diff options
Diffstat (limited to 'drivers')
-rw-r--r-- | drivers/Kconfig | 2 | ||||
-rw-r--r-- | drivers/Makefile | 3 | ||||
-rw-r--r-- | drivers/base/platform.c | 21 | ||||
-rw-r--r-- | drivers/cpufreq/Kconfig | 5 | ||||
-rw-r--r-- | drivers/cpufreq/Kconfig.powerpc | 7 | ||||
-rw-r--r-- | drivers/cpufreq/Makefile | 4 | ||||
-rw-r--r-- | drivers/cpufreq/maple-cpufreq.c | 309 | ||||
-rw-r--r-- | drivers/of/platform.c | 4 | ||||
-rw-r--r-- | drivers/tty/hvc/Kconfig | 5 | ||||
-rw-r--r-- | drivers/tty/hvc/Makefile | 3 | ||||
-rw-r--r-- | drivers/tty/hvc/hvc_console.c | 70 | ||||
-rw-r--r-- | drivers/tty/hvc/hvc_console.h | 4 | ||||
-rw-r--r-- | drivers/tty/hvc/hvc_vio.c | 408 | ||||
-rw-r--r-- | drivers/tty/hvc/hvsi.c | 129 | ||||
-rw-r--r-- | drivers/tty/hvc/hvsi_lib.c | 426 | ||||
-rw-r--r-- | drivers/virt/Kconfig | 32 | ||||
-rw-r--r-- | drivers/virt/Makefile | 5 | ||||
-rw-r--r-- | drivers/virt/fsl_hypervisor.c | 938 |
18 files changed, 2225 insertions, 150 deletions
diff --git a/drivers/Kconfig b/drivers/Kconfig index 9e7a4f5b5c2e..95b9e7eefadc 100644 --- a/drivers/Kconfig +++ b/drivers/Kconfig @@ -128,4 +128,6 @@ source "drivers/clocksource/Kconfig" source "drivers/iommu/Kconfig" +source "drivers/virt/Kconfig" + endmenu diff --git a/drivers/Makefile b/drivers/Makefile index 939fcdeb2d31..7fa433a7030c 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -124,3 +124,6 @@ obj-y += clk/ obj-$(CONFIG_HWSPINLOCK) += hwspinlock/ obj-$(CONFIG_NFC) += nfc/ obj-$(CONFIG_IOMMU_SUPPORT) += iommu/ + +# Virtualization drivers +obj-$(CONFIG_VIRT_DRIVERS) += virt/ diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 6040717b62bb..0cad9c7f6bb5 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -32,6 +32,25 @@ struct device platform_bus = { EXPORT_SYMBOL_GPL(platform_bus); /** + * arch_setup_pdev_archdata - Allow manipulation of archdata before its used + * @dev: platform device + * + * This is called before platform_device_add() such that any pdev_archdata may + * be setup before the platform_notifier is called. So if a user needs to + * manipulate any relevant information in the pdev_archdata they can do: + * + * platform_devic_alloc() + * ... manipulate ... + * platform_device_add() + * + * And if they don't care they can just call platform_device_register() and + * everything will just work out. + */ +void __weak arch_setup_pdev_archdata(struct platform_device *pdev) +{ +} + +/** * platform_get_resource - get a resource for a device * @dev: platform device * @type: resource type @@ -173,6 +192,7 @@ struct platform_device *platform_device_alloc(const char *name, int id) pa->pdev.id = id; device_initialize(&pa->pdev.dev); pa->pdev.dev.release = platform_device_release; + arch_setup_pdev_archdata(&pa->pdev); } return pa ? &pa->pdev : NULL; @@ -334,6 +354,7 @@ EXPORT_SYMBOL_GPL(platform_device_del); int platform_device_register(struct platform_device *pdev) { device_initialize(&pdev->dev); + arch_setup_pdev_archdata(pdev); return platform_device_add(pdev); } EXPORT_SYMBOL_GPL(platform_device_register); diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig index e898215b88af..e24a2a1b6666 100644 --- a/drivers/cpufreq/Kconfig +++ b/drivers/cpufreq/Kconfig @@ -189,5 +189,10 @@ depends on ARM source "drivers/cpufreq/Kconfig.arm" endmenu +menu "PowerPC CPU frequency scaling drivers" +depends on PPC32 || PPC64 +source "drivers/cpufreq/Kconfig.powerpc" +endmenu + endif endmenu diff --git a/drivers/cpufreq/Kconfig.powerpc b/drivers/cpufreq/Kconfig.powerpc new file mode 100644 index 000000000000..e76992f79683 --- /dev/null +++ b/drivers/cpufreq/Kconfig.powerpc @@ -0,0 +1,7 @@ +config CPU_FREQ_MAPLE + bool "Support for Maple 970FX Evaluation Board" + depends on PPC_MAPLE + select CPU_FREQ_TABLE + help + This adds support for frequency switching on Maple 970FX + Evaluation Board and compatible boards (IBM JS2x blades). diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile index ab75e573c69f..a48bc02cd765 100644 --- a/drivers/cpufreq/Makefile +++ b/drivers/cpufreq/Makefile @@ -43,3 +43,7 @@ obj-$(CONFIG_UX500_SOC_DB8500) += db8500-cpufreq.o obj-$(CONFIG_ARM_S3C64XX_CPUFREQ) += s3c64xx-cpufreq.o obj-$(CONFIG_ARM_S5PV210_CPUFREQ) += s5pv210-cpufreq.o obj-$(CONFIG_ARM_EXYNOS4210_CPUFREQ) += exynos4210-cpufreq.o + +################################################################################## +# PowerPC platform drivers +obj-$(CONFIG_CPU_FREQ_MAPLE) += maple-cpufreq.o diff --git a/drivers/cpufreq/maple-cpufreq.c b/drivers/cpufreq/maple-cpufreq.c new file mode 100644 index 000000000000..89b178a3f849 --- /dev/null +++ b/drivers/cpufreq/maple-cpufreq.c @@ -0,0 +1,309 @@ +/* + * Copyright (C) 2011 Dmitry Eremin-Solenikov + * Copyright (C) 2002 - 2005 Benjamin Herrenschmidt <benh@kernel.crashing.org> + * and Markus Demleitner <msdemlei@cl.uni-heidelberg.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 as + * published by the Free Software Foundation. + * + * This driver adds basic cpufreq support for SMU & 970FX based G5 Macs, + * that is iMac G5 and latest single CPU desktop. + */ + +#undef DEBUG + +#include <linux/module.h> +#include <linux/types.h> +#include <linux/errno.h> +#include <linux/kernel.h> +#include <linux/delay.h> +#include <linux/sched.h> +#include <linux/cpufreq.h> +#include <linux/init.h> +#include <linux/completion.h> +#include <linux/mutex.h> +#include <linux/time.h> +#include <linux/of.h> + +#define DBG(fmt...) pr_debug(fmt) + +/* see 970FX user manual */ + +#define SCOM_PCR 0x0aa001 /* PCR scom addr */ + +#define PCR_HILO_SELECT 0x80000000U /* 1 = PCR, 0 = PCRH */ +#define PCR_SPEED_FULL 0x00000000U /* 1:1 speed value */ +#define PCR_SPEED_HALF 0x00020000U /* 1:2 speed value */ +#define PCR_SPEED_QUARTER 0x00040000U /* 1:4 speed value */ +#define PCR_SPEED_MASK 0x000e0000U /* speed mask */ +#define PCR_SPEED_SHIFT 17 +#define PCR_FREQ_REQ_VALID 0x00010000U /* freq request valid */ +#define PCR_VOLT_REQ_VALID 0x00008000U /* volt request valid */ +#define PCR_TARGET_TIME_MASK 0x00006000U /* target time */ +#define PCR_STATLAT_MASK 0x00001f00U /* STATLAT value */ +#define PCR_SNOOPLAT_MASK 0x000000f0U /* SNOOPLAT value */ +#define PCR_SNOOPACC_MASK 0x0000000fU /* SNOOPACC value */ + +#define SCOM_PSR 0x408001 /* PSR scom addr */ +/* warning: PSR is a 64 bits register */ +#define PSR_CMD_RECEIVED 0x2000000000000000U /* command received */ +#define PSR_CMD_COMPLETED 0x1000000000000000U /* command completed */ +#define PSR_CUR_SPEED_MASK 0x0300000000000000U /* current speed */ +#define PSR_CUR_SPEED_SHIFT (56) + +/* + * The G5 only supports two frequencies (Quarter speed is not supported) + */ +#define CPUFREQ_HIGH 0 +#define CPUFREQ_LOW 1 + +static struct cpufreq_frequency_table maple_cpu_freqs[] = { + {CPUFREQ_HIGH, 0}, + {CPUFREQ_LOW, 0}, + {0, CPUFREQ_TABLE_END}, +}; + +static struct freq_attr *maple_cpu_freqs_attr[] = { + &cpufreq_freq_attr_scaling_available_freqs, + NULL, +}; + +/* Power mode data is an array of the 32 bits PCR values to use for + * the various frequencies, retrieved from the device-tree + */ +static int maple_pmode_cur; + +static DEFINE_MUTEX(maple_switch_mutex); + +static const u32 *maple_pmode_data; +static int maple_pmode_max; + +/* + * SCOM based frequency switching for 970FX rev3 + */ +static int maple_scom_switch_freq(int speed_mode) +{ + unsigned long flags; + int to; + + local_irq_save(flags); + + /* Clear PCR high */ + scom970_write(SCOM_PCR, 0); + /* Clear PCR low */ + scom970_write(SCOM_PCR, PCR_HILO_SELECT | 0); + /* Set PCR low */ + scom970_write(SCOM_PCR, PCR_HILO_SELECT | + maple_pmode_data[speed_mode]); + + /* Wait for completion */ + for (to = 0; to < 10; to++) { + unsigned long psr = scom970_read(SCOM_PSR); + + if ((psr & PSR_CMD_RECEIVED) == 0 && + (((psr >> PSR_CUR_SPEED_SHIFT) ^ + (maple_pmode_data[speed_mode] >> PCR_SPEED_SHIFT)) & 0x3) + == 0) + break; + if (psr & PSR_CMD_COMPLETED) + break; + udelay(100); + } + + local_irq_restore(flags); + + maple_pmode_cur = speed_mode; + ppc_proc_freq = maple_cpu_freqs[speed_mode].frequency * 1000ul; + + return 0; +} + +static int maple_scom_query_freq(void) +{ + unsigned long psr = scom970_read(SCOM_PSR); + int i; + + for (i = 0; i <= maple_pmode_max; i++) + if ((((psr >> PSR_CUR_SPEED_SHIFT) ^ + (maple_pmode_data[i] >> PCR_SPEED_SHIFT)) & 0x3) == 0) + break; + return i; +} + +/* + * Common interface to the cpufreq core + */ + +static int maple_cpufreq_verify(struct cpufreq_policy *policy) +{ + return cpufreq_frequency_table_verify(policy, maple_cpu_freqs); +} + +static int maple_cpufreq_target(struct cpufreq_policy *policy, + unsigned int target_freq, unsigned int relation) +{ + unsigned int newstate = 0; + struct cpufreq_freqs freqs; + int rc; + + if (cpufreq_frequency_table_target(policy, maple_cpu_freqs, + target_freq, relation, &newstate)) + return -EINVAL; + + if (maple_pmode_cur == newstate) + return 0; + + mutex_lock(&maple_switch_mutex); + + freqs.old = maple_cpu_freqs[maple_pmode_cur].frequency; + freqs.new = maple_cpu_freqs[newstate].frequency; + freqs.cpu = 0; + + cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); + rc = maple_scom_switch_freq(newstate); + cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); + + mutex_unlock(&maple_switch_mutex); + + return rc; +} + +static unsigned int maple_cpufreq_get_speed(unsigned int cpu) +{ + return maple_cpu_freqs[maple_pmode_cur].frequency; +} + +static int maple_cpufreq_cpu_init(struct cpufreq_policy *policy) +{ + policy->cpuinfo.transition_latency = 12000; + policy->cur = maple_cpu_freqs[maple_scom_query_freq()].frequency; + /* secondary CPUs are tied to the primary one by the + * cpufreq core if in the secondary policy we tell it that + * it actually must be one policy together with all others. */ + cpumask_copy(policy->cpus, cpu_online_mask); + cpufreq_frequency_table_get_attr(maple_cpu_freqs, policy->cpu); + + return cpufreq_frequency_table_cpuinfo(policy, + maple_cpu_freqs); +} + + +static struct cpufreq_driver maple_cpufreq_driver = { + .name = "maple", + .owner = THIS_MODULE, + .flags = CPUFREQ_CONST_LOOPS, + .init = maple_cpufreq_cpu_init, + .verify = maple_cpufreq_verify, + .target = maple_cpufreq_target, + .get = maple_cpufreq_get_speed, + .attr = maple_cpu_freqs_attr, +}; + +static int __init maple_cpufreq_init(void) +{ + struct device_node *cpus; + struct device_node *cpunode; + unsigned int psize; + unsigned long max_freq; + const u32 *valp; + u32 pvr_hi; + int rc = -ENODEV; + + /* + * Behave here like powermac driver which checks machine compatibility + * to ease merging of two drivers in future. + */ + if (!of_machine_is_compatible("Momentum,Maple") && + !of_machine_is_compatible("Momentum,Apache")) + return 0; + + cpus = of_find_node_by_path("/cpus"); + if (cpus == NULL) { + DBG("No /cpus node !\n"); + return -ENODEV; + } + + /* Get first CPU node */ + for (cpunode = NULL; + (cpunode = of_get_next_child(cpus, cpunode)) != NULL;) { + const u32 *reg = of_get_property(cpunode, "reg", NULL); + if (reg == NULL || (*reg) != 0) + continue; + if (!strcmp(cpunode->type, "cpu")) + break; + } + if (cpunode == NULL) { + printk(KERN_ERR "cpufreq: Can't find any CPU 0 node\n"); + goto bail_cpus; + } + + /* Check 970FX for now */ + /* we actually don't care on which CPU to access PVR */ + pvr_hi = PVR_VER(mfspr(SPRN_PVR)); + if (pvr_hi != 0x3c && pvr_hi != 0x44) { + printk(KERN_ERR "cpufreq: Unsupported CPU version (%x)\n", + pvr_hi); + goto bail_noprops; + } + + /* Look for the powertune data in the device-tree */ + /* + * On Maple this property is provided by PIBS in dual-processor config, + * not provided by PIBS in CPU0 config and also not provided by SLOF, + * so YMMV + */ + maple_pmode_data = of_get_property(cpunode, "power-mode-data", &psize); + if (!maple_pmode_data) { + DBG("No power-mode-data !\n"); + goto bail_noprops; + } + maple_pmode_max = psize / sizeof(u32) - 1; + + /* + * From what I see, clock-frequency is always the maximal frequency. + * The current driver can not slew sysclk yet, so we really only deal + * with powertune steps for now. We also only implement full freq and + * half freq in this version. So far, I haven't yet seen a machine + * supporting anything else. + */ + valp = of_get_property(cpunode, "clock-frequency", NULL); + if (!valp) + return -ENODEV; + max_freq = (*valp)/1000; + maple_cpu_freqs[0].frequency = max_freq; + maple_cpu_freqs[1].frequency = max_freq/2; + + /* Force apply current frequency to make sure everything is in + * sync (voltage is right for example). Firmware may leave us with + * a strange setting ... + */ + msleep(10); + maple_pmode_cur = -1; + maple_scom_switch_freq(maple_scom_query_freq()); + + printk(KERN_INFO "Registering Maple CPU frequency driver\n"); + printk(KERN_INFO "Low: %d Mhz, High: %d Mhz, Cur: %d MHz\n", + maple_cpu_freqs[1].frequency/1000, + maple_cpu_freqs[0].frequency/1000, + maple_cpu_freqs[maple_pmode_cur].frequency/1000); + + rc = cpufreq_register_driver(&maple_cpufreq_driver); + + of_node_put(cpunode); + of_node_put(cpus); + + return rc; + +bail_noprops: + of_node_put(cpunode); +bail_cpus: + of_node_put(cpus); + + return rc; +} + +module_init(maple_cpufreq_init); + + +MODULE_LICENSE("GPL"); diff --git a/drivers/of/platform.c b/drivers/of/platform.c index e75af391e286..ed5a6d3c26aa 100644 --- a/drivers/of/platform.c +++ b/drivers/of/platform.c @@ -162,7 +162,7 @@ struct platform_device *of_device_alloc(struct device_node *np, } dev->dev.of_node = of_node_get(np); -#if defined(CONFIG_PPC) || defined(CONFIG_MICROBLAZE) +#if defined(CONFIG_MICROBLAZE) dev->dev.dma_mask = &dev->archdata.dma_mask; #endif dev->dev.parent = parent; @@ -201,7 +201,7 @@ struct platform_device *of_platform_device_create_pdata( if (!dev) return NULL; -#if defined(CONFIG_PPC) || defined(CONFIG_MICROBLAZE) +#if defined(CONFIG_MICROBLAZE) dev->archdata.dma_mask = 0xffffffffUL; #endif dev->dev.coherent_dma_mask = DMA_BIT_MASK(32); diff --git a/drivers/tty/hvc/Kconfig b/drivers/tty/hvc/Kconfig index 6f2c9809f1fb..e371753ba921 100644 --- a/drivers/tty/hvc/Kconfig +++ b/drivers/tty/hvc/Kconfig @@ -19,6 +19,11 @@ config HVC_CONSOLE console. This driver allows each pSeries partition to have a console which is accessed via the HMC. +config HVC_OLD_HVSI + bool "Old driver for pSeries serial port (/dev/hvsi*)" + depends on HVC_CONSOLE + default n + config HVC_ISERIES bool "iSeries Hypervisor Virtual Console support" depends on PPC_ISERIES diff --git a/drivers/tty/hvc/Makefile b/drivers/tty/hvc/Makefile index 40a25d93fe52..e29205316376 100644 --- a/drivers/tty/hvc/Makefile +++ b/drivers/tty/hvc/Makefile @@ -1,4 +1,5 @@ -obj-$(CONFIG_HVC_CONSOLE) += hvc_vio.o hvsi.o +obj-$(CONFIG_HVC_CONSOLE) += hvc_vio.o hvsi_lib.o +obj-$(CONFIG_HVC_OLD_HVSI) += hvsi.o obj-$(CONFIG_HVC_ISERIES) += hvc_iseries.o obj-$(CONFIG_HVC_RTAS) += hvc_rtas.o obj-$(CONFIG_HVC_TILE) += hvc_tile.o diff --git a/drivers/tty/hvc/hvc_console.c b/drivers/tty/hvc/hvc_console.c index e9cba13ee800..e1aaf4f309b3 100644 --- a/drivers/tty/hvc/hvc_console.c +++ b/drivers/tty/hvc/hvc_console.c @@ -39,6 +39,7 @@ #include <linux/delay.h> #include <linux/freezer.h> #include <linux/slab.h> +#include <linux/serial_core.h> #include <asm/uaccess.h> @@ -163,8 +164,10 @@ static void hvc_console_print(struct console *co, const char *b, } else { r = cons_ops[index]->put_chars(vtermnos[index], c, i); if (r <= 0) { - /* throw away chars on error */ - i = 0; + /* throw away characters on error + * but spin in case of -EAGAIN */ + if (r != -EAGAIN) + i = 0; } else if (r > 0) { i -= r; if (i > 0) @@ -184,7 +187,7 @@ static struct tty_driver *hvc_console_device(struct console *c, int *index) } static int __init hvc_console_setup(struct console *co, char *options) -{ +{ if (co->index < 0 || co->index >= MAX_NR_HVC_CONSOLES) return -ENODEV; @@ -448,7 +451,7 @@ static int hvc_push(struct hvc_struct *hp) n = hp->ops->put_chars(hp->vtermno, hp->outbuf, hp->n_outbuf); if (n <= 0) { - if (n == 0) { + if (n == 0 || n == -EAGAIN) { hp->do_wakeup = 1; return 0; } @@ -745,6 +748,58 @@ static int khvcd(void *unused) return 0; } +static int hvc_tiocmget(struct tty_struct *tty) +{ + struct hvc_struct *hp = tty->driver_data; + + if (!hp || !hp->ops->tiocmget) + return -EINVAL; + return hp->ops->tiocmget(hp); +} + +static int hvc_tiocmset(struct tty_struct *tty, + unsigned int set, unsigned int clear) +{ + struct hvc_struct *hp = tty->driver_data; + + if (!hp || !hp->ops->tiocmset) + return -EINVAL; + return hp->ops->tiocmset(hp, set, clear); +} + +#ifdef CONFIG_CONSOLE_POLL +int hvc_poll_init(struct tty_driver *driver, int line, char *options) +{ + return 0; +} + +static int hvc_poll_get_char(struct tty_driver *driver, int line) +{ + struct tty_struct *tty = driver->ttys[0]; + struct hvc_struct *hp = tty->driver_data; + int n; + char ch; + + n = hp->ops->get_chars(hp->vtermno, &ch, 1); + + if (n == 0) + return NO_POLL_CHAR; + + return ch; +} + +static void hvc_poll_put_char(struct tty_driver *driver, int line, char ch) +{ + struct tty_struct *tty = driver->ttys[0]; + struct hvc_struct *hp = tty->driver_data; + int n; + + do { + n = hp->ops->put_chars(hp->vtermno, &ch, 1); + } while (n <= 0); +} +#endif + static const struct tty_operations hvc_ops = { .open = hvc_open, .close = hvc_close, @@ -753,6 +808,13 @@ static const struct tty_operations hvc_ops = { .unthrottle = hvc_unthrottle, .write_room = hvc_write_room, .chars_in_buffer = hvc_chars_in_buffer, + .tiocmget = hvc_tiocmget, + .tiocmset = hvc_tiocmset, +#ifdef CONFIG_CONSOLE_POLL + .poll_init = hvc_poll_init, + .poll_get_char = hvc_poll_get_char, + .poll_put_char = hvc_poll_put_char, +#endif }; struct hvc_struct *hvc_alloc(uint32_t vtermno, int data, diff --git a/drivers/tty/hvc/hvc_console.h b/drivers/tty/hvc/hvc_console.h index 54381eba4e4a..c335a1492a54 100644 --- a/drivers/tty/hvc/hvc_console.h +++ b/drivers/tty/hvc/hvc_console.h @@ -73,6 +73,10 @@ struct hv_ops { int (*notifier_add)(struct hvc_struct *hp, int irq); void (*notifier_del)(struct hvc_struct *hp, int irq); void (*notifier_hangup)(struct hvc_struct *hp, int irq); + + /* tiocmget/set implementation */ + int (*tiocmget)(struct hvc_struct *hp); + int (*tiocmset)(struct hvc_struct *hp, unsigned int set, unsigned int clear); }; /* Register a vterm and a slot index for use as a console (console_init) */ diff --git a/drivers/tty/hvc/hvc_vio.c b/drivers/tty/hvc/hvc_vio.c index e6eea1485244..130aace67f31 100644 --- a/drivers/tty/hvc/hvc_vio.c +++ b/drivers/tty/hvc/hvc_vio.c @@ -27,15 +27,27 @@ * You should have received a copy of the GNU General Public License * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * TODO: + * + * - handle error in sending hvsi protocol packets + * - retry nego on subsequent sends ? */ +#undef DEBUG + #include <linux/types.h> #include <linux/init.h> +#include <linux/delay.h> +#include <linux/slab.h> +#include <linux/console.h> #include <asm/hvconsole.h> #include <asm/vio.h> #include <asm/prom.h> #include <asm/firmware.h> +#include <asm/hvsi.h> +#include <asm/udbg.h> #include "hvc_console.h" @@ -43,59 +55,236 @@ static const char hvc_driver_name[] = "hvc_console"; static struct vio_device_id hvc_driver_table[] __devinitdata = { {"serial", "hvterm1"}, +#ifndef HVC_OLD_HVSI + {"serial", "hvterm-protocol"}, +#endif { "", "" } }; MODULE_DEVICE_TABLE(vio, hvc_driver_table); -static int filtered_get_chars(uint32_t vtermno, char *buf, int count) +typedef enum hv_protocol { + HV_PROTOCOL_RAW, + HV_PROTOCOL_HVSI +} hv_protocol_t; + +struct hvterm_priv { + u32 termno; /* HV term number */ + hv_protocol_t proto; /* Raw data or HVSI packets */ + struct hvsi_priv hvsi; /* HVSI specific data */ + spinlock_t buf_lock; + char buf[SIZE_VIO_GET_CHARS]; + int left; + int offset; +}; +static struct hvterm_priv *hvterm_privs[MAX_NR_HVC_CONSOLES]; +/* For early boot console */ +static struct hvterm_priv hvterm_priv0; + +static int hvterm_raw_get_chars(uint32_t vtermno, char *buf, int count) { - unsigned long got; - int i; + struct hvterm_priv *pv = hvterm_privs[vtermno]; + unsigned long i; + unsigned long flags; + int got; - /* - * Vio firmware will read up to SIZE_VIO_GET_CHARS at its own discretion - * so we play safe and avoid the situation where got > count which could - * overload the flip buffer. - */ - if (count < SIZE_VIO_GET_CHARS) - return -EAGAIN; + if (WARN_ON(!pv)) + return 0; - got = hvc_get_chars(vtermno, buf, count); + spin_lock_irqsave(&pv->buf_lock, flags); - /* - * Work around a HV bug where it gives us a null - * after every \r. -- paulus - */ - for (i = 1; i < got; ++i) { - if (buf[i] == 0 && buf[i-1] == '\r') { - --got; - if (i < got) - memmove(&buf[i], &buf[i+1], - got - i); + if (pv->left == 0) { + pv->offset = 0; + pv->left = hvc_get_chars(pv->termno, pv->buf, count); + + /* + * Work around a HV bug where it gives us a null + * after every \r. -- paulus + */ + for (i = 1; i < pv->left; ++i) { + if (pv->buf[i] == 0 && pv->buf[i-1] == '\r') { + --pv->left; + if (i < pv->left) { + memmove(&pv->buf[i], &pv->buf[i+1], + pv->left - i); + } + } } } + + got = min(count, pv->left); + memcpy(buf, &pv->buf[pv->offset], got); + pv->offset += got; + pv->left -= got; + + spin_unlock_irqrestore(&pv->buf_lock, flags); + return got; } -static const struct hv_ops hvc_get_put_ops = { - .get_chars = filtered_get_chars, - .put_chars = hvc_put_chars, +static int hvterm_raw_put_chars(uint32_t vtermno, const char *buf, int count) +{ + struct hvterm_priv *pv = hvterm_privs[vtermno]; + + if (WARN_ON(!pv)) + return 0; + + return hvc_put_chars(pv->termno, buf, count); +} + +static const struct hv_ops hvterm_raw_ops = { + .get_chars = hvterm_raw_get_chars, + .put_chars = hvterm_raw_put_chars, .notifier_add = notifier_add_irq, .notifier_del = notifier_del_irq, .notifier_hangup = notifier_hangup_irq, }; +static int hvterm_hvsi_get_chars(uint32_t vtermno, char *buf, int count) +{ + struct hvterm_priv *pv = hvterm_privs[vtermno]; + + if (WARN_ON(!pv)) + return 0; + + return hvsilib_get_chars(&pv->hvsi, buf, count); +} + +static int hvterm_hvsi_put_chars(uint32_t vtermno, const char *buf, int count) +{ + struct hvterm_priv *pv = hvterm_privs[vtermno]; + + if (WARN_ON(!pv)) + return 0; + + return hvsilib_put_chars(&pv->hvsi, buf, count); +} + +static int hvterm_hvsi_open(struct hvc_struct *hp, int data) +{ + struct hvterm_priv *pv = hvterm_privs[hp->vtermno]; + int rc; + + pr_devel("HVSI@%x: open !\n", pv->termno); + + rc = notifier_add_irq(hp, data); + if (rc) + return rc; + + return hvsilib_open(&pv->hvsi, hp); +} + +static void hvterm_hvsi_close(struct hvc_struct *hp, int data) +{ + struct hvterm_priv *pv = hvterm_privs[hp->vtermno]; + + pr_devel("HVSI@%x: do close !\n", pv->termno); + + hvsilib_close(&pv->hvsi, hp); + + notifier_del_irq(hp, data); +} + +void hvterm_hvsi_hangup(struct hvc_struct *hp, int data) +{ + struct hvterm_priv *pv = hvterm_privs[hp->vtermno]; + + pr_devel("HVSI@%x: do hangup !\n", pv->termno); + + hvsilib_close(&pv->hvsi, hp); + + notifier_hangup_irq(hp, data); +} + +static int hvterm_hvsi_tiocmget(struct hvc_struct *hp) +{ + struct hvterm_priv *pv = hvterm_privs[hp->vtermno]; + + if (!pv) + return -EINVAL; + return pv->hvsi.mctrl; +} + +static int hvterm_hvsi_tiocmset(struct hvc_struct *hp, unsigned int set, + unsigned int clear) +{ + struct hvterm_priv *pv = hvterm_privs[hp->vtermno]; + + pr_devel("HVSI@%x: Set modem control, set=%x,clr=%x\n", + pv->termno, set, clear); + + if (set & TIOCM_DTR) + hvsilib_write_mctrl(&pv->hvsi, 1); + else if (clear & TIOCM_DTR) + hvsilib_write_mctrl(&pv->hvsi, 0); + + return 0; +} + +static const struct hv_ops hvterm_hvsi_ops = { + .get_chars = hvterm_hvsi_get_chars, + .put_chars = hvterm_hvsi_put_chars, + .notifier_add = hvterm_hvsi_open, + .notifier_del = hvterm_hvsi_close, + .notifier_hangup = hvterm_hvsi_hangup, + .tiocmget = hvterm_hvsi_tiocmget, + .tiocmset = hvterm_hvsi_tiocmset, +}; + static int __devinit hvc_vio_probe(struct vio_dev *vdev, - const struct vio_device_id *id) + const struct vio_device_id *id) { + const struct hv_ops *ops; struct hvc_struct *hp; + struct hvterm_priv *pv; + hv_protocol_t proto; + int i, termno = -1; /* probed with invalid parameters. */ if (!vdev || !id) return -EPERM; - hp = hvc_alloc(vdev->unit_address, vdev->irq, &hvc_get_put_ops, - MAX_VIO_PUT_CHARS); + if (of_device_is_compatible(vdev->dev.of_node, "hvterm1")) { + proto = HV_PROTOCOL_RAW; + ops = &hvterm_raw_ops; + } else if (of_device_is_compatible(vdev->dev.of_node, "hvterm-protocol")) { + proto = HV_PROTOCOL_HVSI; + ops = &hvterm_hvsi_ops; + } else { + pr_err("hvc_vio: Unkown protocol for %s\n", vdev->dev.of_node->full_name); + return -ENXIO; + } + + pr_devel("hvc_vio_probe() device %s, using %s protocol\n", + vdev->dev.of_node->full_name, + proto == HV_PROTOCOL_RAW ? "raw" : "hvsi"); + + /* Is it our boot one ? */ + if (hvterm_privs[0] == &hvterm_priv0 && + vdev->unit_address == hvterm_priv0.termno) { + pv = hvterm_privs[0]; + termno = 0; + pr_devel("->boot console, using termno 0\n"); + } + /* nope, allocate a new one */ + else { + for (i = 0; i < MAX_NR_HVC_CONSOLES && termno < 0; i++) + if (!hvterm_privs[i]) + termno = i; + pr_devel("->non-boot console, using termno %d\n", termno); + if (termno < 0) + return -ENODEV; + pv = kzalloc(sizeof(struct hvterm_priv), GFP_KERNEL); + if (!pv) + return -ENOMEM; + pv->termno = vdev->unit_address; + pv->proto = proto; + spin_lock_init(&pv->buf_lock); + hvterm_privs[termno] = pv; + hvsilib_init(&pv->hvsi, hvc_get_chars, hvc_put_chars, + pv->termno, 0); + } + + hp = hvc_alloc(termno, vdev->irq, ops, MAX_VIO_PUT_CHARS); if (IS_ERR(hp)) return PTR_ERR(hp); dev_set_drvdata(&vdev->dev, hp); @@ -106,8 +295,16 @@ static int __devinit hvc_vio_probe(struct vio_dev *vdev, static int __devexit hvc_vio_remove(struct vio_dev *vdev) { struct hvc_struct *hp = dev_get_drvdata(&vdev->dev); + int rc, termno; - return hvc_remove(hp); + termno = hp->vtermno; + rc = hvc_remove(hp); + if (rc == 0) { + if (hvterm_privs[termno] != &hvterm_priv0) + kfree(hvterm_privs[termno]); + hvterm_privs[termno] = NULL; + } + return rc; } static struct vio_driver hvc_vio_driver = { @@ -140,34 +337,149 @@ static void __exit hvc_vio_exit(void) } module_exit(hvc_vio_exit); -/* the device tree order defines our numbering */ -static int hvc_find_vtys(void) +static void udbg_hvc_putc(char c) { - struct device_node *vty; - int num_found = 0; + int count = -1; - for (vty = of_find_node_by_name(NULL, "vty"); vty != NULL; - vty = of_find_node_by_name(vty, "vty")) { - const uint32_t *vtermno; + if (c == '\n') + udbg_hvc_putc('\r'); - /* We have statically defined space for only a certain number - * of console adapters. - */ - if (num_found >= MAX_NR_HVC_CONSOLES) { - of_node_put(vty); + do { + switch(hvterm_priv0.proto) { + case HV_PROTOCOL_RAW: + count = hvterm_raw_put_chars(0, &c, 1); + break; + case HV_PROTOCOL_HVSI: + count = hvterm_hvsi_put_chars(0, &c, 1); break; } + } while(count == 0); +} + +static int udbg_hvc_getc_poll(void) +{ + int rc = 0; + char c; - vtermno = of_get_property(vty, "reg", NULL); - if (!vtermno) - continue; + switch(hvterm_priv0.proto) { + case HV_PROTOCOL_RAW: + rc = hvterm_raw_get_chars(0, &c, 1); + break; + case HV_PROTOCOL_HVSI: + rc = hvterm_hvsi_get_chars(0, &c, 1); + break; + } + if (!rc) + return -1; + return c; +} - if (of_device_is_compatible(vty, "hvterm1")) { - hvc_instantiate(*vtermno, num_found, &hvc_get_put_ops); - ++num_found; +static int udbg_hvc_getc(void) +{ + int ch; + for (;;) { + ch = udbg_hvc_getc_poll(); + if (ch == -1) { + /* This shouldn't be needed...but... */ + volatile unsigned long delay; + for (delay=0; delay < 2000000; delay++) + ; + } else { + return ch; } } +} + +void __init hvc_vio_init_early(void) +{ + struct device_node *stdout_node; + const u32 *termno; + const char *name; + const struct hv_ops *ops; + + /* find the boot console from /chosen/stdout */ + if (!of_chosen) + return; + name = of_get_property(of_chosen, "linux,stdout-path", NULL); + if (name == NULL) + return; + stdout_node = of_find_node_by_path(name); + if (!stdout_node) + return; + name = of_get_property(stdout_node, "name", NULL); + if (!name) { + printk(KERN_WARNING "stdout node missing 'name' property!