_thread); + cd->health_thread = NULL; + return 0; +} + +/** + * genwqe_pci_setup() - Allocate PCIe related resources for our card + */ +static int genwqe_pci_setup(struct genwqe_dev *cd) +{ + int err, bars; + struct pci_dev *pci_dev = cd->pci_dev; + + bars = pci_select_bars(pci_dev, IORESOURCE_MEM); + err = pci_enable_device_mem(pci_dev); + if (err) { + dev_err(&pci_dev->dev, + "err: failed to enable pci memory (err=%d)\n", err); + goto err_out; + } + + /* Reserve PCI I/O and memory resources */ + err = pci_request_selected_regions(pci_dev, bars, genwqe_driver_name); + if (err) { + dev_err(&pci_dev->dev, + "[%s] err: request bars failed (%d)\n", __func__, err); + err = -EIO; + goto err_disable_device; + } + + /* check for 64-bit DMA address supported (DAC) */ + if (!pci_set_dma_mask(pci_dev, DMA_BIT_MASK(64))) { + err = pci_set_consistent_dma_mask(pci_dev, DMA_BIT_MASK(64)); + if (err) { + dev_err(&pci_dev->dev, + "err: DMA64 consistent mask error\n"); + err = -EIO; + goto out_release_resources; + } + /* check for 32-bit DMA address supported (SAC) */ + } else if (!pci_set_dma_mask(pci_dev, DMA_BIT_MASK(32))) { + err = pci_set_consistent_dma_mask(pci_dev, DMA_BIT_MASK(32)); + if (err) { + dev_err(&pci_dev->dev, + "err: DMA32 consistent mask error\n"); + err = -EIO; + goto out_release_resources; + } + } else { + dev_err(&pci_dev->dev, + "err: neither DMA32 nor DMA64 supported\n"); + err = -EIO; + goto out_release_resources; + } + + pci_set_master(pci_dev); + pci_enable_pcie_error_reporting(pci_dev); + + /* request complete BAR-0 space (length = 0) */ + cd->mmio_len = pci_resource_len(pci_dev, 0); + cd->mmio = pci_iomap(pci_dev, 0, 0); + if (cd->mmio == NULL) { + dev_err(&pci_dev->dev, + "[%s] err: mapping BAR0 failed\n", __func__); + err = -ENOMEM; + goto out_release_resources; + } + + cd->num_vfs = pci_sriov_get_totalvfs(pci_dev); + + err = genwqe_read_ids(cd); + if (err) + goto out_iounmap; + + return 0; + + out_iounmap: + pci_iounmap(pci_dev, cd->mmio); + out_release_resources: + pci_release_selected_regions(pci_dev, bars); + err_disable_device: + pci_disable_device(pci_dev); + err_out: + return err; +} + +/** + * genwqe_pci_remove() - Free PCIe related resources for our card + */ +static void genwqe_pci_remove(struct genwqe_dev *cd) +{ + int bars; + struct pci_dev *pci_dev = cd->pci_dev; + + if (cd->mmio) + pci_iounmap(pci_dev, cd->mmio); + + bars = pci_select_bars(pci_dev, IORESOURCE_MEM); + pci_release_selected_regions(pci_dev, bars); + pci_disable_device(pci_dev); +} + +/** + * genwqe_probe() - Device initialization + * @pdev: PCI device information struct + * + * Callable for multiple cards. This function is called on bind. + * + * Return: 0 if succeeded, < 0 when failed + */ +static int genwqe_probe(struct pci_dev *pci_dev, + const struct pci_device_id *id) +{ + int err; + struct genwqe_dev *cd; + + genwqe_init_crc32(); + + cd = genwqe_dev_alloc(); + if (IS_ERR(cd)) { + dev_err(&pci_dev->dev, "err: could not alloc mem (err=%d)!\n", + (int)PTR_ERR(cd)); + return PTR_ERR(cd); + } + + dev_set_drvdata(&pci_dev->dev, cd); + cd->pci_dev = pci_dev; + + err = genwqe_pci_setup(cd); + if (err < 0) { + dev_err(&pci_dev->dev, + "err: problems with PCI setup (err=%d)\n", err); + goto out_free_dev; + } + + err = genwqe_start(cd); + if (err < 0) { + dev_err(&pci_dev->dev, + "err: cannot start card services! (err=%d)\n", err); + goto out_pci_remove; + } + + if (genwqe_is_privileged(cd)) { + err = genwqe_health_check_start(cd); + if (err < 0) { + dev_err(&pci_dev->dev, + "err: cannot start health checking! " + "(err=%d)\n", err); + goto out_stop_services; + } + } + return 0; + + out_stop_services: + genwqe_stop(cd); + out_pci_remove: + genwqe_pci_remove(cd); + out_free_dev: + genwqe_dev_free(cd); + return err; +} + +/** + * genwqe_remove() - Called when device is removed (hot-plugable) + * + * Or when driver is unloaded respecitively when unbind is done. + */ +static void genwqe_remove(struct pci_dev *pci_dev) +{ + struct genwqe_dev *cd = dev_get_drvdata(&pci_dev->dev); + + genwqe_health_check_stop(cd); + + /* + * genwqe_stop() must survive if it is called twice + * sequentially. This happens when the health thread calls it + * and fails on genwqe_bus_reset(). + */ + genwqe_stop(cd); + genwqe_pci_remove(cd); + genwqe_dev_free(cd); +} + +/* + * genwqe_err_error_detected() - Error detection callback + * + * This callback is called by the PCI subsystem whenever a PCI bus + * error is detected. + */ +static pci_ers_result_t genwqe_err_error_detected(struct pci_dev *pci_dev, + enum pci_channel_state state) +{ + struct genwqe_dev *cd; + + dev_err(&pci_dev->dev, "[%s] state=%d\n", __func__, state); + + if (pci_dev == NULL) + return PCI_ERS_RESULT_NEED_RESET; + + cd = dev_get_drvdata(&pci_dev->dev); + if (cd == NULL) + return PCI_ERS_RESULT_NEED_RESET; + + switch (state) { + case pci_channel_io_normal: + return PCI_ERS_RESULT_CAN_RECOVER; + case pci_channel_io_frozen: + return PCI_ERS_RESULT_NEED_RESET; + case pci_channel_io_perm_failure: + return PCI_ERS_RESULT_DISCONNECT; + } + + return PCI_ERS_RESULT_NEED_RESET; +} + +static pci_ers_result_t genwqe_err_result_none(struct pci_dev *dev) +{ + return PCI_ERS_RESULT_NONE; +} + +static void genwqe_err_resume(struct pci_dev *dev) +{ +} + +static int genwqe_sriov_configure(struct pci_dev *dev, int numvfs) +{ + struct genwqe_dev *cd = dev_get_drvdata(&dev->dev); + + if (numvfs > 0) { + genwqe_setup_vf_jtimer(cd); + pci_enable_sriov(dev, numvfs); + return numvfs; + } + if (numvfs == 0) { + pci_disable_sriov(dev); + return 0; + } + return 0; +} + +static struct pci_error_handlers genwqe_err_handler = { + .error_detected = genwqe_err_error_detected, + .mmio_enabled = genwqe_err_result_none, + .link_reset = genwqe_err_result_none, + .slot_reset = genwqe_err_result_none, + .resume = genwqe_err_resume, +}; + +static struct pci_driver genwqe_driver = { + .name = genwqe_driver_name, + .id_table = genwqe_device_table, + .probe = genwqe_probe, + .remove = genwqe_remove, + .sriov_configure = genwqe_sriov_configure, + .err_handler = &genwqe_err_handler, +}; + +/** + * genwqe_init_module() - Driver registration and initialization + */ +static int __init genwqe_init_module(void) +{ + int rc; + + class_genwqe = class_create(THIS_MODULE, GENWQE_DEVNAME); + if (IS_ERR(class_genwqe)) { + pr_err("[%s] create class failed\n", __func__); + return -ENOMEM; + } + + debugfs_genwqe = debugfs_create_dir(GENWQE_DEVNAME, NULL); + if (!debugfs_genwqe) { + rc = -ENOMEM; + goto err_out; + } + + rc = pci_register_driver(&genwqe_driver); + if (rc != 0) { + pr_err("[%s] pci_reg_driver (rc=%d)\n", __func__, rc); + goto err_out0; + } + + return rc; + + err_out0: + debugfs_remove(debugfs_genwqe); + err_out: + class_destroy(class_genwqe); + return rc; +} + +/** + * genwqe_exit_module() - Driver exit + */ +static void __exit genwqe_exit_module(void) +{ + pci_unregister_driver(&genwqe_driver); + debugfs_remove(debugfs_genwqe); + class_destroy(class_genwqe); +} + +module_init(genwqe_init_module); +module_exit(genwqe_exit_module); diff --git a/drivers/misc/genwqe/card_base.h b/drivers/misc/genwqe/card_base.h new file mode 100644 index 000000000000..5e4dbd21f89a --- /dev/null +++ b/drivers/misc/genwqe/card_base.h @@ -0,0 +1,557 @@ +#ifndef __CARD_BASE_H__ +#define __CARD_BASE_H__ + +/** + * IBM Accelerator Family 'GenWQE' + * + * (C) Copyright IBM Corp. 2013 + * + * Author: Frank Haverkamp <haver@linux.vnet.ibm.com> + * Author: Joerg-Stephan Vogt <jsvogt@de.ibm.com> + * Author: Michael Jung <mijung@de.ibm.com> + * Author: Michael Ruettger <michael@ibmra.de> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +/* + * Interfaces within the GenWQE module. Defines genwqe_card and + * ddcb_queue as well as ddcb_requ. + */ + +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/cdev.h> +#include <linux/stringify.h> +#include <linux/pci.h> +#include <linux/semaphore.h> +#include <linux/uaccess.h> +#include <linux/io.h> +#include <linux/version.h> +#include <linux/debugfs.h> +#include <linux/slab.h> + +#include <linux/genwqe/genwqe_card.h> +#include "genwqe_driver.h" + +#define GENWQE_MSI_IRQS 4 /* Just one supported, no MSIx */ +#define GENWQE_FLAG_MSI_ENABLED (1 << 0) + +#define GENWQE_MAX_VFS 15 /* maximum 15 VFs are possible */ +#define GENWQE_MAX_FUNCS 16 /* 1 PF and 15 VFs */ +#define GENWQE_CARD_NO_MAX (16 * GENWQE_MAX_FUNCS) + +/* Compile parameters, some of them appear in debugfs for later adjustment */ +#define genwqe_ddcb_max 32 /* DDCBs on the work-queue */ +#define genwqe_polling_enabled 0 /* in case of irqs not working */ +#define genwqe_ddcb_software_timeout 10 /* timeout per DDCB in seconds */ +#define genwqe_kill_timeout 8 /* time until process gets killed */ +#define genwqe_vf_jobtimeout_msec 250 /* 250 msec */ +#define genwqe_pf_jobtimeout_msec 8000 /* 8 sec should be ok */ +#define genwqe_health_check_interval 4 /* <= 0: disabled */ + +/* Sysfs attribute groups used when we create the genwqe device */ +extern const struct attribute_group *genwqe_attribute_groups[]; + +/* + * Config space for Genwqe5 A7: + * 00:[14 10 4b 04]40 00 10 00[00 00 00 12]00 00 00 00 + * 10: 0c 00 00 f0 07 3c 00 00 00 00 00 00 00 00 00 00 + * 20: 00 00 00 00 00 00 00 00 00 00 00 00[14 10 4b 04] + * 30: 00 00 00 00 50 00 00 00 00 00 00 00 00 00 00 00 + */ +#define PCI_DEVICE_GENWQE 0x044b /* Genwqe DeviceID */ + +#define PCI_SUBSYSTEM_ID_GENWQE5 0x035f /* Genwqe A5 Subsystem-ID */ +#define PCI_SUBSYSTEM_ID_GENWQE5_NEW 0x044b /* Genwqe A5 Subsystem-ID */ +#define PCI_CLASSCODE_GENWQE5 0x1200 /* UNKNOWN */ + +#define PCI_SUBVENDOR_ID_IBM_SRIOV 0x0000 +#define PCI_SUBSYSTEM_ID_GENWQE5_SRIOV 0x0000 /* Genwqe A5 Subsystem-ID */ +#define PCI_CLASSCODE_GENWQE5_SRIOV 0x1200 /* UNKNOWN */ + +#define GENWQE_SLU_ARCH_REQ 2 /* Required SLU architecture level */ + +/** + * struct genwqe_reg - Genwqe data dump functionality + */ +struct genwqe_reg { + u32 addr; + u32 idx; + u64 val; +}; + +/* + * enum genwqe_dbg_type - Specify chip unit to dump/debug + */ +enum genwqe_dbg_type { + GENWQE_DBG_UNIT0 = 0, /* captured before prev errs cleared */ + GENWQE_DBG_UNIT1 = 1, + GENWQE_DBG_UNIT2 = 2, + GENWQE_DBG_UNIT3 = 3, + GENWQE_DBG_UNIT4 = 4, + GENWQE_DBG_UNIT5 = 5, + GENWQE_DBG_UNIT6 = 6, + GENWQE_DBG_UNIT7 = 7, + GENWQE_DBG_REGS = 8, + GENWQE_DBG_DMA = 9, + GENWQE_DBG_UNITS = 10, /* max number of possible debug units */ +}; + +/* Software error injection to simulate card failures */ +#define GENWQE_INJECT_HARDWARE_FAILURE 0x00000001 /* injects -1 reg reads */ +#define GENWQE_INJECT_BUS_RESET_FAILURE 0x00000002 /* pci_bus_reset fail */ +#define GENWQE_INJECT_GFIR_FATAL 0x00000004 /* GFIR = 0x0000ffff */ +#define GENWQE_INJECT_GFIR_INFO 0x00000008 /* GFIR = 0xffff0000 */ + +/* + * Genwqe card description and management data. + * + * Error-handling in case of card malfunction + * ------------------------------------------ + * + * If the card is detected to be defective the outside environment + * will cause the PCI layer to call deinit (the cleanup function for + * probe). This is the same effect like doing a unbind/bind operation + * on the card. + * + * The genwqe card driver implements a health checking thread which + * verifies the card function. If this detects a problem the cards + * device is being shutdown and restarted again, along with a reset of + * the card and queue. + * + * All functions accessing the card device return either -EIO or -ENODEV + * code to indicate the malfunction to the user. The user has to close + * the file descriptor and open a new one, once the card becomes + * available again. + * + * If the open file descriptor is setup to receive SIGIO, the signal is + * genereated for the application which has to provide a handler to + * react on it. If the application does not close the open + * file descriptor a SIGKILL is send to enforce freeing the cards + * resources. + * + * I did not find a different way to prevent kernel problems due to + * reference counters for the cards character devices getting out of + * sync. The character device deallocation does not block, even if + * there is still an open file descriptor pending. If this pending + * descriptor is closed, the data structures used by the character + * device is reinstantiated, which will lead to the reference counter + * dropping below the allowed values. + * + * Card recovery + * ------------- + * + * To test the internal driver recovery the following command can be used: + * sudo sh -c 'echo 0xfffff > /sys/class/genwqe/genwqe0_card/err_inject' + */ + + +/** + * struct dma_mapping_type - Mapping type definition + * + * To avoid memcpying data arround we use user memory directly. To do + * this we need to pin/swap-in the memory and request a DMA address + * for it. + */ +enum dma_mapping_type { + GENWQE_MAPPING_RAW = 0, /* contignous memory buffer */ + GENWQE_MAPPING_SGL_TEMP, /* sglist dynamically used */ + GENWQE_MAPPING_SGL_PINNED, /* sglist used with pinning */ +}; + +/** + * struct dma_mapping - Information about memory mappings done by the driver + */ +struct dma_mapping { + enum dma_mapping_type type; + + void *u_vaddr; /* user-space vaddr/non-aligned */ + void *k_vaddr; /* kernel-space vaddr/non-aligned */ + dma_addr_t dma_addr; /* physical DMA address */ + + struct page **page_list; /* list of pages used by user buff */ + dma_addr_t *dma_list; /* list of dma addresses per page */ + unsigned int nr_pages; /* number of pages */ + unsigned int size; /* size in bytes */ + + struct list_head card_list; /* list of usr_maps for card */ + struct list_head pin_list; /* list of pinned memory for dev */ +}; + +static inline void genwqe_mapping_init(struct dma_mapping *m, + enum dma_mapping_type type) +{ + memset(m, 0, sizeof(*m)); + m->type = type; +} + +/** + * struct ddcb_queue - DDCB queue data + * @ddcb_max: Number of DDCBs on the queue + * @ddcb_next: Next free DDCB + * @ddcb_act: Next DDCB supposed to finish + * @ddcb_seq: Sequence number of last DDCB + * @ddcbs_in_flight: Currently enqueued DDCBs + * @ddcbs_completed: Number of already completed DDCBs + * @busy: Number of -EBUSY returns + * @ddcb_daddr: DMA address of first DDCB in the queue + * @ddcb_vaddr: Kernel virtual address of first DDCB in the queue + * @ddcb_req: Associated requests (one per DDCB) + * @ddcb_waitqs: Associated wait queues (one per DDCB) + * @ddcb_lock: Lock to protect queuing operations + * @ddcb_waitq: Wait on next DDCB finishing + */ + +struct ddcb_queue { + int ddcb_max; /* amount of DDCBs */ + int ddcb_next; /* next available DDCB num */ + int ddcb_act; /* DDCB to be processed */ + u16 ddcb_seq; /* slc seq num */ + unsigned int ddcbs_in_flight; /* number of ddcbs in processing */ + unsigned int ddcbs_completed; + unsigned int ddcbs_max_in_flight; + unsigned int busy; /* how many times -EBUSY? */ + + dma_addr_t ddcb_daddr; /* DMA address */ + struct ddcb *ddcb_vaddr; /* kernel virtual addr for DDCBs */ + struct ddcb_requ **ddcb_req; /* ddcb processing parameter */ + wait_queue_head_t *ddcb_waitqs; /* waitqueue per ddcb */ + + spinlock_t ddcb_lock; /* exclusive access to queue */ + wait_queue_head_t ddcb_waitq; /* wait for ddcb processing */ + + /* registers or the respective queue to be used */ + u32 IO_QUEUE_CONFIG; + u32 IO_QUEUE_STATUS; + u32 IO_QUEUE_SEGMENT; + u32 IO_QUEUE_INITSQN; + u32 IO_QUEUE_WRAP; + u32 IO_QUEUE_OFFSET; + u32 IO_QUEUE_WTIME; + u32 IO_QUEUE_ERRCNTS; + u32 IO_QUEUE_LRW; +}; + +/* + * GFIR, SLU_UNITCFG, APP_UNITCFG + * 8 Units with FIR/FEC + 64 * 2ndary FIRS/FEC. + */ +#define GENWQE_FFDC_REGS (3 + (8 * (2 + 2 * 64))) + +struct genwqe_ffdc { + unsigned int entries; + struct genwqe_reg *regs; +}; + +/** + * struct genwqe_dev - GenWQE device information + * @card_state: Card operation state, see above + * @ffdc: First Failure Data Capture buffers for each unit + * @card_thread: Working thread to operate the DDCB queue + * @card_waitq: Wait queue used in card_thread + * @queue: DDCB queue + * @health_thread: Card monitoring thread (only for PFs) + * @health_waitq: Wait queue used in health_thread + * @pci_dev: Associated PCI device (function) + * @mmio: Base address of 64-bit register space + * @mmio_len: Length of register area + * @file_lock: Lock to protect access to file_list + * @file_list: List of all processes with open GenWQE file descriptors + * + * This struct contains all information needed to communicate with a + * GenWQE card. It is initialized when a GenWQE device is found and + * destroyed when it goes away. It holds data to maintain the queue as + * well as data needed to feed the user interfaces. + */ +struct genwqe_dev { + enum genwqe_card_state card_state; + spinlock_t print_lock; + + int card_idx; /* card index 0..CARD_NO_MAX-1 */ + u64 flags; /* general flags */ + + /* FFDC data gathering */ + struct genwqe_ffdc ffdc[GENWQE_DBG_UNITS]; + + /* DDCB workqueue */ + struct task_struct *card_thread; + wait_queue_head_t queue_waitq; + struct ddcb_queue queue; /* genwqe DDCB queue */ + unsigned int irqs_processed; + + /* Card health checking thread */ + struct task_struct *health_thread; + wait_queue_head_t health_waitq; + + /* char device */ + dev_t devnum_genwqe; /* major/minor num card */ + struct class *class_genwqe; /* reference to class object */ + struct device *dev; /* for device creation */ + struct cdev cdev_genwqe; /* char device for card */ + + struct dentry *debugfs_root; /* debugfs card root directory */ + struct dentry *debugfs_genwqe; /* debugfs driver root directory */ + + /* pci resources */ + struct pci_dev *pci_dev; /* PCI device */ + void __iomem *mmio; /* BAR-0 MMIO start */ + unsigned long mmio_len; + u16 num_vfs; + u32 vf_jobtimeout_msec[GENWQE_MAX_VFS]; + int is_privileged; /* access to all regs possible */ + + /* config regs which we need often */ + u64 slu_unitcfg; + u64 app_unitcfg; + u64 softreset; + u64 err_inject; + u64 last_gfir; + char app_name[5]; + + spinlock_t file_lock; /* lock for open files */ + struct list_head file_list; /* list of open files */ + + /* debugfs parameters */ + int ddcb_software_timeout; /* wait until DDCB times out */ + int skip_recovery; /* circumvention if recovery fails */ + int kill_timeout; /* wait after sending SIGKILL */ +}; + +/** + * enum genwqe_requ_state - State of a DDCB execution request + */ +enum genwqe_requ_state { + GENWQE_REQU_NEW = 0, + GENWQE_REQU_ENQUEUED = 1, + GENWQE_REQU_TAPPED = 2, + GENWQE_REQU_FINISHED = 3, + GENWQE_REQU_STATE_MAX, +}; + +/** + * struct ddcb_requ - Kernel internal representation of the DDCB request + * @cmd: User space representation of the DDCB execution request + */ +struct ddcb_requ { + /* kernel specific content */ + enum genwqe_requ_state req_state; /* request status */ + int num; /* ddcb_no for this request */ + struct ddcb_queue *queue; /* associated queue */ + + struct dma_mapping dma_mappings[DDCB_FIXUPS]; + struct sg_entry *sgl[DDCB_FIXUPS]; + dma_addr_t sgl_dma_addr[DDCB_FIXUPS]; + size_t sgl_size[DDCB_FIXUPS]; + + /* kernel/user shared content */ + struct genwqe_ddcb_cmd cmd; /* ddcb_no for this request */ + struct genwqe_debug_data debug_data; +}; + +/** + * struct genwqe_file - Information for open GenWQE devices + */ +struct genwqe_file { + struct genwqe_dev *cd; + struct genwqe_driver *client; + struct file *filp; + + struct fasync_struct *async_queue; + struct task_struct *owner; + struct list_head list; /* entry in list of open files */ + + spinlock_t map_lock; /* lock for dma_mappings */ + struct list_head map_list; /* list of dma_mappings */ + + spinlock_t pin_lock; /* lock for pinned memory */ + struct list_head pin_list; /* list of pinned memory */ +}; + +int genwqe_setup_service_layer(struct genwqe_dev *cd); /* for PF only */ +int genwqe_finish_queue(struct genwqe_dev *cd); +int genwqe_release_service_layer(struct genwqe_dev *cd); + +/** + * genwqe_get_slu_id() - Read Service Layer Unit Id + * Return: 0x00: Development code + * 0x01: SLC1 (old) + * 0x02: SLC2 (sept2012) + * 0x03: SLC2 (feb2013, generic driver) + */ +static inline int genwqe_get_slu_id(struct genwqe_dev *cd) +{ + return (int)((cd->slu_unitcfg >> 32) & 0xff); +} + +int genwqe_ddcbs_in_flight(struct genwqe_dev *cd); + +u8 genwqe_card_type(struct genwqe_dev *cd); +int genwqe_card_reset(struct genwqe_dev *cd); +int genwqe_set_interrupt_capability(struct genwqe_dev *cd, int count); +void genwqe_reset_interrupt_capability(struct genwqe_dev *cd); + +int genwqe_device_create(struct genwqe_dev *cd); +int genwqe_device_remove(struct genwqe_dev *cd); + +/* debugfs */ +int genwqe_init_debugfs(struct genwqe_dev *cd); +void genqwe_exit_debugfs(struct genwqe_dev *cd); + +int genwqe_read_softreset(struct genwqe_dev *cd); + +/* Hardware Circumventions */ +int genwqe_recovery_on_fatal_gfir_required(struct genwqe_dev *cd); +int genwqe_flash_readback_fails(struct genwqe_dev *cd); + +/** + * genwqe_write_vreg() - Write register in VF window + * @cd: genwqe device + * @reg: register address + * @val: value to write + * @func: 0: PF, 1: VF0, ..., 15: VF14 + */ +int genwqe_write_vreg(struct genwqe_dev *cd, u32 reg, u64 val, int func); + +/** + * genwqe_read_vreg() - Read register in VF window + * @cd: genwqe device + * @reg: register address + * @func: 0: PF, 1: VF0, ..., 15: VF14 + * + * Return: content of the register + */ +u64 genwqe_read_vreg(struct genwqe_dev *cd, u32 reg, int func); + +/* FFDC Buffer Management */ +int genwqe_ffdc_buff_size(struct genwqe_dev *cd, int unit_id); +int genwqe_ffdc_buff_read(struct genwqe_dev *cd, int unit_id, + struct genwqe_reg *regs, unsigned int max_regs); +int genwqe_read_ffdc_regs(struct genwqe_dev *cd, struct genwqe_reg *regs, + unsigned int max_regs, int all); +int genwqe_ffdc_dump_dma(struct genwqe_dev *cd, + struct genwqe_reg *regs, unsigned int max_regs); + +int genwqe_init_debug_data(struct genwqe_dev *cd, + struct genwqe_debug_data *d); + +void genwqe_init_crc32(void); +int genwqe_read_app_id(struct genwqe_dev *cd, char *app_name, int len); + +/* Memory allocation/deallocation; dma address handling */ +int genwqe_user_vmap(struct genwqe_dev *cd, struct dma_mapping *m, + void *uaddr, unsigned long size, + struct ddcb_requ *req); + +int genwqe_user_vunmap(struct genwqe_dev *cd, struct dma_mapping *m, + struct ddcb_requ *req); + +struct sg_entry *genwqe_alloc_sgl(struct genwqe_dev *cd, int num_pages, + dma_addr_t *dma_addr, size_t *sgl_size); + +void genwqe_free_sgl(struct genwqe_dev *cd, struct sg_entry *sg_list, + dma_addr_t dma_addr, size_t size); + +int genwqe_setup_sgl(struct genwqe_dev *cd, + unsigned long offs, + unsigned long size, + struct sg_entry *sgl, /* genwqe sgl */ + dma_addr_t dma_addr, size_t sgl_size, + dma_addr_t *dma_list, int page_offs, int num_pages); + +int genwqe_check_sgl(struct genwqe_dev *cd, struct sg_entry *sg_list, + int size); + +static inline bool dma_mapping_used(struct dma_mapping *m) +{ + if (!m) + return 0; + return m->size != 0; +} + +/** + * __genwqe_execute_ddcb() - Execute DDCB request with addr translation + * + * This function will do the address translation changes to the DDCBs + * according to the definitions required by the ATS field. It looks up + * the memory allocation buffer or does vmap/vunmap for the respective + * user-space buffers, inclusive page pinning and scatter gather list + * buildup and teardown. + */ +int __genwqe_execute_ddcb(struct genwqe_dev *cd, + struct genwqe_ddcb_cmd *cmd); + +/** + * __genwqe_execute_raw_ddcb() - Execute DDCB request without addr translation + * + * This version will not do address translation or any modifcation of + * the DDCB data. It is used e.g. for the MoveFlash DDCB which is + * entirely prepared by the driver itself. That means the appropriate + * DMA addresses are already in the DDCB and do not need any + * modification. + */ +int __genwqe_execute_raw_ddcb(struct genwqe_dev *cd, + struct genwqe_ddcb_cmd *cmd); + +int __genwqe_enqueue_ddcb(struct genwqe_dev *cd, struct ddcb_requ *req); +int __genwqe_wait_ddcb(struct genwqe_dev *cd, struct ddcb_requ *req); +int __genwqe_purge_ddcb(struct genwqe_dev *cd, struct ddcb_requ *req); + +/* register access */ +int __genwqe_writeq(struct genwqe_dev *cd, u64 byte_offs, u64 val); +u64 __genwqe_readq(struct genwqe_dev *cd, u64 byte_offs); +int __genwqe_writel(struct genwqe_dev *cd, u64 byte_offs, u32 val); +u32 __genwqe_readl(struct genwqe_dev *cd, u64 byte_offs); + +void *__genwqe_alloc_consistent(struct genwqe_dev *cd, size_t size, + dma_addr_t *dma_handle); +void __genwqe_free_consistent(struct genwqe_dev *cd, size_t size, + void *vaddr, dma_addr_t dma_handle); + +/* Base clock frequency in MHz */ +int genwqe_base_clock_frequency(struct genwqe_dev *cd); + +/* Before FFDC is captured the traps should be stopped. */ +void genwqe_stop_traps(struct genwqe_dev *cd); +void genwqe_start_traps(struct genwqe_dev *cd); + +/* Hardware circumvention */ +bool genwqe_need_err_masking(struct genwqe_dev *cd); + +/** + * genwqe_is_privileged() - Determine operation mode for PCI function + * + * On Intel with SRIOV support we see: + * PF: is_physfn = 1 is_virtfn = 0 + * VF: is_physfn = 0 is_virtfn = 1 + * + * On Systems with no SRIOV support _and_ virtualized systems we get: + * is_physfn = 0 is_virtfn = 0 + * + * Other vendors have individual pci device ids to distinguish between + * virtual function drivers and physical function drivers. GenWQE + * unfortunately has just on pci device id for both, VFs and PF. + * + * The following code is used to distinguish if the card is running in + * privileged mode, either as true PF or in a virtualized system with + * full register access e.g. currently on PowerPC. + * + * if (pci_dev->is_virtfn) + * cd->is_privileged = 0; + * else + * cd->is_privileged = (__genwqe_readq(cd, IO_SLU_BITSTREAM) + * != IO_ILLEGAL_VALUE); + */ +static inline int genwqe_is_privileged(struct genwqe_dev *cd) +{ + return cd->is_privileged; +} + +#endif /* __CARD_BASE_H__ */ diff --git a/drivers/misc/genwqe/card_ddcb.c b/drivers/misc/genwqe/card_ddcb.c new file mode 100644 index 000000000000..6f1acc0ccf88 --- /dev/null +++ b/drivers/misc/genwqe/card_ddcb.c @@ -0,0 +1,1376 @@ +/** + * IBM Accelerator Family 'GenWQE' + * + * (C) Copyright IBM Corp. 2013 + * + * Author: Frank Haverkamp <haver@linux.vnet.ibm.com> + * Author: Joerg-Stephan Vogt <jsvogt@de.ibm.com> + * Author: Michael Jung <mijung@de.ibm.com> + * Author: Michael Ruettger <michael@ibmra.de> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +/* + * Device Driver Control Block (DDCB) queue support. Definition of + * interrupt handlers for queue support as well as triggering the + * health monitor code in case of problems. The current hardware uses + * an MSI interrupt which is shared between error handling and + * functional code. + */ + +#include <linux/types.h> +#include <linux/module.h> +#include <linux/sched.h> +#include <linux/wait.h> +#include <linux/pci.h> +#include <linux/string.h> +#include <linux/dma-mapping.h> +#include <linux/delay.h> +#include <linux/module.h> +#include <linux/interrupt.h> +#include <linux/crc-itu-t.h> + +#include "card_base.h" +#include "card_ddcb.h" + +/* + * N: next DDCB, this is where the next DDCB will be put. + * A: active DDCB, this is where the code will look for the next completion. + * x: DDCB is enqueued, we are waiting for its completion. + + * Situation (1): Empty queue + * +---+---+---+---+---+---+---+---+ + * | 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | + * | | | | | | | | | + * +---+---+---+---+---+---+---+---+ + * A/N + * enqueued_ddcbs = A - N = 2 - 2 = 0 + * + * Situation (2): Wrapped, N > A + * +---+---+---+---+---+---+---+---+ + * | 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | + * | | | x | x | | | | | + * +---+---+---+---+---+---+---+---+ + * A N + * enqueued_ddcbs = N - A = 4 - 2 = 2 + * + * Situation (3): Queue wrapped, A > N + * +---+---+---+---+---+---+---+---+ + * | 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | + * | x | x | | | x | x | x | x | + * +---+---+---+---+---+---+---+---+ + * N A + * enqueued_ddcbs = queue_max - (A - N) = 8 - (4 - 2) = 6 + * + * Situation (4a): Queue full N > A + * +---+---+---+---+---+---+---+---+ + * | 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | + * | x | x | x | x | x | x | x | | + * +---+---+---+---+---+---+---+---+ + * A N + * + * enqueued_ddcbs = N - A = 7 - 0 = 7 + * + * Situation (4a): Queue full A > N + * +---+---+---+---+---+---+---+---+ + * | 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | + * | x | x | x | | x | x | x | x | + * +---+---+---+---+---+---+---+---+ + * N A + * enqueued_ddcbs = queue_max - (A - N) = 8 - (4 - 3) = 7 + */ + +static int queue_empty(struct ddcb_queue *queue) +{ + return queue->ddcb_next == queue->ddcb_act; +} + +static int queue_enqueued_ddcbs(struct ddcb_queue *queue) +{ + if (queue->ddcb_next >= queue->ddcb_act) + return queue->ddcb_next - queue->ddcb_act; + + return queue->ddcb_max - (queue->ddcb_act - queue->ddcb_next); +} + +static int queue_free_ddcbs(struct ddcb_queue *queue) +{ + int free_ddcbs = queue->ddcb_max - queue_enqueued_ddcbs(queue) - 1; + + if (WARN_ON_ONCE(free_ddcbs < 0)) { /* must never ever happen! */ + return 0; + } + return free_ddcbs; +} + +/* + * Use of the PRIV field in the DDCB for queue debugging: + * + * (1) Trying to get rid of a DDCB which saw a timeout: + * pddcb->priv[6] = 0xcc; # cleared + * + * (2) Append a DDCB via NEXT bit: + * pddcb->priv[7] = 0xaa; # appended + * + * (3) DDCB needed tapping: + * pddcb->priv[7] = 0xbb; # tapped + * + * (4) DDCB marked as correctly finished: + * pddcb->priv[6] = 0xff; # finished + */ + +static inline void ddcb_mark_tapped(struct ddcb *pddcb) +{ + pddcb->priv[7] = 0xbb; /* tapped */ +} + +static inline void ddcb_mark_appended(struct ddcb *pddcb) +{ + pddcb->priv[7] = 0xaa; /* appended */ +} + +static inline void ddcb_mark_cleared(struct ddcb *pddcb) +{ + pddcb->priv[6] = 0xcc; /* cleared */ +} + +static inline void ddcb_mark_finished(struct ddcb *pddcb) +{ + pddcb->priv[6] = 0xff; /* finished */ +} + +static inline void ddcb_mark_unused(struct ddcb *pddcb) +{ + pddcb->priv_64 = cpu_to_be64(0); /* not tapped */ +} + +/** + * genwqe_crc16() - Generate 16-bit crc as required for DDCBs + * @buff: pointer to data buffer + * @len: length of data for calculation + * @init: initial crc (0xffff at start) + * + * Polynomial = x^16 + x^12 + x^5 + 1 (0x1021) + * Example: 4 bytes 0x01 0x02 0x03 0x04 with init = 0xffff + * should result in a crc16 of 0x89c3 + * + * Return: crc16 checksum in big endian format ! + */ +static inline u16 genwqe_crc16(const u8 *buff, size_t len, u16 init) +{ + return crc_itu_t(init, buff, len); +} + +static void print_ddcb_info(struct genwqe_dev *cd, struct ddcb_queue *queue) +{ + int i; + struct ddcb *pddcb; + unsigned long flags; + struct pci_dev *pci_dev = cd->pci_dev; + + spin_lock_irqsave(&cd->print_lock, flags); + + dev_info(&pci_dev->dev, + "DDCB list for card #%d (ddcb_act=%d / ddcb_next=%d):\n", + cd->card_idx, queue->ddcb_act, queue->ddcb_next); + + pddcb = queue->ddcb_vaddr; + for (i = 0; i < queue->ddcb_max; i++) { + dev_err(&pci_dev->dev, + " %c %-3d: RETC=%03x SEQ=%04x " + "HSI=%02X SHI=%02x PRIV=%06llx CMD=%03x\n", + i == queue->ddcb_act ? '>' : ' ', + i, + be16_to_cpu(pddcb->retc_16), + be16_to_cpu(pddcb->seqnum_16), + pddcb->hsi, + pddcb->shi, + be64_to_cpu(pddcb->priv_64), + pddcb->cmd); + pddcb++; + } + spin_unlock_irqrestore(&cd->print_lock, flags); +} + +struct genwqe_ddcb_cmd *ddcb_requ_alloc(void) +{ + struct ddcb_requ *req; + + req = kzalloc(sizeof(*req), GFP_ATOMIC); + if (!req) + return NULL; + + return &req->cmd; +} + +void ddcb_requ_free(struct genwqe_ddcb_cmd *cmd) +{ + struct ddcb_requ *req = container_of(cmd, struct ddcb_requ, cmd); + kfree(req); +} + +static inline enum genwqe_requ_state ddcb_requ_get_state(struct ddcb_requ *req) +{ + return req->req_state; +} + +static inline void ddcb_requ_set_state(struct ddcb_requ *req, + enum genwqe_requ_state new_state) +{ + req->req_state = new_state; +} + +static inline int ddcb_requ_collect_debug_data(struct ddcb_requ *req) +{ + return req->cmd.ddata_addr != 0x0; +} + +/** + * ddcb_requ_finished() - Returns the hardware state of the associated DDCB + * @cd: pointer to genwqe device descriptor + * @req: DDCB work request + * + * Status of ddcb_requ mirrors this hardware state, but is copied in + * the ddcb_requ on interrupt/polling function. The lowlevel code + * should check the hardware state directly, the higher level code + * should check the copy. + * + * This function will also return true if the state of the queue is + * not GENWQE_CARD_USED. This enables us to purge all DDCBs in the + * shutdown case. + */ +static int ddcb_requ_finished(struct genwqe_dev *cd, struct ddcb_requ *req) +{ + return (ddcb_requ_get_state(req) == GENWQE_REQU_FINISHED) || + (cd->card_state != GENWQE_CARD_USED); +} + +/** + * enqueue_ddcb() - Enqueue a DDCB + * @cd: pointer to genwqe device descriptor + * @queue: queue this operation should be done on + * @ddcb_no: pointer to ddcb number being tapped + * + * Start execution of DDCB by tapping or append to queue via NEXT + * bit. This is done by an atomic 'compare and swap' instruction and + * checking SHI and HSI of the previous DDCB. + * + * This function must only be called with ddcb_lock held. + * + * Return: 1 if new DDCB is appended to previous + * 2 if DDCB queue is tapped via register/simulation + */ +#define RET_DDCB_APPENDED 1 +#define RET_DDCB_TAPPED 2 + +static int enqueue_ddcb(struct genwqe_dev *cd, struct ddcb_queue *queue, + struct ddcb *pddcb, int ddcb_no) +{ + unsigned int try; + int prev_no; + struct ddcb *prev_ddcb; + __be32 old, new, icrc_hsi_shi; + u64 num; + + /* + * For performance checks a Dispatch Timestamp can be put into + * DDCB It is supposed to use the SLU's free running counter, + * but this requires PCIe cycles. + */ + ddcb_mark_unused(pddcb); + + /* check previous DDCB if already fetched */ + prev_no = (ddcb_no == 0) ? queue->ddcb_max - 1 : ddcb_no - 1; + prev_ddcb = &queue->ddcb_vaddr[prev_no]; + + /* + * It might have happened that the HSI.FETCHED bit is + * set. Retry in this case. Therefore I expect maximum 2 times + * trying. + */ + ddcb_mark_appended(pddcb); + for (try = 0; try < 2; try++) { + old = prev_ddcb->icrc_hsi_shi_32; /* read SHI/HSI in BE32 */ + + /* try to append via NEXT bit if prev DDCB is not completed */ + if ((old & DDCB_COMPLETED_BE32) != 0x00000000) + break; + + new = (old | DDCB_NEXT_BE32); + icrc_hsi_shi = cmpxchg(&prev_ddcb->icrc_hsi_shi_32, old, new); + + if (icrc_hsi_shi == old) + return RET_DDCB_APPENDED; /* appended to queue */ + } + + /* Queue must be re-started by updating QUEUE_OFFSET */ + ddcb_mark_tapped(pddcb); + num = (u64)ddcb_no << 8; + __genwqe_writeq(cd, queue->IO_QUEUE_OFFSET, num); /* start queue */ + + return RET_DDCB_TAPPED; +} + +/** + * copy_ddcb_results() - Copy output state from real DDCB to request + * + * Copy DDCB ASV to request struct. There is no endian + * conversion made, since data structure in ASV is still + * unknown here. + * + * This is needed by: + * - genwqe_purge_ddcb() + * - genwqe_check_ddcb_queue() + */ +static void copy_ddcb_results(struct ddcb_requ *req, int ddcb_no) +{ + struct ddcb_queue *queue = req->queue; + struct ddcb *pddcb = &queue->ddcb_vaddr[req->num]; + + memcpy(&req->cmd.asv[0], &pddcb->asv[0], DDCB_ASV_LENGTH); + + /* copy status flags of the variant part */ + req->cmd.vcrc = be16_to_cpu(pddcb->vcrc_16); + req->cmd.deque_ts = be64_to_cpu(pddcb->deque_ts_64); + req->cmd.cmplt_ts = be64_to_cpu(pddcb->cmplt_ts_64); + + req->cmd.attn = be16_to_cpu(pddcb->attn_16); + req->cmd.progress = be32_to_cpu(pddcb->progress_32); + req->cmd.retc = be16_to_cpu(pddcb->retc_16); + + if (ddcb_requ_collect_debug_data(req)) { + int prev_no = (ddcb_no == 0) ? + queue->ddcb_max - 1 : ddcb_no - 1; + struct ddcb *prev_pddcb = &queue->ddcb_vaddr[prev_no]; + + memcpy(&req->debug_data.ddcb_finished, pddcb, + sizeof(req->debug_data.ddcb_finished)); + memcpy(&req->debug_data.ddcb_prev, prev_pddcb, + sizeof(req->debug_data.ddcb_prev)); + } +} + +/** + * genwqe_check_ddcb_queue() - Checks DDCB queue for completed work equests. + * @cd: pointer to genwqe device descriptor + * + * Return: Number of DDCBs which were finished + */ +static int genwqe_check_ddcb_queue(struct genwqe_dev *cd, + struct ddcb_queue *queue) +{ + unsigned long flags; + int ddcbs_finished = 0; + struct pci_dev *pci_dev = cd->pci_dev; + + spin_lock_irqsave(&queue->ddcb_lock, flags); + + /* FIXME avoid soft locking CPU */ + while (!queue_empty(queue) && (ddcbs_finished < queue->ddcb_max)) { + + struct ddcb *pddcb; + struct ddcb_requ *req; + u16 vcrc, vcrc_16, retc_16; + + pddcb = &queue->ddcb_vaddr[queue->ddcb_act]; + + if ((pddcb->icrc_hsi_shi_32 & DDCB_COMPLETED_BE32) == + 0x00000000) + goto go_home; /* not completed, continue waiting */ + + /* Note: DDCB could be purged */ + + req = queue->ddcb_req[queue->ddcb_act]; + if (req == NULL) { + /* this occurs if DDCB is purged, not an error */ + /* Move active DDCB further; Nothing to do anymore. */ + goto pick_next_one; + } + + /* + * HSI=0x44 (fetched and completed), but RETC is + * 0x101, or even worse 0x000. + * + * In case of seeing the queue in inconsistent state + * we read the errcnts and the queue status to provide + * a trigger for our PCIe analyzer stop capturing. + */ + retc_16 = be16_to_cpu(pddcb->retc_16); + if ((pddcb->hsi == 0x44) && (retc_16 <= 0x101)) { + u64 errcnts, status; + u64 ddcb_offs = (u64)pddcb - (u64)queue->ddcb_vaddr; + + errcnts = __genwqe_readq(cd, queue->IO_QUEUE_ERRCNTS); + status = __genwqe_readq(cd, queue->IO_QUEUE_STATUS); + + dev_err(&pci_dev->dev, + "[%s] SEQN=%04x HSI=%02x RETC=%03x " + " Q_ERRCNTS=%016llx Q_STATUS=%016llx\n" + " DDCB_DMA_ADDR=%016llx\n", + __func__, be16_to_cpu(pddcb->seqnum_16), + pddcb->hsi, retc_16, errcnts, status, + queue->ddcb_daddr + ddcb_offs); + } + + copy_ddcb_results(req, queue->ddcb_act); + queue->ddcb_req[queue->ddcb_act] = NULL; /* take from queue */ + + dev_dbg(&pci_dev->dev, "FINISHED DDCB#%d\n", req->num); + genwqe_hexdump(pci_dev, pddcb, sizeof(*pddcb)); + + ddcb_mark_finished(pddcb); + + /* calculate CRC_16 to see if VCRC is correct */ + vcrc = genwqe_crc16(pddcb->asv, + VCRC_LENGTH(req->cmd.asv_length), + 0xffff); + vcrc_16 = be16_to_cpu(pddcb->vcrc_16); + if (vcrc != vcrc_16) { + printk_ratelimited(KERN_ERR + "%s %s: err: wrong VCRC pre=%02x vcrc_len=%d " + "bytes vcrc_data=%04x is not vcrc_card=%04x\n", + GENWQE_DEVNAME, dev_name(&pci_dev->dev), + pddcb->pre, VCRC_LENGTH(req->cmd.asv_length), + vcrc, vcrc_16); + } + + ddcb_requ_set_state(req, GENWQE_REQU_FINISHED); + queue->ddcbs_completed++; + queue->ddcbs_in_flight--; + + /* wake up process waiting for this DDCB */ + wake_up_interruptible(&queue->ddcb_waitqs[queue->ddcb_act]); + +pick_next_one: + queue->ddcb_act = (queue->ddcb_act + 1) % queue->ddcb_max; + ddcbs_finished++; + } + + go_home: + spin_unlock_irqrestore(&queue->ddcb_lock, flags); + return ddcbs_finished; +} + +/** + * __genwqe_wait_ddcb(): Waits until DDCB is completed + * @cd: pointer to genwqe device descriptor + * @req: pointer to requsted DDCB parameters + * + * The Service Layer will update the RETC in DDCB when processing is + * pending or done. + * + * Return: > 0 remaining jiffies, DDCB completed + * -ETIMEDOUT when timeout + * -ERESTARTSYS when ^C + * -EINVAL when unknown error condition + * + * When an error is returned the called needs to ensure that + * purge_ddcb() is being called to get the &req removed from the + * queue. + */ +int __genwqe_wait_ddcb(struct genwqe_dev *cd, struct ddcb_requ *req) +{ + int rc; + unsigned int ddcb_no; + struct ddcb_queue *queue; + struct pci_dev *pci_dev = cd->pci_dev; + + if (req == NULL) + return -EINVAL; + + queue = req->queue; + if (queue == NULL) + return -EINVAL; + + ddcb_no = req->num; + if (ddcb_no >= queue->ddcb_max) + return -EINVAL; + + rc = wait_event_interruptible_timeout(queue->ddcb_waitqs[ddcb_no], + ddcb_requ_finished(cd, req), + genwqe_ddcb_software_timeout * HZ); + + /* + * We need to distinguish 3 cases here: + * 1. rc == 0 timeout occured + * 2. rc == -ERESTARTSYS signal received + * 3. rc > 0 remaining jiffies condition is true + */ + if (rc == 0) { + struct ddcb_queue *queue = req->queue; + struct ddcb *pddcb; + + /* + * Timeout may be caused by long task switching time. + * When timeout happens, check if the request has + * meanwhile completed. + */ + genwqe_check_ddcb_queue(cd, req->queue); + if (ddcb_requ_finished(cd, req)) + return rc; + + dev_err(&pci_dev->dev, + "[%s] err: DDCB#%d timeout rc=%d state=%d req @ %p\n", + __func__, req->num, rc, ddcb_requ_get_state(req), + req); + dev_err(&pci_dev->dev, + "[%s] IO_QUEUE_STATUS=0x%016llx\n", __func__, + __genwqe_readq(cd, queue->IO_QUEUE_STATUS)); + + pddcb = &queue->ddcb_vaddr[req->num]; + genwqe_hexdump(pci_dev, pddcb, sizeof(*pddcb)); + + print_ddcb_info(cd, req->queue); + return -ETIMEDOUT; + + } else if (rc == -ERESTARTSYS) { + return rc; + /* + * EINTR: Stops the application + * ERESTARTSYS: Restartable systemcall; called again + */ + + } else if (rc < 0) { + dev_err(&pci_dev->dev, + "[%s] err: DDCB#%d unknown result (rc=%d) %d!\n", + __func__, req->num, rc, ddcb_requ_get_state(req)); + return -EINVAL; + } + + /* Severe error occured. Driver is forced to stop operation */ + if (cd->card_state != GENWQE_CARD_USED) { + dev_err(&pci_dev->dev, + "[%s] err: DDCB#%d forced to stop (rc=%d)\n", + __func__, req->num, rc); + return -EIO; + } + return rc; +} + +/** + * get_next_ddcb() - Get next available DDCB + * @cd: pointer to genwqe device descriptor + * + * DDCB's content is completely cleared but presets for PRE and + * SEQNUM. This function must only be called when ddcb_lock is held. + * + * Return: NULL if no empty DDCB available otherwise ptr to next DDCB. + */ +static struct ddcb *get_next_ddcb(struct genwqe_dev *cd, + struct ddcb_queue *queue, + int *num) +{ + u64 *pu64; + struct ddcb *pddcb; + + if (queue_free_ddcbs(queue) == 0) /* queue is full */ + return NULL; + + /* find new ddcb */ + pddcb = &queue->ddcb_vaddr[queue->ddcb_next]; + + /* if it is not completed, we are not allowed to use it */ + /* barrier(); */ + if ((pddcb->icrc_hsi_shi_32 & DDCB_COMPLETED_BE32) == 0x00000000) + return NULL; + + *num = queue->ddcb_next; /* internal DDCB number */ + queue->ddcb_next = (queue->ddcb_next + 1) % queue->ddcb_max; + + /* clear important DDCB fields */ + pu64 = (u64 *)pddcb; + pu64[0] = 0ULL; /* offs 0x00 (ICRC,HSI,SHI,...) */ + pu64[1] = 0ULL; /* offs 0x01 (ACFUNC,CMD...) */ + + /* destroy previous results in ASV */ + pu64[0x80/8] = 0ULL; /* offs 0x80 (ASV + 0) */ + pu64[0x88/8] = 0ULL; /* offs 0x88 (ASV + 0x08) */ + pu64[0x90/8] = 0ULL; /* offs 0x90 (ASV + 0x10) */ + pu64[0x98/8] = 0ULL; /* offs 0x98 (ASV + 0x18) */ + pu64[0xd0/8] = 0ULL; /* offs 0xd0 (RETC,ATTN...) */ + + pddcb->pre = DDCB_PRESET_PRE; /* 128 */ + pddcb->seqnum_16 = cpu_to_be16(queue->ddcb_seq++); + return pddcb; +} + +/** + * __genwqe_purge_ddcb() - Remove a DDCB from the workqueue + * @cd: genwqe device descriptor + * @req: DDCB request + * + * This will fail when the request was already FETCHED. In this case + * we need to wait until it is finished. Else the DDCB can be + * reused. This function also ensures that the request data structure + * is removed from ddcb_req[]. + * + * Do not forget to call this function when genwqe_wait_ddcb() fails, + * such that the request gets really removed from ddcb_req[]. + * + * Return: 0 success + */ +int __genwqe_purge_ddcb(struct genwqe_dev *cd, struct ddcb_requ *req) +{ + struct ddcb *pddcb = NULL; + unsigned int t; + unsigned long flags; + struct ddcb_queue *queue = req->queue; + struct pci_dev *pci_dev = cd->pci_dev; + u64 queue_status; + __be32 icrc_hsi_shi = 0x0000; + __be32 old, new; + + /* unsigned long flags; */ + if (genwqe_ddcb_software_timeout <= 0) { + dev_err(&pci_dev->dev, + "[%s] err: software timeout is not set!\n", __func__); + return -EFAULT; + } + + pddcb = &queue->ddcb_vaddr[req->num]; + + for (t = 0; t < genwqe_ddcb_software_timeout * 10; t++) { + + spin_lock_irqsave(&queue->ddcb_lock, flags); + + /* Check if req was meanwhile finished */ + if (ddcb_requ_get_state(req) == GENWQE_REQU_FINISHED) + goto go_home; + + /* try to set PURGE bit if FETCHED/COMPLETED are not set */ + old = pddcb->icrc_hsi_shi_32; /* read SHI/HSI in BE32 */ + if ((old & DDCB_FETCHED_BE32) == 0x00000000) { + + new = (old | DDCB_PURGE_BE32); + icrc_hsi_shi = cmpxchg(&pddcb->icrc_hsi_shi_32, + old, new); + if (icrc_hsi_shi == old) + goto finish_ddcb; + } + + /* normal finish with HSI bit */ + barrier(); + icrc_hsi_shi = pddcb->icrc_hsi_shi_32; + if (icrc_hsi_shi & DDCB_COMPLETED_BE32) + goto finish_ddcb; + + spin_unlock_irqrestore(&queue->ddcb_lock, flags); + + /* + * Here the check_ddcb() function will most likely + * discover this DDCB to be finished some point in + * time. It will mark the req finished and free it up + * in the list. + */ + + copy_ddcb_results(req, req->num); /* for the failing case */ + msleep(100); /* sleep for 1/10 second and try again */ + continue; + +finish_ddcb: + copy_ddcb_results(req, req->num); + ddcb_requ_set_state(req, GENWQE_REQU_FINISHED); + queue->ddcbs_in_flight--; + queue->ddcb_req[req->num] = NULL; /* delete from array */ + ddcb_mark_cleared(pddcb); + + /* Move active DDCB further; Nothing to do here anymore. */ + + /* + * We need to ensure that there is at least one free + * DDCB in the queue. To do that, we must update + * ddcb_act only if the COMPLETED bit is set for the + * DDCB we are working on else we treat that DDCB even + * if we PURGED it as occupied (hardware is supposed + * to set the COMPLETED bit yet!). + */ + icrc_hsi_shi = pddcb->icrc_hsi_shi_32; + if ((icrc_hsi_shi & DDCB_COMPLETED_BE32) && + (queue->ddcb_act == req->num)) { + queue->ddcb_act = ((queue->ddcb_act + 1) % + queue->ddcb_max); + } +go_home: + spin_unlock_irqrestore(&queue->ddcb_lock, flags); + return 0; + } + + /* + * If the card is dead and the queue is forced to stop, we + * might see this in the queue status register. + */ + queue_status = __genwqe_readq(cd, queue->IO_QUEUE_STATUS); + + dev_dbg(&pci_dev->dev, "UN/FINISHED DDCB#%d\n", req->num); + genwqe_hexdump(pci_dev, pddcb, sizeof(*pddcb)); + + dev_err(&pci_dev->dev, + "[%s] err: DDCB#%d not purged and not completed " + "after %d seconds QSTAT=%016llx!!\n", + __func__, req->num, genwqe_ddcb_software_timeout, + queue_status); + + print_ddcb_info(cd, req->queue); + + return -EFAULT; +} + +int genwqe_init_debug_data(struct genwqe_dev *cd, struct genwqe_debug_data *d) +{ + int len; + struct pci_dev *pci_dev = cd->pci_dev; + + if (d == NULL) { + dev_err(&pci_dev->dev, + "[%s] err: invalid memory for debug data!\n", + __func__); + return -EFAULT; + } + + len = sizeof(d->driver_version); + snprintf(d->driver_version, len, "%s", DRV_VERS_STRING); + d->slu_unitcfg = cd->slu_unitcfg; + d->app_unitcfg = cd->app_unitcfg; + return 0; +} + +/** + * __genwqe_enqueue_ddcb() - Enqueue a DDCB + * @cd: pointer to genwqe device descriptor + * @req: pointer to DDCB execution request + * + * Return: 0 if enqueuing succeeded + * -EIO if card is unusable/PCIe problems + * -EBUSY if enqueuing failed + */ +int __genwqe_enqueue_ddcb(struct genwqe_dev *cd, struct ddcb_requ *req) +{ + struct ddcb *pddcb; + unsigned long flags; + struct ddcb_queue *queue; + struct pci_dev *pci_dev = cd->pci_dev; + u16 icrc; + + if (cd->card_state != GENWQE_CARD_USED) { + printk_ratelimited(KERN_ERR + "%s %s: [%s] Card is unusable/PCIe problem Req#%d\n", + GENWQE_DEVNAME, dev_name(&pci_dev->dev), + __func__, req->num); + return -EIO; + } + + queue = req->queue = &cd->queue; + + /* FIXME circumvention to improve performance when no irq is + * there. + */ + if (genwqe_polling_enabled) + genwqe_check_ddcb_queue(cd, queue); + + /* + * It must be ensured to process all DDCBs in successive + * order. Use a lock here in order to prevent nested DDCB + * enqueuing. + */ + spin_lock_irqsave(&queue->ddcb_lock, flags); + + pddcb = get_next_ddcb(cd, queue, &req->num); /* get ptr and num */ + if (pddcb == NULL) { + spin_unlock_irqrestore(&queue->ddcb_lock, flags); + queue->busy++; + return -EBUSY; + } + + if (queue->ddcb_req[req->num] != NULL) { + spin_unlock_irqrestore(&queue->ddcb_lock, flags); + + dev_err(&pci_dev->dev, + "[%s] picked DDCB %d with req=%p still in use!!\n", + __func__, req->num, req); + return -EFAULT; + } + ddcb_requ_set_state(req, GENWQE_REQU_ENQUEUED); + queue->ddcb_req[req->num] = req; + + pddcb->cmdopts_16 = cpu_to_be16(req->cmd.cmdopts); + pddcb->cmd = req->cmd.cmd; + pddcb->acfunc = req->cmd.acfunc; /* functional unit */ + + /* + * We know that we can get retc 0x104 with CRC error, do not + * stop the queue in those cases for this command. XDIR = 1 + * does not work for old SLU versions. + * + * Last bitstream with the old XDIR behavior had SLU_ID + * 0x34199. + */ + if ((cd->slu_unitcfg & 0xFFFF0ull) > 0x34199ull) + pddcb->xdir = 0x1; + else + pddcb->xdir = 0x0; + + + pddcb->psp = (((req->cmd.asiv_length / 8) << 4) | + ((req->cmd.asv_length / 8))); + pddcb->disp_ts_64 = cpu_to_be64(req->cmd.disp_ts); + + /* + * If copying the whole DDCB_ASIV_LENGTH is impacting + * performance we need to change it to + * req->cmd.asiv_length. But simulation benefits from some + * non-architectured bits behind the architectured content. + * + * How much data is copied depends on the availability of the + * ATS field, which was introduced late. If the ATS field is + * supported ASIV is 8 bytes shorter than it used to be. Since + * the ATS field is copied too, the code should do exactly + * what it did before, but I wanted to make copying of the ATS + * field very explicit. + */ + if (genwqe_get_slu_id(cd) <= 0x2) { + memcpy(&pddcb->__asiv[0], /* destination */ + &req->cmd.