diff options
94 files changed, 3073 insertions, 916 deletions
diff --git a/Documentation/cpu-freq/core.txt b/Documentation/cpu-freq/core.txt index 29b3f9ffc66..ce0666e5103 100644 --- a/Documentation/cpu-freq/core.txt +++ b/Documentation/cpu-freq/core.txt @@ -24,7 +24,7 @@ Contents: 1. General Information ======================= -The CPUFreq core code is located in linux/kernel/cpufreq.c. This +The CPUFreq core code is located in drivers/cpufreq/cpufreq.c. This cpufreq code offers a standardized interface for the CPUFreq architecture drivers (those pieces of code that do actual frequency transitions), as well as to "notifiers". These are device diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index 031029e89fd..64ce44da593 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -259,3 +259,25 @@ Why: The new layer 3 independant connection tracking replaces the old Who: Patrick McHardy <kaber@trash.net> --------------------------- + +What: ACPI hooks (X86_SPEEDSTEP_CENTRINO_ACPI) in speedstep-centrino driver +When: December 2006 +Why: Speedstep-centrino driver with ACPI hooks and acpi-cpufreq driver are + functionally very much similar. They talk to ACPI in same way. Only + difference between them is the way they do frequency transitions. + One uses MSRs and the other one uses IO ports. Functionaliy of + speedstep_centrino with ACPI hooks is now merged into acpi-cpufreq. + That means one common driver will support all Intel Enhanced Speedstep + capable CPUs. That means less confusion over name of + speedstep-centrino driver (with that driver supposed to be used on + non-centrino platforms). That means less duplication of code and + less maintenance effort and no possibility of these two drivers + going out of sync. + Current users of speedstep_centrino with ACPI hooks are requested to + switch over to acpi-cpufreq driver. speedstep-centrino will continue + to work using older non-ACPI static table based scheme even after this + date. + +Who: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> + +--------------------------- diff --git a/Documentation/kbuild/kconfig-language.txt b/Documentation/kbuild/kconfig-language.txt index 125093c3ef7..536d5bfbdb8 100644 --- a/Documentation/kbuild/kconfig-language.txt +++ b/Documentation/kbuild/kconfig-language.txt @@ -29,7 +29,7 @@ them. A single configuration option is defined like this: config MODVERSIONS bool "Set version information on all module symbols" - depends MODULES + depends on MODULES help Usually, modules have to be recompiled whenever you switch to a new kernel. ... @@ -163,7 +163,7 @@ The position of a menu entry in the tree is determined in two ways. First it can be specified explicitly: menu "Network device support" - depends NET + depends on NET config NETDEVICES ... @@ -188,10 +188,10 @@ config MODULES config MODVERSIONS bool "Set version information on all module symbols" - depends MODULES + depends on MODULES comment "module support disabled" - depends !MODULES + depends on !MODULES MODVERSIONS directly depends on MODULES, this means it's only visible if MODULES is different from 'n'. The comment on the other hand is always diff --git a/MAINTAINERS b/MAINTAINERS index b2024938adc..8a0bfeca55c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -740,7 +740,7 @@ P: Dave Jones M: davej@codemonkey.org.uk L: cpufreq@lists.linux.org.uk W: http://www.codemonkey.org.uk/projects/cpufreq/ -T: git kernel.org/pub/scm/linux/kernel/davej/cpufreq.git +T: git kernel.org/pub/scm/linux/kernel/git/davej/cpufreq.git S: Maintained CPUID/MSR DRIVER @@ -1504,8 +1504,10 @@ T: git kernel.org:/pub/scm/linux/kernel/git/dtor/input.git S: Maintained INOTIFY -P: John McCutchan and Robert Love -M: ttb@tentacle.dhs.org and rml@novell.com +P: John McCutchan +M: ttb@tentacle.dhs.org +P: Robert Love +M: rml@novell.com L: linux-kernel@vger.kernel.org S: Maintained @@ -1100,9 +1100,9 @@ boards := $(notdir $(boards)) help: @echo 'Cleaning targets:' - @echo ' clean - remove most generated files but keep the config and' + @echo ' clean - Remove most generated files but keep the config and' @echo ' enough build support to build external modules' - @echo ' mrproper - remove all generated files + config + various backup files' + @echo ' mrproper - Remove all generated files + config + various backup files' @echo ' distclean - mrproper + remove editor backup and patch files' @echo '' @echo 'Configuration targets:' diff --git a/arch/arm/mach-pxa/Kconfig b/arch/arm/mach-pxa/Kconfig index 9e3d0bdcba0..5c0a10041cd 100644 --- a/arch/arm/mach-pxa/Kconfig +++ b/arch/arm/mach-pxa/Kconfig @@ -75,28 +75,28 @@ endmenu config MACH_POODLE bool "Enable Sharp SL-5600 (Poodle) Support" - depends PXA_SHARPSL_25x + depends on PXA_SHARPSL_25x select SHARP_LOCOMO select PXA_SSP config MACH_CORGI bool "Enable Sharp SL-C700 (Corgi) Support" - depends PXA_SHARPSL_25x + depends on PXA_SHARPSL_25x select PXA_SHARP_C7xx config MACH_SHEPHERD bool "Enable Sharp SL-C750 (Shepherd) Support" - depends PXA_SHARPSL_25x + depends on PXA_SHARPSL_25x select PXA_SHARP_C7xx config MACH_HUSKY bool "Enable Sharp SL-C760 (Husky) Support" - depends PXA_SHARPSL_25x + depends on PXA_SHARPSL_25x select PXA_SHARP_C7xx config MACH_AKITA bool "Enable Sharp SL-1000 (Akita) Support" - depends PXA_SHARPSL_27x + depends on PXA_SHARPSL_27x select PXA_SHARP_Cxx00 select MACH_SPITZ select I2C @@ -104,17 +104,17 @@ config MACH_AKITA config MACH_SPITZ bool "Enable Sharp Zaurus SL-3000 (Spitz) Support" - depends PXA_SHARPSL_27x + depends on PXA_SHARPSL_27x select PXA_SHARP_Cxx00 config MACH_BORZOI bool "Enable Sharp Zaurus SL-3100 (Borzoi) Support" - depends PXA_SHARPSL_27x + depends on PXA_SHARPSL_27x select PXA_SHARP_Cxx00 config MACH_TOSA bool "Enable Sharp SL-6000x (Tosa) Support" - depends PXA_SHARPSL_25x + depends on PXA_SHARPSL_25x config PXA25x bool diff --git a/arch/arm/plat-omap/Kconfig b/arch/arm/plat-omap/Kconfig index ec752e16d61..f2dc363de66 100644 --- a/arch/arm/plat-omap/Kconfig +++ b/arch/arm/plat-omap/Kconfig @@ -113,7 +113,7 @@ endchoice config OMAP_SERIAL_WAKE bool "Enable wake-up events for serial ports" - depends OMAP_MUX + depends on OMAP_MUX default y help Select this option if you want to have your system wake up diff --git a/arch/i386/kernel/cpu/cpufreq/Kconfig b/arch/i386/kernel/cpu/cpufreq/Kconfig index ccc1edff5c9..5299c5bf445 100644 --- a/arch/i386/kernel/cpu/cpufreq/Kconfig +++ b/arch/i386/kernel/cpu/cpufreq/Kconfig @@ -17,6 +17,7 @@ config X86_ACPI_CPUFREQ help This driver adds a CPUFreq driver which utilizes the ACPI Processor Performance States. + This driver also supports Intel Enhanced Speedstep. For details, take a look at <file:Documentation/cpu-freq/>. @@ -121,11 +122,14 @@ config X86_SPEEDSTEP_CENTRINO If in doubt, say N. config X86_SPEEDSTEP_CENTRINO_ACPI - bool "Use ACPI tables to decode valid frequency/voltage pairs" + bool "Use ACPI tables to decode valid frequency/voltage (deprecated)" depends on X86_SPEEDSTEP_CENTRINO && ACPI_PROCESSOR depends on !(X86_SPEEDSTEP_CENTRINO = y && ACPI_PROCESSOR = m) default y help + This is deprecated and this functionality is now merged into + acpi_cpufreq (X86_ACPI_CPUFREQ). Use that driver instead of + speedstep_centrino. Use primarily the information provided in the BIOS ACPI tables to determine valid CPU frequency and voltage pairings. It is required for the driver to work on non-Banias CPUs. diff --git a/arch/i386/kernel/cpu/cpufreq/Makefile b/arch/i386/kernel/cpu/cpufreq/Makefile index 2e894f1c891..8de3abe322a 100644 --- a/arch/i386/kernel/cpu/cpufreq/Makefile +++ b/arch/i386/kernel/cpu/cpufreq/Makefile @@ -7,9 +7,9 @@ obj-$(CONFIG_SC520_CPUFREQ) += sc520_freq.o obj-$(CONFIG_X86_LONGRUN) += longrun.o obj-$(CONFIG_X86_GX_SUSPMOD) += gx-suspmod.o obj-$(CONFIG_X86_SPEEDSTEP_ICH) += speedstep-ich.o -obj-$(CONFIG_X86_SPEEDSTEP_CENTRINO) += speedstep-centrino.o obj-$(CONFIG_X86_SPEEDSTEP_LIB) += speedstep-lib.o obj-$(CONFIG_X86_SPEEDSTEP_SMI) += speedstep-smi.o obj-$(CONFIG_X86_ACPI_CPUFREQ) += acpi-cpufreq.o +obj-$(CONFIG_X86_SPEEDSTEP_CENTRINO) += speedstep-centrino.o obj-$(CONFIG_X86_P4_CLOCKMOD) += p4-clockmod.o obj-$(CONFIG_X86_CPUFREQ_NFORCE2) += cpufreq-nforce2.o diff --git a/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c index 57c880bf0bd..18f4715c655 100644 --- a/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -1,9 +1,10 @@ /* - * acpi-cpufreq.c - ACPI Processor P-States Driver ($Revision: 1.3 $) + * acpi-cpufreq.c - ACPI Processor P-States Driver ($Revision: 1.4 $) * * Copyright (C) 2001, 2002 Andy Grover <andrew.grover@intel.com> * Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com> * Copyright (C) 2002 - 2004 Dominik Brodowski <linux@brodo.de> + * Copyright (C) 2006 Denis Sadykov <denis.m.sadykov@intel.com> * * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * @@ -27,202 +28,387 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> +#include <linux/smp.h> +#include <linux/sched.h> #include <linux/cpufreq.h> -#include <linux/proc_fs.h> -#include <linux/seq_file.h> #include <linux/compiler.h> -#include <linux/sched.h> /* current */ #include <linux/dmi.h> -#include <asm/io.h> -#include <asm/delay.h> -#include <asm/uaccess.h> #include <linux/acpi.h> #include <acpi/processor.h> +#include <asm/io.h> +#include <asm/msr.h> +#include <asm/processor.h> +#include <asm/cpufeature.h> +#include <asm/delay.h> +#include <asm/uaccess.h> + #define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "acpi-cpufreq", msg) MODULE_AUTHOR("Paul Diefenbaugh, Dominik Brodowski"); MODULE_DESCRIPTION("ACPI Processor P-States Driver"); MODULE_LICENSE("GPL"); +enum { + UNDEFINED_CAPABLE = 0, + SYSTEM_INTEL_MSR_CAPABLE, + SYSTEM_IO_CAPABLE, +}; + +#define INTEL_MSR_RANGE (0xffff) +#define CPUID_6_ECX_APERFMPERF_CAPABILITY (0x1) -struct cpufreq_acpi_io { - struct acpi_processor_performance *acpi_data; - struct cpufreq_frequency_table *freq_table; - unsigned int resume; +struct acpi_cpufreq_data { + struct acpi_processor_performance *acpi_data; + struct cpufreq_frequency_table *freq_table; + unsigned int max_freq; + unsigned int resume; + unsigned int cpu_feature; }; -static struct cpufreq_acpi_io *acpi_io_data[NR_CPUS]; -static struct acpi_processor_performance *acpi_perf_data[NR_CPUS]; +static struct acpi_cpufreq_data *drv_data[NR_CPUS]; +static struct acpi_processor_performance *acpi_perf_data[NR_CPUS]; static struct cpufreq_driver acpi_cpufreq_driver; static unsigned int acpi_pstate_strict; -static int -acpi_processor_write_port( - u16 port, - u8 bit_width, - u32 value) +static int check_est_cpu(unsigned int cpuid) +{ + struct cpuinfo_x86 *cpu = &cpu_data[cpuid]; + + if (cpu->x86_vendor != X86_VENDOR_INTEL || + !cpu_has(cpu, X86_FEATURE_EST)) + return 0; + + return 1; +} + +static unsigned extract_io(u32 value, struct acpi_cpufreq_data *data) +{ + struct acpi_processor_performance *perf; + int i; + + perf = data->acpi_data; + + for (i=0; i<perf->state_count; i++) { + if (value == perf->states[i].status) + return data->freq_table[i].frequency; + } + return 0; +} + +static unsigned extract_msr(u32 msr, struct acpi_cpufreq_data *data) { - if (bit_width <= 8) { + int i; + struct acpi_processor_performance *perf; + + msr &= INTEL_MSR_RANGE; + perf = data->acpi_data; + + for (i=0; data->freq_table[i].frequency != CPUFREQ_TABLE_END; i++) { + if (msr == perf->states[data->freq_table[i].index].status) + return data->freq_table[i].frequency; + } + return data->freq_table[0].frequency; +} + +static unsigned extract_freq(u32 val, struct acpi_cpufreq_data *data) +{ + switch (data->cpu_feature) { + case SYSTEM_INTEL_MSR_CAPABLE: + return extract_msr(val, data); + case SYSTEM_IO_CAPABLE: + return extract_io(val, data); + default: + return 0; + } +} + +static void wrport(u16 port, u8 bit_width, u32 value) +{ + if (bit_width <= 8) outb(value, port); - } else if (bit_width <= 16) { + else if (bit_width <= 16) outw(value, port); - } else if (bit_width <= 32) { + else if (bit_width <= 32) outl(value, port); - } else { - return -ENODEV; - } - return 0; } -static int -acpi_processor_read_port( - u16 port, - u8 bit_width, - u32 *ret) +static void rdport(u16 port, u8 bit_width, u32 * ret) { *ret = 0; - if (bit_width <= 8) { + if (bit_width <= 8) *ret = inb(port); - } else if (bit_width <= 16) { + else if (bit_width <= 16) *ret = inw(port); - } else if (bit_width <= 32) { + else if (bit_width <= 32) *ret = inl(port); - } else { - return -ENODEV; +} + +struct msr_addr { + u32 reg; +}; + +struct io_addr { + u16 port; + u8 bit_width; +}; + +typedef union { + struct msr_addr msr; + struct io_addr io; +} drv_addr_union; + +struct drv_cmd { + unsigned int type; + cpumask_t mask; + drv_addr_union addr; + u32 val; +}; + +static void do_drv_read(struct drv_cmd *cmd) +{ + u32 h; + + switch (cmd->type) { + case SYSTEM_INTEL_MSR_CAPABLE: + rdmsr(cmd->addr.msr.reg, cmd->val, h); + break; + case SYSTEM_IO_CAPABLE: + rdport(cmd->addr.io.port, cmd->addr.io.bit_width, &cmd->val); + break; + default: + break; } - return 0; } -static int -acpi_processor_set_performance ( - struct cpufreq_acpi_io *data, - unsigned int cpu, - int state) +static void do_drv_write(struct drv_cmd *cmd) { - u16 port = 0; - u8 bit_width = 0; - int i = 0; - int ret = 0; - u32 value = 0; - int retval; - struct acpi_processor_performance *perf; - - dprintk("acpi_processor_set_performance\n"); - - retval = 0; - perf = data->acpi_data; - if (state == perf->state) { - if (unlikely(data->resume)) { - dprintk("Called after resume, resetting to P%d\n", state); - data->resume = 0; - } else { - dprintk("Already at target state (P%d)\n", state); - return (retval); - } + u32 h = 0; + + switch (cmd->type) { + case SYSTEM_INTEL_MSR_CAPABLE: + wrmsr(cmd->addr.msr.reg, cmd->val, h); + break; + case SYSTEM_IO_CAPABLE: + wrport(cmd->addr.io.port, cmd->addr.io.bit_width, cmd->val); + break; + default: + break; } +} - dprintk("Transitioning from P%d to P%d\n", perf->state, state); +static void drv_read(struct drv_cmd *cmd) +{ + cpumask_t saved_mask = current->cpus_allowed; + cmd->val = 0; - /* - * First we write the target state's 'control' value to the - * control_register. - */ + set_cpus_allowed(current, cmd->mask); + do_drv_read(cmd); + set_cpus_allowed(current, saved_mask); +} + +static void drv_write(struct drv_cmd *cmd) +{ + cpumask_t saved_mask = current->cpus_allowed; + unsigned int i; + + for_each_cpu_mask(i, cmd->mask) { + set_cpus_allowed(current, cpumask_of_cpu(i)); + do_drv_write(cmd); + } + + set_cpus_allowed(current, saved_mask); + return; +} + +static u32 get_cur_val(cpumask_t mask) +{ + struct acpi_processor_performance *perf; + struct drv_cmd cmd; + + if (unlikely(cpus_empty(mask))) + return 0; + + switch (drv_data[first_cpu(mask)]->cpu_feature) { + case SYSTEM_INTEL_MSR_CAPABLE: + cmd.type = SYSTEM_INTEL_MSR_CAPABLE; + cmd.addr.msr.reg = MSR_IA32_PERF_STATUS; + break; + case SYSTEM_IO_CAPABLE: + cmd.type = SYSTEM_IO_CAPABLE; + perf = drv_data[first_cpu(mask)]->acpi_data; + cmd.addr.io.port = perf->control_register.address; + cmd.addr.io.bit_width = perf->control_register.bit_width; + break; + default: + return 0; + } + + cmd.mask = mask; - port = perf->control_register.address; - bit_width = perf->control_register.bit_width; - value = (u32) perf->states[state].control; + drv_read(&cmd); - dprintk("Writing 0x%08x to port 0x%04x\n", value, port); + dprintk("get_cur_val = %u\n", cmd.val); - ret = acpi_processor_write_port(port, bit_width, value); - if (ret) { - dprintk("Invalid port width 0x%04x\n", bit_width); - return (ret); + return cmd.val; +} + +/* + * Return the measured active (C0) frequency on this CPU since last call + * to this function. + * Input: cpu number + * Return: Average CPU frequency in terms of max frequency (zero on error) + * + * We use IA32_MPERF and IA32_APERF MSRs to get the measured performance + * over a period of time, while CPU is in C0 state. + * IA32_MPERF counts at the rate of max advertised frequency + * IA32_APERF counts at the rate of actual CPU frequency + * Only IA32_APERF/IA32_MPERF ratio is architecturally defined and + * no meaning should be associated with absolute values of these MSRs. + */ +static unsigned int get_measured_perf(unsigned int cpu) +{ + union { + struct { + u32 lo; + u32 hi; + } split; + u64 whole; + } aperf_cur, mperf_cur; + + cpumask_t saved_mask; + unsigned int perf_percent; + unsigned int retval; + + saved_mask = current->cpus_allowed; + set_cpus_allowed(current, cpumask_of_cpu(cpu)); + if (get_cpu() != cpu) { + /* We were not able to run on requested processor */ + put_cpu(); + return 0; } + rdmsr(MSR_IA32_APERF, aperf_cur.split.lo, aperf_cur.split.hi); + rdmsr(MSR_IA32_MPERF, mperf_cur.split.lo, mperf_cur.split.hi); + + wrmsr(MSR_IA32_APERF, 0,0); + wrmsr(MSR_IA32_MPERF, 0,0); + +#ifdef __i386__ /* - * Assume the write went through when acpi_pstate_strict is not used. - * As read status_register is an expensive operation and there - * are no specific error cases where an IO port write will fail. + * We dont want to do 64 bit divide with 32 bit kernel + * Get an approximate value. Return failure in case we cannot get + * an approximate value. */ - if (acpi_pstate_strict) { - /* Then we read the 'status_register' and compare the value - * with the target state's 'status' to make sure the - * transition was successful. - * Note that we'll poll for up to 1ms (100 cycles of 10us) - * before giving up. - */ - - port = perf->status_register.address; - bit_width = perf->status_register.bit_width; - - dprintk("Looking for 0x%08x from port 0x%04x\n", - (u32) perf->states[state].status, port); - - for (i = 0; i < 100; i++) { - ret = acpi_processor_read_port(port, bit_width, &value); - if (ret) { - dprintk("Invalid port width 0x%04x\n", bit_width); - return (ret); - } - if (value == (u32) perf->states[state].status) - break; - udelay(10); - } - } else { - value = (u32) perf->states[state].status; + if (unlikely(aperf_cur.split.hi || mperf_cur.split.hi)) { + int shift_count; + u32 h; + + h = max_t(u32, aperf_cur.split.hi, mperf_cur.split.hi); + shift_count = fls(h); + + aperf_cur.whole >>= shift_count; + mperf_cur.whole >>= shift_count; + } + + if (((unsigned long)(-1) / 100) < aperf_cur.split.lo) { + int shift_count = 7; + aperf_cur.split.lo >>= shift_count; + mperf_cur.split.lo >>= shift_count; + } + + if (aperf_cur.split.lo && mperf_cur.split.lo) + perf_percent = (aperf_cur.split.lo * 100) / mperf_cur.split.lo; + else + perf_percent = 0; + +#else + if (unlikely(((unsigned long)(-1) / 100) < aperf_cur.whole)) { + int shift_count = 7; + aperf_cur.whole >>= shift_count; + mperf_cur.whole >>= shift_count; } - if (unlikely(value != (u32) perf->states[state].status)) { - printk(KERN_WARNING "acpi-cpufreq: Transition failed\n"); - retval = -ENODEV; - return (retval); + if (aperf_cur.whole && mperf_cur.whole) + perf_percent = (aperf_cur.whole * 100) / mperf_cur.whole; + else + perf_percent = 0; + +#endif + + retval = drv_data[cpu]->max_freq * perf_percent / 100; + + put_cpu(); + set_cpus_allowed(current, saved_mask); + + dprintk("cpu %d: performance percent %d\n", cpu, perf_percent); + return retval; +} + +static unsigned int get_cur_freq_on_cpu(unsigned int cpu) +{ + struct acpi_cpufreq_data *data = drv_data[cpu]; + unsigned int freq; + + dprintk("get_cur_freq_on_cpu (%d)\n", cpu); + + if (unlikely(data == NULL || + data->acpi_data == NULL || data->freq_table == NULL)) { + return 0; } - dprintk("Transition successful after %d microseconds\n", i * 10); + freq = extract_freq(get_cur_val(cpumask_of_cpu(cpu)), data); + dprintk("cur freq = %u\n", freq); - perf->state = state; - return (retval); + return freq; } +static unsigned int check_freqs(cpumask_t mask, unsigned int freq, + struct acpi_cpufreq_data *data) +{ + unsigned int cur_freq; + unsigned int i; + + for (i=0; i<100; i++) { + cur_freq = extract_freq(get_cur_val(mask), data); + if (cur_freq == freq) + return 1; + udelay(10); + } + return 0; +} -static int -acpi_cpufreq_target ( - struct cpufreq_policy *policy, - unsigned int target_freq, - unsigned int relation) +static int acpi_cpufreq_target(struct cpufreq_policy *policy, + unsigned int target_freq, unsigned int relation) { - struct cpufreq_acpi_io *data = acpi_io_data[policy->cpu]; + struct acpi_cpufreq_data *data = drv_data[policy->cpu]; struct acpi_processor_performance *perf; struct cpufreq_freqs freqs; cpumask_t online_policy_cpus; - cpumask_t saved_mask; - cpumask_t set_mask; - cpumask_t covered_cpus; - unsigned int cur_state = 0; + struct drv_cmd cmd; + unsigned int msr; unsigned int next_state = 0; - unsigned int result = 0; - unsigned int j; - unsigned int tmp; + unsigned int next_perf_state = 0; + unsigned int i; + int result = 0; - dprintk("acpi_cpufreq_setpolicy\n"); + dprintk("acpi_cpufreq_target %d (%d)\n", target_freq, policy->cpu); - result = cpufreq_frequency_table_target(policy, - data->freq_table, - target_freq, - relation, - &next_state); - if (unlikely(result)) - return (result); + if (unlikely(data == NULL || + data->acpi_data == NULL || data->freq_table == NULL)) { + return -ENODEV; + } perf = data->acpi_data; - cur_state = perf->state; - freqs.old = data->freq_table[cur_state].frequency; - freqs.new = data->freq_table[next_state].frequency; + result = cpufreq_frequency_table_target(policy, + data->freq_table, + target_freq, + relation, &next_state); + if (unlikely(result)) + return -ENODEV; #ifdef CONFIG_HOTPLUG_CPU /* cpufreq holds the hotplug lock, so we are safe from here on */ @@ -231,106 +417,84 @@ acpi_cpufreq_target ( online_policy_cpus = policy->cpus; #endif - for_each_cpu_mask(j, online_policy_cpus) { - freqs.cpu = j; - cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); + next_perf_state = data->freq_table[next_state].index; + if (perf->state == next_perf_state) { + if (unlikely(data->resume)) { + dprintk("Called after resume, resetting to P%d\n", + next_perf_state); + data->resume = 0; + } else { + dprintk("Already at target state (P%d)\n", + next_perf_state); + return 0; + } } - /* - * We need to call driver->target() on all or any CPU in - * policy->cpus, depending on policy->shared_type. - */ - saved_mask = current->cpus_allowed; - cpus_clear(covered_cpus); - for_each_cpu_mask(j, online_policy_cpus) { - /* - * Support for SMP systems. - * Make sure we are running on CPU that wants to change freq - */ - cpus_clear(set_mask); - if (policy->shared_type == CPUFREQ_SHARED_TYPE_ANY) - cpus_or(set_mask, set_mask, online_policy_cpus); - else - cpu_set(j, set_mask); - - set_cpus_allowed(current, set_mask); - if (unlikely(!cpu_isset(smp_processor_id(), set_mask))) { - dprintk("couldn't limit to CPUs in this domain\n"); - result = -EAGAIN; - break; - } + switch (data->cpu_feature) { + case SYSTEM_INTEL_MSR_CAPABLE: + cmd.type = SYSTEM_INTEL_MSR_CAPABLE; + cmd.addr.msr.reg = MSR_IA32_PERF_CTL; + msr = + (u32) perf->states[next_perf_state]. + control & INTEL_MSR_RANGE; + cmd.val = (cmd.val & ~INTEL_MSR_RANGE) | msr; + break; + case SYSTEM_IO_CAPABLE: + cmd.type = SYSTEM_IO_CAPABLE; + cmd.addr.io.port = perf->control_register.address; + cmd.addr.io.bit_width = perf->control_register.bit_width; + cmd.val = (u32) perf->states[next_perf_state].control; + break; + default: + return -ENODEV; + } - result = acpi_processor_set_performance (data, j, next_state); - if (result) { - result = -EAGAIN; - break; - } + cpus_clear(cmd.mask); - if (policy->shared_type == CPUFREQ_SHARED_TYPE_ANY) - break; - - cpu_set(j, covered_cpus); - } + if (policy->shared_type != CPUFREQ_SHARED_TYPE_ANY) + cmd.mask = online_policy_cpus; + else + cpu_set(policy->cpu, cmd.mask); - for_each_cpu_mask(j, online_policy_cpus) { - freqs.cpu = j; - cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); + freqs.old = data->freq_table[perf->state].frequency; + freqs.new = data->freq_table[next_perf_state].frequency; + for_each_cpu_mask(i, cmd.mask) { + freqs.cpu = i; + cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); } - if (unlikely(result)) { - /* - * We have failed halfway through the frequency change. - * We have sent callbacks to online_policy_cpus and - * acpi_processor_set_performance() has been called on - * coverd_cpus. Best effort undo.. - */ - - if (!cpus_empty(covered_cpus)) { - for_each_cpu_mask(j, covered_cpus) { - policy->cpu = j; - acpi_processor_set_performance (data, - j, - cur_state); - } - } + drv_write(&cmd); - tmp = freqs.new; - freqs.new = freqs.old; - freqs.old = tmp; - for_each_cpu_mask(j, online_policy_cpus) { - freqs.cpu = j; - cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); - cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); + if (acpi_pstate_strict) { + if (!check_freqs(cmd.mask, freqs.new, data)) { + dprintk("acpi_cpufreq_target failed (%d)\n", + policy->cpu); + return -EAGAIN; } } - set_cpus_allowed(current, saved_mask); - return (result); -} + for_each_cpu_mask(i, cmd.mask) { + freqs.cpu = i; + cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); + } + perf->state = next_perf_state; + return result; +} -static int -acpi_cpufreq_verify ( - struct cpufreq_policy *policy) +static int acpi_cpufreq_verify(struct cpufreq_policy *policy) { - unsigned int result = 0; - struct cpufreq_acpi_io *data = acpi_io_data[policy->cpu]; + struct acpi_cpufreq_data *data = drv_data[policy->cpu]; dprintk("acpi_cpufreq_verify\n"); - result = cpufreq_frequency_table_verify(policy, - data->freq_table); - - return (result); + return cpufreq_frequency_table_verify(policy, data->freq_table); } - static unsigned long -acpi_cpufreq_guess_freq ( - struct cpufreq_acpi_io *data, - unsigned int cpu) +acpi_cpufreq_guess_freq(struct acpi_cpufreq_data *data, unsigned int cpu) { - struct acpi_processor_performance *perf = data->acpi_data; + struct acpi_processor_performance *perf = data->acpi_data; if (cpu_khz) { /* search the closest match to cpu_khz */ @@ -338,16 +502,16 @@ acpi_cpufreq_guess_freq ( unsigned long freq; unsigned long freqn = perf->states[0].core_frequency * 1000; - for (i = 0; i < (perf->state_count - 1); i++) { + for (i=0; i<(perf->state_count-1); i++) { freq = freqn; freqn = perf->states[i+1].core_frequency * 1000; if ((2 * cpu_khz) > (freqn + freq)) { perf->state = i; - return (freq); + return freq; } } - perf->state = perf->state_count - 1; - return (freqn); + perf->state = perf->state_count-1; + return freqn; } else { /* assume CPU is at P0... */ perf->state = 0; @@ -355,7 +519,6 @@ acpi_cpufreq_guess_freq ( } } - /* * acpi_cpufreq_early_init - initialize ACPI P-States library * @@ -364,30 +527,34 @@ acpi_cpufreq_guess_freq ( * do _PDC and _PSD and find out the processor dependency for the * actual init that will happen later... */ -static int acpi_cpufreq_early_init_acpi(void) +static int acpi_cpufreq_early_init(void) { - struct acpi_processor_performance *data; - unsigned int i, j; + struct acpi_processor_performance *data; + cpumask_t covered; + unsigned int i, j; dprintk("acpi_cpufreq_early_init\n"); for_each_possible_cpu(i) { - data = kzalloc(sizeof(struct acpi_processor_performance), - GFP_KERNEL); + data = kzalloc(sizeof(struct acpi_processor_performance), + GFP_KERNEL); if (!data) { - for_each_possible_cpu(j) { + for_each_cpu_mask(j, covered) { kfree(acpi_perf_data[j]); acpi_perf_data[j] = NULL; } - return (-ENOMEM); + return -ENOMEM; } acpi_perf_data[i] = data; + cpu_set(i, covered); } /* Do initialization in ACPI core */ - return acpi_processor_preregister_performance(acpi_perf_data); + acpi_processor_preregister_performance(acpi_perf_data); + return 0; } +#ifdef CONFIG_SMP /* * Some BIOSes do SW_ANY coordination internally, either set it up in hw * or do it in BIOS firmware and won't inform about it to OS. If not @@ -414,39 +581,42 @@ static struct dmi_system_id sw_any_bug_dmi_table[] = { }, { } }; +#endif -static int -acpi_cpufreq_cpu_init ( - struct cpufreq_policy *policy) +static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) { - unsigned int i; - unsigned int cpu = policy->cpu; - struct cpufreq_acpi_io *data; - unsigned int result = 0; + unsigned int i; + unsigned int valid_states = 0; + unsigned int cpu = policy->cpu; + struct acpi_cpufreq_data *data; + unsigned int result = 0; struct cpuinfo_x86 *c = &cpu_data[policy->cpu]; - struct acpi_processor_performance *perf; + struct acpi_processor_performance *perf; dprintk("acpi_cpufreq_cpu_init\n"); if (!acpi_perf_data[cpu]) - return (-ENODEV); + return -ENODEV; - data = kzalloc(sizeof(struct cpufreq_acpi_io), GFP_KERNEL); + data = kzalloc(sizeof(struct acpi_cpufreq_data), GFP_KERNEL); if (!data) - return (-ENOMEM); + return -ENOMEM; data->acpi_data = acpi_perf_data[cpu]; - acpi_io_data[cpu] = data; + drv_data[cpu] = data; - result = acpi_processor_register_performance(data->acpi_data, cpu); + if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) + acpi_cpufreq_driver.flags |= CPUFREQ_CONST_LOOPS; + result = acpi_processor_register_performance(data->acpi_data, cpu); if (result) goto err_free; perf = data->acpi_data; policy->shared_type = perf->shared_type; + /* - * Will let policy->cpus know about dependency only when software + * Will let policy->cpus know about dependency only when software * coordination is required. */ if (policy->shared_type == CPUFREQ_SHARED_TYPE_ALL || @@ -462,10 +632,6 @@ acpi_cpufreq_cpu_init ( } #endif - if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) { - acpi_cpufreq_driver.flags |= CPUFREQ_CONST_LOOPS; - } - /* capability check */ if (perf->state_count <= 1) { dprintk("No P-States\n"); @@ -473,17 +639,33 @@ acpi_cpufreq_cpu_init ( goto err_unreg; } - if ((perf->control_register.space_id != ACPI_ADR_SPACE_SYSTEM_IO) || - (perf->status_register.space_id != ACPI_ADR_SPACE_SYSTEM_IO)) { - dprintk("Unsupported address space [%d, %d]\n", - (u32) (perf->control_register.space_id), - (u32) (perf->status_register.space_id)); + if (perf->control_register.space_id != perf->status_register.space_id) { + result = -ENODEV; + goto err_unreg; + } + + switch (perf->control_register.space_id) { + case ACPI_ADR_SPACE_SYSTEM_IO: + dprintk("SYSTEM IO addr space\n"); + data->cpu_feature = SYSTEM_IO_CAPABLE; + break; + case ACPI_ADR_SPACE_FIXED_HARDWARE: + dprintk("HARDWARE addr space\n"); + if (!check_est_cpu(cpu)) { + result = -ENODEV; + goto err_unreg; + } + data->cpu_feature = SYSTEM_INTEL_MSR_CAPABLE; + break; + default: + dprintk("Unknown addr space %d\n", + (u32) (perf->control_register.space_id)); result = -ENODEV; goto err_unreg; } - /* alloc freq_table */ - data->freq_table = kmalloc(sizeof(struct cpufreq_frequency_table) * (perf->state_count + 1), GFP_KERNEL); + data->freq_table = kmalloc(sizeof(struct cpufreq_frequency_table) * + (perf->state_count+1), GFP_KERNEL); if (!data->freq_table) { result = -ENOMEM; goto err_unreg; @@ -492,129 +674,140 @@ acpi_cpufreq_cpu_init ( /* detect transition latency */ policy->cpuinfo.transition_latency = 0; for (i=0; i<perf->state_count; i++) { - if ((perf->states[i].transition_latency * 1000) > policy->cpuinfo.transition_latency) - policy->cpuinfo.transition_latency = perf->states[i].transition_latency * 1000; + if ((perf->states[i].transition_latency * 1000) > + policy->cpuinfo.transition_latency) + policy->cpuinfo.transition_latency = + perf->states[i].transition_latency * 1000; } policy->governor = CPUFREQ_DEFAULT_GOVERNOR; - /* The current speed is unknown and not detectable by ACPI... */ - policy->cur = acpi_cpufreq_guess_freq(data, policy->cpu); - + data->max_freq = perf->states[0].core_frequency * 1000; /* table init */ - for (i=0; i<=perf->state_count; i++) - { - data->freq_table[i].index = i; - if (i<perf->state_count) - data->freq_table[i].frequency = perf->states[i].core_frequency * 1000; - else - data->freq_table[i].frequency = CPUFREQ_TABLE_END; + for (i=0; i<perf->state_count; i++) { + if (i>0 && perf->states[i].core_frequency == + perf->states[i-1].core_frequency) + continue; + + data->freq_table[valid_states].index = i; + data->freq_table[valid_states].frequency = + perf->states[i].core_frequency * 1000; + valid_states++; } + data->freq_table[valid_states].frequency = CPUFREQ_TABLE_END; result = cpufreq_frequency_table_cpuinfo(policy, data->freq_table); - if (result) { + if (result) goto err_freqfree; + + switch (data->cpu_feature) { + case ACPI_ADR_SPACE_SYSTEM_IO: + /* Current speed is unknown and not detectable by IO port */ + policy->cur = acpi_cpufreq_guess_freq(data, policy->cpu); + break; + case ACPI_ADR_SPACE_FIXED_HARDWARE: + acpi_cpufreq_driver.get = get_cur_freq_on_cpu; + get_cur_freq_on_cpu(cpu); + break; + default: + break; } /* notify BIOS that we exist */ acpi_processor_notify_smm(THIS_MODULE); - printk(KERN_INFO "acpi-cpufreq: CPU%u - ACPI performance management activated.\n", - cpu); + /* Check for APERF/MPERF support in hardware */ + if (c->x86_vendor == X86_VENDOR_INTEL && c->cpuid_level >= 6) { + unsigned int ecx; + ecx = cpuid_ecx(6); + if (ecx & CPUID_6_ECX_APERFMPERF_CAPABILITY) + acpi_cpufreq_driver.getavg = get_measured_perf; + } + + dprintk("CPU%u - ACPI performance management activated.\n", cpu); for (i = 0; i < perf->state_count; i++) dprintk(" %cP%d: %d MHz, %d mW, %d uS\n", - (i == perf->state?'*':' '), i, + (i == perf->state ? '*' : ' '), i, (u32) perf->states[i].core_frequency, (u32) perf->states[i].power, (u32) perf->states[i].transition_latency); cpufreq_frequency_table_get_attr(data->freq_table, policy->cpu); - + /* * the first call to ->target() should result in us actually * writing something to the appropriate registers. */ data->resume = 1; - - return (result); - err_freqfree: + return result; + +err_freqfree: kfree(data->freq_table); - err_unreg: +err_unreg: acpi_processor_unregister_performance(perf, cpu); - err_free: +err_free: kfree(data); - acpi_io_data[cpu] = NULL; + drv_data[cpu] = NULL; - return (result); + return result; } - -static int -acpi_cpufreq_cpu_exit ( - struct cpufreq_policy *policy) +static int acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy) { - struct cpufreq_acpi_io *data = acpi_io_data[policy->cpu]; - + struct acpi_cpufreq_data *data = drv_data[policy->cpu]; dprintk("acpi_cpufreq_cpu_exit\n"); if (data) { cpufreq_frequency_table_put_attr(policy->cpu); - acpi_io_data[policy->cpu] = NULL; - acpi_processor_unregister_performance(data->acpi_data, policy->cpu); + drv_data[policy->cpu] = NULL; + acpi_processor_unregister_performance(data->acpi_data, + policy->cpu); kfree(data); } - return (0); + return 0; } -static int -acpi_cpufreq_resume ( - struct cpufreq_policy *policy) +static int acpi_cpufreq_resume(struct cpufreq_policy *policy) { - struct cpufreq_acpi_io *data = acpi_io_data[policy->cpu]; - + struct acpi_cpufreq_data *data = drv_data[policy->cpu]; dprintk("acpi_cpufreq_resume\n"); data->resume = 1; - return (0); + return 0; } - -static struct freq_attr* acpi_cpufreq_attr[] = { +static struct freq_attr *acpi_cpufreq_attr[] = { &cpufreq_freq_attr_scaling_available_freqs, NULL, }; static struct cpufreq_driver acpi_cpufreq_driver = { - .verify = acpi_cpufreq_verify, - .target = acpi_cpufreq_target, - .init = acpi_cpufreq_cpu_init, - .exit = acpi_cpufreq_cpu_exit, - .resume = acpi_cpufreq_resume, - .name = "acpi-cpufreq", - .owner = THIS_MODULE, - .attr = acpi_cpufreq_attr, + .verify = acpi_cpufreq_verify, + .target = acpi_cpufreq_target, + .init = acpi_cpufreq_cpu_init, + .exit = acpi_cpufreq_cpu_exit, + .resume = acpi_cpufreq_resume, + .name = "acpi-cpufreq", + .owner = THIS_MODULE, + .attr = acpi_cpufreq_attr, }; - -static int __init -acpi_cpufreq_init (void) +static int __init acpi_cpufreq_init(void) { dprintk("acpi_cpufreq_init\n"); - acpi_cpufreq_early_init_acpi(); + acpi_cpufreq_early_init(); return cpufreq_register_driver(&acpi_cpufreq_driver); } - -static void __exit -acpi_cpufreq_exit (void) +static void __exit acpi_cpufreq_exit(void) { - unsigned int i; + unsigned int i; dprintk("acpi_cpufreq_exit\n"); cpufreq_unregister_driver(&acpi_cpufreq_driver); @@ -627,7 +820,9 @@ acpi_cpufreq_exit (void) } module_param(acpi_pstate_strict, uint, 0644); -MODULE_PARM_DESC(acpi_pstate_strict, "value 0 or non-zero. non-zero -> strict ACPI checks are performed during frequency changes."); +MODULE_PARM_DESC(acpi_pstate_strict, + "value 0 or non-zero. non-zero -> strict ACPI checks are " + "performed during frequency changes."); late_initcall(acpi_cpufreq_init); module_exit(acpi_cpufreq_exit); diff --git a/arch/i386/kernel/cpu/cpufreq/gx-suspmod.c b/arch/i386/kernel/cpu/cpufreq/gx-suspmod.c index 92afa3bc84f..6667e9cceb9 100644 --- a/arch/i386/kernel/cpu/cpufreq/gx-suspmod.c +++ b/arch/i386/kernel/cpu/cpufreq/gx-suspmod.c @@ -447,7 +447,6 @@ static int __init cpufreq_gx_init(void) int ret; struct gxfreq_params *params; struct pci_dev *gx_pci; - u32 class_rev; /* Test if we have the right hardware */ if ((gx_pci = gx_detect_chipset()) == NULL) @@ -472,8 +471,7 @@ static int __init cpufreq_gx_init(void) pci_read_config_byte(params->cs55x0, PCI_PMER2, &(params->pci_pmer2)); pci_read_config_byte(params->cs55x0, PCI_MODON, &(params->on_duration)); pci_read_config_byte(params->cs55x0, PCI_MODOFF, &(params->off_duration)); - pci_read_config_dword(params->cs55x0, PCI_CLASS_REVISION, &class_rev); - params->pci_rev = class_rev && 0xff; + pci_read_config_byte(params->cs55x0, PCI_REVISION_ID, ¶ms->pci_rev); if ((ret = cpufreq_register_driver(&gx_suspmod_driver))) { kfree(params); diff --git a/arch/i386/kernel/cpu/cpufreq/longhaul.c b/arch/i386/kernel/cpu/cpufreq/longhaul.c index 7233abe5d69..c548daad347 100644 --- a/arch/i386/kernel/cpu/cpufreq/longhaul.c +++ b/arch/i386/kernel/cpu/cpufreq/longhaul.c @@ -410,7 +410,7 @@ static int __init longhaul_get_ranges(void) maxmult=longhaul_get_cpu_mult(); /* Starting with the 1.2GHz parts, theres a 200MHz bus. */ - if ((cpu_khz/1000) > 1200) + if ((cpu_khz/maxmult) > 13400) fsb = 200; else fsb = eblcr_fsb_table_v2[longhaul.bits.MaxMHzFSB]; @@ -583,6 +583,10 @@ static int enable_arbiter_disable(void) if (dev == NULL) { reg = 0x76; dev = pci_find_device(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_862X_0, NULL); + /* Find CN400 V-Link host bridge */ + if (dev == NULL) + dev = pci_find_device(PCI_VENDOR_ID_VIA, 0x7259, NULL); + } if (dev != NULL) { /* Enable access to port 0x22 */ @@ -734,7 +738,7 @@ print_support_type: return 0; err_acpi: - printk(KERN_ERR PFX "No ACPI support. No VT8601 or VT8623 northbridge. Aborting.\n"); + printk(KERN_ERR PFX "No ACPI support. Unsupported northbridge. Aborting.\n"); return -ENODEV; } diff --git a/arch/i386/kernel/cpu/cpufreq/p4-clockmod.c b/arch/i386/kernel/cpu/cpufreq/p4-clockmod.c index 304d2eaa4a1..bec50170b75 100644 --- a/arch/i386/kernel/cpu/cpufreq/p4-clockmod.c +++ b/arch/i386/kernel/cpu/cpufreq/p4-clockmod.c @@ -163,29 +163,27 @@ static int cpufreq_p4_verify(struct cpufreq_policy *policy) static unsigned int cpufreq_p4_get_frequency(struct cpuinfo_x86 *c) { - if ((c->x86 == 0x06) && (c->x86_model == 0x09)) { - /* Pentium M (Banias) */ - printk(KERN_WARNING PFX "Warning: Pentium M detected. " - "The speedstep_centrino module offers voltage scaling" - " in addition of frequency scaling. You should use " - "that instead of p4-clockmod, if possible.\n"); - return speedstep_get_processor_frequency(SPEEDSTEP_PROCESSOR_PM); - } - - if ((c->x86 == 0x06) && (c->x86_model == 0x0D)) { - /* Pentium M (Dothan) */ - printk(KERN_WARNING PFX "Warning: Pentium M detected. " - "The speedstep_centrino module offers voltage scaling" - " in addition of frequency scaling. You should use " - "that instead of p4-clockmod, if possible.\n"); - /* on P-4s, the TSC runs with constant frequency independent whether - * throttling is active or not. */ - p4clockmod_driver.flags |= CPUFREQ_CONST_LOOPS; - return speedstep_get_processor_frequency(SPEEDSTEP_PROCESSOR_PM); + if (c->x86 == 0x06) { + if (cpu_has(c, X86_FEATURE_EST)) + printk(KERN_WARNING PFX "Warning: EST-capable CPU detected. " + "The acpi-cpufreq module offers voltage scaling" + " in addition of frequency scaling. You should use " + "that instead of p4-clockmod, if possible.\n"); + switch (c->x86_model) { + case 0x0E: /* Core */ + case 0x0F: /* Core Duo */ + p4clockmod_driver.flags |= CPUFREQ_CONST_LOOPS; + return speedstep_get_processor_frequency(SPEEDSTEP_PROCESSOR_PCORE); + case 0x0D: /* Pentium M (Dothan) */ + p4clockmod_driver.flags |= CPUFREQ_CONST_LOOPS; + /* fall through */ + case 0x09: /* Pentium M (Banias) */ + return speedstep_get_processor_frequency(SPEEDSTEP_PROCESSOR_PM); + } } if (c->x86 != 0xF) { - printk(KERN_WARNING PFX "Unknown p4-clockmod-capable CPU. Please send an e-mail to <linux@brodo.de>\n"); + printk(KERN_WARNING PFX "Unknown p4-clockmod-capable CPU. Please send an e-mail to <cpufreq@lists.linux.org.uk>\n"); return 0; } diff --git a/arch/i386/kernel/cpu/cpufreq/sc520_freq.c b/arch/i386/kernel/cpu/cpufreq/sc520_freq.c index ef457d50f4a..b8fb4b521c6 100644 --- a/arch/i386/kernel/cpu/cpufreq/sc520_freq.c +++ b/arch/i386/kernel/cpu/cpufreq/sc520_freq.c @@ -153,6 +153,7 @@ static struct cpufreq_driver sc520_freq_driver = { static int __init sc520_freq_init(void) { struct cpuinfo_x86 *c = cpu_data; + int err; /* Test if we have the right hardware */ if(c->x86_vendor != X86_VENDOR_AMD || @@ -166,7 +167,11 @@ static int __init sc520_freq_init(void) return -ENOMEM; } - return cpufreq_register_driver(&sc520_freq_driver); + err = cpufreq_register_driver(&sc520_freq_driver); + if (err) + iounmap(cpuctl); + + return err; } diff --git a/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c b/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c index e8993baf3d1..5113e923163 100644 --- a/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c +++ b/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c @@ -36,6 +36,7 @@ #define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "speedstep-centrino", msg) +#define INTEL_MSR_RANGE (0xffff) struct cpu_id { @@ -379,6 +380,7 @@ static int centrino_cpu_early_init_acpi(void) } +#ifdef CONFIG_SMP /* * Some BIOSes do SW_ANY coordination internally, either set it up in hw * or do it in BIOS firmware and won't inform about it to OS. If not @@ -392,7 +394,6 @@ static int sw_any_bug_found(struct dmi_system_id *d) return 0; } - static struct dmi_system_id sw_any_bug_dmi_table[] = { { .callback = sw_any_bug_found, @@ -405,7 +406,7 @@ static struct dmi_system_id sw_any_bug_dmi_table[] = { }, { } }; - +#endif /* * centrino_cpu_init_acpi - register with ACPI P-States library @@ -463,8 +464,9 @@ static int centrino_cpu_init_acpi(struct cpufreq_policy *policy) } for (i=0; i<p->state_count; i++) { - if (p->states[i].control != p->states[i].status) { - dprintk("Different control (%llu) and status values (%llu)\n", + if ((p->states[i].control & INTEL_MSR_RANGE) != + (p->states[i].status & INTEL_MSR_RANGE)) { + dprintk("Different MSR bits in control (%llu) and status (%llu)\n", p->states[i].control, p->states[i].status); result = -EINVAL; goto err_unreg; @@ -500,7 +502,7 @@ static int centrino_cpu_init_acpi(struct cpufreq_policy *policy) } for (i=0; i<p->state_count; i++) { - centrino_model[cpu]->op_points[i].index = p->states[i].control; + centrino_model[cpu]->op_points[i].index = p->states[i].control & INTEL_MSR_RANGE; centrino_model[cpu]->op_points[i].frequency = p->states[i].core_frequency * 1000; dprintk("adding state %i with frequency %u and control value %04x\n", i, centrino_model[cpu]->op_points[i].frequency, centrino_model[cpu]->op_points[i].index); @@ -531,6 +533,9 @@ static int centrino_cpu_init_acpi(struct cpufreq_policy *policy) /* notify BIOS that we exist */ acpi_processor_notify_smm(THIS_MODULE); + printk("speedstep-centrino with X86_SPEEDSTEP_CENTRINO_ACPI" + "config is deprecated.\n " + "Use X86_ACPI_CPUFREQ (acpi-cpufreq instead.\n" ); return 0; diff --git a/arch/i386/kernel/cpu/cpufreq/speedstep-lib.c b/arch/i386/kernel/cpu/cpufreq/speedstep-lib.c index 4f46cac155c..d59277c0091 100644 --- a/arch/i386/kernel/cpu/cpufreq/speedstep-lib.c +++ b/arch/i386/kernel/cpu/cpufreq/speedstep-lib.c @@ -123,6 +123,36 @@ static unsigned int pentiumM_get_frequency(void) return (msr_tmp * 100 * 1000); } +static unsigned int pentium_core_get_frequency(void) +{ + u32 fsb = 0; + u32 msr_lo, msr_tmp; + + rdmsr(MSR_FSB_FREQ, msr_lo, msr_tmp); + /* see table B-2 of 25366920.pdf */ + switch (msr_lo & 0x07) { + case 5: + fsb = 100000; + break; + case 1: + fsb = 133333; + break; + case 3: + fsb = 166667; + break; + default: + printk(KERN_ERR "PCORE - MSR_FSB_FREQ undefined value"); + } + + rdmsr(MSR_IA32_EBL_CR_POWERON, msr_lo, msr_tmp); + dprintk("PCORE - MSR_IA32_EBL_CR_POWERON: 0x%x 0x%x\n", msr_lo, msr_tmp); + + msr_tmp = (msr_lo >> 22) & 0x1f; + dprintk("bits 22-26 are 0x%x, speed is %u\n", msr_tmp, (msr_tmp * fsb)); + + return (msr_tmp * fsb); +} + static unsigned int pentium4_get_frequency(void) { @@ -174,6 +204,8 @@ static unsigned int pentium4_get_frequency(void) unsigned int speedstep_get_processor_frequency(unsigned int processor) { switch (processor) { + case SPEEDSTEP_PROCESSOR_PCORE: + return pentium_core_get_frequency(); case SPEEDSTEP_PROCESSOR_PM: return pentiumM_get_frequency(); case SPEEDSTEP_PROCESSOR_P4D: diff --git a/arch/i386/kernel/cpu/cpufreq/speedstep-lib.h b/arch/i386/kernel/cpu/cpufreq/speedstep-lib.h index b735429c50b..b11bcc608ca 100644 --- a/arch/i386/kernel/cpu/cpufreq/speedstep-lib.h +++ b/arch/i386/kernel/cpu/cpufreq/speedstep-lib.h @@ -22,6 +22,7 @@ * the speedstep_get_processor_frequency() call. */ #define SPEEDSTEP_PROCESSOR_PM 0xFFFFFF03 /* Pentium M */ #define SPEEDSTEP_PROCESSOR_P4D 0xFFFFFF04 /* desktop P4 */ +#define SPEEDSTEP_PROCESSOR_PCORE 0xFFFFFF05 /* Core */ /* speedstep states -- only two of them */ diff --git a/arch/i386/kernel/cpu/cpufreq/speedstep-smi.c b/arch/i386/kernel/cpu/cpufreq/speedstep-smi.c index c28333d5364..ff0d8980611 100644 --- a/arch/i386/kernel/cpu/cpufreq/speedstep-smi.c +++ b/arch/i386/kernel/cpu/cpufreq/speedstep-smi.c @@ -360,9 +360,6 @@ static int __init speedstep_init(void) case SPEEDSTEP_PROCESSOR_PIII_C: case SPEEDSTEP_PROCESSOR_PIII_C_EARLY: break; - case SPEEDSTEP_PROCESSOR_P4M: - printk(KERN_INFO "speedstep-smi: you're trying to use this cpufreq driver on a Pentium 4-based CPU. Most likely it will not work.