\n"); + goto out; + } + + /* Check if it's a virtual terminal */ + if (strncmp(name, "vty", 3) != 0) + goto out; + termno = of_get_property(stdout_node, "reg", NULL); + if (termno == NULL) + goto out; + hvterm_priv0.termno = *termno; + spin_lock_init(&hvterm_priv0.buf_lock); + hvterm_privs[0] = &hvterm_priv0; + + /* Check the protocol */ + if (of_device_is_compatible(stdout_node, "hvterm1")) { + hvterm_priv0.proto = HV_PROTOCOL_RAW; + ops = &hvterm_raw_ops; + } + else if (of_device_is_compatible(stdout_node, "hvterm-protocol")) { + hvterm_priv0.proto = HV_PROTOCOL_HVSI; + ops = &hvterm_hvsi_ops; + hvsilib_init(&hvterm_priv0.hvsi, hvc_get_chars, hvc_put_chars, + hvterm_priv0.termno, 1); + /* HVSI, perform the handshake now */ + hvsilib_establish(&hvterm_priv0.hvsi); + } else + goto out; + udbg_putc = udbg_hvc_putc; + udbg_getc = udbg_hvc_getc; + udbg_getc_poll = udbg_hvc_getc_poll; +#ifdef HVC_OLD_HVSI + /* When using the old HVSI driver don't register the HVC + * backend for HVSI, only do udbg + */ + if (hvterm_priv0.proto == HV_PROTOCOL_HVSI) + goto out; +#endif + add_preferred_console("hvc", 0, NULL); + hvc_instantiate(0, 0, ops); +out: + of_node_put(stdout_node); +} - return num_found; +/* call this from early_init() for a working debug console on + * vterm capable LPAR machines + */ +#ifdef CONFIG_PPC_EARLY_DEBUG_LPAR +void __init udbg_init_debug_lpar(void) +{ + hvterm_privs[0] = &hvterm_priv0; + hvterm_priv0.termno = 0; + hvterm_priv0.proto = HV_PROTOCOL_RAW; + spin_lock_init(&hvterm_priv0.buf_lock); + udbg_putc = udbg_hvc_putc; + udbg_getc = udbg_hvc_getc; + udbg_getc_poll = udbg_hvc_getc_poll; +} +#endif /* CONFIG_PPC_EARLY_DEBUG_LPAR */ + +#ifdef CONFIG_PPC_EARLY_DEBUG_LPAR_HVSI +void __init udbg_init_debug_lpar_hvsi(void) +{ + hvterm_privs[0] = &hvterm_priv0; + hvterm_priv0.termno = CONFIG_PPC_EARLY_DEBUG_HVSI_VTERMNO; + hvterm_priv0.proto = HV_PROTOCOL_HVSI; + spin_lock_init(&hvterm_priv0.buf_lock); + udbg_putc = udbg_hvc_putc; + udbg_getc = udbg_hvc_getc; + udbg_getc_poll = udbg_hvc_getc_poll; + hvsilib_init(&hvterm_priv0.hvsi, hvc_get_chars, hvc_put_chars, + hvterm_priv0.termno, 1); + hvsilib_establish(&hvterm_priv0.hvsi); } -console_initcall(hvc_find_vtys); +#endif /* CONFIG_PPC_EARLY_DEBUG_LPAR_HVSI */ diff --git a/drivers/tty/hvc/hvsi.c b/drivers/tty/hvc/hvsi.c index 8a8d6373f164..c94e2f5853d8 100644 --- a/drivers/tty/hvc/hvsi.c +++ b/drivers/tty/hvc/hvsi.c @@ -49,6 +49,7 @@ #include <asm/uaccess.h> #include <asm/vio.h> #include <asm/param.h> +#include <asm/hvsi.h> #define HVSI_MAJOR 229 #define HVSI_MINOR 128 @@ -109,68 +110,6 @@ enum HVSI_PROTOCOL_STATE { }; #define HVSI_CONSOLE 0x1 -#define VS_DATA_PACKET_HEADER 0xff -#define VS_CONTROL_PACKET_HEADER 0xfe -#define VS_QUERY_PACKET_HEADER 0xfd -#define VS_QUERY_RESPONSE_PACKET_HEADER 0xfc - -/* control verbs */ -#define VSV_SET_MODEM_CTL 1 /* to service processor only */ -#define VSV_MODEM_CTL_UPDATE 2 /* from service processor only */ -#define VSV_CLOSE_PROTOCOL 3 - -/* query verbs */ -#define VSV_SEND_VERSION_NUMBER 1 -#define VSV_SEND_MODEM_CTL_STATUS 2 - -/* yes, these masks are not consecutive. */ -#define HVSI_TSDTR 0x01 -#define HVSI_TSCD 0x20 - -struct hvsi_header { - uint8_t type; - uint8_t len; - uint16_t seqno; -} __attribute__((packed)); - -struct hvsi_data { - uint8_t type; - uint8_t len; - uint16_t seqno; - uint8_t data[HVSI_MAX_OUTGOING_DATA]; -} __attribute__((packed)); - -struct hvsi_control { - uint8_t type; - uint8_t len; - uint16_t seqno; - uint16_t verb; - /* optional depending on verb: */ - uint32_t word; - uint32_t mask; -} __attribute__((packed)); - -struct hvsi_query { - uint8_t type; - uint8_t len; - uint16_t seqno; - uint16_t verb; -} __attribute__((packed)); - -struct hvsi_query_response { - uint8_t type; - uint8_t len; - uint16_t seqno; - uint16_t verb; - uint16_t query_seqno; - union { - uint8_t version; - uint32_t mctrl_word; - } u; -} __attribute__((packed)); - - - static inline int is_console(struct hvsi_struct *hp) { return hp->flags & HVSI_CONSOLE; @@ -356,18 +295,18 @@ static int hvsi_version_respond(struct hvsi_struct *hp, uint16_t query_seqno) struct hvsi_query_response packet __ALIGNED__; int wrote; - packet.type = VS_QUERY_RESPONSE_PACKET_HEADER; - packet.len = sizeof(struct hvsi_query_response); - packet.seqno = atomic_inc_return(&hp->seqno); + packet.hdr.type = VS_QUERY_RESPONSE_PACKET_HEADER; + packet.hdr.len = sizeof(struct hvsi_query_response); + packet.hdr.seqno = atomic_inc_return(&hp->seqno); packet.verb = VSV_SEND_VERSION_NUMBER; packet.u.version = HVSI_VERSION; packet.query_seqno = query_seqno+1; - pr_debug("%s: sending %i bytes\n", __func__, packet.len); - dbg_dump_hex((uint8_t*)&packet, packet.len); + pr_debug("%s: sending %i bytes\n", __func__, packet.hdr.len); + dbg_dump_hex((uint8_t*)&packet, packet.hdr.len); - wrote = hvc_put_chars(hp->vtermno, (char *)&packet, packet.len); - if (wrote != packet.len) { + wrote = hvc_put_chars(hp->vtermno, (char *)&packet, packet.hdr.len); + if (wrote != packet.hdr.len) { printk(KERN_ERR "hvsi%i: couldn't send query response!\n", hp->index); return -EIO; @@ -382,7 +321,7 @@ static void hvsi_recv_query(struct hvsi_struct *hp, uint8_t *packet) switch (hp->state) { case HVSI_WAIT_FOR_VER_QUERY: - hvsi_version_respond(hp, query->seqno); + hvsi_version_respond(hp, query->hdr.seqno); __set_state(hp, HVSI_OPEN); break; default: @@ -640,16 +579,16 @@ static int hvsi_query(struct hvsi_struct *hp, uint16_t verb) struct hvsi_query packet __ALIGNED__; int wrote; - packet.type = VS_QUERY_PACKET_HEADER; - packet.len = sizeof(struct hvsi_query); - packet.seqno = atomic_inc_return(&hp->seqno); + packet.hdr.type = VS_QUERY_PACKET_HEADER; + packet.hdr.len = sizeof(struct hvsi_query); + packet.hdr.seqno = atomic_inc_return(&hp->seqno); packet.verb = verb; - pr_debug("%s: sending %i bytes\n", __func__, packet.len); - dbg_dump_hex((uint8_t*)&packet, packet.len); + pr_debug("%s: sending %i bytes\n", __func__, packet.hdr.len); + dbg_dump_hex((uint8_t*)&packet, packet.hdr.len); - wrote = hvc_put_chars(hp->vtermno, (char *)&packet, packet.len); - if (wrote != packet.len) { + wrote = hvc_put_chars(hp->vtermno, (char *)&packet, packet.hdr.len); + if (wrote != packet.hdr.len) { printk(KERN_ERR "hvsi%i: couldn't send query (%i)!\n", hp->index, wrote); return -EIO; @@ -683,20 +622,20 @@ static int hvsi_set_mctrl(struct hvsi_struct *hp, uint16_t mctrl) struct hvsi_control packet __ALIGNED__; int wrote; - packet.type = VS_CONTROL_PACKET_HEADER, - packet.seqno = atomic_inc_return(&hp->seqno); - packet.len = sizeof(struct hvsi_control); + packet.hdr.type = VS_CONTROL_PACKET_HEADER, + packet.hdr.seqno = atomic_inc_return(&hp->seqno); + packet.hdr.len = sizeof(struct hvsi_control); packet.verb = VSV_SET_MODEM_CTL; packet.mask = HVSI_TSDTR; if (mctrl & TIOCM_DTR) packet.word = HVSI_TSDTR; - pr_debug("%s: sending %i bytes\n", __func__, packet.len); - dbg_dump_hex((uint8_t*)&packet, packet.len); + pr_debug("%s: sending %i bytes\n", __func__, packet.hdr.len); + dbg_dump_hex((uint8_t*)&packet, packet.hdr.len); - wrote = hvc_put_chars(hp->vtermno, (char *)&packet, packet.len); - if (wrote != packet.len) { + wrote = hvc_put_chars(hp->vtermno, (char *)&packet, packet.hdr.len); + if (wrote != packet.hdr.len) { printk(KERN_ERR "hvsi%i: couldn't set DTR!