__asiv[0], /* source */ + DDCB_ASIV_LENGTH); /* req->cmd.asiv_length */ + } else { + pddcb->n.ats_64 = cpu_to_be64(req->cmd.ats); + memcpy(&pddcb->n.asiv[0], /* destination */ + &req->cmd.asiv[0], /* source */ + DDCB_ASIV_LENGTH_ATS); /* req->cmd.asiv_length */ + } + + pddcb->icrc_hsi_shi_32 = cpu_to_be32(0x00000000); /* for crc */ + + /* + * Calculate CRC_16 for corresponding range PSP(7:4). Include + * empty 4 bytes prior to the data. + */ + icrc = genwqe_crc16((const u8 *)pddcb, + ICRC_LENGTH(req->cmd.asiv_length), 0xffff); + pddcb->icrc_hsi_shi_32 = cpu_to_be32((u32)icrc << 16); + + /* enable DDCB completion irq */ + if (!genwqe_polling_enabled) + pddcb->icrc_hsi_shi_32 |= DDCB_INTR_BE32; + + dev_dbg(&pci_dev->dev, "INPUT DDCB#%d\n", req->num); + genwqe_hexdump(pci_dev, pddcb, sizeof(*pddcb)); + + if (ddcb_requ_collect_debug_data(req)) { + /* use the kernel copy of debug data. copying back to + user buffer happens later */ + + genwqe_init_debug_data(cd, &req->debug_data); + memcpy(&req->debug_data.ddcb_before, pddcb, + sizeof(req->debug_data.ddcb_before)); + } + + enqueue_ddcb(cd, queue, pddcb, req->num); + queue->ddcbs_in_flight++; + + if (queue->ddcbs_in_flight > queue->ddcbs_max_in_flight) + queue->ddcbs_max_in_flight = queue->ddcbs_in_flight; + + ddcb_requ_set_state(req, GENWQE_REQU_TAPPED); + spin_unlock_irqrestore(&queue->ddcb_lock, flags); + wake_up_interruptible(&cd->queue_waitq); + + return 0; +} + +/** + * __genwqe_execute_raw_ddcb() - Setup and execute DDCB + * @cd: pointer to genwqe device descriptor + * @req: user provided DDCB request + */ +int __genwqe_execute_raw_ddcb(struct genwqe_dev *cd, + struct genwqe_ddcb_cmd *cmd) +{ + int rc = 0; + struct pci_dev *pci_dev = cd->pci_dev; + struct ddcb_requ *req = container_of(cmd, struct ddcb_requ, cmd); + + if (cmd->asiv_length > DDCB_ASIV_LENGTH) { + dev_err(&pci_dev->dev, "[%s] err: wrong asiv_length of %d\n", + __func__, cmd->asiv_length); + return -EINVAL; + } + if (cmd->asv_length > DDCB_ASV_LENGTH) { + dev_err(&pci_dev->dev, "[%s] err: wrong asv_length of %d\n", + __func__, cmd->asiv_length); + return -EINVAL; + } + rc = __genwqe_enqueue_ddcb(cd, req); + if (rc != 0) + return rc; + + rc = __genwqe_wait_ddcb(cd, req); + if (rc < 0) /* error or signal interrupt */ + goto err_exit; + + if (ddcb_requ_collect_debug_data(req)) { + if (copy_to_user((struct genwqe_debug_data __user *) + (unsigned long)cmd->ddata_addr, + &req->debug_data, + sizeof(struct genwqe_debug_data))) + return -EFAULT; + } + + /* + * Higher values than 0x102 indicate completion with faults, + * lower values than 0x102 indicate processing faults. Note + * that DDCB might have been purged. E.g. Cntl+C. + */ + if (cmd->retc != DDCB_RETC_COMPLETE) { + /* This might happen e.g. flash read, and needs to be + handled by the upper layer code. */ + rc = -EBADMSG; /* not processed/error retc */ + } + + return rc; + + err_exit: + __genwqe_purge_ddcb(cd, req); + + if (ddcb_requ_collect_debug_data(req)) { + if (copy_to_user((struct genwqe_debug_data __user *) + (unsigned long)cmd->ddata_addr, + &req->debug_data, + sizeof(struct genwqe_debug_data))) + return -EFAULT; + } + return rc; +} + +/** + * genwqe_next_ddcb_ready() - Figure out if the next DDCB is already finished + * + * We use this as condition for our wait-queue code. + */ +static int genwqe_next_ddcb_ready(struct genwqe_dev *cd) +{ + unsigned long flags; + struct ddcb *pddcb; + struct ddcb_queue *queue = &cd->queue; + + spin_lock_irqsave(&queue->ddcb_lock, flags); + + if (queue_empty(queue)) { /* emtpy queue */ + spin_unlock_irqrestore(&queue->ddcb_lock, flags); + return 0; + } + + pddcb = &queue->ddcb_vaddr[queue->ddcb_act]; + if (pddcb->icrc_hsi_shi_32 & DDCB_COMPLETED_BE32) { /* ddcb ready */ + spin_unlock_irqrestore(&queue->ddcb_lock, flags); + return 1; + } + + spin_unlock_irqrestore(&queue->ddcb_lock, flags); + return 0; +} + +/** + * genwqe_ddcbs_in_flight() - Check how many DDCBs are in flight + * + * Keep track on the number of DDCBs which ware currently in the + * queue. This is needed for statistics as well as conditon if we want + * to wait or better do polling in case of no interrupts available. + */ +int genwqe_ddcbs_in_flight(struct genwqe_dev *cd) +{ + unsigned long flags; + int ddcbs_in_flight = 0; + struct ddcb_queue *queue = &cd->queue; + + spin_lock_irqsave(&queue->ddcb_lock, flags); + ddcbs_in_flight += queue->ddcbs_in_flight; + spin_unlock_irqrestore(&queue->ddcb_lock, flags); + + return ddcbs_in_flight; +} + +static int setup_ddcb_queue(struct genwqe_dev *cd, struct ddcb_queue *queue) +{ + int rc, i; + struct ddcb *pddcb; + u64 val64; + unsigned int queue_size; + struct pci_dev *pci_dev = cd->pci_dev; + + if (genwqe_ddcb_max < 2) + return -EINVAL; + + queue_size = roundup(genwqe_ddcb_max * sizeof(struct ddcb), PAGE_SIZE); + + queue->ddcbs_in_flight = 0; /* statistics */ + queue->ddcbs_max_in_flight = 0; + queue->ddcbs_completed = 0; + queue->busy = 0; + + queue->ddcb_seq = 0x100; /* start sequence number */ + queue->ddcb_max = genwqe_ddcb_max; /* module parameter */ + queue->ddcb_vaddr = __genwqe_alloc_consistent(cd, queue_size, + &queue->ddcb_daddr); + if (queue->ddcb_vaddr == NULL) { + dev_err(&pci_dev->dev, + "[%s] **err: could not allocate DDCB **\n", __func__); + return -ENOMEM; + } + memset(queue->ddcb_vaddr, 0, queue_size); + + queue->ddcb_req = kzalloc(sizeof(struct ddcb_requ *) * + queue->ddcb_max, GFP_KERNEL); + if (!queue->ddcb_req) { + rc = -ENOMEM; + goto free_ddcbs; + } + + queue->ddcb_waitqs = kzalloc(sizeof(wait_queue_head_t) * + queue->ddcb_max, GFP_KERNEL); + if (!queue->ddcb_waitqs) { + rc = -ENOMEM; + goto free_requs; + } + + for (i = 0; i < queue->ddcb_max; i++) { + pddcb = &queue->ddcb_vaddr[i]; /* DDCBs */ + pddcb->icrc_hsi_shi_32 = DDCB_COMPLETED_BE32; + pddcb->retc_16 = cpu_to_be16(0xfff); + + queue->ddcb_req[i] = NULL; /* requests */ + init_waitqueue_head(&queue->ddcb_waitqs[i]); /* waitqueues */ + } + + queue->ddcb_act = 0; + queue->ddcb_next = 0; /* queue is empty */ + + spin_lock_init(&queue->ddcb_lock); + init_waitqueue_head(&queue->ddcb_waitq); + + val64 = ((u64)(queue->ddcb_max - 1) << 8); /* lastptr */ + __genwqe_writeq(cd, queue->IO_QUEUE_CONFIG, 0x07); /* iCRC/vCRC */ + __genwqe_writeq(cd, queue->IO_QUEUE_SEGMENT, queue->ddcb_daddr); + __genwqe_writeq(cd, queue->IO_QUEUE_INITSQN, queue->ddcb_seq); + __genwqe_writeq(cd, queue->IO_QUEUE_WRAP, val64); + return 0; + + free_requs: + kfree(queue->ddcb_req); + queue->ddcb_req = NULL; + free_ddcbs: + __genwqe_free_consistent(cd, queue_size, queue->ddcb_vaddr, + queue->ddcb_daddr); + queue->ddcb_vaddr = NULL; + queue->ddcb_daddr = 0ull; + return -ENODEV; + +} + +static int ddcb_queue_initialized(struct ddcb_queue *queue) +{ + return queue->ddcb_vaddr != NULL; +} + +static void free_ddcb_queue(struct genwqe_dev *cd, struct ddcb_queue *queue) +{ + unsigned int queue_size; + + queue_size = roundup(queue->ddcb_max * sizeof(struct ddcb), PAGE_SIZE); + + kfree(queue->ddcb_req); + queue->ddcb_req = NULL; + + if (queue->ddcb_vaddr) { + __genwqe_free_consistent(cd, queue_size, queue->ddcb_vaddr, + queue->ddcb_daddr); + queue->ddcb_vaddr = NULL; + queue->ddcb_daddr = 0ull; + } +} + +static irqreturn_t genwqe_pf_isr(int irq, void *dev_id) +{ + u64 gfir; + struct genwqe_dev *cd = (struct genwqe_dev *)dev_id; + struct pci_dev *pci_dev = cd->pci_dev; + + /* + * In case of fatal FIR error the queue is stopped, such that + * we can safely check it without risking anything. + */ + cd->irqs_processed++; + wake_up_interruptible(&cd->queue_waitq); + + /* + * Checking for errors before kicking the queue might be + * safer, but slower for the good-case ... See above. + */ + gfir = __genwqe_readq(cd, IO_SLC_CFGREG_GFIR); + if ((gfir & GFIR_ERR_TRIGGER) != 0x0) { + + wake_up_interruptible(&cd->health_waitq); + + /* + * By default GFIRs causes recovery actions. This + * count is just for debug when recovery is masked. + */ + printk_ratelimited(KERN_ERR + "%s %s: [%s] GFIR=%016llx\n", + GENWQE_DEVNAME, dev_name(&pci_dev->dev), + __func__, gfir); + } + + return IRQ_HANDLED; +} + +static irqreturn_t genwqe_vf_isr(int irq, void *dev_id) +{ + struct genwqe_dev *cd = (struct genwqe_dev *)dev_id; + + cd->irqs_processed++; + wake_up_interruptible(&cd->queue_waitq); + + return IRQ_HANDLED; +} + +/** + * genwqe_card_thread() - Work thread for the DDCB queue + * + * The idea is to check if there are DDCBs in processing. If there are + * some finished DDCBs, we process them and wakeup the + * requestors. Otherwise we give other processes time using + * cond_resched(). + */ +static int genwqe_card_thread(void *data) +{ + int should_stop = 0, rc = 0; + struct genwqe_dev *cd = (struct genwqe_dev *)data; + + while (!kthread_should_stop()) { + + genwqe_check_ddcb_queue(cd, &cd->queue); + + if (genwqe_polling_enabled) { + rc = wait_event_interruptible_timeout( + cd->queue_waitq, + genwqe_ddcbs_in_flight(cd) || + (should_stop = kthread_should_stop()), 1); + } else { + rc = wait_event_interruptible_timeout( + cd->queue_waitq, + genwqe_next_ddcb_ready(cd) || + (should_stop = kthread_should_stop()), HZ); + } + if (should_stop) + break; + + /* + * Avoid soft lockups on heavy loads; we do not want + * to disable our interrupts. + */ + cond_resched(); + } + return 0; +} + +/** + * genwqe_setup_service_layer() - Setup DDCB queue + * @cd: pointer to genwqe device descriptor + * + * Allocate DDCBs. Configure Service Layer Controller (SLC). + * + * Return: 0 success + */ +int genwqe_setup_service_layer(struct genwqe_dev *cd) +{ + int rc; + struct ddcb_queue *queue; + struct pci_dev *pci_dev = cd->pci_dev; + + if (genwqe_is_privileged(cd)) { + rc = genwqe_card_reset(cd); + if (rc < 0) { + dev_err(&pci_dev->dev, + "[%s] err: reset failed.\n", __func__); + return rc; + } + genwqe_read_softreset(cd); + } + + queue = &cd->queue; + queue->IO_QUEUE_CONFIG = IO_SLC_QUEUE_CONFIG; + queue->IO_QUEUE_STATUS = IO_SLC_QUEUE_STATUS; + queue->IO_QUEUE_SEGMENT = IO_SLC_QUEUE_SEGMENT; + queue->IO_QUEUE_INITSQN = IO_SLC_QUEUE_INITSQN; + queue->IO_QUEUE_OFFSET = IO_SLC_QUEUE_OFFSET; + queue->IO_QUEUE_WRAP = IO_SLC_QUEUE_WRAP; + queue->IO_QUEUE_WTIME = IO_SLC_QUEUE_WTIME; + queue->IO_QUEUE_ERRCNTS = IO_SLC_QUEUE_ERRCNTS; + queue->IO_QUEUE_LRW = IO_SLC_QUEUE_LRW; + + rc = setup_ddcb_queue(cd, queue); + if (rc != 0) { + rc = -ENODEV; + goto err_out; + } + + init_waitqueue_head(&cd->queue_waitq); + cd->card_thread = kthread_run(genwqe_card_thread, cd, + GENWQE_DEVNAME "%d_thread", + cd->card_idx); + if (IS_ERR(cd->card_thread)) { + rc = PTR_ERR(cd->card_thread); + cd->card_thread = NULL; + goto stop_free_queue; + } + + rc = genwqe_set_interrupt_capability(cd, GENWQE_MSI_IRQS); + if (rc > 0) + rc = genwqe_set_interrupt_capability(cd, rc); + if (rc != 0) { + rc = -ENODEV; + goto stop_kthread; + } + + /* + * We must have all wait-queues initialized when we enable the + * interrupts. Otherwise we might crash if we get an early + * irq. + */ + init_waitqueue_head(&cd->health_waitq); + + if (genwqe_is_privileged(cd)) { + rc = request_irq(pci_dev->irq, genwqe_pf_isr, IRQF_SHARED, + GENWQE_DEVNAME, cd); + } else { + rc = request_irq(pci_dev->irq, genwqe_vf_isr, IRQF_SHARED, + GENWQE_DEVNAME, cd); + } + if (rc < 0) { + dev_err(&pci_dev->dev, "irq %d not free.\n", pci_dev->irq); + goto stop_irq_cap; + } + + cd->card_state = GENWQE_CARD_USED; + return 0; + + stop_irq_cap: + genwqe_reset_interrupt_capability(cd); + stop_kthread: + kthread_stop(cd->card_thread); + cd->card_thread = NULL; + stop_free_queue: + free_ddcb_queue(cd, queue); + err_out: + return rc; +} + +/** + * queue_wake_up_all() - Handles fatal error case + * + * The PCI device got unusable and we have to stop all pending + * requests as fast as we can. The code after this must purge the + * DDCBs in question and ensure that all mappings are freed. + */ +static int queue_wake_up_all(struct genwqe_dev *cd) +{ + unsigned int i; + unsigned long flags; + struct ddcb_queue *queue = &cd->queue; + + spin_lock_irqsave(&queue->ddcb_lock, flags); + + for (i = 0; i < queue->ddcb_max; i++) + wake_up_interruptible(&queue->ddcb_waitqs[queue->ddcb_act]); + + spin_unlock_irqrestore(&queue->ddcb_lock, flags); + + return 0; +} + +/** + * genwqe_finish_queue() - Remove any genwqe devices and user-interfaces + * + * Relies on the pre-condition that there are no users of the card + * device anymore e.g. with open file-descriptors. + * + * This function must be robust enough to be called twice. + */ +int genwqe_finish_queue(struct genwqe_dev *cd) +{ + int i, rc, in_flight; + int waitmax = genwqe_ddcb_software_timeout; + struct pci_dev *pci_dev = cd->pci_dev; + struct ddcb_queue *queue = &cd->queue; + + if (!ddcb_queue_initialized(queue)) + return 0; + + /* Do not wipe out the error state. */ + if (cd->card_state == GENWQE_CARD_USED) + cd->card_state = GENWQE_CARD_UNUSED; + + /* Wake up all requests in the DDCB queue such that they + should be removed nicely. */ + queue_wake_up_all(cd); + + /* We must wait to get rid of the DDCBs in flight */ + for (i = 0; i < waitmax; i++) { + in_flight = genwqe_ddcbs_in_flight(cd); + + if (in_flight == 0) + break; + + dev_dbg(&pci_dev->dev, + " DEBUG [%d/%d] waiting for queue to get empty: " + "%d requests!\n", i, waitmax, in_flight); + + /* + * Severe severe error situation: The card itself has + * 16 DDCB queues, each queue has e.g. 32 entries, + * each DDBC has a hardware timeout of currently 250 + * msec but the PFs have a hardware timeout of 8 sec + * ... so I take something large. + */ + msleep(1000); + } + if (i == waitmax) { + dev_err(&pci_dev->dev, " [%s] err: queue is not empty!!\n", + __func__); + rc = -EIO; + } + return rc; +} + +/** + * genwqe_release_service_layer() - Shutdown DDCB queue + * @cd: genwqe device descriptor + * + * This function must be robust enough to be called twice. + */ +int genwqe_release_service_layer(struct genwqe_dev *cd) +{ + struct pci_dev *pci_dev = cd->pci_dev; + + if (!ddcb_queue_initialized(&cd->queue)) + return 1; + + free_irq(pci_dev->irq, cd); + genwqe_reset_interrupt_capability(cd); + + if (cd->card_thread != NULL) { + kthread_stop(cd->card_thread); + cd->card_thread = NULL; + } + + free_ddcb_queue(cd, &cd->queue); + return 0; +} diff --git a/drivers/misc/genwqe/card_ddcb.h b/drivers/misc/genwqe/card_ddcb.h new file mode 100644 index 000000000000..c4f26720753e --- /dev/null +++ b/drivers/misc/genwqe/card_ddcb.h @@ -0,0 +1,188 @@ +#ifndef __CARD_DDCB_H__ +#define __CARD_DDCB_H__ + +/** + * IBM Accelerator Family 'GenWQE' + * + * (C) Copyright IBM Corp. 2013 + * + * Author: Frank Haverkamp <haver@linux.vnet.ibm.com> + * Author: Joerg-Stephan Vogt <jsvogt@de.ibm.com> + * Author: Michael Jung <mijung@de.ibm.com> + * Author: Michael Ruettger <michael@ibmra.de> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2, or (at your option) + * any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/types.h> +#include <asm/byteorder.h> + +#include "genwqe_driver.h" +#include "card_base.h" + +/** + * struct ddcb - Device Driver Control Block DDCB + * @hsi: Hardware software interlock + * @shi: Software hardware interlock. Hsi and shi are used to interlock + * software and hardware activities. We are using a compare and + * swap operation to ensure that there are no races when + * activating new DDCBs on the queue, or when we need to + * purge a DDCB from a running queue. + * @acfunc: Accelerator function addresses a unit within the chip + * @cmd: Command to work on + * @cmdopts_16: Options for the command + * @asiv: Input data + * @asv: Output data + * + * The DDCB data format is big endian. Multiple consequtive DDBCs form + * a DDCB queue. + */ +#define ASIV_LENGTH 104 /* Old specification without ATS field */ +#define ASIV_LENGTH_ATS 96 /* New specification with ATS field */ +#define ASV_LENGTH 64 + +struct ddcb { + union { + __be32 icrc_hsi_shi_32; /* iCRC, Hardware/SW interlock */ + struct { + __be16 icrc_16; + u8 hsi; + u8 shi; + }; + }; + u8 pre; /* Preamble */ + u8 xdir; /* Execution Directives */ + __be16 seqnum_16; /* Sequence Number */ + + u8 acfunc; /* Accelerator Function.. */ + u8 cmd; /* Command. */ + __be16 cmdopts_16; /* Command Options */ + u8 sur; /* Status Update Rate */ + u8 psp; /* Protection Section Pointer */ + __be16 rsvd_0e_16; /* Reserved invariant */ + + __be64 fwiv_64; /* Firmware Invariant. */ + + union { + struct { + __be64 ats_64; /* Address Translation Spec */ + u8 asiv[ASIV_LENGTH_ATS]; /* New ASIV */ + } n; + u8 __asiv[ASIV_LENGTH]; /* obsolete */ + }; + u8 asv[ASV_LENGTH]; /* Appl Spec Variant */ + + __be16 rsvd_c0_16; /* Reserved Variant */ + __be16 vcrc_16; /* Variant CRC */ + __be32 rsvd_32; /* Reserved unprotected */ + + __be64 deque_ts_64; /* Deque Time Stamp. */ + + __be16 retc_16; /* Return Code */ + __be16 attn_16; /* Attention/Extended Error Codes */ + __be32 progress_32; /* Progress indicator. */ + + __be64 cmplt_ts_64; /* Completion Time Stamp. */ + + /* The following layout matches the new service layer format */ + __be32 ibdc_32; /* Inbound Data Count (* 256) */ + __be32 obdc_32; /* Outbound Data Count (* 256) */ + + __be64 rsvd_SLH_64; /* Reserved for hardware */ + union { /* private data for driver */ + u8 priv[8]; + __be64 priv_64; + }; + __be64 disp_ts_64; /* Dispatch TimeStamp */ +} __attribute__((__packed__)); + +/* CRC polynomials for DDCB */ +#define CRC16_POLYNOMIAL 0x1021 + +/* + * SHI: Software to Hardware Interlock + * This 1 byte field is written by software to interlock the + * movement of one queue entry to another with the hardware in the + * chip. + */ +#define DDCB_SHI_INTR 0x04 /* Bit 2 */ +#define DDCB_SHI_PURGE 0x02 /* Bit 1 */ +#define DDCB_SHI_NEXT 0x01 /* Bit 0 */ + +/* + * HSI: Hardware to Software interlock + * This 1 byte field is written by hardware to interlock the movement + * of one queue entry to another with the software in the chip. + */ +#define DDCB_HSI_COMPLETED 0x40 /* Bit 6 */ +#define DDCB_HSI_FETCHED 0x04 /* Bit 2 */ + +/* + * Accessing HSI/SHI is done 32-bit wide + * Normally 16-bit access would work too, but on some platforms the + * 16 compare and swap operation is not supported. Therefore + * switching to 32-bit such that those platforms will work too. + * + * iCRC HSI/SHI + */ +#define DDCB_INTR_BE32 cpu_to_be32(0x00000004) +#define DDCB_PURGE_BE32 cpu_to_be32(0x00000002) +#define DDCB_NEXT_BE32 cpu_to_be32(0x00000001) +#define DDCB_COMPLETED_BE32 cpu_to_be32(0x00004000) +#define DDCB_FETCHED_BE32 cpu_to_be32(0x00000400) + +/* Definitions of DDCB presets */ +#define DDCB_PRESET_PRE 0x80 +#define ICRC_LENGTH(n) ((n) + 8 + 8 + 8) /* used ASIV + hdr fields */ +#define VCRC_LENGTH(n) ((n)) /* used ASV */ + +/* + * Genwqe Scatter Gather list + * Each element has up to 8 entries. + * The chaining element is element 0 cause of prefetching needs. + */ + +/* + * 0b0110 Chained descriptor. The descriptor is describing the next + * descriptor list. + */ +#define SG_CHAINED (0x6) + +/* + * 0b0010 First entry of a descriptor list. Start from a Buffer-Empty + * condition. + */ +#define SG_DATA (0x2) + +/* + * 0b0000 Early terminator. This is the last entry on the list + * irregardless of the length indicated. + */ +#define SG_END_LIST (0x0) + +/** + * struct sglist - Scatter gather list + * @target_addr: Either a dma addr of memory to work on or a + * dma addr or a subsequent sglist block. + * @len: Length of the data block. + * @flags: See above. + * + * Depending on the command the GenWQE card can use a scatter gather + * list to describe the memory it works on. Always 8 sg_entry's form + * a block. + */ +struct sg_entry { + __be64 target_addr; + __be32 len; + __be32 flags; +}; + +#endif /* __CARD_DDCB_H__ */ diff --git a/drivers/misc/genwqe/card_debugfs.c b/drivers/misc/genwqe/card_debugfs.c new file mode 100644 index 000000000000..3bfdc07a7248 --- /dev/null +++ b/drivers/misc/genwqe/card_debugfs.c @@ -0,0 +1,500 @@ +/** + * IBM Accelerator Family 'GenWQE' + * + * (C) Copyright IBM Corp. 2013 + * + * Author: Frank Haverkamp <haver@linux.vnet.ibm.com> + * Author: Joerg-Stephan Vogt <jsvogt@de.ibm.com> + * Author: Michael Jung <mijung@de.ibm.com> + * Author: Michael Ruettger <michael@ibmra.de> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +/* + * Debugfs interfaces for the GenWQE card. Help to debug potential + * problems. Dump internal chip state for debugging and failure + * determination. + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/debugfs.h> +#include <linux/seq_file.h> +#include <linux/uaccess.h> + +#include "card_base.h" +#include "card_ddcb.h" + +#define GENWQE_DEBUGFS_RO(_name, _showfn) \ + static int genwqe_debugfs_##_name##_open(struct inode *inode, \ + struct file *file) \ + { \ + return single_open(file, _showfn, inode->i_private); \ + } \ + static const struct file_operations genwqe_##_name##_fops = { \ + .open = genwqe_debugfs_##_name##_open, \ + .read = seq_read, \ + .llseek = seq_lseek, \ + .release = single_release, \ + } + +static void dbg_uidn_show(struct seq_file *s, struct genwqe_reg *regs, + int entries) +{ + unsigned int i; + u32 v_hi, v_lo; + + for (i = 0; i < entries; i++) { + v_hi = (regs[i].val >> 32) & 0xffffffff; + v_lo = (regs[i].val) & 0xffffffff; + + seq_printf(s, " 0x%08x 0x%08x 0x%08x 0x%08x EXT_ERR_REC\n", + regs[i].addr, regs[i].idx, v_hi, v_lo); + } +} + +static int curr_dbg_uidn_show(struct seq_file *s, void *unused, int uid) +{ + struct genwqe_dev *cd = s->private; + int entries; + struct genwqe_reg *regs; + + entries = genwqe_ffdc_buff_size(cd, uid); + if (entries < 0) + return -EINVAL; + + if (entries == 0) + return 0; + + regs = kcalloc(entries, sizeof(*regs), GFP_KERNEL); + if (regs == NULL) + return -ENOMEM; + + genwqe_stop_traps(cd); /* halt the traps while dumping data */ + genwqe_ffdc_buff_read(cd, uid, regs, entries); + genwqe_start_traps(cd); + + dbg_uidn_show(s, regs, entries); + kfree(regs); + return 0; +} + +static int genwqe_curr_dbg_uid0_show(struct seq_file *s, void *unused) +{ + return curr_dbg_uidn_show(s, unused, 0); +} + +GENWQE_DEBUGFS_RO(curr_dbg_uid0, genwqe_curr_dbg_uid0_show); + +static int genwqe_curr_dbg_uid1_show(struct seq_file *s, void *unused) +{ + return curr_dbg_uidn_show(s, unused, 1); +} + +GENWQE_DEBUGFS_RO(curr_dbg_uid1, genwqe_curr_dbg_uid1_show); + +static int genwqe_curr_dbg_uid2_show(struct seq_file *s, void *unused) +{ + return curr_dbg_uidn_show(s, unused, 2); +} + +GENWQE_DEBUGFS_RO(curr_dbg_uid2, genwqe_curr_dbg_uid2_show); + +static int prev_dbg_uidn_show(struct seq_file *s, void *unused, int uid) +{ + struct genwqe_dev *cd = s->private; + + dbg_uidn_show(s, cd->ffdc[uid].regs, cd->ffdc[uid].entries); + return 0; +} + +static int genwqe_prev_dbg_uid0_show(struct seq_file *s, void *unused) +{ + return prev_dbg_uidn_show(s, unused, 0); +} + +GENWQE_DEBUGFS_RO(prev_dbg_uid0, genwqe_prev_dbg_uid0_show); + +static int genwqe_prev_dbg_uid1_show(struct seq_file *s, void *unused) +{ + return prev_dbg_uidn_show(s, unused, 1); +} + +GENWQE_DEBUGFS_RO(prev_dbg_uid1, genwqe_prev_dbg_uid1_show); + +static int genwqe_prev_dbg_uid2_show(struct seq_file *s, void *unused) +{ + return prev_dbg_uidn_show(s, unused, 2); +} + +GENWQE_DEBUGFS_RO(prev_dbg_uid2, genwqe_prev_dbg_uid2_show); + +static int genwqe_curr_regs_show(struct seq_file *s, void *unused) +{ + struct genwqe_dev *cd = s->private; + unsigned int i; + struct genwqe_reg *regs; + + regs = kcalloc(GENWQE_FFDC_REGS, sizeof(*regs), GFP_KERNEL); + if (regs == NULL) + return -ENOMEM; + + genwqe_stop_traps(cd); + genwqe_read_ffdc_regs(cd, regs, GENWQE_FFDC_REGS, 1); + genwqe_start_traps(cd); + + for (i = 0; i < GENWQE_FFDC_REGS; i++) { + if (regs[i].addr == 0xffffffff) + break; /* invalid entries */ + + if (regs[i].val == 0x0ull) + continue; /* do not print 0x0 FIRs */ + + seq_printf(s, " 0x%08x 0x%016llx\n", + regs[i].addr, regs[i].val); + } + return 0; +} + +GENWQE_DEBUGFS_RO(curr_regs, genwqe_curr_regs_show); + +static int genwqe_prev_regs_show(struct seq_file *s, void *unused) +{ + struct genwqe_dev *cd = s->private; + unsigned int i; + struct genwqe_reg *regs = cd->ffdc[GENWQE_DBG_REGS].regs; + + if (regs == NULL) + return -EINVAL; + + for (i = 0; i < GENWQE_FFDC_REGS; i++) { + if (regs[i].addr == 0xffffffff) + break; /* invalid entries */ + + if (regs[i].val == 0x0ull) + continue; /* do not print 0x0 FIRs */ + + seq_printf(s, " 0x%08x 0x%016llx\n", + regs[i].addr, regs[i].val); + } + return 0; +} + +GENWQE_DEBUGFS_RO(prev_regs, genwqe_prev_regs_show); + +static int genwqe_jtimer_show(struct seq_file *s, void *unused) +{ + struct genwqe_dev *cd = s->private; + unsigned int vf_num; + u64 jtimer; + + jtimer = genwqe_read_vreg(cd, IO_SLC_VF_APPJOB_TIMEOUT, 0); + seq_printf(s, " PF 0x%016llx %d msec\n", jtimer, + genwqe_pf_jobtimeout_msec); + + for (vf_num = 0; vf_num < cd->num_vfs; vf_num++) { + jtimer = genwqe_read_vreg(cd, IO_SLC_VF_APPJOB_TIMEOUT, + vf_num + 1); + seq_printf(s, " VF%-2d 0x%016llx %d msec\n", vf_num, jtimer, + cd->vf_jobtimeout_msec[vf_num]); + } + return 0; +} + +GENWQE_DEBUGFS_RO(jtimer, genwqe_jtimer_show); + +static int genwqe_queue_working_time_show(struct seq_file *s, void *unused) +{ + struct genwqe_dev *cd = s->private; + unsigned int vf_num; + u64 t; + + t = genwqe_read_vreg(cd, IO_SLC_VF_QUEUE_WTIME, 0); + seq_printf(s, " PF 0x%016llx\n", t); + + for (vf_num = 0; vf_num < cd->num_vfs; vf_num++) { + t = genwqe_read_vreg(cd, IO_SLC_VF_QUEUE_WTIME, vf_num + 1); + seq_printf(s, " VF%-2d 0x%016llx\n", vf_num, t); + } + return 0; +} + +GENWQE_DEBUGFS_RO(queue_working_time, genwqe_queue_working_time_show); + +static int genwqe_ddcb_info_show(struct seq_file *s, void *unused) +{ + struct genwqe_dev *cd = s->private; + unsigned int i; + struct ddcb_queue *queue; + struct ddcb *pddcb; + + queue = &cd->queue; + seq_puts(s, "DDCB QUEUE:\n"); + seq_printf(s, " ddcb_max: %d\n" + " ddcb_daddr: %016llx - %016llx\n" + " ddcb_vaddr: %016llx\n" + " ddcbs_in_flight: %u\n" + " ddcbs_max_in_flight: %u\n" + " ddcbs_completed: %u\n" + " busy: %u\n" + " irqs_processed: %u\n", + queue->ddcb_max, (long long)queue->ddcb_daddr, + (long long)queue->ddcb_daddr + + (queue->ddcb_max * DDCB_LENGTH), + (long long)queue->ddcb_vaddr, queue->ddcbs_in_flight, + queue->ddcbs_max_in_flight, queue->ddcbs_completed, + queue->busy, cd->irqs_processed); + + /* Hardware State */ + seq_printf(s, " 0x%08x 0x%016llx IO_QUEUE_CONFIG\n" + " 0x%08x 0x%016llx IO_QUEUE_STATUS\n" + " 0x%08x 0x%016llx IO_QUEUE_SEGMENT\n" + " 0x%08x 0x%016llx IO_QUEUE_INITSQN\n" + " 0x%08x 0x%016llx IO_QUEUE_WRAP\n" + " 0x%08x 0x%016llx IO_QUEUE_OFFSET\n" + " 0x%08x 0x%016llx IO_QUEUE_WTIME\n" + " 0x%08x 0x%016llx IO_QUEUE_ERRCNTS\n" + " 0x%08x 0x%016llx IO_QUEUE_LRW\n", + queue->IO_QUEUE_CONFIG, + __genwqe_readq(cd, queue->IO_QUEUE_CONFIG), + queue->IO_QUEUE_STATUS, + __genwqe_readq(cd, queue->IO_QUEUE_STATUS), + queue->IO_QUEUE_SEGMENT, + __genwqe_readq(cd, queue->IO_QUEUE_SEGMENT), + queue->IO_QUEUE_INITSQN, + __genwqe_readq(cd, queue->IO_QUEUE_INITSQN), + queue->IO_QUEUE_WRAP, + __genwqe_readq(cd, queue->IO_QUEUE_WRAP), + queue->IO_QUEUE_OFFSET, + __genwqe_readq(cd, queue->IO_QUEUE_OFFSET), + queue->IO_QUEUE_WTIME, + __genwqe_readq(cd, queue->IO_QUEUE_WTIME), + queue->IO_QUEUE_ERRCNTS, + __genwqe_readq(cd, queue->IO_QUEUE_ERRCNTS), + queue->IO_QUEUE_LRW, + __genwqe_readq(cd, queue->IO_QUEUE_LRW)); + + seq_printf(s, "DDCB list (ddcb_act=%d/ddcb_next=%d):\n", + queue->ddcb_act, queue->ddcb_next); + + pddcb = queue->ddcb_vaddr; + for (i = 0; i < queue->ddcb_max; i++) { + seq_printf(s, " %-3d: RETC=%03x SEQ=%04x HSI/SHI=%02x/%02x ", + i, be16_to_cpu(pddcb->retc_16), + be16_to_cpu(pddcb->seqnum_16), + pddcb->hsi, pddcb->shi); + seq_printf(s, "PRIV=%06llx CMD=%02x\n", + be64_to_cpu(pddcb->priv_64), pddcb->cmd); + pddcb++; + } + return 0; +} + +GENWQE_DEBUGFS_RO(ddcb_info, genwqe_ddcb_info_show); + +static int genwqe_info_show(struct seq_file *s, void *unused) +{ + struct genwqe_dev *cd = s->private; + u16 val16, type; + u64 app_id, slu_id, bitstream = -1; + struct pci_dev *pci_dev = cd->pci_dev; + + slu_id = __genwqe_readq(cd, IO_SLU_UNITCFG); + app_id = __genwqe_readq(cd, IO_APP_UNITCFG); + + if (genwqe_is_privileged(cd)) + bitstream = __genwqe_readq(cd, IO_SLU_BITSTREAM); + + val16 = (u16)(slu_id & 0x0fLLU); + type = (u16)((slu_id >> 20) & 0xffLLU); + + seq_printf(s, "%s driver version: %s\n" + " Device Name/Type: %s %s CardIdx: %d\n" + " SLU/APP Config : 0x%016llx/0x%016llx\n" + " Build Date : %u/%x/%u\n" + " Base Clock : %u MHz\n" + " Arch/SVN Release: %u/%llx\n" + " Bitstream : %llx\n", + GENWQE_DEVNAME, DRV_VERS_STRING, dev_name(&pci_dev->dev), + genwqe_is_privileged(cd) ? + "Physical" : "Virtual or no SR-IOV", + cd->card_idx, slu_id, app_id, + (u16)((slu_id >> 12) & 0x0fLLU), /* month */ + (u16)((slu_id >> 4) & 0xffLLU), /* day */ + (u16)((slu_id >> 16) & 0x0fLLU) + 2010, /* year */ + genwqe_base_clock_frequency(cd), + (u16)((slu_id >> 32) & 0xffLLU), slu_id >> 40, + bitstream); + + return 0; +} + +GENWQE_DEBUGFS_RO(info, genwqe_info_show); + +int genwqe_init_debugfs(struct genwqe_dev *cd) +{ + struct dentry *root; + struct dentry *file; + int ret; + char card_name[64]; + char name[64]; + unsigned int i; + + sprintf(card_name, "%s%u_card", GENWQE_DEVNAME, cd->card_idx); + + root = debugfs_create_dir(card_name, cd->debugfs_genwqe); + if (!root) { + ret = -ENOMEM; + goto err0; + } + + /* non privileged interfaces are done here */ + file = debugfs_create_file("ddcb_info", S_IRUGO, root, cd, + &genwqe_ddcb_info_fops); + if (!file) { + ret = -ENOMEM; + goto err1; + } + + file = debugfs_create_file("info", S_IRUGO, root, cd, + &genwqe_info_fops); + if (!file) { + ret = -ENOMEM; + goto err1; + } + + file = debugfs_create_x64("err_inject", 0666, root, &cd->err_inject); + if (!file) { + ret = -ENOMEM; + goto err1; + } + + file = debugfs_create_u32("ddcb_software_timeout", 0666, root, + &cd->ddcb_software_timeout); + if (!file) { + ret = -ENOMEM; + goto err1; + } + + file = debugfs_create_u32("kill_timeout", 0666, root, + &cd->kill_timeout); + if (!file) { + ret = -ENOMEM; + goto err1; + } + + /* privileged interfaces follow here */ + if (!genwqe_is_privileged(cd)) { + cd->debugfs_root = root; + return 0; + } + + file = debugfs_create_file("curr_regs", S_IRUGO, root, cd, + &genwqe_curr_regs_fops); + if (!file) { + ret = -ENOMEM; + goto err1; + } + + file = debugfs_create_file("curr_dbg_uid0", S_IRUGO, root, cd, + &genwqe_curr_dbg_uid0_fops); + if (!file) { + ret = -ENOMEM; + goto err1; + } + + file = debugfs_create_file("curr_dbg_uid1", S_IRUGO, root, cd, + &genwqe_curr_dbg_uid1_fops); + if (!file) { + ret = -ENOMEM; + goto err1; + } + + file = debugfs_create_file("curr_dbg_uid2", S_IRUGO, root, cd, + &genwqe_curr_dbg_uid2_fops); + if (!file) { + ret = -ENOMEM; + goto err1; + } + + file = debugfs_create_file("prev_regs", S_IRUGO, root, cd, + &genwqe_prev_regs_fops); + if (!file) { + ret = -ENOMEM; + goto err1; + } + + file = debugfs_create_file("prev_dbg_uid0", S_IRUGO, root, cd, + &genwqe_prev_dbg_uid0_fops); + if (!file) { + ret = -ENOMEM; + goto err1; + } + + file = debugfs_create_file("prev_dbg_uid1", S_IRUGO, root, cd, + &genwqe_prev_dbg_uid1_fops); + if (!file) { + ret = -ENOMEM; + goto err1; + } + + file = debugfs_create_file("prev_dbg_uid2", S_IRUGO, root, cd, + &genwqe_prev_dbg_uid2_fops); + if (!file) { + ret = -ENOMEM; + goto err1; + } + + for (i = 0; i < GENWQE_MAX_VFS; i++) { + sprintf(name, "vf%d_jobtimeout_msec", i); + + file = debugfs_create_u32(name, 0666, root, + &cd->vf_jobtimeout_msec[i]); + if (!file) { + ret = -ENOMEM; + goto err1; + } + } + + file = debugfs_create_file("jobtimer", S_IRUGO, root, cd, + &genwqe_jtimer_fops); + if (!file) { + ret = -ENOMEM; + goto err1; + } + + file = debugfs_create_file("queue_working_time", S_IRUGO, root, cd, + &genwqe_queue_working_time_fops); + if (!file) { + ret = -ENOMEM; + goto err1; + } + + file = debugfs_create_u32("skip_recovery", 0666, root, + &cd->skip_recovery); + if (!file) { + ret = -ENOMEM; + goto err1; + } + + cd->debugfs_root = root; + return 0; +err1: + debugfs_remove_recursive(root); +err0: + return ret; +} + +void genqwe_exit_debugfs(struct genwqe_dev *cd) +{ + debugfs_remove_recursive(cd->debugfs_root); +} diff --git a/drivers/misc/genwqe/card_dev.c b/drivers/misc/genwqe/card_dev.c new file mode 100644 index 000000000000..8f8a6b327cdb --- /dev/null +++ b/drivers/misc/genwqe/card_dev.c @@ -0,0 +1,1414 @@ +/** + * IBM Accelerator Family 'GenWQE' + * + * (C) Copyright IBM Corp. 2013 + * + * Author: Frank Haverkamp <haver@linux.vnet.ibm.com> + * Author: Joerg-Stephan Vogt <jsvogt@de.ibm.com> + * Author: Michael Jung <mijung@de.ibm.com> + * Author: Michael Ruettger <michael@ibmra.de> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +/* + * Character device representation of the GenWQE device. This allows + * user-space applications to communicate with the card. + */ + +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/string.h> +#include <linux/fs.h> +#include <linux/sched.h> +#include <linux/wait.h> +#include <linux/delay.h> +#include <linux/atomic.h> + +#include "card_base.h" +#include "card_ddcb.h" + +static int genwqe_open_files(struct genwqe_dev *cd) +{ + int rc; + unsigned long flags; + + spin_lock_irqsave(&cd->file_lock, flags); + rc = list_empty(&cd->file_list); + spin_unlock_irqrestore(&cd->file_lock, flags); + return !rc; +} + +static void genwqe_add_file(struct genwqe_dev *cd, struct genwqe_file *cfile) +{ + unsigned long flags; + + cfile->owner = current; + spin_lock_irqsave(&cd->file_lock, flags); + list_add(&cfile->list, &cd->file_list); + spin_unlock_irqrestore(&cd->file_lock, flags); +} + +static int genwqe_del_file(struct genwqe_dev *cd, struct genwqe_file *cfile) +{ + unsigned long flags; + + spin_lock_irqsave(&cd->file_lock, flags); + list_del(&cfile->list); + spin_unlock_irqrestore(&cd->file_lock, flags); + + return 0; +} + +static void genwqe_add_pin(struct genwqe_file *cfile, struct dma_mapping *m) +{ + unsigned long flags; + + spin_lock_irqsave(&cfile->pin_lock, flags); + list_add(&m->pin_list, &cfile->pin_list); + spin_unlock_irqrestore(&cfile->pin_lock, flags); +} + +static int genwqe_del_pin(struct genwqe_file *cfile, struct dma_mapping *m) +{ + unsigned long flags; + + spin_lock_irqsave(&cfile->pin_lock, flags); + list_del(&m->pin_list); + spin_unlock_irqrestore(&cfile->pin_lock, flags); + + return 0; +} + +/** + * genwqe_search_pin() - Search for the mapping for a userspace address + * @cfile: Descriptor of opened file + * @u_addr: User virtual address + * @size: Size of buffer + * @dma_addr: DMA address to be updated + * + * Return: Pointer to the corresponding mapping NULL if not found + */ +static struct dma_mapping *genwqe_search_pin(struct genwqe_file *cfile, + unsigned long u_addr, + unsigned int size, + void **virt_addr) +{ + unsigned long flags; + struct dma_mapping *m; + + spin_lock_irqsave(&cfile->pin_lock, flags); + + list_for_each_entry(m, &cfile->pin_list, pin_list) { + if ((((u64)m->u_vaddr) <= (u_addr)) && + (((u64)m->u_vaddr + m->size) >= (u_addr + size))) { + + if (virt_addr) + *virt_addr = m->k_vaddr + + (u_addr - (u64)m->u_vaddr); + + spin_unlock_irqrestore(&cfile->pin_lock, flags); + return m; + } + } + spin_unlock_irqrestore(&cfile->pin_lock, flags); + return NULL; +} + +static void __genwqe_add_mapping(struct genwqe_file *cfile, + struct dma_mapping *dma_map) +{ + unsigned long flags; + + spin_lock_irqsave(&cfile->map_lock, flags); + list_add(&dma_map->card_list, &cfile->map_list); + spin_unlock_irqrestore(&cfile->map_lock, flags); +} + +static void __genwqe_del_mapping(struct genwqe_file *cfile, + struct dma_mapping *dma_map) +{ + unsigned long flags; + + spin_lock_irqsave(&cfile->map_lock, flags); + list_del(&dma_map->card_list); + spin_unlock_irqrestore(&cfile->map_lock, flags); +} + + +/** + * __genwqe_search_mapping() - Search for the mapping for a userspace address + * @cfile: descriptor of opened file + * @u_addr: user virtual address + * @size: size of buffer + * @dma_addr: DMA address to be updated + * Return: Pointer to the corresponding mapping NULL if not found + */ +static struct dma_mapping *__genwqe_search_mapping(struct genwqe_file *cfile, + unsigned long u_addr, + unsigned int size, + dma_addr_t *dma_addr, + void **virt_addr) +{ + unsigned long flags; + struct dma_mapping *m; + struct pci_dev *pci_dev = cfile->cd->pci_dev; + + spin_lock_irqsave(&cfile->map_lock, flags); + list_for_each_entry(m, &cfile->map_list, card_list) { + + if ((((u64)m->u_vaddr) <= (u_addr)) && + (((u64)m->u_vaddr + m->size) >= (u_addr + size))) { + + /* match found: current is as expected and + addr is in range */ + if (dma_addr) + *dma_addr = m->dma_addr + + (u_addr - (u64)m->u_vaddr); + + if (virt_addr) + *virt_addr = m->k_vaddr + + (u_addr - (u64)m->u_vaddr); + + spin_unlock_irqrestore(&cfile->map_lock, flags); + return m; + } + } + spin_unlock_irqrestore(&cfile->map_lock, flags); + + dev_err(&pci_dev->dev, + "[%s] Entry not found: u_addr=%lx, size=%x\n", + __func__, u_addr, size); + + return NULL; +} + +static void genwqe_remove_mappings(struct genwqe_file *cfile) +{ + int i = 0; + struct list_head *node, *next; + struct dma_mapping *dma_map; + struct genwqe_dev *cd = cfile->cd; + struct pci_dev *pci_dev = cfile->cd->pci_dev; + + list_for_each_safe(node, next, &cfile->map_list) { + dma_map = list_entry(node, struct dma_mapping, card_list); + + list_del_init(&dma_map->card_list); + + /* + * This is really a bug, because those things should + * have been already tidied up. + * + * GENWQE_MAPPING_RAW should have been removed via mmunmap(). + * GENWQE_MAPPING_SGL_TEMP should be removed by tidy up code. + */ + dev_err(&pci_dev->dev, + "[%s] %d. cleanup mapping: u_vaddr=%p " + "u_kaddr=%016lx dma_addr=%lx\n", __func__, i++, + dma_map->u_vaddr, (unsigned long)dma_map->k_vaddr, + (unsigned long)dma_map->dma_addr); + + if (dma_map->type == GENWQE_MAPPING_RAW) { + /* we allocated this dynamically */ + __genwqe_free_consistent(cd, dma_map->size, + dma_map->k_vaddr, + dma_map->dma_addr); + kfree(dma_map); + } else if (dma_map->type == GENWQE_MAPPING_SGL_TEMP) { + /* we use dma_map statically from the request */ + genwqe_user_vunmap(cd, dma_map, NULL); + } + } +} + +static void genwqe_remove_pinnings(struct genwqe_file *cfile) +{ + struct list_head *node, *next; + struct dma_mapping *dma_map; + struct genwqe_dev *cd = cfile->cd; + + list_for_each_safe(node, next, &cfile->pin_list) { + dma_map = list_entry(node, struct dma_mapping, pin_list); + + /* + * This is not a bug, because a killed processed might + * not call the unpin ioctl, which is supposed to free + * the resources. + * + * Pinnings are dymically allocated and need to be + * deleted. + */ + list_del_init(&dma_map->pin_list); + genwqe_user_vunmap(cd, dma_map, NULL); + kfree(dma_map); + } +} + +/** + * genwqe_kill_fasync() - Send signal to all processes with open GenWQE files + * + * E.g. genwqe_send_signal(cd, SIGIO); + */ +static int genwqe_kill_fasync(struct genwqe_dev *cd, int sig) +{ + unsigned int files = 0; + unsigned long flags; + struct genwqe_file *cfile; + + spin_lock_irqsave(&cd->file_lock, flags); + list_for_each_entry(cfile, &cd->file_list, list) { + if (cfile->async_queue) + kill_fasync(&cfile->async_queue, sig, POLL_HUP); + files++; + } + spin_unlock_irqrestore(&cd->file_lock, flags); + return files; +} + +static int genwqe_force_sig(struct genwqe_dev *cd, int sig) +{ + unsigned int files = 0; + unsigned long flags; + struct genwqe_file *cfile; + + spin_lock_irqsave(&cd->file_lock, flags); + list_for_each_entry(cfile, &cd->file_list, list) { + force_sig(sig, cfile->owner); + files++; + } + spin_unlock_irqrestore(&cd->file_lock, flags); + return files; +} + +/** + * genwqe_open() - file open + * @inode: file system information + * @filp: file handle + * + * This function is executed whenever an application calls + * open("/dev/genwqe",..). + * + * Return: 0 if successful or <0 if errors + */ +static int genwqe_open(struct inode *inode, struct file *filp) +{ + struct genwqe_dev *cd; + struct genwqe_file *cfile; + struct pci_dev *pci_dev; + + cfile = kzalloc(sizeof(*cfile), GFP_KERNEL); + if (cfile == NULL) + return -ENOMEM; + + cd = container_of(inode->i_cdev, struct genwqe_dev, cdev_genwqe); + pci_dev = cd->pci_dev; + cfile->cd = cd; + cfile->filp = filp; + cfile->client = NULL; + + spin_lock_init(&cfile->map_lock); /* list of raw memory allocations */ + INIT_LIST_HEAD(&cfile->map_list); + + spin_lock_init(&cfile->pin_lock); /* list of user pinned memory */ + INIT_LIST_HEAD(&cfile->pin_list); + + filp->private_data = cfile; + + genwqe_add_file(cd, cfile); + return 0; +} + +/** + * genwqe_fasync() - Setup process to receive SIGIO. + * @fd: file descriptor + * @filp: file handle + * @mode: file mode + * + * Sending a signal is working as following: + * + * if (cdev->async_queue) + * kill_fasync(&cdev->async_queue, SIGIO, POLL_IN); + * + * Some devices also implement asynchronous notification to indicate + * when the device can be written; in this case, of course, + * kill_fasync must be called with a mode of POLL_OUT. + */ +static int genwqe_fasync(int fd, struct file *filp, int mode) +{ + struct genwqe_file *cdev = (struct genwqe_file *)filp->private_data; + return fasync_helper(fd, filp, mode, &cdev->async_queue); +} + + +/** + * genwqe_release() - file close + * @inode: file system information + * @filp: file handle + * + * This function is executed whenever an application calls 'close(fd_genwqe)' + * + * Return: always 0 + */ +static int genwqe_release(struct inode *inode, struct file *filp) +{ + struct genwqe_file *cfile = (struct genwqe_file *)filp->private_data; + struct genwqe_dev *cd = cfile->cd; + + /* there must be no entries in these lists! */ + genwqe_remove_mappings(cfile); + genwqe_remove_pinnings(cfile); + + /* remove this filp from the asynchronously notified filp's */ + genwqe_fasync(-1, filp, 0); + + /* + * For this to work we must not release cd when this cfile is + * not yet released, otherwise the list entry is invalid, + * because the list itself gets reinstantiated! + */ + genwqe_del_file(cd, cfile); + kfree(cfile); + return 0; +} + +static void genwqe_vma_open(struct vm_area_struct *vma) +{ + /* nothing ... */ +} + +/** + * genwqe_vma_close() - Called each time when vma is unmapped + * + * Free memory which got allocated by GenWQE mmap(). + */ +static void genwqe_vma_close(struct vm_area_struct *vma) +{ + unsigned long vsize = vma->vm_end - vma->vm_start; + struct inode *inode = vma->vm_file->f_dentry->d_inode; + struct dma_mapping *dma_map; + struct genwqe_dev *cd = container_of(inode->i_cdev, struct genwqe_dev, + cdev_genwqe); + struct pci_dev *pci_dev = cd->pci_dev; + dma_addr_t d_addr = 0; + struct genwqe_file *cfile = vma->vm_private_data; + + dma_map = __genwqe_search_mapping(cfile, vma->vm_start, vsize, + &d_addr, NULL); + if (dma_map == NULL) { + dev_err(&pci_dev->dev, + " [%s] err: mapping not found: v=%lx, p=%lx s=%lx\n", + __func__, vma->vm_start, vma->vm_pgoff << PAGE_SHIFT, + vsize); + return; + } + __genwqe_del_mapping(cfile, dma_map); + __genwqe_free_consistent(cd, dma_map->size, dma_map->k_vaddr, + dma_map->dma_addr); + kfree(dma_map); +} + +static struct vm_operations_struct genwqe_vma_ops = { + .open = genwqe_vma_open, + .close = genwqe_vma_close, +}; + +/** + * genwqe_mmap() - Provide contignous buffers to userspace + * + * We use mmap() to allocate contignous buffers used for DMA + * transfers. After the buffer is allocated we remap it to user-space + * and remember a reference to our dma_mapping data structure, where + * we store the associated DMA address and allocated size. + * + * When we receive a DDCB execution request with the ATS bits set to + * plain buffer, we lookup our dma_mapping list to find the + * corresponding DMA address for the associated user-space address. + */ +static int genwqe_mmap(struct file *filp, struct vm_area_struct *vma) +{ + int rc; + unsigned long pfn, vsize = vma->vm_end - vma->vm_start; + struct genwqe_file *cfile = (struct genwqe_file *)filp->private_data; + struct genwqe_dev *cd = cfile->cd; + struct dma_mapping *dma_map; + + if (vsize == 0) + return -EINVAL; + + if (get_order(vsize) > MAX_ORDER) + return -ENOMEM; + + dma_map = kzalloc(sizeof(struct dma_mapping), GFP_ATOMIC); + if (dma_map == NULL) + return -ENOMEM; + + genwqe_mapping_init(dma_map, GENWQE_MAPPING_RAW); + dma_map->u_vaddr = (void *)vma->vm_start; + dma_map->size = vsize; + dma_map->nr_pages = DIV_ROUND_UP(vsize, PAGE_SIZE); + dma_map->k_vaddr = __genwqe_alloc_consistent(cd, vsize, + &dma_map->dma_addr); + if (dma_map->k_vaddr == NULL) { + rc = -ENOMEM; + goto free_dma_map; + } + + if (capable(CAP_SYS_ADMIN) && (vsize > sizeof(dma_addr_t))) + *(dma_addr_t *)dma_map->k_vaddr = dma_map->dma_addr; + + pfn = virt_to_phys(dma_map->k_vaddr) >> PAGE_SHIFT; + rc = remap_pfn_range(vma, + vma->vm_start, + pfn, + vsize, + vma->vm_page_prot); + if (rc != 0) { + rc = -EFAULT; + goto free_dma_mem; + } + + vma->vm_private_data = cfile; + vma->vm_ops = &genwqe_vma_ops; + __genwqe_add_mapping(cfile, dma_map); + + return 0; + + free_dma_mem: + __genwqe_free_consistent(cd, dma_map->size, + dma_map->k_vaddr, + dma_map->dma_addr); + free_dma_map: + kfree(dma_map); + return rc; +} + +/** + * do_flash_update() - Excute flash update (write image or CVPD) + * @cd: genwqe device + * @load: details about image load + * + * Return: 0 if successful + */ + +#define FLASH_BLOCK 0x40000 /* we use 256k blocks */ + +static int do_flash_update(struct genwqe_file *cfile, + struct genwqe_bitstream *load) +{ + int rc = 0; + int blocks_to_flash; + dma_addr_t dma_addr; + u64 flash = 0; + size_t tocopy = 0; + u8 __user *buf; + u8 *xbuf; + u32 crc; + u8 cmdopts; + struct genwqe_dev *cd = cfile->cd; + struct pci_dev *pci_dev = cd->pci_dev; + + if ((load->size & 0x3) != 0) + return -EINVAL; + + if (((unsigned long)(load->data_addr) & ~PAGE_MASK) != 0) + return -EINVAL; + + /* FIXME Bits have changed for new service layer! */ + switch ((char)load->partition) { + case '0': + cmdopts = 0x14; + break; /* download/erase_first/part_0 */ + case '1': + cmdopts = 0x1C; + break; /* download/erase_first/part_1 */ + case 'v': /* cmdopts = 0x0c (VPD) */ + default: + return -EINVAL; + } + + buf = (u8 __user *)load->data_addr; + xbuf = __genwqe_alloc_consistent(cd, FLASH_BLOCK, &dma_addr); + if (xbuf == NULL) + return -ENOMEM; + + blocks_to_flash = load->size / FLASH_BLOCK; + while (load->size) { + struct genwqe_ddcb_cmd *req; + + /* + * We must be 4 byte aligned. Buffer must be 0 appened + * to have defined values when calculating CRC. + */ + tocopy = min_t(size_t, load->size, FLASH_BLOCK); + + rc = copy_from_user(xbuf, buf, tocopy); + if (rc) { + rc = -EFAULT; + goto free_buffer; + } + crc = genwqe_crc32(xbuf, tocopy, 0xffffffff); + + dev_dbg(&pci_dev->dev, + "[%s] DMA: %lx CRC: %08x SZ: %ld %d\n", + __func__, (unsigned long)dma_addr, crc, tocopy, + blocks_to_flash); + + /* prepare DDCB for SLU process */ + req = ddcb_requ_alloc(); + if (req == NULL) { + rc = -ENOMEM; + goto free_buffer; + } + + req->cmd = SLCMD_MOVE_FLASH; + req->cmdopts = cmdopts; + + /* prepare invariant values */ + if (genwqe_get_slu_id(cd) <= 0x2) { + *(__be64 *)&req->__asiv[0] = cpu_to_be64(dma_addr); + *(__be64 *)&req->__asiv[8] = cpu_to_be64(tocopy); + *(__be64 *)&req->__asiv[16] = cpu_to_be64(flash); + *(__be32 *)&req->__asiv[24] = cpu_to_be32(0); + req->__asiv[24] = load->uid; + *(__be32 *)&req->__asiv[28] = cpu_to_be32(crc); + + /* for simulation only */ + *(__be64 *)&req->__asiv[88] = cpu_to_be64(load->slu_id); + *(__be64 *)&req->__asiv[96] = cpu_to_be64(load->app_id); + req->asiv_length = 32; /* bytes included in crc calc */ + } else { /* setup DDCB for ATS architecture */ + *(__be64 *)&req->asiv[0] = cpu_to_be64(dma_addr); + *(__be32 *)&req->asiv[8] = cpu_to_be32(tocopy); + *(__be32 *)&req->asiv[12] = cpu_to_be32(0); /* resvd */ + *(__be64 *)&req->asiv[16] = cpu_to_be64(flash); + *(__be32 *)&req->asiv[24] = cpu_to_be32(load->uid<<24); + *(__be32 *)&req->asiv[28] = cpu_to_be32(crc); + + /* for simulation only */ + *(__be64 *)&req->asiv[80] = cpu_to_be64(load->slu_id); + *(__be64 *)&req->asiv[88] = cpu_to_be64(load->app_id); + + /* Rd only */ + req->ats = 0x4ULL << 44; + req->asiv_length = 40; /* bytes included in crc calc */ + } + req->asv_length = 8; + + /* For Genwqe5 we get back the calculated CRC */ + *(u64 *)&req->asv[0] = 0ULL; /* 0x80 */ + + rc = __genwqe_execute_raw_ddcb(cd, req); + + load->retc = req->retc; + load->attn = req->attn; + load->progress = req->progress; + + if (rc < 0) { + ddcb_requ_free(req); + goto free_buffer; + } + + if (req->retc != DDCB_RETC_COMPLETE) { + rc = -EIO; + ddcb_requ_free(req); + goto free_buffer; + } + + load->size -= tocopy; + flash += tocopy; + buf += tocopy; + blocks_to_flash--; + ddcb_requ_free(req); + } + + free_buffer: + __genwqe_free_consistent(cd, FLASH_BLOCK, xbuf, dma_addr); + return rc; +} + +static int do_flash_read(struct genwqe_file *cfile, + struct genwqe_bitstream *load) +{ + int rc, blocks_to_flash; + dma_addr_t dma_addr; + u64 flash = 0; + size_t tocopy = 0; + u8 __user *buf; + u8 *xbuf; + u8 cmdopts; + struct genwqe_dev *cd = cfile->cd; + struct pci_dev *pci_dev = cd->pci_dev; + struct genwqe_ddcb_cmd *cmd; + + if ((load->size & 0x3) != 0) + return -EINVAL; + + if (((unsigned long)(load->data_addr) & ~PAGE_MASK) != 0) + return -EINVAL; + + /* FIXME Bits have changed for new service layer! */ + switch ((char)load->partition) { + case '0': + cmdopts = 0x12; + break; /* upload/part_0 */ + case '1': + cmdopts = 0x1A; + break; /* upload/part_1 */ + case 'v': + default: + return -EINVAL; + } + + buf = (u8 __user *)load->data_addr; + xbuf = __genwqe_alloc_consistent(cd, FLASH_BLOCK, &dma_addr); + if (xbuf == NULL) + return -ENOMEM; + + blocks_to_flash = load->size / FLASH_BLOCK; + while (load->size) { + /* + * We must be 4 byte aligned. Buffer must be 0 appened + * to have defined values when calculating CRC. + */ + tocopy = min_t(size_t, load->size, FLASH_BLOCK); + + dev_dbg(&pci_dev->dev, + "[%s] DMA: %lx SZ: %ld %d\n", + __func__, (unsigned long)dma_addr, tocopy, + blocks_to_flash); + + /* prepare DDCB for SLU process */ + cmd = ddcb_requ_alloc(); + if (cmd == NULL) { + rc = -ENOMEM; + goto free_buffer; + } + cmd->cmd = SLCMD_MOVE_FLASH; + cmd->cmdopts = cmdopts; + + /* prepare invariant values */ + if (genwqe_get_slu_id(cd) <= 0x2) { + *(__be64 *)&cmd->__asiv[0] = cpu_to_be64(dma_addr); + *(__be64 *)&cmd->__asiv[8] = cpu_to_be64(tocopy); + *(__be64 *)&cmd->__asiv[16] = cpu_to_be64(flash); + *(__be32 *)&cmd->__asiv[24] = cpu_to_be32(0); + cmd->__asiv[24] = load->uid; + *(__be32 *)&cmd->__asiv[28] = cpu_to_be32(0) /* CRC */; + cmd->asiv_length = 32; /* bytes included in crc calc */ + } else { /* setup DDCB for ATS architecture */ + *(__be64 *)&cmd->asiv[0] = cpu_to_be64(dma_addr); + *(__be32 *)&cmd->asiv[8] = cpu_to_be32(tocopy); + *(__be32 *)&cmd->asiv[12] = cpu_to_be32(0); /* resvd */ + *(__be64 *)&cmd->asiv[16] = cpu_to_be64(flash); + *(__be32 *)&cmd->asiv[24] = cpu_to_be32(load->uid<<24); + *(__be32 *)&cmd->asiv[28] = cpu_to_be32(0); /* CRC */ + + /* rd/wr */ + cmd->ats = 0x5ULL << 44; + cmd->asiv_length = 40; /* bytes included in crc calc */ + } + cmd->asv_length = 8; + + /* we only get back the calculated CRC */ + *(u64 *)&cmd->asv[0] = 0ULL; /* 0x80 */ + + rc = __genwqe_execute_raw_ddcb(cd, cmd); + + load->retc = cmd->retc; + load->attn = cmd->attn; + load->progress = cmd->progress; + + if ((rc < 0) && (rc != -EBADMSG)) { + ddcb_requ_free(cmd); + goto free_buffer; + } + + rc = copy_to_user(buf, xbuf, tocopy); + if (rc) { + rc = -EFAULT; + ddcb_requ_free(cmd); + goto free_buffer; + } + + /* We know that we can get retc 0x104 with CRC err */ + if (((cmd->retc == DDCB_RETC_FAULT) && + (cmd->attn != 0x02)) || /* Normally ignore CRC error */ + ((cmd->retc == DDCB_RETC_COMPLETE) && + (cmd->attn != 0x00))) { /* Everything was fine */ + rc = -EIO; + ddcb_requ_free(cmd); + goto free_buffer; + } + + load->size -= tocopy; + flash += tocopy; + buf += tocopy; + blocks_to_flash--; + ddcb_requ_free(cmd); + } + rc = 0; + + free_buffer: + __genwqe_free_consistent(cd, FLASH_BLOCK, xbuf, dma_addr); + return rc; +} + +static int genwqe_pin_mem(struct genwqe_file *cfile, struct genwqe_mem *m) +{ + int rc; + struct genwqe_dev *cd = cfile->cd; + struct pci_dev *pci_dev = cfile->cd->pci_dev; + struct dma_mapping *dma_map; + unsigned long map_addr; + unsigned long map_size; + + if ((m->addr == 0x0) || (m->size == 0)) + return -EINVAL; + + map_addr = (m->addr & PAGE_MASK); + map_size = round_up(m->size + (m->addr & ~PAGE_MASK), PAGE_SIZE); + + dma_map = kzalloc(sizeof(struct dma_mapping), GFP_ATOMIC); + if (dma_map == NULL) + return -ENOMEM; + + genwqe_mapping_init(dma_map, GENWQE_MAPPING_SGL_PINNED); + rc = genwqe_user_vmap(cd, dma_map, (void *)map_addr, map_size, NULL); + if (rc != 0) { + dev_err(&pci_dev->dev, + "[%s] genwqe_user_vmap rc=%d\n", __func__, rc); + return rc; + } + + genwqe_add_pin(cfile, dma_map); + return 0; +} + +static int genwqe_unpin_mem(struct genwqe_file *cfile, struct genwqe_mem *m) +{ + struct genwqe_dev *cd = cfile->cd; + struct dma_mapping *dma_map; + unsigned long map_addr; + unsigned long map_size; + + if (m->addr == 0x0) + return -EINVAL; + + map_addr = (m->addr & PAGE_MASK); + map_size = round_up(m->size + (m->addr & ~PAGE_MASK), PAGE_SIZE); + + dma_map = genwqe_search_pin(cfile, map_addr, map_size, NULL); + if (dma_map == NULL) + return -ENOENT; + + genwqe_del_pin(cfile, dma_map); + genwqe_user_vunmap(cd, dma_map, NULL); + kfree(dma_map); + return 0; +} + +/** + * ddcb_cmd_cleanup() - Remove dynamically created fixup entries + * + * Only if there are any. Pinnings are not removed. + */ +static int ddcb_cmd_cleanup(struct genwqe_file *cfile, struct ddcb_requ *req) +{ + unsigned int