\n"); - break; default: speedstep_processor = 0; } diff --git a/arch/powerpc/platforms/4xx/Kconfig b/arch/powerpc/platforms/4xx/Kconfig index ed39d6a3d22..2f2a13ed766 100644 --- a/arch/powerpc/platforms/4xx/Kconfig +++ b/arch/powerpc/platforms/4xx/Kconfig @@ -179,7 +179,7 @@ config BIOS_FIXUP # OAK doesn't exist but wanted to keep this around for any future 403GCX boards config 403GCX bool - depends OAK + depends on OAK default y config 405EP diff --git a/arch/powerpc/platforms/embedded6xx/Kconfig b/arch/powerpc/platforms/embedded6xx/Kconfig index ddbe398fbd4..b3c2ce4cb7a 100644 --- a/arch/powerpc/platforms/embedded6xx/Kconfig +++ b/arch/powerpc/platforms/embedded6xx/Kconfig @@ -35,7 +35,7 @@ config HDPU Select HDPU if configuring a Sky Computers Compute Blade. config HDPU_FEATURES - depends HDPU + depends on HDPU tristate "HDPU-Features" help Select to enable HDPU enhanced features. diff --git a/arch/ppc/Kconfig b/arch/ppc/Kconfig index 692b5ba5320..8eb82efe05a 100644 --- a/arch/ppc/Kconfig +++ b/arch/ppc/Kconfig @@ -624,7 +624,7 @@ config HDPU Select HDPU if configuring a Sky Computers Compute Blade. config HDPU_FEATURES - depends HDPU + depends on HDPU tristate "HDPU-Features" help Select to enable HDPU enhanced features. @@ -735,7 +735,7 @@ config LITE5200 config LITE5200B bool "Freescale LITE5200B" - depends LITE5200 + depends on LITE5200 help Support for the LITE5200B dev board for the MPC5200 from Freescale. This is the new board with 2 PCI slots. diff --git a/arch/ppc/platforms/4xx/Kconfig b/arch/ppc/platforms/4xx/Kconfig index 293bd489e7d..6980de420e9 100644 --- a/arch/ppc/platforms/4xx/Kconfig +++ b/arch/ppc/platforms/4xx/Kconfig @@ -189,7 +189,7 @@ config BIOS_FIXUP # OAK doesn't exist but wanted to keep this around for any future 403GCX boards config 403GCX bool - depends OAK + depends on OAK default y config 405EP diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c index 286bc0b3207..b2e9762e13c 100644 --- a/arch/um/drivers/net_kern.c +++ b/arch/um/drivers/net_kern.c @@ -334,13 +334,12 @@ static int eth_configure(int n, void *init, char *mac, size = transport->private_size + sizeof(struct uml_net_private) + sizeof(((struct uml_net_private *) 0)->user); - device = kmalloc(sizeof(*device), GFP_KERNEL); + device = kzalloc(sizeof(*device), GFP_KERNEL); if (device == NULL) { printk(KERN_ERR "eth_configure failed to allocate uml_net\n"); return(1); } - memset(device, 0, sizeof(*device)); INIT_LIST_HEAD(&device->list); device->index = n; diff --git a/arch/v850/Kconfig b/arch/v850/Kconfig index bcf825875d1..f0d4d72e560 100644 --- a/arch/v850/Kconfig +++ b/arch/v850/Kconfig @@ -105,17 +105,17 @@ menu "Processor type and features" # currently support config V850E_MA1 bool - depends RTE_CB_MA1 + depends on RTE_CB_MA1 default y # Similarly for the RTE-V850E/NB85E-CB - V850E/TEG config V850E_TEG bool - depends RTE_CB_NB85E + depends on RTE_CB_NB85E default y # ... and the RTE-V850E/ME2-CB - V850E/ME2 config V850E_ME2 bool - depends RTE_CB_ME2 + depends on RTE_CB_ME2 default y @@ -123,7 +123,7 @@ menu "Processor type and features" config V850E2_SIM85E2 bool - depends V850E2_SIM85E2C || V850E2_SIM85E2S + depends on V850E2_SIM85E2C || V850E2_SIM85E2S default y @@ -132,7 +132,7 @@ menu "Processor type and features" # V850E2 processors config V850E2 bool - depends V850E2_SIM85E2 || V850E2_FPGA85E2C || V850E2_ANNA + depends on V850E2_SIM85E2 || V850E2_FPGA85E2C || V850E2_ANNA default y @@ -141,7 +141,7 @@ menu "Processor type and features" # Boards in the RTE-x-CB series config RTE_CB bool - depends RTE_CB_MA1 || RTE_CB_NB85E || RTE_CB_ME2 + depends on RTE_CB_MA1 || RTE_CB_NB85E || RTE_CB_ME2 default y config RTE_CB_MULTI @@ -149,28 +149,28 @@ menu "Processor type and features" # RTE_CB_NB85E can either have multi ROM support or not, but # other platforms (currently only RTE_CB_MA1) require it. prompt "Multi monitor ROM support" if RTE_CB_NB85E - depends RTE_CB_MA1 || RTE_CB_NB85E + depends on RTE_CB_MA1 || RTE_CB_NB85E default y config RTE_CB_MULTI_DBTRAP bool "Pass illegal insn trap / dbtrap to kernel" - depends RTE_CB_MULTI + depends on RTE_CB_MULTI default n config RTE_CB_MA1_KSRAM bool "Kernel in SRAM (limits size of kernel)" - depends RTE_CB_MA1 && RTE_CB_MULTI + depends on RTE_CB_MA1 && RTE_CB_MULTI default n config RTE_MB_A_PCI bool "Mother-A PCI support" - depends RTE_CB + depends on RTE_CB default y # The GBUS is used to talk to the RTE-MOTHER-A board config RTE_GBUS_INT bool - depends RTE_MB_A_PCI + depends on RTE_MB_A_PCI default y # The only PCI bus we support is on the RTE-MOTHER-A board @@ -209,7 +209,7 @@ menu "Processor type and features" config ROM_KERNEL bool "Kernel in ROM" - depends V850E2_ANNA || V850E_AS85EP1 || RTE_CB_ME2 + depends on V850E2_ANNA || V850E_AS85EP1 || RTE_CB_ME2 # Some platforms pre-zero memory, in which case the kernel doesn't need to config ZERO_BSS @@ -225,10 +225,10 @@ menu "Processor type and features" config V850E_HIGHRES_TIMER bool "High resolution timer support" - depends V850E_TIMER_D + depends on V850E_TIMER_D config TIME_BOOTUP bool "Time bootup" - depends V850E_HIGHRES_TIMER + depends on V850E_HIGHRES_TIMER config RESET_GUARD bool "Reset Guard" diff --git a/arch/x86_64/kernel/cpufreq/Kconfig b/arch/x86_64/kernel/cpufreq/Kconfig index 81f1562e539..3abcfa3e1ed 100644 --- a/arch/x86_64/kernel/cpufreq/Kconfig +++ b/arch/x86_64/kernel/cpufreq/Kconfig @@ -27,10 +27,13 @@ config X86_POWERNOW_K8_ACPI default y config X86_SPEEDSTEP_CENTRINO - tristate "Intel Enhanced SpeedStep" + tristate "Intel Enhanced SpeedStep (deprecated)" select CPU_FREQ_TABLE depends on ACPI_PROCESSOR help + This is deprecated and this functionality is now merged into + acpi_cpufreq (X86_ACPI_CPUFREQ). Use that driver instead of + speedstep_centrino. This adds the CPUFreq driver for Enhanced SpeedStep enabled mobile CPUs. This means Intel Pentium M (Centrino) CPUs or 64bit enabled Intel Xeons. @@ -50,6 +53,7 @@ config X86_ACPI_CPUFREQ help This driver adds a CPUFreq driver which utilizes the ACPI Processor Performance States. + This driver also supports Intel Enhanced Speedstep. For details, take a look at <file:Documentation/cpu-freq/>. diff --git a/arch/x86_64/kernel/cpufreq/Makefile b/arch/x86_64/kernel/cpufreq/Makefile index d8b59387922..753ce1dd418 100644 --- a/arch/x86_64/kernel/cpufreq/Makefile +++ b/arch/x86_64/kernel/cpufreq/Makefile @@ -5,8 +5,8 @@ SRCDIR := ../../../i386/kernel/cpu/cpufreq obj-$(CONFIG_X86_POWERNOW_K8) += powernow-k8.o -obj-$(CONFIG_X86_SPEEDSTEP_CENTRINO) += speedstep-centrino.o obj-$(CONFIG_X86_ACPI_CPUFREQ) += acpi-cpufreq.o +obj-$(CONFIG_X86_SPEEDSTEP_CENTRINO) += speedstep-centrino.o obj-$(CONFIG_X86_P4_CLOCKMOD) += p4-clockmod.o obj-$(CONFIG_X86_SPEEDSTEP_LIB) += speedstep-lib.o diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig index b10f4d8fdc7..0a3aee29e06 100644 --- a/drivers/char/Kconfig +++ b/drivers/char/Kconfig @@ -867,7 +867,7 @@ config SONYPI config TANBAC_TB0219 tristate "TANBAC TB0219 base board support" - depends TANBAC_TB022X + depends on TANBAC_TB022X select GPIO_VR41XX source "drivers/char/agp/Kconfig" diff --git a/drivers/char/watchdog/at91rm9200_wdt.c b/drivers/char/watchdog/at91rm9200_wdt.c index cb86967e2c5..38bd3737259 100644 --- a/drivers/char/watchdog/at91rm9200_wdt.c +++ b/drivers/char/watchdog/at91rm9200_wdt.c @@ -203,9 +203,9 @@ static int __init at91wdt_probe(struct platform_device *pdev) { int res; - if (at91wdt_miscdev.dev) + if (at91wdt_miscdev.parent) return -EBUSY; - at91wdt_miscdev.dev = &pdev->dev; + at91wdt_miscdev.parent = &pdev->dev; res = misc_register(&at91wdt_miscdev); if (res) @@ -221,7 +221,7 @@ static int __exit at91wdt_remove(struct platform_device *pdev) res = misc_deregister(&at91wdt_miscdev); if (!res) - at91wdt_miscdev.dev = NULL; + at91wdt_miscdev.parent = NULL; return res; } diff --git a/drivers/char/watchdog/mpcore_wdt.c b/drivers/char/watchdog/mpcore_wdt.c index 3404a9c67f0..e88947f8fe5 100644 --- a/drivers/char/watchdog/mpcore_wdt.c +++ b/drivers/char/watchdog/mpcore_wdt.c @@ -347,7 +347,7 @@ static int __devinit mpcore_wdt_probe(struct platform_device *dev) goto err_free; } - mpcore_wdt_miscdev.dev = &dev->dev; + mpcore_wdt_miscdev.parent = &dev->dev; ret = misc_register(&mpcore_wdt_miscdev); if (ret) { dev_printk(KERN_ERR, _dev, "cannot register miscdev on minor=%d (err=%d)\n", diff --git a/drivers/char/watchdog/omap_wdt.c b/drivers/char/watchdog/omap_wdt.c index 5dbd7dc2936..6c6f97332db 100644 --- a/drivers/char/watchdog/omap_wdt.c +++ b/drivers/char/watchdog/omap_wdt.c @@ -290,7 +290,7 @@ static int __init omap_wdt_probe(struct platform_device *pdev) omap_wdt_disable(); omap_wdt_adjust_timeout(timer_margin); - omap_wdt_miscdev.dev = &pdev->dev; + omap_wdt_miscdev.parent = &pdev->dev; ret = misc_register(&omap_wdt_miscdev); if (ret) goto fail; diff --git a/drivers/char/watchdog/pcwd_usb.c b/drivers/char/watchdog/pcwd_usb.c index 61138726b50..2da5ac99687 100644 --- a/drivers/char/watchdog/pcwd_usb.c +++ b/drivers/char/watchdog/pcwd_usb.c @@ -42,6 +42,7 @@ #include <asm/uaccess.h> #include <linux/usb.h> #include <linux/mutex.h> +#include <linux/hid.h> /* For HID_REQ_SET_REPORT & HID_DT_REPORT */ #ifdef CONFIG_USB_DEBUG @@ -109,10 +110,6 @@ MODULE_DEVICE_TABLE (usb, usb_pcwd_table); #define CMD_ENABLE_WATCHDOG 0x30 /* Enable / Disable Watchdog */ #define CMD_DISABLE_WATCHDOG CMD_ENABLE_WATCHDOG -/* Some defines that I like to be somewhere else like include/linux/usb_hid.h */ -#define HID_REQ_SET_REPORT 0x09 -#define HID_DT_REPORT (USB_TYPE_CLASS | 0x02) - /* We can only use 1 card due to the /dev/watchdog restriction */ static int cards_found; diff --git a/drivers/char/watchdog/rm9k_wdt.c b/drivers/char/watchdog/rm9k_wdt.c index ec3909371c2..7576a13e86b 100644 --- a/drivers/char/watchdog/rm9k_wdt.c +++ b/drivers/char/watchdog/rm9k_wdt.c @@ -47,7 +47,7 @@ /* Function prototypes */ -static irqreturn_t wdt_gpi_irqhdl(int, void *, struct pt_regs *); +static irqreturn_t wdt_gpi_irqhdl(int, void *); static void wdt_gpi_start(void); static void wdt_gpi_stop(void); static void wdt_gpi_set_timeout(unsigned int); @@ -94,8 +94,28 @@ module_param(nowayout, bool, 0444); MODULE_PARM_DESC(nowayout, "Watchdog cannot be disabled once started"); +/* Kernel interfaces */ +static struct file_operations fops = { + .owner = THIS_MODULE, + .open = wdt_gpi_open, + .release = wdt_gpi_release, + .write = wdt_gpi_write, + .unlocked_ioctl = wdt_gpi_ioctl, +}; + +static struct miscdevice miscdev = { + .minor = WATCHDOG_MINOR, + .name = wdt_gpi_name, + .fops = &fops, +}; + +static struct notifier_block wdt_gpi_shutdown = { + .notifier_call = wdt_gpi_notify, +}; + + /* Interrupt handler */ -static irqreturn_t wdt_gpi_irqhdl(int irq, void *ctxt, struct pt_regs *regs) +static irqreturn_t wdt_gpi_irqhdl(int irq, void *ctxt) { if (!unlikely(__raw_readl(wd_regs + 0x0008) & 0x1)) return IRQ_NONE; @@ -312,26 +332,6 @@ wdt_gpi_notify(struct notifier_block *this, unsigned long code, void *unused) } -/* Kernel interfaces */ -static struct file_operations fops = { - .owner = THIS_MODULE, - .open = wdt_gpi_open, - .release = wdt_gpi_release, - .write = wdt_gpi_write, - .unlocked_ioctl = wdt_gpi_ioctl, -}; - -static struct miscdevice miscdev = { - .minor = WATCHDOG_MINOR, - .name = wdt_gpi_name, - .fops = &fops, -}; - -static struct notifier_block wdt_gpi_shutdown = { - .notifier_call = wdt_gpi_notify, -}; - - /* Init & exit procedures */ static const struct resource * wdt_gpi_get_resource(struct platform_device *pdv, const char *name, diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 47ab42db122..9fb2edf3661 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -29,7 +29,8 @@ #include <linux/completion.h> #include <linux/mutex.h> -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_CORE, "cpufreq-core", msg) +#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_CORE, \ + "cpufreq-core", msg) /** * The "cpufreq driver" - the arch- or hardware-dependent low @@ -151,7 +152,8 @@ static void cpufreq_debug_disable_ratelimit(void) spin_unlock_irqrestore(&disable_ratelimit_lock, flags); } -void cpufreq_debug_printk(unsigned int type, const char *prefix, const char *fmt, ...) +void cpufreq_debug_printk(unsigned int type, const char *prefix, + const char *fmt, ...) { char s[256]; va_list args; @@ -161,7 +163,8 @@ void cpufreq_debug_printk(unsigned int type, const char *prefix, const char *fmt WARN_ON(!prefix); if (type & debug) { spin_lock_irqsave(&disable_ratelimit_lock, flags); - if (!disable_ratelimit && debug_ratelimit && !printk_ratelimit()) { + if (!disable_ratelimit && debug_ratelimit + && !printk_ratelimit()) { spin_unlock_irqrestore(&disable_ratelimit_lock, flags); return; } @@ -182,10 +185,12 @@ EXPORT_SYMBOL(cpufreq_debug_printk); module_param(debug, uint, 0644); -MODULE_PARM_DESC(debug, "CPUfreq debugging: add 1 to debug core, 2 to debug drivers, and 4 to debug governors."); +MODULE_PARM_DESC(debug, "CPUfreq debugging: add 1 to debug core," + " 2 to debug drivers, and 4 to debug governors."); module_param(debug_ratelimit, uint, 0644); -MODULE_PARM_DESC(debug_ratelimit, "CPUfreq debugging: set to 0 to disable ratelimiting."); +MODULE_PARM_DESC(debug_ratelimit, "CPUfreq debugging:" + " set to 0 to disable ratelimiting."); #else /* !CONFIG_CPU_FREQ_DEBUG */ @@ -219,17 +224,23 @@ static void adjust_jiffies(unsigned long val, struct cpufreq_freqs *ci) if (!l_p_j_ref_freq) { l_p_j_ref = loops_per_jiffy; l_p_j_ref_freq = ci->old; - dprintk("saving %lu as reference value for loops_per_jiffy; freq is %u kHz\n", l_p_j_ref, l_p_j_ref_freq); + dprintk("saving %lu as reference value for loops_per_jiffy;" + "freq is %u kHz\n", l_p_j_ref, l_p_j_ref_freq); } if ((val == CPUFREQ_PRECHANGE && ci->old < ci->new) || (val == CPUFREQ_POSTCHANGE && ci->old > ci->new) || (val == CPUFREQ_RESUMECHANGE || val == CPUFREQ_SUSPENDCHANGE)) { - loops_per_jiffy = cpufreq_scale(l_p_j_ref, l_p_j_ref_freq, ci->new); - dprintk("scaling loops_per_jiffy to %lu for frequency %u kHz\n", loops_per_jiffy, ci->new); + loops_per_jiffy = cpufreq_scale(l_p_j_ref, l_p_j_ref_freq, + ci->new); + dprintk("scaling loops_per_jiffy to %lu" + "for frequency %u kHz\n", loops_per_jiffy, ci->new); } } #else -static inline void adjust_jiffies(unsigned long val, struct cpufreq_freqs *ci) { return; } +static inline void adjust_jiffies(unsigned long val, struct cpufreq_freqs *ci) +{ + return; +} #endif @@ -316,7 +327,8 @@ static int cpufreq_parse_governor (char *str_governor, unsigned int *policy, if (!strnicmp(str_governor, "performance", CPUFREQ_NAME_LEN)) { *policy = CPUFREQ_POLICY_PERFORMANCE; err = 0; - } else if (!strnicmp(str_governor, "powersave", CPUFREQ_NAME_LEN)) { + } else if (!strnicmp(str_governor, "powersave", + CPUFREQ_NAME_LEN)) { *policy = CPUFREQ_POLICY_POWERSAVE; err = 0; } @@ -328,7 +340,8 @@ static int cpufreq_parse_governor (char *str_governor, unsigned int *policy, t = __find_governor(str_governor); if (t == NULL) { - char *name = kasprintf(GFP_KERNEL, "cpufreq_%s", str_governor); + char *name = kasprintf(GFP_KERNEL, "cpufreq_%s", + str_governor); if (name) { int ret; @@ -361,7 +374,8 @@ extern struct sysdev_class cpu_sysdev_class; /** - * cpufreq_per_cpu_attr_read() / show_##file_name() - print out cpufreq information + * cpufreq_per_cpu_attr_read() / show_##file_name() - + * print out cpufreq information * * Write out information from cpufreq_driver->policy[cpu]; object must be * "unsigned int". @@ -380,7 +394,8 @@ show_one(scaling_min_freq, min); show_one(scaling_max_freq, max); show_one(scaling_cur_freq, cur); -static int __cpufreq_set_policy(struct cpufreq_policy *data, struct cpufreq_policy *policy); +static int __cpufreq_set_policy(struct cpufreq_policy *data, + struct cpufreq_policy *policy); /** * cpufreq_per_cpu_attr_write() / store_##file_name() - sysfs write access @@ -416,7 +431,8 @@ store_one(scaling_max_freq,max); /** * show_cpuinfo_cur_freq - current CPU frequency as detected by hardware */ -static ssize_t show_cpuinfo_cur_freq (struct cpufreq_policy * policy, char *buf) +static ssize_t show_cpuinfo_cur_freq (struct cpufreq_policy * policy, + char *buf) { unsigned int cur_freq = cpufreq_get(policy->cpu); if (!cur_freq) @@ -428,7 +444,8 @@ static ssize_t show_cpuinfo_cur_freq (struct cpufreq_policy * policy, char *buf) /** * show_scaling_governor - show the current policy for the specified CPU */ -static ssize_t show_scaling_governor (struct cpufreq_policy * policy, char *buf) +static ssize_t show_scaling_governor (struct cpufreq_policy * policy, + char *buf) { if(policy->policy == CPUFREQ_POLICY_POWERSAVE) return sprintf(buf, "powersave\n"); @@ -458,7 +475,8 @@ static ssize_t store_scaling_governor (struct cpufreq_policy * policy, if (ret != 1) return -EINVAL; - if (cpufreq_parse_governor(str_governor, &new_policy.policy, &new_policy.governor)) + if (cpufreq_parse_governor(str_governor, &new_policy.policy, + &new_policy.governor)) return -EINVAL; lock_cpu_hotplug(); @@ -474,7 +492,10 @@ static ssize_t store_scaling_governor (struct cpufreq_policy * policy, unlock_cpu_hotplug(); - return ret ? ret : count; + if (ret) + return ret; + else + return count; } /** @@ -488,7 +509,7 @@ static ssize_t show_scaling_driver (struct cpufreq_policy * policy, char *buf) /** * show_scaling_available_governors - show the available CPUfreq governors */ -static ssize_t show_scaling_available_governors (struct cpufreq_policy * policy, +static ssize_t show_scaling_available_governors (struct cpufreq_policy *policy, char *buf) { ssize_t i = 0; @@ -574,7 +595,11 @@ static ssize_t show(struct kobject * kobj, struct attribute * attr ,char * buf) policy = cpufreq_cpu_get(policy->cpu); if (!policy) return -EINVAL; - ret = fattr->show ? fattr->show(policy,buf) : -EIO; + if (fattr->show) + ret = fattr->show(policy, buf); + else + ret = -EIO; + cpufreq_cpu_put(policy); return ret; } @@ -588,7 +613,11 @@ static ssize_t store(struct kobject * kobj, struct attribute * attr, policy = cpufreq_cpu_get(policy->cpu); if (!policy) return -EINVAL; - ret = fattr->store ? fattr->store(policy,buf,count) : -EIO; + if (fattr->store) + ret = fattr->store(policy, buf, count); + else + ret = -EIO; + cpufreq_cpu_put(policy); return ret; } @@ -913,7 +942,8 @@ static void handle_update(struct work_struct *work) * We adjust to current frequency first, and need to clean up later. So either call * to cpufreq_update_policy() or schedule handle_update()). */ -static void cpufreq_out_of_sync(unsigned int cpu, unsigned int old_freq, unsigned int new_freq) +static void cpufreq_out_of_sync(unsigned int cpu, unsigned int old_freq, + unsigned int new_freq) { struct cpufreq_freqs freqs; @@ -938,16 +968,16 @@ static void cpufreq_out_of_sync(unsigned int cpu, unsigned int old_freq, unsigne unsigned int cpufreq_quick_get(unsigned int cpu) { struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); - unsigned int ret = 0; + unsigned int ret_freq = 0; if (policy) { mutex_lock(&policy->lock); - ret = policy->cur; + ret_freq = policy->cur; mutex_unlock(&policy->lock); cpufreq_cpu_put(policy); } - return (ret); + return (ret_freq); } EXPORT_SYMBOL(cpufreq_quick_get); @@ -961,7 +991,7 @@ EXPORT_SYMBOL(cpufreq_quick_get); unsigned int cpufreq_get(unsigned int cpu) { struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); - unsigned int ret = 0; + unsigned int ret_freq = 0; if (!policy) return 0; @@ -971,12 +1001,14 @@ unsigned int cpufreq_get(unsigned int cpu) mutex_lock(&policy->lock); - ret = cpufreq_driver->get(cpu); + ret_freq = cpufreq_driver->get(cpu); - if (ret && policy->cur && !(cpufreq_driver->flags & CPUFREQ_CONST_LOOPS)) { - /* verify no discrepancy between actual and saved value exists */ - if (unlikely(ret != policy->cur)) { - cpufreq_out_of_sync(cpu, policy->cur, ret); + if (ret_freq && policy->cur && + !(cpufreq_driver->flags & CPUFREQ_CONST_LOOPS)) { + /* verify no discrepancy between actual and + saved value exists */ + if (unlikely(ret_freq != policy->cur)) { + cpufreq_out_of_sync(cpu, policy->cur, ret_freq); schedule_work(&policy->update); } } @@ -986,7 +1018,7 @@ unsigned int cpufreq_get(unsigned int cpu) out: cpufreq_cpu_put(policy); - return (ret); + return (ret_freq); } EXPORT_SYMBOL(cpufreq_get); @@ -998,7 +1030,7 @@ EXPORT_SYMBOL(cpufreq_get); static int cpufreq_suspend(struct sys_device * sysdev, pm_message_t pmsg) { int cpu = sysdev->id; - unsigned int ret = 0; + int ret = 0; unsigned int cur_freq = 0; struct cpufreq_policy *cpu_policy; @@ -1080,7 +1112,7 @@ out: static int cpufreq_resume(struct sys_device * sysdev) { int cpu = sysdev->id; - unsigned int ret = 0; + int ret = 0; struct cpufreq_policy *cpu_policy; dprintk("resuming cpu %u\n", cpu); @@ -1276,22 +1308,45 @@ int cpufreq_driver_target(struct cpufreq_policy *policy, } EXPORT_SYMBOL_GPL(cpufreq_driver_target); +int cpufreq_driver_getavg(struct cpufreq_policy *policy) +{ + int ret = 0; + + policy = cpufreq_cpu_get(policy->cpu); + if (!policy) + return -EINVAL; + + mutex_lock(&policy->lock); + + if (cpu_online(policy->cpu) && cpufreq_driver->getavg) + ret = cpufreq_driver->getavg(policy->cpu); + + mutex_unlock(&policy->lock); + + cpufreq_cpu_put(policy); + return ret; +} +EXPORT_SYMBOL_GPL(cpufreq_driver_getavg); + /* * Locking: Must be called with the lock_cpu_hotplug() lock held * when "event" is CPUFREQ_GOV_LIMITS */ -static int __cpufreq_governor(struct cpufreq_policy *policy, unsigned int event) +static int __cpufreq_governor(struct cpufreq_policy *policy, + unsigned int event) { int ret; if (!try_module_get(policy->governor->owner)) return -EINVAL; - dprintk("__cpufreq_governor for CPU %u, event %u\n", policy->cpu, event); + dprintk("__cpufreq_governor for CPU %u, event %u\n", + policy->cpu, event); ret = policy->governor->governor(policy, event); - /* we keep one module reference alive for each CPU governed by this CPU */ + /* we keep one module reference alive for + each CPU governed by this CPU */ if ((event != CPUFREQ_GOV_START) || ret) module_put(policy->governor->owner); if ((event == CPUFREQ_GOV_STOP) && !ret) @@ -1367,9 +1422,12 @@ EXPORT_SYMBOL(cpufreq_get_policy); /* + * data : current policy. + * policy : policy to be set. * Locking: Must be called with the lock_cpu_hotplug() lock held */ -static int __cpufreq_set_policy(struct cpufreq_policy *data, struct cpufreq_policy *policy) +static int __cpufreq_set_policy(struct cpufreq_policy *data, + struct cpufreq_policy *policy) { int ret = 0; @@ -1377,7 +1435,8 @@ static int __cpufreq_set_policy(struct cpufreq_policy *data, struct cpufreq_poli dprintk("setting new policy for CPU %u: %u - %u kHz\n", policy->cpu, policy->min, policy->max); - memcpy(&policy->cpuinfo, &data->cpuinfo, sizeof(struct cpufreq_cpuinfo)); + memcpy(&policy->cpuinfo, &data->cpuinfo, + sizeof(struct cpufreq_cpuinfo)); if (policy->min > data->min && policy->min > policy->max) { ret = -EINVAL; @@ -1410,7 +1469,8 @@ static int __cpufreq_set_policy(struct cpufreq_policy *data, struct cpufreq_poli data->min = policy->min; data->max = policy->max; - dprintk("new min and max freqs are %u - %u kHz\n", data->min, data->max); + dprintk("new min and max freqs are %u - %u kHz\n", + data->min, data->max); if (cpufreq_driver->setpolicy) { data->policy = policy->policy; @@ -1431,10 +1491,12 @@ static int __cpufreq_set_policy(struct cpufreq_policy *data, struct cpufreq_poli data->governor = policy->governor; if (__cpufreq_governor(data, CPUFREQ_GOV_START)) { /* new governor failed, so re-start old one */ - dprintk("starting governor %s failed\n", data->governor->name); + dprintk("starting governor %s failed\n", + data->governor->name); if (old_gov) { data->governor = old_gov; - __cpufreq_governor(data, CPUFREQ_GOV_START); + __cpufreq_governor(data, + CPUFREQ_GOV_START); } ret = -EINVAL; goto error_out; @@ -1524,7 +1586,8 @@ int cpufreq_update_policy(unsigned int cpu) data->cur = policy.cur; } else { if (data->cur != policy.cur) - cpufreq_out_of_sync(cpu, data->cur, policy.cur); + cpufreq_out_of_sync(cpu, data->cur, + policy.cur); } } @@ -1626,8 +1689,10 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data) /* if all ->init() calls failed, unregister */ if (ret) { - dprintk("no CPU initialized for driver %s\n", driver_data->name); - sysdev_driver_unregister(&cpu_sysdev_class, &cpufreq_sysdev_driver); + dprintk("no CPU initialized for driver %s\n", + driver_data->name); + sysdev_driver_unregister(&cpu_sysdev_class, + &cpufreq_sysdev_driver); spin_lock_irqsave(&cpufreq_driver_lock, flags); cpufreq_driver = NULL; diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c index 5ef5ede5b88..eef0270c6f3 100644 --- a/drivers/cpufreq/cpufreq_conservative.c +++ b/drivers/cpufreq/cpufreq_conservative.c @@ -44,15 +44,17 @@ * latency of the processor. The governor will work on any processor with * transition latency <= 10mS, using appropriate sampling * rate. - * For CPUs with transition latency > 10mS (mostly drivers with CPUFREQ_ETERNAL) - * this governor will not work. + * For CPUs with transition latency > 10mS (mostly drivers + * with