\n", hp->index); return -EIO; } @@ -766,13 +705,13 @@ static int hvsi_put_chars(struct hvsi_struct *hp, const char *buf, int count) BUG_ON(count > HVSI_MAX_OUTGOING_DATA); - packet.type = VS_DATA_PACKET_HEADER; - packet.seqno = atomic_inc_return(&hp->seqno); - packet.len = count + sizeof(struct hvsi_header); + packet.hdr.type = VS_DATA_PACKET_HEADER; + packet.hdr.seqno = atomic_inc_return(&hp->seqno); + packet.hdr.len = count + sizeof(struct hvsi_header); memcpy(&packet.data, buf, count); - ret = hvc_put_chars(hp->vtermno, (char *)&packet, packet.len); - if (ret == packet.len) { + ret = hvc_put_chars(hp->vtermno, (char *)&packet, packet.hdr.len); + if (ret == packet.hdr.len) { /* return the number of chars written, not the packet length */ return count; } @@ -783,15 +722,15 @@ static void hvsi_close_protocol(struct hvsi_struct *hp) { struct hvsi_control packet __ALIGNED__; - packet.type = VS_CONTROL_PACKET_HEADER; - packet.seqno = atomic_inc_return(&hp->seqno); - packet.len = 6; + packet.hdr.type = VS_CONTROL_PACKET_HEADER; + packet.hdr.seqno = atomic_inc_return(&hp->seqno); + packet.hdr.len = 6; packet.verb = VSV_CLOSE_PROTOCOL; - pr_debug("%s: sending %i bytes\n", __func__, packet.len); - dbg_dump_hex((uint8_t*)&packet, packet.len); + pr_debug("%s: sending %i bytes\n", __func__, packet.hdr.len); + dbg_dump_hex((uint8_t*)&packet, packet.hdr.len); - hvc_put_chars(hp->vtermno, (char *)&packet, packet.len); + hvc_put_chars(hp->vtermno, (char *)&packet, packet.hdr.len); } static int hvsi_open(struct tty_struct *tty, struct file *filp) diff --git a/drivers/tty/hvc/hvsi_lib.c b/drivers/tty/hvc/hvsi_lib.c new file mode 100644 index 000000000000..bd9b09827b24 --- /dev/null +++ b/drivers/tty/hvc/hvsi_lib.c @@ -0,0 +1,426 @@ +#include <linux/types.h> +#include <linux/init.h> +#include <linux/delay.h> +#include <linux/slab.h> +#include <linux/console.h> +#include <asm/hvsi.h> + +#include "hvc_console.h" + +static int hvsi_send_packet(struct hvsi_priv *pv, struct hvsi_header *packet) +{ + packet->seqno = atomic_inc_return(&pv->seqno); + + /* Assumes that always succeeds, works in practice */ + return pv->put_chars(pv->termno, (char *)packet, packet->len); +} + +static void hvsi_start_handshake(struct hvsi_priv *pv) +{ + struct hvsi_query q; + + /* Reset state */ + pv->established = 0; + atomic_set(&pv->seqno, 0); + + pr_devel("HVSI@%x: Handshaking started\n", pv->termno); + + /* Send version query */ + q.hdr.type = VS_QUERY_PACKET_HEADER; + q.hdr.len = sizeof(struct hvsi_query); + q.verb = VSV_SEND_VERSION_NUMBER; + hvsi_send_packet(pv, &q.hdr); +} + +static int hvsi_send_close(struct hvsi_priv *pv) +{ + struct hvsi_control ctrl; + + pv->established = 0; + + ctrl.hdr.type = VS_CONTROL_PACKET_HEADER; + ctrl.hdr.len = sizeof(struct hvsi_control); + ctrl.verb = VSV_CLOSE_PROTOCOL; + return hvsi_send_packet(pv, &ctrl.hdr); +} + +static void hvsi_cd_change(struct hvsi_priv *pv, int cd) +{ + if (cd) + pv->mctrl |= TIOCM_CD; + else { + pv->mctrl &= ~TIOCM_CD; + + /* We copy the existing hvsi driver semantics + * here which are to trigger a hangup when + * we get a carrier loss. + * Closing our connection to the server will + * do just that. + */ + if (!pv->is_console && pv->opened) { + pr_devel("HVSI@%x Carrier lost, hanging up !\n", + pv->termno); + hvsi_send_close(pv); + } + } +} + +static void hvsi_got_control(struct hvsi_priv *pv) +{ + struct hvsi_control *pkt = (struct hvsi_control *)pv->inbuf; + + switch (pkt->verb) { + case VSV_CLOSE_PROTOCOL: + /* We restart the handshaking */ + hvsi_start_handshake(pv); + break; + case VSV_MODEM_CTL_UPDATE: + /* Transition of carrier detect */ + hvsi_cd_change(pv, pkt->word & HVSI_TSCD); + break; + } +} + +static void hvsi_got_query(struct hvsi_priv *pv) +{ + struct hvsi_query *pkt = (struct hvsi_query *)pv->inbuf; + struct hvsi_query_response r; + + /* We only handle version queries */ + if (pkt->verb != VSV_SEND_VERSION_NUMBER) + return; + + pr_devel("HVSI@%x: Got version query, sending response...\n", + pv->termno); + + /* Send version response */ + r.hdr.type = VS_QUERY_RESPONSE_PACKET_HEADER; + r.hdr.len = sizeof(struct hvsi_query_response); + r.verb = VSV_SEND_VERSION_NUMBER; + r.u.version = HVSI_VERSION; + r.query_seqno = pkt->hdr.seqno; + hvsi_send_packet(pv, &r.hdr); + + /* Assume protocol is open now */ + pv->established = 1; +} + +static void hvsi_got_response(struct hvsi_priv *pv) +{ + struct hvsi_query_response *r = + (struct hvsi_query_response *)pv->inbuf; + + switch(r->verb) { + case VSV_SEND_MODEM_CTL_STATUS: + hvsi_cd_change(pv, r->u.mctrl_word & HVSI_TSCD); + pv->mctrl_update = 1; + break; + } +} + +static int hvsi_check_packet(struct hvsi_priv *pv) +{ + u8 len, type; + + /* Check header validity. If it's invalid, we ditch + * the whole buffer and hope we eventually resync + */ + if (pv->inbuf[0] < 0xfc) { + pv->inbuf_len = pv->inbuf_pktlen = 0; + return 0; + } + type = pv->inbuf[0]; + len = pv->inbuf[1]; + + /* Packet incomplete ? */ + if (pv->inbuf_len < len) + return 0; + + pr_devel("HVSI@%x: Got packet type %x len %d bytes:\n", + pv->termno, type, len); + + /* We have a packet, yay ! Handle it */ + switch(type) { + case VS_DATA_PACKET_HEADER: + pv->inbuf_pktlen = len - 4; + pv->inbuf_cur = 4; + return 1; + case VS_CONTROL_PACKET_HEADER: + hvsi_got_control(pv); + break; + case VS_QUERY_PACKET_HEADER: + hvsi_got_query(pv); + break; + case VS_QUERY_RESPONSE_PACKET_HEADER: + hvsi_got_response(pv); + break; + } + + /* Swallow packet and retry */ + pv->inbuf_len -= len; + memmove(pv->inbuf, &pv->inbuf[len], pv->inbuf_len); + return 1; +} + +static int hvsi_get_packet(struct hvsi_priv *pv) +{ + /* If we have room in the buffer, ask HV for more */ + if (pv->inbuf_len < HVSI_INBUF_SIZE) + pv->inbuf_len += pv->get_chars(pv->termno, + &pv->inbuf[pv->inbuf_len], + HVSI_INBUF_SIZE - pv->inbuf_len); + /* + * If we have at least 4 bytes in the buffer, check for + * a full packet and retry + */ + if (pv->inbuf_len >= 4) + return hvsi_check_packet(pv); + return 0; +} + +int hvsilib_get_chars(struct hvsi_priv *pv, char *buf, int count) +{ + unsigned int tries, read = 0; + + if (WARN_ON(!pv)) + return 0; + + /* If we aren't open, don't do anything in order to avoid races + * with connection establishment. The hvc core will call this + * before we have returned from notifier_add(), and we need to + * avoid multiple users playing with the receive buffer + */ + if (!pv->opened) + return 0; + + /* We try twice, once with what data we have and once more + * after we try to fetch some more from the hypervisor + */ + for (tries = 1; count && tries < 2; tries++) { + /* Consume existing data packet */ + if (pv->inbuf_pktlen) { + unsigned int l = min(count, (int)pv->inbuf_pktlen); + memcpy(&buf[read], &pv->inbuf[pv->inbuf_cur], l); + pv->inbuf_cur += l; + pv->inbuf_pktlen -= l; + count -= l; + read += l; + } + if (count == 0) + break; + + /* Data packet fully consumed, move down remaning data */ + if (pv->inbuf_cur) { + pv->inbuf_len -= pv->inbuf_cur; + memmove(pv->inbuf, &pv->inbuf[pv->inbuf_cur], + pv->inbuf_len); + pv->inbuf_cur = 0; + } + + /* Try to get another packet */ + if (hvsi_get_packet(pv)) + tries--; + } + if (!pv->established) { + pr_devel("HVSI@%x: returning -EPIPE\n", pv->termno); + return -EPIPE; + } + return read; +} + +int hvsilib_put_chars(struct hvsi_priv *pv, const char *buf, int count) +{ + struct hvsi_data dp; + int rc, adjcount = min(count, HVSI_MAX_OUTGOING_DATA); + + if (WARN_ON(!pv)) + return 0; + + dp.hdr.type = VS_DATA_PACKET_HEADER; + dp.hdr.len = adjcount + sizeof(struct hvsi_header); + memcpy(dp.data, buf, adjcount); + rc = hvsi_send_packet(pv, &dp.hdr); + if (rc <= 0) + return rc; + return adjcount; +} + +static void maybe_msleep(unsigned long ms) +{ + /* During early boot, IRQs are disabled, use mdelay */ + if (irqs_disabled()) + mdelay(ms); + else + msleep(ms); +} + +int hvsilib_read_mctrl(struct hvsi_priv *pv) +{ + struct hvsi_query q; + int rc, timeout; + + pr_devel("HVSI@%x: Querying modem control status...\n", + pv->termno); + + pv->mctrl_update = 0; + q.hdr.type = VS_QUERY_PACKET_HEADER; + q.hdr.len = sizeof(struct hvsi_query); + q.hdr.seqno = atomic_inc_return(&pv->seqno); + q.verb = VSV_SEND_MODEM_CTL_STATUS; + rc = hvsi_send_packet(pv, &q.hdr); + if (rc <= 0) { + pr_devel("HVSI@%x: Error %d...\n", pv->termno, rc); + return rc; + } + + /* Try for up to 200ms */ + for (timeout = 0; timeout < 20; timeout++) { + if (!pv->established) + return -ENXIO; + if (pv->mctrl_update) + return 0; + if (!hvsi_get_packet(pv)) + maybe_msleep(10); + } + return -EIO; +} + +int hvsilib_write_mctrl(struct hvsi_priv *pv, int dtr) +{ + struct hvsi_control ctrl; + unsigned short mctrl; + + mctrl = pv->mctrl; + if (dtr) + mctrl |= TIOCM_DTR; + else + mctrl &= ~TIOCM_DTR; + if (mctrl == pv->mctrl) + return 0; + pv->mctrl = mctrl; + + pr_devel("HVSI@%x: %s DTR...\n", pv->termno, + dtr ? "Setting" : "Clearing"); + + ctrl.hdr.type = VS_CONTROL_PACKET_HEADER, + ctrl.hdr.len = sizeof(struct hvsi_control); + ctrl.verb = VSV_SET_MODEM_CTL; + ctrl.mask = HVSI_TSDTR; + ctrl.word = dtr ? HVSI_TSDTR : 0; + return hvsi_send_packet(pv, &ctrl.hdr); +} + +void hvsilib_establish(struct hvsi_priv *pv) +{ + int timeout; + + pr_devel("HVSI@%x: Establishing...\n", pv->termno); + + /* Try for up to 200ms, there can be a packet to + * start the process waiting for us... + */ + for (timeout = 0; timeout < 20; timeout++) { + if (pv->established) + goto established; + if (!hvsi_get_packet(pv)) + maybe_msleep(10); + } + + /* Failed, send a close connection packet just + * in case + */ + pr_devel("HVSI@%x: ... sending close\n", pv->termno); + + hvsi_send_close(pv); + + /* Then restart handshake */ + + pr_devel("HVSI@%x: ... restarting handshake\n", pv->termno); + + hvsi_start_handshake(pv); + + pr_devel("HVSI@%x: ... waiting handshake\n", pv->termno); + + /* Try for up to 200s */ + for (timeout = 0; timeout < 20; timeout++) { + if (pv->established) + goto established; + if (!hvsi_get_packet(pv)) + maybe_msleep(10); + } + + if (!pv->established) { + pr_devel("HVSI@%x: Timeout handshaking, giving up !