i; + struct dma_mapping *dma_map; + struct genwqe_dev *cd = cfile->cd; + + for (i = 0; i < DDCB_FIXUPS; i++) { + dma_map = &req->dma_mappings[i]; + + if (dma_mapping_used(dma_map)) { + __genwqe_del_mapping(cfile, dma_map); + genwqe_user_vunmap(cd, dma_map, req); + } + if (req->sgl[i] != NULL) { + genwqe_free_sgl(cd, req->sgl[i], + req->sgl_dma_addr[i], + req->sgl_size[i]); + req->sgl[i] = NULL; + req->sgl_dma_addr[i] = 0x0; + req->sgl_size[i] = 0; + } + + } + return 0; +} + +/** + * ddcb_cmd_fixups() - Establish DMA fixups/sglists for user memory references + * + * Before the DDCB gets executed we need to handle the fixups. We + * replace the user-space addresses with DMA addresses or do + * additional setup work e.g. generating a scatter-gather list which + * is used to describe the memory referred to in the fixup. + */ +static int ddcb_cmd_fixups(struct genwqe_file *cfile, struct ddcb_requ *req) +{ + int rc; + unsigned int asiv_offs, i; + struct genwqe_dev *cd = cfile->cd; + struct genwqe_ddcb_cmd *cmd = &req->cmd; + struct dma_mapping *m; + const char *type = "UNKNOWN"; + + for (i = 0, asiv_offs = 0x00; asiv_offs <= 0x58; + i++, asiv_offs += 0x08) { + + u64 u_addr; + dma_addr_t d_addr; + u32 u_size = 0; + u64 ats_flags; + + ats_flags = ATS_GET_FLAGS(cmd->ats, asiv_offs); + + switch (ats_flags) { + + case ATS_TYPE_DATA: + break; /* nothing to do here */ + + case ATS_TYPE_FLAT_RDWR: + case ATS_TYPE_FLAT_RD: { + u_addr = be64_to_cpu(*((__be64 *)&cmd-> + asiv[asiv_offs])); + u_size = be32_to_cpu(*((__be32 *)&cmd-> + asiv[asiv_offs + 0x08])); + + /* + * No data available. Ignore u_addr in this + * case and set addr to 0. Hardware must not + * fetch the buffer. + */ + if (u_size == 0x0) { + *((__be64 *)&cmd->asiv[asiv_offs]) = + cpu_to_be64(0x0); + break; + } + + m = __genwqe_search_mapping(cfile, u_addr, u_size, + &d_addr, NULL); + if (m == NULL) { + rc = -EFAULT; + goto err_out; + } + + *((__be64 *)&cmd->asiv[asiv_offs]) = + cpu_to_be64(d_addr); + break; + } + + case ATS_TYPE_SGL_RDWR: + case ATS_TYPE_SGL_RD: { + int page_offs, nr_pages, offs; + + u_addr = be64_to_cpu(*((__be64 *) + &cmd->asiv[asiv_offs])); + u_size = be32_to_cpu(*((__be32 *) + &cmd->asiv[asiv_offs + 0x08])); + + /* + * No data available. Ignore u_addr in this + * case and set addr to 0. Hardware must not + * fetch the empty sgl. + */ + if (u_size == 0x0) { + *((__be64 *)&cmd->asiv[asiv_offs]) = + cpu_to_be64(0x0); + break; + } + + m = genwqe_search_pin(cfile, u_addr, u_size, NULL); + if (m != NULL) { + type = "PINNING"; + page_offs = (u_addr - + (u64)m->u_vaddr)/PAGE_SIZE; + } else { + type = "MAPPING"; + m = &req->dma_mappings[i]; + + genwqe_mapping_init(m, + GENWQE_MAPPING_SGL_TEMP); + rc = genwqe_user_vmap(cd, m, (void *)u_addr, + u_size, req); + if (rc != 0) + goto err_out; + + __genwqe_add_mapping(cfile, m); + page_offs = 0; + } + + offs = offset_in_page(u_addr); + nr_pages = DIV_ROUND_UP(offs + u_size, PAGE_SIZE); + + /* create genwqe style scatter gather list */ + req->sgl[i] = genwqe_alloc_sgl(cd, m->nr_pages, + &req->sgl_dma_addr[i], + &req->sgl_size[i]); + if (req->sgl[i] == NULL) { + rc = -ENOMEM; + goto err_out; + } + genwqe_setup_sgl(cd, offs, u_size, + req->sgl[i], + req->sgl_dma_addr[i], + req->sgl_size[i], + m->dma_list, + page_offs, + nr_pages); + + *((__be64 *)&cmd->asiv[asiv_offs]) = + cpu_to_be64(req->sgl_dma_addr[i]); + + break; + } + default: + rc = -EINVAL; + goto err_out; + } + } + return 0; + + err_out: + ddcb_cmd_cleanup(cfile, req); + return rc; +} + +/** + * genwqe_execute_ddcb() - Execute DDCB using userspace address fixups + * + * The code will build up the translation tables or lookup the + * contignous memory allocation table to find the right translations + * and DMA addresses. + */ +static int genwqe_execute_ddcb(struct genwqe_file *cfile, + struct genwqe_ddcb_cmd *cmd) +{ + int rc; + struct genwqe_dev *cd = cfile->cd; + struct ddcb_requ *req = container_of(cmd, struct ddcb_requ, cmd); + + rc = ddcb_cmd_fixups(cfile, req); + if (rc != 0) + return rc; + + rc = __genwqe_execute_raw_ddcb(cd, cmd); + ddcb_cmd_cleanup(cfile, req); + return rc; +} + +static int do_execute_ddcb(struct genwqe_file *cfile, + unsigned long arg, int raw) +{ + int rc; + struct genwqe_ddcb_cmd *cmd; + struct ddcb_requ *req; + struct genwqe_dev *cd = cfile->cd; + + cmd = ddcb_requ_alloc(); + if (cmd == NULL) + return -ENOMEM; + + req = container_of(cmd, struct ddcb_requ, cmd); + + if (copy_from_user(cmd, (void __user *)arg, sizeof(*cmd))) { + ddcb_requ_free(cmd); + return -EFAULT; + } + + if (!raw) + rc = genwqe_execute_ddcb(cfile, cmd); + else + rc = __genwqe_execute_raw_ddcb(cd, cmd); + + /* Copy back only the modifed fields. Do not copy ASIV + back since the copy got modified by the driver. */ + if (copy_to_user((void __user *)arg, cmd, + sizeof(*cmd) - DDCB_ASIV_LENGTH)) { + ddcb_requ_free(cmd); + return -EFAULT; + } + + ddcb_requ_free(cmd); + return rc; +} + +/** + * genwqe_ioctl() - IO control + * @filp: file handle + * @cmd: command identifier (passed from user) + * @arg: argument (passed from user) + * + * Return: 0 success + */ +static long genwqe_ioctl(struct file *filp, unsigned int cmd, + unsigned long arg) +{ + int rc = 0; + struct genwqe_file *cfile = (struct genwqe_file *)filp->private_data; + struct genwqe_dev *cd = cfile->cd; + struct genwqe_reg_io __user *io; + u64 val; + u32 reg_offs; + + if (_IOC_TYPE(cmd) != GENWQE_IOC_CODE) + return -EINVAL; + + switch (cmd) { + + case GENWQE_GET_CARD_STATE: + put_user(cd->card_state, (enum genwqe_card_state __user *)arg); + return 0; + + /* Register access */ + case GENWQE_READ_REG64: { + io = (struct genwqe_reg_io __user *)arg; + + if (get_user(reg_offs, &io->num)) + return -EFAULT; + + if ((reg_offs >= cd->mmio_len) || (reg_offs & 0x7)) + return -EINVAL; + + val = __genwqe_readq(cd, reg_offs); + put_user(val, &io->val64); + return 0; + } + + case GENWQE_WRITE_REG64: { + io = (struct genwqe_reg_io __user *)arg; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if ((filp->f_flags & O_ACCMODE) == O_RDONLY) + return -EPERM; + + if (get_user(reg_offs, &io->num)) + return -EFAULT; + + if ((reg_offs >= cd->mmio_len) || (reg_offs & 0x7)) + return -EINVAL; + + if (get_user(val, &io->val64)) + return -EFAULT; + + __genwqe_writeq(cd, reg_offs, val); + return 0; + } + + case GENWQE_READ_REG32: { + io = (struct genwqe_reg_io __user *)arg; + + if (get_user(reg_offs, &io->num)) + return -EFAULT; + + if ((reg_offs >= cd->mmio_len) || (reg_offs & 0x3)) + return -EINVAL; + + val = __genwqe_readl(cd, reg_offs); + put_user(val, &io->val64); + return 0; + } + + case GENWQE_WRITE_REG32: { + io = (struct genwqe_reg_io __user *)arg; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if ((filp->f_flags & O_ACCMODE) == O_RDONLY) + return -EPERM; + + if (get_user(reg_offs, &io->num)) + return -EFAULT; + + if ((reg_offs >= cd->mmio_len) || (reg_offs & 0x3)) + return -EINVAL; + + if (get_user(val, &io->val64)) + return -EFAULT; + + __genwqe_writel(cd, reg_offs, val); + return 0; + } + + /* Flash update/reading */ + case GENWQE_SLU_UPDATE: { + struct genwqe_bitstream load; + + if (!genwqe_is_privileged(cd)) + return -EPERM; + + if ((filp->f_flags & O_ACCMODE) == O_RDONLY) + return -EPERM; + + if (copy_from_user(&load, (void __user *)arg, + sizeof(load))) + return -EFAULT; + + rc = do_flash_update(cfile, &load); + + if (copy_to_user((void __user *)arg, &load, sizeof(load))) + return -EFAULT; + + return rc; + } + + case GENWQE_SLU_READ: { + struct genwqe_bitstream load; + + if (!genwqe_is_privileged(cd)) + return -EPERM; + + if (genwqe_flash_readback_fails(cd)) + return -ENOSPC; /* known to fail for old versions */ + + if (copy_from_user(&load, (void __user *)arg, sizeof(load))) + return -EFAULT; + + rc = do_flash_read(cfile, &load); + + if (copy_to_user((void __user *)arg, &load, sizeof(load))) + return -EFAULT; + + return rc; + } + + /* memory pinning and unpinning */ + case GENWQE_PIN_MEM: { + struct genwqe_mem m; + + if (copy_from_user(&m, (void __user *)arg, sizeof(m))) + return -EFAULT; + + return genwqe_pin_mem(cfile, &m); + } + + case GENWQE_UNPIN_MEM: { + struct genwqe_mem m; + + if (copy_from_user(&m, (void __user *)arg, sizeof(m))) + return -EFAULT; + + return genwqe_unpin_mem(cfile, &m); + } + + /* launch an DDCB and wait for completion */ + case GENWQE_EXECUTE_DDCB: + return do_execute_ddcb(cfile, arg, 0); + + case GENWQE_EXECUTE_RAW_DDCB: { + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + return do_execute_ddcb(cfile, arg, 1); + } + + default: + return -EINVAL; + } + + return rc; +} + +#if defined(CONFIG_COMPAT) +/** + * genwqe_compat_ioctl() - Compatibility ioctl + * + * Called whenever a 32-bit process running under a 64-bit kernel + * performs an ioctl on /dev/genwqe<n>_card. + * + * @filp: file pointer. + * @cmd: command. + * @arg: user argument. + * Return: zero on success or negative number on failure. + */ +static long genwqe_compat_ioctl(struct file *filp, unsigned int cmd, + unsigned long arg) +{ + return genwqe_ioctl(filp, cmd, arg); +} +#endif /* defined(CONFIG_COMPAT) */ + +static const struct file_operations genwqe_fops = { + .owner = THIS_MODULE, + .open = genwqe_open, + .fasync = genwqe_fasync, + .mmap = genwqe_mmap, + .unlocked_ioctl = genwqe_ioctl, +#if defined(CONFIG_COMPAT) + .compat_ioctl = genwqe_compat_ioctl, +#endif + .release = genwqe_release, +}; + +static int genwqe_device_initialized(struct genwqe_dev *cd) +{ + return cd->dev != NULL; +} + +/** + * genwqe_device_create() - Create and configure genwqe char device + * @cd: genwqe device descriptor + * + * This function must be called before we create any more genwqe + * character devices, because it is allocating the major and minor + * number which are supposed to be used by the client drivers. + */ +int genwqe_device_create(struct genwqe_dev *cd) +{ + int rc; + struct pci_dev *pci_dev = cd->pci_dev; + + /* + * Here starts the individual setup per client. It must + * initialize its own cdev data structure with its own fops. + * The appropriate devnum needs to be created. The ranges must + * not overlap. + */ + rc = alloc_chrdev_region(&cd->devnum_genwqe, 0, + GENWQE_MAX_MINOR, GENWQE_DEVNAME); + if (rc < 0) { + dev_err(&pci_dev->dev, "err: alloc_chrdev_region failed\n"); + goto err_dev; + } + + cdev_init(&cd->cdev_genwqe, &genwqe_fops); + cd->cdev_genwqe.owner = THIS_MODULE; + + rc = cdev_add(&cd->cdev_genwqe, cd->devnum_genwqe, 1); + if (rc < 0) { + dev_err(&pci_dev->dev, "err: cdev_add failed\n"); + goto err_add; + } + + /* + * Finally the device in /dev/... must be created. The rule is + * to use card%d_clientname for each created device. + */ + cd->dev = device_create_with_groups(cd->class_genwqe, + &cd->pci_dev->dev, + cd->devnum_genwqe, cd, + genwqe_attribute_groups, + GENWQE_DEVNAME "%u_card", + cd->card_idx); + if (IS_ERR(cd->dev)) { + rc = PTR_ERR(cd->dev); + goto err_cdev; + } + + rc = genwqe_init_debugfs(cd); + if (rc != 0) + goto err_debugfs; + + return 0; + + err_debugfs: + device_destroy(cd->class_genwqe, cd->devnum_genwqe); + err_cdev: + cdev_del(&cd->cdev_genwqe); + err_add: + unregister_chrdev_region(cd->devnum_genwqe, GENWQE_MAX_MINOR); + err_dev: + cd->dev = NULL; + return rc; +} + +static int genwqe_inform_and_stop_processes(struct genwqe_dev *cd) +{ + int rc; + unsigned int i; + struct pci_dev *pci_dev = cd->pci_dev; + + if (!genwqe_open_files(cd)) + return 0; + + dev_warn(&pci_dev->dev, "[%s] send SIGIO and wait ...\n", __func__); + + rc = genwqe_kill_fasync(cd, SIGIO); + if (rc > 0) { + /* give kill_timeout seconds to close file descriptors ... */ + for (i = 0; (i < genwqe_kill_timeout) && + genwqe_open_files(cd); i++) { + dev_info(&pci_dev->dev, " %d sec ...", i); + + cond_resched(); + msleep(1000); + } + + /* if no open files we can safely continue, else ... */ + if (!genwqe_open_files(cd)) + return 0; + + dev_warn(&pci_dev->dev, + "[%s] send SIGKILL and wait ...\n", __func__); + + rc = genwqe_force_sig(cd, SIGKILL); /* force terminate */ + if (rc) { + /* Give kill_timout more seconds to end processes */ + for (i = 0; (i < genwqe_kill_timeout) && + genwqe_open_files(cd); i++) { + dev_warn(&pci_dev->dev, " %d sec ...", i); + + cond_resched(); + msleep(1000); + } + } + } + return 0; +} + +/** + * genwqe_device_remove() - Remove genwqe's char device + * + * This function must be called after the client devices are removed + * because it will free the major/minor number range for the genwqe + * drivers. + * + * This function must be robust enough to be called twice. + */ +int genwqe_device_remove(struct genwqe_dev *cd) +{ + int rc; + struct pci_dev *pci_dev = cd->pci_dev; + + if (!genwqe_device_initialized(cd)) + return 1; + + genwqe_inform_and_stop_processes(cd); + + /* + * We currently do wait until all filedescriptors are + * closed. This leads to a problem when we abort the + * application which will decrease this reference from + * 1/unused to 0/illegal and not from 2/used 1/empty. + */ + rc = atomic_read(&cd->cdev_genwqe.kobj.kref.refcount); + if (rc != 1) { + dev_err(&pci_dev->dev, + "[%s] err: cdev_genwqe...refcount=%d\n", __func__, rc); + panic("Fatal err: cannot free resources with pending references!"); + } + + genqwe_exit_debugfs(cd); + device_destroy(cd->class_genwqe, cd->devnum_genwqe); + cdev_del(&cd->cdev_genwqe); + unregister_chrdev_region(cd->devnum_genwqe, GENWQE_MAX_MINOR); + cd->dev = NULL; + + return 0; +} diff --git a/drivers/misc/genwqe/card_sysfs.c b/drivers/misc/genwqe/card_sysfs.c new file mode 100644 index 000000000000..a72a99266c3c --- /dev/null +++ b/drivers/misc/genwqe/card_sysfs.c @@ -0,0 +1,288 @@ +/** + * IBM Accelerator Family 'GenWQE' + * + * (C) Copyright IBM Corp. 2013 + * + * Author: Frank Haverkamp <haver@linux.vnet.ibm.com> + * Author: Joerg-Stephan Vogt <jsvogt@de.ibm.com> + * Author: Michael Jung <mijung@de.ibm.com> + * Author: Michael Ruettger <michael@ibmra.de> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +/* + * Sysfs interfaces for the GenWQE card. There are attributes to query + * the version of the bitstream as well as some for the driver. For + * debugging, please also see the debugfs interfaces of this driver. + */ + +#include <linux/version.h> +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/string.h> +#include <linux/fs.h> +#include <linux/sysfs.h> +#include <linux/ctype.h> +#include <linux/device.h> + +#include "card_base.h" +#include "card_ddcb.h" + +static const char * const genwqe_types[] = { + [GENWQE_TYPE_ALTERA_230] = "GenWQE4-230", + [GENWQE_TYPE_ALTERA_530] = "GenWQE4-530", + [GENWQE_TYPE_ALTERA_A4] = "GenWQE5-A4", + [GENWQE_TYPE_ALTERA_A7] = "GenWQE5-A7", +}; + +static ssize_t status_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct genwqe_dev *cd = dev_get_drvdata(dev); + const char *cs[GENWQE_CARD_STATE_MAX] = { "unused", "used", "error" }; + + return sprintf(buf, "%s\n", cs[cd->card_state]); +} +static DEVICE_ATTR_RO(status); + +static ssize_t appid_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + char app_name[5]; + struct genwqe_dev *cd = dev_get_drvdata(dev); + + genwqe_read_app_id(cd, app_name, sizeof(app_name)); + return sprintf(buf, "%s\n", app_name); +} +static DEVICE_ATTR_RO(appid); + +static ssize_t version_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + u64 slu_id, app_id; + struct genwqe_dev *cd = dev_get_drvdata(dev); + + slu_id = __genwqe_readq(cd, IO_SLU_UNITCFG); + app_id = __genwqe_readq(cd, IO_APP_UNITCFG); + + return sprintf(buf, "%016llx.%016llx\n", slu_id, app_id); +} +static DEVICE_ATTR_RO(version); + +static ssize_t type_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + u8 card_type; + struct genwqe_dev *cd = dev_get_drvdata(dev); + + card_type = genwqe_card_type(cd); + return sprintf(buf, "%s\n", (card_type >= ARRAY_SIZE(genwqe_types)) ? + "invalid" : genwqe_types[card_type]); +} +static DEVICE_ATTR_RO(type); + +static ssize_t driver_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + return sprintf(buf, "%s\n", DRV_VERS_STRING); +} +static DEVICE_ATTR_RO(driver); + +static ssize_t tempsens_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + u64 tempsens; + struct genwqe_dev *cd = dev_get_drvdata(dev); + + tempsens = __genwqe_readq(cd, IO_SLU_TEMPERATURE_SENSOR); + return sprintf(buf, "%016llx\n", tempsens); +} +static DEVICE_ATTR_RO(tempsens); + +static ssize_t freerunning_timer_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + u64 t; + struct genwqe_dev *cd = dev_get_drvdata(dev); + + t = __genwqe_readq(cd, IO_SLC_FREE_RUNNING_TIMER); + return sprintf(buf, "%016llx\n", t); +} +static DEVICE_ATTR_RO(freerunning_timer); + +static ssize_t queue_working_time_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + u64 t; + struct genwqe_dev *cd = dev_get_drvdata(dev); + + t = __genwqe_readq(cd, IO_SLC_QUEUE_WTIME); + return sprintf(buf, "%016llx\n", t); +} +static DEVICE_ATTR_RO(queue_working_time); + +static ssize_t base_clock_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + u64 base_clock; + struct genwqe_dev *cd = dev_get_drvdata(dev); + + base_clock = genwqe_base_clock_frequency(cd); + return sprintf(buf, "%lld\n", base_clock); +} +static DEVICE_ATTR_RO(base_clock); + +/** + * curr_bitstream_show() - Show the current bitstream id + * + * There is a bug in some old versions of the CPLD which selects the + * bitstream, which causes the IO_SLU_BITSTREAM register to report + * unreliable data in very rare cases. This makes this sysfs + * unreliable up to the point were a new CPLD version is being used. + * + * Unfortunately there is no automatic way yet to query the CPLD + * version, such that you need to manually ensure via programming + * tools that you have a recent version of the CPLD software. + * + * The proposed circumvention is to use a special recovery bitstream + * on the backup partition (0) to identify problems while loading the + * image. + */ +static ssize_t curr_bitstream_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + int curr_bitstream; + struct genwqe_dev *cd = dev_get_drvdata(dev); + + curr_bitstream = __genwqe_readq(cd, IO_SLU_BITSTREAM) & 0x1; + return sprintf(buf, "%d\n", curr_bitstream); +} +static DEVICE_ATTR_RO(curr_bitstream); + +/** + * next_bitstream_show() - Show the next activated bitstream + * + * IO_SLC_CFGREG_SOFTRESET: This register can only be accessed by the PF. + */ +static ssize_t next_bitstream_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + int next_bitstream; + struct genwqe_dev *cd = dev_get_drvdata(dev); + + switch ((cd->softreset & 0xc) >> 2) { + case 0x2: + next_bitstream = 0; + break; + case 0x3: + next_bitstream = 1; + break; + default: + next_bitstream = -1; + break; /* error */ + } + return sprintf(buf, "%d\n", next_bitstream); +} + +static ssize_t next_bitstream_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + int partition; + struct genwqe_dev *cd = dev_get_drvdata(dev); + + if (kstrtoint(buf, 0, &partition) < 0) + return -EINVAL; + + switch (partition) { + case 0x0: + cd->softreset = 0x78; + break; + case 0x1: + cd->softreset = 0x7c; + break; + default: + return -EINVAL; + } + + __genwqe_writeq(cd, IO_SLC_CFGREG_SOFTRESET, cd->softreset); + return count; +} +static DEVICE_ATTR_RW(next_bitstream); + +/* + * Create device_attribute structures / params: name, mode, show, store + * additional flag if valid in VF + */ +static struct attribute *genwqe_attributes[] = { + &dev_attr_tempsens.attr, + &dev_attr_next_bitstream.attr, + &dev_attr_curr_bitstream.attr, + &dev_attr_base_clock.attr, + &dev_attr_driver.attr, + &dev_attr_type.attr, + &dev_attr_version.attr, + &dev_attr_appid.attr, + &dev_attr_status.attr, + &dev_attr_freerunning_timer.attr, + &dev_attr_queue_working_time.attr, + NULL, +}; + +static struct attribute *genwqe_normal_attributes[] = { + &dev_attr_driver.attr, + &dev_attr_type.attr, + &dev_attr_version.attr, + &dev_attr_appid.attr, + &dev_attr_status.attr, + &dev_attr_freerunning_timer.attr, + &dev_attr_queue_working_time.attr, + NULL, +}; + +/** + * genwqe_is_visible() - Determine if sysfs attribute should be visible or not + * + * VFs have restricted mmio capabilities, so not all sysfs entries + * are allowed in VFs. + */ +static umode_t genwqe_is_visible(struct kobject *kobj, + struct attribute *attr, int n) +{ + unsigned int j; + struct device *dev = container_of(kobj, struct device, kobj); + struct genwqe_dev *cd = dev_get_drvdata(dev); + umode_t mode = attr->mode; + + if (genwqe_is_privileged(cd)) + return mode; + + for (j = 0; genwqe_normal_attributes[j] != NULL; j++) + if (genwqe_normal_attributes[j] == attr) + return mode; + + return 0; +} + +static struct attribute_group genwqe_attribute_group = { + .is_visible = genwqe_is_visible, + .attrs = genwqe_attributes, +}; + +const struct attribute_group *genwqe_attribute_groups[] = { + &genwqe_attribute_group, + NULL, +}; diff --git a/drivers/misc/genwqe/card_utils.c b/drivers/misc/genwqe/card_utils.c new file mode 100644 index 000000000000..6b1a6ef9f1a8 --- /dev/null +++ b/drivers/misc/genwqe/card_utils.c @@ -0,0 +1,944 @@ +/** + * IBM Accelerator Family 'GenWQE' + * + * (C) Copyright IBM Corp. 2013 + * + * Author: Frank Haverkamp <haver@linux.vnet.ibm.com> + * Author: Joerg-Stephan Vogt <jsvogt@de.ibm.com> + * Author: Michael Jung <mijung@de.ibm.com> + * Author: Michael Ruettger <michael@ibmra.de> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +/* + * Miscelanous functionality used in the other GenWQE driver parts. + */ + +#include <linux/kernel.h> +#include <linux/dma-mapping.h> +#include <linux/sched.h> +#include <linux/vmalloc.h> +#include <linux/page-flags.h> +#include <linux/scatterlist.h> +#include <linux/hugetlb.h> +#include <linux/iommu.h> +#include <linux/delay.h> +#include <linux/pci.h> +#include <linux/dma-mapping.h> +#include <linux/ctype.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/delay.h> +#include <asm/pgtable.h> + +#include "genwqe_driver.h" +#include "card_base.h" +#include "card_ddcb.h" + +/** + * __genwqe_writeq() - Write 64-bit register + * @cd: genwqe device descriptor + * @byte_offs: byte offset within BAR + * @val: 64-bit value + * + * Return: 0 if success; < 0 if error + */ +int __genwqe_writeq(struct genwqe_dev *cd, u64 byte_offs, u64 val) +{ + if (cd->err_inject & GENWQE_INJECT_HARDWARE_FAILURE) + return -EIO; + + if (cd->mmio == NULL) + return -EIO; + + __raw_writeq((__force u64)cpu_to_be64(val), cd->mmio + byte_offs); + return 0; +} + +/** + * __genwqe_readq() - Read 64-bit register + * @cd: genwqe device descriptor + * @byte_offs: offset within BAR + * + * Return: value from register + */ +u64 __genwqe_readq(struct genwqe_dev *cd, u64 byte_offs) +{ + if (cd->err_inject & GENWQE_INJECT_HARDWARE_FAILURE) + return 0xffffffffffffffffull; + + if ((cd->err_inject & GENWQE_INJECT_GFIR_FATAL) && + (byte_offs == IO_SLC_CFGREG_GFIR)) + return 0x000000000000ffffull; + + if ((cd->err_inject & GENWQE_INJECT_GFIR_INFO) && + (byte_offs == IO_SLC_CFGREG_GFIR)) + return 0x00000000ffff0000ull; + + if (cd->mmio == NULL) + return 0xffffffffffffffffull; + + return be64_to_cpu((__force __be64)__raw_readq(cd->mmio + byte_offs)); +} + +/** + * __genwqe_writel() - Write 32-bit register + * @cd: genwqe device descriptor + * @byte_offs: byte offset within BAR + * @val: 32-bit value + * + * Return: 0 if success; < 0 if error + */ +int __genwqe_writel(struct genwqe_dev *cd, u64 byte_offs, u32 val) +{ + if (cd->err_inject & GENWQE_INJECT_HARDWARE_FAILURE) + return -EIO; + + if (cd->mmio == NULL) + return -EIO; + + __raw_writel((__force u32)cpu_to_be32(val), cd->mmio + byte_offs); + return 0; +} + +/** + * __genwqe_readl() - Read 32-bit register + * @cd: genwqe device descriptor + * @byte_offs: offset within BAR + * + * Return: Value from register + */ +u32 __genwqe_readl(struct genwqe_dev *cd, u64 byte_offs) +{ + if (cd->err_inject & GENWQE_INJECT_HARDWARE_FAILURE) + return 0xffffffff; + + if (cd->mmio == NULL) + return 0xffffffff; + + return be32_to_cpu((__force __be32)__raw_readl(cd->mmio + byte_offs)); +} + +/** + * genwqe_read_app_id() - Extract app_id + * + * app_unitcfg need to be filled with valid data first + */ +int genwqe_read_app_id(struct genwqe_dev *cd, char *app_name, int len) +{ + int i, j; + u32 app_id = (u32)cd->app_unitcfg; + + memset(app_name, 0, len); + for (i = 0, j = 0; j < min(len, 4); j++) { + char ch = (char)((app_id >> (24 - j*8)) & 0xff); + if (ch == ' ') + continue; + app_name[i++] = isprint(ch) ? ch : 'X'; + } + return i; +} + +/** + * genwqe_init_crc32() - Prepare a lookup table for fast crc32 calculations + * + * Existing kernel functions seem to use a different polynom, + * therefore we could not use them here. + * + * Genwqe's Polynomial = 0x20044009 + */ +#define CRC32_POLYNOMIAL 0x20044009 +static u32 crc32_tab[256]; /* crc32 lookup table */ + +void genwqe_init_crc32(void) +{ + int i, j; + u32 crc; + + for (i = 0; i < 256; i++) { + crc = i << 24; + for (j = 0; j < 8; j++) { + if (crc & 0x80000000) + crc = (crc << 1) ^ CRC32_POLYNOMIAL; + else + crc = (crc << 1); + } + crc32_tab[i] = crc; + } +} + +/** + * genwqe_crc32() - Generate 32-bit crc as required for DDCBs + * @buff: pointer to data buffer + * @len: length of data for calculation + * @init: initial crc (0xffffffff at start) + * + * polynomial = x^32 * + x^29 + x^18 + x^14 + x^3 + 1 (0x20044009) + + * Example: 4 bytes 0x01 0x02 0x03 0x04 with init=0xffffffff should + * result in a crc32 of 0xf33cb7d3. + * + * The existing kernel crc functions did not cover this polynom yet. + * + * Return: crc32 checksum. + */ +u32 genwqe_crc32(u8 *buff, size_t len, u32 init) +{ + int i; + u32 crc; + + crc = init; + while (len--) { + i = ((crc >> 24) ^ *buff++) & 0xFF; + crc = (crc << 8) ^ crc32_tab[i]; + } + return crc; +} + +void *__genwqe_alloc_consistent(struct genwqe_dev *cd, size_t size, + dma_addr_t *dma_handle) +{ + if (get_order(size) > MAX_ORDER) + return NULL; + + return pci_alloc_consistent(cd->pci_dev, size, dma_handle); +} + +void __genwqe_free_consistent(struct genwqe_dev *cd, size_t size, + void *vaddr, dma_addr_t dma_handle) +{ + if (vaddr == NULL) + return; + + pci_free_consistent(cd->pci_dev, size, vaddr, dma_handle); +} + +static void genwqe_unmap_pages(struct genwqe_dev *cd, dma_addr_t *dma_list, + int num_pages) +{ + int i; + struct pci_dev *pci_dev = cd->pci_dev; + + for (i = 0; (i < num_pages) && (dma_list[i] != 0x0); i++) { + pci_unmap_page(pci_dev, dma_list[i], + PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); + dma_list[i] = 0x0; + } +} + +static int genwqe_map_pages(struct genwqe_dev *cd, + struct page **page_list, int num_pages, + dma_addr_t *dma_list) +{ + int i; + struct pci_dev *pci_dev = cd->pci_dev; + + /* establish DMA mapping for requested pages */ + for (i = 0; i < num_pages; i++) { + dma_addr_t daddr; + + dma_list[i] = 0x0; + daddr = pci_map_page(pci_dev, page_list[i], + 0, /* map_offs */ + PAGE_SIZE, + PCI_DMA_BIDIRECTIONAL); /* FIXME rd/rw */ + + if (pci_dma_mapping_error(pci_dev, daddr)) { + dev_err(&pci_dev->dev, + "[%s] err: no dma addr daddr=%016llx!\n", + __func__, (long long)daddr); + goto err; + } + + dma_list[i] = daddr; + } + return 0; + + err: + genwqe_unmap_pages(cd, dma_list, num_pages); + return -EIO; +} + +static int genwqe_sgl_size(int num_pages) +{ + int len, num_tlb = num_pages / 7; + + len = sizeof(struct sg_entry) * (num_pages+num_tlb + 1); + return roundup(len, PAGE_SIZE); +} + +struct sg_entry *genwqe_alloc_sgl(struct genwqe_dev *cd, int num_pages, + dma_addr_t *dma_addr, size_t *sgl_size) +{ + struct pci_dev *pci_dev = cd->pci_dev; + struct sg_entry *sgl; + + *sgl_size = genwqe_sgl_size(num_pages); + if (get_order(*sgl_size) > MAX_ORDER) { + dev_err(&pci_dev->dev, + "[%s] err: too much memory requested!\n", __func__); + return NULL; + } + + sgl = __genwqe_alloc_consistent(cd, *sgl_size, dma_addr); + if (sgl == NULL) { + dev_err(&pci_dev->dev, + "[%s] err: no memory available!\n", __func__); + return NULL; + } + + return sgl; +} + +int genwqe_setup_sgl(struct genwqe_dev *cd, + unsigned long offs, + unsigned long size, + struct sg_entry *sgl, + dma_addr_t dma_addr, size_t sgl_size, + dma_addr_t *dma_list, int page_offs, int num_pages) +{ + int i = 0, j = 0, p; + unsigned long dma_offs, map_offs; + struct pci_dev *pci_dev = cd->pci_dev; + dma_addr_t prev_daddr = 0; + struct sg_entry *s, *last_s = NULL; + + /* sanity checks */ + if (offs > PAGE_SIZE) { + dev_err(&pci_dev->dev, + "[%s] too large start offs %08lx\n", __func__, offs); + return -EFAULT; + } + if (sgl_size < genwqe_sgl_size(num_pages)) { + dev_err(&pci_dev->dev, + "[%s] sgl_size too small %08lx for %d pages\n", + __func__, sgl_size, num_pages); + return -EFAULT; + } + + dma_offs = 128; /* next block if needed/dma_offset */ + map_offs = offs; /* offset in first page */ + + s = &sgl[0]; /* first set of 8 entries */ + p = 0; /* page */ + while (p < num_pages) { + dma_addr_t daddr; + unsigned int size_to_map; + + /* always write the chaining entry, cleanup is done later */ + j = 0; + s[j].target_addr = cpu_to_be64(dma_addr + dma_offs); + s[j].len = cpu_to_be32(128); + s[j].flags = cpu_to_be32(SG_CHAINED); + j++; + + while (j < 8) { + /* DMA mapping for requested page, offs, size */ + size_to_map = min(size, PAGE_SIZE - map_offs); + daddr = dma_list[page_offs + p] + map_offs; + size -= size_to_map; + map_offs = 0; + + if (prev_daddr == daddr) { + u32 prev_len = be32_to_cpu(last_s->len); + + /* pr_info("daddr combining: " + "%016llx/%08x -> %016llx\n", + prev_daddr, prev_len, daddr); */ + + last_s->len = cpu_to_be32(prev_len + + size_to_map); + + p++; /* process next page */ + if (p == num_pages) + goto fixup; /* nothing to do */ + + prev_daddr = daddr + size_to_map; + continue; + } + + /* start new entry */ + s[j].target_addr = cpu_to_be64(daddr); + s[j].len = cpu_to_be32(size_to_map); + s[j].flags = cpu_to_be32(SG_DATA); + prev_daddr = daddr + size_to_map; + last_s = &s[j]; + j++; + + p++; /* process next page */ + if (p == num_pages) + goto fixup; /* nothing to do */ + } + dma_offs += 128; + s += 8; /* continue 8 elements further */ + } + fixup: + if (j == 1) { /* combining happend on last entry! */ + s -= 8; /* full shift needed on previous sgl block */ + j = 7; /* shift all elements */ + } + + for (i = 0; i < j; i++) /* move elements 1 up */ + s[i] = s[i + 1]; + + s[i].target_addr = cpu_to_be64(0); + s[i].len = cpu_to_be32(0); + s[i].flags = cpu_to_be32(SG_END_LIST); + return 0; +} + +void genwqe_free_sgl(struct genwqe_dev *cd, struct sg_entry *sg_list, + dma_addr_t dma_addr, size_t size) +{ + __genwqe_free_consistent(cd, size, sg_list, dma_addr); +} + +/** + * free_user_pages() - Give pinned pages back + * + * Documentation of get_user_pages is in mm/memory.c: + * + * If the page is written to, set_page_dirty (or set_page_dirty_lock, + * as appropriate) must be called after the page is finished with, and + * before put_page is called. + * + * FIXME Could be of use to others and might belong in the generic + * code, if others agree. E.g. + * ll_free_user_pages in drivers/staging/lustre/lustre/llite/rw26.c + * ceph_put_page_vector in net/ceph/pagevec.c + * maybe more? + */ +static int free_user_pages(struct page **page_list, unsigned int nr_pages, + int dirty) +{ + unsigned int i; + + for (i = 0; i < nr_pages; i++) { + if (page_list[i] != NULL) { + if (dirty) + set_page_dirty_lock(page_list[i]); + put_page(page_list[i]); + } + } + return 0; +} + +/** + * genwqe_user_vmap() - Map user-space memory to virtual kernel memory + * @cd: pointer to genwqe device + * @m: mapping params + * @uaddr: user virtual address + * @size: size of memory to be mapped + * + * We need to think about how we could speed this up. Of course it is + * not a good idea to do this over and over again, like we are + * currently doing it. Nevertheless, I am curious where on the path + * the performance is spend. Most probably within the memory + * allocation functions, but maybe also in the DMA mapping code. + * + * Restrictions: The maximum size of the possible mapping currently depends + * on the amount of memory we can get using kzalloc() for the + * page_list and pci_alloc_consistent for the sg_list. + * The sg_list is currently itself not scattered, which could + * be fixed with some effort. The page_list must be split into + * PAGE_SIZE chunks too. All that will make the complicated + * code more complicated. + * + * Return: 0 if success + */ +int genwqe_user_vmap(struct genwqe_dev *cd, struct dma_mapping *m, void *uaddr, + unsigned long size, struct ddcb_requ *req) +{ + int rc = -EINVAL; + unsigned long data, offs; + struct pci_dev *pci_dev = cd->pci_dev; + + if ((uaddr == NULL) || (size == 0)) { + m->size = 0; /* mark unused and not added */ + return -EINVAL; + } + m->u_vaddr = uaddr; + m->size = size; + + /* determine space needed for page_list. */ + data = (unsigned long)uaddr; + offs = offset_in_page(data); + m->nr_pages = DIV_ROUND_UP(offs + size, PAGE_SIZE); + + m->page_list = kcalloc(m->nr_pages, + sizeof(struct page *) + sizeof(dma_addr_t), + GFP_KERNEL); + if (!m->page_list) { + dev_err(&pci_dev->dev, "err: alloc page_list failed\n"); + m->nr_pages = 0; + m->u_vaddr = NULL; + m->size = 0; /* mark unused and not added */ + return -ENOMEM; + } + m->dma_list = (dma_addr_t *)(m->page_list + m->nr_pages); + + /* pin user pages in memory */ + rc = get_user_pages_fast(data & PAGE_MASK, /* page aligned addr */ + m->nr_pages, + 1, /* write by caller */ + m->page_list); /* ptrs to pages */ + + /* assumption: get_user_pages can be killed by signals. */ + if (rc < m->nr_pages) { + free_user_pages(m->page_list, rc, 0); + rc = -EFAULT; + goto fail_get_user_pages; + } + + rc = genwqe_map_pages(cd, m->page_list, m->nr_pages, m->dma_list); + if (rc != 0) + goto fail_free_user_pages; + + return 0; + + fail_free_user_pages: + free_user_pages(m->page_list, m->nr_pages, 0); + + fail_get_user_pages: + kfree(m->page_list); + m->page_list = NULL; + m->dma_list = NULL; + m->nr_pages = 0; + m->u_vaddr = NULL; + m->size = 0; /* mark unused and not added */ + return rc; +} + +/** + * genwqe_user_vunmap() - Undo mapping of user-space mem to virtual kernel + * memory + * @cd: pointer to genwqe device + * @m: mapping params + */ +int genwqe_user_vunmap(struct genwqe_dev *cd, struct dma_mapping *m, + struct ddcb_requ *req) +{ + struct pci_dev *pci_dev = cd->pci_dev; + + if (!dma_mapping_used(m)) { + dev_err(&pci_dev->dev, "[%s] err: mapping %p not used!\n", + __func__, m); + return -EINVAL; + } + + if (m->dma_list) + genwqe_unmap_pages(cd, m->dma_list, m->nr_pages); + + if (m->page_list) { + free_user_pages(m->page_list, m->nr_pages, 1); + + kfree(m->page_list); + m->page_list = NULL; + m->dma_list = NULL; + m->nr_pages = 0; + } + + m->u_vaddr = NULL; + m->size = 0; /* mark as unused and not added */ + return 0; +} + +/** + * genwqe_card_type() - Get chip type SLU Configuration Register + * @cd: pointer to the genwqe device descriptor + * Return: 0: Altera Stratix-IV 230 + * 1: Altera Stratix-IV 530 + * 2: Altera Stratix-V A4 + * 3: Altera Stratix-V A7 + */ +u8 genwqe_card_type(struct genwqe_dev *cd) +{ + u64 card_type = cd->slu_unitcfg; + return (u8)((card_type & IO_SLU_UNITCFG_TYPE_MASK) >> 20); +} + +/** + * genwqe_card_reset() - Reset the card + * @cd: pointer to the genwqe device descriptor + */ +int genwqe_card_reset(struct genwqe_dev *cd) +{ + u64 softrst; + struct pci_dev *pci_dev = cd->pci_dev; + + if (!genwqe_is_privileged(cd)) + return -ENODEV; + + /* new SL */ + __genwqe_writeq(cd, IO_SLC_CFGREG_SOFTRESET, 0x1ull); + msleep(1000); + __genwqe_readq(cd, IO_HSU_FIR_CLR); + __genwqe_readq(cd, IO_APP_FIR_CLR); + __genwqe_readq(cd, IO_SLU_FIR_CLR); + + /* + * Read-modify-write to preserve the stealth bits + * + * For SL >= 039, Stealth WE bit allows removing + * the read-modify-wrote. + * r-m-w may require a mask 0x3C to avoid hitting hard + * reset again for error reset (should be 0, chicken). + */ + softrst = __genwqe_readq(cd, IO_SLC_CFGREG_SOFTRESET) & 0x3cull; + __genwqe_writeq(cd, IO_SLC_CFGREG_SOFTRESET, softrst | 0x2ull); + + /* give ERRORRESET some time to finish */ + msleep(50); + + if (genwqe_need_err_masking(cd)) { + dev_info(&pci_dev->dev, + "[%s] masking errors for old bitstreams\n", __func__); + __genwqe_writeq(cd, IO_SLC_MISC_DEBUG, 0x0aull); + } + return 0; +} + +int genwqe_read_softreset(struct genwqe_dev *cd) +{ + u64 bitstream; + + if (!genwqe_is_privileged(cd)) + return -ENODEV; + + bitstream = __genwqe_readq(cd, IO_SLU_BITSTREAM) & 0x1; + cd->softreset = (bitstream == 0) ? 0x8ull : 0xcull; + return 0; +} + +/** + * genwqe_set_interrupt_capability() - Configure MSI capability structure + * @cd: pointer to the device + * Return: 0 if no error + */ +int genwqe_set_interrupt_capability(struct genwqe_dev *cd, int count) +{ + int rc; + struct pci_dev *pci_dev = cd->pci_dev; + + rc = pci_enable_msi_block(pci_dev, count); + if (rc == 0) + cd->flags |= GENWQE_FLAG_MSI_ENABLED; + return rc; +} + +/** + * genwqe_reset_interrupt_capability() - Undo genwqe_set_interrupt_capability() + * @cd: pointer to the device + */ +void genwqe_reset_interrupt_capability(struct genwqe_dev *cd) +{ + struct pci_dev *pci_dev = cd->pci_dev; + + if (cd->flags & GENWQE_FLAG_MSI_ENABLED) { + pci_disable_msi(pci_dev); + cd->flags &= ~GENWQE_FLAG_MSI_ENABLED; + } +} + +/** + * set_reg_idx() - Fill array with data. Ignore illegal offsets. + * @cd: card device + * @r: debug register array + * @i: index to desired entry + * @m: maximum possible entries + * @addr: addr which is read + * @index: index in debug array + * @val: read value + */ +static int set_reg_idx(struct genwqe_dev *cd, struct genwqe_reg *r, + unsigned int *i, unsigned int m, u32 addr, u32 idx, + u64 val) +{ + if (WARN_ON_ONCE(*i >= m)) + return -EFAULT; + + r[*i].addr = addr; + r[*i].idx = idx; + r[*i].val = val; + ++*i; + return 0; +} + +static int set_reg(struct genwqe_dev *cd, struct genwqe_reg *r, + unsigned int *i, unsigned int m, u32 addr, u64 val) +{ + return set_reg_idx(cd, r, i, m, addr, 0, val); +} + +int genwqe_read_ffdc_regs(struct genwqe_dev *cd, struct genwqe_reg *regs, + unsigned int max_regs, int all) +{ + unsigned int i, j, idx = 0; + u32 ufir_addr, ufec_addr, sfir_addr, sfec_addr; + u64 gfir, sluid, appid, ufir, ufec, sfir, sfec; + + /* Global FIR */ + gfir = __genwqe_readq(cd, IO_SLC_CFGREG_GFIR); + set_reg(cd, regs, &idx, max_regs, IO_SLC_CFGREG_GFIR, gfir); + + /* UnitCfg for SLU */ + sluid = __genwqe_readq(cd, IO_SLU_UNITCFG); /* 0x00000000 */ + set_reg(cd, regs, &idx, max_regs, IO_SLU_UNITCFG, sluid); + + /* UnitCfg for APP */ + appid = __genwqe_readq(cd, IO_APP_UNITCFG); /* 0x02000000 */ + set_reg(cd, regs, &idx, max_regs, IO_APP_UNITCFG, appid); + + /* Check all chip Units */ + for (i = 0; i < GENWQE_MAX_UNITS; i++) { + + /* Unit FIR */ + ufir_addr = (i << 24) | 0x008; + ufir = __genwqe_readq(cd, ufir_addr); + set_reg(cd, regs, &idx, max_regs, ufir_addr, ufir); + + /* Unit FEC */ + ufec_addr = (i << 24) | 0x018; + ufec = __genwqe_readq(cd, ufec_addr); + set_reg(cd, regs, &idx, max_regs, ufec_addr, ufec); + + for (j = 0; j < 64; j++) { + /* wherever there is a primary 1, read the 2ndary */ + if (!all && (!(ufir & (1ull << j)))) + continue; + + sfir_addr = (i << 24) | (0x100 + 8 * j); + sfir = __genwqe_readq(cd, sfir_addr); + set_reg(cd, regs, &idx, max_regs, sfir_addr, sfir); + + sfec_addr = (i << 24) | (0x300 + 8 * j); + sfec = __genwqe_readq(cd, sfec_addr); + set_reg(cd, regs, &idx, max_regs, sfec_addr, sfec); + } + } + + /* fill with invalid data until end */ + for (i = idx; i < max_regs; i++) { + regs[i].addr = 0xffffffff; + regs[i].val = 0xffffffffffffffffull; + } + return idx; +} + +/** + * genwqe_ffdc_buff_size() - Calculates the number of dump registers + */ +int genwqe_ffdc_buff_size(struct genwqe_dev *cd, int uid) +{ + int entries = 0, ring, traps, traces, trace_entries; + u32 eevptr_addr, l_addr, d_len, d_type; + u64 eevptr, val, addr; + + eevptr_addr = GENWQE_UID_OFFS(uid) | IO_EXTENDED_ERROR_POINTER; + eevptr = __genwqe_readq(cd, eevptr_addr); + + if ((eevptr != 0x0) && (eevptr != -1ull)) { + l_addr = GENWQE_UID_OFFS(uid) | eevptr; + + while (1) { + val = __genwqe_readq(cd, l_addr); + + if ((val == 0x0) || (val == -1ull)) + break; + + /* 38:24 */ + d_len = (val & 0x0000007fff000000ull) >> 24; + + /* 39 */ + d_type = (val & 0x0000008000000000ull) >> 36; + + if (d_type) { /* repeat */ + entries += d_len; + } else { /* size in bytes! */ + entries += d_len >> 3; + } + + l_addr += 8; + } + } + + for (ring = 0; ring < 8; ring++) { + addr = GENWQE_UID_OFFS(uid) | IO_EXTENDED_DIAG_MAP(ring); + val = __genwqe_readq(cd, addr); + + if ((val == 0x0ull) || (val == -1ull)) + continue; + + traps = (val >> 24) & 0xff; + traces = (val >> 16) & 0xff; + trace_entries = val & 0xffff; + + entries += traps + (traces * trace_entries); + } + return entries; +} + +/** + * genwqe_ffdc_buff_read() - Implements LogoutExtendedErrorRegisters procedure + */ +int genwqe_ffdc_buff_read(struct genwqe_dev *cd, int uid, + struct genwqe_reg *regs, unsigned int max_regs) +{ + int i, traps, traces, trace, trace_entries, trace_entry, ring; + unsigned int idx = 0; + u32 eevptr_addr, l_addr, d_addr, d_len, d_type; + u64 eevptr, e, val, addr; + + eevptr_addr = GENWQE_UID_OFFS(uid) | IO_EXTENDED_ERROR_POINTER; + eevptr = __genwqe_readq(cd, eevptr_addr); + + if ((eevptr != 0x0) && (eevptr != 0xffffffffffffffffull)) { + l_addr = GENWQE_UID_OFFS(uid) | eevptr; + while (1) { + e = __genwqe_readq(cd, l_addr); + if ((e == 0x0) || (e == 0xffffffffffffffffull)) + break; + + d_addr = (e & 0x0000000000ffffffull); /* 23:0 */ + d_len = (e & 0x0000007fff000000ull) >> 24; /* 38:24 */ + d_type = (e & 0x0000008000000000ull) >> 36; /* 39 */ + d_addr |= GENWQE_UID_OFFS(uid); + + if (d_type) { + for (i = 0; i < (int)d_len; i++) { + val = __genwqe_readq(cd, d_addr); + set_reg_idx(cd, regs, &idx, max_regs, + d_addr, i, val); + } + } else { + d_len >>= 3; /* Size in bytes! */ + for (i = 0; i < (int)d_len; i++, d_addr += 8) { + val = __genwqe_readq(cd, d_addr); + set_reg_idx(cd, regs, &idx, max_regs, + d_addr, 0, val); + } + } + l_addr += 8; + } + } + + /* + * To save time, there are only 6 traces poplulated on Uid=2, + * Ring=1. each with iters=512. + */ + for (ring = 0; ring < 8; ring++) { /* 0 is fls, 1 is fds, + 2...7 are ASI rings */ + addr = GENWQE_UID_OFFS(uid) | IO_EXTENDED_DIAG_MAP(ring); + val = __genwqe_readq(cd, addr); + + if ((val == 0x0ull) || (val == -1ull)) + continue; + + traps = (val >> 24) & 0xff; /* Number of Traps */ + traces = (val >> 16) & 0xff; /* Number of Traces */ + trace_entries = val & 0xffff; /* Entries per trace */ + + /* Note: This is a combined loop that dumps both the traps */ + /* (for the trace == 0 case) as well as the traces 1 to */ + /* 'traces'. */ + for (trace = 0; trace <= traces; trace++) { + u32 diag_sel = + GENWQE_EXTENDED_DIAG_SELECTOR(ring, trace); + + addr = (GENWQE_UID_OFFS(uid) | + IO_EXTENDED_DIAG_SELECTOR); + __genwqe_writeq(cd, addr, diag_sel); + + for (trace_entry = 0; + trace_entry < (trace ? trace_entries : traps); + trace_entry++) { + addr = (GENWQE_UID_OFFS(uid) | + IO_EXTENDED_DIAG_READ_MBX); + val = __genwqe_readq(cd, addr); + set_reg_idx(cd, regs, &idx, max_regs, addr, + (diag_sel<<16) | trace_entry, val); + } + } + } + return 0; +} + +/** + * genwqe_write_vreg() - Write register in virtual window + * + * Note, these registers are only accessible to the PF through the + * VF-window. It is not intended for the VF to access. + */ +int genwqe_write_vreg(struct genwqe_dev *cd, u32 reg, u64 val, int func) +{ + __genwqe_writeq(cd, IO_PF_SLC_VIRTUAL_WINDOW, func & 0xf); + __genwqe_writeq(cd, reg, val); + return 0; +} + +/** + * genwqe_read_vreg() - Read register in virtual window + * + * Note, these registers are only accessible to the PF through the + * VF-window. It is not intended for the VF to access. + */ +u64 genwqe_read_vreg(struct genwqe_dev *cd, u32 reg, int func) +{ + __genwqe_writeq(cd, IO_PF_SLC_VIRTUAL_WINDOW, func & 0xf); + return __genwqe_readq(cd, reg); +} + +/** + * genwqe_base_clock_frequency() - Deteremine base clock frequency of the card + * + * Note: From a design perspective it turned out to be a bad idea to + * use codes here to specifiy the frequency/speed values. An old + * driver cannot understand new codes and is therefore always a + * problem. Better is to measure out the value or put the + * speed/frequency directly into a register which is always a valid + * value for old as well as for new software. + * + * Return: Card clock in MHz + */ +int genwqe_base_clock_frequency(struct genwqe_dev *cd) +{ + u16 speed; /* MHz MHz MHz MHz */ + static const int speed_grade[] = { 250, 200, 166, 175 }; + + speed = (u16)((cd->slu_unitcfg >> 28) & 0x0full); + if (speed >= ARRAY_SIZE(speed_grade)) + return 0; /* illegal value */ + + return speed_grade[speed]; +} + +/** + * genwqe_stop_traps() - Stop traps + * + * Before reading out the analysis data, we need to stop the traps. + */ +void genwqe_stop_traps(struct genwqe_dev *cd) +{ + __genwqe_writeq(cd, IO_SLC_MISC_DEBUG_SET, 0xcull); +} + +/** + * genwqe_start_traps() - Start traps + * + * After having read the data, we can/must enable the traps again. + */ +void genwqe_start_traps(struct genwqe_dev *cd) +{ + __genwqe_writeq(cd, IO_SLC_MISC_DEBUG_CLR, 0xcull); + + if (genwqe_need_err_masking(cd)) + __genwqe_writeq(cd, IO_SLC_MISC_DEBUG, 0x0aull); +} diff --git a/drivers/misc/genwqe/genwqe_driver.h b/drivers/misc/genwqe/genwqe_driver.h new file mode 100644 index 000000000000..46e916b36c70 --- /dev/null +++ b/drivers/misc/genwqe/genwqe_driver.h @@ -0,0 +1,77 @@ +#ifndef __GENWQE_DRIVER_H__ +#define __GENWQE_DRIVER_H__ + +/** + * IBM Accelerator Family 'GenWQE' + * + * (C) Copyright IBM Corp. 2013 + * + * Author: Frank Haverkamp <haver@linux.vnet.ibm.com> + * Author: Joerg-Stephan Vogt <jsvogt@de.ibm.com> + * Author: Michael Jung <mijung@de.ibm.com> + * Author: Michael Ruettger <michael@ibmra.de> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/types.h> +#include <linux/stddef.h> +#include <linux/cdev.h> +#include <linux/list.h> +#include <linux/kthread.h> +#include <linux/scatterlist.h> +#include <linux/iommu.h> +#include <linux/spinlock.h> +#include <linux/mutex.h> +#include <linux/platform_device.h> +#include <linux/printk.h> + +#include <asm/byteorder.h> +#include <linux/genwqe/genwqe_card.h> + +#define DRV_VERS_STRING "2.0.0" + +/* + * Static minor number assignement, until we decide/implement + * something dynamic. + */ +#define GENWQE_MAX_MINOR 128 /* up to 128 possible genwqe devices */ + +/** + * genwqe_requ_alloc() - Allocate a new DDCB execution request + * + * This data structure contains the user visiable fields of the DDCB + * to be executed. + * + * Return: ptr to genwqe_ddcb_cmd data structure + */ +struct genwqe_ddcb_cmd *ddcb_requ_alloc(void); + +/** + * ddcb_requ_free() - Free DDCB execution request. + * @req: ptr to genwqe_ddcb_cmd data structure. + */ +void ddcb_requ_free(struct genwqe_ddcb_cmd *req); + +u32 genwqe_crc32(u8 *buff, size_t len, u32 init); + +static inline void genwqe_hexdump(struct pci_dev *pci_dev, + const void *buff, unsigned int size) +{ + char prefix[32]; + + scnprintf(prefix, sizeof(prefix), "%s %s: ", + GENWQE_DEVNAME, pci_name(pci_dev)); + + print_hex_dump_debug(prefix, DUMP_PREFIX_OFFSET, 16, 1, buff, + size, true); +} + +#endif /* __GENWQE_DRIVER_H__ */ diff --git a/drivers/misc/ibmasm/module.c b/drivers/misc/ibmasm/module.c index 0346d87c5fed..6b3bf9ab051d 100644 --- a/drivers/misc/ibmasm/module.c +++ b/drivers/misc/ibmasm/module.c @@ -153,7 +153,6 @@ error_ioremap: error_heartbeat: ibmasm_event_buffer_exit(sp); error_eventbuffer: - pci_set_drvdata(pdev, NULL); kfree(sp); error_kmalloc: pci_release_regions(pdev); @@ -165,7 +164,7 @@ error_resources: static void ibmasm_remove_one(struct pci_dev *pdev) { - struct service_processor *sp = (struct service_processor *)pci_get_drvdata(pdev); + struct service_processor *sp = pci_get_drvdata(pdev); dbg("Unregistering UART\n"); ibmasm_unregister_uart(sp); @@ -182,7 +181,6 @@ static void ibmasm_remove_one(struct pci_dev *pdev) ibmasm_free_remote_input_dev(sp); iounmap(sp->base_address); ibmasm_event_buffer_exit(sp); - pci_set_drvdata(pdev, NULL); kfree(sp); pci_release_regions(pdev); pci_disable_device(pdev); diff --git a/drivers/misc/lkdtm.c b/drivers/misc/lkdtm.c index 2fc0586ce3bb..49c7a23f02fc 100644 --- a/drivers/misc/lkdtm.c +++ b/drivers/misc/lkdtm.c @@ -44,13 +44,25 @@ #include <scsi/scsi_cmnd.h> #include <linux/debugfs.h> #include <linux/vmalloc.h> +#include <linux/mman.h> #ifdef CONFIG_IDE #include <linux/ide.h> #endif +/* + * Make sure our attempts to over run the kernel stack doesn't trigger + * a compiler warning when CONFIG_FRAME_WARN is set. Then make sure we + * recurse past the end of THREAD_SIZE by default. + */ +#if defined(CONFIG_FRAME_WARN) && (CONFIG_FRAME_WARN > 0) +#define REC_STACK_SIZE (CONFIG_FRAME_WARN / 2) +#else +#define REC_STACK_SIZE (THREAD_SIZE / 8) +#endif +#define REC_NUM_DEFAULT ((THREAD_SIZE / REC_STACK_SIZE) * 2) + #define DEFAULT_COUNT 10 -#define REC_NUM_DEFAULT 10 #define EXEC_SIZE 64 enum cname { @@ -86,6 +98,9 @@ enum ctype { CT_EXEC_STACK, CT_EXEC_KMALLOC, CT_EXEC_VMALLOC, + CT_EXEC_USERSPACE, + CT_ACCESS_USERSPACE, + CT_WRITE_RO, }; static char* cp_name[] = { @@ -119,6 +134,9 @@ static char* cp_type[] = { "EXEC_STACK", "EXEC_KMALLOC", "EXEC_VMALLOC", + "EXEC_USERSPACE", + "ACCESS_USERSPACE", + "WRITE_RO", }; static struct jprobe lkdtm; @@ -139,9 +157,10 @@ static DEFINE_SPINLOCK(lock_me_up); static u8 data_area[EXEC_SIZE]; +static const unsigned long rodata = 0xAA55AA55; + module_param(recur_count, int, 0644); -MODULE_PARM_DESC(recur_count, " Recursion level for the stack overflow test, "\ - "default is 10"); +MODULE_PARM_DESC(recur_count, " Recursion level for the stack overflow test"); module_param(cpoint_name, charp, 0444); MODULE_PARM_DESC(cpoint_name, " Crash Point, where kernel is to be crashed"); module_param(cpoint_type, charp, 0444); @@ -205,7 +224,7 @@ static int jp_scsi_dispatch_cmd(struct scsi_cmnd *cmd) } #ifdef CONFIG_IDE -int jp_generic_ide_ioctl(ide_drive_t *drive, struct file *file, +static int jp_generic_ide_ioctl(ide_drive_t *drive, struct file *file, struct block_device *bdev, unsigned int cmd, unsigned long arg) { @@ -280,16 +299,16 @@ static int lkdtm_parse_commandline(void) return -EINVAL; } -static int recursive_loop(int a) +static int recursive_loop(int remaining) { - char buf[1024]; + char buf[REC_STACK_SIZE]; - memset(buf,0xFF,1024); - recur_count--; - if (!recur_count) + /* Make sure compiler does not optimize this away. */ + memset(buf, (remaining & 0xff) | 0x1, REC_STACK_SIZE); + if (!remaining) return 0; else - return recursive_loop(a); + return recursive_loop(remaining - 1); } static void do_nothing(void) @@ -297,6 +316,14 @@ static void do_nothing(void) return; } +static noinline void corrupt_stack(void) +{ + /* Use default char array length that triggers stack protection. */ + char data[8]; + + memset((void *)data, 0, 64); +} + static void execute_location(void *dst) { void (*func)(void) = dst; @@ -305,6 +332,16 @@ static void execute_location(void *dst) func(); } +static void execute_user_location(void *dst) +{ + /* Intentionally crossing kernel/user memory boundary. */ + void (*func)(void) = dst; + + if (copy_to_user((void __user *)dst, do_nothing, EXEC_SIZE)) + return; + func(); +} + static void lkdtm_do_action(enum ctype which) { switch (which) { @@ -325,15 +362,11 @@ static void lkdtm_do_action(enum ctype which) ; break; case CT_OVERFLOW: - (void) recursive_loop(0); + (void) recursive_loop(recur_count); break; - case CT_CORRUPT_STACK: { - /* Make sure the compiler creates and uses an 8 char array. */ - volatile char data[8]; - - memset((void *)data, 0, 64); + case CT_CORRUPT_STACK: + corrupt_stack(); break; - } case CT_UNALIGNED_LOAD_STORE_WRITE: { static u8 data[5] __attribute__((aligned(4))) = {1, 2, 3, 4, 5}; @@ -376,6 +409,8 @@ static void lkdtm_do_action(enum ctype which) case CT_SPINLOCKUP: /* Must be called twice to trigger. */ spin_lock(&lock_me_up); + /* Let sparse know we intended to exit holding the lock. */ + __release(&lock_me_up); break; case CT_HUNG_TASK: set_current_state(TASK_UNINTERRUPTIBLE); @@ -401,6 +436,49 @@ static void lkdtm_do_action(enum ctype which) vfree(vmalloc_area); break; } + case CT_EXEC_USERSPACE: { + unsigned long user_addr; + + user_addr = vm_mmap(NULL, 0, PAGE_SIZE, + PROT_READ | PROT_WRITE | PROT_EXEC, + MAP_ANONYMOUS | MAP_PRIVATE, 0); + if (user_addr >= TASK_SIZE) { + pr_warn("Failed to allocate user memory\n"); + return; + } + execute_user_location((void *)user_addr); + vm_munmap(user_addr, PAGE_SIZE); + break; + } + case CT_ACCESS_USERSPACE: { + unsigned long user_addr, tmp; + unsigned long *ptr; + + user_addr = vm_mmap(NULL, 0, PAGE_SIZE, + PROT_READ | PROT_WRITE | PROT_EXEC, + MAP_ANONYMOUS | MAP_PRIVATE, 0); + if (user_addr >= TASK_SIZE) { + pr_warn("Failed to allocate user memory\n"); + return; + } + + ptr = (unsigned long *)user_addr; + tmp = *ptr; + tmp += 0xc0dec0de; + *ptr = tmp; + + vm_munmap(user_addr, PAGE_SIZE); + + break; + } + case CT_WRITE_RO: { + unsigned long *ptr; + + ptr = (unsigned long *)&rodata; + *ptr ^= 0xabcd1234; + + break; + } case CT_NONE: default: break; diff --git a/drivers/misc/mei/amthif.c b/drivers/misc/mei/amthif.c index f6ff711aa5bb..2fad84432829 100644 --- a/drivers/misc/mei/amthif.c +++ b/drivers/misc/mei/amthif.c @@ -58,6 +58,7 @@ void mei_amthif_reset_params(struct mei_device *dev) dev->iamthif_state = MEI_IAMTHIF_IDLE; dev->iamthif_timer = 0; dev->iamthif_stall_timer = 0; + dev->iamthif_open_count = 0; } /** @@ -78,8 +79,10 @@ int mei_amthif_host_init(struct mei_device *dev) i = mei_me_cl_by_uuid(dev, &mei_amthif_guid); if (i < 0) { - dev_info(&dev->pdev->dev, "amthif: failed to find the client\n"); - return -ENOENT; + ret = i; + dev_info(&dev->pdev->dev, + "amthif: failed to find the client %d\n", ret); + return ret; } cl->me_client_id = dev->me_clients[i].client_id; @@ -106,8 +109,9 @@ int mei_amthif_host_init(struct mei_device *dev) ret = mei_cl_link(cl, MEI_IAMTHIF_HOST_CLIENT_ID); if (ret < 0) { - dev_err(&dev->pdev->dev, "amthif: failed link client\n"); - return -ENOENT; + dev_err(&dev->pdev->dev, + "amthif: failed link client %d\n", ret); + return ret; } cl->state = MEI_FILE_CONNECTING; @@ -173,7 +177,7 @@ int mei_amthif_read(struct mei_device *dev, struct file *file, unsigned long timeout; int i; - /* Only Posible if we are in timeout */ + /* Only possible if we are in timeout */ if (!cl || cl != &dev->iamthif_cl) { dev_dbg(&dev->pdev->dev, "bad file ext.