CPUFREQ_ETERNAL), this governor will not work. * All times here are in uS. */ static unsigned int def_sampling_rate; #define MIN_SAMPLING_RATE_RATIO (2) /* for correct statistics, we need at least 10 ticks between each measure */ -#define MIN_STAT_SAMPLING_RATE (MIN_SAMPLING_RATE_RATIO * jiffies_to_usecs(10)) -#define MIN_SAMPLING_RATE (def_sampling_rate / MIN_SAMPLING_RATE_RATIO) +#define MIN_STAT_SAMPLING_RATE \ + (MIN_SAMPLING_RATE_RATIO * jiffies_to_usecs(10)) +#define MIN_SAMPLING_RATE \ + (def_sampling_rate / MIN_SAMPLING_RATE_RATIO) #define MAX_SAMPLING_RATE (500 * def_sampling_rate) #define DEF_SAMPLING_RATE_LATENCY_MULTIPLIER (1000) #define DEF_SAMPLING_DOWN_FACTOR (1) @@ -103,11 +105,16 @@ static struct dbs_tuners dbs_tuners_ins = { static inline unsigned int get_cpu_idle_time(unsigned int cpu) { - return kstat_cpu(cpu).cpustat.idle + + unsigned int add_nice = 0, ret; + + if (dbs_tuners_ins.ignore_nice) + add_nice = kstat_cpu(cpu).cpustat.nice; + + ret = kstat_cpu(cpu).cpustat.idle + kstat_cpu(cpu).cpustat.iowait + - ( dbs_tuners_ins.ignore_nice ? - kstat_cpu(cpu).cpustat.nice : - 0); + add_nice; + + return ret; } /************************** sysfs interface ************************/ @@ -452,6 +459,7 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy, unsigned int cpu = policy->cpu; struct cpu_dbs_info_s *this_dbs_info; unsigned int j; + int rc; this_dbs_info = &per_cpu(cpu_dbs_info, cpu); @@ -468,6 +476,13 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy, break; mutex_lock(&dbs_mutex); + + rc = sysfs_create_group(&policy->kobj, &dbs_attr_group); + if (rc) { + mutex_unlock(&dbs_mutex); + return rc; + } + for_each_cpu_mask(j, policy->cpus) { struct cpu_dbs_info_s *j_dbs_info; j_dbs_info = &per_cpu(cpu_dbs_info, j); @@ -480,7 +495,7 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy, this_dbs_info->enable = 1; this_dbs_info->down_skip = 0; this_dbs_info->requested_freq = policy->cur; - sysfs_create_group(&policy->kobj, &dbs_attr_group); + dbs_enable++; /* * Start the timerschedule work, when this governor diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c index e1cc5113c2a..f697449327c 100644 --- a/drivers/cpufreq/cpufreq_ondemand.c +++ b/drivers/cpufreq/cpufreq_ondemand.c @@ -41,8 +41,10 @@ static unsigned int def_sampling_rate; #define MIN_SAMPLING_RATE_RATIO (2) /* for correct statistics, we need at least 10 ticks between each measure */ -#define MIN_STAT_SAMPLING_RATE (MIN_SAMPLING_RATE_RATIO * jiffies_to_usecs(10)) -#define MIN_SAMPLING_RATE (def_sampling_rate / MIN_SAMPLING_RATE_RATIO) +#define MIN_STAT_SAMPLING_RATE \ + (MIN_SAMPLING_RATE_RATIO * jiffies_to_usecs(10)) +#define MIN_SAMPLING_RATE \ + (def_sampling_rate / MIN_SAMPLING_RATE_RATIO) #define MAX_SAMPLING_RATE (500 * def_sampling_rate) #define DEF_SAMPLING_RATE_LATENCY_MULTIPLIER (1000) #define TRANSITION_LATENCY_LIMIT (10 * 1000) @@ -206,7 +208,8 @@ static ssize_t store_sampling_rate(struct cpufreq_policy *unused, ret = sscanf(buf, "%u", &input); mutex_lock(&dbs_mutex); - if (ret != 1 || input > MAX_SAMPLING_RATE || input < MIN_SAMPLING_RATE) { + if (ret != 1 || input > MAX_SAMPLING_RATE + || input < MIN_SAMPLING_RATE) { mutex_unlock(&dbs_mutex); return -EINVAL; } @@ -397,8 +400,15 @@ static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info) * policy. To be safe, we focus 10 points under the threshold. */ if (load < (dbs_tuners_ins.up_threshold - 10)) { - unsigned int freq_next = (policy->cur * load) / + unsigned int freq_next, freq_cur; + + freq_cur = cpufreq_driver_getavg(policy); + if (!freq_cur) + freq_cur = policy->cur; + + freq_next = (freq_cur * load) / (dbs_tuners_ins.up_threshold - 10); + if (!dbs_tuners_ins.powersave_bias) { __cpufreq_driver_target(policy, freq_next, CPUFREQ_RELATION_L); @@ -472,6 +482,7 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy, unsigned int cpu = policy->cpu; struct cpu_dbs_info_s *this_dbs_info; unsigned int j; + int rc; this_dbs_info = &per_cpu(cpu_dbs_info, cpu); @@ -494,12 +505,23 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy, if (dbs_enable == 1) { kondemand_wq = create_workqueue("kondemand"); if (!kondemand_wq) { - printk(KERN_ERR "Creation of kondemand failed\n"); + printk(KERN_ERR + "Creation of kondemand failed\n"); dbs_enable--; mutex_unlock(&dbs_mutex); return -ENOSPC; } } + + rc = sysfs_create_group(&policy->kobj, &dbs_attr_group); + if (rc) { + if (dbs_enable == 1) + destroy_workqueue(kondemand_wq); + dbs_enable--; + mutex_unlock(&dbs_mutex); + return rc; + } + for_each_cpu_mask(j, policy->cpus) { struct cpu_dbs_info_s *j_dbs_info; j_dbs_info = &per_cpu(cpu_dbs_info, j); @@ -509,7 +531,6 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy, j_dbs_info->prev_cpu_wall = get_jiffies_64(); } this_dbs_info->enable = 1; - sysfs_create_group(&policy->kobj, &dbs_attr_group); /* * Start the timerschedule work, when this governor * is used for first time diff --git a/drivers/cpufreq/cpufreq_performance.c b/drivers/cpufreq/cpufreq_performance.c index de91e3371ef..e8e1451ef1c 100644 --- a/drivers/cpufreq/cpufreq_performance.c +++ b/drivers/cpufreq/cpufreq_performance.c @@ -15,7 +15,8 @@ #include <linux/cpufreq.h> #include <linux/init.h> -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_GOVERNOR, "performance", msg) +#define dprintk(msg...) \ + cpufreq_debug_printk(CPUFREQ_DEBUG_GOVERNOR, "performance", msg) static int cpufreq_governor_performance(struct cpufreq_policy *policy, @@ -24,8 +25,10 @@ static int cpufreq_governor_performance(struct cpufreq_policy *policy, switch (event) { case CPUFREQ_GOV_START: case CPUFREQ_GOV_LIMITS: - dprintk("setting to %u kHz because of event %u\n", policy->max, event); - __cpufreq_driver_target(policy, policy->max, CPUFREQ_RELATION_H); + dprintk("setting to %u kHz because of event %u\n", + policy->max, event); + __cpufreq_driver_target(policy, policy->max, + CPUFREQ_RELATION_H); break; default: break; diff --git a/drivers/cpufreq/cpufreq_powersave.c b/drivers/cpufreq/cpufreq_powersave.c index 0a2596044e6..13fe06b94b0 100644 --- a/drivers/cpufreq/cpufreq_powersave.c +++ b/drivers/cpufreq/cpufreq_powersave.c @@ -15,7 +15,8 @@ #include <linux/cpufreq.h> #include <linux/init.h> -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_GOVERNOR, "powersave", msg) +#define dprintk(msg...) \ + cpufreq_debug_printk(CPUFREQ_DEBUG_GOVERNOR, "powersave", msg) static int cpufreq_governor_powersave(struct cpufreq_policy *policy, unsigned int event) @@ -23,8 +24,10 @@ static int cpufreq_governor_powersave(struct cpufreq_policy *policy, switch (event) { case CPUFREQ_GOV_START: case CPUFREQ_GOV_LIMITS: - dprintk("setting to %u kHz because of event %u\n", policy->min, event); - __cpufreq_driver_target(policy, policy->min, CPUFREQ_RELATION_L); + dprintk("setting to %u kHz because of event %u\n", + policy->min, event); + __cpufreq_driver_target(policy, policy->min, + CPUFREQ_RELATION_L); break; default: break; diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c index c2ecc599dc5..6742b1adf2c 100644 --- a/drivers/cpufreq/cpufreq_stats.c +++ b/drivers/cpufreq/cpufreq_stats.c @@ -351,8 +351,8 @@ __init cpufreq_stats_init(void) register_hotcpu_notifier(&cpufreq_stat_cpu_notifier); for_each_online_cpu(cpu) { - cpufreq_stat_cpu_callback(&cpufreq_stat_cpu_notifier, CPU_ONLINE, - (void *)(long)cpu); + cpufreq_stat_cpu_callback(&cpufreq_stat_cpu_notifier, + CPU_ONLINE, (void *)(long)cpu); } return 0; } @@ -368,14 +368,15 @@ __exit cpufreq_stats_exit(void) unregister_hotcpu_notifier(&cpufreq_stat_cpu_notifier); lock_cpu_hotplug(); for_each_online_cpu(cpu) { - cpufreq_stat_cpu_callback(&cpufreq_stat_cpu_notifier, CPU_DEAD, - (void *)(long)cpu); + cpufreq_stat_cpu_callback(&cpufreq_stat_cpu_notifier, + CPU_DEAD, (void *)(long)cpu); } unlock_cpu_hotplug(); } MODULE_AUTHOR ("Zou Nan hai <nanhai.zou@intel.com>"); -MODULE_DESCRIPTION ("'cpufreq_stats' - A driver to export cpufreq stats through sysfs filesystem"); +MODULE_DESCRIPTION ("'cpufreq_stats' - A driver to export cpufreq stats" + "through sysfs filesystem"); MODULE_LICENSE ("GPL"); module_init(cpufreq_stats_init); diff --git a/drivers/cpufreq/cpufreq_userspace.c b/drivers/cpufreq/cpufreq_userspace.c index a06c204589c..2a4eb0bfaf3 100644 --- a/drivers/cpufreq/cpufreq_userspace.c +++ b/drivers/cpufreq/cpufreq_userspace.c @@ -131,19 +131,26 @@ static int cpufreq_governor_userspace(struct cpufreq_policy *policy, unsigned int event) { unsigned int cpu = policy->cpu; + int rc = 0; + switch (event) { case CPUFREQ_GOV_START: if (!cpu_online(cpu)) return -EINVAL; BUG_ON(!policy->cur); mutex_lock(&userspace_mutex); + rc = sysfs_create_file (&policy->kobj, + &freq_attr_scaling_setspeed.attr); + if (rc) + goto start_out; + cpu_is_managed[cpu] = 1; cpu_min_freq[cpu] = policy->min; cpu_max_freq[cpu] = policy->max; cpu_cur_freq[cpu] = policy->cur; cpu_set_freq[cpu] = policy->cur; - sysfs_create_file (&policy->kobj, &freq_attr_scaling_setspeed.attr); dprintk("managing cpu %u started (%u - %u kHz, currently %u kHz)\n", cpu, cpu_min_freq[cpu], cpu_max_freq[cpu], cpu_cur_freq[cpu]); +start_out: mutex_unlock(&userspace_mutex); break; case CPUFREQ_GOV_STOP: @@ -180,7 +187,7 @@ static int cpufreq_governor_userspace(struct cpufreq_policy *policy, mutex_unlock(&userspace_mutex); break; } - return 0; + return rc; } diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c index 551f4ccf87f..e7490925fdc 100644 --- a/drivers/cpufreq/freq_table.c +++ b/drivers/cpufreq/freq_table.c @@ -9,7 +9,8 @@ #include <linux/init.h> #include <linux/cpufreq.h> -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_CORE, "freq-table", msg) +#define dprintk(msg...) \ + cpufreq_debug_printk(CPUFREQ_DEBUG_CORE, "freq-table", msg) /********************************************************************* * FREQUENCY TABLE HELPERS * @@ -29,7 +30,8 @@ int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy, continue; } - dprintk("table entry %u: %u kHz, %u index\n", i, freq, table[i].index); + dprintk("table entry %u: %u kHz, %u index\n", + i, freq, table[i].index); if (freq < min_freq) min_freq = freq; if (freq > max_freq) @@ -54,13 +56,14 @@ int cpufreq_frequency_table_verify(struct cpufreq_policy *policy, unsigned int i; unsigned int count = 0; - dprintk("request for verification of policy (%u - %u kHz) for cpu %u\n", policy->min, policy->max, policy->cpu); + dprintk("request for verification of policy (%u - %u kHz) for cpu %u\n", + policy->min, policy->max, policy->cpu); if (!cpu_online(policy->cpu)) return -EINVAL; - cpufreq_verify_within_limits(policy, - policy->cpuinfo.min_freq, policy->cpuinfo.max_freq); + cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq, + policy->cpuinfo.max_freq); for (i=0; (table[i].frequency != CPUFREQ_TABLE_END); i++) { unsigned int freq = table[i].frequency; @@ -75,10 +78,11 @@ int cpufreq_frequency_table_verify(struct cpufreq_policy *policy, if (!count) policy->max = next_larger; - cpufreq_verify_within_limits(policy, - policy->cpuinfo.min_freq, policy->cpuinfo.max_freq); + cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq, + policy->cpuinfo.max_freq); - dprintk("verification lead to (%u - %u kHz) for cpu %u\n", policy->min, policy->max, policy->cpu); + dprintk("verification lead to (%u - %u kHz) for cpu %u\n", + policy->min, policy->max, policy->cpu); return 0; } @@ -101,7 +105,8 @@ int cpufreq_frequency_table_target(struct cpufreq_policy *policy, }; unsigned int i; - dprintk("request for target %u kHz (relation: %u) for cpu %u\n", target_freq, relation, policy->cpu); + dprintk("request for target %u kHz (relation: %u) for cpu %u\n", + target_freq, relation, policy->cpu); switch (relation) { case CPUFREQ_RELATION_H: @@ -192,7 +197,10 @@ static ssize_t show_available_freqs (struct cpufreq_policy *policy, char *buf) } struct freq_attr cpufreq_freq_attr_scaling_available_freqs = { - .attr = { .name = "scaling_available_frequencies", .mode = 0444, .owner=THIS_MODULE }, + .attr = { .name = "scaling_available_frequencies", + .mode = 0444, + .owner=THIS_MODULE + }, .show = show_available_freqs, }; EXPORT_SYMBOL_GPL(cpufreq_freq_attr_scaling_available_freqs); diff --git a/drivers/ide/Kconfig b/drivers/ide/Kconfig index e23bc0d6215..3f828052f8d 100644 --- a/drivers/ide/Kconfig +++ b/drivers/ide/Kconfig @@ -796,7 +796,7 @@ endchoice config BLK_DEV_IDE_AU1XXX_SEQTS_PER_RQ int "Maximum transfer size (KB) per request (up to 128)" default "128" - depends BLK_DEV_IDE_AU1XXX + depends on BLK_DEV_IDE_AU1XXX config IDE_ARM def_bool ARM && (ARCH_A5K || ARCH_CLPS7500 || ARCH_RPC || ARCH_SHARK) diff --git a/drivers/infiniband/core/Makefile b/drivers/infiniband/core/Makefile index 163d991eb8c..50fb1cd447b 100644 --- a/drivers/infiniband/core/Makefile +++ b/drivers/infiniband/core/Makefile @@ -1,9 +1,11 @@ infiniband-$(CONFIG_INFINIBAND_ADDR_TRANS) := ib_addr.o rdma_cm.o +user_access-$(CONFIG_INFINIBAND_ADDR_TRANS) := rdma_ucm.o obj-$(CONFIG_INFINIBAND) += ib_core.o ib_mad.o ib_sa.o \ ib_cm.o iw_cm.o $(infiniband-y) obj-$(CONFIG_INFINIBAND_USER_MAD) += ib_umad.o -obj-$(CONFIG_INFINIBAND_USER_ACCESS) += ib_uverbs.o ib_ucm.o +obj-$(CONFIG_INFINIBAND_USER_ACCESS) += ib_uverbs.o ib_ucm.o \ + $(user_access-y) ib_core-y := packer.o ud_header.o verbs.o sysfs.o \ device.o fmr_pool.o cache.o @@ -18,6 +20,8 @@ iw_cm-y := iwcm.o rdma_cm-y := cma.o +rdma_ucm-y := ucma.o + ib_addr-y := addr.o ib_umad-y := user_mad.o diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index 79c937bf696..d446998b12a 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -3289,6 +3289,10 @@ static int cm_init_qp_rts_attr(struct cm_id_private *cm_id_priv, spin_lock_irqsave(&cm_id_priv->lock, flags); switch (cm_id_priv->id.state) { + /* Allow transition to RTS before sending REP */ + case IB_CM_REQ_RCVD: + case IB_CM_MRA_REQ_SENT: + case IB_CM_REP_RCVD: case IB_CM_MRA_REP_SENT: case IB_CM_REP_SENT: diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 985a6b564d8..533193d4e5d 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -70,6 +70,7 @@ static DEFINE_MUTEX(lock); static struct workqueue_struct *cma_wq; static DEFINE_IDR(sdp_ps); static DEFINE_IDR(tcp_ps); +static DEFINE_IDR(udp_ps); struct cma_device { struct list_head list; @@ -133,7 +134,6 @@ struct rdma_id_private { u32 seq_num; u32 qp_num; - enum ib_qp_type qp_type; u8 srq; }; @@ -392,7 +392,6 @@ int rdma_create_qp(struct rdma_cm_id *id, struct ib_pd *pd, id->qp = qp; id_priv->qp_num = qp->qp_num; - id_priv->qp_type = qp->qp_type; id_priv->srq = (qp->srq != NULL); return 0; err: @@ -510,9 +509,17 @@ static inline int cma_any_addr(struct sockaddr *addr) return cma_zero_addr(addr) || cma_loopback_addr(addr); } +static inline __be16 cma_port(struct sockaddr *addr) +{ + if (addr->sa_family == AF_INET) + return ((struct sockaddr_in *) addr)->sin_port; + else + return ((struct sockaddr_in6 *) addr)->sin6_port; +} + static inline int cma_any_port(struct sockaddr *addr) { - return !((struct sockaddr_in *) addr)->sin_port; + return !cma_port(addr); } static int cma_get_net_info(void *hdr, enum rdma_port_space ps, @@ -594,20 +601,6 @@ static inline int cma_user_data_offset(enum rdma_port_space ps) } } -static int cma_notify_user(struct rdma_id_private *id_priv, - enum rdma_cm_event_type type, int status, - void *data, u8 data_len) -{ - struct rdma_cm_event event; - - event.event = type; - event.status = status; - event.private_data = data; - event.private_data_len = data_len; - - return id_priv->id.event_handler(&id_priv->id, &event); -} - static void cma_cancel_route(struct rdma_id_private *id_priv) { switch (rdma_node_get_transport(id_priv->id.device->node_type)) { @@ -776,63 +769,61 @@ static int cma_verify_rep(struct rdma_id_private *id_priv, void *data) return 0; } -static int cma_rtu_recv(struct rdma_id_private *id_priv) +static void cma_set_rep_event_data(struct rdma_cm_event *event, + struct ib_cm_rep_event_param *rep_data, + void *private_data) { - int ret; - - ret = cma_modify_qp_rts(&id_priv->id); - if (ret) - goto reject; - - return 0; -reject: - cma_modify_qp_err(&id_priv->id); - ib_send_cm_rej(id_priv->cm_id.ib, IB_CM_REJ_CONSUMER_DEFINED, - NULL, 0, NULL, 0); - return ret; + event->param.conn.private_data = private_data; + event->param.conn.private_data_len = IB_CM_REP_PRIVATE_DATA_SIZE; + event->param.conn.responder_resources = rep_data->responder_resources; + event->param.conn.initiator_depth = rep_data->initiator_depth; + event->param.conn.flow_control = rep_data->flow_control; + event->param.conn.rnr_retry_count = rep_data->rnr_retry_count; + event->param.conn.srq = rep_data->srq; + event->param.conn.qp_num = rep_data->remote_qpn; } static int cma_ib_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event) { struct rdma_id_private *id_priv = cm_id->context; - enum rdma_cm_event_type event; - u8 private_data_len = 0; - int ret = 0, status = 0; + struct rdma_cm_event event; + int ret = 0; atomic_inc(&id_priv->dev_remove); if (!cma_comp(id_priv, CMA_CONNECT)) goto out; + memset(&event, 0, sizeof event); switch (ib_event->event) { case IB_CM_REQ_ERROR: case IB_CM_REP_ERROR: - event = RDMA_CM_EVENT_UNREACHABLE; - status = -ETIMEDOUT; + event.event = RDMA_CM_EVENT_UNREACHABLE; + event.status = -ETIMEDOUT; break; case IB_CM_REP_RECEIVED: - status = cma_verify_rep(id_priv, ib_event->private_data); - if (status) - event = RDMA_CM_EVENT_CONNECT_ERROR; + event.status = cma_verify_rep(id_priv, ib_event->private_data); + if (event.status) + event.event = RDMA_CM_EVENT_CONNECT_ERROR; else if (id_priv->id.qp && id_priv->id.ps != RDMA_PS_SDP) { - status = cma_rep_recv(id_priv); - event = status ? RDMA_CM_EVENT_CONNECT_ERROR : - RDMA_CM_EVENT_ESTABLISHED; + event.status = cma_rep_recv(id_priv); + event.event = event.status ? RDMA_CM_EVENT_CONNECT_ERROR : + RDMA_CM_EVENT_ESTABLISHED; } else - event = RDMA_CM_EVENT_CONNECT_RESPONSE; - private_data_len = IB_CM_REP_PRIVATE_DATA_SIZE; + event.event = RDMA_CM_EVENT_CONNECT_RESPONSE; + cma_set_rep_event_data(&event, &ib_event->param.rep_rcvd, + ib_event->private_data); break; case IB_CM_RTU_RECEIVED: - status = cma_rtu_recv(id_priv); - event = status ? RDMA_CM_EVENT_CONNECT_ERROR : - RDMA_CM_EVENT_ESTABLISHED; + case IB_CM_USER_ESTABLISHED: + event.event = RDMA_CM_EVENT_ESTABLISHED; break; case IB_CM_DREQ_ERROR: - status = -ETIMEDOUT; /* fall through */ + event.status = -ETIMEDOUT; /* fall through */ case IB_CM_DREQ_RECEIVED: case IB_CM_DREP_RECEIVED: if (!cma_comp_exch(id_priv, CMA_CONNECT, CMA_DISCONNECT)) goto out; - event = RDMA_CM_EVENT_DISCONNECTED; + event.event = RDMA_CM_EVENT_DISCONNECTED; break; case IB_CM_TIMEWAIT_EXIT: case IB_CM_MRA_RECEIVED: @@ -840,9 +831,10 @@ static int cma_ib_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event) goto out; case IB_CM_REJ_RECEIVED: cma_modify_qp_err(&id_priv->id); - status = ib_event->param.rej_rcvd.reason; - event = RDMA_CM_EVENT_REJECTED; - private_data_len = IB_CM_REJ_PRIVATE_DATA_SIZE; + event.status = ib_event->param.rej_rcvd.reason; + event.event = RDMA_CM_EVENT_REJECTED; + event.param.conn.private_data = ib_event->private_data; + event.param.conn.private_data_len = IB_CM_REJ_PRIVATE_DATA_SIZE; break; default: printk(KERN_ERR "RDMA CMA: unexpected IB CM event: %d", @@ -850,8 +842,7 @@ static int cma_ib_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event) goto out; } - ret = cma_notify_user(id_priv, event, status, ib_event->private_data, - private_data_len); + ret = id_priv->id.event_handler(&id_priv->id, &event); if (ret) { /* Destroy the CM ID by returning a non-zero value. */ id_priv->cm_id.ib = NULL; @@ -865,8 +856,8 @@ out: return ret; } -static struct rdma_id_private *cma_new_id(struct rdma_cm_id *listen_id, - struct ib_cm_event *ib_event) +static struct rdma_id_private *cma_new_conn_id(struct rdma_cm_id *listen_id, + struct ib_cm_event *ib_event) { struct rdma_id_private *id_priv; struct rdma_cm_id *id; @@ -913,9 +904,61 @@ err: return NULL; } +static struct rdma_id_private *cma_new_udp_id(struct rdma_cm_id *listen_id, + struct ib_cm_event *ib_event) +{ + struct rdma_id_private *id_priv; + struct rdma_cm_id *id; + union cma_ip_addr *src, *dst; + __u16 port; + u8 ip_ver; + int ret; + + id = rdma_create_id(listen_id->event_handler, listen_id->context, + listen_id->ps); + if (IS_ERR(id)) + return NULL; + + + if (cma_get_net_info(ib_event->private_data, listen_id->ps, + &ip_ver, &port, &src, &dst)) + goto err; + + cma_save_net_info(&id->route.addr, &listen_id->route.addr, + ip_ver, port, src, dst); + + ret = rdma_translate_ip(&id->route.addr.src_addr, + &id->route.addr.dev_addr); + if (ret) + goto err; + + id_priv = container_of(id, struct rdma_id_private, id); + id_priv->state = CMA_CONNECT; + return id_priv; +err: + rdma_destroy_id(id); + return NULL; +} + +static void cma_set_req_event_data(struct rdma_cm_event *event, + struct ib_cm_req_event_param *req_data, + void *private_data, int offset) +{ + event->param.conn.private_data = private_data + offset; + event->param.conn.private_data_len = IB_CM_REQ_PRIVATE_DATA_SIZE - offset; + event->param.conn.responder_resources = req_data->responder_resources; + event->param.conn.initiator_depth = req_data->initiator_depth; + event->param.conn.flow_control = req_data->flow_control; + event->param.conn.retry_count = req_data->retry_count; + event->param.conn.rnr_retry_count = req_data->rnr_retry_count; + event->param.conn.srq = req_data->srq; + event->param.conn.qp_num = req_data->remote_qpn; +} + static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event) { struct rdma_id_private *listen_id, *conn_id; + struct rdma_cm_event event; int offset, ret; listen_id = cm_id->context; @@ -925,7 +968,19 @@ static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event) goto out; } - conn_id = cma_new_id(&listen_id->id, ib_event); + memset(&event, 0, sizeof event); + offset = cma_user_data_offset(listen_id->id.ps); + event.event = RDMA_CM_EVENT_CONNECT_REQUEST; + if (listen_id->id.ps == RDMA_PS_UDP) { + conn_id = cma_new_udp_id(&listen_id->id, ib_event); + event.param.ud.private_data = ib_event->private_data + offset; + event.param.ud.private_data_len = + IB_CM_SIDR_REQ_PRIVATE_DATA_SIZE - offset; + } else { + conn_id = cma_new_conn_id(&listen_id->id, ib_event); + cma_set_req_event_data(&event, &ib_event->param.req_rcvd, + ib_event->private_data, offset); + } if (!conn_id) { ret = -ENOMEM; goto out; @@ -942,10 +997,7 @@ static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event) cm_id->context = conn_id; cm_id->cm_handler = cma_ib_handler; - offset = cma_user_data_offset(listen_id->id.ps); - ret = cma_notify_user(conn_id, RDMA_CM_EVENT_CONNECT_REQUEST, 0, - ib_event->private_data + offset, - IB_CM_REQ_PRIVATE_DATA_SIZE - offset); + ret = conn_id->id.event_handler(&conn_id->id, &event); if (!ret) goto out; @@ -964,8 +1016,7 @@ out: static __be64 cma_get_service_id(enum rdma_port_space ps, struct sockaddr *addr) { - return cpu_to_be64(((u64)ps << 16) + - be16_to_cpu(((struct sockaddr_in *) addr)->sin_port)); + return cpu_to_be64(((u64)ps << 16) + be16_to_cpu(cma_port(addr))); } static void cma_set_compare_data(enum rdma_port_space ps, struct sockaddr *addr, @@ -1021,15 +1072,16 @@ static void cma_set_compare_data(enum rdma_port_space ps, struct sockaddr *addr, static int cma_iw_handler(struct iw_cm_id *iw_id, struct iw_cm_event *iw_event) { struct rdma_id_private *id_priv = iw_id->context; - enum rdma_cm_event_type event = 0; + struct rdma_cm_event event; struct sockaddr_in *sin; int ret = 0; + memset(&event, 0, sizeof event); atomic_inc(&id_priv->dev_remove); switch (iw_event->event) { case IW_CM_EVENT_CLOSE: - event = RDMA_CM_EVENT_DISCONNECTED; + event.event = RDMA_CM_EVENT_DISCONNECTED; break; case IW_CM_EVENT_CONNECT_REPLY: sin = (struct sockaddr_in *) &id_priv->id.route.addr.src_addr; @@ -1037,20 +1089,21 @@ static int cma_iw_handler(struct iw_cm_id *iw_id, struct iw_cm_event *iw_event) sin = (struct sockaddr_in *) &id_priv->id.route.addr.dst_addr; *sin = iw_event->remote_addr; if (iw_event->status) - event = RDMA_CM_EVENT_REJECTED; + event.event = RDMA_CM_EVENT_REJECTED; else - event = RDMA_CM_EVENT_ESTABLISHED; + event.event = RDMA_CM_EVENT_ESTABLISHED; break; case IW_CM_EVENT_ESTABLISHED: - event = RDMA_CM_EVENT_ESTABLISHED; + event.event = RDMA_CM_EVENT_ESTABLISHED; break; default: BUG_ON(1); } - ret = cma_notify_user(id_priv, event, iw_event->status, - iw_event->private_data, - iw_event->private_data_len); + event.status = iw_event->status; + event.param.conn.private_data = iw_event->private_data; + event.param.conn.private_data_len = iw_event->private_data_len; + ret = id_priv->id.event_handler(&id_priv->id, &event); if (ret) { /* Destroy the CM ID by returning a non-zero value. */ id_priv->cm_id.iw = NULL; @@ -1071,6 +1124,7 @@ static int iw_conn_req_handler(struct iw_cm_id *cm_id, struct rdma_id_private *listen_id, *conn_id; struct sockaddr_in *sin; struct net_device *dev = NULL; + struct rdma_cm_event event; int ret; listen_id = cm_id->context; @@ -1124,9 +1178,11 @@ static int iw_conn_req_handler(struct iw_cm_id *cm_id, sin = (struct sockaddr_in *) &new_cm_id->route.addr.dst_addr; *sin = iw_event->remote_addr; - ret = cma_notify_user(conn_id, RDMA_CM_EVENT_CONNECT_REQUEST, 0, - iw_event->private_data, - iw_event->private_data_len); + memset(&event, 0, sizeof event); + event.event = RDMA_CM_EVENT_CONNECT_REQUEST; + event.param.conn.private_data = iw_event->private_data; + event.param.conn.private_data_len = iw_event->private_data_len; + ret = conn_id->id.event_handler(&conn_id->id, &event); if (ret) { /* User wants to destroy the CM ID */ conn_id->cm_id.iw = NULL; @@ -1515,8 +1571,9 @@ static void addr_handler(int status, struct sockaddr *src_addr, struct rdma_dev_addr *dev_addr, void *context) { struct rdma_id_private *id_priv = context; - enum rdma_cm_event_type event; + struct rdma_cm_event event; + memset(&event, 0, sizeof event); atomic_inc(&id_priv->dev_remove); /* @@ -1536,14 +1593,15 @@ static void addr_handler(int status, struct sockaddr *src_addr, if (status) { if (!cma_comp_exch(id_priv, CMA_ADDR_RESOLVED, CMA_ADDR_BOUND)) goto out; - event = RDMA_CM_EVENT_ADDR_ERROR; + event.event = RDMA_CM_EVENT_ADDR_ERROR; + event.status = status; } else { memcpy(&id_priv->id.route.addr.src_addr, src_addr, ip_addr_size(src_addr)); - event = RDMA_CM_EVENT_ADDR_RESOLVED; + event.event = RDMA_CM_EVENT_ADDR_RESOLVED; } - if (cma_notify_user(id_priv, event, status, NULL, 0)) { + if (id_priv->id.event_handler(&id_priv->id, &event)) { cma_exch(id_priv, CMA_DESTROYING); cma_release_remove(id_priv); cma_deref_id(id_priv); @@ -1733,6 +1791,9 @@ static int cma_get_port(struct rdma_id_private *id_priv) case RDMA_PS_TCP: ps = &tcp_ps; break; + case RDMA_PS_UDP: + ps = &udp_ps; + break; default: return -EPROTONOSUPPORT; } @@ -1821,6 +1882,110 @@ static int cma_format_hdr(void *hdr, enum rdma_port_space ps, return 0; } +static int cma_sidr_rep_handler(struct ib_cm_id *cm_id, + struct ib_cm_event *ib_event) +{ + struct rdma_id_private *id_priv = cm_id->context; + struct rdma_cm_event event; + struct ib_cm_sidr_rep_event_param *rep = &ib_event->param.sidr_rep_rcvd; + int ret = 0; + + memset(&event, 0, sizeof event); + atomic_inc(&id_priv->dev_remove); + if (!cma_comp(id_priv, CMA_CONNECT)) + goto out; + + switch (ib_event->event) { + case IB_CM_SIDR_REQ_ERROR: + event.event = RDMA_CM_EVENT_UNREACHABLE; + event.status = -ETIMEDOUT; + break; + case IB_CM_SIDR_REP_RECEIVED: + event.param.ud.private_data = ib_event->private_data; + event.param.ud.private_data_len = IB_CM_SIDR_REP_PRIVATE_DATA_SIZE; + if (rep->status != IB_SIDR_SUCCESS) { + event.event = RDMA_CM_EVENT_UNREACHABLE; + event.status = ib_event->param.sidr_rep_rcvd.status; + break; + } + if (rep->qkey != RDMA_UD_QKEY) { + event.event = RDMA_CM_EVENT_UNREACHABLE; + event.status = -EINVAL; + break; + } + ib_init_ah_from_path(id_priv->id.device, id_priv->id.port_num, + id_priv->id.route.path_rec, + &event.param.ud.ah_attr); + event.param.ud.qp_num = rep->qpn; + event.param.ud.qkey = rep->qkey; + event.event = RDMA_CM_EVENT_ESTABLISHED; + event.status = 0; + break; + default: + printk(KERN_ERR "RDMA CMA: unexpected IB CM event: %d", + ib_event->event); + goto out; + } + + ret = id_priv->id.event_handler(&id_priv->id, &event); + if (ret) { + /* Destroy the CM ID by returning a non-zero value. */ + id_priv->cm_id.ib = NULL; + cma_exch(id_priv, CMA_DESTROYING); + cma_release_remove(id_priv); + rdma_destroy_id(&id_priv->id); + return ret; + } +out: + cma_release_remove(id_priv); + return ret; +} + +static int cma_resolve_ib_udp(struct rdma_id_private *id_priv, + struct rdma_conn_param *conn_param) +{ + struct ib_cm_sidr_req_param req; + struct rdma_route *route; + int ret; + + req.private_data_len = sizeof(struct cma_hdr) + + conn_param->private_data_len; + req.private_data = kzalloc(req.private_data_len, GFP_ATOMIC); + if (!req.private_data) + return -ENOMEM; + + if (conn_param->private_data && conn_param->private_data_len) + memcpy((void *) req.private_data + sizeof(struct cma_hdr), + conn_param->private_data, conn_param->private_data_len); + + route = &id_priv->id.route; + ret = cma_format_hdr((void *) req.private_data, id_priv->id.ps, route); + if (ret) + goto out; + + id_priv->cm_id.ib = ib_create_cm_id(id_priv->id.device, + cma_sidr_rep_handler, id_priv); + if (IS_ERR(id_priv->cm_id.ib)) { + ret = PTR_ERR(id_priv->cm_id.ib); + goto out; + } + + req.path = route->path_rec; + req.service_id = cma_get_service_id(id_priv->id.ps, + &route->addr.dst_addr); + req.timeout_ms = 1 << (CMA_CM_RESPONSE_TIMEOUT - 8); + req.max_cm_retries = CMA_MAX_CM_RETRIES; + + ret = ib_send_cm_sidr_req(id_priv->cm_id.ib, &req); + if (ret) { + ib_destroy_cm_id(id_priv->cm_id.ib); + id_priv->cm_id.ib = NULL; + } +out: + kfree(req.private_data); + return ret; +} + static int cma_connect_ib(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { @@ -1860,7 +2025,7 @@ static int cma_connect_ib(struct rdma_id_private *id_priv, req.service_id = cma_get_service_id(id_priv->id.ps, &route->addr.dst_addr); req.qp_num = id_priv->qp_num; - req.qp_type = id_priv->qp_type; + req.qp_type = IB_QPT_RC; req.starting_psn = id_priv->seq_num; req.responder_resources = conn_param->responder_resources; req.initiator_depth = conn_param->initiator_depth; @@ -1937,13 +2102,15 @@ int rdma_connect(struct rdma_cm_id *id, struct rdma_conn_param *conn_param) if (!id->qp) { id_priv->qp_num = conn_param->qp_num; - id_priv->qp_type = conn_param->qp_type; id_priv->srq = conn_param->srq; } switch (rdma_node_get_transport(id->device->node_type)) { case RDMA_TRANSPORT_IB: - ret = cma_connect_ib(id_priv, conn_param); + if (id->ps == RDMA_PS_UDP) + ret = cma_resolve_ib_udp(id_priv, conn_param); + else + ret = cma_connect_ib(id_priv, conn_param); break; case RDMA_TRANSPORT_IWARP: ret = cma_connect_iw(id_priv, conn_param); @@ -1966,11 +2133,25 @@ static int cma_accept_ib(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct ib_cm_rep_param rep; - int ret; + struct ib_qp_attr qp_attr; + int qp_attr_mask, ret; - ret = cma_modify_qp_rtr(&id_priv->id); - if (ret) - return ret; + if (id_priv->id.qp) { + ret = cma_modify_qp_rtr(&id_priv->id); + if (ret) + goto out; + + qp_attr.qp_state = IB_QPS_RTS; + ret = ib_cm_init_qp_attr(id_priv->cm_id.ib, &qp_attr, + &qp_attr_mask); + if (ret) + goto out; + + qp_attr.max_rd_atomic = conn_param->initiator_depth; + ret = ib_modify_qp(id_priv->id.qp, &qp_attr, qp_attr_mask); + if (ret) + goto out; + } memset(&rep, 0, sizeof rep); rep.qp_num = id_priv->qp_num; @@ -1985,7 +2166,9 @@ static int cma_accept_ib(struct rdma_id_private *id_priv, rep.rnr_retry_count = conn_param->rnr_retry_count; rep.srq = id_priv->srq ? 1 : 0; - return ib_send_cm_rep(id_priv->cm_id.ib, &rep); + ret = ib_send_cm_rep(id_priv->cm_id.ib, &rep); +out: + return ret; } static int cma_accept_iw(struct rdma_id_private *id_priv, @@ -2010,6 +2193,24 @@ static int cma_accept_iw(struct rdma_id_private *id_priv, return iw_cm_accept(id_priv->cm_id.iw, &iw_param); } +static int cma_send_sidr_rep(struct rdma_id_private *id_priv, + enum ib_cm_sidr_status status, + const void *private_data, int private_data_len) +{ + struct ib_cm_sidr_rep_param rep; + + memset(&rep, 0, sizeof rep); + rep.status = status; + if (status == IB_SIDR_SUCCESS) { + rep.qp_num = id_priv->qp_num; + rep.qkey = RDMA_UD_QKEY; + } + rep.private_data = private_data; + rep.private_data_len = private_data_len; + + return ib_send_cm_sidr_rep(id_priv->cm_id.ib, &rep); +} + int rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param) { struct rdma_id_private *id_priv; @@ -2021,13 +2222,16 @@ int rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param) if (!id->qp && conn_param) { id_priv->qp_num = conn_param->qp_num; - id_priv->qp_type = conn_param->qp_type; id_priv->srq = conn_param->srq; } switch (rdma_node_get_transport(id->device->node_type)) { case RDMA_TRANSPORT_IB: - if (conn_param) + if (id->ps == RDMA_PS_UDP) + ret = cma_send_sidr_rep(id_priv, IB_SIDR_SUCCESS, + conn_param->private_data, + conn_param->private_data_len); + else if (conn_param) ret = cma_accept_ib(id_priv, conn_param); else ret = cma_rep_recv(id_priv); @@ -2051,6 +2255,27 @@ reject: } EXPORT_SYMBOL(rdma_accept); +int rdma_notify(struct rdma_cm_id *id, enum ib_event_type event) +{ + struct rdma_id_private *id_priv; + int ret; + + id_priv = container_of(id, struct rdma_id_private, id); + if (!cma_comp(id_priv, CMA_CONNECT)) + return -EINVAL; + + switch (id->device->node_type) { + case RDMA_NODE_IB_CA: + ret = ib_cm_notify(id_priv->cm_id.ib, event); + break; + default: + ret = 0; + break; + } + return ret; +} +EXPORT_SYMBOL(rdma_notify); + int rdma_reject(struct rdma_cm_id *id, const void *private_data, u8 private_data_len) { @@ -2063,9 +2288,13 @@ int rdma_reject(struct rdma_cm_id *id, const void *private_data, switch (rdma_node_get_transport(id->device->node_type)) { case RDMA_TRANSPORT_IB: - ret = ib_send_cm_rej(id_priv->cm_id.ib, - IB_CM_REJ_CONSUMER_DEFINED, NULL, 0, - private_data, private_data_len); + if (id->ps == RDMA_PS_UDP) + ret = cma_send_sidr_rep(id_priv, IB_SIDR_REJECT, + private_data, private_data_len); + else + ret = ib_send_cm_rej(id_priv->cm_id.ib, + IB_CM_REJ_CONSUMER_DEFINED, NULL, + 0, private_data, private_data_len); break; case RDMA_TRANSPORT_IWARP: ret = iw_cm_reject(id_priv->cm_id.iw, @@ -2136,6 +2365,7 @@ static void cma_add_one(struct ib_device *device) static int cma_remove_id_dev(struct rdma_id_private *id_priv) { + struct rdma_cm_event event; enum cma_state state; /* Record that we want to remove the device */ @@ -2150,8 +2380,9 @@ static int cma_remove_id_dev(struct rdma_id_private *id_priv) if (!cma_comp(id_priv, CMA_DEVICE_REMOVAL)) return 0; - return cma_notify_user(id_priv, RDMA_CM_EVENT_DEVICE_REMOVAL, - 0, NULL, 0); + memset(&event, 0, sizeof event); + event.event = RDMA_CM_EVENT_DEVICE_REMOVAL; + return id_priv->id.event_handler(&id_priv->id, &event); } static void cma_process_remove(struct cma_device *cma_dev) @@ -2233,6 +2464,7 @@ static void cma_cleanup(void) destroy_workqueue(cma_wq); idr_destroy(&sdp_ps); idr_destroy(&tcp_ps); + idr_destroy(&udp_ps); } module_init(cma_init); diff --git a/drivers/infiniband/core/fmr_pool.c b/drivers/infiniband/core/fmr_pool.c index 86a3b2d401d..8926a2bd4a8 100644 --- a/drivers/infiniband/core/fmr_pool.c +++ b/drivers/infiniband/core/fmr_pool.c @@ -394,20 +394,12 @@ EXPORT_SYMBOL(ib_destroy_fmr_pool); */ int ib_flush_fmr_pool(struct ib_fmr_pool *pool) { - int serial; - - atomic_inc(&pool->req_ser); - /* - * It's OK if someone else bumps req_ser again here -- we'll - * just wait a little longer. - */ - serial = atomic_read(&pool->req_ser); + int serial = atomic_inc_return(&pool->req_ser); wake_up_process(pool->thread); if (wait_event_interruptible(pool->force_wait, - atomic_read(&pool->flush_ser) - - atomic_read(&pool->req_ser) >= 0)) + atomic_read(&pool->flush_ser) - serial >= 0)) return -EINTR; return 0; diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c index 15f38d94b3a..5ed141ebd1c 100644 --- a/drivers/infiniband/core/mad.c +++ b/drivers/infiniband/core/mad.c @@ -998,17 +998,17 @@ int ib_send_mad(struct ib_mad_send_wr_private *mad_send_wr) mad_agent = mad_send_wr->send_buf.mad_agent; sge = mad_send_wr->sg_list; - sge[0].addr = dma_map_single(mad_agent->device->dma_device, - mad_send_wr->send_buf.mad, - sge[0].length, - DMA_TO_DEVICE); - pci_unmap_addr_set(mad_send_wr, header_mapping, sge[0].addr); - - sge[1].addr = dma_map_single(mad_agent->device->dma_device, - ib_get_payload(mad_send_wr), - sge[1].length, - DMA_TO_DEVICE); - pci_unmap_addr_set(mad_send_wr, payload_mapping, sge[1].addr); + sge[0].addr = ib_dma_map_single(mad_agent->device, + mad_send_wr->send_buf.mad, + sge[0].length, + DMA_TO_DEVICE); + mad_send_wr->header_mapping = sge[0].addr; + + sge[1].addr = ib_dma_map_single(mad_agent->device, + ib_get_payload(mad_send_wr), + sge[1].length, + DMA_TO_DEVICE); + mad_send_wr->payload_mapping = sge[1].addr; spin_lock_irqsave(&qp_info->send_queue.lock, flags); if (qp_info->send_queue.count < qp_info->send_queue.max_active) { @@ -1026,12 +1026,12 @@ int ib_send_mad(struct ib_mad_send_wr_private *mad_send_wr) } spin_unlock_irqrestore(&qp_info->send_queue.lock, flags); if (ret) { - dma_unmap_single(mad_agent->device->dma_device, - pci_unmap_addr(mad_send_wr, header_mapping), - sge[0].length, DMA_TO_DEVICE); - dma_unmap_single(mad_agent->device->dma_device, - pci_unmap_addr(mad_send_wr, payload_mapping), - sge[1].length, DMA_TO_DEVICE); + ib_dma_unmap_single(mad_agent->device, + mad_send_wr->header_mapping, + sge[0].length, DMA_TO_DEVICE); + ib_dma_unmap_single(mad_agent->device, + mad_send_wr->payload_mapping, + sge[1].length, DMA_TO_DEVICE); } return ret; } @@ -1850,11 +1850,11 @@ static void ib_mad_recv_done_handler(struct ib_mad_port_private *port_priv, mad_priv_hdr = container_of(mad_list, struct ib_mad_private_header, mad_list); recv = container_of(mad_priv_hdr, struct ib_mad_private, header); - dma_unmap_single(port_priv->device->dma_device, - pci_unmap_addr(&recv->header, mapping), - sizeof(struct ib_mad_private) - - sizeof(struct ib_mad_private_header), - DMA_FROM_DEVICE); + ib_dma_unmap_single(port_priv->device, + recv->header.mapping, + sizeof(struct ib_mad_private) - + sizeof(struct ib_mad_private_header), + DMA_FROM_DEVICE); /* Setup MAD receive work completion from "normal" work completion */ recv->header.wc = *wc; @@ -2080,12 +2080,12 @@ static void ib_mad_send_done_handler(struct ib_mad_port_private *port_priv, qp_info = send_queue->qp_info; retry: - dma_unmap_single(mad_send_wr->send_buf.mad_agent->device->dma_device, - pci_unmap_addr(mad_send_wr, header_mapping), - mad_send_wr->sg_list[0].length, DMA_TO_DEVICE); - dma_unmap_single(mad_send_wr->send_buf.mad_agent->device->dma_device, - pci_unmap_addr(mad_send_wr, payload_mapping), - mad_send_wr->sg_list[1].length, DMA_TO_DEVICE); + ib_dma_unmap_single(mad_send_wr->send_buf.mad_agent->device, + mad_send_wr->header_mapping, + mad_send_wr->sg_list[0].length, DMA_TO_DEVICE); + ib_dma_unmap_single(mad_send_wr->send_buf.mad_agent->device, + mad_send_wr->payload_mapping, + mad_send_wr->sg_list[1].length, DMA_TO_DEVICE); queued_send_wr = NULL; spin_lock_irqsave(&send_queue->lock, flags); list_del(&mad_list->list); @@ -2528,13 +2528,12 @@ static int ib_mad_post_receive_mads(struct ib_mad_qp_info *qp_info, break; } } - sg_list.addr = dma_map_single(qp_info->port_priv-> - device->dma_device, - &mad_priv->grh, - sizeof *mad_priv - - sizeof mad_priv->header, - DMA_FROM_DEVICE); - pci_unmap_addr_set(&mad_priv->header, mapping, sg_list.addr); + sg_list.addr = ib_dma_map_single(qp_info->port_priv->device, + &mad_priv->grh, + sizeof *mad_priv - + sizeof mad_priv->header, + DMA_FROM_DEVICE); + mad_priv->header.mapping = sg_list.addr; recv_wr.wr_id = (unsigned long)&mad_priv->header.mad_list; mad_priv->header.mad_list.mad_queue = recv_queue; @@ -2549,12 +2548,11 @@ static int ib_mad_post_receive_mads(struct ib_mad_qp_info *qp_info, list_del(&mad_priv->header.mad_list.list); recv_queue->count--; spin_unlock_irqrestore(&recv_queue->lock, flags); - dma_unmap_single(qp_info->port_priv->device->dma_device, - pci_unmap_addr(&mad_priv->header, - mapping), - sizeof *mad_priv - - sizeof mad_priv->header, - DMA_FROM_DEVICE); + ib_dma_unmap_single(qp_info->port_priv->device, + mad_priv->header.mapping, + sizeof *mad_priv - + sizeof mad_priv->header, + DMA_FROM_DEVICE); kmem_cache_free(ib_mad_cache, mad_priv); printk(KERN_ERR PFX "ib_post_recv failed: %d\n", ret); break; @@ -2586,11 +2584,11 @@ static void cleanup_recv_queue(struct ib_mad_qp_info *qp_info) /* Remove from posted receive MAD list */ list_del(&mad_list->list); - dma_unmap_single(qp_info->port_priv->device->dma_device, - pci_unmap_addr(&recv->header, mapping), - sizeof(struct ib_mad_private) - - sizeof(struct ib_mad_private_header), - DMA_FROM_DEVICE); + ib_dma_unmap_single(qp_info->port_priv->device, + recv->header.mapping, + sizeof(struct ib_mad_private) - + sizeof(struct ib_mad_private_header), + DMA_FROM_DEVICE); kmem_cache_free(ib_mad_cache, recv); } diff --git a/drivers/infiniband/core/mad_priv.h b/drivers/infiniband/core/mad_priv.h index d5548e73e06..de89717f49f 100644 --- a/drivers/infiniband/core/mad_priv.h +++ b/drivers/infiniband/core/mad_priv.h @@ -73,7 +73,7 @@ struct ib_mad_private_header { struct ib_mad_list_head mad_list; struct ib_mad_recv_wc recv_wc; struct ib_wc wc; - DECLARE_PCI_UNMAP_ADDR(mapping) + u64 mapping; } __attribute__ ((packed)); struct ib_mad_private { @@ -126,8 +126,8 @@ struct ib_mad_send_wr_private { struct list_head agent_list; struct ib_mad_agent_private *mad_agent_priv; struct ib_mad_send_buf send_buf; - DECLARE_PCI_UNMAP_ADDR(header_mapping) - DECLARE_PCI_UNMAP_ADDR(payload_mapping) + u64 header_mapping; + u64 payload_mapping; struct ib_send_wr send_wr; struct ib_sge sg_list[IB_MAD_SEND_REQ_MAX_SG]; __be64 tid; diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c new file mode 100644 index 00000000000..81a5cdc5733 --- /dev/null +++ b/drivers/infiniband/core/ucma.c @@ -0,0 +1,874 @@ +/* + * Copyright (c) 2005-2006 Intel Corporation. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include <linux/completion.h> +#include <linux/mutex.h> +#include <linux/poll.h> +#include <linux/idr.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <linux/miscdevice.h> + +#include <rdma/rdma_user_cm.h> +#include <rdma/ib_marshall.h> +#include <rdma/rdma_cm.h> + +MODULE_AUTHOR("Sean Hefty"); +MODULE_DESCRIPTION("RDMA Userspace Connection Manager Access"); +MODULE_LICENSE("Dual BSD/GPL"); + +enum { + UCMA_MAX_BACKLOG = 128 +}; + +struct ucma_file { + struct mutex mut; + struct file *filp; + struct list_head ctx_list; + struct list_head event_list; + wait_queue_head_t poll_wait; +}; + +struct ucma_context { + int id; + struct completion comp; + atomic_t ref; + int events_reported; + int backlog; + + struct ucma_file *file; + struct rdma_cm_id *cm_id; + u64 uid; + + struct list_head list; +}; + +struct ucma_event { + struct ucma_context *ctx; + struct list_head list; + struct rdma_cm_id *cm_id; + struct rdma_ucm_event_resp resp; +}; + +static DEFINE_MUTEX(mut); +static DEFINE_IDR(ctx_idr); + +static inline struct ucma_context *_ucma_find_context(int id, + struct ucma_file *file) +{ + struct ucma_context *ctx; + + ctx = idr_find(&ctx_idr, id); + if (!ctx) + ctx = ERR_PTR(-ENOENT); + else if (ctx->file != file) + ctx = ERR_PTR(-EINVAL); + return ctx; +} + +static struct ucma_context *ucma_get_ctx(struct ucma_file *file, int id) +{ + struct ucma_context *ctx; + + mutex_lock(&mut); + ctx = _ucma_find_context(id, file); + if (!IS_ERR(ctx)) + atomic_inc(&ctx->ref); + mutex_unlock(&mut); + return ctx; +} + +static void ucma_put_ctx(struct ucma_context *ctx) +{ + if (atomic_dec_and_test(&ctx->ref)) + complete(&ctx->comp); +} + +static struct ucma_context *ucma_alloc_ctx(struct ucma_file *file) +{ + struct ucma_context *ctx; + int ret; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return NULL; + + atomic_set(&ctx->ref, 1); + init_completion(&ctx->comp); + ctx->file = file; + + do { + ret = idr_pre_get(&ctx_idr, GFP_KERNEL); + if (!ret) + goto error; + + mutex_lock(&mut); + ret = idr_get_new(&ctx_idr, ctx, &ctx->id); + mutex_unlock(&mut); + } while (ret == -EAGAIN); + + if (ret) + goto error; + + list_add_tail(&ctx->list, &file->ctx_list); + return ctx; + +error: + kfree(ctx); + return NULL; +} + +static void ucma_copy_conn_event(struct rdma_ucm_conn_param *dst, + struct rdma_conn_param *src) +{ + if (src->private_data_len) + memcpy(dst->private_data, src->private_data, + src->private_data_len); + dst->private_data_len = src->private_data_len; + dst->responder_resources =src->responder_resources; + dst->initiator_depth = src->initiator_depth; + dst->flow_control = src->flow_control; + dst->retry_count = src->retry_count; + dst->rnr_retry_count = src->rnr_retry_count; + dst->srq = src->srq; + dst->qp_num = src->qp_num; +} + +static void ucma_copy_ud_event(struct rdma_ucm_ud_param *dst, + struct rdma_ud_param *src) +{ + if (src->private_data_len) + memcpy(dst->private_data, src->private_data, + src->private_data_len); + dst->private_data_len = src->private_data_len; + ib_copy_ah_attr_to_user(&dst->ah_attr, &src->ah_attr); + dst->qp_num = src->qp_num; + dst->qkey = src->qkey; +} + +static void ucma_set_event_context(struct ucma_context *ctx, + struct rdma_cm_event *event, + struct ucma_event *uevent) +{ + uevent->ctx = ctx; + uevent->resp.uid = ctx->uid; + uevent->resp.id = ctx->id; +} + +static int ucma_event_handler(struct rdma_cm_id *cm_id, + struct rdma_cm_event *event) +{ + struct ucma_event *uevent; + struct ucma_context *ctx = cm_id->context; + int ret = 0; + + uevent = kzalloc(sizeof(*uevent), GFP_KERNEL); + if (!uevent) + return event->event == RDMA_CM_EVENT_CONNECT_REQUEST; + + uevent->cm_id = cm_id; + ucma_set_event_context(ctx, event, uevent); + uevent->resp.event = event->event; + uevent->resp.status = event->status; + if (cm_id->ps == RDMA_PS_UDP) + ucma_copy_ud_event(&uevent->resp.param.ud, &event->param.ud); + else + ucma_copy_conn_event(&uevent->resp.param.conn, + &event->param.conn); + + mutex_lock(&ctx->file->mut); + if (event->event == RDMA_CM_EVENT_CONNECT_REQUEST) { + if (!ctx->backlog) { + ret = -EDQUOT; + goto out; + } + ctx->backlog--; + } + list_add_tail(&uevent->list, &ctx->file->event_list); + wake_up_interruptible(&ctx->file->poll_wait); +out: + mutex_unlock(&ctx->file->mut); + return ret; +} + +static ssize_t ucma_get_event(struct ucma_file *file, const char __user *inbuf, + int in_len, int out_len) +{ + struct ucma_context *ctx; + struct rdma_ucm_get_event cmd; + struct ucma_event *uevent; + int ret = 0; + DEFINE_WAIT(wait); + + if (out_len < sizeof uevent->resp) + return -ENOSPC; + + if (copy_from_user(&cmd, inbuf, sizeof(cmd))) + return -EFAULT; + + mutex_lock(&file->mut); + while (list_empty(&file->event_list)) { + if (file->filp->f_flags & O_NONBLOCK) { + ret = -EAGAIN; + break; + } + + if (signal_pending(current)) { + ret = -ERESTARTSYS; + break; + } + + prepare_to_wait(&file->poll_wait, &wait, TASK_INTERRUPTIBLE); + mutex_unlock(&file->mut); + schedule(); + mutex_lock(&file->mut); + finish_wait(&file->poll_wait, &wait); + } + + if (ret) + goto done; + + uevent = list_entry(file->event_list.next, struct ucma_event, list); + + if (uevent->resp.event == RDMA_CM_EVENT_CONNECT_REQUEST) { + ctx = ucma_alloc_ctx(file); + if (!ctx) { + ret = -ENOMEM; + goto