\n", + pv->termno); + return; + } + established: + /* Query modem control lines */ + + pr_devel("HVSI@%x: ... established, reading mctrl\n", pv->termno); + + hvsilib_read_mctrl(pv); + + /* Set our own DTR */ + + pr_devel("HVSI@%x: ... setting mctrl\n", pv->termno); + + hvsilib_write_mctrl(pv, 1); + + /* Set the opened flag so reads are allowed */ + wmb(); + pv->opened = 1; +} + +int hvsilib_open(struct hvsi_priv *pv, struct hvc_struct *hp) +{ + pr_devel("HVSI@%x: open !\n", pv->termno); + + /* Keep track of the tty data structure */ + pv->tty = tty_kref_get(hp->tty); + + hvsilib_establish(pv); + + return 0; +} + +void hvsilib_close(struct hvsi_priv *pv, struct hvc_struct *hp) +{ + unsigned long flags; + + pr_devel("HVSI@%x: close !\n", pv->termno); + + if (!pv->is_console) { + pr_devel("HVSI@%x: Not a console, tearing down\n", + pv->termno); + + /* Clear opened, synchronize with khvcd */ + spin_lock_irqsave(&hp->lock, flags); + pv->opened = 0; + spin_unlock_irqrestore(&hp->lock, flags); + + /* Clear our own DTR */ + if (!pv->tty || (pv->tty->termios->c_cflag & HUPCL)) + hvsilib_write_mctrl(pv, 0); + + /* Tear down the connection */ + hvsi_send_close(pv); + } + + if (pv->tty) + tty_kref_put(pv->tty); + pv->tty = NULL; +} + +void hvsilib_init(struct hvsi_priv *pv, + int (*get_chars)(uint32_t termno, char *buf, int count), + int (*put_chars)(uint32_t termno, const char *buf, + int count), + int termno, int is_console) +{ + memset(pv, 0, sizeof(*pv)); + pv->get_chars = get_chars; + pv->put_chars = put_chars; + pv->termno = termno; + pv->is_console = is_console; +} diff --git a/drivers/virt/Kconfig b/drivers/virt/Kconfig new file mode 100644 index 000000000000..2dcdbc9364d8 --- /dev/null +++ b/drivers/virt/Kconfig @@ -0,0 +1,32 @@ +# +# Virtualization support drivers +# + +menuconfig VIRT_DRIVERS + bool "Virtualization drivers" + ---help--- + Say Y here to get to see options for device drivers that support + virtualization environments. + + If you say N, all options in this submenu will be skipped and disabled. + +if VIRT_DRIVERS + +config FSL_HV_MANAGER + tristate "Freescale hypervisor management driver" + depends on FSL_SOC + help + The Freescale hypervisor management driver provides several services + to drivers and applications related to the Freescale hypervisor: + + 1) An ioctl interface for querying and managing partitions. + + 2) A file interface to reading incoming doorbells. + + 3) An interrupt handler for shutting down the partition upon + receiving the shutdown doorbell from a manager partition. + + 4) A kernel interface for receiving callbacks when a managed + partition shuts down. + +endif diff --git a/drivers/virt/Makefile b/drivers/virt/Makefile new file mode 100644 index 000000000000..c47f04dd343b --- /dev/null +++ b/drivers/virt/Makefile @@ -0,0 +1,5 @@ +# +# Makefile for drivers that support virtualization +# + +obj-$(CONFIG_FSL_HV_MANAGER) += fsl_hypervisor.o diff --git a/drivers/virt/fsl_hypervisor.c b/drivers/virt/fsl_hypervisor.c new file mode 100644 index 000000000000..3d9162151fd2 --- /dev/null +++ b/drivers/virt/fsl_hypervisor.c @@ -0,0 +1,938 @@ +/* + * Freescale Hypervisor Management Driver + + * Copyright (C) 2008-2011 Freescale Semiconductor, Inc. + * Author: Timur Tabi <timur@freescale.com> + * + * This file is licensed under the terms of the GNU General Public License + * version 2. This program is licensed "as is" without any warranty of any + * kind, whether express or implied. + * + * The Freescale hypervisor management driver provides several services to + * drivers and applications related to the Freescale hypervisor: + * + * 1. An ioctl interface for querying and managing partitions. + * + * 2. A file interface to reading incoming doorbells. + * + * 3. An interrupt handler for shutting down the partition upon receiving the + * shutdown doorbell from a manager partition. + * + * 4. A kernel interface for receiving callbacks when a managed partition + * shuts down. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/types.h> +#include <linux/err.h> +#include <linux/fs.h> +#include <linux/miscdevice.h> +#include <linux/mm.h> +#include <linux/pagemap.h> +#include <linux/slab.h> +#include <linux/poll.h> +#include <linux/of.h> +#include <linux/reboot.h> +#include <linux/uaccess.h> +#include <linux/notifier.h> +#include <linux/interrupt.h> + +#include <linux/io.h> +#include <asm/fsl_hcalls.h> + +#include <linux/fsl_hypervisor.h> + +static BLOCKING_NOTIFIER_HEAD(failover_subscribers); + +/* + * Ioctl interface for FSL_HV_IOCTL_PARTITION_RESTART + * + * Restart a running partition + */ +static long ioctl_restart(struct fsl_hv_ioctl_restart __user *p) +{ + struct fsl_hv_ioctl_restart param; + + /* Get the parameters from the user */ + if (copy_from_user(¶m, p, sizeof(struct fsl_hv_ioctl_restart))) + return -EFAULT; + + param.ret = fh_partition_restart(param.partition); + + if (copy_to_user(&p->ret, ¶m.ret, sizeof(__u32))) + return -EFAULT; + + return 0; +} + +/* + * Ioctl interface for FSL_HV_IOCTL_PARTITION_STATUS + * + * Query the status of a partition + */ +static long ioctl_status(struct fsl_hv_ioctl_status __user *p) +{ + struct fsl_hv_ioctl_status param; + u32 status; + + /* Get the parameters from the user */ + if (copy_from_user(¶m, p, sizeof(struct fsl_hv_ioctl_status))) + return -EFAULT; + + param.ret = fh_partition_get_status(param.partition, &status); + if (!param.ret) + param.status = status; + + if (copy_to_user(p, ¶m, sizeof(struct fsl_hv_ioctl_status))) + return -EFAULT; + + return 0; +} + +/* + * Ioctl interface for FSL_HV_IOCTL_PARTITION_START + * + * Start a stopped partition. + */ +static long ioctl_start(struct fsl_hv_ioctl_start __user *p) +{ + struct fsl_hv_ioctl_start param; + + /* Get the parameters from the user */ + if (copy_from_user(¶m, p, sizeof(struct fsl_hv_ioctl_start))) + return -EFAULT; + + param.ret = fh_partition_start(param.partition, param.entry_point, + param.load); + + if (copy_to_user(&p->ret, ¶m.ret, sizeof(__u32))) + return -EFAULT; + + return 0; +} + +/* + * Ioctl interface for FSL_HV_IOCTL_PARTITION_STOP + * + * Stop a running partition + */ +static long ioctl_stop(struct fsl_hv_ioctl_stop __user *p) +{ + struct fsl_hv_ioctl_stop param; + + /* Get the parameters from the user */ + if (copy_from_user(¶m, p, sizeof(struct fsl_hv_ioctl_stop))) + return -EFAULT; + + param.ret = fh_partition_stop(param.partition); + + if (copy_to_user(&p->ret, ¶m.ret, sizeof(__u32))) + return -EFAULT; + + return 0; +} + +/* + * Ioctl interface for FSL_HV_IOCTL_MEMCPY + * + * The FH_MEMCPY hypercall takes an array of address/address/size structures + * to represent the data being copied. As a convenience to the user, this + * ioctl takes a user-create buffer and a pointer to a guest physically + * contiguous buffer in the remote partition, and creates the + * address/address/size array for the hypercall. + */ +static long ioctl_memcpy(struct fsl_hv_ioctl_memcpy __user *p) +{ + struct fsl_hv_ioctl_memcpy param; + + struct page **pages = NULL; + void *sg_list_unaligned = NULL; + struct fh_sg_list *sg_list = NULL; + + unsigned int num_pages; + unsigned long lb_offset; /* Offset within a page of the local buffer */ + + unsigned int i; + long ret = 0; + int num_pinned; /* return value from get_user_pages() */ + phys_addr_t remote_paddr; /* The next address in the remote buffer */ + uint32_t count; /* The number of bytes left to copy */ + + /* Get the parameters from the user */ + if (copy_from_user(¶m, p, sizeof(struct fsl_hv_ioctl_memcpy))) + return -EFAULT; + + /* + * One partition must be local, the other must be remote. In other + * words, if source and target are both -1, or are both not -1, then + * return an error. + */ + if ((param.source == -1) == (param.target == -1)) + return -EINVAL; + + /* + * The array of pages returned by get_user_pages() covers only + * page-aligned memory. Since the user buffer is probably not + * page-aligned, we need to handle the discrepancy. + * + * We calculate the offset within a page of the S/G list, and make + * adjustments accordingly. This will result in a page list that looks + * like this: + * + * ---- <-- first page starts before the buffer + * | | + * |////|-> ---- + * |////| | | + * ---- | | + * | | + * ---- | | + * |////| | | + * |////| | | + * |////| | | + * ---- | | + * | | + * ---- | | + * |////| | | + * |////| | | + * |////| | | + * ---- | | + * | | + * ---- | | + * |////| | | + * |////|-> ---- + * | | <-- last page ends after the buffer + * ---- + * + * The distance between the start of the first page and the start of the + * buffer is lb_offset. The hashed (///) areas are the parts of the + * page list that contain the actual buffer. + * + * The