\n"); return -ETIMEDOUT; @@ -245,7 +249,7 @@ int mei_amthif_read(struct mei_device *dev, struct file *file, cb->response_buffer.size); dev_dbg(&dev->pdev->dev, "amthif cb->buf_idx - %lu\n", cb->buf_idx); - /* length is being turncated to PAGE_SIZE, however, + /* length is being truncated to PAGE_SIZE, however, * the buf_idx may point beyond */ length = min_t(size_t, length, (cb->buf_idx - *offset)); @@ -312,14 +316,15 @@ static int mei_amthif_send_cmd(struct mei_device *dev, struct mei_cl_cb *cb) mei_hdr.host_addr = dev->iamthif_cl.host_client_id; mei_hdr.me_addr = dev->iamthif_cl.me_client_id; mei_hdr.reserved = 0; + mei_hdr.internal = 0; dev->iamthif_msg_buf_index += mei_hdr.length; - if (mei_write_message(dev, &mei_hdr, - (unsigned char *)dev->iamthif_msg_buf)) - return -ENODEV; + ret = mei_write_message(dev, &mei_hdr, dev->iamthif_msg_buf); + if (ret) + return ret; if (mei_hdr.msg_complete) { if (mei_cl_flow_ctrl_reduce(&dev->iamthif_cl)) - return -ENODEV; + return -EIO; dev->iamthif_flow_control_pending = true; dev->iamthif_state = MEI_IAMTHIF_FLOW_CONTROL; dev_dbg(&dev->pdev->dev, "add amthif cb to write waiting list\n"); @@ -459,10 +464,21 @@ int mei_amthif_irq_write_complete(struct mei_cl *cl, struct mei_cl_cb *cb, struct mei_msg_hdr mei_hdr; size_t len = dev->iamthif_msg_buf_size - dev->iamthif_msg_buf_index; u32 msg_slots = mei_data2slots(len); + int rets; + + rets = mei_cl_flow_ctrl_creds(cl); + if (rets < 0) + return rets; + + if (rets == 0) { + cl_dbg(dev, cl, "No flow control credentials: not sending.\n"); + return 0; + } mei_hdr.host_addr = cl->host_client_id; mei_hdr.me_addr = cl->me_client_id; mei_hdr.reserved = 0; + mei_hdr.internal = 0; if (*slots >= msg_slots) { mei_hdr.length = len; @@ -481,16 +497,17 @@ int mei_amthif_irq_write_complete(struct mei_cl *cl, struct mei_cl_cb *cb, dev_dbg(&dev->pdev->dev, MEI_HDR_FMT, MEI_HDR_PRM(&mei_hdr)); *slots -= msg_slots; - if (mei_write_message(dev, &mei_hdr, - dev->iamthif_msg_buf + dev->iamthif_msg_buf_index)) { - dev->iamthif_state = MEI_IAMTHIF_IDLE; - cl->status = -ENODEV; - list_del(&cb->list); - return -ENODEV; + rets = mei_write_message(dev, &mei_hdr, + dev->iamthif_msg_buf + dev->iamthif_msg_buf_index); + if (rets) { + dev->iamthif_state = MEI_IAMTHIF_IDLE; + cl->status = rets; + list_del(&cb->list); + return rets; } if (mei_cl_flow_ctrl_reduce(cl)) - return -ENODEV; + return -EIO; dev->iamthif_msg_buf_index += mei_hdr.length; cl->status = 0; @@ -720,8 +737,8 @@ static bool mei_clear_lists(struct mei_device *dev, struct file *file) */ int mei_amthif_release(struct mei_device *dev, struct file *file) { - if (dev->open_handle_count > 0) - dev->open_handle_count--; + if (dev->iamthif_open_count > 0) + dev->iamthif_open_count--; if (dev->iamthif_file_object == file && dev->iamthif_state != MEI_IAMTHIF_IDLE) { diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c index cd2033cd7120..4bc7d620d695 100644 --- a/drivers/misc/mei/bus.c +++ b/drivers/misc/mei/bus.c @@ -245,7 +245,7 @@ static int ___mei_cl_send(struct mei_cl *cl, u8 *buf, size_t length, /* Check if we have an ME client device */ id = mei_me_cl_by_id(dev, cl->me_client_id); if (id < 0) - return -ENODEV; + return id; if (length > dev->me_clients[id].props.max_msg_length) return -EINVAL; diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c index e0684b4d9a08..1ee2b9492a82 100644 --- a/drivers/misc/mei/client.c +++ b/drivers/misc/mei/client.c @@ -154,7 +154,7 @@ int mei_io_cb_alloc_req_buf(struct mei_cl_cb *cb, size_t length) return 0; } /** - * mei_io_cb_alloc_resp_buf - allocate respose buffer + * mei_io_cb_alloc_resp_buf - allocate response buffer * * @cb: io callback structure * @length: size of the buffer @@ -187,10 +187,14 @@ int mei_io_cb_alloc_resp_buf(struct mei_cl_cb *cb, size_t length) */ int mei_cl_flush_queues(struct mei_cl *cl) { + struct mei_device *dev; + if (WARN_ON(!cl || !cl->dev)) return -EINVAL; - dev_dbg(&cl->dev->pdev->dev, "remove list entry belonging to cl\n"); + dev = cl->dev; + + cl_dbg(dev, cl, "remove list entry belonging to cl\n"); mei_io_list_flush(&cl->dev->read_list, cl); mei_io_list_flush(&cl->dev->write_list, cl); mei_io_list_flush(&cl->dev->write_waiting_list, cl); @@ -203,7 +207,7 @@ int mei_cl_flush_queues(struct mei_cl *cl) /** - * mei_cl_init - initializes intialize cl. + * mei_cl_init - initializes cl. * * @cl: host client to be initialized * @dev: mei device @@ -259,10 +263,10 @@ struct mei_cl_cb *mei_cl_find_read_cb(struct mei_cl *cl) return NULL; } -/** mei_cl_link: allocte host id in the host map +/** mei_cl_link: allocate host id in the host map * * @cl - host client - * @id - fixed host id or -1 for genereting one + * @id - fixed host id or -1 for generic one * * returns 0 on success * -EINVAL on incorrect values @@ -271,20 +275,28 @@ struct mei_cl_cb *mei_cl_find_read_cb(struct mei_cl *cl) int mei_cl_link(struct mei_cl *cl, int id) { struct mei_device *dev; + long open_handle_count; if (WARN_ON(!cl || !cl->dev)) return -EINVAL; dev = cl->dev; - /* If Id is not asigned get one*/ + /* If Id is not assigned get one*/ if (id == MEI_HOST_CLIENT_ID_ANY) id = find_first_zero_bit(dev->host_clients_map, MEI_CLIENTS_MAX); if (id >= MEI_CLIENTS_MAX) { - dev_err(&dev->pdev->dev, "id exceded %d", MEI_CLIENTS_MAX) ; - return -ENOENT; + dev_err(&dev->pdev->dev, "id exceeded %d", MEI_CLIENTS_MAX); + return -EMFILE; + } + + open_handle_count = dev->open_handle_count + dev->iamthif_open_count; + if (open_handle_count >= MEI_MAX_OPEN_HANDLE_COUNT) { + dev_err(&dev->pdev->dev, "open_handle_count exceeded %d", + MEI_MAX_OPEN_HANDLE_COUNT); + return -EMFILE; } dev->open_handle_count++; @@ -296,7 +308,7 @@ int mei_cl_link(struct mei_cl *cl, int id) cl->state = MEI_FILE_INITIALIZING; - dev_dbg(&dev->pdev->dev, "link cl host id = %d\n", cl->host_client_id); + cl_dbg(dev, cl, "link cl\n"); return 0; } @@ -308,7 +320,6 @@ int mei_cl_link(struct mei_cl *cl, int id) int mei_cl_unlink(struct mei_cl *cl) { struct mei_device *dev; - struct mei_cl *pos, *next; /* don't shout on error exit path */ if (!cl) @@ -320,14 +331,19 @@ int mei_cl_unlink(struct mei_cl *cl) dev = cl->dev; - list_for_each_entry_safe(pos, next, &dev->file_list, link) { - if (cl->host_client_id == pos->host_client_id) { - dev_dbg(&dev->pdev->dev, "remove host client = %d, ME client = %d\n", - pos->host_client_id, pos->me_client_id); - list_del_init(&pos->link); - break; - } - } + cl_dbg(dev, cl, "unlink client"); + + if (dev->open_handle_count > 0) + dev->open_handle_count--; + + /* never clear the 0 bit */ + if (cl->host_client_id) + clear_bit(cl->host_client_id, dev->host_clients_map); + + list_del_init(&cl->link); + + cl->state = MEI_FILE_INITIALIZING; + return 0; } @@ -341,17 +357,6 @@ void mei_host_client_init(struct work_struct *work) mutex_lock(&dev->device_lock); - bitmap_zero(dev->host_clients_map, MEI_CLIENTS_MAX); - dev->open_handle_count = 0; - - /* - * Reserving the first three client IDs - * 0: Reserved for MEI Bus Message communications - * 1: Reserved for Watchdog - * 2: Reserved for AMTHI - */ - bitmap_set(dev->host_clients_map, 0, 3); - for (i = 0; i < dev->me_clients_num; i++) { client_props = &dev->me_clients[i].props; @@ -365,13 +370,14 @@ void mei_host_client_init(struct work_struct *work) } dev->dev_state = MEI_DEV_ENABLED; + dev->reset_count = 0; mutex_unlock(&dev->device_lock); } /** - * mei_cl_disconnect - disconnect host clinet form the me one + * mei_cl_disconnect - disconnect host client from the me one * * @cl: host client * @@ -390,6 +396,8 @@ int mei_cl_disconnect(struct mei_cl *cl) dev = cl->dev; + cl_dbg(dev, cl, "disconnecting"); + if (cl->state != MEI_FILE_DISCONNECTING) return 0; @@ -402,13 +410,13 @@ int mei_cl_disconnect(struct mei_cl *cl) dev->hbuf_is_ready = false; if (mei_hbm_cl_disconnect_req(dev, cl)) { rets = -ENODEV; - dev_err(&dev->pdev->dev, "failed to disconnect.\n"); + cl_err(dev, cl, "failed to disconnect.\n"); goto free; } mdelay(10); /* Wait for hardware disconnection ready */ list_add_tail(&cb->list, &dev->ctrl_rd_list.list); } else { - dev_dbg(&dev->pdev->dev, "add disconnect cb to control write list\n"); + cl_dbg(dev, cl, "add disconnect cb to control write list\n"); list_add_tail(&cb->list, &dev->ctrl_wr_list.list); } @@ -421,18 +429,17 @@ int mei_cl_disconnect(struct mei_cl *cl) mutex_lock(&dev->device_lock); if (MEI_FILE_DISCONNECTED == cl->state) { rets = 0; - dev_dbg(&dev->pdev->dev, "successfully disconnected from FW client.\n"); + cl_dbg(dev, cl, "successfully disconnected from FW client.\n"); } else { rets = -ENODEV; if (MEI_FILE_DISCONNECTED != cl->state) - dev_dbg(&dev->pdev->dev, "wrong status client disconnect.\n"); + cl_err(dev, cl, "wrong status client disconnect.\n"); if (err) - dev_dbg(&dev->pdev->dev, - "wait failed disconnect err=%08x\n", + cl_dbg(dev, cl, "wait failed disconnect err=%08x\n", err); - dev_dbg(&dev->pdev->dev, "failed to disconnect from FW client.\n"); + cl_err(dev, cl, "failed to disconnect from FW client.\n"); } mei_io_list_flush(&dev->ctrl_rd_list, cl); @@ -449,7 +456,7 @@ free: * * @cl: private data of the file object * - * returns ture if other client is connected, 0 - otherwise. + * returns true if other client is connected, false - otherwise. */ bool mei_cl_is_other_connecting(struct mei_cl *cl) { @@ -473,7 +480,7 @@ bool mei_cl_is_other_connecting(struct mei_cl *cl) } /** - * mei_cl_connect - connect host clinet to the me one + * mei_cl_connect - connect host client to the me one * * @cl: host client * @@ -639,13 +646,12 @@ int mei_cl_read_start(struct mei_cl *cl, size_t length) return -ENODEV; if (cl->read_cb) { - dev_dbg(&dev->pdev->dev, "read is pending.\n"); + cl_dbg(dev, cl, "read is pending.\n"); return -EBUSY; } i = mei_me_cl_by_id(dev, cl->me_client_id); if (i < 0) { - dev_err(&dev->pdev->dev, "no such me client %d\n", - cl->me_client_id); + cl_err(dev, cl, "no such me client %d\n", cl->me_client_id); return -ENODEV; } @@ -664,6 +670,7 @@ int mei_cl_read_start(struct mei_cl *cl, size_t length) if (dev->hbuf_is_ready) { dev->hbuf_is_ready = false; if (mei_hbm_cl_flow_control_req(dev, cl)) { + cl_err(dev, cl, "flow control send failed\n"); rets = -ENODEV; goto err; } @@ -691,14 +698,37 @@ err: int mei_cl_irq_write_complete(struct mei_cl *cl, struct mei_cl_cb *cb, s32 *slots, struct mei_cl_cb *cmpl_list) { - struct mei_device *dev = cl->dev; + struct mei_device *dev; + struct mei_msg_data *buf; struct mei_msg_hdr mei_hdr; - size_t len = cb->request_buffer.size - cb->buf_idx; - u32 msg_slots = mei_data2slots(len); + size_t len; + u32 msg_slots; + int rets; + + + if (WARN_ON(!cl || !cl->dev)) + return -ENODEV; + + dev = cl->dev; + + buf = &cb->request_buffer; + + rets = mei_cl_flow_ctrl_creds(cl); + if (rets < 0) + return rets; + + if (rets == 0) { + cl_dbg(dev, cl, "No flow control credentials: not sending.\n"); + return 0; + } + + len = buf->size - cb->buf_idx; + msg_slots = mei_data2slots(len); mei_hdr.host_addr = cl->host_client_id; mei_hdr.me_addr = cl->me_client_id; mei_hdr.reserved = 0; + mei_hdr.internal = cb->internal; if (*slots >= msg_slots) { mei_hdr.length = len; @@ -714,16 +744,15 @@ int mei_cl_irq_write_complete(struct mei_cl *cl, struct mei_cl_cb *cb, return 0; } - dev_dbg(&dev->pdev->dev, "buf: size = %d idx = %lu\n", + cl_dbg(dev, cl, "buf: size = %d idx = %lu\n", cb->request_buffer.size, cb->buf_idx); - dev_dbg(&dev->pdev->dev, MEI_HDR_FMT, MEI_HDR_PRM(&mei_hdr)); *slots -= msg_slots; - if (mei_write_message(dev, &mei_hdr, - cb->request_buffer.data + cb->buf_idx)) { - cl->status = -ENODEV; + rets = mei_write_message(dev, &mei_hdr, buf->data + cb->buf_idx); + if (rets) { + cl->status = rets; list_move_tail(&cb->list, &cmpl_list->list); - return -ENODEV; + return rets; } cl->status = 0; @@ -732,7 +761,7 @@ int mei_cl_irq_write_complete(struct mei_cl *cl, struct mei_cl_cb *cb, if (mei_hdr.msg_complete) { if (mei_cl_flow_ctrl_reduce(cl)) - return -ENODEV; + return -EIO; list_move_tail(&cb->list, &dev->write_waiting_list.list); } @@ -746,7 +775,7 @@ int mei_cl_irq_write_complete(struct mei_cl *cl, struct mei_cl_cb *cb, * @cl: host client * @cl: write callback with filled data * - * returns numbe of bytes sent on success, <0 on failure. + * returns number of bytes sent on success, <0 on failure. */ int mei_cl_write(struct mei_cl *cl, struct mei_cl_cb *cb, bool blocking) { @@ -767,7 +796,7 @@ int mei_cl_write(struct mei_cl *cl, struct mei_cl_cb *cb, bool blocking) buf = &cb->request_buffer; - dev_dbg(&dev->pdev->dev, "mei_cl_write %d\n", buf->size); + cl_dbg(dev, cl, "mei_cl_write %d\n", buf->size); cb->fop_type = MEI_FOP_WRITE; @@ -799,15 +828,12 @@ int mei_cl_write(struct mei_cl *cl, struct mei_cl_cb *cb, bool blocking) mei_hdr.host_addr = cl->host_client_id; mei_hdr.me_addr = cl->me_client_id; mei_hdr.reserved = 0; - - dev_dbg(&dev->pdev->dev, "write " MEI_HDR_FMT "\n", - MEI_HDR_PRM(&mei_hdr)); + mei_hdr.internal = cb->internal; - if (mei_write_message(dev, &mei_hdr, buf->data)) { - rets = -EIO; + rets = mei_write_message(dev, &mei_hdr, buf->data); + if (rets) goto err; - } cl->writing_state = MEI_WRITING; cb->buf_idx = mei_hdr.length; @@ -898,11 +924,11 @@ void mei_cl_all_wakeup(struct mei_device *dev) struct mei_cl *cl, *next; list_for_each_entry_safe(cl, next, &dev->file_list, link) { if (waitqueue_active(&cl->rx_wait)) { - dev_dbg(&dev->pdev->dev, "Waking up reading client!\n"); + cl_dbg(dev, cl, "Waking up reading client!\n"); wake_up_interruptible(&cl->rx_wait); } if (waitqueue_active(&cl->tx_wait)) { - dev_dbg(&dev->pdev->dev, "Waking up writing client!\n"); + cl_dbg(dev, cl, "Waking up writing client!\n"); wake_up_interruptible(&cl->tx_wait); } } diff --git a/drivers/misc/mei/client.h b/drivers/misc/mei/client.h index 892cc4207fa2..c8396e582f1c 100644 --- a/drivers/misc/mei/client.h +++ b/drivers/misc/mei/client.h @@ -115,4 +115,13 @@ void mei_cl_all_disconnect(struct mei_device *dev); void mei_cl_all_wakeup(struct mei_device *dev); void mei_cl_all_write_clear(struct mei_device *dev); +#define MEI_CL_FMT "cl:host=%02d me=%02d " +#define MEI_CL_PRM(cl) (cl)->host_client_id, (cl)->me_client_id + +#define cl_dbg(dev, cl, format, arg...) \ + dev_dbg(&(dev)->pdev->dev, MEI_CL_FMT format, MEI_CL_PRM(cl), ##arg) + +#define cl_err(dev, cl, format, arg...) \ + dev_err(&(dev)->pdev->dev, MEI_CL_FMT format, MEI_CL_PRM(cl), ##arg) + #endif /* _MEI_CLIENT_H_ */ diff --git a/drivers/misc/mei/debugfs.c b/drivers/misc/mei/debugfs.c index e3870f22d238..a3ae154444b2 100644 --- a/drivers/misc/mei/debugfs.c +++ b/drivers/misc/mei/debugfs.c @@ -43,7 +43,7 @@ static ssize_t mei_dbgfs_read_meclients(struct file *fp, char __user *ubuf, mutex_lock(&dev->device_lock); - /* if the driver is not enabled the list won't b consitent */ + /* if the driver is not enabled the list won't be consistent */ if (dev->dev_state != MEI_DEV_ENABLED) goto out; @@ -101,7 +101,7 @@ static const struct file_operations mei_dbgfs_fops_devstate = { /** * mei_dbgfs_deregister - Remove the debugfs files and directories - * @mei - pointer to mei device private dat + * @mei - pointer to mei device private data */ void mei_dbgfs_deregister(struct mei_device *dev) { diff --git a/drivers/misc/mei/hbm.c b/drivers/misc/mei/hbm.c index 0a0448326e9d..28cd74c073b9 100644 --- a/drivers/misc/mei/hbm.c +++ b/drivers/misc/mei/hbm.c @@ -28,9 +28,9 @@ * * @dev: the device structure * - * returns none. + * returns 0 on success -ENOMEM on allocation failure */ -static void mei_hbm_me_cl_allocate(struct mei_device *dev) +static int mei_hbm_me_cl_allocate(struct mei_device *dev) { struct mei_me_client *clients; int b; @@ -44,24 +44,22 @@ static void mei_hbm_me_cl_allocate(struct mei_device *dev) dev->me_clients_num++; if (dev->me_clients_num == 0) - return; + return 0; kfree(dev->me_clients); dev->me_clients = NULL; - dev_dbg(&dev->pdev->dev, "memory allocation for ME clients size=%zd.\n", + dev_dbg(&dev->pdev->dev, "memory allocation for ME clients size=%ld.\n", dev->me_clients_num * sizeof(struct mei_me_client)); /* allocate storage for ME clients representation */ clients = kcalloc(dev->me_clients_num, sizeof(struct mei_me_client), GFP_KERNEL); if (!clients) { dev_err(&dev->pdev->dev, "memory allocation for ME clients failed.\n"); - dev->dev_state = MEI_DEV_RESETTING; - mei_reset(dev, 1); - return; + return -ENOMEM; } dev->me_clients = clients; - return; + return 0; } /** @@ -85,12 +83,12 @@ void mei_hbm_cl_hdr(struct mei_cl *cl, u8 hbm_cmd, void *buf, size_t len) } /** - * same_disconn_addr - tells if they have the same address + * mei_hbm_cl_addr_equal - tells if they have the same address * - * @file: private data of the file object. - * @disconn: disconnection request. + * @cl: - client + * @buf: buffer with cl header * - * returns true if addres are same + * returns true if addresses are the same */ static inline bool mei_hbm_cl_addr_equal(struct mei_cl *cl, void *buf) @@ -128,6 +126,17 @@ static bool is_treat_specially_client(struct mei_cl *cl, return false; } +/** + * mei_hbm_idle - set hbm to idle state + * + * @dev: the device structure + */ +void mei_hbm_idle(struct mei_device *dev) +{ + dev->init_clients_timer = 0; + dev->hbm_state = MEI_HBM_IDLE; +} + int mei_hbm_start_wait(struct mei_device *dev) { int ret; @@ -137,7 +146,7 @@ int mei_hbm_start_wait(struct mei_device *dev) mutex_unlock(&dev->device_lock); ret = wait_event_interruptible_timeout(dev->wait_recvd_msg, dev->hbm_state == MEI_HBM_IDLE || - dev->hbm_state > MEI_HBM_START, + dev->hbm_state >= MEI_HBM_STARTED, mei_secs_to_jiffies(MEI_INTEROP_TIMEOUT)); mutex_lock(&dev->device_lock); @@ -153,12 +162,15 @@ int mei_hbm_start_wait(struct mei_device *dev) * mei_hbm_start_req - sends start request message. * * @dev: the device structure + * + * returns 0 on success and < 0 on failure */ int mei_hbm_start_req(struct mei_device *dev) { struct mei_msg_hdr *mei_hdr = &dev->wr_msg.hdr; struct hbm_host_version_request *start_req; const size_t len = sizeof(struct hbm_host_version_request); + int ret; mei_hbm_hdr(mei_hdr, len); @@ -170,12 +182,13 @@ int mei_hbm_start_req(struct mei_device *dev) start_req->host_version.minor_version = HBM_MINOR_VERSION; dev->hbm_state = MEI_HBM_IDLE; - if (mei_write_message(dev, mei_hdr, dev->wr_msg.data)) { - dev_err(&dev->pdev->dev, "version message write failed\n"); - dev->dev_state = MEI_DEV_RESETTING; - mei_reset(dev, 1); - return -ENODEV; + ret = mei_write_message(dev, mei_hdr, dev->wr_msg.data); + if (ret) { + dev_err(&dev->pdev->dev, "version message write failed: ret = %d\n", + ret); + return ret; } + dev->hbm_state = MEI_HBM_START; dev->init_clients_timer = MEI_CLIENTS_INIT_TIMEOUT; return 0; @@ -186,13 +199,15 @@ int mei_hbm_start_req(struct mei_device *dev) * * @dev: the device structure * - * returns none. + * returns 0 on success and < 0 on failure */ -static void mei_hbm_enum_clients_req(struct mei_device *dev) +static int mei_hbm_enum_clients_req(struct mei_device *dev) { struct mei_msg_hdr *mei_hdr = &dev->wr_msg.hdr; struct hbm_host_enum_request *enum_req; const size_t len = sizeof(struct hbm_host_enum_request); + int ret; + /* enumerate clients */ mei_hbm_hdr(mei_hdr, len); @@ -200,14 +215,15 @@ static void mei_hbm_enum_clients_req(struct mei_device *dev) memset(enum_req, 0, len); enum_req->hbm_cmd = HOST_ENUM_REQ_CMD; - if (mei_write_message(dev, mei_hdr, dev->wr_msg.data)) { - dev->dev_state = MEI_DEV_RESETTING; - dev_err(&dev->pdev->dev, "enumeration request write failed.\n"); - mei_reset(dev, 1); + ret = mei_write_message(dev, mei_hdr, dev->wr_msg.data); + if (ret) { + dev_err(&dev->pdev->dev, "enumeration request write failed: ret = %d.\n", + ret); + return ret; } dev->hbm_state = MEI_HBM_ENUM_CLIENTS; dev->init_clients_timer = MEI_CLIENTS_INIT_TIMEOUT; - return; + return 0; } /** @@ -215,7 +231,7 @@ static void mei_hbm_enum_clients_req(struct mei_device *dev) * * @dev: the device structure * - * returns none. + * returns 0 on success and < 0 on failure */ static int mei_hbm_prop_req(struct mei_device *dev) @@ -226,7 +242,7 @@ static int mei_hbm_prop_req(struct mei_device *dev) const size_t len = sizeof(struct hbm_props_request); unsigned long next_client_index; unsigned long client_num; - + int ret; client_num = dev->me_client_presentation_num; @@ -253,12 +269,11 @@ static int mei_hbm_prop_req(struct mei_device *dev) prop_req->hbm_cmd = HOST_CLIENT_PROPERTIES_REQ_CMD; prop_req->address = next_client_index; - if (mei_write_message(dev, mei_hdr, dev->wr_msg.data)) { - dev->dev_state = MEI_DEV_RESETTING; - dev_err(&dev->pdev->dev, "properties request write failed\n"); - mei_reset(dev, 1); - - return -EIO; + ret = mei_write_message(dev, mei_hdr, dev->wr_msg.data); + if (ret) { + dev_err(&dev->pdev->dev, "properties request write failed: ret = %d\n", + ret); + return ret; } dev->init_clients_timer = MEI_CLIENTS_INIT_TIMEOUT; @@ -268,7 +283,7 @@ static int mei_hbm_prop_req(struct mei_device *dev) } /** - * mei_hbm_stop_req_prepare - perpare stop request message + * mei_hbm_stop_req_prepare - prepare stop request message * * @dev - mei device * @mei_hdr - mei message header @@ -289,7 +304,7 @@ static void mei_hbm_stop_req_prepare(struct mei_device *dev, } /** - * mei_hbm_cl_flow_control_req - sends flow control requst. + * mei_hbm_cl_flow_control_req - sends flow control request. * * @dev: the device structure * @cl: client info @@ -451,7 +466,7 @@ int mei_hbm_cl_connect_req(struct mei_device *dev, struct mei_cl *cl) } /** - * mei_hbm_cl_connect_res - connect resposne from the ME + * mei_hbm_cl_connect_res - connect response from the ME * * @dev: the device structure * @rs: connect response bus message @@ -505,8 +520,8 @@ static void mei_hbm_cl_connect_res(struct mei_device *dev, /** - * mei_hbm_fw_disconnect_req - disconnect request initiated by me - * host sends disoconnect response + * mei_hbm_fw_disconnect_req - disconnect request initiated by ME firmware + * host sends disconnect response * * @dev: the device structure. * @disconnect_req: disconnect request bus message from the me @@ -559,8 +574,10 @@ bool mei_hbm_version_is_supported(struct mei_device *dev) * * @dev: the device structure * @mei_hdr: header of bus message + * + * returns 0 on success and < 0 on failure */ -void mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr) +int mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr) { struct mei_bus_message *mei_msg; struct mei_me_client *me_client; @@ -577,8 +594,20 @@ void mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr) mei_read_slots(dev, dev->rd_msg_buf, hdr->length); mei_msg = (struct mei_bus_message *)dev->rd_msg_buf; + /* ignore spurious message and prevent reset nesting + * hbm is put to idle during system reset + */ + if (dev->hbm_state == MEI_HBM_IDLE) { + dev_dbg(&dev->pdev->dev, "hbm: state is idle ignore spurious messages\n"); + return 0; + } + switch (mei_msg->hbm_cmd) { case HOST_START_RES_CMD: + dev_dbg(&dev->pdev->dev, "hbm: start: response message received.\n"); + + dev->init_clients_timer = 0; + version_res = (struct hbm_host_version_response *)mei_msg; dev_dbg(&dev->pdev->dev, "HBM VERSION: DRIVER=%02d:%02d DEVICE=%02d:%02d\n", @@ -597,73 +626,89 @@ void mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr) } if (!mei_hbm_version_is_supported(dev)) { - dev_warn(&dev->pdev->dev, "hbm version mismatch: stopping the driver.\n"); + dev_warn(&dev->pdev->dev, "hbm: start: version mismatch - stopping the driver.\n"); - dev->hbm_state = MEI_HBM_STOP; + dev->hbm_state = MEI_HBM_STOPPED; mei_hbm_stop_req_prepare(dev, &dev->wr_msg.hdr, dev->wr_msg.data); - mei_write_message(dev, &dev->wr_msg.hdr, - dev->wr_msg.data); + if (mei_write_message(dev, &dev->wr_msg.hdr, + dev->wr_msg.data)) { + dev_err(&dev->pdev->dev, "hbm: start: failed to send stop request\n"); + return -EIO; + } + break; + } - return; + if (dev->dev_state != MEI_DEV_INIT_CLIENTS || + dev->hbm_state != MEI_HBM_START) { + dev_err(&dev->pdev->dev, "hbm: start: state mismatch, [%d, %d]\n", + dev->dev_state, dev->hbm_state); + return -EPROTO; } - if (dev->dev_state == MEI_DEV_INIT_CLIENTS && - dev->hbm_state == MEI_HBM_START) { - dev->init_clients_timer = 0; - mei_hbm_enum_clients_req(dev); - } else { - dev_err(&dev->pdev->dev, "reset: wrong host start response\n"); - mei_reset(dev, 1); - return; + dev->hbm_state = MEI_HBM_STARTED; + + if (mei_hbm_enum_clients_req(dev)) { + dev_err(&dev->pdev->dev, "hbm: start: failed to send enumeration request\n"); + return -EIO; } wake_up_interruptible(&dev->wait_recvd_msg); - dev_dbg(&dev->pdev->dev, "host start response message received.\n"); break; case CLIENT_CONNECT_RES_CMD: + dev_dbg(&dev->pdev->dev, "hbm: client connect response: message received.\n"); + connect_res = (struct hbm_client_connect_response *) mei_msg; mei_hbm_cl_connect_res(dev, connect_res); - dev_dbg(&dev->pdev->dev, "client connect response message received.\n"); wake_up(&dev->wait_recvd_msg); break; case CLIENT_DISCONNECT_RES_CMD: + dev_dbg(&dev->pdev->dev, "hbm: client disconnect response: message received.\n"); + disconnect_res = (struct hbm_client_connect_response *) mei_msg; mei_hbm_cl_disconnect_res(dev, disconnect_res); - dev_dbg(&dev->pdev->dev, "client disconnect response message received.\n"); wake_up(&dev->wait_recvd_msg); break; case MEI_FLOW_CONTROL_CMD: + dev_dbg(&dev->pdev->dev, "hbm: client flow control response: message received.\n"); + flow_control = (struct hbm_flow_control *) mei_msg; mei_hbm_cl_flow_control_res(dev, flow_control); - dev_dbg(&dev->pdev->dev, "client flow control response message received.\n"); break; case HOST_CLIENT_PROPERTIES_RES_CMD: + dev_dbg(&dev->pdev->dev, "hbm: properties response: message received.\n"); + + dev->init_clients_timer = 0; + + if (dev->me_clients == NULL) { + dev_err(&dev->pdev->dev, "hbm: properties response: mei_clients not allocated\n"); + return -EPROTO; + } + props_res = (struct hbm_props_response *)mei_msg; me_client = &dev->me_clients[dev->me_client_presentation_num]; - if (props_res->status || !dev->me_clients) { - dev_err(&dev->pdev->dev, "reset: properties response hbm wrong status.\n"); - mei_reset(dev, 1); - return; + if (props_res->status) { + dev_err(&dev->pdev->dev, "hbm: properties response: wrong status = %d\n", + props_res->status); + return -EPROTO; } if (me_client->client_id != props_res->address) { - dev_err(&dev->pdev->dev, "reset: host properties response address mismatch\n"); - mei_reset(dev, 1); - return; + dev_err(&dev->pdev->dev, "hbm: properties response: address mismatch %d ?= %d\n", + me_client->client_id, props_res->address); + return -EPROTO; } if (dev->dev_state != MEI_DEV_INIT_CLIENTS || dev->hbm_state != MEI_HBM_CLIENT_PROPERTIES) { - dev_err(&dev->pdev->dev, "reset: unexpected properties response\n"); - mei_reset(dev, 1); - - return; + dev_err(&dev->pdev->dev, "hbm: properties response: state mismatch, [%d, %d]\n", + dev->dev_state, dev->hbm_state); + return -EPROTO; } me_client->props = props_res->client_properties; @@ -671,46 +716,70 @@ void mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr) dev->me_client_presentation_num++; /* request property for the next client */ - mei_hbm_prop_req(dev); + if (mei_hbm_prop_req(dev)) + return -EIO; break; case HOST_ENUM_RES_CMD: + dev_dbg(&dev->pdev->dev, "hbm: enumeration response: message received\n"); + + dev->init_clients_timer = 0; + enum_res = (struct hbm_host_enum_response *) mei_msg; - memcpy(dev->me_clients_map, enum_res->valid_addresses, 32); - if (dev->dev_state == MEI_DEV_INIT_CLIENTS && - dev->hbm_state == MEI_HBM_ENUM_CLIENTS) { - dev->init_clients_timer = 0; - mei_hbm_me_cl_allocate(dev); - dev->hbm_state = MEI_HBM_CLIENT_PROPERTIES; - - /* first property reqeust */ - mei_hbm_prop_req(dev); - } else { - dev_err(&dev->pdev->dev, "reset: unexpected enumeration response hbm.\n"); - mei_reset(dev, 1); - return; + BUILD_BUG_ON(sizeof(dev->me_clients_map) + < sizeof(enum_res->valid_addresses)); + memcpy(dev->me_clients_map, enum_res->valid_addresses, + sizeof(enum_res->valid_addresses)); + + if (dev->dev_state != MEI_DEV_INIT_CLIENTS || + dev->hbm_state != MEI_HBM_ENUM_CLIENTS) { + dev_err(&dev->pdev->dev, "hbm: enumeration response: state mismatch, [%d, %d]\n", + dev->dev_state, dev->hbm_state); + return -EPROTO; + } + + if (mei_hbm_me_cl_allocate(dev)) { + dev_err(&dev->pdev->dev, "hbm: enumeration response: cannot allocate clients array\n"); + return -ENOMEM; } + + dev->hbm_state = MEI_HBM_CLIENT_PROPERTIES; + + /* first property request */ + if (mei_hbm_prop_req(dev)) + return -EIO; + break; case HOST_STOP_RES_CMD: + dev_dbg(&dev->pdev->dev, "hbm: stop response: message received\n"); + + dev->init_clients_timer = 0; - if (dev->hbm_state != MEI_HBM_STOP) - dev_err(&dev->pdev->dev, "unexpected stop response hbm.\n"); - dev->dev_state = MEI_DEV_DISABLED; - dev_info(&dev->pdev->dev, "reset: FW stop response.\n"); - mei_reset(dev, 1); + if (dev->hbm_state != MEI_HBM_STOPPED) { + dev_err(&dev->pdev->dev, "hbm: stop response: state mismatch, [%d, %d]\n", + dev->dev_state, dev->hbm_state); + return -EPROTO; + } + + dev->dev_state = MEI_DEV_POWER_DOWN; + dev_info(&dev->pdev->dev, "hbm: stop response: resetting.\n"); + /* force the reset */ + return -EPROTO; break; case CLIENT_DISCONNECT_REQ_CMD: - /* search for client */ + dev_dbg(&dev->pdev->dev, "hbm: disconnect request: message received\n"); + disconnect_req = (struct hbm_client_connect_request *)mei_msg; mei_hbm_fw_disconnect_req(dev, disconnect_req); break; case ME_STOP_REQ_CMD: + dev_dbg(&dev->pdev->dev, "hbm: stop request: message received\n"); - dev->hbm_state = MEI_HBM_STOP; + dev->hbm_state = MEI_HBM_STOPPED; mei_hbm_stop_req_prepare(dev, &dev->wr_ext_msg.hdr, dev->wr_ext_msg.data); break; @@ -719,5 +788,6 @@ void mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr) break; } + return 0; } diff --git a/drivers/misc/mei/hbm.h b/drivers/misc/mei/hbm.h index 4ae2e56e404f..5f92188a5cd7 100644 --- a/drivers/misc/mei/hbm.h +++ b/drivers/misc/mei/hbm.h @@ -32,13 +32,13 @@ struct mei_cl; enum mei_hbm_state { MEI_HBM_IDLE = 0, MEI_HBM_START, + MEI_HBM_STARTED, MEI_HBM_ENUM_CLIENTS, MEI_HBM_CLIENT_PROPERTIES, - MEI_HBM_STARTED, - MEI_HBM_STOP, + MEI_HBM_STOPPED, }; -void mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr); +int mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr); static inline void mei_hbm_hdr(struct mei_msg_hdr *hdr, size_t length) { @@ -49,6 +49,7 @@ static inline void mei_hbm_hdr(struct mei_msg_hdr *hdr, size_t length) hdr->reserved = 0; } +void mei_hbm_idle(struct mei_device *dev); int mei_hbm_start_req(struct mei_device *dev); int mei_hbm_start_wait(struct mei_device *dev); int mei_hbm_cl_flow_control_req(struct mei_device *dev, struct mei_cl *cl); diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h index 6a203b6e8346..66f411a6e8ea 100644 --- a/drivers/misc/mei/hw-me-regs.h +++ b/drivers/misc/mei/hw-me-regs.h @@ -109,8 +109,12 @@ #define MEI_DEV_ID_PPT_2 0x1CBA /* Panther Point */ #define MEI_DEV_ID_PPT_3 0x1DBA /* Panther Point */ -#define MEI_DEV_ID_LPT 0x8C3A /* Lynx Point */ +#define MEI_DEV_ID_LPT_H 0x8C3A /* Lynx Point H */ +#define MEI_DEV_ID_LPT_W 0x8D3A /* Lynx Point - Wellsburg */ #define MEI_DEV_ID_LPT_LP 0x9C3A /* Lynx Point LP */ +#define MEI_DEV_ID_LPT_HR 0x8CBA /* Lynx Point H Refresh */ + +#define MEI_DEV_ID_WPT_LP 0x9CBA /* Wildcat Point LP */ /* * MEI HW Section */ diff --git a/drivers/misc/mei/hw-me.c b/drivers/misc/mei/hw-me.c index 3412adcdaeb0..6f656c053b14 100644 --- a/drivers/misc/mei/hw-me.c +++ b/drivers/misc/mei/hw-me.c @@ -185,7 +185,7 @@ static int mei_me_hw_reset(struct mei_device *dev, bool intr_enable) mei_me_reg_write(hw, H_CSR, hcsr); - if (dev->dev_state == MEI_DEV_POWER_DOWN) + if (intr_enable == false) mei_me_hw_reset_release(dev); return 0; @@ -469,7 +469,7 @@ irqreturn_t mei_me_irq_thread_handler(int irq, void *dev_id) struct mei_device *dev = (struct mei_device *) dev_id; struct mei_cl_cb complete_list; s32 slots; - int rets; + int rets = 0; dev_dbg(&dev->pdev->dev, "function called after ISR to handle the interrupt processing.\n"); /* initialize our complete list */ @@ -482,15 +482,10 @@ irqreturn_t mei_me_irq_thread_handler(int irq, void *dev_id) mei_clear_interrupts(dev); /* check if ME wants a reset */ - if (!mei_hw_is_ready(dev) && - dev->dev_state != MEI_DEV_RESETTING && - dev->dev_state != MEI_DEV_INITIALIZING && - dev->dev_state != MEI_DEV_POWER_DOWN && - dev->dev_state != MEI_DEV_POWER_UP) { - dev_dbg(&dev->pdev->dev, "FW not ready.\n"); - mei_reset(dev, 1); - mutex_unlock(&dev->device_lock); - return IRQ_HANDLED; + if (!mei_hw_is_ready(dev) && dev->dev_state != MEI_DEV_RESETTING) { + dev_warn(&dev->pdev->dev, "FW not ready: resetting.\n"); + schedule_work(&dev->reset_work); + goto end; } /* check if we need to start the dev */ @@ -500,15 +495,12 @@ irqreturn_t mei_me_irq_thread_handler(int irq, void *dev_id) dev->recvd_hw_ready = true; wake_up_interruptible(&dev->wait_hw_ready); - - mutex_unlock(&dev->device_lock); - return IRQ_HANDLED; } else { + dev_dbg(&dev->pdev->dev, "Reset Completed.\n"); mei_me_hw_reset_release(dev); - mutex_unlock(&dev->device_lock); - return IRQ_HANDLED; } + goto end; } /* check slots available for reading */ slots = mei_count_full_read_slots(dev); @@ -516,21 +508,23 @@ irqreturn_t mei_me_irq_thread_handler(int irq, void *dev_id) /* we have urgent data to send so break the read */ if (dev->wr_ext_msg.hdr.length) break; - dev_dbg(&dev->pdev->dev, "slots =%08x\n", slots); - dev_dbg(&dev->pdev->dev, "call mei_irq_read_handler.\n"); + dev_dbg(&dev->pdev->dev, "slots to read = %08x\n", slots); rets = mei_irq_read_handler(dev, &complete_list, &slots); - if (rets) + if (rets && dev->dev_state != MEI_DEV_RESETTING) { + schedule_work(&dev->reset_work); goto end; + } } + rets = mei_irq_write_handler(dev, &complete_list); -end: - dev_dbg(&dev->pdev->dev, "end of bottom half function.\n"); - dev->hbuf_is_ready = mei_hbuf_is_ready(dev); - mutex_unlock(&dev->device_lock); + dev->hbuf_is_ready = mei_hbuf_is_ready(dev); mei_irq_compl_handler(dev, &complete_list); +end: + dev_dbg(&dev->pdev->dev, "interrupt thread end ret = %d\n", rets); + mutex_unlock(&dev->device_lock); return IRQ_HANDLED; } static const struct mei_hw_ops mei_me_hw_ops = { diff --git a/drivers/misc/mei/hw.h b/drivers/misc/mei/hw.h index cb2f556b4252..dd44e33ad2b6 100644 --- a/drivers/misc/mei/hw.h +++ b/drivers/misc/mei/hw.h @@ -111,7 +111,8 @@ struct mei_msg_hdr { u32 me_addr:8; u32 host_addr:8; u32 length:9; - u32 reserved:6; + u32 reserved:5; + u32 internal:1; u32 msg_complete:1; } __packed; diff --git a/drivers/misc/mei/init.c b/drivers/misc/mei/init.c index 6197018e2f16..cdd31c2a2a2b 100644 --- a/drivers/misc/mei/init.c +++ b/drivers/misc/mei/init.c @@ -43,33 +43,119 @@ const char *mei_dev_state_str(int state) #undef MEI_DEV_STATE } -void mei_device_init(struct mei_device *dev) + +/** + * mei_cancel_work. Cancel mei background jobs + * + * @dev: the device structure + * + * returns 0 on success or < 0 if the reset hasn't succeeded + */ +void mei_cancel_work(struct mei_device *dev) { - /* setup our list array */ - INIT_LIST_HEAD(&dev->file_list); - INIT_LIST_HEAD(&dev->device_list); - mutex_init(&dev->device_lock); - init_waitqueue_head(&dev->wait_hw_ready); - init_waitqueue_head(&dev->wait_recvd_msg); - init_waitqueue_head(&dev->wait_stop_wd); - dev->dev_state = MEI_DEV_INITIALIZING; + cancel_work_sync(&dev->init_work); + cancel_work_sync(&dev->reset_work); - mei_io_list_init(&dev->read_list); - mei_io_list_init(&dev->write_list); - mei_io_list_init(&dev->write_waiting_list); - mei_io_list_init(&dev->ctrl_wr_list); - mei_io_list_init(&dev->ctrl_rd_list); + cancel_delayed_work(&dev->timer_work); +} +EXPORT_SYMBOL_GPL(mei_cancel_work); - INIT_DELAYED_WORK(&dev->timer_work, mei_timer); - INIT_WORK(&dev->init_work, mei_host_client_init); +/** + * mei_reset - resets host and fw. + * + * @dev: the device structure + */ +int mei_reset(struct mei_device *dev) +{ + enum mei_dev_state state = dev->dev_state; + bool interrupts_enabled; + int ret; - INIT_LIST_HEAD(&dev->wd_cl.link); - INIT_LIST_HEAD(&dev->iamthif_cl.link); - mei_io_list_init(&dev->amthif_cmd_list); - mei_io_list_init(&dev->amthif_rd_complete_list); + if (state != MEI_DEV_INITIALIZING && + state != MEI_DEV_DISABLED && + state != MEI_DEV_POWER_DOWN && + state != MEI_DEV_POWER_UP) + dev_warn(&dev->pdev->dev, "unexpected reset: dev_state = %s\n", + mei_dev_state_str(state)); + + /* we're already in reset, cancel the init timer + * if the reset was called due the hbm protocol error + * we need to call it before hw start + * so the hbm watchdog won't kick in + */ + mei_hbm_idle(dev); + + /* enter reset flow */ + interrupts_enabled = state != MEI_DEV_POWER_DOWN; + dev->dev_state = MEI_DEV_RESETTING; + + dev->reset_count++; + if (dev->reset_count > MEI_MAX_CONSEC_RESET) { + dev_err(&dev->pdev->dev, "reset: reached maximal consecutive resets: disabling the device\n"); + dev->dev_state = MEI_DEV_DISABLED; + return -ENODEV; + } + + ret = mei_hw_reset(dev, interrupts_enabled); + /* fall through and remove the sw state even if hw reset has failed */ + + /* no need to clean up software state in case of power up */ + if (state != MEI_DEV_INITIALIZING && + state != MEI_DEV_POWER_UP) { + /* remove all waiting requests */ + mei_cl_all_write_clear(dev); + + mei_cl_all_disconnect(dev); + + /* wake up all readers and writers so they can be interrupted */ + mei_cl_all_wakeup(dev); + + /* remove entry if already in list */ + dev_dbg(&dev->pdev->dev, "remove iamthif and wd from the file list.\n"); + mei_cl_unlink(&dev->wd_cl); + mei_cl_unlink(&dev->iamthif_cl); + mei_amthif_reset_params(dev); + memset(&dev->wr_ext_msg, 0, sizeof(dev->wr_ext_msg)); + } + + + dev->me_clients_num = 0; + dev->rd_msg_hdr = 0; + dev->wd_pending = false; + + if (ret) { + dev_err(&dev->pdev->dev, "hw_reset failed ret = %d\n", ret); + dev->dev_state = MEI_DEV_DISABLED; + return ret; + } + + if (state == MEI_DEV_POWER_DOWN) { + dev_dbg(&dev->pdev->dev, "powering down: end of reset\n"); + dev->dev_state = MEI_DEV_DISABLED; + return 0; + } + + ret = mei_hw_start(dev); + if (ret) { + dev_err(&dev->pdev->dev, "hw_start failed ret = %d\n", ret); + dev->dev_state = MEI_DEV_DISABLED; + return ret; + } + + dev_dbg(&dev->pdev->dev, "link is established start sending messages.\n"); + + dev->dev_state = MEI_DEV_INIT_CLIENTS; + ret = mei_hbm_start_req(dev); + if (ret) { + dev_err(&dev->pdev->dev, "hbm_start failed ret = %d\n", ret); + dev->dev_state = MEI_DEV_DISABLED; + return ret; + } + + return 0; } -EXPORT_SYMBOL_GPL(mei_device_init); +EXPORT_SYMBOL_GPL(mei_reset); /** * mei_start - initializes host and fw to start work. @@ -82,14 +168,21 @@ int mei_start(struct mei_device *dev) { mutex_lock(&dev->device_lock); - /* acknowledge interrupt and stop interupts */ + /* acknowledge interrupt and stop interrupts */ mei_clear_interrupts(dev); mei_hw_config(dev); dev_dbg(&dev->pdev->dev, "reset in start the mei device.\n"); - mei_reset(dev, 1); + dev->dev_state = MEI_DEV_INITIALIZING; + dev->reset_count = 0; + mei_reset(dev); + + if (dev->dev_state == MEI_DEV_DISABLED) { + dev_err(&dev->pdev->dev, "reset failed"); + goto err; + } if (mei_hbm_start_wait(dev)) { dev_err(&dev->pdev->dev, "HBM haven't started"); @@ -124,106 +217,64 @@ err: EXPORT_SYMBOL_GPL(mei_start); /** - * mei_reset - resets host and fw. + * mei_restart - restart device after suspend * * @dev: the device structure - * @interrupts_enabled: if interrupt should be enabled after reset. + * + * returns 0 on success or -ENODEV if the restart hasn't succeeded */ -void mei_reset(struct mei_device *dev, int interrupts_enabled) +int mei_restart(struct mei_device *dev) { - bool unexpected; - int ret; - - unexpected = (dev->dev_state != MEI_DEV_INITIALIZING && - dev->dev_state != MEI_DEV_DISABLED && - dev->dev_state != MEI_DEV_POWER_DOWN && - dev->dev_state != MEI_DEV_POWER_UP); + int err; - ret = mei_hw_reset(dev, interrupts_enabled); - if (ret) { - dev_err(&dev->pdev->dev, "hw reset failed disabling the device\n"); - interrupts_enabled = false; - dev->dev_state = MEI_DEV_DISABLED; - } - - dev->hbm_state = MEI_HBM_IDLE; - - if (dev->dev_state != MEI_DEV_INITIALIZING && - dev->dev_state != MEI_DEV_POWER_UP) { - if (dev->dev_state != MEI_DEV_DISABLED && - dev->dev_state != MEI_DEV_POWER_DOWN) - dev->dev_state = MEI_DEV_RESETTING; - - /* remove all waiting requests */ - mei_cl_all_write_clear(dev); - - mei_cl_all_disconnect(dev); + mutex_lock(&dev->device_lock); - /* wake up all readings so they can be interrupted */ - mei_cl_all_wakeup(dev); + mei_clear_interrupts(dev); - /* remove entry if already in list */ - dev_dbg(&dev->pdev->dev, "remove iamthif and wd from the file list.\n"); - mei_cl_unlink(&dev->wd_cl); - if (dev->open_handle_count > 0) - dev->open_handle_count--; - mei_cl_unlink(&dev->iamthif_cl); - if (dev->open_handle_count > 0) - dev->open_handle_count--; + dev->dev_state = MEI_DEV_POWER_UP; + dev->reset_count = 0; - mei_amthif_reset_params(dev); - memset(&dev->wr_ext_msg, 0, sizeof(dev->wr_ext_msg)); - } + err = mei_reset(dev); - /* we're already in reset, cancel the init timer */ - dev->init_clients_timer = 0; + mutex_unlock(&dev->device_lock); - dev->me_clients_num = 0; - dev->rd_msg_hdr = 0; - dev->wd_pending = false; + if (err || dev->dev_state == MEI_DEV_DISABLED) + return -ENODEV; - if (unexpected) - dev_warn(&dev->pdev->dev, "unexpected reset: dev_state = %s\n", - mei_dev_state_str(dev->dev_state)); + return 0; +} +EXPORT_SYMBOL_GPL(mei_restart); - if (!interrupts_enabled) { - dev_dbg(&dev->pdev->dev, "intr not enabled end of reset\n"); - return; - } - ret = mei_hw_start(dev); - if (ret) { - dev_err(&dev->pdev->dev, "hw_start failed disabling the device\n"); - dev->dev_state = MEI_DEV_DISABLED; - return; - } +static void mei_reset_work(struct work_struct *work) +{ + struct mei_device *dev = + container_of(work, struct mei_device, reset_work); - dev_dbg(&dev->pdev->dev, "link is established start sending messages.\n"); - /* link is established * start sending messages. */ + mutex_lock(&dev->device_lock); - dev->dev_state = MEI_DEV_INIT_CLIENTS; + mei_reset(dev); - mei_hbm_start_req(dev); + mutex_unlock(&dev->device_lock); + if (dev->dev_state == MEI_DEV_DISABLED) + dev_err(&dev->pdev->dev, "reset failed"); } -EXPORT_SYMBOL_GPL(mei_reset); void mei_stop(struct mei_device *dev) { dev_dbg(&dev->pdev->dev, "stopping the device.\n"); - flush_scheduled_work(); + mei_cancel_work(dev); - mutex_lock(&dev->device_lock); + mei_nfc_host_exit(dev); - cancel_delayed_work(&dev->timer_work); + mutex_lock(&dev->device_lock); mei_wd_stop(dev); - mei_nfc_host_exit(); - dev->dev_state = MEI_DEV_POWER_DOWN; - mei_reset(dev, 0); + mei_reset(dev); mutex_unlock(&dev->device_lock); @@ -233,3 +284,41 @@ EXPORT_SYMBOL_GPL(mei_stop); +void mei_device_init(struct mei_device *dev) +{ + /* setup our list array */ + INIT_LIST_HEAD(&dev->file_list); + INIT_LIST_HEAD(&dev->device_list); + mutex_init(&dev->device_lock); + init_waitqueue_head(&dev->wait_hw_ready); + init_waitqueue_head(&dev->wait_recvd_msg); + init_waitqueue_head(&dev->wait_stop_wd); + dev->dev_state = MEI_DEV_INITIALIZING; + dev->reset_count = 0; + + mei_io_list_init(&dev->read_list); + mei_io_list_init(&dev->write_list); + mei_io_list_init(&dev->write_waiting_list); + mei_io_list_init(&dev->ctrl_wr_list); + mei_io_list_init(&dev->ctrl_rd_list); + + INIT_DELAYED_WORK(&dev->timer_work, mei_timer); + INIT_WORK(&dev->init_work, mei_host_client_init); + INIT_WORK(&dev->reset_work, mei_reset_work); + + INIT_LIST_HEAD(&dev->wd_cl.link); + INIT_LIST_HEAD(&dev->iamthif_cl.link); + mei_io_list_init(&dev->amthif_cmd_list); + mei_io_list_init(&dev->amthif_rd_complete_list); + + bitmap_zero(dev->host_clients_map, MEI_CLIENTS_MAX); + dev->open_handle_count = 0; + + /* + * Reserving the first client ID + * 0: Reserved for MEI Bus Message communications + */ + bitmap_set(dev->host_clients_map, 0, 1); +} +EXPORT_SYMBOL_GPL(mei_device_init); + diff --git a/drivers/misc/mei/interrupt.c b/drivers/misc/mei/interrupt.c index 4b59cb742dee..f0fbb5179f80 100644 --- a/drivers/misc/mei/interrupt.c +++ b/drivers/misc/mei/interrupt.c @@ -31,7 +31,7 @@ /** - * mei_irq_compl_handler - dispatch complete handelers + * mei_irq_compl_handler - dispatch complete handlers * for the completed callbacks * * @dev - mei device @@ -113,13 +113,13 @@ static int mei_cl_irq_read_msg(struct mei_device *dev, if (cb->response_buffer.size == 0 || cb->response_buffer.data == NULL) { - dev_err(&dev->pdev->dev, "response buffer is not allocated.\n"); + cl_err(dev, cl, "response buffer is not allocated.\n"); list_del(&cb->list); return -ENOMEM; } if (cb->response_buffer.size < mei_hdr->length + cb->buf_idx) { - dev_dbg(&dev->pdev->dev, "message overflow. size %d len %d idx %ld\n", + cl_dbg(dev, cl, "message overflow. size %d len %d idx %ld\n", cb->response_buffer.size, mei_hdr->length, cb->buf_idx); buffer = krealloc(cb->response_buffer.data, @@ -127,7 +127,7 @@ static int mei_cl_irq_read_msg(struct mei_device *dev, GFP_KERNEL); if (!buffer) { - dev_err(&dev->pdev->dev, "allocation failed.\n"); + cl_err(dev, cl, "allocation failed.\n"); list_del(&cb->list); return -ENOMEM; } @@ -143,9 +143,7 @@ static int mei_cl_irq_read_msg(struct mei_device *dev, if (mei_hdr->msg_complete) { cl->status = 0; list_del(&cb->list); - dev_dbg(&dev->pdev->dev, "completed read H cl = %d, ME cl = %d, length = %lu\n", - cl->host_client_id, - cl->me_client_id, + cl_dbg(dev, cl, "completed read length = %lu\n", cb->buf_idx); list_add_tail(&cb->list, &complete_list->list); } @@ -218,9 +216,11 @@ static int mei_cl_irq_read(struct mei_cl *cl, struct mei_cl_cb *cb, s32 *slots, struct mei_cl_cb *cmpl_list) { struct mei_device *dev = cl->dev; - u32 msg_slots = mei_data2slots(sizeof(struct hbm_flow_control)); + int ret; + + if (*slots < msg_slots) { /* return the cancel routine */ list_del(&cb->list); @@ -229,12 +229,14 @@ static int mei_cl_irq_read(struct mei_cl *cl, struct mei_cl_cb *cb, *slots -= msg_slots; - if (mei_hbm_cl_flow_control_req(dev, cl)) { - cl->status = -ENODEV; + ret = mei_hbm_cl_flow_control_req(dev, cl); + if (ret) { + cl->status = ret; cb->buf_idx = 0; list_move_tail(&cb->list, &cmpl_list->list); - return -ENODEV; + return ret; } + list_move_tail(&cb->list, &dev->read_list.list); return 0; @@ -256,6 +258,7 @@ static int mei_cl_irq_ioctl(struct mei_cl *cl, struct mei_cl_cb *cb, s32 *slots, struct mei_cl_cb *cmpl_list) { struct mei_device *dev = cl->dev; + int ret; u32 msg_slots = mei_data2slots(sizeof(struct hbm_client_connect_request)); @@ -270,11 +273,12 @@ static int mei_cl_irq_ioctl(struct mei_cl *cl, struct mei_cl_cb *cb, cl->state = MEI_FILE_CONNECTING; - if (mei_hbm_cl_connect_req(dev, cl)) { - cl->status = -ENODEV; + ret = mei_hbm_cl_connect_req(dev, cl); + if (ret) { + cl->status = ret; cb->buf_idx = 0; list_del(&cb->list); - return -ENODEV; + return ret; } list_move_tail(&cb->list, &dev->ctrl_rd_list.list); @@ -297,13 +301,11 @@ int mei_irq_read_handler(struct mei_device *dev, struct mei_cl_cb *cmpl_list, s32 *slots) { struct mei_msg_hdr *mei_hdr; - struct mei_cl *cl_pos = NULL; - struct mei_cl *cl_next = NULL; - int ret = 0; + struct mei_cl *cl; + int ret; if (!dev->rd_msg_hdr) { dev->rd_msg_hdr = mei_read_hdr(dev); - dev_dbg(&dev->pdev->dev, "slots =%08x.\n", *slots); (*slots)--; dev_dbg(&dev->pdev->dev, "slots =%08x.\n", *slots); } @@ -311,61 +313,67 @@ int mei_irq_read_handler(struct mei_device *dev, dev_dbg(&dev->pdev->dev, MEI_HDR_FMT, MEI_HDR_PRM(mei_hdr)); if (mei_hdr->reserved || !dev->rd_msg_hdr) { - dev_dbg(&dev->pdev->dev, "corrupted message header.\n"); + dev_err(&dev->pdev->dev, "corrupted message header 0x%08X\n", + dev->rd_msg_hdr); ret = -EBADMSG; goto end; } - if (mei_hdr->host_addr || mei_hdr->me_addr) { - list_for_each_entry_safe(cl_pos, cl_next, - &dev->file_list, link) { - dev_dbg(&dev->pdev->dev, - "list_for_each_entry_safe read host" - " client = %d, ME client = %d\n", - cl_pos->host_client_id, - cl_pos->me_client_id); - if (mei_cl_hbm_equal(cl_pos, mei_hdr)) - break; - } - - if (&cl_pos->link == &dev->file_list) { - dev_dbg(&dev->pdev->dev, "corrupted message header\n"); - ret = -EBADMSG; - goto end; - } - } - if (((*slots) * sizeof(u32)) < mei_hdr->length) { - dev_err(&dev->pdev->dev, - "we can't read the message slots =%08x.\n", + if (mei_slots2data(*slots) < mei_hdr->length) { + dev_err(&dev->pdev->dev, "less data available than length=%08x.\n", *slots); /* we can't read the message */ ret = -ERANGE; goto end; } - /* decide where to read the message too */ - if (!mei_hdr->host_addr) { - dev_dbg(&dev->pdev->dev, "call mei_irq_thread_read_bus_message.\n"); - mei_hbm_dispatch(dev, mei_hdr); - dev_dbg(&dev->pdev->dev, "end mei_irq_thread_read_bus_message.\n"); - } else if (mei_hdr->host_addr == dev->iamthif_cl.host_client_id && - (MEI_FILE_CONNECTED == dev->iamthif_cl.state) && - (dev->iamthif_state == MEI_IAMTHIF_READING)) { + /* HBM message */ + if (mei_hdr->host_addr == 0 && mei_hdr->me_addr == 0) { + ret = mei_hbm_dispatch(dev, mei_hdr); + if (ret) { + dev_dbg(&dev->pdev->dev, "mei_hbm_dispatch failed ret = %d\n", + ret); + goto end; + } + goto reset_slots; + } - dev_dbg(&dev->pdev->dev, "call mei_irq_thread_read_iamthif_message.