done; + } + uevent->ctx->backlog++; + ctx->cm_id = uevent->cm_id; + ctx->cm_id->context = ctx; + uevent->resp.id = ctx->id; + } + + if (copy_to_user((void __user *)(unsigned long)cmd.response, + &uevent->resp, sizeof uevent->resp)) { + ret = -EFAULT; + goto done; + } + + list_del(&uevent->list); + uevent->ctx->events_reported++; + kfree(uevent); +done: + mutex_unlock(&file->mut); + return ret; +} + +static ssize_t ucma_create_id(struct ucma_file *file, + const char __user *inbuf, + int in_len, int out_len) +{ + struct rdma_ucm_create_id cmd; + struct rdma_ucm_create_id_resp resp; + struct ucma_context *ctx; + int ret; + + if (out_len < sizeof(resp)) + return -ENOSPC; + + if (copy_from_user(&cmd, inbuf, sizeof(cmd))) + return -EFAULT; + + mutex_lock(&file->mut); + ctx = ucma_alloc_ctx(file); + mutex_unlock(&file->mut); + if (!ctx) + return -ENOMEM; + + ctx->uid = cmd.uid; + ctx->cm_id = rdma_create_id(ucma_event_handler, ctx, cmd.ps); + if (IS_ERR(ctx->cm_id)) { + ret = PTR_ERR(ctx->cm_id); + goto err1; + } + + resp.id = ctx->id; + if (copy_to_user((void __user *)(unsigned long)cmd.response, + &resp, sizeof(resp))) { + ret = -EFAULT; + goto err2; + } + return 0; + +err2: + rdma_destroy_id(ctx->cm_id); +err1: + mutex_lock(&mut); + idr_remove(&ctx_idr, ctx->id); + mutex_unlock(&mut); + kfree(ctx); + return ret; +} + +static void ucma_cleanup_events(struct ucma_context *ctx) +{ + struct ucma_event *uevent, *tmp; + + list_for_each_entry_safe(uevent, tmp, &ctx->file->event_list, list) { + if (uevent->ctx != ctx) + continue; + + list_del(&uevent->list); + + /* clear incoming connections. */ + if (uevent->resp.event == RDMA_CM_EVENT_CONNECT_REQUEST) + rdma_destroy_id(uevent->cm_id); + + kfree(uevent); + } +} + +static int ucma_free_ctx(struct ucma_context *ctx) +{ + int events_reported; + + /* No new events will be generated after destroying the id. */ + rdma_destroy_id(ctx->cm_id); + + /* Cleanup events not yet reported to the user. */ + mutex_lock(&ctx->file->mut); + ucma_cleanup_events(ctx); + list_del(&ctx->list); + mutex_unlock(&ctx->file->mut); + + events_reported = ctx->events_reported; + kfree(ctx); + return events_reported; +} + +static ssize_t ucma_destroy_id(struct ucma_file *file, const char __user *inbuf, + int in_len, int out_len) +{ + struct rdma_ucm_destroy_id cmd; + struct rdma_ucm_destroy_id_resp resp; + struct ucma_context *ctx; + int ret = 0; + + if (out_len < sizeof(resp)) + return -ENOSPC; + + if (copy_from_user(&cmd, inbuf, sizeof(cmd))) + return -EFAULT; + + mutex_lock(&mut); + ctx = _ucma_find_context(cmd.id, file); + if (!IS_ERR(ctx)) + idr_remove(&ctx_idr, ctx->id); + mutex_unlock(&mut); + + if (IS_ERR(ctx)) + return PTR_ERR(ctx); + + ucma_put_ctx(ctx); + wait_for_completion(&ctx->comp); + resp.events_reported = ucma_free_ctx(ctx); + + if (copy_to_user((void __user *)(unsigned long)cmd.response, + &resp, sizeof(resp))) + ret = -EFAULT; + + return ret; +} + +static ssize_t ucma_bind_addr(struct ucma_file *file, const char __user *inbuf, + int in_len, int out_len) +{ + struct rdma_ucm_bind_addr cmd; + struct ucma_context *ctx; + int ret; + + if (copy_from_user(&cmd, inbuf, sizeof(cmd))) + return -EFAULT; + + ctx = ucma_get_ctx(file, cmd.id); + if (IS_ERR(ctx)) + return PTR_ERR(ctx); + + ret = rdma_bind_addr(ctx->cm_id, (struct sockaddr *) &cmd.addr); + ucma_put_ctx(ctx); + return ret; +} + +static ssize_t ucma_resolve_addr(struct ucma_file *file, + const char __user *inbuf, + int in_len, int out_len) +{ + struct rdma_ucm_resolve_addr cmd; + struct ucma_context *ctx; + int ret; + + if (copy_from_user(&cmd, inbuf, sizeof(cmd))) + return -EFAULT; + + ctx = ucma_get_ctx(file, cmd.id); + if (IS_ERR(ctx)) + return PTR_ERR(ctx); + + ret = rdma_resolve_addr(ctx->cm_id, (struct sockaddr *) &cmd.src_addr, + (struct sockaddr *) &cmd.dst_addr, + cmd.timeout_ms); + ucma_put_ctx(ctx); + return ret; +} + +static ssize_t ucma_resolve_route(struct ucma_file *file, + const char __user *inbuf, + int in_len, int out_len) +{ + struct rdma_ucm_resolve_route cmd; + struct ucma_context *ctx; + int ret; + + if (copy_from_user(&cmd, inbuf, sizeof(cmd))) + return -EFAULT; + + ctx = ucma_get_ctx(file, cmd.id); + if (IS_ERR(ctx)) + return PTR_ERR(ctx); + + ret = rdma_resolve_route(ctx->cm_id, cmd.timeout_ms); + ucma_put_ctx(ctx); + return ret; +} + +static void ucma_copy_ib_route(struct rdma_ucm_query_route_resp *resp, + struct rdma_route *route) +{ + struct rdma_dev_addr *dev_addr; + + resp->num_paths = route->num_paths; + switch (route->num_paths) { + case 0: + dev_addr = &route->addr.dev_addr; + ib_addr_get_dgid(dev_addr, + (union ib_gid *) &resp->ib_route[0].dgid); + ib_addr_get_sgid(dev_addr, + (union ib_gid *) &resp->ib_route[0].sgid); + resp->ib_route[0].pkey = cpu_to_be16(ib_addr_get_pkey(dev_addr)); + break; + case 2: + ib_copy_path_rec_to_user(&resp->ib_route[1], + &route->path_rec[1]); + /* fall through */ + case 1: + ib_copy_path_rec_to_user(&resp->ib_route[0], + &route->path_rec[0]); + break; + default: + break; + } +} + +static ssize_t ucma_query_route(struct ucma_file *file, + const char __user *inbuf, + int in_len, int out_len) +{ + struct rdma_ucm_query_route cmd; + struct rdma_ucm_query_route_resp resp; + struct ucma_context *ctx; + struct sockaddr *addr; + int ret = 0; + + if (out_len < sizeof(resp)) + return -ENOSPC; + + if (copy_from_user(&cmd, inbuf, sizeof(cmd))) + return -EFAULT; + + ctx = ucma_get_ctx(file, cmd.id); + if (IS_ERR(ctx)) + return PTR_ERR(ctx); + + memset(&resp, 0, sizeof resp); + addr = &ctx->cm_id->route.addr.src_addr; + memcpy(&resp.src_addr, addr, addr->sa_family == AF_INET ? + sizeof(struct sockaddr_in) : + sizeof(struct sockaddr_in6)); + addr = &ctx->cm_id->route.addr.dst_addr; + memcpy(&resp.dst_addr, addr, addr->sa_family == AF_INET ? + sizeof(struct sockaddr_in) : + sizeof(struct sockaddr_in6)); + if (!ctx->cm_id->device) + goto out; + + resp.node_guid = ctx->cm_id->device->node_guid; + resp.port_num = ctx->cm_id->port_num; + switch (rdma_node_get_transport(ctx->cm_id->device->node_type)) { + case RDMA_TRANSPORT_IB: + ucma_copy_ib_route(&resp, &ctx->cm_id->route); + break; + default: + break; + } + +out: + if (copy_to_user((void __user *)(unsigned long)cmd.response, + &resp, sizeof(resp))) + ret = -EFAULT; + + ucma_put_ctx(ctx); + return ret; +} + +static void ucma_copy_conn_param(struct rdma_conn_param *dst, + struct rdma_ucm_conn_param *src) +{ + dst->private_data = src->private_data; + dst->private_data_len = src->private_data_len; + dst->responder_resources =src->responder_resources; + dst->initiator_depth = src->initiator_depth; + dst->flow_control = src->flow_control; + dst->retry_count = src->retry_count; + dst->rnr_retry_count = src->rnr_retry_count; + dst->srq = src->srq; + dst->qp_num = src->qp_num; +} + +static ssize_t ucma_connect(struct ucma_file *file, const char __user *inbuf, + int in_len, int out_len) +{ + struct rdma_ucm_connect cmd; + struct rdma_conn_param conn_param; + struct ucma_context *ctx; + int ret; + + if (copy_from_user(&cmd, inbuf, sizeof(cmd))) + return -EFAULT; + + if (!cmd.conn_param.valid) + return -EINVAL; + + ctx = ucma_get_ctx(file, cmd.id); + if (IS_ERR(ctx)) + return PTR_ERR(ctx); + + ucma_copy_conn_param(&conn_param, &cmd.conn_param); + ret = rdma_connect(ctx->cm_id, &conn_param); + ucma_put_ctx(ctx); + return ret; +} + +static ssize_t ucma_listen(struct ucma_file *file, const char __user *inbuf, + int in_len, int out_len) +{ + struct rdma_ucm_listen cmd; + struct ucma_context *ctx; + int ret; + + if (copy_from_user(&cmd, inbuf, sizeof(cmd))) + return -EFAULT; + + ctx = ucma_get_ctx(file, cmd.id); + if (IS_ERR(ctx)) + return PTR_ERR(ctx); + + ctx->backlog = cmd.backlog > 0 && cmd.backlog < UCMA_MAX_BACKLOG ? + cmd.backlog : UCMA_MAX_BACKLOG; + ret = rdma_listen(ctx->cm_id, ctx->backlog); + ucma_put_ctx(ctx); + return ret; +} + +static ssize_t ucma_accept(struct ucma_file *file, const char __user *inbuf, + int in_len, int out_len) +{ + struct rdma_ucm_accept cmd; + struct rdma_conn_param conn_param; + struct ucma_context *ctx; + int ret; + + if (copy_from_user(&cmd, inbuf, sizeof(cmd))) + return -EFAULT; + + ctx = ucma_get_ctx(file, cmd.id); + if (IS_ERR(ctx)) + return PTR_ERR(ctx); + + if (cmd.conn_param.valid) { + ctx->uid = cmd.uid; + ucma_copy_conn_param(&conn_param, &cmd.conn_param); + ret = rdma_accept(ctx->cm_id, &conn_param); + } else + ret = rdma_accept(ctx->cm_id, NULL); + + ucma_put_ctx(ctx); + return ret; +} + +static ssize_t ucma_reject(struct ucma_file *file, const char __user *inbuf, + int in_len, int out_len) +{ + struct rdma_ucm_reject cmd; + struct ucma_context *ctx; + int ret; + + if (copy_from_user(&cmd, inbuf, sizeof(cmd))) + return -EFAULT; + + ctx = ucma_get_ctx(file, cmd.id); + if (IS_ERR(ctx)) + return PTR_ERR(ctx); + + ret = rdma_reject(ctx->cm_id, cmd.private_data, cmd.private_data_len); + ucma_put_ctx(ctx); + return ret; +} + +static ssize_t ucma_disconnect(struct ucma_file *file, const char __user *inbuf, + int in_len, int out_len) +{ + struct rdma_ucm_disconnect cmd; + struct ucma_context *ctx; + int ret; + + if (copy_from_user(&cmd, inbuf, sizeof(cmd))) + return -EFAULT; + + ctx = ucma_get_ctx(file, cmd.id); + if (IS_ERR(ctx)) + return PTR_ERR(ctx); + + ret = rdma_disconnect(ctx->cm_id); + ucma_put_ctx(ctx); + return ret; +} + +static ssize_t ucma_init_qp_attr(struct ucma_file *file, + const char __user *inbuf, + int in_len, int out_len) +{ + struct rdma_ucm_init_qp_attr cmd; + struct ib_uverbs_qp_attr resp; + struct ucma_context *ctx; + struct ib_qp_attr qp_attr; + int ret; + + if (out_len < sizeof(resp)) + return -ENOSPC; + + if (copy_from_user(&cmd, inbuf, sizeof(cmd))) + return -EFAULT; + + ctx = ucma_get_ctx(file, cmd.id); + if (IS_ERR(ctx)) + return PTR_ERR(ctx); + + resp.qp_attr_mask = 0; + memset(&qp_attr, 0, sizeof qp_attr); + qp_attr.qp_state = cmd.qp_state; + ret = rdma_init_qp_attr(ctx->cm_id, &qp_attr, &resp.qp_attr_mask); + if (ret) + goto out; + + ib_copy_qp_attr_to_user(&resp, &qp_attr); + if (copy_to_user((void __user *)(unsigned long)cmd.response, + &resp, sizeof(resp))) + ret = -EFAULT; + +out: + ucma_put_ctx(ctx); + return ret; +} + +static ssize_t ucma_notify(struct ucma_file *file, const char __user *inbuf, + int in_len, int out_len) +{ + struct rdma_ucm_notify cmd; + struct ucma_context *ctx; + int ret; + + if (copy_from_user(&cmd, inbuf, sizeof(cmd))) + return -EFAULT; + + ctx = ucma_get_ctx(file, cmd.id); + if (IS_ERR(ctx)) + return PTR_ERR(ctx); + + ret = rdma_notify(ctx->cm_id, (enum ib_event_type) cmd.event); + ucma_put_ctx(ctx); + return ret; +} + +static ssize_t (*ucma_cmd_table[])(struct ucma_file *file, + const char __user *inbuf, + int in_len, int out_len) = { + [RDMA_USER_CM_CMD_CREATE_ID] = ucma_create_id, + [RDMA_USER_CM_CMD_DESTROY_ID] = ucma_destroy_id, + [RDMA_USER_CM_CMD_BIND_ADDR] = ucma_bind_addr, + [RDMA_USER_CM_CMD_RESOLVE_ADDR] = ucma_resolve_addr, + [RDMA_USER_CM_CMD_RESOLVE_ROUTE]= ucma_resolve_route, + [RDMA_USER_CM_CMD_QUERY_ROUTE] = ucma_query_route, + [RDMA_USER_CM_CMD_CONNECT] = ucma_connect, + [RDMA_USER_CM_CMD_LISTEN] = ucma_listen, + [RDMA_USER_CM_CMD_ACCEPT] = ucma_accept, + [RDMA_USER_CM_CMD_REJECT] = ucma_reject, + [RDMA_USER_CM_CMD_DISCONNECT] = ucma_disconnect, + [RDMA_USER_CM_CMD_INIT_QP_ATTR] = ucma_init_qp_attr, + [RDMA_USER_CM_CMD_GET_EVENT] = ucma_get_event, + [RDMA_USER_CM_CMD_GET_OPTION] = NULL, + [RDMA_USER_CM_CMD_SET_OPTION] = NULL, + [RDMA_USER_CM_CMD_NOTIFY] = ucma_notify, +}; + +static ssize_t ucma_write(struct file *filp, const char __user *buf, + size_t len, loff_t *pos) +{ + struct ucma_file *file = filp->private_data; + struct rdma_ucm_cmd_hdr hdr; + ssize_t ret; + + if (len < sizeof(hdr)) + return -EINVAL; + + if (copy_from_user(&hdr, buf, sizeof(hdr))) + return -EFAULT; + + if (hdr.cmd < 0 || hdr.cmd >= ARRAY_SIZE(ucma_cmd_table)) + return -EINVAL; + + if (hdr.in + sizeof(hdr) > len) + return -EINVAL; + + if (!ucma_cmd_table[hdr.cmd]) + return -ENOSYS; + + ret = ucma_cmd_table[hdr.cmd](file, buf + sizeof(hdr), hdr.in, hdr.out); + if (!ret) + ret = len; + + return ret; +} + +static unsigned int ucma_poll(struct file *filp, struct poll_table_struct *wait) +{ + struct ucma_file *file = filp->private_data; + unsigned int mask = 0; + + poll_wait(filp, &file->poll_wait, wait); + + if (!list_empty(&file->event_list)) + mask = POLLIN | POLLRDNORM; + + return mask; +} + +static int ucma_open(struct inode *inode, struct file *filp) +{ + struct ucma_file *file; + + file = kmalloc(sizeof *file, GFP_KERNEL); + if (!file) + return -ENOMEM; + + INIT_LIST_HEAD(&file->event_list); + INIT_LIST_HEAD(&file->ctx_list); + init_waitqueue_head(&file->poll_wait); + mutex_init(&file->mut); + + filp->private_data = file; + file->filp = filp; + return 0; +} + +static int ucma_close(struct inode *inode, struct file *filp) +{ + struct ucma_file *file = filp->private_data; + struct ucma_context *ctx, *tmp; + + mutex_lock(&file->mut); + list_for_each_entry_safe(ctx, tmp, &file->ctx_list, list) { + mutex_unlock(&file->mut); + + mutex_lock(&mut); + idr_remove(&ctx_idr, ctx->id); + mutex_unlock(&mut); + + ucma_free_ctx(ctx); + mutex_lock(&file->mut); + } + mutex_unlock(&file->mut); + kfree(file); + return 0; +} + +static struct file_operations ucma_fops = { + .owner = THIS_MODULE, + .open = ucma_open, + .release = ucma_close, + .write = ucma_write, + .poll = ucma_poll, +}; + +static struct miscdevice ucma_misc = { + .minor = MISC_DYNAMIC_MINOR, + .name = "rdma_cm", + .fops = &ucma_fops, +}; + +static ssize_t show_abi_version(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + return sprintf(buf, "%d\n", RDMA_USER_CM_ABI_VERSION); +} +static DEVICE_ATTR(abi_version, S_IRUGO, show_abi_version, NULL); + +static int __init ucma_init(void) +{ + int ret; + + ret = misc_register(&ucma_misc); + if (ret) + return ret; + + ret = device_create_file(ucma_misc.this_device, &dev_attr_abi_version); + if (ret) { + printk(KERN_ERR "rdma_ucm: couldn't create abi_version attr\n"); + goto err; + } + return 0; +err: + misc_deregister(&ucma_misc); + return ret; +} + +static void __exit ucma_cleanup(void) +{ + device_remove_file(ucma_misc.this_device, &dev_attr_abi_version); + misc_deregister(&ucma_misc); + idr_destroy(&ctx_idr); +} + +module_init(ucma_init); +module_exit(ucma_cleanup); diff --git a/drivers/infiniband/core/uverbs_marshall.c b/drivers/infiniband/core/uverbs_marshall.c index ce46b13ae02..5440da0e59b 100644 --- a/drivers/infiniband/core/uverbs_marshall.c +++ b/drivers/infiniband/core/uverbs_marshall.c @@ -32,8 +32,8 @@ #include <rdma/ib_marshall.h> -static void ib_copy_ah_attr_to_user(struct ib_uverbs_ah_attr *dst, - struct ib_ah_attr *src) +void ib_copy_ah_attr_to_user(struct ib_uverbs_ah_attr *dst, + struct ib_ah_attr *src) { memcpy(dst->grh.dgid, src->grh.dgid.raw, sizeof src->grh.dgid); dst->grh.flow_label = src->grh.flow_label; @@ -47,6 +47,7 @@ static void ib_copy_ah_attr_to_user(struct ib_uverbs_ah_attr *dst, dst->is_global = src->ah_flags & IB_AH_GRH ? 1 : 0; dst->port_num = src->port_num; } +EXPORT_SYMBOL(ib_copy_ah_attr_to_user); void ib_copy_qp_attr_to_user(struct ib_uverbs_qp_attr *dst, struct ib_qp_attr *src) diff --git a/drivers/infiniband/core/uverbs_mem.c b/drivers/infiniband/core/uverbs_mem.c index db12cc0841d..c95fe952abd 100644 --- a/drivers/infiniband/core/uverbs_mem.c +++ b/drivers/infiniband/core/uverbs_mem.c @@ -52,8 +52,8 @@ static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int d int i; list_for_each_entry_safe(chunk, tmp, &umem->chunk_list, list) { - dma_unmap_sg(dev->dma_device, chunk->page_list, - chunk->nents, DMA_BIDIRECTIONAL); + ib_dma_unmap_sg(dev, chunk->page_list, + chunk->nents, DMA_BIDIRECTIONAL); for (i = 0; i < chunk->nents; ++i) { if (umem->writable && dirty) set_page_dirty_lock(chunk->page_list[i].page); @@ -136,10 +136,10 @@ int ib_umem_get(struct ib_device *dev, struct ib_umem *mem, chunk->page_list[i].length = PAGE_SIZE; } - chunk->nmap = dma_map_sg(dev->dma_device, - &chunk->page_list[0], - chunk->nents, - DMA_BIDIRECTIONAL); + chunk->nmap = ib_dma_map_sg(dev, + &chunk->page_list[0], + chunk->nents, + DMA_BIDIRECTIONAL); if (chunk->nmap <= 0) { for (i = 0; i < chunk->nents; ++i) put_page(chunk->page_list[i].page); diff --git a/drivers/infiniband/hw/amso1100/c2_qp.c b/drivers/infiniband/hw/amso1100/c2_qp.c index 179d005ed4a..420c1380f5c 100644 --- a/drivers/infiniband/hw/amso1100/c2_qp.c +++ b/drivers/infiniband/hw/amso1100/c2_qp.c @@ -161,8 +161,10 @@ int c2_qp_modify(struct c2_dev *c2dev, struct c2_qp *qp, if (attr_mask & IB_QP_STATE) { /* Ensure the state is valid */ - if (attr->qp_state < 0 || attr->qp_state > IB_QPS_ERR) - return -EINVAL; + if (attr->qp_state < 0 || attr->qp_state > IB_QPS_ERR) { + err = -EINVAL; + goto bail0; + } wr.next_qp_state = cpu_to_be32(to_c2_state(attr->qp_state)); @@ -184,9 +186,10 @@ int c2_qp_modify(struct c2_dev *c2dev, struct c2_qp *qp, if (attr->cur_qp_state != IB_QPS_RTR && attr->cur_qp_state != IB_QPS_RTS && attr->cur_qp_state != IB_QPS_SQD && - attr->cur_qp_state != IB_QPS_SQE) - return -EINVAL; - else + attr->cur_qp_state != IB_QPS_SQE) { + err = -EINVAL; + goto bail0; + } else wr.next_qp_state = cpu_to_be32(to_c2_state(attr->cur_qp_state)); diff --git a/drivers/infiniband/hw/ipath/Makefile b/drivers/infiniband/hw/ipath/Makefile index 7dc10551cf1..ec2e603ea24 100644 --- a/drivers/infiniband/hw/ipath/Makefile +++ b/drivers/infiniband/hw/ipath/Makefile @@ -6,6 +6,7 @@ obj-$(CONFIG_INFINIBAND_IPATH) += ib_ipath.o ib_ipath-y := \ ipath_cq.o \ ipath_diag.o \ + ipath_dma.o \ ipath_driver.o \ ipath_eeprom.o \ ipath_file_ops.o \ diff --git a/drivers/infiniband/hw/ipath/ipath_dma.c b/drivers/infiniband/hw/ipath/ipath_dma.c new file mode 100644 index 00000000000..6e0f2b8918c --- /dev/null +++ b/drivers/infiniband/hw/ipath/ipath_dma.c @@ -0,0 +1,189 @@ +/* + * Copyright (c) 2006 QLogic, Corporation. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include <rdma/ib_verbs.h> + +#include "ipath_verbs.h" + +#define BAD_DMA_ADDRESS ((u64) 0) + +/* + * The following functions implement driver specific replacements + * for the ib_dma_*() functions. + * + * These functions return kernel virtual addresses instead of + * device bus addresses since the driver uses the CPU to copy + * data instead of using hardware DMA. + */ + +static int ipath_mapping_error(struct ib_device *dev, u64 dma_addr) +{ + return dma_addr == BAD_DMA_ADDRESS; +} + +static u64 ipath_dma_map_single(struct ib_device *dev, + void *cpu_addr, size_t size, + enum dma_data_direction direction) +{ + BUG_ON(!valid_dma_direction(direction)); + return (u64) cpu_addr; +} + +static void ipath_dma_unmap_single(struct ib_device *dev, + u64 addr, size_t size, + enum dma_data_direction direction) +{ + BUG_ON(!valid_dma_direction(direction)); +} + +static u64 ipath_dma_map_page(struct ib_device *dev, + struct page *page, + unsigned long offset, + size_t size, + enum dma_data_direction direction) +{ + u64 addr; + + BUG_ON(!valid_dma_direction(direction)); + + if (offset + size > PAGE_SIZE) { + addr = BAD_DMA_ADDRESS; + goto done; + } + + addr = (u64) page_address(page); + if (addr) + addr += offset; + /* TODO: handle highmem pages */ + +done: + return addr; +} + +static void ipath_dma_unmap_page(struct ib_device *dev, + u64 addr, size_t size, + enum dma_data_direction direction) +{ + BUG_ON(!valid_dma_direction(direction)); +} + +int ipath_map_sg(struct ib_device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction direction) +{ + u64 addr; + int i; + int ret = nents; + + BUG_ON(!valid_dma_direction(direction)); + + for (i = 0; i < nents; i++) { + addr = (u64) page_address(sg[i].page); + /* TODO: handle highmem pages */ + if (!addr) { + ret = 0; + break; + } + } + return ret; +} + +static void ipath_unmap_sg(struct ib_device *dev, + struct scatterlist *sg, int nents, + enum dma_data_direction direction) +{ + BUG_ON(!valid_dma_direction(direction)); +} + +static u64 ipath_sg_dma_address(struct ib_device *dev, struct scatterlist *sg) +{ + u64 addr = (u64) page_address(sg->page); + + if (addr) + addr += sg->offset; + return addr; +} + +static unsigned int ipath_sg_dma_len(struct ib_device *dev, + struct scatterlist *sg) +{ + return sg->length; +} + +static void ipath_sync_single_for_cpu(struct ib_device *dev, + u64 addr, + size_t size, + enum dma_data_direction dir) +{ +} + +static void ipath_sync_single_for_device(struct ib_device *dev, + u64 addr, + size_t size, + enum dma_data_direction dir) +{ +} + +static void *ipath_dma_alloc_coherent(struct ib_device *dev, size_t size, + u64 *dma_handle, gfp_t flag) +{ + struct page *p; + void *addr = NULL; + + p = alloc_pages(flag, get_order(size)); + if (p) + addr = page_address(p); + if (dma_handle) + *dma_handle = (u64) addr; + return addr; +} + +static void ipath_dma_free_coherent(struct ib_device *dev, size_t size, + void *cpu_addr, dma_addr_t dma_handle) +{ + free_pages((unsigned long) cpu_addr, get_order(size)); +} + +struct ib_dma_mapping_ops ipath_dma_mapping_ops = { + ipath_mapping_error, + ipath_dma_map_single, + ipath_dma_unmap_single, + ipath_dma_map_page, + ipath_dma_unmap_page, + ipath_map_sg, + ipath_unmap_sg, + ipath_sg_dma_address, + ipath_sg_dma_len, + ipath_sync_single_for_cpu, + ipath_sync_single_for_device, + ipath_dma_alloc_coherent, + ipath_dma_free_coherent +}; diff --git a/drivers/infiniband/hw/ipath/ipath_driver.c b/drivers/infiniband/hw/ipath/ipath_driver.c index 1aeddb48e35..ae7f21a0cdc 100644 --- a/drivers/infiniband/hw/ipath/ipath_driver.c +++ b/drivers/infiniband/hw/ipath/ipath_driver.c @@ -1825,8 +1825,6 @@ void ipath_write_kreg_port(const struct ipath_devdata *dd, ipath_kreg regno, */ void ipath_shutdown_device(struct ipath_devdata *dd) { - u64 val; - ipath_dbg("Shutting down the device\n"); dd->ipath_flags |= IPATH_LINKUNK; @@ -1849,7 +1847,7 @@ void ipath_shutdown_device(struct ipath_devdata *dd) */ ipath_write_kreg(dd, dd->ipath_kregs->kr_sendctrl, 0ULL); /* flush it */ - val = ipath_read_kreg64(dd, dd->ipath_kregs->kr_scratch); + ipath_read_kreg64(dd, dd->ipath_kregs->kr_scratch); /* * enough for anything that's going to trickle out to have actually * done so. diff --git a/drivers/infiniband/hw/ipath/ipath_file_ops.c b/drivers/infiniband/hw/ipath/ipath_file_ops.c index 340f27e3ebf..b932bcb67a5 100644 --- a/drivers/infiniband/hw/ipath/ipath_file_ops.c +++ b/drivers/infiniband/hw/ipath/ipath_file_ops.c @@ -699,7 +699,6 @@ static int ipath_manage_rcvq(struct ipath_portdata *pd, unsigned subport, int start_stop) { struct ipath_devdata *dd = pd->port_dd; - u64 tval; ipath_cdbg(PROC, "%sabling rcv for unit %u port %u:%u\n", start_stop ? "en" : "dis", dd->ipath_unit, @@ -729,7 +728,7 @@ static int ipath_manage_rcvq(struct ipath_portdata *pd, unsigned subport, ipath_write_kreg(dd, dd->ipath_kregs->kr_rcvctrl, dd->ipath_rcvctrl); /* now be sure chip saw it before we return */ - tval = ipath_read_kreg64(dd, dd->ipath_kregs->kr_scratch); + ipath_read_kreg64(dd, dd->ipath_kregs->kr_scratch); if (start_stop) { /* * And try to be sure that tail reg update has happened too. @@ -738,7 +737,7 @@ static int ipath_manage_rcvq(struct ipath_portdata *pd, unsigned subport, * in memory copy, since we could overwrite an update by the * chip if we did. */ - tval = ipath_read_ureg32(dd, ur_rcvhdrtail, pd->port_port); + ipath_read_ureg32(dd, ur_rcvhdrtail, pd->port_port); } /* always; new head should be equal to new tail; see above */ bail: diff --git a/drivers/infiniband/hw/ipath/ipath_iba6110.c b/drivers/infiniband/hw/ipath/ipath_iba6110.c index e57c7a351cb..7468477ba83 100644 --- a/drivers/infiniband/hw/ipath/ipath_iba6110.c +++ b/drivers/infiniband/hw/ipath/ipath_iba6110.c @@ -1447,7 +1447,7 @@ static void ipath_ht_tidtemplate(struct