advantage of this approach is that the number of pages is + * equal to the number of entries in the S/G list that we give to the + * hypervisor. + */ + lb_offset = param.local_vaddr & (PAGE_SIZE - 1); + num_pages = (param.count + lb_offset + PAGE_SIZE - 1) >> PAGE_SHIFT; + + /* Allocate the buffers we need */ + + /* + * 'pages' is an array of struct page pointers that's initialized by + * get_user_pages(). + */ + pages = kzalloc(num_pages * sizeof(struct page *), GFP_KERNEL); + if (!pages) { + pr_debug("fsl-hv: could not allocate page list\n"); + return -ENOMEM; + } + + /* + * sg_list is the list of fh_sg_list objects that we pass to the + * hypervisor. + */ + sg_list_unaligned = kmalloc(num_pages * sizeof(struct fh_sg_list) + + sizeof(struct fh_sg_list) - 1, GFP_KERNEL); + if (!sg_list_unaligned) { + pr_debug("fsl-hv: could not allocate S/G list\n"); + ret = -ENOMEM; + goto exit; + } + sg_list = PTR_ALIGN(sg_list_unaligned, sizeof(struct fh_sg_list)); + + /* Get the physical addresses of the source buffer */ + down_read(¤t->mm->mmap_sem); + num_pinned = get_user_pages(current, current->mm, + param.local_vaddr - lb_offset, num_pages, + (param.source == -1) ? READ : WRITE, + 0, pages, NULL); + up_read(¤t->mm->mmap_sem); + + if (num_pinned != num_pages) { + /* get_user_pages() failed */ + pr_debug("fsl-hv: could not lock source buffer\n"); + ret = (num_pinned < 0) ? num_pinned : -EFAULT; + goto exit; + } + + /* + * Build the fh_sg_list[] array. The first page is special + * because it's misaligned. + */ + if (param.source == -1) { + sg_list[0].source = page_to_phys(pages[0]) + lb_offset; + sg_list[0].target = param.remote_paddr; + } else { + sg_list[0].source = param.remote_paddr; + sg_list[0].target = page_to_phys(pages[0]) + lb_offset; + } + sg_list[0].size = min_t(uint64_t, param.count, PAGE_SIZE - lb_offset); + + remote_paddr = param.remote_paddr + sg_list[0].size; + count = param.count - sg_list[0].size; + + for (i = 1; i < num_pages; i++) { + if (param.source == -1) { + /* local to remote */ + sg_list[i].source = page_to_phys(pages[i]); + sg_list[i].target = remote_paddr; + } else { + /* remote to local */ + sg_list[i].source = remote_paddr; + sg_list[i].target = page_to_phys(pages[i]); + } + sg_list[i].size = min_t(uint64_t, count, PAGE_SIZE); + + remote_paddr += sg_list[i].size; + count -= sg_list[i].size; + } + + param.ret = fh_partition_memcpy(param.source, param.target, + virt_to_phys(sg_list), num_pages); + +exit: + if (pages) { + for (i = 0; i < num_pages; i++) + if (pages[i]) + put_page(pages[i]); + } + + kfree(sg_list_unaligned); + kfree(pages); + + if (!ret) + if (copy_to_user(&p->ret, ¶m.ret, sizeof(__u32))) + return -EFAULT; + + return ret; +} + +/* + * Ioctl interface for FSL_HV_IOCTL_DOORBELL + * + * Ring a doorbell + */ +static long ioctl_doorbell(struct fsl_hv_ioctl_doorbell __user *p) +{ + struct fsl_hv_ioctl_doorbell param; + + /* Get the parameters from the user. */ + if (copy_from_user(¶m, p, sizeof(struct fsl_hv_ioctl_doorbell))) + return -EFAULT; + + param.ret = ev_doorbell_send(param.doorbell); + + if (copy_to_user(&p->ret, ¶m.ret, sizeof(__u32))) + return -EFAULT; + + return 0; +} + +static long ioctl_dtprop(struct fsl_hv_ioctl_prop __user *p, int set) +{ + struct fsl_hv_ioctl_prop param; + char __user *upath, *upropname; + void __user *upropval; + char *path = NULL, *propname = NULL; + void *propval = NULL; + int ret = 0; + + /* Get the parameters from the user. */ + if (copy_from_user(¶m, p, sizeof(struct fsl_hv_ioctl_prop))) + return -EFAULT; + + upath = (char __user *)(uintptr_t)param.path; + upropname = (char __user *)(uintptr_t)param.propname; + upropval = (void __user *)(uintptr_t)param.propval; + + path = strndup_user(upath, FH_DTPROP_MAX_PATHLEN); + if (IS_ERR(path)) { + ret = PTR_ERR(path); + goto out; + } + + propname = strndup_user(upropname, FH_DTPROP_MAX_PATHLEN); + if (IS_ERR(propname)) { + ret = PTR_ERR(propname); + goto out; + } + + if (param.proplen > FH_DTPROP_MAX_PROPLEN) { + ret = -EINVAL; + goto out; + } + + propval = kmalloc(param.proplen, GFP_KERNEL); + if (!propval) { + ret = -ENOMEM; + goto out; + } + + if (set) { + if (copy_from_user(propval, upropval, param.proplen)) { + ret = -EFAULT; + goto out; + } + + param.ret = fh_partition_set_dtprop(param.handle, + virt_to_phys(path), + virt_to_phys(propname), + virt_to_phys(propval), + param.proplen); + } else { + param.ret = fh_partition_get_dtprop(param.handle, + virt_to_phys(path), + virt_to_phys(propname), + virt_to_phys(propval), + ¶m.proplen); + + if (param.ret == 0) { + if (copy_to_user(upropval, propval, param.proplen) || + put_user(param.proplen, &p->proplen)) { + ret = -EFAULT; + goto out; + } + } + } + + if (put_user(param.ret, &p->ret)) + ret = -EFAULT; + +out: + kfree(path); + kfree(propval); + kfree(propname); + + return ret; +} + +/* + * Ioctl main entry point + */ +static long fsl_hv_ioctl(struct file *file, unsigned int cmd, + unsigned long argaddr) +{ + void __user *arg = (void __user *)argaddr; + long ret; + + switch (cmd) { + case FSL_HV_IOCTL_PARTITION_RESTART: + ret = ioctl_restart(arg); + break; + case FSL_HV_IOCTL_PARTITION_GET_STATUS: + ret = ioctl_status(arg); + break; + case FSL_HV_IOCTL_PARTITION_START: + ret = ioctl_start(arg); + break; + case FSL_HV_IOCTL_PARTITION_STOP: + ret = ioctl_stop(arg); + break; + case FSL_HV_IOCTL_MEMCPY: + ret = ioctl_memcpy(arg); + break; + case FSL_HV_IOCTL_DOORBELL: + ret = ioctl_doorbell(arg); + break; + case FSL_HV_IOCTL_GETPROP: + ret = ioctl_dtprop(arg, 0); + break; + case FSL_HV_IOCTL_SETPROP: + ret = ioctl_dtprop(arg, 1); + break; + default: + pr_debug("fsl-hv: bad ioctl dir=%u type=%u cmd=%u size=%u\n", + _IOC_DIR(cmd), _IOC_TYPE(cmd), _IOC_NR(cmd), + _IOC_SIZE(cmd)); + return -ENOTTY; + } + + return ret; +} + +/* Linked list of processes that have us open */ +static struct list_head db_list; + +/* spinlock for db_list */ +static DEFINE_SPINLOCK(db_list_lock); + +/* The size of the doorbell event queue. This must be a power of two. */ +#define QSIZE 16 + +/* Returns the next head/tail pointer, wrapping around the queue if necessary */ +#define nextp(x) (((x) + 1) & (QSIZE - 1)) + +/* Per-open data structure */ +struct doorbell_queue { + struct list_head list; + spinlock_t lock; + wait_queue_head_t wait; + unsigned int head; + unsigned int tail; + uint32_t q[QSIZE]; +}; + +/* Linked list of ISRs that we registered */ +struct list_head isr_list; + +/* Per-ISR data structure */ +struct doorbell_isr { + struct list_head list; + unsigned int irq; + uint32_t doorbell; /* The doorbell handle */ + uint32_t partition; /* The partition handle, if used */ +}; + +/* + * Add a doorbell to all of the doorbell queues + */ +static void fsl_hv_queue_doorbell(uint32_t doorbell) +{ + struct doorbell_queue *dbq; + unsigned long flags; + + /* Prevent another core from modifying db_list */ + spin_lock_irqsave(&db_list_lock, flags); + + list_for_each_entry(dbq, &db_list, list) { + if (dbq->head != nextp(dbq->tail)) { + dbq->q[dbq->tail] = doorbell; + /* + * This memory barrier eliminates the need to grab + * the spinlock for dbq. + */ + smp_wmb(); + dbq->tail = nextp(dbq->tail); + wake_up_interruptible(&dbq->wait); + } + } + + spin_unlock_irqrestore(&db_list_lock, flags); +} + +/* + * Interrupt handler for all doorbells + * + * We use the same interrupt handler for all doorbells. Whenever a doorbell + * is rung, and we receive an interrupt, we just put the handle for that + * doorbell (passed to us as *data) into all of the queues. + */ +static irqreturn_t fsl_hv_isr(int irq, void *data) +{ + fsl_hv_queue_doorbell((uintptr_t) data); + + return IRQ_HANDLED; +} + +/* + * State change thread function + * + * The state change notification arrives in an interrupt, but we can't call + * blocking_notifier_call_chain() in an interrupt handler. We could call + * atomic_notifier_call_chain(), but that would require the clients' call-back + * function to run in interrupt context. Since we don't want to impose that + * restriction on the clients, we use a threaded IRQ to process the + * notification in kernel context. + */ +static irqreturn_t fsl_hv_state_change_thread(int irq, void *data) +{ + struct doorbell_isr *dbisr = data; + + blocking_notifier_call_chain(&failover_subscribers, dbisr->partition, + NULL); + + return IRQ_HANDLED; +} + +/* + * Interrupt handler for state-change doorbells + */ +static irqreturn_t fsl_hv_state_change_isr(int irq, void *data) +{ + unsigned int status; + struct doorbell_isr *dbisr = data; + int ret; + + /* It's still a doorbell, so add it to all the queues. */ + fsl_hv_queue_doorbell(dbisr->doorbell); + + /* Determine the new state, and if it's stopped, notify the clients. */ + ret = fh_partition_get_status(dbisr->partition, &status); + if (!ret && (status == FH_PARTITION_STOPPED)) + return IRQ_WAKE_THREAD; + + return IRQ_HANDLED; +} + +/* + * Returns a bitmask indicating whether a read will block + */ +static unsigned int fsl_hv_poll(struct file *filp, struct poll_table_struct *p) +{ + struct doorbell_queue *dbq = filp->private_data; + unsigned long flags; + unsigned int mask; + + spin_lock_irqsave(&dbq->lock, flags); + + poll_wait(filp, &dbq->wait, p); + mask = (dbq->head == dbq->tail) ? 