\n"); - dev_dbg(&dev->pdev->dev, MEI_HDR_FMT, MEI_HDR_PRM(mei_hdr)); + /* find recipient cl */ + list_for_each_entry(cl, &dev->file_list, link) { + if (mei_cl_hbm_equal(cl, mei_hdr)) { + cl_dbg(dev, cl, "got a message\n"); + break; + } + } + + /* if no recipient cl was found we assume corrupted header */ + if (&cl->link == &dev->file_list) { + dev_err(&dev->pdev->dev, "no destination client found 0x%08X\n", + dev->rd_msg_hdr); + ret = -EBADMSG; + goto end; + } + + if (mei_hdr->host_addr == dev->iamthif_cl.host_client_id && + MEI_FILE_CONNECTED == dev->iamthif_cl.state && + dev->iamthif_state == MEI_IAMTHIF_READING) { ret = mei_amthif_irq_read_msg(dev, mei_hdr, cmpl_list); - if (ret) + if (ret) { + dev_err(&dev->pdev->dev, "mei_amthif_irq_read_msg failed = %d\n", + ret); goto end; + } } else { - dev_dbg(&dev->pdev->dev, "call mei_cl_irq_read_msg.\n"); - dev_dbg(&dev->pdev->dev, MEI_HDR_FMT, MEI_HDR_PRM(mei_hdr)); ret = mei_cl_irq_read_msg(dev, mei_hdr, cmpl_list); - if (ret) + if (ret) { + dev_err(&dev->pdev->dev, "mei_cl_irq_read_msg failed = %d\n", + ret); goto end; + } } +reset_slots: /* reset the number of slots and header */ *slots = mei_count_full_read_slots(dev); dev->rd_msg_hdr = 0; @@ -423,12 +431,12 @@ int mei_irq_write_handler(struct mei_device *dev, struct mei_cl_cb *cmpl_list) if (MEI_WRITING == cl->writing_state && cb->fop_type == MEI_FOP_WRITE && cl != &dev->iamthif_cl) { - dev_dbg(&dev->pdev->dev, "MEI WRITE COMPLETE\n"); + cl_dbg(dev, cl, "MEI WRITE COMPLETE\n"); cl->writing_state = MEI_WRITE_COMPLETE; list_add_tail(&cb->list, &cmpl_list->list); } if (cl == &dev->iamthif_cl) { - dev_dbg(&dev->pdev->dev, "check iamthif flow control.\n"); + cl_dbg(dev, cl, "check iamthif flow control.\n"); if (dev->iamthif_flow_control_pending) { ret = mei_amthif_irq_read(dev, &slots); if (ret) @@ -509,13 +517,6 @@ int mei_irq_write_handler(struct mei_device *dev, struct mei_cl_cb *cmpl_list) cl = cb->cl; if (cl == NULL) continue; - if (mei_cl_flow_ctrl_creds(cl) <= 0) { - dev_dbg(&dev->pdev->dev, - "No flow control credentials for client %d, not sending.\n", - cl->host_client_id); - continue; - } - if (cl == &dev->iamthif_cl) ret = mei_amthif_irq_write_complete(cl, cb, &slots, cmpl_list); @@ -536,7 +537,6 @@ EXPORT_SYMBOL_GPL(mei_irq_write_handler); * * @work: pointer to the work_struct structure * - * NOTE: This function is called by timer interrupt work */ void mei_timer(struct work_struct *work) { @@ -551,24 +551,30 @@ void mei_timer(struct work_struct *work) mutex_lock(&dev->device_lock); - if (dev->dev_state != MEI_DEV_ENABLED) { - if (dev->dev_state == MEI_DEV_INIT_CLIENTS) { - if (dev->init_clients_timer) { - if (--dev->init_clients_timer == 0) { - dev_err(&dev->pdev->dev, "reset: init clients timeout hbm_state = %d.\n", - dev->hbm_state); - mei_reset(dev, 1); - } + + /* Catch interrupt stalls during HBM init handshake */ + if (dev->dev_state == MEI_DEV_INIT_CLIENTS && + dev->hbm_state != MEI_HBM_IDLE) { + + if (dev->init_clients_timer) { + if (--dev->init_clients_timer == 0) { + dev_err(&dev->pdev->dev, "timer: init clients timeout hbm_state = %d.\n", + dev->hbm_state); + mei_reset(dev); + goto out; } } - goto out; } + + if (dev->dev_state != MEI_DEV_ENABLED) + goto out; + /*** connect/disconnect timeouts ***/ list_for_each_entry_safe(cl_pos, cl_next, &dev->file_list, link) { if (cl_pos->timer_count) { if (--cl_pos->timer_count == 0) { - dev_err(&dev->pdev->dev, "reset: connect/disconnect timeout.\n"); - mei_reset(dev, 1); + dev_err(&dev->pdev->dev, "timer: connect/disconnect timeout.\n"); + mei_reset(dev); goto out; } } @@ -576,8 +582,8 @@ void mei_timer(struct work_struct *work) if (dev->iamthif_stall_timer) { if (--dev->iamthif_stall_timer == 0) { - dev_err(&dev->pdev->dev, "reset: amthif hanged.\n"); - mei_reset(dev, 1); + dev_err(&dev->pdev->dev, "timer: amthif hanged.\n"); + mei_reset(dev); dev->iamthif_msg_buf_size = 0; dev->iamthif_msg_buf_index = 0; dev->iamthif_canceled = false; @@ -630,7 +636,8 @@ void mei_timer(struct work_struct *work) } } out: - schedule_delayed_work(&dev->timer_work, 2 * HZ); + if (dev->dev_state != MEI_DEV_DISABLED) + schedule_delayed_work(&dev->timer_work, 2 * HZ); mutex_unlock(&dev->device_lock); } diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c index cabeddd66c1f..5424f8ff3f7f 100644 --- a/drivers/misc/mei/main.c +++ b/drivers/misc/mei/main.c @@ -48,7 +48,7 @@ * * @inode: pointer to inode structure * @file: pointer to file structure - e + * * returns 0 on success, <0 on error */ static int mei_open(struct inode *inode, struct file *file) @@ -60,48 +60,45 @@ static int mei_open(struct inode *inode, struct file *file) int err; - err = -ENODEV; if (!misc->parent) - goto out; + return -ENODEV; pdev = container_of(misc->parent, struct pci_dev, dev); dev = pci_get_drvdata(pdev); if (!dev) - goto out; + return -ENODEV; mutex_lock(&dev->device_lock); - err = -ENOMEM; - cl = mei_cl_allocate(dev); - if (!cl) - goto out_unlock; + + cl = NULL; err = -ENODEV; if (dev->dev_state != MEI_DEV_ENABLED) { dev_dbg(&dev->pdev->dev, "dev_state != MEI_ENABLED dev_state = %s\n", mei_dev_state_str(dev->dev_state)); - goto out_unlock; - } - err = -EMFILE; - if (dev->open_handle_count >= MEI_MAX_OPEN_HANDLE_COUNT) { - dev_err(&dev->pdev->dev, "open_handle_count exceded %d", - MEI_MAX_OPEN_HANDLE_COUNT); - goto out_unlock; + goto err_unlock; } + err = -ENOMEM; + cl = mei_cl_allocate(dev); + if (!cl) + goto err_unlock; + + /* open_handle_count check is handled in the mei_cl_link */ err = mei_cl_link(cl, MEI_HOST_CLIENT_ID_ANY); if (err) - goto out_unlock; + goto err_unlock; file->private_data = cl; + mutex_unlock(&dev->device_lock); return nonseekable_open(inode, file); -out_unlock: +err_unlock: mutex_unlock(&dev->device_lock); kfree(cl); -out: return err; } @@ -144,10 +141,6 @@ static int mei_release(struct inode *inode, struct file *file) cl->host_client_id, cl->me_client_id); - if (dev->open_handle_count > 0) { - clear_bit(cl->host_client_id, dev->host_clients_map); - dev->open_handle_count--; - } mei_cl_unlink(cl); @@ -165,10 +158,7 @@ static int mei_release(struct inode *inode, struct file *file) file->private_data = NULL; - if (cb) { - mei_io_cb_free(cb); - cb = NULL; - } + mei_io_cb_free(cb); kfree(cl); out: @@ -203,12 +193,18 @@ static ssize_t mei_read(struct file *file, char __user *ubuf, dev = cl->dev; + mutex_lock(&dev->device_lock); if (dev->dev_state != MEI_DEV_ENABLED) { rets = -ENODEV; goto out; } + if (length == 0) { + rets = 0; + goto out; + } + if (cl == &dev->iamthif_cl) { rets = mei_amthif_read(dev, file, ubuf, length, offset); goto out; @@ -347,8 +343,14 @@ static ssize_t mei_write(struct file *file, const char __user *ubuf, rets = -ENODEV; goto out; } - if (length > dev->me_clients[id].props.max_msg_length || length <= 0) { - rets = -EMSGSIZE; + + if (length == 0) { + rets = 0; + goto out; + } + + if (length > dev->me_clients[id].props.max_msg_length) { + rets = -EFBIG; goto out; } @@ -401,8 +403,11 @@ static ssize_t mei_write(struct file *file, const char __user *ubuf, goto out; rets = copy_from_user(write_cb->request_buffer.data, ubuf, length); - if (rets) + if (rets) { + dev_err(&dev->pdev->dev, "failed to copy data from userland\n"); + rets = -EFAULT; goto out; + } if (cl == &dev->iamthif_cl) { rets = mei_amthif_write(dev, write_cb); @@ -489,11 +494,11 @@ static int mei_ioctl_connect_client(struct file *file, rets = -ENODEV; goto end; } - clear_bit(cl->host_client_id, dev->host_clients_map); mei_cl_unlink(cl); kfree(cl); cl = NULL; + dev->iamthif_open_count++; file->private_data = &dev->iamthif_cl; client = &data->out_client_properties; @@ -564,7 +569,7 @@ static long mei_ioctl(struct file *file, unsigned int cmd, unsigned long data) dev_dbg(&dev->pdev->dev, "copy connect data from user\n"); if (copy_from_user(connect_data, (char __user *)data, sizeof(struct mei_connect_client_data))) { - dev_dbg(&dev->pdev->dev, "failed to copy data from userland\n"); + dev_err(&dev->pdev->dev, "failed to copy data from userland\n"); rets = -EFAULT; goto out; } diff --git a/drivers/misc/mei/mei_dev.h b/drivers/misc/mei/mei_dev.h index 456b322013e2..f7de95b4cdd9 100644 --- a/drivers/misc/mei/mei_dev.h +++ b/drivers/misc/mei/mei_dev.h @@ -61,11 +61,16 @@ extern const uuid_le mei_wd_guid; #define MEI_CLIENTS_MAX 256 /* + * maximum number of consecutive resets + */ +#define MEI_MAX_CONSEC_RESET 3 + +/* * Number of File descriptors/handles * that can be opened to the driver. * * Limit to 255: 256 Total Clients - * minus internal client for MEI Bus Messags + * minus internal client for MEI Bus Messages */ #define MEI_MAX_OPEN_HANDLE_COUNT (MEI_CLIENTS_MAX - 1) @@ -178,9 +183,10 @@ struct mei_cl_cb { unsigned long buf_idx; unsigned long read_time; struct file *file_object; + u32 internal:1; }; -/* MEI client instance carried as file->pirvate_data*/ +/* MEI client instance carried as file->private_data*/ struct mei_cl { struct list_head link; struct mei_device *dev; @@ -326,6 +332,7 @@ struct mei_cl_device { /** * struct mei_device - MEI private device struct + * @reset_count - limits the number of consecutive resets * @hbm_state - state of host bus message protocol * @mem_addr - mem mapped base register address @@ -369,6 +376,7 @@ struct mei_device { /* * mei device states */ + unsigned long reset_count; enum mei_dev_state dev_state; enum mei_hbm_state hbm_state; u16 init_clients_timer; @@ -414,6 +422,7 @@ struct mei_device { struct file *iamthif_file_object; struct mei_cl iamthif_cl; struct mei_cl_cb *iamthif_current_cb; + long iamthif_open_count; int iamthif_mtu; unsigned long iamthif_timer; u32 iamthif_stall_timer; @@ -426,6 +435,7 @@ struct mei_device { bool iamthif_canceled; struct work_struct init_work; + struct work_struct reset_work; /* List of bus devices */ struct list_head device_list; @@ -455,13 +465,25 @@ static inline u32 mei_data2slots(size_t length) return DIV_ROUND_UP(sizeof(struct mei_msg_hdr) + length, 4); } +/** + * mei_slots2data- get data in slots - bytes from slots + * @slots - number of available slots + * returns - number of bytes in slots + */ +static inline u32 mei_slots2data(int slots) +{ + return slots * 4; +} + /* * mei init function prototypes */ void mei_device_init(struct mei_device *dev); -void mei_reset(struct mei_device *dev, int interrupts); +int mei_reset(struct mei_device *dev); int mei_start(struct mei_device *dev); +int mei_restart(struct mei_device *dev); void mei_stop(struct mei_device *dev); +void mei_cancel_work(struct mei_device *dev); /* * MEI interrupt functions prototype @@ -509,7 +531,7 @@ int mei_amthif_irq_read(struct mei_device *dev, s32 *slots); * NFC functions */ int mei_nfc_host_init(struct mei_device *dev); -void mei_nfc_host_exit(void); +void mei_nfc_host_exit(struct mei_device *dev); /* * NFC Client UUID @@ -625,9 +647,9 @@ static inline void mei_dbgfs_deregister(struct mei_device *dev) {} int mei_register(struct mei_device *dev); void mei_deregister(struct mei_device *dev); -#define MEI_HDR_FMT "hdr:host=%02d me=%02d len=%d comp=%1d" +#define MEI_HDR_FMT "hdr:host=%02d me=%02d len=%d internal=%1d comp=%1d" #define MEI_HDR_PRM(hdr) \ (hdr)->host_addr, (hdr)->me_addr, \ - (hdr)->length, (hdr)->msg_complete + (hdr)->length, (hdr)->internal, (hdr)->msg_complete #endif diff --git a/drivers/misc/mei/nfc.c b/drivers/misc/mei/nfc.c index d0c6907dfd92..a58320c0c049 100644 --- a/drivers/misc/mei/nfc.c +++ b/drivers/misc/mei/nfc.c @@ -92,7 +92,7 @@ struct mei_nfc_hci_hdr { * @cl: NFC host client * @cl_info: NFC info host client * @init_work: perform connection to the info client - * @fw_ivn: NFC Intervace Version Number + * @fw_ivn: NFC Interface Version Number * @vendor_id: NFC manufacturer ID * @radio_type: NFC radio type */ @@ -163,7 +163,7 @@ static int mei_nfc_build_bus_name(struct mei_nfc_dev *ndev) return 0; default: - dev_err(&dev->pdev->dev, "Unknow radio type 0x%x\n", + dev_err(&dev->pdev->dev, "Unknown radio type 0x%x\n", ndev->radio_type); return -EINVAL; @@ -175,14 +175,14 @@ static int mei_nfc_build_bus_name(struct mei_nfc_dev *ndev) ndev->bus_name = "pn544"; return 0; default: - dev_err(&dev->pdev->dev, "Unknow radio type 0x%x\n", + dev_err(&dev->pdev->dev, "Unknown radio type 0x%x\n", ndev->radio_type); return -EINVAL; } default: - dev_err(&dev->pdev->dev, "Unknow vendor ID 0x%x\n", + dev_err(&dev->pdev->dev, "Unknown vendor ID 0x%x\n", ndev->vendor_id); return -EINVAL; @@ -428,7 +428,7 @@ static void mei_nfc_init(struct work_struct *work) mutex_unlock(&dev->device_lock); if (mei_nfc_if_version(ndev) < 0) { - dev_err(&dev->pdev->dev, "Could not get the NFC interfave version"); + dev_err(&dev->pdev->dev, "Could not get the NFC interface version"); goto err; } @@ -469,7 +469,9 @@ static void mei_nfc_init(struct work_struct *work) return; err: + mutex_lock(&dev->device_lock); mei_nfc_free(ndev); + mutex_unlock(&dev->device_lock); return; } @@ -481,12 +483,15 @@ int mei_nfc_host_init(struct mei_device *dev) struct mei_cl *cl_info, *cl = NULL; int i, ret; - /* already initialzed */ + /* already initialized */ if (ndev->cl_info) return 0; - cl_info = mei_cl_allocate(dev); - cl = mei_cl_allocate(dev); + ndev->cl_info = mei_cl_allocate(dev); + ndev->cl = mei_cl_allocate(dev); + + cl = ndev->cl; + cl_info = ndev->cl_info; if (!cl || !cl_info) { ret = -ENOMEM; @@ -527,10 +532,9 @@ int mei_nfc_host_init(struct mei_device *dev) cl->device_uuid = mei_nfc_guid; + list_add_tail(&cl->device_link, &dev->device_list); - ndev->cl_info = cl_info; - ndev->cl = cl; ndev->req_id = 1; INIT_WORK(&ndev->init_work, mei_nfc_init); @@ -545,12 +549,16 @@ err: return ret; } -void mei_nfc_host_exit(void) +void mei_nfc_host_exit(struct mei_device *dev) { struct mei_nfc_dev *ndev = &nfc_dev; + cancel_work_sync(&ndev->init_work); + + mutex_lock(&dev->device_lock); if (ndev->cl && ndev->cl->device) mei_cl_remove_device(ndev->cl->device); mei_nfc_free(ndev); + mutex_unlock(&dev->device_lock); } diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index 1b3844e82379..ddadd08956f4 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -76,8 +76,11 @@ static DEFINE_PCI_DEVICE_TABLE(mei_me_pci_tbl) = { {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_PPT_1)}, {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_PPT_2)}, {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_PPT_3)}, - {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_LPT)}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_LPT_H)}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_LPT_W)}, {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_LPT_LP)}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_LPT_HR)}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_WPT_LP)}, /* required last entry */ {0, } @@ -141,6 +144,21 @@ static int mei_me_probe(struct pci_dev *pdev, const struct pci_device_id *ent) dev_err(&pdev->dev, "failed to get pci regions.\n"); goto disable_device; } + + if (dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)) || + dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64))) { + + err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); + if (err) + err = dma_set_coherent_mask(&pdev->dev, + DMA_BIT_MASK(32)); + } + if (err) { + dev_err(&pdev->dev, "No usable DMA configuration, aborting\n"); + goto release_regions; + } + + /* allocates and initializes the mei dev structure */ dev = mei_me_dev_init(pdev); if (!dev) { @@ -189,13 +207,13 @@ static int mei_me_probe(struct pci_dev *pdev, const struct pci_device_id *ent) schedule_delayed_work(&dev->timer_work, HZ); - pr_debug("initialization successful.\n"); + dev_dbg(&pdev->dev, "initialization successful.\n"); return 0; release_irq: + mei_cancel_work(dev); mei_disable_interrupts(dev); - flush_scheduled_work(); free_irq(pdev->irq, dev); disable_msi: pci_disable_msi(pdev); @@ -231,7 +249,7 @@ static void mei_me_remove(struct pci_dev *pdev) hw = to_me_hw(dev); - dev_err(&pdev->dev, "stop\n"); + dev_dbg(&pdev->dev, "stop\n"); mei_stop(dev); /* disable interrupts */ @@ -239,7 +257,6 @@ static void mei_me_remove(struct pci_dev *pdev) free_irq(pdev->irq, dev); pci_disable_msi(pdev); - pci_set_drvdata(pdev, NULL); if (hw->mem_addr) pci_iounmap(pdev, hw->mem_addr); @@ -262,7 +279,7 @@ static int mei_me_pci_suspend(struct device *device) if (!dev) return -ENODEV; - dev_err(&pdev->dev, "suspend\n"); + dev_dbg(&pdev->dev, "suspend\n"); mei_stop(dev); @@ -304,16 +321,14 @@ static int mei_me_pci_resume(struct device *device) return err; } - mutex_lock(&dev->device_lock); - dev->dev_state = MEI_DEV_POWER_UP; - mei_clear_interrupts(dev); - mei_reset(dev, 1); - mutex_unlock(&dev->device_lock); + err = mei_restart(dev); + if (err) + return err; /* Start timer if stopped in suspend */ schedule_delayed_work(&dev->timer_work, HZ); - return err; + return 0; } static SIMPLE_DEV_PM_OPS(mei_me_pm_ops, mei_me_pci_suspend, mei_me_pci_resume); #define MEI_ME_PM_OPS (&mei_me_pm_ops) diff --git a/drivers/misc/mei/wd.c b/drivers/misc/mei/wd.c index b8921432e89d..f70945ed96f6 100644 --- a/drivers/misc/mei/wd.c +++ b/drivers/misc/mei/wd.c @@ -60,7 +60,7 @@ static void mei_wd_set_start_timeout(struct mei_device *dev, u16 timeout) int mei_wd_host_init(struct mei_device *dev) { struct mei_cl *cl = &dev->wd_cl; - int i; + int id; int ret; mei_cl_init(cl, dev); @@ -70,19 +70,19 @@ int mei_wd_host_init(struct mei_device *dev) /* check for valid client id */ - i = mei_me_cl_by_uuid(dev, &mei_wd_guid); - if (i < 0) { + id = mei_me_cl_by_uuid(dev, &mei_wd_guid); + if (id < 0) { dev_info(&dev->pdev->dev, "wd: failed to find the client\n"); - return -ENOENT; + return id; } - cl->me_client_id = dev->me_clients[i].client_id; + cl->me_client_id = dev->me_clients[id].client_id; ret = mei_cl_link(cl, MEI_WD_HOST_CLIENT_ID); if (ret < 0) { dev_info(&dev->pdev->dev, "wd: failed link client\n"); - return -ENOENT; + return ret; } cl->state = MEI_FILE_CONNECTING; @@ -115,6 +115,7 @@ int mei_wd_send(struct mei_device *dev) hdr.me_addr = dev->wd_cl.me_client_id; hdr.msg_complete = 1; hdr.reserved = 0; + hdr.internal = 0; if (!memcmp(dev->wd_data, mei_start_wd_params, MEI_WD_HDR_SIZE)) hdr.length = MEI_WD_START_MSG_SIZE; diff --git a/drivers/misc/mic/Kconfig b/drivers/misc/mic/Kconfig new file mode 100644 index 000000000000..e42b331edbc6 --- /dev/null +++ b/drivers/misc/mic/Kconfig @@ -0,0 +1,39 @@ +comment "Intel MIC Host Driver" + +config INTEL_MIC_HOST + tristate "Intel MIC Host Driver" + depends on 64BIT && PCI && X86 + select VHOST_RING + default N + help + This enables Host Driver support for the Intel Many Integrated + Core (MIC) family of PCIe form factor coprocessor devices that + run a 64 bit Linux OS. The driver manages card OS state and + enables communication between host and card. Intel MIC X100 + devices are currently supported. + + If you are building a host kernel with an Intel MIC device then + say M (recommended) or Y, else say N. If unsure say N. + + More information about the Intel MIC family as well as the Linux + OS and tools for MIC to use with this driver are available from + <http://software.intel.com/en-us/mic-developer>. + +comment "Intel MIC Card Driver" + +config INTEL_MIC_CARD + tristate "Intel MIC Card Driver" + depends on 64BIT && X86 + select VIRTIO + default N + help + This enables card driver support for the Intel Many Integrated + Core (MIC) device family. The card driver communicates shutdown/ + crash events to the host and allows registration/configuration of + virtio devices. Intel MIC X100 devices are currently supported. + + If you are building a card kernel for an Intel MIC device then + say M (recommended) or Y, else say N. If unsure say N. + + For more information see + <http://software.intel.com/en-us/mic-developer>. diff --git a/drivers/misc/mic/Makefile b/drivers/misc/mic/Makefile new file mode 100644 index 000000000000..05b34d683a58 --- /dev/null +++ b/drivers/misc/mic/Makefile @@ -0,0 +1,6 @@ +# +# Makefile - Intel MIC Linux driver. +# Copyright(c) 2013, Intel Corporation. +# +obj-$(CONFIG_INTEL_MIC_HOST) += host/ +obj-$(CONFIG_INTEL_MIC_CARD) += card/ diff --git a/drivers/misc/mic/card/Makefile b/drivers/misc/mic/card/Makefile new file mode 100644 index 000000000000..69d58bef92ce --- /dev/null +++ b/drivers/misc/mic/card/Makefile @@ -0,0 +1,11 @@ +# +# Makefile - Intel MIC Linux driver. +# Copyright(c) 2013, Intel Corporation. +# +ccflags-y += -DINTEL_MIC_CARD + +obj-$(CONFIG_INTEL_MIC_CARD) += mic_card.o +mic_card-y += mic_x100.o +mic_card-y += mic_device.o +mic_card-y += mic_debugfs.o +mic_card-y += mic_virtio.o diff --git a/drivers/misc/mic/card/mic_debugfs.c b/drivers/misc/mic/card/mic_debugfs.c new file mode 100644 index 000000000000..421b3d7911df --- /dev/null +++ b/drivers/misc/mic/card/mic_debugfs.c @@ -0,0 +1,130 @@ +/* + * Intel MIC Platform Software Stack (MPSS) + * + * Copyright(c) 2013 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Disclaimer: The codes contained in these modules may be specific to + * the Intel Software Development Platform codenamed: Knights Ferry, and + * the Intel product codenamed: Knights Corner, and are not backward + * compatible with other Intel products. Additionally, Intel will NOT + * support the codes or instruction set in future products. + * + * Intel MIC Card driver. + * + */ +#include <linux/debugfs.h> +#include <linux/delay.h> +#include <linux/seq_file.h> +#include <linux/interrupt.h> +#include <linux/device.h> + +#include "../common/mic_dev.h" +#include "mic_device.h" + +/* Debugfs parent dir */ +static struct dentry *mic_dbg; + +/** + * mic_intr_test - Send interrupts to host. + */ +static int mic_intr_test(struct seq_file *s, void *unused) +{ + struct mic_driver *mdrv = s->private; + struct mic_device *mdev = &mdrv->mdev; + + mic_send_intr(mdev, 0); + msleep(1000); + mic_send_intr(mdev, 1); + msleep(1000); + mic_send_intr(mdev, 2); + msleep(1000); + mic_send_intr(mdev, 3); + msleep(1000); + + return 0; +} + +static int mic_intr_test_open(struct inode *inode, struct file *file) +{ + return single_open(file, mic_intr_test, inode->i_private); +} + +static int mic_intr_test_release(struct inode *inode, struct file *file) +{ + return single_release(inode, file); +} + +static const struct file_operations intr_test_ops = { + .owner = THIS_MODULE, + .open = mic_intr_test_open, + .read = seq_read, + .llseek = seq_lseek, + .release = mic_intr_test_release +}; + +/** + * mic_create_card_debug_dir - Initialize MIC debugfs entries. + */ +void __init mic_create_card_debug_dir(struct mic_driver *mdrv) +{ + struct dentry *d; + + if (!mic_dbg) + return; + + mdrv->dbg_dir = debugfs_create_dir(mdrv->name, mic_dbg); + if (!mdrv->dbg_dir) { + dev_err(mdrv->dev, "Cant create dbg_dir %s\n", mdrv->name); + return; + } + + d = debugfs_create_file("intr_test", 0444, mdrv->dbg_dir, + mdrv, &intr_test_ops); + + if (!d) { + dev_err(mdrv->dev, + "Cant create dbg intr_test %s\n", mdrv->name); + return; + } +} + +/** + * mic_delete_card_debug_dir - Uninitialize MIC debugfs entries. + */ +void mic_delete_card_debug_dir(struct mic_driver *mdrv) +{ + if (!mdrv->dbg_dir) + return; + + debugfs_remove_recursive(mdrv->dbg_dir); +} + +/** + * mic_init_card_debugfs - Initialize global debugfs entry. + */ +void __init mic_init_card_debugfs(void) +{ + mic_dbg = debugfs_create_dir(KBUILD_MODNAME, NULL); + if (!mic_dbg) + pr_err("can't create debugfs dir\n"); +} + +/** + * mic_exit_card_debugfs - Uninitialize global debugfs entry + */ +void mic_exit_card_debugfs(void) +{ + debugfs_remove(mic_dbg); +} diff --git a/drivers/misc/mic/card/mic_device.c b/drivers/misc/mic/card/mic_device.c new file mode 100644 index 000000000000..d0980ff96833 --- /dev/null +++ b/drivers/misc/mic/card/mic_device.c @@ -0,0 +1,305 @@ +/* + * Intel MIC Platform Software Stack (MPSS) + * + * Copyright(c) 2013 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Disclaimer: The codes contained in these modules may be specific to + * the Intel Software Development Platform codenamed: Knights Ferry, and + * the Intel product codenamed: Knights Corner, and are not backward + * compatible with other Intel products. Additionally, Intel will NOT + * support the codes or instruction set in future products. + * + * Intel MIC Card driver. + * + */ +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/interrupt.h> +#include <linux/reboot.h> + +#include <linux/mic_common.h> +#include "../common/mic_dev.h" +#include "mic_device.h" +#include "mic_virtio.h" + +static struct mic_driver *g_drv; +static struct mic_irq *shutdown_cookie; + +static void mic_notify_host(u8 state) +{ + struct mic_driver *mdrv = g_drv; + struct mic_bootparam __iomem *bootparam = mdrv->dp; + + iowrite8(state, &bootparam->shutdown_status); + dev_dbg(mdrv->dev, "%s %d system_state %d\n", + __func__, __LINE__, state); + mic_send_intr(&mdrv->mdev, ioread8(&bootparam->c2h_shutdown_db)); +} + +static int mic_panic_event(struct notifier_block *this, unsigned long event, + void *ptr) +{ + struct mic_driver *mdrv = g_drv; + struct mic_bootparam __iomem *bootparam = mdrv->dp; + + iowrite8(-1, &bootparam->h2c_config_db); + iowrite8(-1, &bootparam->h2c_shutdown_db); + mic_notify_host(MIC_CRASHED); + return NOTIFY_DONE; +} + +static struct notifier_block mic_panic = { + .notifier_call = mic_panic_event, +}; + +static irqreturn_t mic_shutdown_isr(int irq, void *data) +{ + struct mic_driver *mdrv = g_drv; + struct mic_bootparam __iomem *bootparam = mdrv->dp; + + mic_ack_interrupt(&g_drv->mdev); + if (ioread8(&bootparam->shutdown_card)) + orderly_poweroff(true); + return IRQ_HANDLED; +} + +static int mic_shutdown_init(void) +{ + int rc = 0; + struct mic_driver *mdrv = g_drv; + struct mic_bootparam __iomem *bootparam = mdrv->dp; + int shutdown_db; + + shutdown_db = mic_next_card_db(); + shutdown_cookie = mic_request_card_irq(mic_shutdown_isr, + "Shutdown", mdrv, shutdown_db); + if (IS_ERR(shutdown_cookie)) + rc = PTR_ERR(shutdown_cookie); + else + iowrite8(shutdown_db, &bootparam->h2c_shutdown_db); + return rc; +} + +static void mic_shutdown_uninit(void) +{ + struct mic_driver *mdrv = g_drv; + struct mic_bootparam __iomem *bootparam = mdrv->dp; + + iowrite8(-1, &bootparam->h2c_shutdown_db); + mic_free_card_irq(shutdown_cookie, mdrv); +} + +static int __init mic_dp_init(void) +{ + struct mic_driver *mdrv = g_drv; + struct mic_device *mdev = &mdrv->mdev; + struct mic_bootparam __iomem *bootparam; + u64 lo, hi, dp_dma_addr; + u32 magic; + + lo = mic_read_spad(&mdrv->mdev, MIC_DPLO_SPAD); + hi = mic_read_spad(&mdrv->mdev, MIC_DPHI_SPAD); + + dp_dma_addr = lo | (hi << 32); + mdrv->dp = mic_card_map(mdev, dp_dma_addr, MIC_DP_SIZE); + if (!mdrv->dp) { + dev_err(mdrv->dev, "Cannot remap Aperture BAR\n"); + return -ENOMEM; + } + bootparam = mdrv->dp; + magic = ioread32(&bootparam->magic); + if (MIC_MAGIC != magic) { + dev_err(mdrv->dev, "bootparam magic mismatch 0x%x\n", magic); + return -EIO; + } + return 0; +} + +/* Uninitialize the device page */ +static void mic_dp_uninit(void) +{ + mic_card_unmap(&g_drv->mdev, g_drv->dp); +} + +/** + * mic_request_card_irq - request an irq. + * + * @func: The callback function that handles the interrupt. + * @name: The ASCII name of the callee requesting the irq. + * @data: private data that is returned back when calling the + * function handler. + * @index: The doorbell index of the requester. + * + * returns: The cookie that is transparent to the caller. Passed + * back when calling mic_free_irq. An appropriate error code + * is returned on failure. Caller needs to use IS_ERR(return_val) + * to check for failure and PTR_ERR(return_val) to obtained the + * error code. + * + */ +struct mic_irq *mic_request_card_irq(irqreturn_t (*func)(int irq, void *data), + const char *name, void *data, int index) +{ + int rc = 0; + unsigned long cookie; + struct mic_driver *mdrv = g_drv; + + rc = request_irq(mic_db_to_irq(mdrv, index), func, + 0, name, data); + if (rc) { + dev_err(mdrv->dev, "request_irq failed rc = %d\n", rc); + goto err; + } + mdrv->irq_info.irq_usage_count[index]++; + cookie = index; + return (struct mic_irq *)cookie; +err: + return ERR_PTR(rc); +} + +/** + * mic_free_card_irq - free irq. + * + * @cookie: cookie obtained during a successful call to mic_request_irq + * @data: private data specified by the calling function during the + * mic_request_irq + * + * returns: none. + */ +void mic_free_card_irq(struct mic_irq *cookie, void *data) +{ + int index; + struct mic_driver *mdrv = g_drv; + + index = (unsigned long)cookie & 0xFFFFU; + free_irq(mic_db_to_irq(mdrv, index), data); + mdrv->irq_info.irq_usage_count[index]--; +} + +/** + * mic_next_card_db - Get the doorbell with minimum usage count. + * + * Returns the irq index. + */ +int mic_next_card_db(void) +{ + int i; + int index = 0; + struct mic_driver *mdrv = g_drv; + + for (i = 0; i < mdrv->intr_info.num_intr; i++) { + if (mdrv->irq_info.irq_usage_count[i] < + mdrv->irq_info.irq_usage_count[index]) + index = i; + } + + return index; +} + +/** + * mic_init_irq - Initialize irq information. + * + * Returns 0 in success. Appropriate error code on failure. + */ +static int mic_init_irq(void) +{ + struct mic_driver *mdrv = g_drv; + + mdrv->irq_info.irq_usage_count = kzalloc((sizeof(u32) * + mdrv->intr_info.num_intr), + GFP_KERNEL); + if (!mdrv->irq_info.irq_usage_count) + return -ENOMEM; + return 0; +} + +/** + * mic_uninit_irq - Uninitialize irq information. + * + * None. + */ +static void mic_uninit_irq(void) +{ + struct mic_driver *mdrv = g_drv; + + kfree(mdrv->irq_info.irq_usage_count); +} + +/* + * mic_driver_init - MIC driver initialization tasks. + * + * Returns 0 in success. Appropriate error code on failure. + */ +int __init mic_driver_init(struct mic_driver *mdrv) +{ + int rc; + + g_drv = mdrv; + /* + * Unloading the card module is not supported. The MIC card module + * handles fundamental operations like host/card initiated shutdowns + * and informing the host about card crashes and cannot be unloaded. + */ + if (!try_module_get(mdrv->dev->driver->owner)) { + rc = -ENODEV; + goto done; + } + rc = mic_dp_init(); + if (rc) + goto put; + rc = mic_init_irq(); + if (rc) + goto dp_uninit; + rc = mic_shutdown_init(); + if (rc) + goto irq_uninit; + rc = mic_devices_init(mdrv); + if (rc) + goto shutdown_uninit; + mic_create_card_debug_dir(mdrv); + atomic_notifier_chain_register(&panic_notifier_list, &mic_panic); +done: + return rc; +shutdown_uninit: + mic_shutdown_uninit(); +irq_uninit: + mic_uninit_irq(); +dp_uninit: + mic_dp_uninit(); +put: + module_put(mdrv->dev->driver->owner); + return rc; +} + +/* + * mic_driver_uninit - MIC driver uninitialization tasks. + * + * Returns None + */ +void mic_driver_uninit(struct mic_driver *mdrv) +{ + mic_delete_card_debug_dir(mdrv); + mic_devices_uninit(mdrv); + /* + * Inform the host about the shutdown status i.e. poweroff/restart etc. + * The module cannot be unloaded so the only code path to call + * mic_devices_uninit(..) is the shutdown callback. + */ + mic_notify_host(system_state); + mic_shutdown_uninit(); + mic_uninit_irq(); + mic_dp_uninit(); + module_put(mdrv->dev->driver->owner); +} diff --git a/drivers/misc/mic/card/mic_device.h b/drivers/misc/mic/card/mic_device.h new file mode 100644 index 000000000000..347b9b3b7916 --- /dev/null +++ b/drivers/misc/mic/card/mic_device.h @@ -0,0 +1,133 @@ +/* + * Intel MIC Platform Software Stack (MPSS) + * + * Copyright(c) 2013 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Disclaimer: The codes contained in these modules may be specific to + * the Intel Software Development Platform codenamed: Knights Ferry, and + * the Intel product codenamed: Knights Corner, and are not backward + * compatible with other Intel products. Additionally, Intel will NOT + * support the codes or instruction set in future products. + * + * Intel MIC Card driver. + * + */ +#ifndef _MIC_CARD_DEVICE_H_ +#define _MIC_CARD_DEVICE_H_ + +#include <linux/workqueue.h> +#include <linux/io.h> + +/** + * struct mic_intr_info - Contains h/w specific interrupt sources info + * + * @num_intr: The number of irqs available + */ +struct mic_intr_info { + u32 num_intr; +}; + +/** + * struct mic_irq_info - OS specific irq information + * + * @irq_usage_count: usage count array tracking the number of sources + * assigned for each irq. + */ +struct mic_irq_info { + int *irq_usage_count; +}; + +/** + * struct mic_device - MIC device information. + * + * @mmio: MMIO bar information. + */ +struct mic_device { + struct mic_mw mmio; +}; + +/** + * struct mic_driver - MIC card driver information. + * + * @name: Name for MIC driver. + * @dbg_dir: debugfs directory of this MIC device. + * @dev: The device backing this MIC. + * @dp: The pointer to the virtio device page. + * @mdev: MIC device information for the host. + * @hotplug_work: Hot plug work for adding/removing virtio devices. + * @irq_info: The OS specific irq information + * @intr_info: H/W specific interrupt information. + */ +struct mic_driver { + char name[20]; + struct dentry *dbg_dir; + struct device *dev; + void __iomem *dp; + struct mic_device mdev; + struct work_struct hotplug_work; + struct mic_irq_info irq_info; + struct mic_intr_info intr_info; +}; + +/** + * struct mic_irq - opaque pointer used as cookie + */ +struct mic_irq; + +/** + * mic_mmio_read - read from an MMIO register. + * @mw: MMIO register base virtual address. + * @offset: register offset. + * + * RETURNS: register value. + */ +static inline u32 mic_mmio_read(struct mic_mw *mw, u32 offset) +{ + return ioread32(mw->va + offset); +} + +/** + * mic_mmio_write - write to an MMIO register. + * @mw: MMIO register base virtual address. + * @val: the data value to put into the register + * @offset: register offset. + * + * RETURNS: none. + */ +static inline void +mic_mmio_write(struct mic_mw *mw, u32 val, u32 offset) +{ + iowrite32(val, mw->va + offset); +} + +int mic_driver_init(struct mic_driver *mdrv); +void mic_driver_uninit(struct mic_driver *mdrv); +int mic_next_card_db(void); +struct mic_irq *mic_request_card_irq(irqreturn_t (*func)(int irq, void *data), + const char *name, void *data, int intr_src); +void mic_free_card_irq(struct mic_irq *cookie, void *data); +u32 mic_read_spad(struct mic_device *mdev, unsigned int idx); +void mic_send_intr(struct mic_device *mdev, int doorbell); +int mic_db_to_irq(struct mic_driver *mdrv, int db); +u32 mic_ack_interrupt(struct mic_device *mdev); +void mic_hw_intr_init(struct mic_driver *mdrv); +void __iomem * +mic_card_map(struct mic_device *mdev, dma_addr_t addr, size_t size); +void mic_card_unmap(struct mic_device *mdev, void __iomem *addr); +void __init mic_create_card_debug_dir(struct mic_driver *mdrv); +void mic_delete_card_debug_dir(struct mic_driver *mdrv); +void __init mic_init_card_debugfs(void); +void mic_exit_card_debugfs(void); +#endif diff --git a/drivers/misc/mic/card/mic_virtio.c b/drivers/misc/mic/card/mic_virtio.c new file mode 100644 index 000000000000..653799b96bfa --- /dev/null +++ b/drivers/misc/mic/card/mic_virtio.c @@ -0,0 +1,633 @@ +/* + * Intel MIC Platform Software Stack (MPSS) + * + * Copyright(c) 2013 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Disclaimer: The codes contained in these modules may be specific to + * the Intel Software Development Platform codenamed: Knights Ferry, and + * the Intel product codenamed: Knights Corner, and are not backward + * compatible with other Intel products. Additionally, Intel will NOT + * support the codes or instruction set in future products. + * + * Adapted from: + * + * virtio for kvm on s390 + * + * Copyright IBM Corp. 2008 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License (version 2 only) + * as published by the Free Software Foundation. + * + * Author(s): Christian Borntraeger <borntraeger@de.ibm.com> + * + * Intel MIC Card driver. + * + */ +#include <linux/delay.h> +#include <linux/slab.h> +#include <linux/virtio_config.h> + +#include "../common/mic_dev.h" +#include "mic_virtio.h" + +#define VIRTIO_SUBCODE_64 0x0D00 + +#define MIC_MAX_VRINGS 4 +struct mic_vdev { + struct virtio_device vdev; + struct mic_device_desc __iomem *desc; + struct mic_device_ctrl __iomem *dc; + struct mic_device *mdev; + void __iomem *vr[MIC_MAX_VRINGS]; + int used_size[MIC_MAX_VRINGS]; + struct completion reset_done; + struct mic_irq *virtio_cookie; + int c2h_vdev_db; +}; + +static struct mic_irq *virtio_config_cookie; +#define to_micvdev(vd) container_of(vd, struct mic_vdev, vdev) + +/* Helper API to obtain the parent of the virtio device */ +static inline struct device *mic_dev(struct mic_vdev *mvdev) +{ + return mvdev->vdev.dev.parent; +} + +/* This gets the device's feature bits. */ +static u32 mic_get_features(struct virtio_device *vdev) +{ + unsigned int i, bits; + u32 features = 0; + struct mic_device_desc __iomem *desc = to_micvdev(vdev)->desc; + u8 __iomem *in_features = mic_vq_features(desc); + int feature_len = ioread8(&desc->feature_len); + + bits = min_t(unsigned, feature_len, + sizeof(vdev->features)) * 8; + for (i = 0; i < bits; i++) + if (ioread8(&in_features[i / 8]) & (BIT(i % 8))) + features |= BIT(i); + + return features; +} + +static void mic_finalize_features(struct virtio_device *vdev) +{ + unsigned int i, bits; + struct mic_device_desc __iomem *desc = to_micvdev(vdev)->desc; + u8 feature_len = ioread8(&desc->feature_len); + /* Second half of bitmap is features we accept. */ + u8 __iomem *out_features = + mic_vq_features(desc) + feature_len; + + /* Give virtio_ring a chance to accept features. */ + vring_transport_features(vdev); + + memset_io(out_features, 0, feature_len); + bits = min_t(unsigned, feature_len, + sizeof(vdev->features)) * 8; + for (i = 0; i < bits; i++) { + if (test_bit(i, vdev->features)) + iowrite8(ioread8(&out_features[i / 8]) | (1 << (i % 8)), + &out_features[i / 8]); + } +} + +/* + * Reading and writing elements in config space + */ +static void mic_get(struct virtio_device *vdev, unsigned int offset, + void *buf, unsigned len) +{ + struct mic_device_desc __iomem *desc = to_micvdev(vdev)->desc; + + if (offset + len > ioread8(&desc->config_len)) + return; + memcpy_fromio(buf, mic_vq_configspace(desc) + offset, len); +} + +static void mic_set(struct virtio_device *vdev, unsigned int offset, + const void *buf, unsigned len) +{ + struct mic_device_desc __iomem *desc = to_micvdev(vdev)->desc; + + if (offset + len > ioread8(&desc->config_len)) + return; + memcpy_toio(mic_vq_configspace(desc) + offset, buf, len); +} + +/* + * The operations to get and set the status word just access the status + * field of the device descriptor. set_status also interrupts the host + * to tell about status changes. + */ +static u8 mic_get_status(struct virtio_device *vdev) +{ + return ioread8(&to_micvdev(vdev)->desc->status); +} + +static void mic_set_status(struct virtio_device *vdev, u8 status) +{ + struct mic_vdev *mvdev = to_micvdev(vdev); + if (!status) + return; + iowrite8(status, &mvdev->desc->status); + mic_send_intr(mvdev->mdev, mvdev->c2h_vdev_db); +} + +/* Inform host on a virtio device reset and wait for ack from host */ +static void mic_reset_inform_host(struct virtio_device *vdev) +{ + struct mic_vdev *mvdev = to_micvdev(vdev); + struct mic_device_ctrl __iomem *dc = mvdev->dc; + int retry; + + iowrite8(0, &dc->host_ack); + iowrite8(1, &dc->vdev_reset); + mic_send_intr(mvdev->mdev, mvdev->c2h_vdev_db); + + /* Wait till host completes all card accesses and acks the reset */ + for (retry = 100; retry--;) { + if (ioread8(&dc->host_ack)) + break; + msleep(100); + }; + + dev_dbg(mic_dev(mvdev), "%s: retry: %d\n", __func__, retry); + + /* Reset status to 0 in case we timed out */ + iowrite8(0, &mvdev->desc->status); +} + +static void mic_reset(struct virtio_device *vdev) +{ + struct mic_vdev *mvdev = to_micvdev(vdev); + + dev_dbg(mic_dev(mvdev), "%s: virtio id %d\n", + __func__, vdev->id.device); + + mic_reset_inform_host(vdev); + complete_all(&mvdev->reset_done); +} + +/* + * The virtio_ring code calls this API when it wants to notify the Host. + */ +static bool mic_notify(struct virtqueue *vq) +{ + struct mic_vdev *mvdev = vq->priv; + + mic_send_intr(mvdev->mdev, mvdev->c2h_vdev_db); + return true; +} + +static void mic_del_vq(struct virtqueue *vq, int n) +{ + struct mic_vdev *mvdev = to_micvdev(vq->vdev); + struct vring *vr = (struct vring *)(vq + 1); + + free_pages((unsigned long) vr->used, get_order(mvdev->used_size[n])); + vring_del_virtqueue(vq); + mic_card_unmap(mvdev->mdev, mvdev->vr[n]); + mvdev->vr[n] = NULL; +} + +static void mic_del_vqs(struct virtio_device *vdev) +{ + struct mic_vdev *mvdev = to_micvdev(vdev); + struct virtqueue *vq, *n; + int idx = 0; + + dev_dbg(mic_dev(mvdev), "%s\n", __func__); + + list_for_each_entry_safe(vq, n, &vdev->vqs, list) + mic_del_vq(vq, idx++); +} + +/* + * This routine will assign vring's allocated in host/io memory. Code in + * virtio_ring.c however continues to access this io memory as if it were local + * memory without io accessors. + */ +static struct virtqueue *mic_find_vq(struct virtio_device *vdev, + unsigned index, + void (*callback)(struct virtqueue *vq), + const char *name) +{ + struct mic_vdev *mvdev = to_micvdev(vdev); + struct mic_vqconfig __iomem *vqconfig; + struct mic_vqconfig config; + struct virtqueue *vq; + void __iomem *va; + struct _mic_vring_info __iomem *info; + void *used; + int vr_size, _vr_size, err, magic; + struct vring *vr; + u8 type = ioread8(&mvdev->desc->type); + + if (index >= ioread8(&mvdev->desc->num_vq)) + return ERR_PTR(-ENOENT); + + if (!name) + return ERR_PTR(-ENOENT); + + /* First assign the vring's allocated in host memory */ + vqconfig = mic_vq_config(mvdev->desc) + index; + memcpy_fromio(&config, vqconfig, sizeof(config)); + _vr_size = vring_size(le16_to_cpu(config.num), MIC_VIRTIO_RING_ALIGN); + vr_size = PAGE_ALIGN(_vr_size + sizeof(struct _mic_vring_info)); + va = mic_card_map(mvdev->mdev, le64_to_cpu(config.address), vr_size); + if (!va) + return ERR_PTR(-ENOMEM); + mvdev->vr[index] = va; + memset_io(va, 0x0, _vr_size); + vq = vring_new_virtqueue(index, le16_to_cpu(config.num), + MIC_VIRTIO_RING_ALIGN, vdev, false, + (void __force *)va, mic_notify, callback, + name); + if (!vq) { + err = -ENOMEM; + goto unmap; + } + info = va + _vr_size; + magic = ioread32(&info->magic); + + if (WARN(magic != MIC_MAGIC + type + index, "magic mismatch")) { + err = -EIO; + goto unmap; + } + + /* Allocate and reassign used ring now */ + mvdev->used_size[index] = PAGE_ALIGN(sizeof(__u16) * 3 + + sizeof(struct vring_used_elem) * + le16_to_cpu(config.num)); + used = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, + get_order(mvdev->used_size[index])); + if (!used) { + err = -ENOMEM; + dev_err(mic_dev(mvdev), "%s %d err %d\n", + __func__, __LINE__, err); + goto del_vq; + } + iowrite64(virt_to_phys(used), &vqconfig->used_address); + + /* + * To reassign the used ring here we are directly accessing + * struct vring_virtqueue which is a private data structure + * in virtio_ring.c. At the minimum, a BUILD_BUG_ON() in + * vring_new_virtqueue() would ensure that + * (&vq->vring == (struct vring *) (&vq->vq + 1)); + */ + vr = (struct vring *)(vq + 1); + vr->used = used; + + vq->priv = mvdev; + return vq; +del_vq: + vring_del_virtqueue(vq); +unmap: + mic_card_unmap(mvdev->mdev, mvdev->vr[index]); + return ERR_PTR(err); +} + +static int mic_find_vqs(struct virtio_device *vdev, unsigned nvqs, + struct virtqueue *vqs[], + vq_callback_t *callbacks[], + const char *names[]) +{ + struct mic_vdev *mvdev = to_micvdev(vdev); + struct mic_device_ctrl __iomem *dc = mvdev->dc; + int i, err, retry; + + /* We must have this many virtqueues. */ + if (nvqs > ioread8(&mvdev->desc->num_vq)) + return -ENOENT; + + for (i = 0; i < nvqs; ++i) { + dev_dbg(mic_dev(mvdev), "%s: %d: %s\n", + __func__, i, names[i]); + vqs[i] = mic_find_vq(vdev, i, callbacks[i], names[i]); + if (IS_ERR(vqs[i])) { + err = PTR_ERR(vqs[i]); + goto error; + } + } + + iowrite8(1, &dc->used_address_updated); + /* + * Send an interrupt to the host to inform it that used + * rings have been re-assigned. + */ + mic_send_intr(mvdev->mdev, mvdev->c2h_vdev_db); + for (retry = 100; retry--;) { + if (!ioread8(&dc->used_address_updated)) + break; + msleep(100); + }; + + dev_dbg(mic_dev(mvdev), "%s: retry: %d\n", __func__, retry); + if (!retry) { + err = -ENODEV; + goto error; + } + + return 0; +error: + mic_del_vqs(vdev); + return err; +} + +/* + * The config ops structure as defined by virtio config + */ +static struct virtio_config_ops mic_vq_config_ops = { + .get_features = mic_get_features, + .finalize_features = mic_finalize_features, + .get = mic_get, + .set = mic_set, + .get_status = mic_get_status, + .set_status = mic_set_status, + .reset = mic_reset, + .find_vqs = mic_find_vqs, + .del_vqs = mic_del_vqs, +}; + +static irqreturn_t +mic_virtio_intr_handler(int irq, void *data) +{ + struct mic_vdev *mvdev = data; + struct virtqueue *vq; + + mic_ack_interrupt(mvdev->mdev); + list_for_each_entry(vq, &mvdev->vdev.vqs, list) + vring_interrupt(0, vq); + + return IRQ_HANDLED; +} + +static void mic_virtio_release_dev(struct device *_d) +{ + /* + * No need for a release method similar to virtio PCI. + * Provide an empty one to avoid getting a warning from core. + */ +} + +/* + * adds a new device and register it with virtio + * appropriate drivers are loaded by the device model + */ +static int mic_add_device(struct mic_device_desc __iomem *d, + unsigned int offset, struct mic_driver *mdrv) +{ + struct mic_vdev *mvdev; + int ret; + int virtio_db; + u8 type = ioread8(&d->type); + + mvdev = kzalloc(sizeof(*mvdev), GFP_KERNEL); + if (!mvdev) { + dev_err(mdrv->dev, "Cannot allocate mic dev %u type %u\n", + offset, type); + return -ENOMEM; + } + + mvdev->mdev = &mdrv->mdev; + mvdev->vdev.dev.parent = mdrv->dev; + mvdev->vdev.dev.release = mic_virtio_release_dev; + mvdev->vdev.id.device = type; + mvdev->vdev.config = &mic_vq_config_ops; + mvdev->desc = d; + mvdev->dc = (void __iomem *)d + mic_aligned_desc_size(d); + init_completion(&mvdev->reset_done); + + virtio_db = mic_next_card_db(); + mvdev->virtio_cookie = mic_request_card_irq(mic_virtio_intr_handler, + "virtio intr", mvdev, virtio_db); + if (IS_ERR(mvdev->virtio_cookie)) { + ret = PTR_ERR(mvdev->virtio_cookie); + goto kfree; + } + iowrite8((u8)virtio_db, &mvdev->dc->h2c_vdev_db); + mvdev->c2h_vdev_db = ioread8(&mvdev->dc->c2h_vdev_db); + + ret = register_virtio_device(&mvdev->vdev); + if (ret) { + dev_err(mic_dev(mvdev), + "Failed to register mic device %u type %u\n", + offset, type); + goto free_irq; + } + iowrite64((u64)mvdev, &mvdev->dc->vdev); + dev_dbg(mic_dev(mvdev), "%s: registered mic device %u type %u mvdev %p\n", + __func__, offset, type, mvdev); + + return 0; + +free_irq: + mic_free_card_irq(mvdev->virtio_cookie, mvdev); +kfree: + kfree(mvdev); + return ret; +} + +/* + * match for a mic device with a specific desc pointer + */ +static int mic_match_desc(struct device *dev, void *data) +{ + struct virtio_device *vdev = dev_to_virtio(dev); + struct mic_vdev *mvdev = to_micvdev(vdev); + + return mvdev->desc == (void __iomem *)data; +} + +static void mic_handle_config_change(struct mic_device_desc __iomem *d, + unsigned int offset, struct mic_driver *mdrv) +{ + struct mic_device_ctrl __iomem *dc + = (void __iomem *)d + mic_aligned_desc_size(d); + struct mic_vdev *mvdev = (struct mic_vdev *)ioread64(&dc->vdev); + struct virtio_driver *drv; + + if (ioread8(&dc->config_change) != MIC_VIRTIO_PARAM_CONFIG_CHANGED) + return; + + dev_dbg(mdrv->dev, "%s %d\n", __func__, __LINE__); + drv = container_of(mvdev->vdev.dev.driver, + struct virtio_driver, driver); + if (drv->config_changed) + drv->config_changed(&mvdev->vdev); + iowrite8(1, &dc->guest_ack); +} + +/* + * removes a virtio device if a hot remove event has been + * requested by the host. + */ +static int mic_remove_device(struct mic_device_desc __iomem *d, + unsigned int offset, struct mic_driver *mdrv) +{ + struct mic_device_ctrl __iomem *dc + = (void __iomem *)d + mic_aligned_desc_size(d); + struct mic_vdev *mvdev = (struct mic_vdev *)ioread64(&dc->vdev); + u8 status; + int ret = -1; + + if (ioread8(&dc->config_change) == MIC_VIRTIO_PARAM_DEV_REMOVE) { + dev_dbg(mdrv->dev, + "%s %d config_change %d type %d mvdev %p\n", + __func__, __LINE__, + ioread8(&dc->config_change), ioread8(&d->type), mvdev); + + status = ioread8(&d->status); + reinit_completion(&mvdev->reset_done); + unregister_virtio_device(&mvdev->vdev); + mic_free_card_irq(mvdev->virtio_cookie, mvdev); + if (status & VIRTIO_CONFIG_S_DRIVER_OK) + wait_for_completion(&mvdev->reset_done); + kfree(mvdev); + iowrite8(1, &dc->guest_ack); + dev_dbg(mdrv->dev, "%s %d guest_ack %d\n", + __func__, __LINE__, ioread8(&dc->guest_ack)); + ret = 0; + } + + return ret; +} + +#define REMOVE_DEVICES true + +static void mic_scan_devices(struct mic_driver *mdrv, bool remove) +{ + s8 type; + unsigned int i; + struct mic_device_desc __iomem *d; + struct mic_device_ctrl __iomem *dc; + struct device *dev; + int ret; + + for (i = sizeof(struct mic_bootparam); i < MIC_DP_SIZE; + i += mic_total_desc_size(d)) { + d = mdrv->dp + i; + dc = (void __iomem *)d + mic_aligned_desc_size(d); + /* + * This read barrier is paired with the corresponding write + * barrier on the host which is inserted before adding or + * removing a virtio device descriptor, by updating the type. + */ + rmb(); + type = ioread8(&d->type); + + /* end of list */ + if (type == 0) + break; + + if (type == -1) + continue; + + /* device already exists */ + dev = device_find_child(mdrv->dev, (void __force *)d, + mic_match_desc); + if (dev) { + if (remove) + iowrite8(MIC_VIRTIO_PARAM_DEV_REMOVE, + &dc->config_change); + put_device(dev); + mic_handle_config_change(d, i, mdrv); + ret = mic_remove_device(d, i, mdrv); + if (!ret && !remove) + iowrite8(-1, &d->type); + if (remove) { + iowrite8(0, &dc->config_change); + iowrite8(0, &dc->guest_ack); + } + continue; + } + + /* new device */ + dev_dbg(mdrv->dev, "%s %d Adding new virtio device %p\n", + __func__, __LINE__, d); + if (!remove) + mic_add_device(d, i, mdrv); + } +} + +/* + * mic_hotplug_device tries to find changes in the device page. + */ +static void mic_hotplug_devices(struct work_struct *work) +{ + struct mic_driver *mdrv = container_of(work, + struct mic_driver, hotplug_work); + + mic_scan_devices(mdrv, !REMOVE_DEVICES); +} + +/* + * Interrupt handler for hot plug/config changes etc. + */ +static irqreturn_t +mic_extint_handler(int irq, void *data) +{ + struct mic_driver *mdrv = (struct mic_driver *)data; + + dev_dbg(mdrv->dev, "%s %d hotplug work\n", + __func__, __LINE__); + mic_ack_interrupt(&mdrv->mdev); + schedule_work(&mdrv->hotplug_work); + return IRQ_HANDLED; +} + +/* + * Init function for virtio + */ +int mic_devices_init(struct mic_driver *mdrv) +{ + int rc; + struct mic_bootparam __iomem *bootparam; + int config_db; + + INIT_WORK(&mdrv->hotplug_work, mic_hotplug_devices); + mic_scan_devices(mdrv, !REMOVE_DEVICES); + + config_db = mic_next_card_db(); + virtio_config_cookie = mic_request_card_irq(mic_extint_handler, + "virtio_config_intr", mdrv, config_db); + if (IS_ERR(virtio_config_cookie)) { + rc = PTR_ERR(virtio_config_cookie); + goto exit; + } + + bootparam = mdrv->dp; + iowrite8(config_db, &bootparam->h2c_config_db); + return 0; +exit: + return rc; +} + +/* + * Uninit function for virtio + */ +void mic_devices_uninit(struct mic_driver *mdrv) +{ + struct mic_bootparam __iomem *bootparam = mdrv->dp; + iowrite8(-1, &bootparam->h2c_config_db); + mic_free_card_irq(virtio_config_cookie, mdrv); + flush_work(&mdrv->hotplug_work); + mic_scan_devices(mdrv, REMOVE_DEVICES); +} diff --git a/drivers/misc/mic/card/mic_virtio.h b/drivers/misc/mic/card/mic_virtio.h new file mode 100644 index 000000000000..d0407ba53bb7 --- /dev/null +++ b/drivers/misc/mic/card/mic_virtio.h @@ -0,0 +1,76 @@ +/* + * Intel MIC Platform Software Stack (MPSS) + * + * Copyright(c) 2013 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Disclaimer: The codes contained in these modules may be specific to + * the Intel Software Development Platform codenamed: Knights Ferry, and + * the Intel product codenamed: Knights Corner, and are not backward + * compatible with other Intel products. Additionally, Intel will NOT + * support the codes or instruction set in future products. + * + * Intel MIC Card driver. + * + */ +#ifndef __MIC_CARD_VIRTIO_H +#define __MIC_CARD_VIRTIO_H + +#include <linux/mic_common.h> +#include "mic_device.h" + +/* + * 64 bit I/O access + */ +#ifndef ioread64 +#define ioread64 readq +#endif +#ifndef iowrite64 +#define iowrite64 writeq +#endif + +static inline unsigned mic_desc_size(struct mic_device_desc __iomem *desc) +{ + return sizeof(*desc) + + ioread8(&desc->num_vq) * sizeof(struct mic_vqconfig) + + ioread8(&desc->feature_len) * 2 + + ioread8(&desc->config_len); +} + +static inline struct mic_vqconfig __iomem * +mic_vq_config(struct mic_device_desc __iomem *desc) +{ + return (struct mic_vqconfig __iomem *)(desc + 1); +} + +static inline __u8 __iomem * +mic_vq_features(struct mic_device_desc __iomem *desc) +{ + return (__u8 __iomem *)(mic_vq_config(desc) + ioread8(&desc->num_vq)); +} + +static inline __u8 __iomem * +mic_vq_configspace(struct mic_device_desc __iomem *desc) +{ + return mic_vq_features(desc) + ioread8(&desc->feature_len) * 2; +} +static inline unsigned mic_total_desc_size(struct mic_device_desc __iomem *desc) +{ + return mic_aligned_desc_size(desc) + sizeof(struct mic_device_ctrl); +} + +int mic_devices_init(struct mic_driver *mdrv); +void mic_devices_uninit(struct mic_driver *mdrv); + +#endif diff --git a/drivers/misc/mic/card/mic_x100.c b/drivers/misc/mic/card/mic_x100.c new file mode 100644 index 000000000000..2868945c9a4d --- /dev/null +++ b/drivers/misc/mic/card/mic_x100.c @@ -0,0 +1,256 @@ +/* + * Intel MIC Platform Software Stack (MPSS) + * + * Copyright(c) 2013 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Disclaimer: The codes contained in these modules may be specific to + * the Intel Software Development Platform codenamed: Knights Ferry, and + * the Intel product codenamed: Knights Corner, and are not backward + * compatible with other Intel products. Additionally, Intel will NOT + * support the codes or instruction set in future products. + * + * Intel MIC Card driver. + * + */ +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/platform_device.h> + +#include "../common/mic_dev.h" +#include "mic_device.h" +#include "mic_x100.h" + +static const char mic_driver_name[] = "mic"; + +static struct mic_driver g_drv; + +/** + * mic_read_spad - read from the scratchpad register + * @mdev: pointer to mic_device instance + * @idx: index to scratchpad register, 0 based + * + * This function allows reading of the 32bit scratchpad register. + * + * RETURNS: An appropriate -ERRNO error value on error, or zero for success. + */ +u32 mic_read_spad(struct mic_device *mdev, unsigned int idx) +{ + return mic_mmio_read(&mdev->mmio, + MIC_X100_SBOX_BASE_ADDRESS + + MIC_X100_SBOX_SPAD0 + idx * 4); +} + +/** + * __mic_send_intr - Send interrupt to Host. + * @mdev: pointer to mic_device instance + * @doorbell: Doorbell number. + */ +void mic_send_intr(struct mic_device *mdev, int doorbell) +{ + struct mic_mw *mw = &mdev->mmio; + + if (doorbell > MIC_X100_MAX_DOORBELL_IDX) + return; + /* Ensure that the interrupt is ordered w.r.t previous stores. */ + wmb(); + mic_mmio_write(mw, MIC_X100_SBOX_SDBIC0_DBREQ_BIT, + MIC_X100_SBOX_BASE_ADDRESS + + (MIC_X100_SBOX_SDBIC0 + (4 * doorbell))); +} + +/** + * mic_ack_interrupt - Device specific interrupt handling. + * @mdev: pointer to mic_device instance + * + * Returns: bitmask of doorbell events triggered. + */ +u32 mic_ack_interrupt(struct mic_device *mdev) +{ + return 0; +} + +static inline int mic_get_sbox_irq(int db) +{ + return MIC_X100_IRQ_BASE + db; +} + +static inline int mic_get_rdmasr_irq(int index) +{ + return MIC_X100_RDMASR_IRQ_BASE + index; +} + +/** + * mic_hw_intr_init - Initialize h/w specific interrupt + * information. + * @mdrv: pointer to mic_driver + */ +void mic_hw_intr_init(struct mic_driver *mdrv) +{ + mdrv->intr_info.num_intr = MIC_X100_NUM_SBOX_IRQ + + MIC_X100_NUM_RDMASR_IRQ; +} + +/** + * mic_db_to_irq - Retrieve irq number corresponding to a doorbell. + * @mdrv: pointer to mic_driver + * @db: The doorbell obtained for which the irq is needed. Doorbell + * may correspond to an sbox doorbell or an rdmasr index. + * + * Returns the irq corresponding to the doorbell. + */ +int mic_db_to_irq(struct mic_driver *mdrv, int db) +{ + int rdmasr_index; + if (db < MIC_X100_NUM_SBOX_IRQ) { + return mic_get_sbox_irq(db); + } else { + rdmasr_index = db - MIC_X100_NUM_SBOX_IRQ + + MIC_X100_RDMASR_IRQ_BASE; + return mic_get_rdmasr_irq(rdmasr_index); + } +} + +/* + * mic_card_map - Allocate virtual address for a remote memory region. + * @mdev: pointer to mic_device instance. + * @addr: Remote DMA address. + * @size: Size of the region. + * + * Returns: Virtual address backing the remote memory region. + */ +void __iomem * +mic_card_map(struct mic_device *mdev, dma_addr_t addr, size_t size) +{ + return ioremap(addr, size); +} + +/* + * mic_card_unmap - Unmap the virtual address for a remote memory region. + * @mdev: pointer to mic_device instance. + * @addr: Virtual address for remote memory region. + * + * Returns: None. + */ +void mic_card_unmap(struct mic_device *mdev, void __iomem *addr) +{ + iounmap(addr); +} + +static int __init mic_probe(struct platform_device *pdev) +{ + struct mic_driver *mdrv = &g_drv; + struct mic_device *mdev = &mdrv->mdev; + int rc = 0; + + mdrv->dev = &pdev->dev; + snprintf(mdrv->name, sizeof(mic_driver_name), mic_driver_name); + + mdev->mmio.pa = MIC_X100_MMIO_BASE; + mdev->mmio.len = MIC_X100_MMIO_LEN; + mdev->mmio.va = ioremap(MIC_X100_MMIO_BASE, MIC_X100_MMIO_LEN); + if (!mdev->mmio.va) { + dev_err(&pdev->dev, "Cannot remap MMIO BAR\n"); + rc = -EIO; + goto done; + } + mic_hw_intr_init(mdrv); + rc = mic_driver_init(mdrv); + if (rc) { + dev_err(&pdev->dev, "mic_driver_init failed rc %d\n", rc); + goto iounmap; + } +done: + return rc; +iounmap: + iounmap(mdev->mmio.va); + return rc; +} + +static int mic_remove(struct platform_device *pdev) +{ + struct mic_driver *mdrv = &g_drv; + struct mic_device *mdev = &mdrv->mdev; + + mic_driver_uninit(mdrv); + iounmap(mdev->mmio.va); + return 0; +} + +static void mic_platform_shutdown(struct platform_device *pdev) +{ + mic_remove(pdev); +} + +static struct platform_device mic_platform_dev = { + .name = mic_driver_name, + .id = 0, + .num_resources = 0, +}; + +static struct platform_driver __refdata mic_platform_driver = { + .probe = mic_probe, + .remove = mic_remove, + .shutdown = mic_platform_shutdown, + .driver = { + .name = mic_driver_name, + .owner = THIS_MODULE, + }, +}; + +static int __init mic_init(void) +{ + int ret; + struct cpuinfo_x86 *c = &cpu_data(0); + + if (!