ipath_devdata *dd) static int ipath_ht_early_init(struct ipath_devdata *dd) { u32 __iomem *piobuf; - u32 pioincr, val32, egrsize; + u32 pioincr, val32; int i; /* @@ -1467,7 +1467,6 @@ static int ipath_ht_early_init(struct ipath_devdata *dd) * errors interrupts if we ever see one). */ dd->ipath_rcvegrbufsize = dd->ipath_piosize2k; - egrsize = dd->ipath_rcvegrbufsize; /* * the min() check here is currently a nop, but it may not diff --git a/drivers/infiniband/hw/ipath/ipath_iba6120.c b/drivers/infiniband/hw/ipath/ipath_iba6120.c index 6af89683f71..ae8bf9950c6 100644 --- a/drivers/infiniband/hw/ipath/ipath_iba6120.c +++ b/drivers/infiniband/hw/ipath/ipath_iba6120.c @@ -602,7 +602,7 @@ static void ipath_pe_init_hwerrors(struct ipath_devdata *dd) */ static int ipath_pe_bringup_serdes(struct ipath_devdata *dd) { - u64 val, tmp, config1, prev_val; + u64 val, config1, prev_val; int ret = 0; ipath_dbg("Trying to bringup serdes\n"); @@ -633,7 +633,7 @@ static int ipath_pe_bringup_serdes(struct ipath_devdata *dd) | INFINIPATH_SERDC0_L1PWR_DN; ipath_write_kreg(dd, dd->ipath_kregs->kr_serdesconfig0, val); /* be sure chip saw it */ - tmp = ipath_read_kreg64(dd, dd->ipath_kregs->kr_scratch); + ipath_read_kreg64(dd, dd->ipath_kregs->kr_scratch); udelay(5); /* need pll reset set at least for a bit */ /* * after PLL is reset, set the per-lane Resets and TxIdle and @@ -647,7 +647,7 @@ static int ipath_pe_bringup_serdes(struct ipath_devdata *dd) "and txidle (%llx)\n", (unsigned long long) val); ipath_write_kreg(dd, dd->ipath_kregs->kr_serdesconfig0, val); /* be sure chip saw it */ - tmp = ipath_read_kreg64(dd, dd->ipath_kregs->kr_scratch); + ipath_read_kreg64(dd, dd->ipath_kregs->kr_scratch); /* need PLL reset clear for at least 11 usec before lane * resets cleared; give it a few more to be sure */ udelay(15); @@ -851,12 +851,12 @@ static int ipath_setup_pe_config(struct ipath_devdata *dd, int pos, ret; dd->ipath_msi_lo = 0; /* used as a flag during reset processing */ - dd->ipath_irq = pdev->irq; ret = pci_enable_msi(dd->pcidev); if (ret) ipath_dev_err(dd, "pci_enable_msi failed: %d, " "interrupts may not work\n", ret); /* continue even if it fails, we may still be OK... */ + dd->ipath_irq = pdev->irq; if ((pos = pci_find_capability(dd->pcidev, PCI_CAP_ID_MSI))) { u16 control; diff --git a/drivers/infiniband/hw/ipath/ipath_init_chip.c b/drivers/infiniband/hw/ipath/ipath_init_chip.c index d819cca524c..d4f6b5239ef 100644 --- a/drivers/infiniband/hw/ipath/ipath_init_chip.c +++ b/drivers/infiniband/hw/ipath/ipath_init_chip.c @@ -347,10 +347,9 @@ done: static int init_chip_reset(struct ipath_devdata *dd, struct ipath_portdata **pdp) { - struct ipath_portdata *pd; u32 rtmp; - *pdp = pd = dd->ipath_pd[0]; + *pdp = dd->ipath_pd[0]; /* ensure chip does no sends or receives while we re-initialize */ dd->ipath_control = dd->ipath_sendctrl = dd->ipath_rcvctrl = 0U; ipath_write_kreg(dd, dd->ipath_kregs->kr_rcvctrl, 0); diff --git a/drivers/infiniband/hw/ipath/ipath_intr.c b/drivers/infiniband/hw/ipath/ipath_intr.c index 5652a550d44..72b9e279d19 100644 --- a/drivers/infiniband/hw/ipath/ipath_intr.c +++ b/drivers/infiniband/hw/ipath/ipath_intr.c @@ -598,10 +598,9 @@ static int handle_errors(struct ipath_devdata *dd, ipath_err_t errs) * on close */ if (errs & INFINIPATH_E_RRCVHDRFULL) { - int any; u32 hd, tl; ipath_stats.sps_hdrqfull++; - for (any = i = 0; i < dd->ipath_cfgports; i++) { + for (i = 0; i < dd->ipath_cfgports; i++) { struct ipath_portdata *pd = dd->ipath_pd[i]; if (i == 0) { hd = dd->ipath_port0head; diff --git a/drivers/infiniband/hw/ipath/ipath_keys.c b/drivers/infiniband/hw/ipath/ipath_keys.c index 9a6cbd05adc..851763d7d2d 100644 --- a/drivers/infiniband/hw/ipath/ipath_keys.c +++ b/drivers/infiniband/hw/ipath/ipath_keys.c @@ -134,7 +134,7 @@ int ipath_lkey_ok(struct ipath_qp *qp, struct ipath_sge *isge, */ if (sge->lkey == 0) { isge->mr = NULL; - isge->vaddr = bus_to_virt(sge->addr); + isge->vaddr = (void *) sge->addr; isge->length = sge->length; isge->sge_length = sge->length; ret = 1; @@ -202,12 +202,12 @@ int ipath_rkey_ok(struct ipath_qp *qp, struct ipath_sge_state *ss, int ret; /* - * We use RKEY == zero for physical addresses - * (see ipath_get_dma_mr). + * We use RKEY == zero for kernel virtual addresses + * (see ipath_get_dma_mr and ipath_dma.c). */ if (rkey == 0) { sge->mr = NULL; - sge->vaddr = phys_to_virt(vaddr); + sge->vaddr = (void *) vaddr; sge->length = len; sge->sge_length = len; ss->sg_list = NULL; diff --git a/drivers/infiniband/hw/ipath/ipath_mr.c b/drivers/infiniband/hw/ipath/ipath_mr.c index a0673c1eef7..8cc8598d6c6 100644 --- a/drivers/infiniband/hw/ipath/ipath_mr.c +++ b/drivers/infiniband/hw/ipath/ipath_mr.c @@ -54,6 +54,8 @@ static inline struct ipath_fmr *to_ifmr(struct ib_fmr *ibfmr) * @acc: access flags * * Returns the memory region on success, otherwise returns an errno. + * Note that all DMA addresses should be created via the + * struct ib_dma_mapping_ops functions (see ipath_dma.c). */ struct ib_mr *ipath_get_dma_mr(struct ib_pd *pd, int acc) { @@ -149,8 +151,7 @@ struct ib_mr *ipath_reg_phys_mr(struct ib_pd *pd, m = 0; n = 0; for (i = 0; i < num_phys_buf; i++) { - mr->mr.map[m]->segs[n].vaddr = - phys_to_virt(buffer_list[i].addr); + mr->mr.map[m]->segs[n].vaddr = (void *) buffer_list[i].addr; mr->mr.map[m]->segs[n].length = buffer_list[i].size; mr->mr.length += buffer_list[i].size; n++; @@ -347,7 +348,7 @@ int ipath_map_phys_fmr(struct ib_fmr *ibfmr, u64 * page_list, n = 0; ps = 1 << fmr->page_shift; for (i = 0; i < list_len; i++) { - fmr->mr.map[m]->segs[n].vaddr = phys_to_virt(page_list[i]); + fmr->mr.map[m]->segs[n].vaddr = (void *) page_list[i]; fmr->mr.map[m]->segs[n].length = ps; if (++n == IPATH_SEGSZ) { m++; diff --git a/drivers/infiniband/hw/ipath/ipath_sysfs.c b/drivers/infiniband/hw/ipath/ipath_sysfs.c index 182de34f9f4..ffa6318ad0c 100644 --- a/drivers/infiniband/hw/ipath/ipath_sysfs.c +++ b/drivers/infiniband/hw/ipath/ipath_sysfs.c @@ -215,7 +215,6 @@ static ssize_t store_mlid(struct device *dev, size_t count) { struct ipath_devdata *dd = dev_get_drvdata(dev); - int unit; u16 mlid; int ret; @@ -223,8 +222,6 @@ static ssize_t store_mlid(struct device *dev, if (ret < 0 || mlid < IPATH_MULTICAST_LID_BASE) goto invalid; - unit = dd->ipath_unit; - dd->ipath_mlid = mlid; goto bail; diff --git a/drivers/infiniband/hw/ipath/ipath_verbs.c b/drivers/infiniband/hw/ipath/ipath_verbs.c index acdee33ee1f..2aaacdb7e52 100644 --- a/drivers/infiniband/hw/ipath/ipath_verbs.c +++ b/drivers/infiniband/hw/ipath/ipath_verbs.c @@ -1599,6 +1599,7 @@ int ipath_register_ib_device(struct ipath_devdata *dd) dev->detach_mcast = ipath_multicast_detach; dev->process_mad = ipath_process_mad; dev->mmap = ipath_mmap; + dev->dma_ops = &ipath_dma_mapping_ops; snprintf(dev->node_desc, sizeof(dev->node_desc), IPATH_IDSTR " %s", init_utsname()->nodename); diff --git a/drivers/infiniband/hw/ipath/ipath_verbs.h b/drivers/infiniband/hw/ipath/ipath_verbs.h index 8039f6e5f0c..c0c8d5b24a7 100644 --- a/drivers/infiniband/hw/ipath/ipath_verbs.h +++ b/drivers/infiniband/hw/ipath/ipath_verbs.h @@ -812,4 +812,6 @@ extern unsigned int ib_ipath_max_srq_wrs; extern const u32 ib_ipath_rnr_table[]; +extern struct ib_dma_mapping_ops ipath_dma_mapping_ops; + #endif /* IPATH_VERBS_H */ diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h index 99547996aba..07deee8f81c 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib.h +++ b/drivers/infiniband/ulp/ipoib/ipoib.h @@ -105,12 +105,12 @@ struct ipoib_mcast; struct ipoib_rx_buf { struct sk_buff *skb; - dma_addr_t mapping; + u64 mapping; }; struct ipoib_tx_buf { struct sk_buff *skb; - DECLARE_PCI_UNMAP_ADDR(mapping) + u64 mapping; }; /* diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index f10fba5d326..59d9594ed6d 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -109,9 +109,8 @@ static int ipoib_ib_post_receive(struct net_device *dev, int id) ret = ib_post_recv(priv->qp, ¶m, &bad_wr); if (unlikely(ret)) { ipoib_warn(priv, "receive failed for buf %d (%d)\n", id, ret); - dma_unmap_single(priv->ca->dma_device, - priv->rx_ring[id].mapping, - IPOIB_BUF_SIZE, DMA_FROM_DEVICE); + ib_dma_unmap_single(priv->ca, priv->rx_ring[id].mapping, + IPOIB_BUF_SIZE, DMA_FROM_DEVICE); dev_kfree_skb_any(priv->rx_ring[id].skb); priv->rx_ring[id].skb = NULL; } @@ -123,7 +122,7 @@ static int ipoib_alloc_rx_skb(struct net_device *dev, int id) { struct ipoib_dev_priv *priv = netdev_priv(dev); struct sk_buff *skb; - dma_addr_t addr; + u64 addr; skb = dev_alloc_skb(IPOIB_BUF_SIZE + 4); if (!skb) @@ -136,10 +135,9 @@ static int ipoib_alloc_rx_skb(struct net_device *dev, int id) */ skb_reserve(skb, 4); - addr = dma_map_single(priv->ca->dma_device, - skb->data, IPOIB_BUF_SIZE, - DMA_FROM_DEVICE); - if (unlikely(dma_mapping_error(addr))) { + addr = ib_dma_map_single(priv->ca, skb->data, IPOIB_BUF_SIZE, + DMA_FROM_DEVICE); + if (unlikely(ib_dma_mapping_error(priv->ca, addr))) { dev_kfree_skb_any(skb); return -EIO; } @@ -174,7 +172,7 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc) struct ipoib_dev_priv *priv = netdev_priv(dev); unsigned int wr_id = wc->wr_id & ~IPOIB_OP_RECV; struct sk_buff *skb; - dma_addr_t addr; + u64 addr; ipoib_dbg_data(priv, "recv completion: id %d, op %d, status: %d\n", wr_id, wc->opcode, wc->status); @@ -193,8 +191,8 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc) ipoib_warn(priv, "failed recv event " "(status=%d, wrid=%d vend_err %x)\n", wc->status, wr_id, wc->vendor_err); - dma_unmap_single(priv->ca->dma_device, addr, - IPOIB_BUF_SIZE, DMA_FROM_DEVICE); + ib_dma_unmap_single(priv->ca, addr, + IPOIB_BUF_SIZE, DMA_FROM_DEVICE); dev_kfree_skb_any(skb); priv->rx_ring[wr_id].skb = NULL; return; @@ -212,8 +210,7 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc) ipoib_dbg_data(priv, "received %d bytes, SLID 0x%04x\n", wc->byte_len, wc->slid); - dma_unmap_single(priv->ca->dma_device, addr, - IPOIB_BUF_SIZE, DMA_FROM_DEVICE); + ib_dma_unmap_single(priv->ca, addr, IPOIB_BUF_SIZE, DMA_FROM_DEVICE); skb_put(skb, wc->byte_len); skb_pull(skb, IB_GRH_BYTES); @@ -261,10 +258,8 @@ static void ipoib_ib_handle_tx_wc(struct net_device *dev, struct ib_wc *wc) tx_req = &priv->tx_ring[wr_id]; - dma_unmap_single(priv->ca->dma_device, - pci_unmap_addr(tx_req, mapping), - tx_req->skb->len, - DMA_TO_DEVICE); + ib_dma_unmap_single(priv->ca, tx_req->mapping, + tx_req->skb->len, DMA_TO_DEVICE); ++priv->stats.tx_packets; priv->stats.tx_bytes += tx_req->skb->len; @@ -311,7 +306,7 @@ void ipoib_ib_completion(struct ib_cq *cq, void *dev_ptr) static inline int post_send(struct ipoib_dev_priv *priv, unsigned int wr_id, struct ib_ah *address, u32 qpn, - dma_addr_t addr, int len) + u64 addr, int len) { struct ib_send_wr *bad_wr; @@ -330,7 +325,7 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb, { struct ipoib_dev_priv *priv = netdev_priv(dev); struct ipoib_tx_buf *tx_req; - dma_addr_t addr; + u64 addr; if (unlikely(skb->len > dev->mtu + INFINIBAND_ALEN)) { ipoib_warn(priv, "packet len %d (> %d) too long to send, dropping\n", @@ -353,21 +348,20 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb, */ tx_req = &priv->tx_ring[priv->tx_head & (ipoib_sendq_size - 1)]; tx_req->skb = skb; - addr = dma_map_single(priv->ca->dma_device, skb->data, skb->len, - DMA_TO_DEVICE); - if (unlikely(dma_mapping_error(addr))) { + addr = ib_dma_map_single(priv->ca, skb->data, skb->len, + DMA_TO_DEVICE); + if (unlikely(ib_dma_mapping_error(priv->ca, addr))) { ++priv->stats.tx_errors; dev_kfree_skb_any(skb); return; } - pci_unmap_addr_set(tx_req, mapping, addr); + tx_req->mapping = addr; if (unlikely(post_send(priv, priv->tx_head & (ipoib_sendq_size - 1), address->ah, qpn, addr, skb->len))) { ipoib_warn(priv, "post_send failed\n"); ++priv->stats.tx_errors; - dma_unmap_single(priv->ca->dma_device, addr, skb->len, - DMA_TO_DEVICE); + ib_dma_unmap_single(priv->ca, addr, skb->len, DMA_TO_DEVICE); dev_kfree_skb_any(skb); } else { dev->trans_start = jiffies; @@ -538,24 +532,27 @@ int ipoib_ib_dev_stop(struct net_device *dev) while ((int) priv->tx_tail - (int) priv->tx_head < 0) { tx_req = &priv->tx_ring[priv->tx_tail & (ipoib_sendq_size - 1)]; - dma_unmap_single(priv->ca->dma_device, - pci_unmap_addr(tx_req, mapping), - tx_req->skb->len, - DMA_TO_DEVICE); + ib_dma_unmap_single(priv->ca, + tx_req->mapping, + tx_req->skb->len, + DMA_TO_DEVICE); dev_kfree_skb_any(tx_req->skb); ++priv->tx_tail; } - for (i = 0; i < ipoib_recvq_size; ++i) - if (priv->rx_ring[i].skb) { - dma_unmap_single(priv->ca->dma_device, - pci_unmap_addr(&priv->rx_ring[i], - mapping), - IPOIB_BUF_SIZE, - DMA_FROM_DEVICE); - dev_kfree_skb_any(priv->rx_ring[i].skb); - priv->rx_ring[i].skb = NULL; - } + for (i = 0; i < ipoib_recvq_size; ++i) { + struct ipoib_rx_buf *rx_req; + + rx_req = &priv->rx_ring[i]; + if (!rx_req->skb) + continue; + ib_dma_unmap_single(priv->ca, + rx_req->mapping, + IPOIB_BUF_SIZE, + DMA_FROM_DEVICE); + dev_kfree_skb_any(rx_req->skb); + rx_req->skb = NULL; + } goto timeout; } diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index c0928024372..705eb1d0e55 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -497,8 +497,6 @@ static void neigh_add_path(struct sk_buff *skb, struct net_device *dev) return; } - skb_queue_head_init(&neigh->queue); - /* * We can only be called from ipoib_start_xmit, so we're * inside tx_lock -- no need to save/restore flags. @@ -806,6 +804,7 @@ struct ipoib_neigh *ipoib_neigh_alloc(struct neighbour *neighbour) neigh->neighbour = neighbour; *to_ipoib_neigh(neighbour) = neigh; + skb_queue_head_init(&neigh->queue); return neigh; } diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.h b/drivers/infiniband/ulp/iser/iscsi_iser.h index 234e5b061a7..cae8c96a55f 100644 --- a/drivers/infiniband/ulp/iser/iscsi_iser.h +++ b/drivers/infiniband/ulp/iser/iscsi_iser.h @@ -182,7 +182,7 @@ struct iser_regd_buf { struct iser_mem_reg reg; /* memory registration info */ void *virt_addr; struct iser_device *device; /* device->device for dma_unmap */ - dma_addr_t dma_addr; /* if non zero, addr for dma_unmap */ + u64 dma_addr; /* if non zero, addr for dma_unmap */ enum dma_data_direction direction; /* direction for dma_unmap */ unsigned int data_size; atomic_t ref_count; /* refcount, freed when dec to 0 */ diff --git a/drivers/infiniband/ulp/iser/iser_initiator.c b/drivers/infiniband/ulp/iser/iser_initiator.c index 9b3d79c796c..e73c87b9be4 100644 --- a/drivers/infiniband/ulp/iser/iser_initiator.c +++ b/drivers/infiniband/ulp/iser/iser_initiator.c @@ -487,10 +487,8 @@ int iser_send_control(struct iscsi_conn *conn, struct iscsi_iser_conn *iser_conn = conn->dd_data; struct iser_desc *mdesc = mtask->dd_data; struct iser_dto *send_dto = NULL; - unsigned int itt; unsigned long data_seg_len; int err = 0; - unsigned char opcode; struct iser_regd_buf *regd_buf; struct iser_device *device; @@ -512,8 +510,6 @@ int iser_send_control(struct iscsi_conn *conn, iser_reg_single(device, send_dto->regd[0], DMA_TO_DEVICE); - itt = ntohl(mtask->hdr->itt); - opcode = mtask->hdr->opcode & ISCSI_OPCODE_MASK; data_seg_len = ntoh24(mtask->hdr->dlength); if (data_seg_len > 0) { diff --git a/drivers/infiniband/ulp/iser/iser_memory.c b/drivers/infiniband/ulp/iser/iser_memory.c index 3aedd59b8a8..fc9f1fd0ae5 100644 --- a/drivers/infiniband/ulp/iser/iser_memory.c +++ b/drivers/infiniband/ulp/iser/iser_memory.c @@ -52,7 +52,7 @@ */ int iser_regd_buff_release(struct iser_regd_buf *regd_buf) { - struct device *dma_device; + struct ib_device *dev; if ((atomic_read(®d_buf->ref_count) == 0) || atomic_dec_and_test(®d_buf->ref_count)) { @@ -61,8 +61,8 @@ int iser_regd_buff_release(struct iser_regd_buf *regd_buf) iser_unreg_mem(®d_buf->reg); if (regd_buf->dma_addr) { - dma_device = regd_buf->device->ib_device->dma_device; - dma_unmap_single(dma_device, + dev = regd_buf->device->ib_device; + ib_dma_unmap_single(dev, regd_buf->dma_addr, regd_buf->data_size, regd_buf->direction); @@ -84,12 +84,12 @@ void iser_reg_single(struct iser_device *device, struct iser_regd_buf *regd_buf, enum dma_data_direction direction) { - dma_addr_t dma_addr; + u64 dma_addr; - dma_addr = dma_map_single(device->ib_device->dma_device, - regd_buf->virt_addr, - regd_buf->data_size, direction); - BUG_ON(dma_mapping_error(dma_addr)); + dma_addr = ib_dma_map_single(device->ib_device, + regd_buf->virt_addr, + regd_buf->data_size, direction); + BUG_ON(ib_dma_mapping_error(device->ib_device, dma_addr)); regd_buf->reg.lkey = device->mr->lkey; regd_buf->reg.len = regd_buf->data_size; @@ -107,7 +107,7 @@ int iser_start_rdma_unaligned_sg(struct iscsi_iser_cmd_task *iser_ctask, enum iser_data_dir cmd_dir) { int dma_nents; - struct device *dma_device; + struct ib_device *dev; char *mem = NULL; struct iser_data_buf *data = &iser_ctask->data[cmd_dir]; unsigned long cmd_data_len = data->data_len; @@ -147,17 +147,12 @@ int iser_start_rdma_unaligned_sg(struct iscsi_iser_cmd_task *iser_ctask, iser_ctask->data_copy[cmd_dir].copy_buf = mem; - dma_device = iser_ctask->iser_conn->ib_conn->device->ib_device->dma_device; - - if (cmd_dir == ISER_DIR_OUT) - dma_nents = dma_map_sg(dma_device, - &iser_ctask->data_copy[cmd_dir].sg_single, - 1, DMA_TO_DEVICE); - else - dma_nents = dma_map_sg(dma_device, - &iser_ctask->data_copy[cmd_dir].sg_single, - 1, DMA_FROM_DEVICE); - + dev = iser_ctask->iser_conn->ib_conn->device->ib_device; + dma_nents = ib_dma_map_sg(dev, + &iser_ctask->data_copy[cmd_dir].sg_single, + 1, + (cmd_dir == ISER_DIR_OUT) ? + DMA_TO_DEVICE : DMA_FROM_DEVICE); BUG_ON(dma_nents == 0); iser_ctask->data_copy[cmd_dir].dma_nents = dma_nents; @@ -170,19 +165,16 @@ int iser_start_rdma_unaligned_sg(struct iscsi_iser_cmd_task *iser_ctask, void iser_finalize_rdma_unaligned_sg(struct iscsi_iser_cmd_task *iser_ctask, enum iser_data_dir cmd_dir) { - struct device *dma_device; + struct ib_device *dev; struct iser_data_buf *mem_copy; unsigned long cmd_data_len; - dma_device = iser_ctask->iser_conn->ib_conn->device->ib_device->dma_device; - mem_copy = &iser_ctask->data_copy[cmd_dir]; + dev = iser_ctask->iser_conn->ib_conn->device->ib_device; + mem_copy = &iser_ctask->data_copy[cmd_dir]; - if (cmd_dir == ISER_DIR_OUT) - dma_unmap_sg(dma_device, &mem_copy->sg_single, 1, - DMA_TO_DEVICE); - else - dma_unmap_sg(dma_device, &mem_copy->sg_single, 1, - DMA_FROM_DEVICE); + ib_dma_unmap_sg(dev, &mem_copy->sg_single, 1, + (cmd_dir == ISER_DIR_OUT) ? + DMA_TO_DEVICE : DMA_FROM_DEVICE); if (cmd_dir == ISER_DIR_IN) { char *mem; @@ -231,11 +223,12 @@ void iser_finalize_rdma_unaligned_sg(struct iscsi_iser_cmd_task *iser_ctask, * consecutive elements. Also, it handles one entry SG. */ static int iser_sg_to_page_vec(struct iser_data_buf *data, - struct iser_page_vec *page_vec) + struct iser_page_vec *page_vec, + struct ib_device *ibdev) { struct scatterlist *sg = (struct scatterlist *)data->buf; - dma_addr_t first_addr, last_addr, page; - int start_aligned, end_aligned; + u64 first_addr, last_addr, page; + int end_aligned; unsigned int cur_page = 0; unsigned long total_sz = 0; int i; @@ -244,19 +237,21 @@ static int iser_sg_to_page_vec(struct iser_data_buf *data, page_vec->offset = (u64) sg[0].offset & ~MASK_4K; for (i = 0; i < data->dma_nents; i++) { - total_sz += sg_dma_len(&sg[i]); + unsigned int dma_len = ib_sg_dma_len(ibdev, &sg[i]); + + total_sz += dma_len; - first_addr = sg_dma_address(&sg[i]); - last_addr = first_addr + sg_dma_len(&sg[i]); + first_addr = ib_sg_dma_address(ibdev, &sg[i]); + last_addr = first_addr + dma_len; - start_aligned = !(first_addr & ~MASK_4K); end_aligned = !(last_addr & ~MASK_4K); /* continue to collect page fragments till aligned or SG ends */ while (!end_aligned && (i + 1 < data->dma_nents)) { i++; - total_sz += sg_dma_len(&sg[i]); - last_addr = sg_dma_address(&sg[i]) + sg_dma_len(&sg[i]); + dma_len = ib_sg_dma_len(ibdev, &sg[i]); + total_sz += dma_len; + last_addr = ib_sg_dma_address(ibdev, &sg[i]) + dma_len; end_aligned = !(last_addr & ~MASK_4K); } @@ -288,10 +283,11 @@ static int iser_sg_to_page_vec(struct iser_data_buf *data, * the number of entries which are aligned correctly. Supports the case where * consecutive SG elements are actually fragments of the same physcial page. */ -static unsigned int iser_data_buf_aligned_len(struct iser_data_buf *data) +static unsigned int iser_data_buf_aligned_len(struct iser_data_buf *data, + struct ib_device *ibdev) { struct scatterlist *sg; - dma_addr_t end_addr, next_addr; + u64 end_addr, next_addr; int i, cnt; unsigned int ret_len = 0; @@ -303,12 +299,12 @@ static unsigned int iser_data_buf_aligned_len(struct iser_data_buf *data) (unsigned long)page_to_phys(sg[i].page), (unsigned long)sg[i].offset, (unsigned long)sg[i].length); */ - end_addr = sg_dma_address(&sg[i]) + - sg_dma_len(&sg[i]); + end_addr = ib_sg_dma_address(ibdev, &sg[i]) + + ib_sg_dma_len(ibdev, &sg[i]); /* iser_dbg("Checking sg iobuf end address " "0x%08lX\n", end_addr); */ if (i + 1 < data->dma_nents) { - next_addr = sg_dma_address(&sg[i+1]); + next_addr = ib_sg_dma_address(ibdev, &sg[i+1]); /* are i, i+1 fragments of the same page? */ if (end_addr == next_addr) continue; @@ -325,7 +321,8 @@ static unsigned int iser_data_buf_aligned_len(struct iser_data_buf *data) return ret_len; } -static void iser_data_buf_dump(struct iser_data_buf *data) +static void iser_data_buf_dump(struct iser_data_buf *data, + struct ib_device *ibdev) { struct scatterlist *sg = (struct scatterlist *)data->buf; int i; @@ -333,9 +330,9 @@ static void iser_data_buf_dump(struct iser_data_buf *data) for (i = 0; i < data->dma_nents; i++) iser_err("sg[%d] dma_addr:0x%lX page:0x%p " "off:0x%x sz:0x%x dma_len:0x%x\n", - i, (unsigned long)sg_dma_address(&sg[i]), + i, (unsigned long)ib_sg_dma_address(ibdev, &sg[i]), sg[i].page, sg[i].offset, - sg[i].length,sg_dma_len(&sg[i])); + sg[i].length, ib_sg_dma_len(ibdev, &sg[i])); } static void iser_dump_page_vec(struct iser_page_vec *page_vec) @@ -349,7 +346,8 @@ static void iser_dump_page_vec(struct iser_page_vec *page_vec) } static void iser_page_vec_build(struct iser_data_buf *data, - struct iser_page_vec *page_vec) + struct iser_page_vec *page_vec, + struct ib_device *ibdev) { int page_vec_len = 0; @@ -357,14 +355,14 @@ static void iser_page_vec_build(struct iser_data_buf *data, page_vec->offset = 0; iser_dbg("Translating sg sz: %d\n", data->dma_nents); - page_vec_len = iser_sg_to_page_vec(data,page_vec); + page_vec_len = iser_sg_to_page_vec(data, page_vec, ibdev); iser_dbg("sg len %d page_vec_len %d\n", data->dma_nents,page_vec_len); page_vec->length = page_vec_len; if (page_vec_len * SIZE_4K < page_vec->data_size) { iser_err("page_vec too short to hold this SG\n"); - iser_data_buf_dump(data); + iser_data_buf_dump(data, ibdev); iser_dump_page_vec(page_vec); BUG(); } @@ -375,13 +373,12 @@ int iser_dma_map_task_data(struct iscsi_iser_cmd_task *iser_ctask, enum iser_data_dir iser_dir, enum dma_data_direction dma_dir) { - struct device *dma_device; + struct ib_device *dev; iser_ctask->dir[iser_dir] = 1; - dma_device = - iser_ctask->iser_conn->ib_conn->device->ib_device->dma_device; + dev = iser_ctask->iser_conn->ib_conn->device->ib_device; - data->dma_nents = dma_map_sg(dma_device, data->buf, data->size, dma_dir); + data->dma_nents = ib_dma_map_sg(dev, data->buf, data->size, dma_dir); if (data->dma_nents == 0) { iser_err("dma_map_sg failed!!!