0 : (POLLIN | POLLRDNORM); + + spin_unlock_irqrestore(&dbq->lock, flags); + + return mask; +} + +/* + * Return the handles for any incoming doorbells + * + * If there are doorbell handles in the queue for this open instance, then + * return them to the caller as an array of 32-bit integers. Otherwise, + * block until there is at least one handle to return. + */ +static ssize_t fsl_hv_read(struct file *filp, char __user *buf, size_t len, + loff_t *off) +{ + struct doorbell_queue *dbq = filp->private_data; + uint32_t __user *p = (uint32_t __user *) buf; /* for put_user() */ + unsigned long flags; + ssize_t count = 0; + + /* Make sure we stop when the user buffer is full. */ + while (len >= sizeof(uint32_t)) { + uint32_t dbell; /* Local copy of doorbell queue data */ + + spin_lock_irqsave(&dbq->lock, flags); + + /* + * If the queue is empty, then either we're done or we need + * to block. If the application specified O_NONBLOCK, then + * we return the appropriate error code. + */ + if (dbq->head == dbq->tail) { + spin_unlock_irqrestore(&dbq->lock, flags); + if (count) + break; + if (filp->f_flags & O_NONBLOCK) + return -EAGAIN; + if (wait_event_interruptible(dbq->wait, + dbq->head != dbq->tail)) + return -ERESTARTSYS; + continue; + } + + /* + * Even though we have an smp_wmb() in the ISR, the core + * might speculatively execute the "dbell = ..." below while + * it's evaluating the if-statement above. In that case, the + * value put into dbell could be stale if the core accepts the + * speculation. To prevent that, we need a read memory barrier + * here as well. + */ + smp_rmb(); + + /* Copy the data to a temporary local buffer, because + * we can't call copy_to_user() from inside a spinlock + */ + dbell = dbq->q[dbq->head]; + dbq->head = nextp(dbq->head); + + spin_unlock_irqrestore(&dbq->lock, flags); + + if (put_user(dbell, p)) + return -EFAULT; + p++; + count += sizeof(uint32_t); + len -= sizeof(uint32_t); + } + + return count; +} + +/* + * Open the driver and prepare for reading doorbells. + * + * Every time an application opens the driver, we create a doorbell queue + * for that file handle. This queue is used for any incoming doorbells. + */ +static int fsl_hv_open(struct inode *inode, struct file *filp) +{ + struct doorbell_queue *dbq; + unsigned long flags; + int ret = 0; + + dbq = kzalloc(sizeof(struct doorbell_queue), GFP_KERNEL); + if (!dbq) { + pr_err("fsl-hv: out of memory\n"); + return -ENOMEM; + } + + spin_lock_init(&dbq->lock); + init_waitqueue_head(&dbq->wait); + + spin_lock_irqsave(&db_list_lock, flags); + list_add(&dbq->list, &db_list); + spin_unlock_irqrestore(&db_list_lock, flags); + + filp->private_data = dbq; + + return ret; +} + +/* + * Close the driver + */ +static int fsl_hv_close(struct inode *inode, struct file *filp) +{ + struct doorbell_queue *dbq = filp->private_data; + unsigned long flags; + + int ret = 0; + + spin_lock_irqsave(&db_list_lock, flags); + list_del(&dbq->list); + spin_unlock_irqrestore(&db_list_lock, flags); + + kfree(dbq); + + return ret; +} + +static const struct file_operations fsl_hv_fops = { + .owner = THIS_MODULE, + .open = fsl_hv_open, + .release = fsl_hv_close, + .poll = fsl_hv_poll, + .read = fsl_hv_read, + .unlocked_ioctl = fsl_hv_ioctl, +}; + +static struct miscdevice fsl_hv_misc_dev = { + MISC_DYNAMIC_MINOR, + "fsl-hv", + &fsl_hv_fops +}; + +static irqreturn_t fsl_hv_shutdown_isr(int irq, void *data) +{ + orderly_poweroff(false); + + return IRQ_HANDLED; +} + +/* + * Returns the handle of the parent of the given node + * + * The handle is the value of the 'hv-handle' property + */ +static int get_parent_handle(struct device_node *np) +{ + struct device_node *parent; + const uint32_t *prop; + uint32_t handle; + int len; + + parent = of_get_parent(np); + if (!parent) + /* It's not really possible for this to fail */ + return -ENODEV; + + /* + * The proper name for the handle property is "hv-handle", but some + * older versions of the hypervisor used "reg". + */ + prop = of_get_property(parent, "hv-handle", &len); + if (!prop) + prop = of_get_property(parent, "reg", &len); + + if (!prop || (len != sizeof(uint32_t))) { + /* This can happen only if the node is malformed */ + of_node_put(parent); + return -ENODEV; + } + + handle = be32_to_cpup(prop); + of_node_put(parent); + + return handle; +} + +/* + * Register a callback for failover events + * + * This function is called by device drivers to register their callback + * functions for fail-over events. + */ +int fsl_hv_failover_register(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&failover_subscribers, nb); +} +EXPORT_SYMBOL(fsl_hv_failover_register); + +/* + * Unregister a callback for failover events + */ +int fsl_hv_failover_unregister(struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&failover_subscribers, nb); +} +EXPORT_SYMBOL(fsl_hv_failover_unregister); + +/* + * Return TRUE if we're running under FSL hypervisor + * + * This function checks to see if we're running under the Freescale + * hypervisor, and returns zero if we're not, or non-zero if we are. + * + * First, it checks if MSR[GS]==1, which means we're running under some + * hypervisor. Then it checks if there is a hypervisor node in the device + * tree. Currently, that means there needs to be a node in the root called + * "hypervisor" and which has a property named "fsl,hv-version". + */ +static int has_fsl_hypervisor(void) +{ + struct device_node *node; + int ret; + + if (!(mfmsr() & MSR_GS)) + return 0; + + node = of_find_node_by_path("/hypervisor"); + if (!node) + return 0; + + ret = of_find_property(node, "fsl,hv-version", NULL) != NULL; + + of_node_put(node); + + return ret; +} + +/* + * Freescale hypervisor management driver init + * + * This function is called when this module is loaded. + * + * Register ourselves as a miscellaneous driver. This will register the + * fops structure and create the right sysfs entries for udev. + */ +static int __init fsl_hypervisor_init(void) +{ + struct device_node *np; + struct doorbell_isr *dbisr, *n; + int ret; + + pr_info("Freescale hypervisor management driver\n"); + + if (!has_fsl_hypervisor()) { + pr_info("fsl-hv: no hypervisor found\n"); + return -ENODEV; + } + + ret = misc_register(&fsl_hv_misc_dev); + if (ret) { + pr_err("fsl-hv: cannot register device\n"); + return ret; + } + + INIT_LIST_HEAD(&db_list); + INIT_LIST_HEAD(&isr_list); + + for_each_compatible_node(np, NULL, "epapr,hv-receive-doorbell") { + unsigned int irq; + const uint32_t *handle; + + handle = of_get_property(np, "interrupts", NULL); + irq = irq_of_parse_and_map(np, 0); + if (!handle || (irq == NO_IRQ)) { + pr_err("fsl-hv: no 'interrupts' property in %s node\n", + np->full_name); + continue; + } + + dbisr = kzalloc(sizeof(*dbisr), GFP_KERNEL); + if (!dbisr) + goto out_of_memory; + + dbisr->irq = irq; + dbisr->doorbell = be32_to_cpup(handle); + + if (of_device_is_compatible(np, "fsl,hv-shutdown-doorbell")) { + /* The shutdown doorbell gets its own ISR */ + ret = request_irq(irq, fsl_hv_shutdown_isr, 0, + np->name, NULL); + } else if (of_device_is_compatible(np, + "fsl,hv-state-change-doorbell")) { + /* + * The state change doorbell triggers a notification if + * the state of the managed partition changes to + * "stopped". We need a separate interrupt handler for + * that, and we also need to know the handle of the + * target partition, not just the handle of the + * doorbell. + */ + dbisr->partition = ret = get_parent_handle(np); + if (ret < 0) { + pr_err("fsl-hv: node %s has missing or " + "malformed parent\n", np->full_name); + kfree(dbisr); + continue; + } + ret = request_threaded_irq(irq, fsl_hv_state_change_isr, + fsl_hv_state_change_thread, + 0, np->name, dbisr); + } else + ret = request_irq(irq, fsl_hv_isr, 0, np->name, dbisr); + + if (ret < 0) { + pr_err("fsl-hv: could not request irq %u for node %s\n", + irq, np->full_name); + kfree(dbisr); + continue; + } + + list_add(&dbisr->list, &isr_list); + + pr_info("fsl-hv: registered handler for doorbell %u\n", + dbisr->doorbell); + } + + return 0; + +out_of_memory: + list_for_each_entry_safe(dbisr, n, &isr_list, list) { + free_irq(dbisr->irq, dbisr); + list_del(&dbisr->list); + kfree(dbisr); + } + + misc_deregister(&fsl_hv_misc_dev); + + return -ENOMEM; +} + +/* + * Freescale hypervisor management driver termination + * + * This function is called when this driver is unloaded. + */ +static void __exit fsl_hypervisor_exit(void) +{ + struct doorbell_isr *dbisr, *n; + + list_for_each_entry_safe(dbisr, n, &isr_list, list) { + free_irq(dbisr->irq, dbisr); + list_del(&dbisr->list); + kfree(dbisr); + } + + misc_deregister(&fsl_hv_misc_dev); +} + +module_init(fsl_hypervisor_init); +module_exit(fsl_hypervisor_exit); + +MODULE_AUTHOR("Timur Tabi <timur@freescale.com>"); +MODULE_DESCRIPTION("Freescale hypervisor management driver"); +MODULE_LICENSE("GPL v2"); |