(c->x86 == 11 && c->x86_model == 1)) { + ret = -ENODEV; + pr_err("%s not running on X100 ret %d\n", __func__, ret); + goto done; + } + + mic_init_card_debugfs(); + ret = platform_device_register(&mic_platform_dev); + if (ret) { + pr_err("platform_device_register ret %d\n", ret); + goto cleanup_debugfs; + } + ret = platform_driver_register(&mic_platform_driver); + if (ret) { + pr_err("platform_driver_register ret %d\n", ret); + goto device_unregister; + } + return ret; + +device_unregister: + platform_device_unregister(&mic_platform_dev); +cleanup_debugfs: + mic_exit_card_debugfs(); +done: + return ret; +} + +static void __exit mic_exit(void) +{ + platform_driver_unregister(&mic_platform_driver); + platform_device_unregister(&mic_platform_dev); + mic_exit_card_debugfs(); +} + +module_init(mic_init); +module_exit(mic_exit); + +MODULE_AUTHOR("Intel Corporation"); +MODULE_DESCRIPTION("Intel(R) MIC X100 Card driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/misc/mic/card/mic_x100.h b/drivers/misc/mic/card/mic_x100.h new file mode 100644 index 000000000000..d66ea55639c3 --- /dev/null +++ b/drivers/misc/mic/card/mic_x100.h @@ -0,0 +1,48 @@ +/* + * Intel MIC Platform Software Stack (MPSS) + * + * Copyright(c) 2013 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Disclaimer: The codes contained in these modules may be specific to + * the Intel Software Development Platform codenamed: Knights Ferry, and + * the Intel product codenamed: Knights Corner, and are not backward + * compatible with other Intel products. Additionally, Intel will NOT + * support the codes or instruction set in future products. + * + * Intel MIC Card driver. + * + */ +#ifndef _MIC_X100_CARD_H_ +#define _MIC_X100_CARD_H_ + +#define MIC_X100_MMIO_BASE 0x08007C0000ULL +#define MIC_X100_MMIO_LEN 0x00020000ULL +#define MIC_X100_SBOX_BASE_ADDRESS 0x00010000ULL + +#define MIC_X100_SBOX_SPAD0 0x0000AB20 +#define MIC_X100_SBOX_SDBIC0 0x0000CC90 +#define MIC_X100_SBOX_SDBIC0_DBREQ_BIT 0x80000000 +#define MIC_X100_SBOX_RDMASR0 0x0000B180 + +#define MIC_X100_MAX_DOORBELL_IDX 8 + +#define MIC_X100_NUM_SBOX_IRQ 8 +#define MIC_X100_NUM_RDMASR_IRQ 8 +#define MIC_X100_SBOX_IRQ_BASE 0 +#define MIC_X100_RDMASR_IRQ_BASE 17 + +#define MIC_X100_IRQ_BASE 26 + +#endif diff --git a/drivers/misc/mic/common/mic_dev.h b/drivers/misc/mic/common/mic_dev.h new file mode 100644 index 000000000000..92999c2bbf82 --- /dev/null +++ b/drivers/misc/mic/common/mic_dev.h @@ -0,0 +1,51 @@ +/* + * Intel MIC Platform Software Stack (MPSS) + * + * Copyright(c) 2013 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Intel MIC driver. + * + */ +#ifndef __MIC_DEV_H__ +#define __MIC_DEV_H__ + +/** + * struct mic_mw - MIC memory window + * + * @pa: Base physical address. + * @va: Base ioremap'd virtual address. + * @len: Size of the memory window. + */ +struct mic_mw { + phys_addr_t pa; + void __iomem *va; + resource_size_t len; +}; + +/* + * Scratch pad register offsets used by the host to communicate + * device page DMA address to the card. + */ +#define MIC_DPLO_SPAD 14 +#define MIC_DPHI_SPAD 15 + +/* + * These values are supposed to be in the config_change field of the + * device page when the host sends a config change interrupt to the card. + */ +#define MIC_VIRTIO_PARAM_DEV_REMOVE 0x1 +#define MIC_VIRTIO_PARAM_CONFIG_CHANGED 0x2 + +#endif diff --git a/drivers/misc/mic/host/Makefile b/drivers/misc/mic/host/Makefile new file mode 100644 index 000000000000..c2197f999394 --- /dev/null +++ b/drivers/misc/mic/host/Makefile @@ -0,0 +1,14 @@ +# +# Makefile - Intel MIC Linux driver. +# Copyright(c) 2013, Intel Corporation. +# +obj-$(CONFIG_INTEL_MIC_HOST) += mic_host.o +mic_host-objs := mic_main.o +mic_host-objs += mic_x100.o +mic_host-objs += mic_sysfs.o +mic_host-objs += mic_smpt.o +mic_host-objs += mic_intr.o +mic_host-objs += mic_boot.o +mic_host-objs += mic_debugfs.o +mic_host-objs += mic_fops.o +mic_host-objs += mic_virtio.o diff --git a/drivers/misc/mic/host/mic_boot.c b/drivers/misc/mic/host/mic_boot.c new file mode 100644 index 000000000000..b75c6b5cc20f --- /dev/null +++ b/drivers/misc/mic/host/mic_boot.c @@ -0,0 +1,300 @@ +/* + * Intel MIC Platform Software Stack (MPSS) + * + * Copyright(c) 2013 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Intel MIC Host driver. + * + */ +#include <linux/delay.h> +#include <linux/firmware.h> +#include <linux/pci.h> + +#include <linux/mic_common.h> +#include "../common/mic_dev.h" +#include "mic_device.h" +#include "mic_smpt.h" +#include "mic_virtio.h" + +/** + * mic_reset - Reset the MIC device. + * @mdev: pointer to mic_device instance + */ +static void mic_reset(struct mic_device *mdev) +{ + int i; + +#define MIC_RESET_TO (45) + + reinit_completion(&mdev->reset_wait); + mdev->ops->reset_fw_ready(mdev); + mdev->ops->reset(mdev); + + for (i = 0; i < MIC_RESET_TO; i++) { + if (mdev->ops->is_fw_ready(mdev)) + goto done; + /* + * Resets typically take 10s of seconds to complete. + * Since an MMIO read is required to check if the + * firmware is ready or not, a 1 second delay works nicely. + */ + msleep(1000); + } + mic_set_state(mdev, MIC_RESET_FAILED); +done: + complete_all(&mdev->reset_wait); +} + +/* Initialize the MIC bootparams */ +void mic_bootparam_init(struct mic_device *mdev) +{ + struct mic_bootparam *bootparam = mdev->dp; + + bootparam->magic = cpu_to_le32(MIC_MAGIC); + bootparam->c2h_shutdown_db = mdev->shutdown_db; + bootparam->h2c_shutdown_db = -1; + bootparam->h2c_config_db = -1; + bootparam->shutdown_status = 0; + bootparam->shutdown_card = 0; +} + +/** + * mic_start - Start the MIC. + * @mdev: pointer to mic_device instance + * @buf: buffer containing boot string including firmware/ramdisk path. + * + * This function prepares an MIC for boot and initiates boot. + * RETURNS: An appropriate -ERRNO error value on error, or zero for success. + */ +int mic_start(struct mic_device *mdev, const char *buf) +{ + int rc; + mutex_lock(&mdev->mic_mutex); +retry: + if (MIC_OFFLINE != mdev->state) { + rc = -EINVAL; + goto unlock_ret; + } + if (!mdev->ops->is_fw_ready(mdev)) { + mic_reset(mdev); + /* + * The state will either be MIC_OFFLINE if the reset succeeded + * or MIC_RESET_FAILED if the firmware reset failed. + */ + goto retry; + } + rc = mdev->ops->load_mic_fw(mdev, buf); + if (rc) + goto unlock_ret; + mic_smpt_restore(mdev); + mic_intr_restore(mdev); + mdev->intr_ops->enable_interrupts(mdev); + mdev->ops->write_spad(mdev, MIC_DPLO_SPAD, mdev->dp_dma_addr); + mdev->ops->write_spad(mdev, MIC_DPHI_SPAD, mdev->dp_dma_addr >> 32); + mdev->ops->send_firmware_intr(mdev); + mic_set_state(mdev, MIC_ONLINE); +unlock_ret: + mutex_unlock(&mdev->mic_mutex); + return rc; +} + +/** + * mic_stop - Prepare the MIC for reset and trigger reset. + * @mdev: pointer to mic_device instance + * @force: force a MIC to reset even if it is already offline. + * + * RETURNS: None. + */ +void mic_stop(struct mic_device *mdev, bool force) +{ + mutex_lock(&mdev->mic_mutex); + if (MIC_OFFLINE != mdev->state || force) { + mic_virtio_reset_devices(mdev); + mic_bootparam_init(mdev); + mic_reset(mdev); + if (MIC_RESET_FAILED == mdev->state) + goto unlock; + mic_set_shutdown_status(mdev, MIC_NOP); + if (MIC_SUSPENDED != mdev->state) + mic_set_state(mdev, MIC_OFFLINE); + } +unlock: + mutex_unlock(&mdev->mic_mutex); +} + +/** + * mic_shutdown - Initiate MIC shutdown. + * @mdev: pointer to mic_device instance + * + * RETURNS: None. + */ +void mic_shutdown(struct mic_device *mdev) +{ + struct mic_bootparam *bootparam = mdev->dp; + s8 db = bootparam->h2c_shutdown_db; + + mutex_lock(&mdev->mic_mutex); + if (MIC_ONLINE == mdev->state && db != -1) { + bootparam->shutdown_card = 1; + mdev->ops->send_intr(mdev, db); + mic_set_state(mdev, MIC_SHUTTING_DOWN); + } + mutex_unlock(&mdev->mic_mutex); +} + +/** + * mic_shutdown_work - Handle shutdown interrupt from MIC. + * @work: The work structure. + * + * This work is scheduled whenever the host has received a shutdown + * interrupt from the MIC. + */ +void mic_shutdown_work(struct work_struct *work) +{ + struct mic_device *mdev = container_of(work, struct mic_device, + shutdown_work); + struct mic_bootparam *bootparam = mdev->dp; + + mutex_lock(&mdev->mic_mutex); + mic_set_shutdown_status(mdev, bootparam->shutdown_status); + bootparam->shutdown_status = 0; + + /* + * if state is MIC_SUSPENDED, OSPM suspend is in progress. We do not + * change the state here so as to prevent users from booting the card + * during and after the suspend operation. + */ + if (MIC_SHUTTING_DOWN != mdev->state && + MIC_SUSPENDED != mdev->state) + mic_set_state(mdev, MIC_SHUTTING_DOWN); + mutex_unlock(&mdev->mic_mutex); +} + +/** + * mic_reset_trigger_work - Trigger MIC reset. + * @work: The work structure. + * + * This work is scheduled whenever the host wants to reset the MIC. + */ +void mic_reset_trigger_work(struct work_struct *work) +{ + struct mic_device *mdev = container_of(work, struct mic_device, + reset_trigger_work); + + mic_stop(mdev, false); +} + +/** + * mic_complete_resume - Complete MIC Resume after an OSPM suspend/hibernate + * event. + * @mdev: pointer to mic_device instance + * + * RETURNS: None. + */ +void mic_complete_resume(struct mic_device *mdev) +{ + if (mdev->state != MIC_SUSPENDED) { + dev_warn(mdev->sdev->parent, "state %d should be %d\n", + mdev->state, MIC_SUSPENDED); + return; + } + + /* Make sure firmware is ready */ + if (!mdev->ops->is_fw_ready(mdev)) + mic_stop(mdev, true); + + mutex_lock(&mdev->mic_mutex); + mic_set_state(mdev, MIC_OFFLINE); + mutex_unlock(&mdev->mic_mutex); +} + +/** + * mic_prepare_suspend - Handle suspend notification for the MIC device. + * @mdev: pointer to mic_device instance + * + * RETURNS: None. + */ +void mic_prepare_suspend(struct mic_device *mdev) +{ + int rc; + +#define MIC_SUSPEND_TIMEOUT (60 * HZ) + + mutex_lock(&mdev->mic_mutex); + switch (mdev->state) { + case MIC_OFFLINE: + /* + * Card is already offline. Set state to MIC_SUSPENDED + * to prevent users from booting the card. + */ + mic_set_state(mdev, MIC_SUSPENDED); + mutex_unlock(&mdev->mic_mutex); + break; + case MIC_ONLINE: + /* + * Card is online. Set state to MIC_SUSPENDING and notify + * MIC user space daemon which will issue card + * shutdown and reset. + */ + mic_set_state(mdev, MIC_SUSPENDING); + mutex_unlock(&mdev->mic_mutex); + rc = wait_for_completion_timeout(&mdev->reset_wait, + MIC_SUSPEND_TIMEOUT); + /* Force reset the card if the shutdown completion timed out */ + if (!rc) { + mutex_lock(&mdev->mic_mutex); + mic_set_state(mdev, MIC_SUSPENDED); + mutex_unlock(&mdev->mic_mutex); + mic_stop(mdev, true); + } + break; + case MIC_SHUTTING_DOWN: + /* + * Card is shutting down. Set state to MIC_SUSPENDED + * to prevent further boot of the card. + */ + mic_set_state(mdev, MIC_SUSPENDED); + mutex_unlock(&mdev->mic_mutex); + rc = wait_for_completion_timeout(&mdev->reset_wait, + MIC_SUSPEND_TIMEOUT); + /* Force reset the card if the shutdown completion timed out */ + if (!rc) + mic_stop(mdev, true); + break; + default: + mutex_unlock(&mdev->mic_mutex); + break; + } +} + +/** + * mic_suspend - Initiate MIC suspend. Suspend merely issues card shutdown. + * @mdev: pointer to mic_device instance + * + * RETURNS: None. + */ +void mic_suspend(struct mic_device *mdev) +{ + struct mic_bootparam *bootparam = mdev->dp; + s8 db = bootparam->h2c_shutdown_db; + + mutex_lock(&mdev->mic_mutex); + if (MIC_SUSPENDING == mdev->state && db != -1) { + bootparam->shutdown_card = 1; + mdev->ops->send_intr(mdev, db); + mic_set_state(mdev, MIC_SUSPENDED); + } + mutex_unlock(&mdev->mic_mutex); +} diff --git a/drivers/misc/mic/host/mic_debugfs.c b/drivers/misc/mic/host/mic_debugfs.c new file mode 100644 index 000000000000..028ba5d6fd1c --- /dev/null +++ b/drivers/misc/mic/host/mic_debugfs.c @@ -0,0 +1,491 @@ +/* + * Intel MIC Platform Software Stack (MPSS) + * + * Copyright(c) 2013 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Intel MIC Host driver. + * + */ +#include <linux/debugfs.h> +#include <linux/pci.h> +#include <linux/seq_file.h> + +#include <linux/mic_common.h> +#include "../common/mic_dev.h" +#include "mic_device.h" +#include "mic_smpt.h" +#include "mic_virtio.h" + +/* Debugfs parent dir */ +static struct dentry *mic_dbg; + +/** + * mic_log_buf_show - Display MIC kernel log buffer. + * + * log_buf addr/len is read from System.map by user space + * and populated in sysfs entries. + */ +static int mic_log_buf_show(struct seq_file *s, void *unused) +{ + void __iomem *log_buf_va; + int __iomem *log_buf_len_va; + struct mic_device *mdev = s->private; + void *kva; + int size; + unsigned long aper_offset; + + if (!mdev || !mdev->log_buf_addr || !mdev->log_buf_len) + goto done; + /* + * Card kernel will never be relocated and any kernel text/data mapping + * can be translated to phys address by subtracting __START_KERNEL_map. + */ + aper_offset = (unsigned long)mdev->log_buf_len - __START_KERNEL_map; + log_buf_len_va = mdev->aper.va + aper_offset; + aper_offset = (unsigned long)mdev->log_buf_addr - __START_KERNEL_map; + log_buf_va = mdev->aper.va + aper_offset; + size = ioread32(log_buf_len_va); + + kva = kmalloc(size, GFP_KERNEL); + if (!kva) + goto done; + mutex_lock(&mdev->mic_mutex); + memcpy_fromio(kva, log_buf_va, size); + switch (mdev->state) { + case MIC_ONLINE: + /* Fall through */ + case MIC_SHUTTING_DOWN: + seq_write(s, kva, size); + break; + default: + break; + } + mutex_unlock(&mdev->mic_mutex); + kfree(kva); +done: + return 0; +} + +static int mic_log_buf_open(struct inode *inode, struct file *file) +{ + return single_open(file, mic_log_buf_show, inode->i_private); +} + +static int mic_log_buf_release(struct inode *inode, struct file *file) +{ + return single_release(inode, file); +} + +static const struct file_operations log_buf_ops = { + .owner = THIS_MODULE, + .open = mic_log_buf_open, + .read = seq_read, + .llseek = seq_lseek, + .release = mic_log_buf_release +}; + +static int mic_smpt_show(struct seq_file *s, void *pos) +{ + int i; + struct mic_device *mdev = s->private; + unsigned long flags; + + seq_printf(s, "MIC %-2d |%-10s| %-14s %-10s\n", + mdev->id, "SMPT entry", "SW DMA addr", "RefCount"); + seq_puts(s, "====================================================\n"); + + if (mdev->smpt) { + struct mic_smpt_info *smpt_info = mdev->smpt; + spin_lock_irqsave(&smpt_info->smpt_lock, flags); + for (i = 0; i < smpt_info->info.num_reg; i++) { + seq_printf(s, "%9s|%-10d| %-#14llx %-10lld\n", + " ", i, smpt_info->entry[i].dma_addr, + smpt_info->entry[i].ref_count); + } + spin_unlock_irqrestore(&smpt_info->smpt_lock, flags); + } + seq_puts(s, "====================================================\n"); + return 0; +} + +static int mic_smpt_debug_open(struct inode *inode, struct file *file) +{ + return single_open(file, mic_smpt_show, inode->i_private); +} + +static int mic_smpt_debug_release(struct inode *inode, struct file *file) +{ + return single_release(inode, file); +} + +static const struct file_operations smpt_file_ops = { + .owner = THIS_MODULE, + .open = mic_smpt_debug_open, + .read = seq_read, + .llseek = seq_lseek, + .release = mic_smpt_debug_release +}; + +static int mic_soft_reset_show(struct seq_file *s, void *pos) +{ + struct mic_device *mdev = s->private; + + mic_stop(mdev, true); + return 0; +} + +static int mic_soft_reset_debug_open(struct inode *inode, struct file *file) +{ + return single_open(file, mic_soft_reset_show, inode->i_private); +} + +static int mic_soft_reset_debug_release(struct inode *inode, struct file *file) +{ + return single_release(inode, file); +} + +static const struct file_operations soft_reset_ops = { + .owner = THIS_MODULE, + .open = mic_soft_reset_debug_open, + .read = seq_read, + .llseek = seq_lseek, + .release = mic_soft_reset_debug_release +}; + +static int mic_post_code_show(struct seq_file *s, void *pos) +{ + struct mic_device *mdev = s->private; + u32 reg = mdev->ops->get_postcode(mdev); + + seq_printf(s, "%c%c", reg & 0xff, (reg >> 8) & 0xff); + return 0; +} + +static int mic_post_code_debug_open(struct inode *inode, struct file *file) +{ + return single_open(file, mic_post_code_show, inode->i_private); +} + +static int mic_post_code_debug_release(struct inode *inode, struct file *file) +{ + return single_release(inode, file); +} + +static const struct file_operations post_code_ops = { + .owner = THIS_MODULE, + .open = mic_post_code_debug_open, + .read = seq_read, + .llseek = seq_lseek, + .release = mic_post_code_debug_release +}; + +static int mic_dp_show(struct seq_file *s, void *pos) +{ + struct mic_device *mdev = s->private; + struct mic_device_desc *d; + struct mic_device_ctrl *dc; + struct mic_vqconfig *vqconfig; + __u32 *features; + __u8 *config; + struct mic_bootparam *bootparam = mdev->dp; + int i, j; + + seq_printf(s, "Bootparam: magic 0x%x\n", + bootparam->magic); + seq_printf(s, "Bootparam: h2c_shutdown_db %d\n", + bootparam->h2c_shutdown_db); + seq_printf(s, "Bootparam: h2c_config_db %d\n", + bootparam->h2c_config_db); + seq_printf(s, "Bootparam: c2h_shutdown_db %d\n", + bootparam->c2h_shutdown_db); + seq_printf(s, "Bootparam: shutdown_status %d\n", + bootparam->shutdown_status); + seq_printf(s, "Bootparam: shutdown_card %d\n", + bootparam->shutdown_card); + + for (i = sizeof(*bootparam); i < MIC_DP_SIZE; + i += mic_total_desc_size(d)) { + d = mdev->dp + i; + dc = (void *)d + mic_aligned_desc_size(d); + + /* end of list */ + if (d->type == 0) + break; + + if (d->type == -1) + continue; + + seq_printf(s, "Type %d ", d->type); + seq_printf(s, "Num VQ %d ", d->num_vq); + seq_printf(s, "Feature Len %d\n", d->feature_len); + seq_printf(s, "Config Len %d ", d->config_len); + seq_printf(s, "Shutdown Status %d\n", d->status); + + for (j = 0; j < d->num_vq; j++) { + vqconfig = mic_vq_config(d) + j; + seq_printf(s, "vqconfig[%d]: ", j); + seq_printf(s, "address 0x%llx ", vqconfig->address); + seq_printf(s, "num %d ", vqconfig->num); + seq_printf(s, "used address 0x%llx\n", + vqconfig->used_address); + } + + features = (__u32 *)mic_vq_features(d); + seq_printf(s, "Features: Host 0x%x ", features[0]); + seq_printf(s, "Guest 0x%x\n", features[1]); + + config = mic_vq_configspace(d); + for (j = 0; j < d->config_len; j++) + seq_printf(s, "config[%d]=%d\n", j, config[j]); + + seq_puts(s, "Device control:\n"); + seq_printf(s, "Config Change %d ", dc->config_change); + seq_printf(s, "Vdev reset %d\n", dc->vdev_reset); + seq_printf(s, "Guest Ack %d ", dc->guest_ack); + seq_printf(s, "Host ack %d\n", dc->host_ack); + seq_printf(s, "Used address updated %d ", + dc->used_address_updated); + seq_printf(s, "Vdev 0x%llx\n", dc->vdev); + seq_printf(s, "c2h doorbell %d ", dc->c2h_vdev_db); + seq_printf(s, "h2c doorbell %d\n", dc->h2c_vdev_db); + } + + return 0; +} + +static int mic_dp_debug_open(struct inode *inode, struct file *file) +{ + return single_open(file, mic_dp_show, inode->i_private); +} + +static int mic_dp_debug_release(struct inode *inode, struct file *file) +{ + return single_release(inode, file); +} + +static const struct file_operations dp_ops = { + .owner = THIS_MODULE, + .open = mic_dp_debug_open, + .read = seq_read, + .llseek = seq_lseek, + .release = mic_dp_debug_release +}; + +static int mic_vdev_info_show(struct seq_file *s, void *unused) +{ + struct mic_device *mdev = s->private; + struct list_head *pos, *tmp; + struct mic_vdev *mvdev; + int i, j; + + mutex_lock(&mdev->mic_mutex); + list_for_each_safe(pos, tmp, &mdev->vdev_list) { + mvdev = list_entry(pos, struct mic_vdev, list); + seq_printf(s, "VDEV type %d state %s in %ld out %ld\n", + mvdev->virtio_id, + mic_vdevup(mvdev) ? "UP" : "DOWN", + mvdev->in_bytes, + mvdev->out_bytes); + for (i = 0; i < MIC_MAX_VRINGS; i++) { + struct vring_desc *desc; + struct vring_avail *avail; + struct vring_used *used; + struct mic_vringh *mvr = &mvdev->mvr[i]; + struct vringh *vrh = &mvr->vrh; + int num = vrh->vring.num; + if (!num) + continue; + desc = vrh->vring.desc; + seq_printf(s, "vring i %d avail_idx %d", + i, mvr->vring.info->avail_idx & (num - 1)); + seq_printf(s, " vring i %d avail_idx %d\n", + i, mvr->vring.info->avail_idx); + seq_printf(s, "vrh i %d weak_barriers %d", + i, vrh->weak_barriers); + seq_printf(s, " last_avail_idx %d last_used_idx %d", + vrh->last_avail_idx, vrh->last_used_idx); + seq_printf(s, " completed %d\n", vrh->completed); + for (j = 0; j < num; j++) { + seq_printf(s, "desc[%d] addr 0x%llx len %d", + j, desc->addr, desc->len); + seq_printf(s, " flags 0x%x next %d\n", + desc->flags, desc->next); + desc++; + } + avail = vrh->vring.avail; + seq_printf(s, "avail flags 0x%x idx %d\n", + avail->flags, avail->idx & (num - 1)); + seq_printf(s, "avail flags 0x%x idx %d\n", + avail->flags, avail->idx); + for (j = 0; j < num; j++) + seq_printf(s, "avail ring[%d] %d\n", + j, avail->ring[j]); + used = vrh->vring.used; + seq_printf(s, "used flags 0x%x idx %d\n", + used->flags, used->idx & (num - 1)); + seq_printf(s, "used flags 0x%x idx %d\n", + used->flags, used->idx); + for (j = 0; j < num; j++) + seq_printf(s, "used ring[%d] id %d len %d\n", + j, used->ring[j].id, + used->ring[j].len); + } + } + mutex_unlock(&mdev->mic_mutex); + + return 0; +} + +static int mic_vdev_info_debug_open(struct inode *inode, struct file *file) +{ + return single_open(file, mic_vdev_info_show, inode->i_private); +} + +static int mic_vdev_info_debug_release(struct inode *inode, struct file *file) +{ + return single_release(inode, file); +} + +static const struct file_operations vdev_info_ops = { + .owner = THIS_MODULE, + .open = mic_vdev_info_debug_open, + .read = seq_read, + .llseek = seq_lseek, + .release = mic_vdev_info_debug_release +}; + +static int mic_msi_irq_info_show(struct seq_file *s, void *pos) +{ + struct mic_device *mdev = s->private; + int reg; + int i, j; + u16 entry; + u16 vector; + struct pci_dev *pdev = container_of(mdev->sdev->parent, + struct pci_dev, dev); + + if (pci_dev_msi_enabled(pdev)) { + for (i = 0; i < mdev->irq_info.num_vectors; i++) { + if (pdev->msix_enabled) { + entry = mdev->irq_info.msix_entries[i].entry; + vector = mdev->irq_info.msix_entries[i].vector; + } else { + entry = 0; + vector = pdev->irq; + } + + reg = mdev->intr_ops->read_msi_to_src_map(mdev, entry); + + seq_printf(s, "%s %-10d %s %-10d MXAR[%d]: %08X\n", + "IRQ:", vector, "Entry:", entry, i, reg); + + seq_printf(s, "%-10s", "offset:"); + for (j = (MIC_NUM_OFFSETS - 1); j >= 0; j--) + seq_printf(s, "%4d ", j); + seq_puts(s, "\n"); + + + seq_printf(s, "%-10s", "count:"); + for (j = (MIC_NUM_OFFSETS - 1); j >= 0; j--) + seq_printf(s, "%4d ", + (mdev->irq_info.mic_msi_map[i] & + BIT(j)) ? 1 : 0); + seq_puts(s, "\n\n"); + } + } else { + seq_puts(s, "MSI/MSIx interrupts not enabled\n"); + } + + return 0; +} + +static int mic_msi_irq_info_debug_open(struct inode *inode, struct file *file) +{ + return single_open(file, mic_msi_irq_info_show, inode->i_private); +} + +static int +mic_msi_irq_info_debug_release(struct inode *inode, struct file *file) +{ + return single_release(inode, file); +} + +static const struct file_operations msi_irq_info_ops = { + .owner = THIS_MODULE, + .open = mic_msi_irq_info_debug_open, + .read = seq_read, + .llseek = seq_lseek, + .release = mic_msi_irq_info_debug_release +}; + +/** + * mic_create_debug_dir - Initialize MIC debugfs entries. + */ +void mic_create_debug_dir(struct mic_device *mdev) +{ + if (!mic_dbg) + return; + + mdev->dbg_dir = debugfs_create_dir(dev_name(mdev->sdev), mic_dbg); + if (!mdev->dbg_dir) + return; + + debugfs_create_file("log_buf", 0444, mdev->dbg_dir, mdev, &log_buf_ops); + + debugfs_create_file("smpt", 0444, mdev->dbg_dir, mdev, &smpt_file_ops); + + debugfs_create_file("soft_reset", 0444, mdev->dbg_dir, mdev, + &soft_reset_ops); + + debugfs_create_file("post_code", 0444, mdev->dbg_dir, mdev, + &post_code_ops); + + debugfs_create_file("dp", 0444, mdev->dbg_dir, mdev, &dp_ops); + + debugfs_create_file("vdev_info", 0444, mdev->dbg_dir, mdev, + &vdev_info_ops); + + debugfs_create_file("msi_irq_info", 0444, mdev->dbg_dir, mdev, + &msi_irq_info_ops); +} + +/** + * mic_delete_debug_dir - Uninitialize MIC debugfs entries. + */ +void mic_delete_debug_dir(struct mic_device *mdev) +{ + if (!mdev->dbg_dir) + return; + + debugfs_remove_recursive(mdev->dbg_dir); +} + +/** + * mic_init_debugfs - Initialize global debugfs entry. + */ +void __init mic_init_debugfs(void) +{ + mic_dbg = debugfs_create_dir(KBUILD_MODNAME, NULL); + if (!mic_dbg) + pr_err("can't create debugfs dir\n"); +} + +/** + * mic_exit_debugfs - Uninitialize global debugfs entry + */ +void mic_exit_debugfs(void) +{ + debugfs_remove(mic_dbg); +} diff --git a/drivers/misc/mic/host/mic_device.h b/drivers/misc/mic/host/mic_device.h new file mode 100644 index 000000000000..1a6edce2ecde --- /dev/null +++ b/drivers/misc/mic/host/mic_device.h @@ -0,0 +1,206 @@ +/* + * Intel MIC Platform Software Stack (MPSS) + * + * Copyright(c) 2013 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Intel MIC Host driver. + * + */ +#ifndef _MIC_DEVICE_H_ +#define _MIC_DEVICE_H_ + +#include <linux/cdev.h> +#include <linux/idr.h> +#include <linux/notifier.h> + +#include "mic_intr.h" + +/* The maximum number of MIC devices supported in a single host system. */ +#define MIC_MAX_NUM_DEVS 256 + +/** + * enum mic_hw_family - The hardware family to which a device belongs. + */ +enum mic_hw_family { + MIC_FAMILY_X100 = 0, + MIC_FAMILY_UNKNOWN +}; + +/** + * enum mic_stepping - MIC stepping ids. + */ +enum mic_stepping { + MIC_A0_STEP = 0x0, + MIC_B0_STEP = 0x10, + MIC_B1_STEP = 0x11, + MIC_C0_STEP = 0x20, +}; + +/** + * struct mic_device - MIC device information for each card. + * + * @mmio: MMIO bar information. + * @aper: Aperture bar information. + * @family: The MIC family to which this device belongs. + * @ops: MIC HW specific operations. + * @id: The unique device id for this MIC device. + * @stepping: Stepping ID. + * @attr_group: Pointer to list of sysfs attribute groups. + * @sdev: Device for sysfs entries. + * @mic_mutex: Mutex for synchronizing access to mic_device. + * @intr_ops: HW specific interrupt operations. + * @smpt_ops: Hardware specific SMPT operations. + * @smpt: MIC SMPT information. + * @intr_info: H/W specific interrupt information. + * @irq_info: The OS specific irq information + * @dbg_dir: debugfs directory of this MIC device. + * @cmdline: Kernel command line. + * @firmware: Firmware file name. + * @ramdisk: Ramdisk file name. + * @bootmode: Boot mode i.e. "linux" or "elf" for flash updates. + * @bootaddr: MIC boot address. + * @reset_trigger_work: Work for triggering reset requests. + * @shutdown_work: Work for handling shutdown interrupts. + * @state: MIC state. + * @shutdown_status: MIC status reported by card for shutdown/crashes. + * @state_sysfs: Sysfs dirent for notifying ring 3 about MIC state changes. + * @reset_wait: Waitqueue for sleeping while reset completes. + * @log_buf_addr: Log buffer address for MIC. + * @log_buf_len: Log buffer length address for MIC. + * @dp: virtio device page + * @dp_dma_addr: virtio device page DMA address. + * @shutdown_db: shutdown doorbell. + * @shutdown_cookie: shutdown cookie. + * @cdev: Character device for MIC. + * @vdev_list: list of virtio devices. + * @pm_notifier: Handles PM notifications from the OS. + */ +struct mic_device { + struct mic_mw mmio; + struct mic_mw aper; + enum mic_hw_family family; + struct mic_hw_ops *ops; + int id; + enum mic_stepping stepping; + const struct attribute_group **attr_group; + struct device *sdev; + struct mutex mic_mutex; + struct mic_hw_intr_ops *intr_ops; + struct mic_smpt_ops *smpt_ops; + struct mic_smpt_info *smpt; + struct mic_intr_info *intr_info; + struct mic_irq_info irq_info; + struct dentry *dbg_dir; + char *cmdline; + char *firmware; + char *ramdisk; + char *bootmode; + u32 bootaddr; + struct work_struct reset_trigger_work; + struct work_struct shutdown_work; + u8 state; + u8 shutdown_status; + struct kernfs_node *state_sysfs; + struct completion reset_wait; + void *log_buf_addr; + int *log_buf_len; + void *dp; + dma_addr_t dp_dma_addr; + int shutdown_db; + struct mic_irq *shutdown_cookie; + struct cdev cdev; + struct list_head vdev_list; + struct notifier_block pm_notifier; +}; + +/** + * struct mic_hw_ops - MIC HW specific operations. + * @aper_bar: Aperture bar resource number. + * @mmio_bar: MMIO bar resource number. + * @read_spad: Read from scratch pad register. + * @write_spad: Write to scratch pad register. + * @send_intr: Send an interrupt for a particular doorbell on the card. + * @ack_interrupt: Hardware specific operations to ack the h/w on + * receipt of an interrupt. + * @intr_workarounds: Hardware specific workarounds needed after + * handling an interrupt. + * @reset: Reset the remote processor. + * @reset_fw_ready: Reset firmware ready field. + * @is_fw_ready: Check if firmware is ready for OS download. + * @send_firmware_intr: Send an interrupt to the card firmware. + * @load_mic_fw: Load firmware segments required to boot the card + * into card memory. This includes the kernel, command line, ramdisk etc. + * @get_postcode: Get post code status from firmware. + */ +struct mic_hw_ops { + u8 aper_bar; + u8 mmio_bar; + u32 (*read_spad)(struct mic_device *mdev, unsigned int idx); + void (*write_spad)(struct mic_device *mdev, unsigned int idx, u32 val); + void (*send_intr)(struct mic_device *mdev, int doorbell); + u32 (*ack_interrupt)(struct mic_device *mdev); + void (*intr_workarounds)(struct mic_device *mdev); + void (*reset)(struct mic_device *mdev); + void (*reset_fw_ready)(struct mic_device *mdev); + bool (*is_fw_ready)(struct mic_device *mdev); + void (*send_firmware_intr)(struct mic_device *mdev); + int (*load_mic_fw)(struct mic_device *mdev, const char *buf); + u32 (*get_postcode)(struct mic_device *mdev); +}; + +/** + * mic_mmio_read - read from an MMIO register. + * @mw: MMIO register base virtual address. + * @offset: register offset. + * + * RETURNS: register value. + */ +static inline u32 mic_mmio_read(struct mic_mw *mw, u32 offset) +{ + return ioread32(mw->va + offset); +} + +/** + * mic_mmio_write - write to an MMIO register. + * @mw: MMIO register base virtual address. + * @val: the data value to put into the register + * @offset: register offset. + * + * RETURNS: none. + */ +static inline void +mic_mmio_write(struct mic_mw *mw, u32 val, u32 offset) +{ + iowrite32(val, mw->va + offset); +} + +void mic_sysfs_init(struct mic_device *mdev); +int mic_start(struct mic_device *mdev, const char *buf); +void mic_stop(struct mic_device *mdev, bool force); +void mic_shutdown(struct mic_device *mdev); +void mic_reset_delayed_work(struct work_struct *work); +void mic_reset_trigger_work(struct work_struct *work); +void mic_shutdown_work(struct work_struct *work); +void mic_bootparam_init(struct mic_device *mdev); +void mic_set_state(struct mic_device *mdev, u8 state); +void mic_set_shutdown_status(struct mic_device *mdev, u8 status); +void mic_create_debug_dir(struct mic_device *dev); +void mic_delete_debug_dir(struct mic_device *dev); +void __init mic_init_debugfs(void); +void mic_exit_debugfs(void); +void mic_prepare_suspend(struct mic_device *mdev); +void mic_complete_resume(struct mic_device *mdev); +void mic_suspend(struct mic_device *mdev); +#endif diff --git a/drivers/misc/mic/host/mic_fops.c b/drivers/misc/mic/host/mic_fops.c new file mode 100644 index 000000000000..85776d7327f3 --- /dev/null +++ b/drivers/misc/mic/host/mic_fops.c @@ -0,0 +1,222 @@ +/* + * Intel MIC Platform Software Stack (MPSS) + * + * Copyright(c) 2013 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Intel MIC Host driver. + * + */ +#include <linux/poll.h> +#include <linux/pci.h> + +#include <linux/mic_common.h> +#include "../common/mic_dev.h" +#include "mic_device.h" +#include "mic_fops.h" +#include "mic_virtio.h" + +int mic_open(struct inode *inode, struct file *f) +{ + struct mic_vdev *mvdev; + struct mic_device *mdev = container_of(inode->i_cdev, + struct mic_device, cdev); + + mvdev = kzalloc(sizeof(*mvdev), GFP_KERNEL); + if (!mvdev) + return -ENOMEM; + + init_waitqueue_head(&mvdev->waitq); + INIT_LIST_HEAD(&mvdev->list); + mvdev->mdev = mdev; + mvdev->virtio_id = -1; + + f->private_data = mvdev; + return 0; +} + +int mic_release(struct inode *inode, struct file *f) +{ + struct mic_vdev *mvdev = (struct mic_vdev *)f->private_data; + + if (-1 != mvdev->virtio_id) + mic_virtio_del_device(mvdev); + f->private_data = NULL; + kfree(mvdev); + return 0; +} + +long mic_ioctl(struct file *f, unsigned int cmd, unsigned long arg) +{ + struct mic_vdev *mvdev = (struct mic_vdev *)f->private_data; + void __user *argp = (void __user *)arg; + int ret; + + switch (cmd) { + case MIC_VIRTIO_ADD_DEVICE: + { + ret = mic_virtio_add_device(mvdev, argp); + if (ret < 0) { + dev_err(mic_dev(mvdev), + "%s %d errno ret %d\n", + __func__, __LINE__, ret); + return ret; + } + break; + } + case MIC_VIRTIO_COPY_DESC: + { + struct mic_copy_desc copy; + + ret = mic_vdev_inited(mvdev); + if (ret) + return ret; + + if (copy_from_user(©, argp, sizeof(copy))) + return -EFAULT; + + dev_dbg(mic_dev(mvdev), + "%s %d === iovcnt 0x%x vr_idx 0x%x update_used %d\n", + __func__, __LINE__, copy.iovcnt, copy.vr_idx, + copy.update_used); + + ret = mic_virtio_copy_desc(mvdev, ©); + if (ret < 0) { + dev_err(mic_dev(mvdev), + "%s %d errno ret %d\n", + __func__, __LINE__, ret); + return ret; + } + if (copy_to_user( + &((struct mic_copy_desc __user *)argp)->out_len, + ©.out_len, sizeof(copy.out_len))) { + dev_err(mic_dev(mvdev), "%s %d errno ret %d\n", + __func__, __LINE__, -EFAULT); + return -EFAULT; + } + break; + } + case MIC_VIRTIO_CONFIG_CHANGE: + { + ret = mic_vdev_inited(mvdev); + if (ret) + return ret; + + ret = mic_virtio_config_change(mvdev, argp); + if (ret < 0) { + dev_err(mic_dev(mvdev), + "%s %d errno ret %d\n", + __func__, __LINE__, ret); + return ret; + } + break; + } + default: + return -ENOIOCTLCMD; + }; + return 0; +} + +/* + * We return POLLIN | POLLOUT from poll when new buffers are enqueued, and + * not when previously enqueued buffers may be available. This means that + * in the card->host (TX) path, when userspace is unblocked by poll it + * must drain all available descriptors or it can stall. + */ +unsigned int mic_poll(struct file *f, poll_table *wait) +{ + struct mic_vdev *mvdev = (struct mic_vdev *)f->private_data; + int mask = 0; + + poll_wait(f, &mvdev->waitq, wait); + + if (mic_vdev_inited(mvdev)) { + mask = POLLERR; + } else if (mvdev->poll_wake) { + mvdev->poll_wake = 0; + mask = POLLIN | POLLOUT; + } + + return mask; +} + +static inline int +mic_query_offset(struct mic_vdev *mvdev, unsigned long offset, + unsigned long *size, unsigned long *pa) +{ + struct mic_device *mdev = mvdev->mdev; + unsigned long start = MIC_DP_SIZE; + int i; + + /* + * MMAP interface is as follows: + * offset region + * 0x0 virtio device_page + * 0x1000 first vring + * 0x1000 + size of 1st vring second vring + * .... + */ + if (!offset) { + *pa = virt_to_phys(mdev->dp); + *size = MIC_DP_SIZE; + return 0; + } + + for (i = 0; i < mvdev->dd->num_vq; i++) { + struct mic_vringh *mvr = &mvdev->mvr[i]; + if (offset == start) { + *pa = virt_to_phys(mvr->vring.va); + *size = mvr->vring.len; + return 0; + } + start += mvr->vring.len; + } + return -1; +} + +/* + * Maps the device page and virtio rings to user space for readonly access. + */ +int +mic_mmap(struct file *f, struct vm_area_struct *vma) +{ + struct mic_vdev *mvdev = (struct mic_vdev *)f->private_data; + unsigned long offset = vma->vm_pgoff << PAGE_SHIFT; + unsigned long pa, size = vma->vm_end - vma->vm_start, size_rem = size; + int i, err; + + err = mic_vdev_inited(mvdev); + if (err) + return err; + + if (vma->vm_flags & VM_WRITE) + return -EACCES; + + while (size_rem) { + i = mic_query_offset(mvdev, offset, &size, &pa); + if (i < 0) + return -EINVAL; + err = remap_pfn_range(vma, vma->vm_start + offset, + pa >> PAGE_SHIFT, size, vma->vm_page_prot); + if (err) + return err; + dev_dbg(mic_dev(mvdev), + "%s %d type %d size 0x%lx off 0x%lx pa 0x%lx vma 0x%lx\n", + __func__, __LINE__, mvdev->virtio_id, size, offset, + pa, vma->vm_start + offset); + size_rem -= size; + offset += size; + } + return 0; +} diff --git a/drivers/misc/mic/host/mic_fops.h b/drivers/misc/mic/host/mic_fops.h new file mode 100644 index 000000000000..dc3893dff667 --- /dev/null +++ b/drivers/misc/mic/host/mic_fops.h @@ -0,0 +1,32 @@ +/* + * Intel MIC Platform Software Stack (MPSS) + * + * Copyright(c) 2013 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Intel MIC Host driver. + * + */ +#ifndef _MIC_FOPS_H_ +#define _MIC_FOPS_H_ + +int mic_open(struct inode *inode, struct file *filp); +int mic_release(struct inode *inode, struct file *filp); +ssize_t mic_read(struct file *filp, char __user *buf, + size_t count, loff_t *pos); +long mic_ioctl(struct file *filp, unsigned int cmd, unsigned long arg); +int mic_mmap(struct file *f, struct vm_area_struct *vma); +unsigned int mic_poll(struct file *f, poll_table *wait); + +#endif diff --git a/drivers/misc/mic/host/mic_intr.c b/drivers/misc/mic/host/mic_intr.c new file mode 100644 index 000000000000..f9c29bc918bc --- /dev/null +++ b/drivers/misc/mic/host/mic_intr.c @@ -0,0 +1,630 @@ +/* + * Intel MIC Platform Software Stack (MPSS) + * + * Copyright(c) 2013 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Intel MIC Host driver. + * + */ +#include <linux/pci.h> +#include <linux/interrupt.h> + +#include "../common/mic_dev.h" +#include "mic_device.h" + +/* + * mic_invoke_callback - Invoke callback functions registered for + * the corresponding source id. + * + * @mdev: pointer to the mic_device instance + * @idx: The interrupt source id. + * + * Returns none. + */ +static inline void mic_invoke_callback(struct mic_device *mdev, int idx) +{ + struct mic_intr_cb *intr_cb; + struct pci_dev *pdev = container_of(mdev->sdev->parent, + struct pci_dev, dev); + + spin_lock(&mdev->irq_info.mic_intr_lock); + list_for_each_entry(intr_cb, &mdev->irq_info.cb_list[idx], list) + if (intr_cb->func) + intr_cb->func(pdev->irq, intr_cb->data); + spin_unlock(&mdev->irq_info.mic_intr_lock); +} + +/** + * mic_interrupt - Generic interrupt handler for + * MSI and INTx based interrupts. + */ +static irqreturn_t mic_interrupt(int irq, void *dev) +{ + struct mic_device *mdev = dev; + struct mic_intr_info *info = mdev->intr_info; + u32 mask; + int i; + + mask = mdev->ops->ack_interrupt(mdev); + if (!mask) + return IRQ_NONE; + + for (i = info->intr_start_idx[MIC_INTR_DB]; + i < info->intr_len[MIC_INTR_DB]; i++) + if (mask & BIT(i)) + mic_invoke_callback(mdev, i); + + return IRQ_HANDLED; +} + +/* Return the interrupt offset from the index. Index is 0 based. */ +static u16 mic_map_src_to_offset(struct mic_device *mdev, + int intr_src, enum mic_intr_type type) +{ + if (type >= MIC_NUM_INTR_TYPES) + return MIC_NUM_OFFSETS; + if (intr_src >= mdev->intr_info->intr_len[type]) + return MIC_NUM_OFFSETS; + + return mdev->intr_info->intr_start_idx[type] + intr_src; +} + +/* Return next available msix_entry. */ +static struct msix_entry *mic_get_available_vector(struct mic_device *mdev) +{ + int i; + struct mic_irq_info *info = &mdev->irq_info; + + for (i = 0; i < info->num_vectors; i++) + if (!info->mic_msi_map[i]) + return &info->msix_entries[i]; + return NULL; +} + +/** + * mic_register_intr_callback - Register a callback handler for the + * given source id. + * + * @mdev: pointer to the mic_device instance + * @idx: The source id to be registered. + * @func: The function to be called when the source id receives + * the interrupt. + * @data: Private data of the requester. + * Return the callback structure that was registered or an + * appropriate error on failure. + */ +static struct mic_intr_cb *mic_register_intr_callback(struct mic_device *mdev, + u8 idx, irqreturn_t (*func) (int irq, void *dev), + void *data) +{ + struct mic_intr_cb *intr_cb; + unsigned long flags; + int rc; + intr_cb = kmalloc(sizeof(*intr_cb), GFP_KERNEL); + + if (!intr_cb) + return ERR_PTR(-ENOMEM); + + intr_cb->func = func; + intr_cb->data = data; + intr_cb->cb_id = ida_simple_get(&mdev->irq_info.cb_ida, + 0, 0, GFP_KERNEL); + if (intr_cb->cb_id < 0) { + rc = intr_cb->cb_id; + goto ida_fail; + } + + spin_lock_irqsave(&mdev->irq_info.mic_intr_lock, flags); + list_add_tail(&intr_cb->list, &mdev->irq_info.cb_list[idx]); + spin_unlock_irqrestore(&mdev->irq_info.mic_intr_lock, flags); + + return intr_cb; +ida_fail: + kfree(intr_cb); + return ERR_PTR(rc); +} + +/** + * mic_unregister_intr_callback - Unregister the callback handler + * identified by its callback id. + * + * @mdev: pointer to the mic_device instance + * @idx: The callback structure id to be unregistered. + * Return the source id that was unregistered or MIC_NUM_OFFSETS if no + * such callback handler was found. + */ +static u8 mic_unregister_intr_callback(struct mic_device *mdev, u32 idx) +{ + struct list_head *pos, *tmp; + struct mic_intr_cb *intr_cb; + unsigned long flags; + int i; + + for (i = 0; i < MIC_NUM_OFFSETS; i++) { + spin_lock_irqsave(&mdev->irq_info.mic_intr_lock, flags); + list_for_each_safe(pos, tmp, &mdev->irq_info.cb_list[i]) { + intr_cb = list_entry(pos, struct mic_intr_cb, list); + if (intr_cb->cb_id == idx) { + list_del(pos); + ida_simple_remove(&mdev->irq_info.cb_ida, + intr_cb->cb_id); + kfree(intr_cb); + spin_unlock_irqrestore( + &mdev->irq_info.mic_intr_lock, flags); + return i; + } + } + spin_unlock_irqrestore(&mdev->irq_info.mic_intr_lock, flags); + } + return MIC_NUM_OFFSETS; +} + +/** + * mic_setup_msix - Initializes MSIx interrupts. + * + * @mdev: pointer to mic_device instance + * + * + * RETURNS: An appropriate -ERRNO error value on error, or zero for success. + */ +static int mic_setup_msix(struct mic_device *mdev, struct pci_dev *pdev) +{ + int rc, i; + int entry_size = sizeof(*mdev->irq_info.msix_entries); + + mdev->irq_info.msix_entries = kmalloc_array(MIC_MIN_MSIX, + entry_size, GFP_KERNEL); + if (!mdev->irq_info.msix_entries) { + rc = -ENOMEM; + goto err_nomem1; + } + + for (i = 0; i < MIC_MIN_MSIX; i++) + mdev->irq_info.msix_entries[i].entry = i; + + rc = pci_enable_msix(pdev, mdev->irq_info.msix_entries, + MIC_MIN_MSIX); + if (rc) { + dev_dbg(&pdev->dev, "Error enabling MSIx. rc = %d\n", rc); + goto err_enable_msix; + } + + mdev->irq_info.num_vectors = MIC_MIN_MSIX; + mdev->irq_info.mic_msi_map = kzalloc((sizeof(u32) * + mdev->irq_info.num_vectors), GFP_KERNEL); + + if (!mdev->irq_info.mic_msi_map) { + rc = -ENOMEM; + goto err_nomem2; + } + + dev_dbg(mdev->sdev->parent, + "%d MSIx irqs setup\n", mdev->irq_info.num_vectors); + return 0; +err_nomem2: + pci_disable_msix(pdev); +err_enable_msix: + kfree(mdev->irq_info.msix_entries); +err_nomem1: + mdev->irq_info.num_vectors = 0; + return rc; +} + +/** + * mic_setup_callbacks - Initialize data structures needed + * to handle callbacks. + * + * @mdev: pointer to mic_device instance + */ +static int mic_setup_callbacks(struct mic_device *mdev) +{ + int i; + + mdev->irq_info.cb_list = kmalloc_array(MIC_NUM_OFFSETS, + sizeof(*mdev->irq_info.cb_list), + GFP_KERNEL); + if (!mdev->irq_info.cb_list) + return -ENOMEM; + + for (i = 0; i < MIC_NUM_OFFSETS; i++) + INIT_LIST_HEAD(&mdev->irq_info.cb_list[i]); + ida_init(&mdev->irq_info.cb_ida); + spin_lock_init(&mdev->irq_info.mic_intr_lock); + return 0; +} + +/** + * mic_release_callbacks - Uninitialize data structures needed + * to handle callbacks. + * + * @mdev: pointer to mic_device instance + */ +static void mic_release_callbacks(struct mic_device *mdev) +{ + unsigned long flags; + struct list_head *pos, *tmp; + struct mic_intr_cb *intr_cb; + int i; + + for (i = 0; i < MIC_NUM_OFFSETS; i++) { + spin_lock_irqsave(&mdev->irq_info.mic_intr_lock, flags); + + if (list_empty(&mdev->irq_info.cb_list[i])) { + spin_unlock_irqrestore(&mdev->irq_info.mic_intr_lock, + flags); + break; + } + + list_for_each_safe(pos, tmp, &mdev->irq_info.cb_list[i]) { + intr_cb = list_entry(pos, struct mic_intr_cb, list); + list_del(pos); + ida_simple_remove(&mdev->irq_info.cb_ida, + intr_cb->cb_id); + kfree(intr_cb); + } + spin_unlock_irqrestore(&mdev->irq_info.mic_intr_lock, flags); + } + ida_destroy(&mdev->irq_info.cb_ida); + kfree(mdev->irq_info.cb_list); +} + +/** + * mic_setup_msi - Initializes MSI interrupts. + * + * @mdev: pointer to mic_device instance + * @pdev: PCI device structure + * + * RETURNS: An appropriate -ERRNO error value on error, or zero for success. + */ +static int mic_setup_msi(struct mic_device *mdev, struct pci_dev *pdev) +{ + int rc; + + rc = pci_enable_msi(pdev); + if (rc) { + dev_dbg(&pdev->dev, "Error enabling MSI. rc = %d\n", rc); + return rc; + } + + mdev->irq_info.num_vectors = 1; + mdev->irq_info.mic_msi_map = kzalloc((sizeof(u32) * + mdev->irq_info.num_vectors), GFP_KERNEL); + + if (!mdev->irq_info.mic_msi_map) { + rc = -ENOMEM; + goto err_nomem1; + } + + rc = mic_setup_callbacks(mdev); + if (rc) { + dev_err(&pdev->dev, "Error setting up callbacks\n"); + goto err_nomem2; + } + + rc = request_irq(pdev->irq, mic_interrupt, 0 , "mic-msi", mdev); + if (rc) { + dev_err(&pdev->dev, "Error allocating MSI interrupt\n"); + goto err_irq_req_fail; + } + + dev_dbg(&pdev->dev, "%d MSI irqs setup\n", mdev->irq_info.num_vectors); + return 0; +err_irq_req_fail: + mic_release_callbacks(mdev); +err_nomem2: + kfree(mdev->irq_info.mic_msi_map); +err_nomem1: + pci_disable_msi(pdev); + mdev->irq_info.num_vectors = 0; + return rc; +} + +/** + * mic_setup_intx - Initializes legacy interrupts. + * + * @mdev: pointer to mic_device instance + * @pdev: PCI device structure + * + * RETURNS: An appropriate -ERRNO error value on error, or zero for success. + */ +static int mic_setup_intx(struct mic_device *mdev, struct pci_dev *pdev) +{ + int rc; + + pci_msi_off(pdev); + + /* Enable intx */ + pci_intx(pdev, 1); + rc = mic_setup_callbacks(mdev); + if (rc) { + dev_err(&pdev->dev, "Error setting up callbacks\n"); + goto err_nomem; + } + + rc = request_irq(pdev->irq, mic_interrupt, + IRQF_SHARED, "mic-intx", mdev); + if (rc) + goto err; + + dev_dbg(&pdev->dev, "intx irq setup\n"); + return 0; +err: + mic_release_callbacks(mdev); +err_nomem: + return rc; +} + +/** + * mic_next_db - Retrieve the next doorbell interrupt source id. + * The id is picked sequentially from the available pool of + * doorlbell ids. + * + * @mdev: pointer to the mic_device instance. + * + * Returns the next doorbell interrupt source. + */ +int mic_next_db(struct mic_device *mdev) +{ + int next_db; + + next_db = mdev->irq_info.next_avail_src % + mdev->intr_info->intr_len[MIC_INTR_DB]; + mdev->irq_info.next_avail_src++; + return next_db; +} + +#define COOKIE_ID_SHIFT 16 +#define GET_ENTRY(cookie) ((cookie) & 0xFFFF) +#define GET_OFFSET(cookie) ((cookie) >> COOKIE_ID_SHIFT) +#define MK_COOKIE(x, y) ((x) | (y) << COOKIE_ID_SHIFT) + +/** + * mic_request_irq - request an irq. mic_mutex needs + * to be held before calling this function. + * + * @mdev: pointer to mic_device instance + * @func: The callback function that handles the interrupt. + * The function needs to call ack_interrupts + * (mdev->ops->ack_interrupt(mdev)) when handling the interrupts. + * @name: The ASCII name of the callee requesting the irq. + * @data: private data that is returned back when calling the + * function handler. + * @intr_src: The source id of the requester. Its the doorbell id + * for Doorbell interrupts and DMA channel id for DMA interrupts. + * @type: The type of interrupt. Values defined in mic_intr_type + * + * returns: The cookie that is transparent to the caller. Passed + * back when calling mic_free_irq. An appropriate error code + * is returned on failure. Caller needs to use IS_ERR(return_val) + * to check for failure and PTR_ERR(return_val) to obtained the + * error code. + * + */ +struct mic_irq *mic_request_irq(struct mic_device *mdev, + irqreturn_t (*func)(int irq, void *dev), + const char *name, void *data, int intr_src, + enum mic_intr_type type) +{ + u16 offset; + int rc = 0; + struct msix_entry *msix = NULL; + unsigned long cookie = 0; + u16 entry; + struct mic_intr_cb *intr_cb; + struct pci_dev *pdev = container_of(mdev->sdev->parent, + struct pci_dev, dev); + + offset = mic_map_src_to_offset(mdev, intr_src, type); + if (offset >= MIC_NUM_OFFSETS) { + dev_err(mdev->sdev->parent, + "Error mapping index %d to a valid source id.\n", + intr_src); + rc = -EINVAL; + goto err; + } + + if (mdev->irq_info.num_vectors > 1) { + msix = mic_get_available_vector(mdev); + if (!msix) { + dev_err(mdev->sdev->parent, + "No MSIx vectors available for use.\n"); + rc = -ENOSPC; + goto err; + } + + rc = request_irq(msix->vector, func, 0, name, data); + if (rc) { + dev_dbg(mdev->sdev->parent, + "request irq failed rc = %d\n", rc); + goto err; + } + entry = msix->entry; + mdev->irq_info.mic_msi_map[entry] |= BIT(offset); + mdev->intr_ops->program_msi_to_src_map(mdev, + entry, offset, true); + cookie = MK_COOKIE(entry, offset); + dev_dbg(mdev->sdev->parent, "irq: %d assigned for src: %d\n", + msix->vector, intr_src); + } else { + intr_cb = mic_register_intr_callback(mdev, + offset, func, data); + if (IS_ERR(intr_cb)) { + dev_err(mdev->sdev->parent, + "No available callback entries for use\n"); + rc = PTR_ERR(intr_cb); + goto err; + } + + entry = 0; + if (pci_dev_msi_enabled(pdev)) { + mdev->irq_info.mic_msi_map[entry] |= (1 << offset); + mdev->intr_ops->program_msi_to_src_map(mdev, + entry, offset, true); + } + cookie = MK_COOKIE(entry, intr_cb->cb_id); + dev_dbg(mdev->sdev->parent, "callback %d registered for src: %d\n", + intr_cb->cb_id, intr_src); + } + return (struct mic_irq *)cookie; +err: + return ERR_PTR(rc); +} + +/** + * mic_free_irq - free irq. mic_mutex + * needs to be held before calling this function. + * + * @mdev: pointer to mic_device instance + * @cookie: cookie obtained during a successful call to mic_request_irq + * @data: private data specified by the calling function during the + * mic_request_irq + * + * returns: none. + */ +void mic_free_irq(struct mic_device *mdev, + struct mic_irq *cookie, void *data) +{ + u32 offset; + u32 entry; + u8 src_id; + unsigned int irq; + struct pci_dev *pdev = container_of(mdev->sdev->parent, + struct pci_dev, dev); + + entry = GET_ENTRY((unsigned long)cookie); + offset = GET_OFFSET((unsigned long)cookie); + if (mdev->irq_info.num_vectors > 1) { + if (entry >= mdev->irq_info.num_vectors) { + dev_warn(mdev->sdev->parent, + "entry %d should be < num_irq %d\n", + entry, mdev->irq_info.num_vectors); + return; + } + irq = mdev->irq_info.msix_entries[entry].vector; + free_irq(irq, data); + mdev->irq_info.mic_msi_map[entry] &= ~(BIT(offset)); + mdev->intr_ops->program_msi_to_src_map(mdev, + entry, offset, false); + + dev_dbg(mdev->sdev->parent, "irq: %d freed\n", irq); + } else { + irq = pdev->irq; + src_id = mic_unregister_intr_callback(mdev, offset); + if (src_id >= MIC_NUM_OFFSETS) { + dev_warn(mdev->sdev->parent, "Error unregistering callback\n"); + return; + } + if (pci_dev_msi_enabled(pdev)) { + mdev->irq_info.mic_msi_map[entry] &= ~(BIT(src_id)); + mdev->intr_ops->program_msi_to_src_map(mdev, + entry, src_id, false); + } + dev_dbg(mdev->sdev->parent, "callback %d unregistered for src: %d\n", + offset, src_id); + } +} + +/** + * mic_setup_interrupts - Initializes interrupts. + * + * @mdev: pointer to mic_device instance + * @pdev: PCI device structure + * + * RETURNS: An appropriate -ERRNO error value on error, or zero for success. + */ +int mic_setup_interrupts(struct mic_device *mdev, struct pci_dev *pdev) +{ + int rc; + + rc = mic_setup_msix(mdev, pdev); + if (!rc) + goto done; + + rc = mic_setup_msi(mdev, pdev); + if (!rc) + goto done; + + rc = mic_setup_intx(mdev, pdev); + if (rc) { + dev_err(mdev->sdev->parent, "no usable interrupts\n"); + return rc; + } +done: + mdev->intr_ops->enable_interrupts(mdev); + return 0; +} + +/** + * mic_free_interrupts - Frees interrupts setup by mic_setup_interrupts + * + * @mdev: pointer to mic_device instance + * @pdev: PCI device structure + * + * returns none. + */ +void mic_free_interrupts(struct mic_device *mdev, struct pci_dev *pdev) +{ + int i; + + mdev->intr_ops->disable_interrupts(mdev); + if (mdev->irq_info.num_vectors > 1) { + for (i = 0; i < mdev->irq_info.num_vectors; i++) { + if (mdev->irq_info.mic_msi_map[i]) + dev_warn(&pdev->dev, "irq %d may still be in use.\n", + mdev->irq_info.msix_entries[i].vector); + } + kfree(mdev->irq_info.mic_msi_map); + kfree(mdev->irq_info.msix_entries); + pci_disable_msix(pdev); + } else { + if (pci_dev_msi_enabled(pdev)) { + free_irq(pdev->irq, mdev); + kfree(mdev->irq_info.mic_msi_map); + pci_disable_msi(pdev); + } else { + free_irq(pdev->irq, mdev); + } + mic_release_callbacks(mdev); + } +} + +/** + * mic_intr_restore - Restore MIC interrupt registers. + * + * @mdev: pointer to mic_device instance. + * + * Restore the interrupt registers to values previously + * stored in the SW data structures. mic_mutex needs to + * be held before calling this function. + * + * returns None. + */ +void mic_intr_restore(struct mic_device *mdev) +{ + int entry, offset; + struct pci_dev *pdev = container_of(mdev->sdev->parent, + struct pci_dev, dev); + + if (!pci_dev_msi_enabled(pdev)) + return; + + for (entry = 0; entry < mdev->irq_info.num_vectors; entry++) { + for (offset = 0; offset < MIC_NUM_OFFSETS; offset++) { + if (mdev->irq_info.mic_msi_map[entry] & BIT(offset)) + mdev->intr_ops->program_msi_to_src_map(mdev, + entry, offset, true); + } + } +} diff --git a/drivers/misc/mic/host/mic_intr.h b/drivers/misc/mic/host/mic_intr.h new file mode 100644 index 000000000000..6091aa97e116 --- /dev/null +++ b/drivers/misc/mic/host/mic_intr.h @@ -0,0 +1,137 @@ +/* + * Intel MIC Platform Software Stack (MPSS) + * + * Copyright(c) 2013 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Intel MIC Host driver. + * + */ +#ifndef _MIC_INTR_H_ +#define _MIC_INTR_H_ + +/* + * The minimum number of msix vectors required for normal operation. + * 3 for virtio network, console and block devices. + * 1 for card shutdown notifications. + */ +#define MIC_MIN_MSIX 4 +#define MIC_NUM_OFFSETS 32 + +/** + * mic_intr_source - The type of source that will generate + * the interrupt.The number of types needs to be in sync with + * MIC_NUM_INTR_TYPES + * + * MIC_INTR_DB: The source is a doorbell + * MIC_INTR_DMA: The source is a DMA channel + * MIC_INTR_ERR: The source is an error interrupt e.g. SBOX ERR + * MIC_NUM_INTR_TYPES: Total number of interrupt sources. + */ +enum mic_intr_type { + MIC_INTR_DB = 0, + MIC_INTR_DMA, + MIC_INTR_ERR, + MIC_NUM_INTR_TYPES +}; + +/** + * struct mic_intr_info - Contains h/w specific interrupt sources + * information. + * + * @intr_start_idx: Contains the starting indexes of the + * interrupt types. + * @intr_len: Contains the length of the interrupt types. + */ +struct mic_intr_info { + u16 intr_start_idx[MIC_NUM_INTR_TYPES]; + u16 intr_len[MIC_NUM_INTR_TYPES]; +}; + +/** + * struct mic_irq_info - OS specific irq information + * + * @next_avail_src: next available doorbell that can be assigned. + * @msix_entries: msix entries allocated while setting up MSI-x + * @mic_msi_map: The MSI/MSI-x mapping information. + * @num_vectors: The number of MSI/MSI-x vectors that have been allocated. + * @cb_ida: callback ID allocator to track the callbacks registered. + * @mic_intr_lock: spinlock to protect the interrupt callback list. + * @cb_list: Array of callback lists one for each source. + */ +struct mic_irq_info { + int next_avail_src; + struct msix_entry *msix_entries; + u32 *mic_msi_map; + u16 num_vectors; + struct ida cb_ida; + spinlock_t mic_intr_lock; + struct list_head *cb_list; +}; + +/** + * struct mic_intr_cb - Interrupt callback structure. + * + * @func: The callback function + * @data: Private data of the requester. + * @cb_id: The callback id. Identifies this callback. + * @list: list head pointing to the next callback structure. + */ +struct mic_intr_cb { + irqreturn_t (*func) (int irq, void *data); + void *data; + int cb_id; + struct list_head list; +}; + +/** + * struct mic_irq - opaque pointer used as cookie + */ +struct mic_irq; + +/* Forward declaration */ +struct mic_device; + +/** + * struct mic_hw_intr_ops: MIC HW specific interrupt operations + * @intr_init: Initialize H/W specific interrupt information. + * @enable_interrupts: Enable interrupts from the hardware. + * @disable_interrupts: Disable interrupts from the hardware. + * @program_msi_to_src_map: Update MSI mapping registers with + * irq information. + * @read_msi_to_src_map: Read MSI mapping registers containing + * irq information. + */ +struct mic_hw_intr_ops { + void (*intr_init)(struct mic_device *mdev); + void (*enable_interrupts)(struct mic_device *mdev); + void (*disable_interrupts)(struct mic_device *mdev); + void (*program_msi_to_src_map) (struct mic_device *mdev, + int idx, int intr_src, bool set); + u32 (*read_msi_to_src_map) (struct mic_device *mdev, + int idx); +}; + +int mic_next_db(struct mic_device *mdev); +struct mic_irq *mic_request_irq(struct mic_device *mdev, + irqreturn_t (*func)(int irq, void *data), + const char *name, void *data, int intr_src, + enum mic_intr_type type); + +void mic_free_irq(struct mic_device *mdev, + struct mic_irq *cookie, void *data); +int mic_setup_interrupts(struct mic_device *mdev, struct pci_dev *pdev); +void mic_free_interrupts(struct mic_device *mdev, struct pci_dev *pdev); +void mic_intr_restore(struct mic_device *mdev); +#endif diff --git a/drivers/misc/mic/host/mic_main.c b/drivers/misc/mic/host/mic_main.c new file mode 100644 index 000000000000..c04a021e20c7 --- /dev/null +++ b/drivers/misc/mic/host/mic_main.c @@ -0,0 +1,536 @@ +/* + * Intel MIC Platform Software Stack (MPSS) + * + * Copyright(c) 2013 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Intel MIC Host driver. + * + * Global TODO's across the driver to be added after initial base + * patches are accepted upstream: + * 1) Enable DMA support. + * 2) Enable per vring interrupt support. + */ +#include <linux/fs.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/poll.h> +#include <linux/suspend.h> + +#include <linux/mic_common.h> +#include "../common/mic_dev.h" +#include "mic_device.h" +#include "mic_x100.h" +#include "mic_smpt.h" +#include "mic_fops.h" +#include "mic_virtio.h" + +static const char mic_driver_name[] = "mic"; + +static DEFINE_PCI_DEVICE_TABLE(mic_pci_tbl) = { + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2250)}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2251)}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2252)}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2253)}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2254)}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2255)}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2256)}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2257)}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2258)}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_2259)}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_225a)}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_225b)}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_225c)}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_225d)}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MIC_X100_PCI_DEVICE_225e)}, + + /* required last entry */ + { 0, } +}; + +MODULE_DEVICE_TABLE(pci, mic_pci_tbl); + +/* ID allocator for MIC devices */ +static struct ida g_mic_ida; +/* Class of MIC devices for sysfs accessibility. */ +static struct class *g_mic_class; +/* Base device node number for MIC devices */ +static dev_t g_mic_devno; + +static const struct file_operations mic_fops = { + .open = mic_open, + .release = mic_release, + .unlocked_ioctl = mic_ioctl, + .poll = mic_poll, + .mmap = mic_mmap, + .owner = THIS_MODULE, +}; + +/* Initialize the device page */ +static int mic_dp_init(struct mic_device *mdev) +{ + mdev->dp = kzalloc(MIC_DP_SIZE, GFP_KERNEL); + if (!mdev->dp) { + dev_err(mdev->sdev->parent, "%s %d err %d\n", + __func__, __LINE__, -ENOMEM); + return -ENOMEM; + } + + mdev->dp_dma_addr = mic_map_single(mdev, + mdev->dp, MIC_DP_SIZE); + if (mic_map_error(mdev->dp_dma_addr)) { + kfree(mdev->dp); + dev_err(mdev->sdev->parent, "%s %d err %d\n", + __func__, __LINE__, -ENOMEM); + return -ENOMEM; + } + mdev->ops->write_spad(mdev, MIC_DPLO_SPAD, mdev->dp_dma_addr); + mdev->ops->write_spad(mdev, MIC_DPHI_SPAD, mdev->dp_dma_addr >> 32); + return 0; +} + +/* Uninitialize the device page */ +static void mic_dp_uninit(struct mic_device *mdev) +{ + mic_unmap_single(mdev, mdev->dp_dma_addr, MIC_DP_SIZE); + kfree(mdev->dp); +} + +/** + * mic_shutdown_db - Shutdown doorbell interrupt handler. + */ +static irqreturn_t mic_shutdown_db(int irq, void *data) +{ + struct mic_device *mdev = data; + struct mic_bootparam *bootparam = mdev->dp; + + mdev->ops->intr_workarounds(mdev); + + switch (bootparam->shutdown_status) { + case MIC_HALTED: + case MIC_POWER_OFF: + case MIC_RESTART: + /* Fall through */ + case MIC_CRASHED: + schedule_work(&mdev->shutdown_work); + break; + default: + break; + }; + return IRQ_HANDLED; +} + +/** + * mic_ops_init: Initialize HW specific operation tables. + * + * @mdev: pointer to mic_device instance + * + * returns none. + */ +static void mic_ops_init(struct mic_device *mdev) +{ + switch (mdev->family) { + case MIC_FAMILY_X100: + mdev->ops = &mic_x100_ops; + mdev->intr_ops = &mic_x100_intr_ops; + mdev->smpt_ops = &mic_x100_smpt_ops; + break; + default: + break; + } +} + +/** + * mic_get_family - Determine hardware family to which this MIC belongs. + * + * @pdev: The pci device structure + * + * returns family. + */ +static enum mic_hw_family mic_get_family(struct pci_dev *pdev) +{ + enum mic_hw_family family; + + switch (pdev->device) { + case MIC_X100_PCI_DEVICE_2250: + case MIC_X100_PCI_DEVICE_2251: + case MIC_X100_PCI_DEVICE_2252: + case MIC_X100_PCI_DEVICE_2253: + case MIC_X100_PCI_DEVICE_2254: + case MIC_X100_PCI_DEVICE_2255: + case MIC_X100_PCI_DEVICE_2256: + case MIC_X100_PCI_DEVICE_2257: + case MIC_X100_PCI_DEVICE_2258: + case MIC_X100_PCI_DEVICE_2259: + case MIC_X100_PCI_DEVICE_225a: + case MIC_X100_PCI_DEVICE_225b: + case MIC_X100_PCI_DEVICE_225c: + case MIC_X100_PCI_DEVICE_225d: + case MIC_X100_PCI_DEVICE_225e: + family = MIC_FAMILY_X100; + break; + default: + family = MIC_FAMILY_UNKNOWN; + break; + } + return family; +} + +/** +* mic_pm_notifier: Notifier callback function that handles +* PM notifications. +* +* @notifier_block: The notifier structure. +* @pm_event: The event for which the driver was notified. +* @unused: Meaningless. Always NULL. +* +* returns NOTIFY_DONE +*/ +static int mic_pm_notifier(struct notifier_block *notifier, + unsigned long pm_event, void *unused) +{ + struct mic_device *mdev = container_of(notifier, + struct mic_device, pm_notifier); + + switch (pm_event) { + case PM_HIBERNATION_PREPARE: + /* Fall through */ + case PM_SUSPEND_PREPARE: + mic_prepare_suspend(mdev); + break; + case PM_POST_HIBERNATION: + /* Fall through */ + case PM_POST_SUSPEND: + /* Fall through */ + case PM_POST_RESTORE: + mic_complete_resume(mdev); + break; + case PM_RESTORE_PREPARE: + break; + default: + break; + } + return NOTIFY_DONE; +} + +/** + * mic_device_init - Allocates and initializes the MIC device structure + * + * @mdev: pointer to mic_device instance + * @pdev: The pci device structure + * + * returns none. + */ +static int +mic_device_init(struct mic_device *mdev, struct pci_dev *pdev) +{ + int rc; + + mdev->family = mic_get_family(pdev); + mdev->stepping = pdev->revision; + mic_ops_init(mdev); + mic_sysfs_init(mdev); + mutex_init(&mdev->mic_mutex); + mdev->irq_info.next_avail_src = 0; + INIT_WORK(&mdev->reset_trigger_work, mic_reset_trigger_work); + INIT_WORK(&mdev->shutdown_work, mic_shutdown_work); + init_completion(&mdev->reset_wait); + INIT_LIST_HEAD(&mdev->vdev_list); + mdev->pm_notifier.notifier_call = mic_pm_notifier; + rc = register_pm_notifier(&mdev->pm_notifier); + if (rc) { + dev_err(&pdev->dev, "register_pm_notifier failed rc %d\n", + rc); + goto register_pm_notifier_fail; + } + return 0; +register_pm_notifier_fail: + flush_work(&mdev->shutdown_work); + flush_work(&mdev->reset_trigger_work); + return rc; +} + +/** + * mic_device_uninit - Frees resources allocated during mic_device_init(..) + * + * @mdev: pointer to mic_device instance + * + * returns none + */ +static void mic_device_uninit(struct mic_device *mdev) +{ + /* The cmdline sysfs entry might have allocated cmdline */ + kfree(mdev->cmdline); + kfree(mdev->firmware); + kfree(mdev->ramdisk); + kfree(mdev->bootmode); + flush_work(&mdev->reset_trigger_work); + flush_work(&mdev->shutdown_work); + unregister_pm_notifier(&mdev->pm_notifier); +} + +/** + * mic_probe - Device Initialization Routine + * + * @pdev: PCI device structure + * @ent: entry in mic_pci_tbl + * + * returns 0 on success, < 0 on failure. + */ +static int mic_probe(struct pci_dev *pdev, + const struct pci_device_id *ent) +{ + int rc; + struct mic_device *mdev; + + mdev = kzalloc(sizeof(*mdev), GFP_KERNEL); + if (!mdev) { + rc = -ENOMEM; + dev_err(&pdev->dev, "mdev kmalloc failed rc %d\n", rc); + goto mdev_alloc_fail; + } + mdev->id = ida_simple_get(&g_mic_ida, 0, MIC_MAX_NUM_DEVS, GFP_KERNEL); + if (mdev->id < 0) { + rc = mdev->id; + dev_err(&pdev->dev, "ida_simple_get failed rc %d\n", rc); + goto ida_fail; + } + + rc = mic_device_init(mdev, pdev); + if (rc) { + dev_err(&pdev->dev, "mic_device_init failed rc %d\n", rc); + goto device_init_fail; + } + + rc = pci_enable_device(pdev); + if (rc) { + dev_err(&pdev->dev, "failed to enable pci device.\n"); + goto uninit_device; + } + + pci_set_master(pdev); + + rc = pci_request_regions(pdev, mic_driver_name); + if (rc) { + dev_err(&pdev->dev, "failed to get pci regions.\n"); + goto disable_device; + } + + rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(64)); + if (rc) { + dev_err(&pdev->dev, "Cannot set DMA mask\n"); + goto release_regions; + } + + mdev->mmio.pa = pci_resource_start(pdev, mdev->ops->mmio_bar); + mdev->mmio.len = pci_resource_len(pdev, mdev->ops->mmio_bar); + mdev->mmio.va = pci_ioremap_bar(pdev, mdev->ops->mmio_bar); + if (!mdev->mmio.va) { + dev_err(&pdev->dev, "Cannot remap MMIO BAR\n"); + rc = -EIO; + goto release_regions; + } + + mdev->aper.pa = pci_resource_start(pdev, mdev->ops->aper_bar); + mdev->aper.len = pci_resource_len(pdev, mdev->ops->aper_bar); + mdev->aper.va = ioremap_wc(mdev->aper.pa, mdev->aper.len); + if (!mdev->aper.va) { + dev_err(&pdev->dev, "Cannot remap Aperture BAR\n"); + rc = -EIO; + goto unmap_mmio; + } + + mdev->intr_ops->intr_init(mdev); + rc = mic_setup_interrupts(mdev, pdev); + if (rc) { + dev_err(&pdev->dev, "mic_setup_interrupts failed %d\n", rc); + goto unmap_aper; + } + rc = mic_smpt_init(mdev); + if (rc) { + dev_err(&pdev->dev, "smpt_init failed %d\n", rc); + goto free_interrupts; + } + + pci_set_drvdata(pdev, mdev); + + mdev->sdev = device_create_with_groups(g_mic_class, &pdev->dev, + MKDEV(MAJOR(g_mic_devno), mdev->id), NULL, + mdev->attr_group, "mic%d", mdev->id); + if (IS_ERR(mdev->sdev)) { + rc = PTR_ERR(mdev->sdev); + dev_err(&pdev->dev, + "device_create_with_groups failed rc %d\n", rc); + goto smpt_uninit; + } + mdev->state_sysfs = sysfs_get_dirent(mdev->sdev->kobj.sd, "state"); + if (!mdev->state_sysfs) { + rc = -ENODEV; + dev_err(&pdev->dev, "sysfs_get_dirent failed rc %d\n", rc); + goto destroy_device; + } + + rc = mic_dp_init(mdev); + if (rc) { + dev_err(&pdev->dev, "mic_dp_init failed rc %d\n", rc); + goto sysfs_put; + } + mutex_lock(&mdev->mic_mutex); + + mdev->shutdown_db = mic_next_db(mdev); + mdev->shutdown_cookie = mic_request_irq(mdev, mic_shutdown_db, + "shutdown-interrupt", mdev, mdev->shutdown_db, MIC_INTR_DB); + if (IS_ERR(mdev->shutdown_cookie)) { + rc = PTR_ERR(mdev->shutdown_cookie); + mutex_unlock(&mdev->mic_mutex); + goto dp_uninit; + } + mutex_unlock(&mdev->mic_mutex); + mic_bootparam_init(mdev); + + mic_create_debug_dir(mdev); + cdev_init(&mdev->cdev, &mic_fops); + mdev->cdev.owner = THIS_MODULE; + rc = cdev_add(&mdev->cdev, MKDEV(MAJOR(g_mic_devno), mdev->id), 1); + if (rc) { + dev_err(&pdev->dev, "cdev_add err id %d rc %d\n", mdev->id, rc); + goto cleanup_debug_dir; + } + return 0; +cleanup_debug_dir: + mic_delete_debug_dir(mdev); + mutex_lock(&mdev->mic_mutex); + mic_free_irq(mdev, mdev->shutdown_cookie, mdev); + mutex_unlock(&mdev->mic_mutex); +dp_uninit: + mic_dp_uninit(mdev); +sysfs_put: + sysfs_put(mdev->state_sysfs); +destroy_device: + device_destroy(g_mic_class, MKDEV(MAJOR(g_mic_devno), mdev->id)); +smpt_uninit: + mic_smpt_uninit(mdev); +free_interrupts: + mic_free_interrupts(mdev, pdev); +unmap_aper: + iounmap(mdev->aper.va); +unmap_mmio: + iounmap(mdev->mmio.va); +release_regions: + pci_release_regions(pdev); +disable_device: + pci_disable_device(pdev); +uninit_device: + mic_device_uninit(mdev); +device_init_fail: + ida_simple_remove(&g_mic_ida, mdev->id); +ida_fail: + kfree(mdev); +mdev_alloc_fail: + dev_err(&pdev->dev, "Probe failed rc %d\n", rc); + return rc; +} + +/** + * mic_remove - Device Removal Routine + * mic_remove is called by the PCI subsystem to alert the driver + * that it should release a PCI device. + * + * @pdev: PCI device structure + */ +static void mic_remove(struct pci_dev *pdev) +{ + struct mic_device *mdev; + + mdev = pci_get_drvdata(pdev); + if (!mdev) + return; + + mic_stop(mdev, false); + cdev_del(&mdev->cdev); + mic_delete_debug_dir(mdev); + mutex_lock(&mdev->mic_mutex); + mic_free_irq(mdev, mdev->shutdown_cookie, mdev); + mutex_unlock(&mdev->mic_mutex); + flush_work(&mdev->shutdown_work); + mic_dp_uninit(mdev); + sysfs_put(mdev->state_sysfs); + device_destroy(g_mic_class, MKDEV(MAJOR(g_mic_devno), mdev->id)); + mic_smpt_uninit(mdev); + mic_free_interrupts(mdev, pdev); + iounmap(mdev->mmio.va); + iounmap(mdev->aper.va); + mic_device_uninit(mdev); + pci_release_regions(pdev); + pci_disable_device(pdev); + ida_simple_remove(&g_mic_ida, mdev->id); + kfree(mdev); +} +static struct pci_driver mic_driver = { + .name = mic_driver_name, + .id_table = mic_pci_tbl, + .probe = mic_probe, + .remove = mic_remove +}; + +static int __init mic_init(void) +{ + int ret; + + ret = alloc_chrdev_region(&g_mic_devno, 0, + MIC_MAX_NUM_DEVS, mic_driver_name); + if (ret) { + pr_err("alloc_chrdev_region failed ret %d\n", ret); + goto error; + } + + g_mic_class = class_create(THIS_MODULE, mic_driver_name); + if (IS_ERR(g_mic_class)) { + ret = PTR_ERR(g_mic_class); + pr_err("class_create failed ret %d\n", ret); + goto cleanup_chrdev; + } + + mic_init_debugfs(); + ida_init(&g_mic_ida); + ret = pci_register_driver(&mic_driver); + if (ret) { + pr_err("pci_register_driver failed ret %d\n", ret); + goto cleanup_debugfs; + } + return ret; +cleanup_debugfs: + mic_exit_debugfs(); + class_destroy(g_mic_class); +cleanup_chrdev: + unregister_chrdev_region(g_mic_devno, MIC_MAX_NUM_DEVS); +error: + return ret; +} + +static void __exit mic_exit(void) +{ + pci_unregister_driver(&mic_driver); + ida_destroy(&g_mic_ida); + mic_exit_debugfs(); + class_destroy(g_mic_class); + unregister_chrdev_region(g_mic_devno, MIC_MAX_NUM_DEVS); +} + +module_init(mic_init); +module_exit(mic_exit); + +MODULE_AUTHOR("Intel Corporation"); +MODULE_DESCRIPTION("Intel(R) MIC X100 Host driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/misc/mic/host/mic_smpt.c b/drivers/misc/mic/host/mic_smpt.c new file mode 100644 index 000000000000..fae474c4899e --- /dev/null +++ b/drivers/misc/mic/host/mic_smpt.c @@ -0,0 +1,442 @@ +/* + * Intel MIC Platform Software Stack (MPSS) + * + * Copyright(c) 2013 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Intel MIC Host driver. + * + */ +#include <linux/pci.h> + +#include "../common/mic_dev.h" +#include "mic_device.h" +#include "mic_smpt.h" + +static inline u64 mic_system_page_mask(struct mic_device *mdev) +{ + return (1ULL << mdev->smpt->info.page_shift) - 1ULL; +} + +static inline u8 mic_sys_addr_to_smpt(struct mic_device *mdev, dma_addr_t pa) +{ + return (pa - mdev->smpt->info.base) >> mdev->smpt->info.page_shift; +} + +static inline u64 mic_smpt_to_pa(struct mic_device *mdev, u8 index) +{ + return mdev->smpt->info.base + (index * mdev->smpt->info.page_size); +} + +static inline u64 mic_smpt_offset(struct mic_device *mdev, dma_addr_t pa) +{ + return pa & mic_system_page_mask(mdev); +} + +static inline u64 mic_smpt_align_low(struct mic_device *mdev, dma_addr_t pa) +{ + return ALIGN(pa - mic_system_page_mask(mdev), + mdev->smpt->info.page_size); +} + +static inline u64 mic_smpt_align_high(struct mic_device *mdev, dma_addr_t pa) +{ + return ALIGN(pa, mdev->smpt->info.page_size); +} + +/* Total Cumulative system memory accessible by MIC across all SMPT entries */ +static inline u64 mic_max_system_memory(struct mic_device *mdev) +{ + return mdev->smpt->info.num_reg * mdev->smpt->info.page_size; +} + +/* Maximum system memory address accessible by MIC */ +static inline u64 mic_max_system_addr(struct mic_device *mdev) +{ + return mdev->smpt->info.base + mic_max_system_memory(mdev) - 1ULL; +} + +/* Check if the DMA address is a MIC system memory address */ +static inline bool +mic_is_system_addr(struct mic_device *mdev, dma_addr_t pa) +{ + return pa >= mdev->smpt->info.base && pa <= mic_max_system_addr(mdev); +} + +/* Populate an SMPT entry and update the reference counts. */ +static void mic_add_smpt_entry(int spt, s64 *ref, u64 addr, + int entries, struct mic_device *mdev) +{ + struct mic_smpt_info *smpt_info = mdev->smpt; + int i; + + for (i = spt; i < spt + entries; i++, + addr += smpt_info->info.page_size) { + if (!smpt_info->entry[i].ref_count && + (smpt_info->entry[i].dma_addr != addr)) { + mdev->smpt_ops->set(mdev, addr, i); + smpt_info->entry[i].dma_addr = addr; + } + smpt_info->entry[i].ref_count += ref[i - spt]; + } +} + +/* + * Find an available MIC address in MIC SMPT address space + * for a given DMA address and size. + */ +static dma_addr_t mic_smpt_op(struct mic_device *mdev, u64 dma_addr, + int entries, s64 *ref, size_t size) +{ + int spt; + int ae = 0; + int i; + unsigned long flags; + dma_addr_t mic_addr = 0; + dma_addr_t addr = dma_addr; + struct mic_smpt_info *smpt_info = mdev->smpt; + + spin_lock_irqsave(&smpt_info->smpt_lock, flags); + + /* find existing entries */ + for (i = 0; i < smpt_info->info.num_reg; i++) { + if (smpt_info->entry[i].dma_addr == addr) { + ae++; + addr += smpt_info->info.page_size; + } else if (ae) /* cannot find contiguous entries */ + goto not_found; + + if (ae == entries) + goto found; + } + + /* find free entry */ + for (ae = 0, i = 0; i < smpt_info->info.num_reg; i++) { + ae = (smpt_info->entry[i].ref_count == 0) ? ae + 1 : 0; + if (ae == entries) + goto found; + } + +not_found: + spin_unlock_irqrestore(&smpt_info->smpt_lock, flags); + return mic_addr; + +found: + spt = i - entries + 1; + mic_addr = mic_smpt_to_pa(mdev, spt); + mic_add_smpt_entry(spt, ref, dma_addr, entries, mdev); + smpt_info->map_count++; + smpt_info->ref_count += (s64)size; + spin_unlock_irqrestore(&smpt_info->smpt_lock, flags); + return mic_addr; +} + +/* + * Returns number of smpt entries needed for dma_addr to dma_addr + size + * also returns the reference count array for each of those entries + * and the starting smpt address + */ +static int mic_get_smpt_ref_count(struct mic_device *mdev, dma_addr_t dma_addr, + size_t size, s64 *ref, u64 *smpt_start) +{ + u64 start = dma_addr; + u64 end = dma_addr + size; + int i = 0; + + while (start < end) { + ref[i++] = min(mic_smpt_align_high(mdev, start + 1), + end) - start; + start = mic_smpt_align_high(mdev, start + 1); + } + + if (smpt_start) + *smpt_start = mic_smpt_align_low(mdev, dma_addr); + + return i; +} + +/* + * mic_to_dma_addr - Converts a MIC address to a DMA address. + * + * @mdev: pointer to mic_device instance. + * @mic_addr: MIC address. + * + * returns a DMA address. + */ +static dma_addr_t +mic_to_dma_addr(struct mic_device *mdev, dma_addr_t mic_addr) +{ + struct mic_smpt_info *smpt_info = mdev->smpt; + int spt; + dma_addr_t dma_addr; + + if (!mic_is_system_addr(mdev, mic_addr)) { + dev_err(mdev->sdev->parent, + "mic_addr is invalid. mic_addr = 0x%llx\n", mic_addr); + return -EINVAL; + } + spt = mic_sys_addr_to_smpt(mdev, mic_addr); + dma_addr = smpt_info->entry[spt].dma_addr + + mic_smpt_offset(mdev, mic_addr); + return dma_addr; +} + +/** + * mic_map - Maps a DMA address to a MIC physical address. + * + * @mdev: pointer to mic_device instance. + * @dma_addr: DMA address. + * @size: Size of the region to be mapped. + * + * This API converts the DMA address provided to a DMA address understood + * by MIC. Caller should check for errors by calling mic_map_error(..). + * + * returns DMA address as required by MIC. + */ +dma_addr_t mic_map(struct mic_device *mdev, dma_addr_t dma_addr, size_t size) +{ + dma_addr_t mic_addr = 0; + int num_entries; + s64 *ref; + u64 smpt_start; + + if (!size || size > mic_max_system_memory(mdev)) + return mic_addr; + + ref = kmalloc(mdev->smpt->info.num_reg * sizeof(s64), GFP_KERNEL); + if (!ref) + return mic_addr; + + num_entries = mic_get_smpt_ref_count(mdev, dma_addr, size, + ref, &smpt_start); + + /* Set the smpt table appropriately and get 16G aligned mic address */ + mic_addr = mic_smpt_op(mdev, smpt_start, num_entries, ref, size); + + kfree(ref); + + /* + * If mic_addr is zero then its an error case + * since mic_addr can never be zero. + * else generate mic_addr by adding the 16G offset in dma_addr + */ + if (!mic_addr && MIC_FAMILY_X100 == mdev->family) { + dev_err(mdev->sdev->parent, + "mic_map failed dma_addr 0x%llx size 0x%lx\n", + dma_addr, size); + return mic_addr; + } else { + return mic_addr + mic_smpt_offset(mdev, dma_addr); + } +} + +/** + * mic_unmap - Unmaps a MIC physical address. + * + * @mdev: pointer to mic_device instance. + * @mic_addr: MIC physical address. + * @size: Size of the region to be unmapped. + * + * This API unmaps the mappings created by mic_map(..). + * + * returns None. + */ +void mic_unmap(struct mic_device *mdev, dma_addr_t mic_addr, size_t size) +{ + struct mic_smpt_info *smpt_info = mdev->smpt; + s64 *ref; + int num_smpt; + int spt; + int i; + unsigned long flags; + + if (!size) + return; + + if (!mic_is_system_addr(mdev, mic_addr)) { + dev_err(mdev->sdev->parent, + "invalid address: 0x%llx\n", mic_addr); + return; + } + + spt = mic_sys_addr_to_smpt(mdev, mic_addr); + ref = kmalloc(mdev->smpt->info.num_reg * sizeof(s64), GFP_KERNEL); + if (!ref) + return; + + /* Get number of smpt entries to be mapped, ref count array */ + num_smpt = mic_get_smpt_ref_count(mdev, mic_addr, size, ref, NULL); + + spin_lock_irqsave(&smpt_info->smpt_lock, flags); + smpt_info->unmap_count++; + smpt_info->ref_count -= (s64)size; + + for (i = spt; i < spt + num_smpt; i++) { + smpt_info->entry[i].ref_count -= ref[i - spt]; + if (smpt_info->entry[i].ref_count < 0) + dev_warn(mdev->sdev->parent, + "ref count for entry %d is negative\n", i); + } + spin_unlock_irqrestore(&smpt_info->smpt_lock, flags); + kfree(ref); +} + +/** + * mic_map_single - Maps a virtual address to a MIC physical address. + * + * @mdev: pointer to mic_device instance. + * @va: Kernel direct mapped virtual address. + * @size: Size of the region to be mapped. + * + * This API calls pci_map_single(..) for the direct mapped virtual address + * and then converts the DMA address provided to a DMA address understood + * by MIC. Caller should check for errors by calling mic_map_error(..). + * + * returns DMA address as required by MIC. + */ +dma_addr_t mic_map_single(struct mic_device *mdev, void *va, size_t size) +{ + dma_addr_t mic_addr = 0; + struct pci_dev *pdev = container_of(mdev->sdev->parent, + struct pci_dev, dev); + dma_addr_t dma_addr = + pci_map_single(pdev, va, size, PCI_DMA_BIDIRECTIONAL); + + if (!pci_dma_mapping_error(pdev, dma_addr)) { + mic_addr = mic_map(mdev, dma_addr, size); + if (!mic_addr) { + dev_err(mdev->sdev->parent, + "mic_map failed dma_addr 0x%llx size 0x%lx\n", + dma_addr, size); + pci_unmap_single(pdev, dma_addr, + size, PCI_DMA_BIDIRECTIONAL); + } + } + return mic_addr; +} + +/** + * mic_unmap_single - Unmaps a MIC physical address. + * + * @mdev: pointer to mic_device instance. + * @mic_addr: MIC physical address. + * @size: Size of the region to be unmapped. + * + * This API unmaps the mappings created by mic_map_single(..). + * + * returns None. + */ +void +mic_unmap_single(struct mic_device *mdev, dma_addr_t mic_addr, size_t size) +{ + struct pci_dev *pdev = container_of(mdev->sdev->parent, + struct pci_dev, dev); + dma_addr_t dma_addr = mic_to_dma_addr(mdev, mic_addr); + mic_unmap(mdev, mic_addr, size); + pci_unmap_single(pdev, dma_addr, size, PCI_DMA_BIDIRECTIONAL); +} + +/** + * mic_smpt_init - Initialize MIC System Memory Page Tables. + * + * @mdev: pointer to mic_device instance. + * + * returns 0 for success and -errno for error. + */ +int mic_smpt_init(struct mic_device *mdev) +{ + int i, err = 0; + dma_addr_t dma_addr; + struct mic_smpt_info *smpt_info; + + mdev->smpt = kmalloc(sizeof(*mdev->smpt), GFP_KERNEL); + if (!mdev->smpt) + return -ENOMEM; + + smpt_info = mdev->smpt; + mdev->smpt_ops->init(mdev); + smpt_info->entry = kmalloc_array(smpt_info->info.num_reg, + sizeof(*smpt_info->entry), GFP_KERNEL); + if (!smpt_info->entry) { + err = -ENOMEM; + goto free_smpt; + } + spin_lock_init(&smpt_info->smpt_lock); + for (i = 0; i < smpt_info->info.num_reg; i++) { + dma_addr = i * smpt_info->info.page_size; + smpt_info->entry[i].dma_addr = dma_addr; + smpt_info->entry[i].ref_count = 0; + mdev->smpt_ops->set(mdev, dma_addr, i); + } + smpt_info->ref_count = 0; + smpt_info->map_count = 0; + smpt_info->unmap_count = 0; + return 0; +free_smpt: + kfree(smpt_info); + return err; +} + +/** + * mic_smpt_uninit - UnInitialize MIC System Memory Page Tables. + * + * @mdev: pointer to mic_device instance. + * + * returns None. + */ +void mic_smpt_uninit(struct mic_device *mdev) +{ + struct mic_smpt_info *smpt_info = mdev->smpt; + int i; + + dev_dbg(mdev->sdev->parent, + "nodeid %d SMPT ref count %lld map %lld unmap %lld\n", + mdev->id, smpt_info->ref_count, + smpt_info->map_count, smpt_info->unmap_count); + + for (i = 0; i < smpt_info->info.num_reg; i++) { + dev_dbg(mdev->sdev->parent, + "SMPT entry[%d] dma_addr = 0x%llx ref_count = %lld\n", + i, smpt_info->entry[i].dma_addr, + smpt_info->entry[i].ref_count); + if (smpt_info->entry[i].ref_count) + dev_warn(mdev->sdev->parent, + "ref count for entry %d is not zero\n", i); + } + kfree(smpt_info->entry); + kfree(smpt_info); +} + +/** + * mic_smpt_restore - Restore MIC System Memory Page Tables. + * + * @mdev: pointer to mic_device instance. + * + * Restore the SMPT registers to values previously stored in the + * SW data structures. Some MIC steppings lose register state + * across resets and this API should be called for performing + * a restore operation if required. + * + * returns None. + */ +void mic_smpt_restore(struct mic_device *mdev) +{ + int i; + dma_addr_t dma_addr; + + for (i = 0; i < mdev->smpt->info.num_reg; i++) { + dma_addr = mdev->smpt->entry[i].dma_addr; + mdev->smpt_ops->set(mdev, dma_addr, i); + } +} diff --git a/drivers/misc/mic/host/mic_smpt.h b/drivers/misc/mic/host/mic_smpt.h new file mode 100644 index 000000000000..51970abfe7df --- /dev/null +++ b/drivers/misc/mic/host/mic_smpt.h @@ -0,0 +1,98 @@ +/* + * Intel MIC Platform Software Stack (MPSS) + * + * Copyright(c) 2013 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Intel MIC Host driver. + * + */ +#ifndef MIC_SMPT_H +#define MIC_SMPT_H +/** + * struct mic_smpt_ops - MIC HW specific SMPT operations. + * @init: Initialize hardware specific SMPT information in mic_smpt_hw_info. + * @set: Set the value for a particular SMPT entry. + */ +struct mic_smpt_ops { + void (*init)(struct mic_device *mdev); + void (*set)(struct mic_device *mdev, dma_addr_t dma_addr, u8 index); +}; + +/** + * struct mic_smpt - MIC SMPT entry information. + * @dma_addr: Base DMA address for this SMPT entry. + * @ref_count: Number of active mappings for this SMPT entry in bytes. + */ +struct mic_smpt { + dma_addr_t dma_addr; + s64 ref_count; +}; + +/** + * struct mic_smpt_hw_info - MIC SMPT hardware specific information. + * @num_reg: Number of SMPT registers. + * @page_shift: System memory page shift. + * @page_size: System memory page size. + * @base: System address base. + */ +struct mic_smpt_hw_info { + u8 num_reg; + u8 page_shift; + u64 page_size; + u64 base; +}; + +/** + * struct mic_smpt_info - MIC SMPT information. + * @entry: Array of SMPT entries. + * @smpt_lock: Spin lock protecting access to SMPT data structures. + * @info: Hardware specific SMPT information. + * @ref_count: Number of active SMPT mappings (for debug). + * @map_count: Number of SMPT mappings created (for debug). + * @unmap_count: Number of SMPT mappings destroyed (for debug). + */ +struct mic_smpt_info { + struct mic_smpt *entry; + spinlock_t smpt_lock; + struct mic_smpt_hw_info info; + s64 ref_count; + s64 map_count; + s64 unmap_count; +}; + +dma_addr_t mic_map_single(struct mic_device *mdev, void *va, size_t size); +void mic_unmap_single(struct mic_device *mdev, + dma_addr_t mic_addr, size_t size); +dma_addr_t mic_map(struct mic_device *mdev, + dma_addr_t dma_addr, size_t size); +void mic_unmap(struct mic_device *mdev, dma_addr_t mic_addr, size_t size); + +/** + * mic_map_error - Check a MIC address for errors. + * + * @mdev: pointer to mic_device instance. + * + * returns Whether there was an error during mic_map..(..) APIs. + */ +static inline bool mic_map_error(dma_addr_t mic_addr) +{ + return !mic_addr; +} + +int mic_smpt_init(struct mic_device *mdev); +void mic_smpt_uninit(struct mic_device *mdev); +void mic_smpt_restore(struct mic_device *mdev); + +#endif diff --git a/drivers/misc/mic/host/mic_sysfs.c b/drivers/misc/mic/host/mic_sysfs.c new file mode 100644 index 000000000000..6dd864e4a617 --- /dev/null +++ b/drivers/misc/mic/host/mic_sysfs.c @@ -0,0 +1,459 @@ +/* + * Intel MIC Platform Software Stack (MPSS) + * + * Copyright(c) 2013 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Intel MIC Host driver. + * + */ +#include <linux/pci.h> + +#include <linux/mic_common.h> +#include "../common/mic_dev.h" +#include "mic_device.h" + +/* + * A state-to-string lookup table, for exposing a human readable state + * via sysfs. Always keep in sync with enum mic_states + */ +static const char * const mic_state_string[] = { + [MIC_OFFLINE] = "offline", + [MIC_ONLINE] = "online", + [MIC_SHUTTING_DOWN] = "shutting_down", + [MIC_RESET_FAILED] = "reset_failed", + [MIC_SUSPENDING] = "suspending", + [MIC_SUSPENDED] = "suspended", +}; + +/* + * A shutdown-status-to-string lookup table, for exposing a human + * readable state via sysfs. Always keep in sync with enum mic_shutdown_status + */ +static const char * const mic_shutdown_status_string[] = { + [MIC_NOP] = "nop", + [MIC_CRASHED] = "crashed", + [MIC_HALTED] = "halted", + [MIC_POWER_OFF] = "poweroff", + [MIC_RESTART] = "restart", +}; + +void mic_set_shutdown_status(struct mic_device *mdev, u8 shutdown_status) +{ + dev_dbg(mdev->sdev->parent, "Shutdown Status %s -> %s\n", + mic_shutdown_status_string[mdev->shutdown_status], + mic_shutdown_status_string[shutdown_status]); + mdev->shutdown_status = shutdown_status; +} + +void mic_set_state(struct mic_device *mdev, u8 state) +{ + dev_dbg(mdev->sdev->parent, "State %s -> %s\n", + mic_state_string[mdev->state], + mic_state_string[state]); + mdev->state = state; + sysfs_notify_dirent(mdev->state_sysfs); +} + +static ssize_t +family_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + static const char x100[] = "x100"; + static const char unknown[] = "Unknown"; + const char *card = NULL; + struct mic_device *mdev = dev_get_drvdata(dev->parent); + + if (!mdev) + return -EINVAL; + + switch (mdev->family) { + case MIC_FAMILY_X100: + card = x100; + break; + default: + card = unknown; + break; + } + return scnprintf(buf, PAGE_SIZE, "%s\n", card); +} +static DEVICE_ATTR_RO(family); + +static ssize_t +stepping_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct mic_device *mdev = dev_get_drvdata(dev->parent); + char *string = "??"; + + if (!mdev) + return -EINVAL; + + switch (mdev->stepping) { + case MIC_A0_STEP: + string = "A0"; + break; + case MIC_B0_STEP: + string = "B0"; + break; + case MIC_B1_STEP: + string = "B1"; + break; + case MIC_C0_STEP: + string = "C0"; + break; + default: + break; + } + return scnprintf(buf, PAGE_SIZE, "%s\n", string); +} +static DEVICE_ATTR_RO(stepping); + +static ssize_t +state_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct mic_device *mdev = dev_get_drvdata(dev->parent); + + if (!mdev || mdev->state >= MIC_LAST) + return -EINVAL; + + return scnprintf(buf, PAGE_SIZE, "%s\n", + mic_state_string[mdev->state]); +} + +static ssize_t +state_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + int rc = 0; + struct mic_device *mdev = dev_get_drvdata(dev->parent); + if (!mdev) + return -EINVAL; + if (sysfs_streq(buf, "boot")) { + rc = mic_start(mdev, buf); + if (rc) { + dev_err(mdev->sdev->parent, + "mic_boot failed rc %d\n", rc); + count = rc; + } + goto done; + } + + if (sysfs_streq(buf, "reset")) { + schedule_work(&mdev->reset_trigger_work); + goto done; + } + + if (sysfs_streq(buf, "shutdown")) { + mic_shutdown(mdev); + goto done; + } + + if (sysfs_streq(buf, "suspend")) { + mic_suspend(mdev); + goto done; + } + + count = -EINVAL; +done: + return count; +} +static DEVICE_ATTR_RW(state); + +static ssize_t shutdown_status_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct mic_device *mdev = dev_get_drvdata(dev->parent); + + if (!mdev || mdev->shutdown_status >= MIC_STATUS_LAST) + return -EINVAL; + + return scnprintf(buf, PAGE_SIZE, "%s\n", + mic_shutdown_status_string[mdev->shutdown_status]); +} +static DEVICE_ATTR_RO(shutdown_status); + +static ssize_t +cmdline_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct mic_device *mdev = dev_get_drvdata(dev->parent); + char *cmdline; + + if (!mdev) + return -EINVAL; + + cmdline = mdev->cmdline; + + if (cmdline) + return scnprintf(buf, PAGE_SIZE, "%s\n", cmdline); + return 0; +} + +static ssize_t +cmdline_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct mic_device *mdev = dev_get_drvdata(dev->parent); + + if (!mdev) + return -EINVAL; + + mutex_lock(&mdev->mic_mutex); + kfree(mdev->cmdline); + + mdev->cmdline = kmalloc(count + 1, GFP_KERNEL); + if (!mdev->cmdline) { + count = -ENOMEM; + goto unlock; + } + + strncpy(mdev->cmdline, buf, count); + + if (mdev->cmdline[count - 1] == '\n') + mdev->cmdline[count - 1] = '\0'; + else + mdev->cmdline[count] = '\0'; +unlock: + mutex_unlock(&mdev->mic_mutex); + return count; +} +static DEVICE_ATTR_RW(cmdline); + +static ssize_t +firmware_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct mic_device *mdev = dev_get_drvdata(dev->parent); + char *firmware; + + if (!mdev) + return -EINVAL; + + firmware = mdev->firmware; + + if (firmware) + return scnprintf(buf, PAGE_SIZE, "%s\n", firmware); + return 0; +} + +static ssize_t +firmware_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct mic_device *mdev = dev_get_drvdata(dev->parent); + + if (!mdev) + return -EINVAL; + + mutex_lock(&mdev->mic_mutex); + kfree(mdev->firmware); + + mdev->firmware = kmalloc(count + 1, GFP_KERNEL); + if (!mdev->firmware) { + count = -ENOMEM; + goto unlock; + } + strncpy(mdev->firmware, buf, count); + + if (mdev->firmware[count - 1] == '\n') + mdev->firmware[count - 1] = '\0'; + else + mdev->firmware[count] = '\0'; +unlock: + mutex_unlock(&mdev->mic_mutex); + return count; +} +static DEVICE_ATTR_RW(firmware); + +static ssize_t +ramdisk_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct mic_device *mdev = dev_get_drvdata(dev->parent); + char *ramdisk; + + if (!mdev) + return -EINVAL; + + ramdisk = mdev->ramdisk; + + if (ramdisk) + return scnprintf(buf, PAGE_SIZE, "%s\n", ramdisk); + return 0; +} + +static ssize_t +ramdisk_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct mic_device *mdev = dev_get_drvdata(dev->parent); + + if (!mdev) + return -EINVAL; + + mutex_lock(&mdev->mic_mutex); + kfree(mdev->ramdisk); + + mdev->ramdisk = kmalloc(count + 1, GFP_KERNEL); + if (!mdev->ramdisk) { + count = -ENOMEM; + goto unlock; + } + + strncpy(mdev->ramdisk, buf, count); + + if (mdev->ramdisk[count - 1] == '\n') + mdev->ramdisk[count - 1] = '\0'; + else + mdev->ramdisk[count] = '\0'; +unlock: + mutex_unlock(&mdev->mic_mutex); + return count; +} +static DEVICE_ATTR_RW(ramdisk); + +static ssize_t +bootmode_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct mic_device *mdev = dev_get_drvdata(dev->parent); + char *bootmode; + + if (!mdev) + return -EINVAL; + + bootmode = mdev->bootmode; + + if (bootmode) + return scnprintf(buf, PAGE_SIZE, "%s\n", bootmode); + return 0; +} + +static ssize_t +bootmode_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct mic_device *mdev = dev_get_drvdata(dev->parent); + + if (!mdev) + return -EINVAL; + + if (!sysfs_streq(buf, "linux") && !sysfs_streq(buf, "elf")) + return -EINVAL; + + mutex_lock(&mdev->mic_mutex); + kfree(mdev->bootmode); + + mdev->bootmode = kmalloc(count + 1, GFP_KERNEL); + if (!mdev->bootmode) { + count = -ENOMEM; + goto unlock; + } + + strncpy(mdev->bootmode, buf, count); + + if (mdev->bootmode[count - 1] == '\n') + mdev->bootmode[count - 1] = '\0'; + else + mdev->bootmode[count] = '\0'; +unlock: + mutex_unlock(&mdev->mic_mutex); + return count; +} +static DEVICE_ATTR_RW(bootmode); + +static ssize_t +log_buf_addr_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct mic_device *mdev = dev_get_drvdata(dev->parent); + + if (!mdev) + return -EINVAL; + + return scnprintf(buf, PAGE_SIZE, "%p\n", mdev->log_buf_addr); +} + +static ssize_t +log_buf_addr_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct mic_device *mdev = dev_get_drvdata(dev->parent); + int ret; + unsigned long addr; + + if (!mdev) + return -EINVAL; + + ret = kstrtoul(buf, 16, &addr); + if (ret) + goto exit; + + mdev->log_buf_addr = (void *)addr; + ret = count; +exit: + return ret; +} +static DEVICE_ATTR_RW(log_buf_addr); + +static ssize_t +log_buf_len_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct mic_device *mdev = dev_get_drvdata(dev->parent); + + if (!mdev) + return -EINVAL; + + return scnprintf(buf, PAGE_SIZE, "%p\n", mdev->log_buf_len); +} + +static ssize_t +log_buf_len_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct mic_device *mdev = dev_get_drvdata(dev->parent); + int ret; + unsigned long addr; + + if (!mdev) + return -EINVAL; + + ret = kstrtoul(buf, 16, &addr); + if (ret) + goto exit; + + mdev->log_buf_len = (int *)addr; + ret = count; +exit: + return ret; +} +static DEVICE_ATTR_RW(log_buf_len); + +static struct attribute *mic_default_attrs[] = { + &dev_attr_family.attr, + &dev_attr_stepping.attr, + &dev_attr_state.attr, + &dev_attr_shutdown_status.attr, + &dev_attr_cmdline.attr, + &dev_attr_firmware.attr, + &dev_attr_ramdisk.attr, + &dev_attr_bootmode.attr, + &dev_attr_log_buf_addr.attr, + &dev_attr_log_buf_len.attr, + + NULL +}; + +ATTRIBUTE_GROUPS(mic_default); + +void mic_sysfs_init(struct mic_device *mdev) +{ + mdev->attr_group = mic_default_groups; +} diff --git a/drivers/misc/mic/host/mic_virtio.c b/drivers/misc/mic/host/mic_virtio.c new file mode 100644 index 000000000000..752ff873f891 --- /dev/null +++ b/drivers/misc/mic/host/mic_virtio.c @@ -0,0 +1,700 @@ +/* + * Intel MIC Platform Software Stack (MPSS) + * + * Copyright(c) 2013 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Intel MIC Host driver. + * + */ +#include <linux/pci.h> +#include <linux/sched.h> +#include <linux/uaccess.h> + +#include <linux/mic_common.h> +#include "../common/mic_dev.h" +#include "mic_device.h" +#include "mic_smpt.h" +#include "mic_virtio.h" + +/* + * Initiates the copies across the PCIe bus from card memory to + * a user space buffer. + */ +static int mic_virtio_copy_to_user(struct mic_vdev *mvdev, + void __user *ubuf, size_t len, u64 addr) +{ + int err; + void __iomem *dbuf = mvdev->mdev->aper.va + addr; + /* + * We are copying from IO below an should ideally use something + * like copy_to_user_fromio(..) if it existed. + */ + if (copy_to_user(ubuf, (void __force *)dbuf, len)) { + err = -EFAULT; + dev_err(mic_dev(mvdev), "%s %d err %d\n", + __func__, __LINE__, err); + goto err; + } + mvdev->in_bytes += len; + err = 0; +err: + return err; +} + +/* + * Initiates copies across the PCIe bus from a user space + * buffer to card memory. + */ +static int mic_virtio_copy_from_user(struct mic_vdev *mvdev, + void __user *ubuf, size_t len, u64 addr) +{ + int err; + void __iomem *dbuf = mvdev->mdev->aper.va + addr; + /* + * We are copying to IO below and should ideally use something + * like copy_from_user_toio(..) if it existed. + */ + if (copy_from_user((void __force *)dbuf, ubuf, len)) { + err = -EFAULT; + dev_err(mic_dev(mvdev), "%s %d err %d\n", + __func__, __LINE__, err); + goto err; + } + mvdev->out_bytes += len; + err = 0; +err: + return err; +} + +#define MIC_VRINGH_READ true + +/* The function to call to notify the card about added buffers */ +static void mic_notify(struct vringh *vrh) +{ + struct mic_vringh *mvrh = container_of(vrh, struct mic_vringh, vrh); + struct mic_vdev *mvdev = mvrh->mvdev; + s8 db = mvdev->dc->h2c_vdev_db; + + if (db != -1) + mvdev->mdev->ops->send_intr(mvdev->mdev, db); +} + +/* Determine the total number of bytes consumed in a VRINGH KIOV */ +static inline u32 mic_vringh_iov_consumed(struct vringh_kiov *iov) +{ + int i; + u32 total = iov->consumed; + + for (i = 0; i < iov->i; i++) + total += iov->iov[i].iov_len; + return total; +} + +/* + * Traverse the VRINGH KIOV and issue the APIs to trigger the copies. + * This API is heavily based on the vringh_iov_xfer(..) implementation + * in vringh.c. The reason we cannot reuse vringh_iov_pull_kern(..) + * and vringh_iov_push_kern(..) directly is because there is no + * way to override the VRINGH xfer(..) routines as of v3.10. + */ +static int mic_vringh_copy(struct mic_vdev *mvdev, struct vringh_kiov *iov, + void __user *ubuf, size_t len, bool read, size_t *out_len) +{ + int ret = 0; + size_t partlen, tot_len = 0; + + while (len && iov->i < iov->used) { + partlen = min(iov->iov[iov->i].iov_len, len); + if (read) + ret = mic_virtio_copy_to_user(mvdev, + ubuf, partlen, + (u64)iov->iov[iov->i].iov_base); + else + ret = mic_virtio_copy_from_user(mvdev, + ubuf, partlen, + (u64)iov->iov[iov->i].iov_base); + if (ret) { + dev_err(mic_dev(mvdev), "%s %d err %d\n", + __func__, __LINE__, ret); + break; + } + len -= partlen; + ubuf += partlen; + tot_len += partlen; + iov->consumed += partlen; + iov->iov[iov->i].iov_len -= partlen; + iov->iov[iov->i].iov_base += partlen; + if (!iov->iov[iov->i].iov_len) { + /* Fix up old iov element then increment. */ + iov->iov[iov->i].iov_len = iov->consumed; + iov->iov[iov->i].iov_base -= iov->consumed; + + iov->consumed = 0; + iov->i++; + } + } + *out_len = tot_len; + return ret; +} + +/* + * Use the standard VRINGH infrastructure in the kernel to fetch new + * descriptors, initiate the copies and update the used ring. + */ +static int _mic_virtio_copy(struct mic_vdev *mvdev, + struct mic_copy_desc *copy) +{ + int ret = 0, iovcnt = copy->iovcnt; + struct iovec iov; + struct iovec __user *u_iov = copy->iov; + void __user *ubuf = NULL; + struct mic_vringh *mvr = &mvdev->mvr[copy->vr_idx]; + struct vringh_kiov *riov = &mvr->riov; + struct vringh_kiov *wiov = &mvr->wiov; + struct vringh *vrh = &mvr->vrh; + u16 *head = &mvr->head; + struct mic_vring *vr = &mvr->vring; + size_t len = 0, out_len; + + copy->out_len = 0; + /* Fetch a new IOVEC if all previous elements have been processed */ + if (riov->i == riov->used && wiov->i == wiov->used) { + ret = vringh_getdesc_kern(vrh, riov, wiov, + head, GFP_KERNEL); + /* Check if there are available descriptors */ + if (ret <= 0) + return ret; + } + while (iovcnt) { + if (!len) { + /* Copy over a new iovec from user space. */ + ret = copy_from_user(&iov, u_iov, sizeof(*u_iov)); + if (ret) { + ret = -EINVAL; + dev_err(mic_dev(mvdev), "%s %d err %d\n", + __func__, __LINE__, ret); + break; + } + len = iov.iov_len; + ubuf = iov.iov_base; + } + /* Issue all the read descriptors first */ + ret = mic_vringh_copy(mvdev, riov, ubuf, len, + MIC_VRINGH_READ, &out_len); + if (ret) { + dev_err(mic_dev(mvdev), "%s %d err %d\n", + __func__, __LINE__, ret); + break; + } + len -= out_len; + ubuf += out_len; + copy->out_len += out_len; + /* Issue the write descriptors next */ + ret = mic_vringh_copy(mvdev, wiov, ubuf, len, + !MIC_VRINGH_READ, &out_len); + if (ret) { + dev_err(mic_dev(mvdev), "%s %d err %d\n", + __func__, __LINE__, ret); + break; + } + len -= out_len; + ubuf += out_len; + copy->out_len += out_len; + if (!len) { + /* One user space iovec is now completed */ + iovcnt--; + u_iov++; + } + /* Exit loop if all elements in KIOVs have been processed. */ + if (riov->i == riov->used && wiov->i == wiov->used) + break; + } + /* + * Update the used ring if a descriptor was available and some data was + * copied in/out and the user asked for a used ring update. + */ + if (*head != USHRT_MAX && copy->out_len && copy->update_used) { + u32 total = 0; + + /* Determine the total data consumed */ + total += mic_vringh_iov_consumed(riov); + total += mic_vringh_iov_consumed(wiov); + vringh_complete_kern(vrh, *head, total); + *head = USHRT_MAX; + if (vringh_need_notify_kern(vrh) > 0) + vringh_notify(vrh); + vringh_kiov_cleanup(riov); + vringh_kiov_cleanup(wiov); + /* Update avail idx for user space */ + vr->info->avail_idx = vrh->last_avail_idx; + } + return ret; +} + +static inline int mic_verify_copy_args(struct mic_vdev *mvdev, + struct mic_copy_desc *copy) +{ + if (copy->vr_idx >= mvdev->dd->num_vq) { + dev_err(mic_dev(mvdev), "%s %d err %d\n", + __func__, __LINE__, -EINVAL); + return -EINVAL; + } + return 0; +} + +/* Copy a specified number of virtio descriptors in a chain */ +int mic_virtio_copy_desc(struct mic_vdev *mvdev, + struct mic_copy_desc *copy) +{ + int err; + struct mic_vringh *mvr = &mvdev->mvr[copy->vr_idx]; + + err = mic_verify_copy_args(mvdev, copy); + if (err) + return err; + + mutex_lock(&mvr->vr_mutex); + if (!mic_vdevup(mvdev)) { + err = -ENODEV; + dev_err(mic_dev(mvdev), "%s %d err %d\n", + __func__, __LINE__, err); + goto err; + } + err = _mic_virtio_copy(mvdev, copy); + if (err) { + dev_err(mic_dev(mvdev), "%s %d err %d\n", + __func__, __LINE__, err); + } +err: + mutex_unlock(&mvr->vr_mutex); + return err; +} + +static void mic_virtio_init_post(struct mic_vdev *mvdev) +{ + struct mic_vqconfig *vqconfig = mic_vq_config(mvdev->dd); + int i; + + for (i = 0; i < mvdev->dd->num_vq; i++) { + if (!le64_to_cpu(vqconfig[i].used_address)) { + dev_warn(mic_dev(mvdev), "used_address zero??\n"); + continue; + } + mvdev->mvr[i].vrh.vring.used = + (void __force *)mvdev->mdev->aper.va + + le64_to_cpu(vqconfig[i].used_address); + } + + mvdev->dc->used_address_updated = 0; + + dev_dbg(mic_dev(mvdev), "%s: device type %d LINKUP\n", + __func__, mvdev->virtio_id); +} + +static inline void mic_virtio_device_reset(struct mic_vdev *mvdev) +{ + int i; + + dev_dbg(mic_dev(mvdev), "%s: status %d device type %d RESET\n", + __func__, mvdev->dd->status, mvdev->virtio_id); + + for (i = 0; i < mvdev->dd->num_vq; i++) + /* + * Avoid lockdep false positive. The + 1 is for the mic + * mutex which is held in the reset devices code path. + */ + mutex_lock_nested(&mvdev->mvr[i].vr_mutex, i + 1); + + /* 0 status means "reset" */ + mvdev->dd->status = 0; + mvdev->dc->vdev_reset = 0; + mvdev->dc->host_ack = 1; + + for (i = 0; i < mvdev->dd->num_vq; i++) { + struct vringh *vrh = &mvdev->mvr[i].vrh; + mvdev->mvr[i].vring.info->avail_idx = 0; + vrh->completed = 0; + vrh->last_avail_idx = 0; + vrh->last_used_idx = 0; + } + + for (i = 0; i < mvdev->dd->num_vq; i++) + mutex_unlock(&mvdev->mvr[i].vr_mutex); +} + +void mic_virtio_reset_devices(struct mic_device *mdev) +{ + struct list_head *pos, *tmp; + struct mic_vdev *mvdev; + + dev_dbg(mdev->sdev->parent, "%s\n", __func__); + + list_for_each_safe(pos, tmp, &mdev->vdev_list) { + mvdev = list_entry(pos, struct mic_vdev, list); + mic_virtio_device_reset(mvdev); + mvdev->poll_wake = 1; + wake_up(&mvdev->waitq); + } +} + +void mic_bh_handler(struct work_struct *work) +{ + struct mic_vdev *mvdev = container_of(work, struct mic_vdev, + virtio_bh_work); + + if (mvdev->dc->used_address_updated) + mic_virtio_init_post(mvdev); + + if (mvdev->dc->vdev_reset) + mic_virtio_device_reset(mvdev); + + mvdev->poll_wake = 1; + wake_up(&mvdev->waitq); +} + +static irqreturn_t mic_virtio_intr_handler(int irq, void *data) +{ + struct mic_vdev *mvdev = data; + struct mic_device *mdev = mvdev->mdev; + + mdev->ops->intr_workarounds(mdev); + schedule_work(&mvdev->virtio_bh_work); + return IRQ_HANDLED; +} + +int mic_virtio_config_change(struct mic_vdev *mvdev, + void __user *argp) +{ + DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wake); + int ret = 0, retry, i; + struct mic_bootparam *bootparam = mvdev->mdev->dp; + s8 db = bootparam->h2c_config_db; + + mutex_lock(&mvdev->mdev->mic_mutex); + for (i = 0; i < mvdev->dd->num_vq; i++) + mutex_lock_nested(&mvdev->mvr[i].vr_mutex, i + 1); + + if (db == -1 || mvdev->dd->type == -1) { + ret = -EIO; + goto exit; + } + + if (copy_from_user(mic_vq_configspace(mvdev->dd), + argp, mvdev->dd->config_len)) { + dev_err(mic_dev(mvdev), "%s %d err %d\n", + __func__, __LINE__, -EFAULT); + ret = -EFAULT; + goto exit; + } + mvdev->dc->config_change = MIC_VIRTIO_PARAM_CONFIG_CHANGED; + mvdev->mdev->ops->send_intr(mvdev->mdev, db); + + for (retry = 100; retry--;) { + ret = wait_event_timeout(wake, + mvdev->dc->guest_ack, msecs_to_jiffies(100)); + if (ret) + break; + } + + dev_dbg(mic_dev(mvdev), + "%s %d retry: %d\n", __func__, __LINE__, retry); + mvdev->dc->config_change = 0; + mvdev->dc->guest_ack = 0; +exit: + for (i = 0; i < mvdev->dd->num_vq; i++) + mutex_unlock(&mvdev->mvr[i].vr_mutex); + mutex_unlock(&mvdev->mdev->mic_mutex); + return ret; +} + +static int mic_copy_dp_entry(struct mic_vdev *mvdev, + void __user *argp, + __u8 *type, + struct mic_device_desc **devpage) +{ + struct mic_device *mdev = mvdev->mdev; + struct mic_device_desc dd, *dd_config, *devp; + struct mic_vqconfig *vqconfig; + int ret = 0, i; + bool slot_found = false; + + if (copy_from_user(&dd, argp, sizeof(dd))) { + dev_err(mic_dev(mvdev), "%s %d err %d\n", + __func__, __LINE__, -EFAULT); + return -EFAULT; + } + + if (mic_aligned_desc_size(&dd) > MIC_MAX_DESC_BLK_SIZE || + dd.num_vq > MIC_MAX_VRINGS) { + dev_err(mic_dev(mvdev), "%s %d err %d\n", + __func__, __LINE__, -EINVAL); + return -EINVAL; + } + + dd_config = kmalloc(mic_desc_size(&dd), GFP_KERNEL); + if (dd_config == NULL) { + dev_err(mic_dev(mvdev), "%s %d err %d\n", + __func__, __LINE__, -ENOMEM); + return -ENOMEM; + } + if (copy_from_user(dd_config, argp, mic_desc_size(&dd))) { + ret = -EFAULT; + dev_err(mic_dev(mvdev), "%s %d err %d\n", + __func__, __LINE__, ret); + goto exit; + } + + vqconfig = mic_vq_config(dd_config); + for (i = 0; i < dd.num_vq; i++) { + if (le16_to_cpu(vqconfig[i].num) > MIC_MAX_VRING_ENTRIES) { + ret = -EINVAL; + dev_err(mic_dev(mvdev), "%s %d err %d\n", + __func__, __LINE__, ret); + goto exit; + } + } + + /* Find the first free device page entry */ + for (i = sizeof(struct mic_bootparam); + i < MIC_DP_SIZE - mic_total_desc_size(dd_config); + i += mic_total_desc_size(devp)) { + devp = mdev->dp + i; + if (devp->type == 0 || devp->type == -1) { + slot_found = true; + break; + } + } + if (!slot_found) { + ret = -EINVAL; + dev_err(mic_dev(mvdev), "%s %d err %d\n", + __func__, __LINE__, ret); + goto exit; + } + /* + * Save off the type before doing the memcpy. Type will be set in the + * end after completing all initialization for the new device. + */ + *type = dd_config->type; + dd_config->type = 0; + memcpy(devp, dd_config, mic_desc_size(dd_config)); + + *devpage = devp; +exit: + kfree(dd_config); + return ret; +} + +static void mic_init_device_ctrl(struct mic_vdev *mvdev, + struct mic_device_desc *devpage) +{ + struct mic_device_ctrl *dc; + + dc = (void *)devpage + mic_aligned_desc_size(devpage); + + dc->config_change = 0; + dc->guest_ack = 0; + dc->vdev_reset = 0; + dc->host_ack = 0; + dc->used_address_updated = 0; + dc->c2h_vdev_db = -1; + dc->h2c_vdev_db = -1; + mvdev->dc = dc; +} + +int mic_virtio_add_device(struct mic_vdev *mvdev, + void __user *argp) +{ + struct mic_device *mdev = mvdev->mdev; + struct mic_device_desc *dd = NULL; + struct mic_vqconfig *vqconfig; + int vr_size, i, j, ret; + u8 type = 0; + s8 db; + char irqname[10]; + struct mic_bootparam *bootparam = mdev->dp; + u16 num; + dma_addr_t vr_addr; + + mutex_lock(&mdev->mic_mutex); + + ret = mic_copy_dp_entry(mvdev, argp, &type, &dd); + if (ret) { + mutex_unlock(&mdev->mic_mutex); + return ret; + } + + mic_init_device_ctrl(mvdev, dd); + + mvdev->dd = dd; + mvdev->virtio_id = type; + vqconfig = mic_vq_config(dd); + INIT_WORK(&mvdev->virtio_bh_work, mic_bh_handler); + + for (i = 0; i < dd->num_vq; i++) { + struct mic_vringh *mvr = &mvdev->mvr[i]; + struct mic_vring *vr = &mvdev->mvr[i].vring; + num = le16_to_cpu(vqconfig[i].num); + mutex_init(&mvr->vr_mutex); + vr_size = PAGE_ALIGN(vring_size(num, MIC_VIRTIO_RING_ALIGN) + + sizeof(struct _mic_vring_info)); + vr->va = (void *) + __get_free_pages(GFP_KERNEL | __GFP_ZERO, + get_order(vr_size)); + if (!vr->va) { + ret = -ENOMEM; + dev_err(mic_dev(mvdev), "%s %d err %d\n", + __func__, __LINE__, ret); + goto err; + } + vr->len = vr_size; + vr->info = vr->va + vring_size(num, MIC_VIRTIO_RING_ALIGN); + vr->info->magic = cpu_to_le32(MIC_MAGIC + mvdev->virtio_id + i); + vr_addr = mic_map_single(mdev, vr->va, vr_size); + if (mic_map_error(vr_addr)) { + free_pages((unsigned long)vr->va, get_order(vr_size)); + ret = -ENOMEM; + dev_err(mic_dev(mvdev), "%s %d err %d\n", + __func__, __LINE__, ret); + goto err; + } + vqconfig[i].address = cpu_to_le64(vr_addr); + + vring_init(&vr->vr, num, vr->va, MIC_VIRTIO_RING_ALIGN); + ret = vringh_init_kern(&mvr->vrh, + *(u32 *)mic_vq_features(mvdev->dd), num, false, + vr->vr.desc, vr->vr.avail, vr->vr.used); + if (ret) { + dev_err(mic_dev(mvdev), "%s %d err %d\n", + __func__, __LINE__, ret); + goto err; + } + vringh_kiov_init(&mvr->riov, NULL, 0); + vringh_kiov_init(&mvr->wiov, NULL, 0); + mvr->head = USHRT_MAX; + mvr->mvdev = mvdev; + mvr->vrh.notify = mic_notify; + dev_dbg(mdev->sdev->parent, + "%s %d index %d va %p info %p vr_size 0x%x\n", + __func__, __LINE__, i, vr->va, vr->info, vr_size); + } + + snprintf(irqname, sizeof(irqname), "mic%dvirtio%d", mdev->id, + mvdev->virtio_id); + mvdev->virtio_db = mic_next_db(mdev); + mvdev->virtio_cookie = mic_request_irq(mdev, mic_virtio_intr_handler, + irqname, mvdev, mvdev->virtio_db, MIC_INTR_DB); + if (IS_ERR(mvdev->virtio_cookie)) { + ret = PTR_ERR(mvdev->virtio_cookie); + dev_dbg(mdev->sdev->parent, "request irq failed\n"); + goto err; + } + + mvdev->dc->c2h_vdev_db = mvdev->virtio_db; + + list_add_tail(&mvdev->list, &mdev->vdev_list); + /* + * Order the type update with previous stores. This write barrier + * is paired with the corresponding read barrier before the uncached + * system memory read of the type, on the card while scanning the + * device page. + */ + smp_wmb(); + dd->type = type; + + dev_dbg(mdev->sdev->parent, "Added virtio device id %d\n", dd->type); + + db = bootparam->h2c_config_db; + if (db != -1) + mdev->ops->send_intr(mdev, db); + mutex_unlock(&mdev->mic_mutex); + return 0; +err: + vqconfig = mic_vq_config(dd); + for (j = 0; j < i; j++) { + struct mic_vringh *mvr = &mvdev->mvr[j]; + mic_unmap_single(mdev, le64_to_cpu(vqconfig[j].address), + mvr->vring.len); + free_pages((unsigned long)mvr->vring.va, + get_order(mvr->vring.len)); + } + mutex_unlock(&mdev->mic_mutex); + return ret; +} + +void mic_virtio_del_device(struct mic_vdev *mvdev) +{ + struct list_head *pos, *tmp; + struct mic_vdev *tmp_mvdev; + struct mic_device *mdev = mvdev->mdev; + DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wake); + int i, ret, retry; + struct mic_vqconfig *vqconfig; + struct mic_bootparam *bootparam = mdev->dp; + s8 db; + + mutex_lock(&mdev->mic_mutex); + db = bootparam->h2c_config_db; + if (db == -1) + goto skip_hot_remove; + dev_dbg(mdev->sdev->parent, + "Requesting hot remove id %d\n", mvdev->virtio_id); + mvdev->dc->config_change = MIC_VIRTIO_PARAM_DEV_REMOVE; + mdev->ops->send_intr(mdev, db); + for (retry = 100; retry--;) { + ret = wait_event_timeout(wake, + mvdev->dc->guest_ack, msecs_to_jiffies(100)); + if (ret) + break; + } + dev_dbg(mdev->sdev->parent, + "Device id %d config_change %d guest_ack %d retry %d\n", + mvdev->virtio_id, mvdev->dc->config_change, + mvdev->dc->guest_ack, retry); + mvdev->dc->config_change = 0; + mvdev->dc->guest_ack = 0; +skip_hot_remove: + mic_free_irq(mdev, mvdev->virtio_cookie, mvdev); + flush_work(&mvdev->virtio_bh_work); + vqconfig = mic_vq_config(mvdev->dd); + for (i = 0; i < mvdev->dd->num_vq; i++) { + struct mic_vringh *mvr = &mvdev->mvr[i]; + vringh_kiov_cleanup(&mvr->riov); + vringh_kiov_cleanup(&mvr->wiov); + mic_unmap_single(mdev, le64_to_cpu(vqconfig[i].address), + mvr->vring.len); + free_pages((unsigned long)mvr->vring.va, + get_order(mvr->vring.len)); + } + + list_for_each_safe(pos, tmp, &mdev->vdev_list) { + tmp_mvdev = list_entry(pos, struct mic_vdev, list); + if (tmp_mvdev == mvdev) { + list_del(pos); + dev_dbg(mdev->sdev->parent, + "Removing virtio device id %d\n", + mvdev->virtio_id); + break; + } + } + /* + * Order the type update with previous stores. This write barrier + * is paired with the corresponding read barrier before the uncached + * system memory read of the type, on the card while scanning the + * device page. + */ + smp_wmb(); + mvdev->dd->type = -1; + mutex_unlock(&mdev->mic_mutex); +} diff --git a/drivers/misc/mic/host/mic_virtio.h b/drivers/misc/mic/host/mic_virtio.h new file mode 100644 index 000000000000..184f3c84805b --- /dev/null +++ b/drivers/misc/mic/host/mic_virtio.h @@ -0,0 +1,138 @@ +/* + * Intel MIC Platform Software Stack (MPSS) + * + * Copyright(c) 2013 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Intel MIC Host driver. + * + */ +#ifndef MIC_VIRTIO_H +#define MIC_VIRTIO_H + +#include <linux/virtio_config.h> +#include <linux/mic_ioctl.h> + +/* + * Note on endianness. + * 1. Host can be both BE or LE + * 2. Guest/card is LE. Host uses le_to_cpu to access desc/avail + * rings and ioreadXX/iowriteXX to access used ring. + * 3. Device page exposed by host to guest contains LE values. Guest + * accesses these using ioreadXX/iowriteXX etc. This way in general we + * obey the virtio spec according to which guest works with native + * endianness and host is aware of guest endianness and does all + * required endianness conversion. + * 4. Data provided from user space to guest (in ADD_DEVICE and + * CONFIG_CHANGE ioctl's) is not interpreted by the driver and should be + * in guest endianness. + */ + +/** + * struct mic_vringh - Virtio ring host information. + * + * @vring: The MIC vring used for setting up user space mappings. + * @vrh: The host VRINGH used for accessing the card vrings. + * @riov: The VRINGH read kernel IOV. + * @wiov: The VRINGH write kernel IOV. + * @head: The VRINGH head index address passed to vringh_getdesc_kern(..). + * @vr_mutex: Mutex for synchronizing access to the VRING. + * @mvdev: Back pointer to MIC virtio device for vringh_notify(..). + */ +struct mic_vringh { + struct mic_vring vring; + struct vringh vrh; + struct vringh_kiov riov; + struct vringh_kiov wiov; + u16 head; + struct mutex vr_mutex; + struct mic_vdev *mvdev; +}; + +/** + * struct mic_vdev - Host information for a card Virtio device. + * + * @virtio_id - Virtio device id. + * @waitq - Waitqueue to allow ring3 apps to poll. + * @mdev - Back pointer to host MIC device. + * @poll_wake - Used for waking up threads blocked in poll. + * @out_bytes - Debug stats for number of bytes copied from host to card. + * @in_bytes - Debug stats for number of bytes copied from card to host. + * @mvr - Store per VRING data structures. + * @virtio_bh_work - Work struct used to schedule virtio bottom half handling. + * @dd - Virtio device descriptor. + * @dc - Virtio device control fields. + * @list - List of Virtio devices. + * @virtio_db - The doorbell used by the card to interrupt the host. + * @virtio_cookie - The cookie returned while requesting interrupts. + */ +struct mic_vdev { + int virtio_id; + wait_queue_head_t waitq; + struct mic_device *mdev; + int poll_wake; + unsigned long out_bytes; + unsigned long in_bytes; + struct mic_vringh mvr[MIC_MAX_VRINGS]; + struct work_struct virtio_bh_work; + struct mic_device_desc *dd; + struct mic_device_ctrl *dc; + struct list_head list; + int virtio_db; + struct mic_irq *virtio_cookie; +}; + +void mic_virtio_uninit(struct mic_device *mdev); +int mic_virtio_add_device(struct mic_vdev *mvdev, + void __user *argp); +void mic_virtio_del_device(struct mic_vdev *mvdev); +int mic_virtio_config_change(struct mic_vdev *mvdev, + void __user *argp); +int mic_virtio_copy_desc(struct mic_vdev *mvdev, + struct mic_copy_desc *request); +void mic_virtio_reset_devices(struct mic_device *mdev); +void mic_bh_handler(struct work_struct *work); + +/* Helper API to obtain the MIC PCIe device */ +static inline struct device *mic_dev(struct mic_vdev *mvdev) +{ + return mvdev->mdev->sdev->parent; +} + +/* Helper API to check if a virtio device is initialized */ +static inline int mic_vdev_inited(struct mic_vdev *mvdev) +{ + /* Device has not been created yet */ + if (!mvdev->dd || !mvdev->dd->type) { + dev_err(mic_dev(mvdev), "%s %d err %d\n", + __func__, __LINE__, -EINVAL); + return -EINVAL; + } + + /* Device has been removed/deleted */ + if (mvdev->dd->type == -1) { + dev_err(mic_dev(mvdev), "%s %d err %d\n", + __func__, __LINE__, -ENODEV); + return -ENODEV; + } + + return 0; +} + +/* Helper API to check if a virtio device is running */ +static inline bool mic_vdevup(struct mic_vdev *mvdev) +{ + return !!mvdev->dd->status; +} +#endif diff --git a/drivers/misc/mic/host/mic_x100.c b/drivers/misc/mic/host/mic_x100.c new file mode 100644 index 000000000000..5562fdd3ef4e --- /dev/null +++ b/drivers/misc/mic/host/mic_x100.c @@ -0,0 +1,574 @@ +/* + * Intel MIC Platform Software Stack (MPSS) + * + * Copyright(c) 2013 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Intel MIC Host driver. + * + */ +#include <linux/fs.h> +#include <linux/pci.h> +#include <linux/sched.h> +#include <linux/firmware.h> +#include <linux/delay.h> + +#include "../common/mic_dev.h" +#include "mic_device.h" +#include "mic_x100.h" +#include "mic_smpt.h" + +/** + * mic_x100_write_spad - write to the scratchpad register + * @mdev: pointer to mic_device instance + * @idx: index to the scratchpad register, 0 based + * @val: the data value to put into the register + * + * This function allows writing of a 32bit value to the indexed scratchpad + * register. + * + * RETURNS: none. + */ +static void +mic_x100_write_spad(struct mic_device *mdev, unsigned int idx, u32 val) +{ + dev_dbg(mdev->sdev->parent, "Writing 0x%x to scratch pad index %d\n", + val, idx); + mic_mmio_write(&mdev->mmio, val, + MIC_X100_SBOX_BASE_ADDRESS + + MIC_X100_SBOX_SPAD0 + idx * 4); +} + +/** + * mic_x100_read_spad - read from the scratchpad register + * @mdev: pointer to mic_device instance + * @idx: index to scratchpad register, 0 based + * + * This function allows reading of the 32bit scratchpad register. + * + * RETURNS: An appropriate -ERRNO error value on error, or zero for success. + */ +static u32 +mic_x100_read_spad(struct mic_device *mdev, unsigned int idx) +{ + u32 val = mic_mmio_read(&mdev->mmio, + MIC_X100_SBOX_BASE_ADDRESS + + MIC_X100_SBOX_SPAD0 + idx * 4); + + dev_dbg(mdev->sdev->parent, + "Reading 0x%x from scratch pad index %d\n", val, idx); + return val; +} + +/** + * mic_x100_enable_interrupts - Enable interrupts. + * @mdev: pointer to mic_device instance + */ +static void mic_x100_enable_interrupts(struct mic_device *mdev) +{ + u32 reg; + struct mic_mw *mw = &mdev->mmio; + u32 sice0 = MIC_X100_SBOX_BASE_ADDRESS + MIC_X100_SBOX_SICE0; + u32 siac0 = MIC_X100_SBOX_BASE_ADDRESS + MIC_X100_SBOX_SIAC0; + + reg = mic_mmio_read(mw, sice0); + reg |= MIC_X100_SBOX_DBR_BITS(0xf) | MIC_X100_SBOX_DMA_BITS(0xff); + mic_mmio_write(mw, reg, sice0); + + /* + * Enable auto-clear when enabling interrupts. Applicable only for + * MSI-x. Legacy and MSI mode cannot have auto-clear enabled. + */ + if (mdev->irq_info.num_vectors > 1) { + reg = mic_mmio_read(mw, siac0); + reg |= MIC_X100_SBOX_DBR_BITS(0xf) | + MIC_X100_SBOX_DMA_BITS(0xff); + mic_mmio_write(mw, reg, siac0); + } +} + +/** + * mic_x100_disable_interrupts - Disable interrupts. + * @mdev: pointer to mic_device instance + */ +static void mic_x100_disable_interrupts(struct mic_device *mdev) +{ + u32 reg; + struct mic_mw *mw = &mdev->mmio; + u32 sice0 = MIC_X100_SBOX_BASE_ADDRESS + MIC_X100_SBOX_SICE0; + u32 siac0 = MIC_X100_SBOX_BASE_ADDRESS + MIC_X100_SBOX_SIAC0; + u32 sicc0 = MIC_X100_SBOX_BASE_ADDRESS + MIC_X100_SBOX_SICC0; + + reg = mic_mmio_read(mw, sice0); + mic_mmio_write(mw, reg, sicc0); + + if (mdev->irq_info.num_vectors > 1) { + reg = mic_mmio_read(mw, siac0); + reg &= ~(MIC_X100_SBOX_DBR_BITS(0xf) | + MIC_X100_SBOX_DMA_BITS(0xff)); + mic_mmio_write(mw, reg, siac0); + } +} + +/** + * mic_x100_send_sbox_intr - Send an MIC_X100_SBOX interrupt to MIC. + * @mdev: pointer to mic_device instance + */ +static void mic_x100_send_sbox_intr(struct mic_device *mdev, + int doorbell) +{ + struct mic_mw *mw = &mdev->mmio; + u64 apic_icr_offset = MIC_X100_SBOX_APICICR0 + doorbell * 8; + u32 apicicr_low = mic_mmio_read(mw, MIC_X100_SBOX_BASE_ADDRESS + + apic_icr_offset); + + /* for MIC we need to make sure we "hit" the send_icr bit (13) */ + apicicr_low = (apicicr_low | (1 << 13)); + + /* Ensure that the interrupt is ordered w.r.t. previous stores. */ + wmb(); + mic_mmio_write(mw, apicicr_low, + MIC_X100_SBOX_BASE_ADDRESS + apic_icr_offset); +} + +/** + * mic_x100_send_rdmasr_intr - Send an RDMASR interrupt to MIC. + * @mdev: pointer to mic_device instance + */ +static void mic_x100_send_rdmasr_intr(struct mic_device *mdev, + int doorbell) +{ + int rdmasr_offset = MIC_X100_SBOX_RDMASR0 + (doorbell << 2); + /* Ensure that the interrupt is ordered w.r.t. previous stores. */ + wmb(); + mic_mmio_write(&mdev->mmio, 0, + MIC_X100_SBOX_BASE_ADDRESS + rdmasr_offset); +} + +/** + * __mic_x100_send_intr - Send interrupt to MIC. + * @mdev: pointer to mic_device instance + * @doorbell: doorbell number. + */ +static void mic_x100_send_intr(struct mic_device *mdev, int doorbell) +{ + int rdmasr_db; + if (doorbell < MIC_X100_NUM_SBOX_IRQ) { + mic_x100_send_sbox_intr(mdev, doorbell); + } else { + rdmasr_db = doorbell - MIC_X100_NUM_SBOX_IRQ + + MIC_X100_RDMASR_IRQ_BASE; + mic_x100_send_rdmasr_intr(mdev, rdmasr_db); + } +} + +/** + * mic_x100_ack_interrupt - Read the interrupt sources register and + * clear it. This function will be called in the MSI/INTx case. + * @mdev: Pointer to mic_device instance. + * + * Returns: bitmask of interrupt sources triggered. + */ +static u32 mic_x100_ack_interrupt(struct mic_device *mdev) +{ + u32 sicr0 = MIC_X100_SBOX_BASE_ADDRESS + MIC_X100_SBOX_SICR0; + u32 reg = mic_mmio_read(&mdev->mmio, sicr0); + mic_mmio_write(&mdev->mmio, reg, sicr0); + return reg; +} + +/** + * mic_x100_intr_workarounds - These hardware specific workarounds are + * to be invoked everytime an interrupt is handled. + * @mdev: Pointer to mic_device instance. + * + * Returns: none + */ +static void mic_x100_intr_workarounds(struct mic_device *mdev) +{ + struct mic_mw *mw = &mdev->mmio; + + /* Clear pending bit array. */ + if (MIC_A0_STEP == mdev->stepping) + mic_mmio_write(mw, 1, MIC_X100_SBOX_BASE_ADDRESS + + MIC_X100_SBOX_MSIXPBACR); + + if (mdev->stepping >= MIC_B0_STEP) + mdev->intr_ops->enable_interrupts(mdev); +} + +/** + * mic_x100_hw_intr_init - Initialize h/w specific interrupt + * information. + * @mdev: pointer to mic_device instance + */ +static void mic_x100_hw_intr_init(struct mic_device *mdev) +{ + mdev->intr_info = (struct mic_intr_info *)mic_x100_intr_init; +} + +/** + * mic_x100_read_msi_to_src_map - read from the MSI mapping registers + * @mdev: pointer to mic_device instance + * @idx: index to the mapping register, 0 based + * + * This function allows reading of the 32bit MSI mapping register. + * + * RETURNS: The value in the register. + */ +static u32 +mic_x100_read_msi_to_src_map(struct mic_device *mdev, int idx) +{ + return mic_mmio_read(&mdev->mmio, + MIC_X100_SBOX_BASE_ADDRESS + + MIC_X100_SBOX_MXAR0 + idx * 4); +} + +/** + * mic_x100_program_msi_to_src_map - program the MSI mapping registers + * @mdev: pointer to mic_device instance + * @idx: index to the mapping register, 0 based + * @offset: The bit offset in the register that needs to be updated. + * @set: boolean specifying if the bit in the specified offset needs + * to be set or cleared. + * + * RETURNS: None. + */ +static void +mic_x100_program_msi_to_src_map(struct mic_device *mdev, + int idx, int offset, bool set) +{ + unsigned long reg; + struct mic_mw *mw = &mdev->mmio; + u32 mxar = MIC_X100_SBOX_BASE_ADDRESS + + MIC_X100_SBOX_MXAR0 + idx * 4; + + reg = mic_mmio_read(mw, mxar); + if (set) + __set_bit(offset, ®); + else + __clear_bit(offset, ®); + mic_mmio_write(mw, reg, mxar); +} + +/* + * mic_x100_reset_fw_ready - Reset Firmware ready status field. + * @mdev: pointer to mic_device instance + */ +static void mic_x100_reset_fw_ready(struct mic_device *mdev) +{ + mdev->ops->write_spad(mdev, MIC_X100_DOWNLOAD_INFO, 0); +} + +/* + * mic_x100_is_fw_ready - Check if firmware is ready. + * @mdev: pointer to mic_device instance + */ +static bool mic_x100_is_fw_ready(struct mic_device *mdev) +{ + u32 scratch2 = mdev->ops->read_spad(mdev, MIC_X100_DOWNLOAD_INFO); + return MIC_X100_SPAD2_DOWNLOAD_STATUS(scratch2) ? true : false; +} + +/** + * mic_x100_get_apic_id - Get bootstrap APIC ID. + * @mdev: pointer to mic_device instance + */ +static u32 mic_x100_get_apic_id(struct mic_device *mdev) +{ + u32 scratch2 = 0; + + scratch2 = mdev->ops->read_spad(mdev, MIC_X100_DOWNLOAD_INFO); + return MIC_X100_SPAD2_APIC_ID(scratch2); +} + +/** + * mic_x100_send_firmware_intr - Send an interrupt to the firmware on MIC. + * @mdev: pointer to mic_device instance + */ +static void mic_x100_send_firmware_intr(struct mic_device *mdev) +{ + u32 apicicr_low; + u64 apic_icr_offset = MIC_X100_SBOX_APICICR7; + int vector = MIC_X100_BSP_INTERRUPT_VECTOR; + struct mic_mw *mw = &mdev->mmio; + + /* + * For MIC we need to make sure we "hit" + * the send_icr bit (13). + */ + apicicr_low = (vector | (1 << 13)); + + mic_mmio_write(mw, mic_x100_get_apic_id(mdev), + MIC_X100_SBOX_BASE_ADDRESS + apic_icr_offset + 4); + + /* Ensure that the interrupt is ordered w.r.t. previous stores. */ + wmb(); + mic_mmio_write(mw, apicicr_low, + MIC_X100_SBOX_BASE_ADDRESS + apic_icr_offset); +} + +/** + * mic_x100_hw_reset - Reset the MIC device. + * @mdev: pointer to mic_device instance + */ +static void mic_x100_hw_reset(struct mic_device *mdev) +{ + u32 reset_reg; + u32 rgcr = MIC_X100_SBOX_BASE_ADDRESS + MIC_X100_SBOX_RGCR; + struct mic_mw *mw = &mdev->mmio; + + /* Ensure that the reset is ordered w.r.t. previous loads and stores */ + mb(); + /* Trigger reset */ + reset_reg = mic_mmio_read(mw, rgcr); + reset_reg |= 0x1; + mic_mmio_write(mw, reset_reg, rgcr); + /* + * It seems we really want to delay at least 1 second + * after touching reset to prevent a lot of problems. + */ + msleep(1000); +} + +/** + * mic_x100_load_command_line - Load command line to MIC. + * @mdev: pointer to mic_device instance + * @fw: the firmware image + * + * RETURNS: An appropriate -ERRNO error value on error, or zero for success. + */ +static int +mic_x100_load_command_line(struct mic_device *mdev, const struct firmware *fw) +{ + u32 len = 0; + u32 boot_mem; + char *buf; + void __iomem *cmd_line_va = mdev->aper.va + mdev->bootaddr + fw->size; +#define CMDLINE_SIZE 2048 + + boot_mem = mdev->aper.len >> 20; + buf = kzalloc(CMDLINE_SIZE, GFP_KERNEL); + if (!buf) { + dev_err(mdev->sdev->parent, + "%s %d allocation failed\n", __func__, __LINE__); + return -ENOMEM; + } + len += snprintf(buf, CMDLINE_SIZE - len, + " mem=%dM", boot_mem); + if (mdev->cmdline) + snprintf(buf + len, CMDLINE_SIZE - len, " %s", mdev->cmdline); + memcpy_toio(cmd_line_va, buf, strlen(buf) + 1); + kfree(buf); + return 0; +} + +/** + * mic_x100_load_ramdisk - Load ramdisk to MIC. + * @mdev: pointer to mic_device instance + * + * RETURNS: An appropriate -ERRNO error value on error, or zero for success. + */ +static int +mic_x100_load_ramdisk(struct mic_device *mdev) +{ + const struct firmware *fw; + int rc; + struct boot_params __iomem *bp = mdev->aper.va + mdev->bootaddr; + + rc = request_firmware(&fw, + mdev->ramdisk, mdev->sdev->parent); + if (rc < 0) { + dev_err(mdev->sdev->parent, + "ramdisk request_firmware failed: %d %s\n", + rc, mdev->ramdisk); + goto error; + } + /* + * Typically the bootaddr for card OS is 64M + * so copy over the ramdisk @ 128M. + */ + memcpy_toio(mdev->aper.va + (mdev->bootaddr << 1), fw->data, fw->size); + iowrite32(mdev->bootaddr << 1, &bp->hdr.ramdisk_image); + iowrite32(fw->size, &bp->hdr.ramdisk_size); + release_firmware(fw); +error: + return rc; +} + +/** + * mic_x100_get_boot_addr - Get MIC boot address. + * @mdev: pointer to mic_device instance + * + * This function is called during firmware load to determine + * the address at which the OS should be downloaded in card + * memory i.e. GDDR. + * RETURNS: An appropriate -ERRNO error value on error, or zero for success. + */ +static int +mic_x100_get_boot_addr(struct mic_device *mdev) +{ + u32 scratch2, boot_addr; + int rc = 0; + + scratch2 = mdev->ops->read_spad(mdev, MIC_X100_DOWNLOAD_INFO); + boot_addr = MIC_X100_SPAD2_DOWNLOAD_ADDR(scratch2); + dev_dbg(mdev->sdev->parent, "%s %d boot_addr 0x%x\n", + __func__, __LINE__, boot_addr); + if (boot_addr > (1 << 31)) { + dev_err(mdev->sdev->parent, + "incorrect bootaddr 0x%x\n", + boot_addr); + rc = -EINVAL; + goto error; + } + mdev->bootaddr = boot_addr; +error: + return rc; +} + +/** + * mic_x100_load_firmware - Load firmware to MIC. + * @mdev: pointer to mic_device instance + * @buf: buffer containing boot string including firmware/ramdisk path. + * + * RETURNS: An appropriate -ERRNO error value on error, or zero for success. + */ +static int +mic_x100_load_firmware(struct mic_device *mdev, const char *buf) +{ + int rc; + const struct firmware *fw; + + rc = mic_x100_get_boot_addr(mdev); + if (rc) + goto error; + /* load OS */ + rc = request_firmware(&fw, mdev->firmware, mdev->sdev->parent); + if (rc < 0) { + dev_err(mdev->sdev->parent, + "ramdisk request_firmware failed: %d %s\n", + rc, mdev->firmware); + goto error; + } + if (mdev->bootaddr > mdev->aper.len - fw->size) { + rc = -EINVAL; + dev_err(mdev->sdev->parent, "%s %d rc %d bootaddr 0x%x\n", + __func__, __LINE__, rc, mdev->bootaddr); + release_firmware(fw); + goto error; + } + memcpy_toio(mdev->aper.va + mdev->bootaddr, fw->data, fw->size); + mdev->ops->write_spad(mdev, MIC_X100_FW_SIZE, fw->size); + if (!strcmp(mdev->bootmode, "elf")) + goto done; + /* load command line */ + rc = mic_x100_load_command_line(mdev, fw); + if (rc) { + dev_err(mdev->sdev->parent, "%s %d rc %d\n", + __func__, __LINE__, rc); + goto error; + } + release_firmware(fw); + /* load ramdisk */ + if (mdev->ramdisk) + rc = mic_x100_load_ramdisk(mdev); +error: + dev_dbg(mdev->sdev->parent, "%s %d rc %d\n", __func__, __LINE__, rc); +done: + return rc; +} + +/** + * mic_x100_get_postcode - Get postcode status from firmware. + * @mdev: pointer to mic_device instance + * + * RETURNS: postcode. + */ +static u32 mic_x100_get_postcode(struct mic_device *mdev) +{ + return mic_mmio_read(&mdev->mmio, MIC_X100_POSTCODE); +} + +/** + * mic_x100_smpt_set - Update an SMPT entry with a DMA address. + * @mdev: pointer to mic_device instance + * + * RETURNS: none. + */ +static void +mic_x100_smpt_set(struct mic_device *mdev, dma_addr_t dma_addr, u8 index) +{ +#define SNOOP_ON (0 << 0) +#define SNOOP_OFF (1 << 0) +/* + * Sbox Smpt Reg Bits: + * Bits 31:2 Host address + * Bits 1 RSVD + * Bits 0 No snoop + */ +#define BUILD_SMPT(NO_SNOOP, HOST_ADDR) \ + (u32)(((HOST_ADDR) << 2) | ((NO_SNOOP) & 0x01)) + + uint32_t smpt_reg_val = BUILD_SMPT(SNOOP_ON, + dma_addr >> mdev->smpt->info.page_shift); + mic_mmio_write(&mdev->mmio, smpt_reg_val, + MIC_X100_SBOX_BASE_ADDRESS + + MIC_X100_SBOX_SMPT00 + (4 * index)); +} + +/** + * mic_x100_smpt_hw_init - Initialize SMPT X100 specific fields. + * @mdev: pointer to mic_device instance + * + * RETURNS: none. + */ +static void mic_x100_smpt_hw_init(struct mic_device *mdev) +{ + struct mic_smpt_hw_info *info = &mdev->smpt->info; + + info->num_reg = 32; + info->page_shift = 34; + info->page_size = (1ULL << info->page_shift); + info->base = 0x8000000000ULL; +} + +struct mic_smpt_ops mic_x100_smpt_ops = { + .init = mic_x100_smpt_hw_init, + .set = mic_x100_smpt_set, +}; + +struct mic_hw_ops mic_x100_ops = { + .aper_bar = MIC_X100_APER_BAR, + .mmio_bar = MIC_X100_MMIO_BAR, + .read_spad = mic_x100_read_spad, + .write_spad = mic_x100_write_spad, + .send_intr = mic_x100_send_intr, + .ack_interrupt = mic_x100_ack_interrupt, + .intr_workarounds = mic_x100_intr_workarounds, + .reset = mic_x100_hw_reset, + .reset_fw_ready = mic_x100_reset_fw_ready, + .is_fw_ready = mic_x100_is_fw_ready, + .send_firmware_intr = mic_x100_send_firmware_intr, + .load_mic_fw = mic_x100_load_firmware, + .get_postcode = mic_x100_get_postcode, +}; + +struct mic_hw_intr_ops mic_x100_intr_ops = { + .intr_init = mic_x100_hw_intr_init, + .enable_interrupts = mic_x100_enable_interrupts, + .disable_interrupts = mic_x100_disable_interrupts, + .program_msi_to_src_map = mic_x100_program_msi_to_src_map, + .read_msi_to_src_map = mic_x100_read_msi_to_src_map, +}; diff --git a/drivers/misc/mic/host/mic_x100.h b/drivers/misc/mic/host/mic_x100.h new file mode 100644 index 000000000000..8b7daa182e54 --- /dev/null +++ b/drivers/misc/mic/host/mic_x100.h @@ -0,0 +1,98 @@ +/* + * Intel MIC Platform Software Stack (MPSS) + * + * Copyright(c) 2013 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License, version 2, as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Intel MIC Host driver. + * + */ +#ifndef _MIC_X100_HW_H_ +#define _MIC_X100_HW_H_ + +#define MIC_X100_PCI_DEVICE_2250 0x2250 +#define MIC_X100_PCI_DEVICE_2251 0x2251 +#define MIC_X100_PCI_DEVICE_2252 0x2252 +#define MIC_X100_PCI_DEVICE_2253 0x2253 +#define MIC_X100_PCI_DEVICE_2254 0x2254 +#define MIC_X100_PCI_DEVICE_2255 0x2255 +#define MIC_X100_PCI_DEVICE_2256 0x2256 +#define MIC_X100_PCI_DEVICE_2257 0x2257 +#define MIC_X100_PCI_DEVICE_2258 0x2258 +#define MIC_X100_PCI_DEVICE_2259 0x2259 +#define MIC_X100_PCI_DEVICE_225a 0x225a +#define MIC_X100_PCI_DEVICE_225b 0x225b +#define MIC_X100_PCI_DEVICE_225c 0x225c +#define MIC_X100_PCI_DEVICE_225d 0x225d +#define MIC_X100_PCI_DEVICE_225e 0x225e + +#define MIC_X100_APER_BAR 0 +#define MIC_X100_MMIO_BAR 4 + +#define MIC_X100_SBOX_BASE_ADDRESS 0x00010000 +#define MIC_X100_SBOX_SPAD0 0x0000AB20 +#define MIC_X100_SBOX_SICR0_DBR(x) ((x) & 0xf) +#define MIC_X100_SBOX_SICR0_DMA(x) (((x) >> 8) & 0xff) +#define MIC_X100_SBOX_SICE0_DBR(x) ((x) & 0xf) +#define MIC_X100_SBOX_DBR_BITS(x) ((x) & 0xf) +#define MIC_X100_SBOX_SICE0_DMA(x) (((x) >> 8) & 0xff) +#define MIC_X100_SBOX_DMA_BITS(x) (((x) & 0xff) << 8) + +#define MIC_X100_SBOX_APICICR0 0x0000A9D0 +#define MIC_X100_SBOX_SICR0 0x00009004 +#define MIC_X100_SBOX_SICE0 0x0000900C +#define MIC_X100_SBOX_SICC0 0x00009010 +#define MIC_X100_SBOX_SIAC0 0x00009014 +#define MIC_X100_SBOX_MSIXPBACR 0x00009084 +#define MIC_X100_SBOX_MXAR0 0x00009044 +#define MIC_X100_SBOX_SMPT00 0x00003100 +#define MIC_X100_SBOX_RDMASR0 0x0000B180 + +#define MIC_X100_DOORBELL_IDX_START 0 +#define MIC_X100_NUM_DOORBELL 4 +#define MIC_X100_DMA_IDX_START 8 +#define MIC_X100_NUM_DMA 8 +#define MIC_X100_ERR_IDX_START 30 +#define MIC_X100_NUM_ERR 1 + +#define MIC_X100_NUM_SBOX_IRQ 8 +#define MIC_X100_NUM_RDMASR_IRQ 8 +#define MIC_X100_RDMASR_IRQ_BASE 17 +#define MIC_X100_SPAD2_DOWNLOAD_STATUS(x) ((x) & 0x1) +#define MIC_X100_SPAD2_APIC_ID(x) (((x) >> 1) & 0x1ff) +#define MIC_X100_SPAD2_DOWNLOAD_ADDR(x) ((x) & 0xfffff000) +#define MIC_X100_SBOX_APICICR7 0x0000AA08 +#define MIC_X100_SBOX_RGCR 0x00004010 +#define MIC_X100_SBOX_SDBIC0 0x0000CC90 +#define MIC_X100_DOWNLOAD_INFO 2 +#define MIC_X100_FW_SIZE 5 +#define MIC_X100_POSTCODE 0x242c + +static const u16 mic_x100_intr_init[] = { + MIC_X100_DOORBELL_IDX_START, + MIC_X100_DMA_IDX_START, + MIC_X100_ERR_IDX_START, + MIC_X100_NUM_DOORBELL, + MIC_X100_NUM_DMA, + MIC_X100_NUM_ERR, +}; + +/* Host->Card(bootstrap) Interrupt Vector */ +#define MIC_X100_BSP_INTERRUPT_VECTOR 229 + +extern struct mic_hw_ops mic_x100_ops; +extern struct mic_smpt_ops mic_x100_smpt_ops; +extern struct mic_hw_intr_ops mic_x100_intr_ops; + +#endif diff --git a/drivers/misc/phantom.c b/drivers/misc/phantom.c index 68b7c773d2cf..30754927fd80 100644 --- a/drivers/misc/phantom.c +++ b/drivers/misc/phantom.c @@ -395,7 +395,7 @@ static int phantom_probe(struct pci_dev *pdev, iowrite32(0, pht->caddr + PHN_IRQCTL); ioread32(pht->caddr + PHN_IRQCTL); /* PCI posting */ retval = request_irq(pdev->irq, phantom_isr, - IRQF_SHARED | IRQF_DISABLED, "phantom", pht); + IRQF_SHARED, "phantom", pht); if (retval) { dev_err(&pdev->dev, "can't establish ISR\n"); goto err_unmo; diff --git a/drivers/misc/pti.c b/drivers/misc/pti.c index f84ff0c06035..eda38cbe8530 100644 --- a/drivers/misc/pti.c +++ b/drivers/misc/pti.c @@ -892,7 +892,6 @@ static void pti_pci_remove(struct pci_dev *pdev) } iounmap(drv_data->pti_ioaddr); - pci_set_drvdata(pdev, NULL); kfree(drv_data); pci_release_region(pdev, 1); pci_disable_device(pdev); diff --git a/drivers/misc/sgi-xp/xpc_channel.c b/drivers/misc/sgi-xp/xpc_channel.c index 652593fc486d..128d5615c804 100644 --- a/drivers/misc/sgi-xp/xpc_channel.c +++ b/drivers/misc/sgi-xp/xpc_channel.c @@ -828,6 +828,7 @@ enum xp_retval xpc_allocate_msg_wait(struct xpc_channel *ch) { enum xp_retval ret; + DEFINE_WAIT(wait); if (ch->flags & XPC_C_DISCONNECTING) { DBUG_ON(ch->reason == xpInterrupted); @@ -835,7 +836,9 @@ xpc_allocate_msg_wait(struct xpc_channel *ch) } atomic_inc(&ch->n_on_msg_allocate_wq); - ret = interruptible_sleep_on_timeout(&ch->msg_allocate_wq, 1); + prepare_to_wait(&ch->msg_allocate_wq, &wait, TASK_INTERRUPTIBLE); + ret = schedule_timeout(1); + finish_wait(&ch->msg_allocate_wq, &wait); atomic_dec(&ch->n_on_msg_allocate_wq); if (ch->flags & XPC_C_DISCONNECTING) { diff --git a/drivers/misc/ti-st/st_core.c b/drivers/misc/ti-st/st_core.c index 8d64b681dd93..3aed525e55b4 100644 --- a/drivers/misc/ti-st/st_core.c +++ b/drivers/misc/ti-st/st_core.c @@ -812,7 +812,7 @@ static void st_tty_flush_buffer(struct tty_struct *tty) kfree_skb(st_gdata->tx_skb); st_gdata->tx_skb = NULL; - tty->ops->flush_buffer(tty); + tty_driver_flush_buffer(tty); return; } diff --git a/drivers/misc/ti-st/st_kim.c b/drivers/misc/ti-st/st_kim.c index 83907c720594..9d3dbb28734b 100644 --- a/drivers/misc/ti-st/st_kim.c +++ b/drivers/misc/ti-st/st_kim.c @@ -218,7 +218,7 @@ static long read_local_version(struct kim_data_s *kim_gdata, char *bts_scr_name) pr_debug("%s", __func__); - INIT_COMPLETION(kim_gdata->kim_rcvd); + reinit_completion(&kim_gdata->kim_rcvd); if (4 != st_int_write(kim_gdata->core_data, read_ver_cmd, 4)) { pr_err("kim: couldn't write 4 bytes"); return -EIO; @@ -229,7 +229,7 @@ static long read_local_version(struct kim_data_s *kim_gdata, char *bts_scr_name) pr_err(" waiting for ver info- timed out "); return -ETIMEDOUT; } - INIT_COMPLETION(kim_gdata->kim_rcvd); + reinit_completion(&kim_gdata->kim_rcvd); /* the positions 12 & 13 in the response buffer provide with the * chip, major & minor numbers */ @@ -362,7 +362,7 @@ static long download_firmware(struct kim_data_s *kim_gdata) /* reinit completion before sending for the * relevant wait */ - INIT_COMPLETION(kim_gdata->kim_rcvd); + reinit_completion(&kim_gdata->kim_rcvd); /* * Free space found in uart buffer, call st_int_write @@ -398,7 +398,7 @@ static long download_firmware(struct kim_data_s *kim_gdata) release_firmware(kim_gdata->fw_entry); return -ETIMEDOUT; } - INIT_COMPLETION(kim_gdata->kim_rcvd); + reinit_completion(&kim_gdata->kim_rcvd); break; case ACTION_DELAY: /* sleep */ pr_info("sleep command in scr"); @@ -474,7 +474,7 @@ long st_kim_start(void *kim_data) gpio_set_value(kim_gdata->nshutdown, GPIO_HIGH); mdelay(100); /* re-initialize the completion */ - INIT_COMPLETION(kim_gdata->ldisc_installed); + reinit_completion(&kim_gdata->ldisc_installed); /* send notification to UIM */ kim_gdata->ldisc_install = 1; pr_info("ldisc_install = 1"); @@ -525,13 +525,12 @@ long st_kim_stop(void *kim_data) kim_gdata->kim_pdev->dev.platform_data; struct tty_struct *tty = kim_gdata->core_data->tty; - INIT_COMPLETION(kim_gdata->ldisc_installed); + reinit_completion(&kim_gdata->ldisc_installed); if (tty) { /* can be called before ldisc is installed */ /* Flush any pending characters in the driver and discipline. */ tty_ldisc_flush(tty); tty_driver_flush_buffer(tty); - tty->ops->flush_buffer(tty); } /* send uninstall notification to UIM */ diff --git a/drivers/misc/ti_dac7512.c b/drivers/misc/ti_dac7512.c index 9b237221bc4e..83da711ce9f1 100644 --- a/drivers/misc/ti_dac7512.c +++ b/drivers/misc/ti_dac7512.c @@ -22,9 +22,7 @@ #include <linux/module.h> #include <linux/init.h> #include <linux/spi/spi.h> - -#define DAC7512_DRV_NAME "dac7512" -#define DRIVER_VERSION "1.0" +#include <linux/of.h> static ssize_t dac7512_store_val(struct device *dev, struct device_attribute *attr, @@ -75,13 +73,29 @@ static int dac7512_remove(struct spi_device *spi) return 0; } +static const struct spi_device_id dac7512_id_table[] = { + { "dac7512", 0 }, + { } +}; +MODULE_DEVICE_TABLE(spi, dac7512_id_table); + +#ifdef CONFIG_OF +static const struct of_device_id dac7512_of_match[] = { + { .compatible = "ti,dac7512", }, + { } +}; +MODULE_DEVICE_TABLE(of, dac7512_of_match); +#endif + static struct spi_driver dac7512_driver = { .driver = { - .name = DAC7512_DRV_NAME, + .name = "dac7512", .owner = THIS_MODULE, + .of_match_table = of_match_ptr(dac7512_of_match), }, .probe = dac7512_probe, .remove = dac7512_remove, + .id_table = dac7512_id_table, }; module_spi_driver(dac7512_driver); @@ -89,4 +103,3 @@ module_spi_driver(dac7512_driver); MODULE_AUTHOR("Daniel Mack <daniel@caiaq.de>"); MODULE_DESCRIPTION("DAC7512 16-bit DAC"); MODULE_LICENSE("GPL v2"); -MODULE_VERSION(DRIVER_VERSION); diff --git a/drivers/misc/tifm_7xx1.c b/drivers/misc/tifm_7xx1.c index f8d6654391e5..a606c8901e18 100644 --- a/drivers/misc/tifm_7xx1.c +++ b/drivers/misc/tifm_7xx1.c @@ -356,8 +356,10 @@ static int tifm_7xx1_probe(struct pci_dev *dev, pci_set_drvdata(dev, fm); fm->addr = pci_ioremap_bar(dev, 0); - if (!fm->addr) + if (!fm->addr) { + rc = -ENODEV; goto err_out_free; + } rc = request_irq(dev->irq, tifm_7xx1_isr, IRQF_SHARED, DRIVER_NAME, fm); if (rc) @@ -378,7 +380,6 @@ err_out_irq: err_out_unmap: iounmap(fm->addr); err_out_free: - pci_set_drvdata(dev, NULL); tifm_free_adapter(fm); err_out_int: pci_intx(dev, 0); @@ -405,8 +406,6 @@ static void tifm_7xx1_remove(struct pci_dev *dev) for (cnt = 0; cnt < fm->num_sockets; cnt++) tifm_7xx1_sock_power_off(tifm_7xx1_sock_addr(fm->addr, cnt)); - pci_set_drvdata(dev, NULL); - iounmap(fm->addr); pci_intx(dev, 0); pci_release_regions(dev); diff --git a/drivers/misc/tifm_core.c b/drivers/misc/tifm_core.c index 0ab7c922212c..a511b2a713b3 100644 --- a/drivers/misc/tifm_core.c +++ b/drivers/misc/tifm_core.c @@ -145,15 +145,17 @@ static ssize_t type_show(struct device *dev, struct device_attribute *attr, struct tifm_dev *sock = container_of(dev, struct tifm_dev, dev); return sprintf(buf, "%x", sock->type); } +static DEVICE_ATTR_RO(type); -static struct device_attribute tifm_dev_attrs[] = { - __ATTR(type, S_IRUGO, type_show, NULL), - __ATTR_NULL +static struct attribute *tifm_dev_attrs[] = { + &dev_attr_type.attr, + NULL, }; +ATTRIBUTE_GROUPS(tifm_dev); static struct bus_type tifm_bus_type = { .name = "tifm", - .dev_attrs = tifm_dev_attrs, + .dev_groups = tifm_dev_groups, .match = tifm_bus_match, .uevent = tifm_uevent, .probe = tifm_device_probe, diff --git a/drivers/misc/vmw_vmci/vmci_guest.c b/drivers/misc/vmw_vmci/vmci_guest.c index b3a2b763ecf2..d35cda06b5e8 100644 --- a/drivers/misc/vmw_vmci/vmci_guest.c +++ b/drivers/misc/vmw_vmci/vmci_guest.c @@ -165,7 +165,7 @@ static void vmci_guest_cid_update(u32 sub_id, * true if required hypercalls (or fallback hypercalls) are * supported by the host, false otherwise. */ -static bool vmci_check_host_caps(struct pci_dev *pdev) +static int vmci_check_host_caps(struct pci_dev *pdev) { bool result; struct vmci_resource_query_msg *msg; @@ -176,7 +176,7 @@ static bool vmci_check_host_caps(struct pci_dev *pdev) check_msg = kmalloc(msg_size, GFP_KERNEL); if (!check_msg) { dev_err(&pdev->dev, "%s: Insufficient memory\n", __func__); - return false; + return -ENOMEM; } check_msg->dst = vmci_make_handle(VMCI_HYPERVISOR_CONTEXT_ID, @@ -196,7 +196,7 @@ static bool vmci_check_host_caps(struct pci_dev *pdev) __func__, result ? "PASSED" : "FAILED"); /* We need the vector. There are no fallbacks. */ - return result; + return result ? 0 : -ENXIO; } /* @@ -564,12 +564,14 @@ static int vmci_guest_probe_device(struct pci_dev *pdev, dev_warn(&pdev->dev, "VMCI device unable to register notification bitmap with PPN 0x%x\n", (u32) bitmap_ppn); + error = -ENXIO; goto err_remove_vmci_dev_g; } } /* Check host capabilities. */ - if (!vmci_check_host_caps(pdev)) + error = vmci_check_host_caps(pdev); + if (error) goto err_remove_bitmap; /* Enable device. */ @@ -649,7 +651,7 @@ static int vmci_guest_probe_device(struct pci_dev *pdev, return 0; err_free_irq: - free_irq(vmci_dev->irq, &vmci_dev); + free_irq(vmci_dev->irq, vmci_dev); tasklet_kill(&vmci_dev->datagram_tasklet); tasklet_kill(&vmci_dev->bm_tasklet); diff --git a/drivers/misc/vmw_vmci/vmci_host.c b/drivers/misc/vmw_vmci/vmci_host.c index d4722b3dc8ec..1723a6e4f2e8 100644 --- a/drivers/misc/vmw_vmci/vmci_host.c +++ b/drivers/misc/vmw_vmci/vmci_host.c @@ -243,11 +243,7 @@ static int vmci_host_setup_notify(struct vmci_ctx *context, /* * Lock physical page backing a given user VA. */ - down_read(¤t->mm->mmap_sem); - retval = get_user_pages(current, current->mm, - PAGE_ALIGN(uva), - 1, 1, 0, &page, NULL); - up_read(¤t->mm->mmap_sem); + retval = get_user_pages_fast(PAGE_ALIGN(uva), 1, 1, &page); if (retval != 1) return VMCI_ERROR_GENERIC; diff --git a/drivers/misc/vmw_vmci/vmci_queue_pair.c b/drivers/misc/vmw_vmci/vmci_queue_pair.c index a0515a6d6ebd..1b7b303085d2 100644 --- a/drivers/misc/vmw_vmci/vmci_queue_pair.c +++ b/drivers/misc/vmw_vmci/vmci_queue_pair.c @@ -732,13 +732,9 @@ static int qp_host_get_user_memory(u64 produce_uva, int retval; int err = VMCI_SUCCESS; - down_write(¤t->mm->mmap_sem); - retval = get_user_pages(current, - current->mm, - (uintptr_t) produce_uva, - produce_q->kernel_if->num_pages, - 1, 0, - produce_q->kernel_if->u.h.header_page, NULL); + retval = get_user_pages_fast((uintptr_t) produce_uva, + produce_q->kernel_if->num_pages, 1, + produce_q->kernel_if->u.h.header_page); if (retval < produce_q->kernel_if->num_pages) { pr_warn("get_user_pages(produce) failed (retval=%d)", retval); qp_release_pages(produce_q->kernel_if->u.h.header_page, @@ -747,12 +743,9 @@ static int qp_host_get_user_memory(u64 produce_uva, goto out; } - retval = get_user_pages(current, - current->mm, - (uintptr_t) consume_uva, - consume_q->kernel_if->num_pages, - 1, 0, - consume_q->kernel_if->u.h.header_page, NULL); + retval = get_user_pages_fast((uintptr_t) consume_uva, + consume_q->kernel_if->num_pages, 1, + consume_q->kernel_if->u.h.header_page); if (retval < consume_q->kernel_if->num_pages) { pr_warn("get_user_pages(consume) failed (retval=%d)", retval); qp_release_pages(consume_q->kernel_if->u.h.header_page, @@ -763,8 +756,6 @@ static int qp_host_get_user_memory(u64 produce_uva, } out: - up_write(¤t->mm->mmap_sem); - return err; } |