\n"); return -EINVAL; @@ -391,20 +388,19 @@ int iser_dma_map_task_data(struct iscsi_iser_cmd_task *iser_ctask, void iser_dma_unmap_task_data(struct iscsi_iser_cmd_task *iser_ctask) { - struct device *dma_device; + struct ib_device *dev; struct iser_data_buf *data; - dma_device = - iser_ctask->iser_conn->ib_conn->device->ib_device->dma_device; + dev = iser_ctask->iser_conn->ib_conn->device->ib_device; if (iser_ctask->dir[ISER_DIR_IN]) { data = &iser_ctask->data[ISER_DIR_IN]; - dma_unmap_sg(dma_device, data->buf, data->size, DMA_FROM_DEVICE); + ib_dma_unmap_sg(dev, data->buf, data->size, DMA_FROM_DEVICE); } if (iser_ctask->dir[ISER_DIR_OUT]) { data = &iser_ctask->data[ISER_DIR_OUT]; - dma_unmap_sg(dma_device, data->buf, data->size, DMA_TO_DEVICE); + ib_dma_unmap_sg(dev, data->buf, data->size, DMA_TO_DEVICE); } } @@ -419,6 +415,7 @@ int iser_reg_rdma_mem(struct iscsi_iser_cmd_task *iser_ctask, { struct iser_conn *ib_conn = iser_ctask->iser_conn->ib_conn; struct iser_device *device = ib_conn->device; + struct ib_device *ibdev = device->ib_device; struct iser_data_buf *mem = &iser_ctask->data[cmd_dir]; struct iser_regd_buf *regd_buf; int aligned_len; @@ -428,11 +425,11 @@ int iser_reg_rdma_mem(struct iscsi_iser_cmd_task *iser_ctask, regd_buf = &iser_ctask->rdma_regd[cmd_dir]; - aligned_len = iser_data_buf_aligned_len(mem); + aligned_len = iser_data_buf_aligned_len(mem, ibdev); if (aligned_len != mem->dma_nents) { iser_err("rdma alignment violation %d/%d aligned\n", aligned_len, mem->size); - iser_data_buf_dump(mem); + iser_data_buf_dump(mem, ibdev); /* unmap the command data before accessing it */ iser_dma_unmap_task_data(iser_ctask); @@ -450,8 +447,8 @@ int iser_reg_rdma_mem(struct iscsi_iser_cmd_task *iser_ctask, regd_buf->reg.lkey = device->mr->lkey; regd_buf->reg.rkey = device->mr->rkey; - regd_buf->reg.len = sg_dma_len(&sg[0]); - regd_buf->reg.va = sg_dma_address(&sg[0]); + regd_buf->reg.len = ib_sg_dma_len(ibdev, &sg[0]); + regd_buf->reg.va = ib_sg_dma_address(ibdev, &sg[0]); regd_buf->reg.is_fmr = 0; iser_dbg("PHYSICAL Mem.register: lkey: 0x%08X rkey: 0x%08X " @@ -461,10 +458,10 @@ int iser_reg_rdma_mem(struct iscsi_iser_cmd_task *iser_ctask, (unsigned long)regd_buf->reg.va, (unsigned long)regd_buf->reg.len); } else { /* use FMR for multiple dma entries */ - iser_page_vec_build(mem, ib_conn->page_vec); + iser_page_vec_build(mem, ib_conn->page_vec, ibdev); err = iser_reg_page_vec(ib_conn, ib_conn->page_vec, ®d_buf->reg); if (err) { - iser_data_buf_dump(mem); + iser_data_buf_dump(mem, ibdev); iser_err("mem->dma_nents = %d (dlength = 0x%x)\n", mem->dma_nents, ntoh24(iser_ctask->desc.iscsi_header.dlength)); iser_err("page_vec: data_size = 0x%x, length = %d, offset = 0x%x\n", diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index a6289595557..e9b6a6f07dd 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -122,9 +122,8 @@ static struct srp_iu *srp_alloc_iu(struct srp_host *host, size_t size, if (!iu->buf) goto out_free_iu; - iu->dma = dma_map_single(host->dev->dev->dma_device, - iu->buf, size, direction); - if (dma_mapping_error(iu->dma)) + iu->dma = ib_dma_map_single(host->dev->dev, iu->buf, size, direction); + if (ib_dma_mapping_error(host->dev->dev, iu->dma)) goto out_free_buf; iu->size = size; @@ -145,8 +144,7 @@ static void srp_free_iu(struct srp_host *host, struct srp_iu *iu) if (!iu) return; - dma_unmap_single(host->dev->dev->dma_device, - iu->dma, iu->size, iu->direction); + ib_dma_unmap_single(host->dev->dev, iu->dma, iu->size, iu->direction); kfree(iu->buf); kfree(iu); } @@ -482,8 +480,8 @@ static void srp_unmap_data(struct scsi_cmnd *scmnd, scat = &req->fake_sg; } - dma_unmap_sg(target->srp_host->dev->dev->dma_device, scat, nents, - scmnd->sc_data_direction); + ib_dma_unmap_sg(target->srp_host->dev->dev, scat, nents, + scmnd->sc_data_direction); } static void srp_remove_req(struct srp_target_port *target, struct srp_request *req) @@ -595,23 +593,26 @@ static int srp_map_fmr(struct srp_target_port *target, struct scatterlist *scat, int i, j; int ret; struct srp_device *dev = target->srp_host->dev; + struct ib_device *ibdev = dev->dev; if (!dev->fmr_pool) return -ENODEV; - if ((sg_dma_address(&scat[0]) & ~dev->fmr_page_mask) && + if ((ib_sg_dma_address(ibdev, &scat[0]) & ~dev->fmr_page_mask) && mellanox_workarounds && !memcmp(&target->ioc_guid, mellanox_oui, 3)) return -EINVAL; len = page_cnt = 0; for (i = 0; i < sg_cnt; ++i) { - if (sg_dma_address(&scat[i]) & ~dev->fmr_page_mask) { + unsigned int dma_len = ib_sg_dma_len(ibdev, &scat[i]); + + if (ib_sg_dma_address(ibdev, &scat[i]) & ~dev->fmr_page_mask) { if (i > 0) return -EINVAL; else ++page_cnt; } - if ((sg_dma_address(&scat[i]) + sg_dma_len(&scat[i])) & + if ((ib_sg_dma_address(ibdev, &scat[i]) + dma_len) & ~dev->fmr_page_mask) { if (i < sg_cnt - 1) return -EINVAL; @@ -619,7 +620,7 @@ static int srp_map_fmr(struct srp_target_port *target, struct scatterlist *scat, ++page_cnt; } - len += sg_dma_len(&scat[i]); + len += dma_len; } page_cnt += len >> dev->fmr_page_shift; @@ -631,10 +632,14 @@ static int srp_map_fmr(struct srp_target_port *target, struct scatterlist *scat, return -ENOMEM; page_cnt = 0; - for (i = 0; i < sg_cnt; ++i) - for (j = 0; j < sg_dma_len(&scat[i]); j += dev->fmr_page_size) + for (i = 0; i < sg_cnt; ++i) { + unsigned int dma_len = ib_sg_dma_len(ibdev, &scat[i]); + + for (j = 0; j < dma_len; j += dev->fmr_page_size) dma_pages[page_cnt++] = - (sg_dma_address(&scat[i]) & dev->fmr_page_mask) + j; + (ib_sg_dma_address(ibdev, &scat[i]) & + dev->fmr_page_mask) + j; + } req->fmr = ib_fmr_pool_map_phys(dev->fmr_pool, dma_pages, page_cnt, io_addr); @@ -644,7 +649,8 @@ static int srp_map_fmr(struct srp_target_port *target, struct scatterlist *scat, goto out; } - buf->va = cpu_to_be64(sg_dma_address(&scat[0]) & ~dev->fmr_page_mask); + buf->va = cpu_to_be64(ib_sg_dma_address(ibdev, &scat[0]) & + ~dev->fmr_page_mask); buf->key = cpu_to_be32(req->fmr->fmr->rkey); buf->len = cpu_to_be32(len); @@ -663,6 +669,8 @@ static int srp_map_data(struct scsi_cmnd *scmnd, struct srp_target_port *target, struct srp_cmd *cmd = req->cmd->buf; int len, nents, count; u8 fmt = SRP_DATA_DESC_DIRECT; + struct srp_device *dev; + struct ib_device *ibdev; if (!scmnd->request_buffer || scmnd->sc_data_direction == DMA_NONE) return sizeof (struct srp_cmd); @@ -687,8 +695,10 @@ static int srp_map_data(struct scsi_cmnd *scmnd, struct srp_target_port *target, sg_init_one(scat, scmnd->request_buffer, scmnd->request_bufflen); } - count = dma_map_sg(target->srp_host->dev->dev->dma_device, - scat, nents, scmnd->sc_data_direction); + dev = target->srp_host->dev; + ibdev = dev->dev; + + count = ib_dma_map_sg(ibdev, scat, nents, scmnd->sc_data_direction); fmt = SRP_DATA_DESC_DIRECT; len = sizeof (struct srp_cmd) + sizeof (struct srp_direct_buf); @@ -702,9 +712,9 @@ static int srp_map_data(struct scsi_cmnd *scmnd, struct srp_target_port *target, */ struct srp_direct_buf *buf = (void *) cmd->add_data; - buf->va = cpu_to_be64(sg_dma_address(scat)); - buf->key = cpu_to_be32(target->srp_host->dev->mr->rkey); - buf->len = cpu_to_be32(sg_dma_len(scat)); + buf->va = cpu_to_be64(ib_sg_dma_address(ibdev, scat)); + buf->key = cpu_to_be32(dev->mr->rkey); + buf->len = cpu_to_be32(ib_sg_dma_len(ibdev, scat)); } else if (srp_map_fmr(target, scat, count, req, (void *) cmd->add_data)) { /* @@ -722,13 +732,14 @@ static int srp_map_data(struct scsi_cmnd *scmnd, struct srp_target_port *target, count * sizeof (struct srp_direct_buf); for (i = 0; i < count; ++i) { + unsigned int dma_len = ib_sg_dma_len(ibdev, &scat[i]); + buf->desc_list[i].va = - cpu_to_be64(sg_dma_address(&scat[i])); + cpu_to_be64(ib_sg_dma_address(ibdev, &scat[i])); buf->desc_list[i].key = - cpu_to_be32(target->srp_host->dev->mr->rkey); - buf->desc_list[i].len = - cpu_to_be32(sg_dma_len(&scat[i])); - datalen += sg_dma_len(&scat[i]); + cpu_to_be32(dev->mr->rkey); + buf->desc_list[i].len = cpu_to_be32(dma_len); + datalen += dma_len; } if (scmnd->sc_data_direction == DMA_TO_DEVICE) @@ -808,13 +819,15 @@ static void srp_process_rsp(struct srp_target_port *target, struct srp_rsp *rsp) static void srp_handle_recv(struct srp_target_port *target, struct ib_wc *wc) { + struct ib_device *dev; struct srp_iu *iu; u8 opcode; iu = target->rx_ring[wc->wr_id & ~SRP_OP_RECV]; - dma_sync_single_for_cpu(target->srp_host->dev->dev->dma_device, iu->dma, - target->max_ti_iu_len, DMA_FROM_DEVICE); + dev = target->srp_host->dev->dev; + ib_dma_sync_single_for_cpu(dev, iu->dma, target->max_ti_iu_len, + DMA_FROM_DEVICE); opcode = *(u8 *) iu->buf; @@ -850,8 +863,8 @@ static void srp_handle_recv(struct srp_target_port *target, struct ib_wc *wc) break; } - dma_sync_single_for_device(target->srp_host->dev->dev->dma_device, iu->dma, - target->max_ti_iu_len, DMA_FROM_DEVICE); + ib_dma_sync_single_for_device(dev, iu->dma, target->max_ti_iu_len, + DMA_FROM_DEVICE); } static void srp_completion(struct ib_cq *cq, void *target_ptr) @@ -969,6 +982,7 @@ static int srp_queuecommand(struct scsi_cmnd *scmnd, struct srp_request *req; struct srp_iu *iu; struct srp_cmd *cmd; + struct ib_device *dev; int len; if (target->state == SRP_TARGET_CONNECTING) @@ -985,8 +999,9 @@ static int srp_queuecommand(struct scsi_cmnd *scmnd, if (!iu) goto err; - dma_sync_single_for_cpu(target->srp_host->dev->dev->dma_device, iu->dma, - srp_max_iu_len, DMA_TO_DEVICE); + dev = target->srp_host->dev->dev; + ib_dma_sync_single_for_cpu(dev, iu->dma, srp_max_iu_len, + DMA_TO_DEVICE); req = list_entry(target->free_reqs.next, struct srp_request, list); @@ -1018,8 +1033,8 @@ static int srp_queuecommand(struct scsi_cmnd *scmnd, goto err_unmap; } - dma_sync_single_for_device(target->srp_host->dev->dev->dma_device, iu->dma, - srp_max_iu_len, DMA_TO_DEVICE); + ib_dma_sync_single_for_device(dev, iu->dma, srp_max_iu_len, + DMA_TO_DEVICE); if (__srp_post_send(target, iu, len)) { printk(KERN_ERR PFX "Send failed\n"); diff --git a/drivers/infiniband/ulp/srp/ib_srp.h b/drivers/infiniband/ulp/srp/ib_srp.h index d4e35ef5137..868a540ef7c 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.h +++ b/drivers/infiniband/ulp/srp/ib_srp.h @@ -161,7 +161,7 @@ struct srp_target_port { }; struct srp_iu { - dma_addr_t dma; + u64 dma; void *buf; size_t size; enum dma_data_direction direction; diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig index 176142c6149..7399ba79111 100644 --- a/drivers/leds/Kconfig +++ b/drivers/leds/Kconfig @@ -12,7 +12,7 @@ config NEW_LEDS config LEDS_CLASS tristate "LED Class Support" - depends NEW_LEDS + depends on NEW_LEDS help This option enables the led sysfs class in /sys/class/leds. You'll need this to do anything useful with LEDs. If unsure, say N. @@ -21,28 +21,28 @@ comment "LED drivers" config LEDS_CORGI tristate "LED Support for the Sharp SL-C7x0 series" - depends LEDS_CLASS && PXA_SHARP_C7xx + depends on LEDS_CLASS && PXA_SHARP_C7xx help This option enables support for the LEDs on Sharp Zaurus SL-C7x0 series (C700, C750, C760, C860). config LEDS_LOCOMO tristate "LED Support for Locomo device" - depends LEDS_CLASS && SHARP_LOCOMO + depends on LEDS_CLASS && SHARP_LOCOMO help This option enables support for the LEDs on Sharp Locomo. Zaurus models SL-5500 and SL-5600. config LEDS_SPITZ tristate "LED Support for the Sharp SL-Cxx00 series" - depends LEDS_CLASS && PXA_SHARP_Cxx00 + depends on LEDS_CLASS && PXA_SHARP_Cxx00 help This option enables support for the LEDs on Sharp Zaurus SL-Cxx00 series (C1000, C3000, C3100). config LEDS_IXP4XX tristate "LED Support for GPIO connected LEDs on IXP4XX processors" - depends LEDS_CLASS && ARCH_IXP4XX + depends on LEDS_CLASS && ARCH_IXP4XX help This option enables support for the LEDs connected to GPIO outputs of the Intel IXP4XX processors. To be useful the @@ -51,7 +51,7 @@ config LEDS_IXP4XX config LEDS_TOSA tristate "LED Support for the Sharp SL-6000 series" - depends LEDS_CLASS && PXA_SHARPSL + depends on LEDS_CLASS && PXA_SHARPSL help This option enables support for the LEDs on Sharp Zaurus SL-6000 series. @@ -65,7 +65,7 @@ config LEDS_S3C24XX config LEDS_AMS_DELTA tristate "LED Support for the Amstrad Delta (E3)" - depends LEDS_CLASS && MACH_AMS_DELTA + depends on LEDS_CLASS && MACH_AMS_DELTA help This option enables support for the LEDs on Amstrad Delta (E3). @@ -86,7 +86,7 @@ comment "LED Triggers" config LEDS_TRIGGERS bool "LED Trigger support" - depends NEW_LEDS + depends on NEW_LEDS help This option enables trigger support for the leds class. These triggers allow kernel events to drive the LEDs and can @@ -94,21 +94,21 @@ config LEDS_TRIGGERS config LEDS_TRIGGER_TIMER tristate "LED Timer Trigger" - depends LEDS_TRIGGERS + depends on LEDS_TRIGGERS help This allows LEDs to be controlled by a programmable timer via sysfs. If unsure, say Y. config LEDS_TRIGGER_IDE_DISK bool "LED IDE Disk Trigger" - depends LEDS_TRIGGERS && BLK_DEV_IDEDISK + depends on LEDS_TRIGGERS && BLK_DEV_IDEDISK help This allows LEDs to be controlled by IDE disk activity. If unsure, say Y. config LEDS_TRIGGER_HEARTBEAT tristate "LED Heartbeat Trigger" - depends LEDS_TRIGGERS + depends on LEDS_TRIGGERS help This allows LEDs to be controlled by a CPU load average. The flash frequency is a hyperbolic function of the 1-minute diff --git a/drivers/media/video/ov7670.c b/drivers/media/video/ov7670.c index 89dd18c3c5c..5ed0adc4ca2 100644 --- a/drivers/media/video/ov7670.c +++ b/drivers/media/video/ov7670.c @@ -18,7 +18,7 @@ #include <linux/i2c.h> -MODULE_AUTHOR("Jonathan Corbet <corbet@lwn.net."); +MODULE_AUTHOR("Jonathan Corbet <corbet@lwn.net>"); MODULE_DESCRIPTION("A low-level driver for OmniVision ov7670 sensors"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/e100.c b/drivers/net/e100.c index 03bf164f9e8..c2ae2a24629 100644 --- a/drivers/net/e100.c +++ b/drivers/net/e100.c @@ -1930,9 +1930,8 @@ static int e100_rx_alloc_list(struct nic *nic) nic->rx_to_use = nic->rx_to_clean = NULL; nic->ru_running = RU_UNINITIALIZED; - if(!(nic->rxs = kmalloc(sizeof(struct rx) * count, GFP_ATOMIC))) + if(!(nic->rxs = kcalloc(count, sizeof(struct rx), GFP_ATOMIC))) return -ENOMEM; - memset(nic->rxs, 0, sizeof(struct rx) * count); for(rx = nic->rxs, i = 0; i < count; rx++, i++) { rx->next = (i + 1 < count) ? rx + 1 : nic->rxs; diff --git a/drivers/serial/Kconfig b/drivers/serial/Kconfig index 0b36dd5cdac..2978c09860e 100644 --- a/drivers/serial/Kconfig +++ b/drivers/serial/Kconfig @@ -663,7 +663,7 @@ config V850E_UART config V850E_UARTB bool - depends V850E_UART && V850E_ME2 + depends on V850E_UART && V850E_ME2 default y config V850E_UART_CONSOLE @@ -909,7 +909,7 @@ config SERIAL_M32R_PLDSIO config SERIAL_TXX9 bool "TMPTX39XX/49XX SIO support" - depends HAS_TXX9_SERIAL + depends on HAS_TXX9_SERIAL select SERIAL_CORE default y diff --git a/drivers/serial/icom.c b/drivers/serial/icom.c index 7d623003e65..71e6a24d8c2 100644 --- a/drivers/serial/icom.c +++ b/drivers/serial/icom.c @@ -1510,7 +1510,7 @@ static int __devinit icom_probe(struct pci_dev *dev, } if ( (retval = pci_request_regions(dev, "icom"))) { - dev_err(&dev->dev, "pci_request_region FAILED\n"); + dev_err(&dev->dev, "pci_request_regions FAILED\n"); pci_disable_device(dev); return retval; } diff --git a/fs/Kconfig b/fs/Kconfig index b3b5aa0edff..276ff3baaaf 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -12,9 +12,7 @@ config EXT2_FS Ext2 is a standard Linux file system for hard disks. To compile this file system support as a module, choose M here: the - module will be called ext2. Be aware however that the file system - of your root partition (the one containing the directory /) cannot - be compiled as a module, and so this could be dangerous. + module will be called ext2. If unsure, say Y. @@ -98,9 +96,7 @@ config EXT3_FS (available at <http://sourceforge.net/projects/e2fsprogs/>). To compile this file system support as a module, choose M here: the - module will be called ext3. Be aware however that the file system - of your root partition (the one containing the directory /) cannot - be compiled as a module, and so this may be dangerous. + module will be called ext3. config EXT3_FS_XATTR bool "Ext3 extended attributes" @@ -163,9 +159,7 @@ config EXT4DEV_FS features will be added to ext4dev gradually. To compile this file system support as a module, choose M here. The - module will be called ext4dev. Be aware, however, that the filesystem - of your root partition (the one containing the directory /) cannot - be compiled as a module, and so this could be dangerous. + module will be called ext4dev. If unsure, say N. @@ -1008,7 +1002,7 @@ config TMPFS_POSIX_ACL config HUGETLBFS bool "HugeTLB file system support" - depends X86 || IA64 || PPC64 || SPARC64 || SUPERH || BROKEN + depends on X86 || IA64 || PPC64 || SPARC64 || SUPERH || BROKEN help hugetlbfs is a filesystem backing for HugeTLB pages, based on ramfs. For architectures that support it, say Y here and read diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index 76f06f6bc2f..6e6d4568d54 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -706,12 +706,11 @@ static int elf_fdpic_map_file(struct elf_fdpic_params *params, return -ELIBBAD; size = sizeof(*loadmap) + nloads * sizeof(*seg); - loadmap = kmalloc(size, GFP_KERNEL); + loadmap = kzalloc(size, GFP_KERNEL); if (!loadmap) return -ENOMEM; params->loadmap = loadmap; - memset(loadmap, 0, size); loadmap->version = ELF32_FDPIC_LOADMAP_VERSION; loadmap->nsegs = nloads; diff --git a/include/asm-i386/msr.h b/include/asm-i386/msr.h index 5679d499307..609a3899475 100644 --- a/include/asm-i386/msr.h +++ b/include/asm-i386/msr.h @@ -100,6 +100,8 @@ static inline void wrmsrl (unsigned long msr, unsigned long long val) #define MSR_P6_PERFCTR0 0xc1 #define MSR_P6_PERFCTR1 0xc2 +#define MSR_FSB_FREQ 0xcd + #define MSR_IA32_BBL_CR_CTL 0x119 @@ -130,6 +132,9 @@ static inline void wrmsrl (unsigned long msr, unsigned long long val) #define MSR_IA32_PERF_STATUS 0x198 #define MSR_IA32_PERF_CTL 0x199 +#define MSR_IA32_MPERF 0xE7 +#define MSR_IA32_APERF 0xE8 + #define MSR_IA32_THERM_CONTROL 0x19a #define MSR_IA32_THERM_INTERRUPT 0x19b #define MSR_IA32_THERM_STATUS 0x19c diff --git a/include/asm-x86_64/msr.h b/include/asm-x86_64/msr.h index 952783d35c7..3227bc93d69 100644 --- a/include/asm-x86_64/msr.h +++ b/include/asm-x86_64/msr.h @@ -189,6 +189,7 @@ static inline unsigned int cpuid_edx(unsigned int op) #define MSR_IA32_PERFCTR0 0xc1 #define MSR_IA32_PERFCTR1 0xc2 +#define MSR_FSB_FREQ 0xcd #define MSR_MTRRcap 0x0fe #define MSR_IA32_BBL_CR_CTL 0x119 @@ -311,6 +312,9 @@ static inline unsigned int cpuid_edx(unsigned int op) #define MSR_IA32_PERF_STATUS 0x198 #define MSR_IA32_PERF_CTL 0x199 +#define MSR_IA32_MPERF 0xE7 +#define MSR_IA32_APERF 0xE8 + #define MSR_IA32_THERM_CONTROL 0x19a #define MSR_IA32_THERM_INTERRUPT 0x19b #define MSR_IA32_THERM_STATUS 0x19c diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 538423d4a86..aca66984aaf 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -40,7 +40,7 @@ extern void __chk_io_ptr(void __iomem *); #error no compiler-gcc.h file for this gcc version #elif __GNUC__ == 4 # include <linux/compiler-gcc4.h> -#elif __GNUC__ == 3 +#elif __GNUC__ == 3 && __GNUC_MINOR__ >= 2 # include <linux/compiler-gcc3.h> #else # error Sorry, your compiler is too old/not recognized. diff --git a/include/linux/configfs.h b/include/linux/configfs.h index a7f01502753..fef6f3d0a4a 100644 --- a/include/linux/configfs.h +++ b/include/linux/configfs.h @@ -160,31 +160,6 @@ struct configfs_group_operations { void (*drop_item)(struct config_group *group, struct config_item *item); }; - - -/** - * Use these macros to make defining attributes easier. See include/linux/device.h - * for examples.. - */ - -#if 0 -#define __ATTR(_name,_mode,_show,_store) { \ - .attr = {.ca_name = __stringify(_name), .ca_mode = _mode, .ca_owner = THIS_MODULE }, \ - .show = _show, \ - .store = _store, \ -} - -#define __ATTR_RO(_name) { \ - .attr = { .ca_name = __stringify(_name), .ca_mode = 0444, .ca_owner = THIS_MODULE }, \ - .show = _name##_show, \ -} - -#define __ATTR_NULL { .attr = { .name = NULL } } - -#define attr_name(_attr) (_attr).attr.name -#endif - - struct configfs_subsystem { struct config_group su_group; struct semaphore su_sem; diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 4ea39fee99c..7f008f6bfdc 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -172,6 +172,8 @@ extern int __cpufreq_driver_target(struct cpufreq_policy *policy, unsigned int relation); +extern int cpufreq_driver_getavg(struct cpufreq_policy *policy); + int cpufreq_register_governor(struct cpufreq_governor *governor); void cpufreq_unregister_governor(struct cpufreq_governor *governor); @@ -204,6 +206,7 @@ struct cpufreq_driver { unsigned int (*get) (unsigned int cpu); /* optional */ + unsigned int (*getavg) (unsigned int cpu); int (*exit) (struct cpufreq_policy *policy); int (*suspend) (struct cpufreq_policy *policy, pm_message_t pmsg); int (*resume) (struct cpufreq_policy *policy); diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 6d8846e7be6..81480e61346 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -11,7 +11,7 @@ ** the sysctl() binary interface. Do *NOT* change the ** numbering of any existing values here, and do not change ** any numbers within any one set of values. If you have to - ** have to redefine an existing interface, use a new number for it. + ** redefine an existing interface, use a new number for it. ** The kernel will then return -ENOTDIR to any application using ** the old binary interface. ** diff --git a/include/rdma/ib_marshall.h b/include/rdma/ib_marshall.h index 66bf4d7d0df..db037205c9e 100644 --- a/include/rdma/ib_marshall.h +++ b/include/rdma/ib_marshall.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2005 Intel Corporation. All rights reserved. + * Copyright (c) 2005-2006 Intel Corporation. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU @@ -41,6 +41,9 @@ void ib_copy_qp_attr_to_user(struct ib_uverbs_qp_attr *dst, struct ib_qp_attr *src); +void ib_copy_ah_attr_to_user(struct ib_uverbs_ah_attr *dst, + struct ib_ah_attr *src); + void ib_copy_path_rec_to_user(struct ib_user_path_rec *dst, struct ib_sa_path_rec *src); diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 8eacc351099..fd2353fa7e1 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -43,6 +43,8 @@ #include <linux/types.h> #include <linux/device.h> +#include <linux/mm.h> +#include <linux/dma-mapping.h> #include <asm/atomic.h> #include <asm/scatterlist.h> @@ -848,6 +850,49 @@ struct ib_cache { u8 *lmc_cache; }; +struct ib_dma_mapping_ops { + int (*mapping_error)(struct ib_device *dev, + u64 dma_addr); + u64 (*map_single)(struct ib_device *dev, + void *ptr, size_t size, + enum dma_data_direction direction); + void (*unmap_single)(struct ib_device *dev, + u64 addr, size_t size, + enum dma_data_direction direction); + u64 (*map_page)(struct ib_device *dev, + struct page *page, unsigned long offset, + size_t size, + enum dma_data_direction direction); + void (*unmap_page)(struct ib_device *dev, + u64 addr, size_t size, + enum dma_data_direction direction); + int (*map_sg)(struct ib_device *dev, + struct scatterlist *sg, int nents, + enum dma_data_direction direction); + void (*unmap_sg)(struct ib_device *dev, + struct scatterlist *sg, int nents, + enum dma_data_direction direction); + u64 (*dma_address)(struct ib_device *dev, + struct scatterlist *sg); + unsigned int (*dma_len)(struct ib_device *dev, + struct scatterlist *sg); + void (*sync_single_for_cpu)(struct ib_device *dev, + u64 dma_handle, + size_t size, + enum dma_data_direction dir); + void (*sync_single_for_device)(struct ib_device *dev, + u64 dma_handle, + size_t size, + enum dma_data_direction dir); + void *(*alloc_coherent)(struct ib_device *dev, + size_t size, + u64 *dma_handle, + gfp_t flag); + void (*free_coherent)(struct ib_device *dev, + size_t size, void *cpu_addr, + u64 dma_handle); +}; + struct iw_cm_verbs; struct ib_device { @@ -992,6 +1037,8 @@ struct ib_device { struct ib_mad *in_mad, struct ib_mad *out_mad); + struct ib_dma_mapping_ops *dma_ops; + struct module *owner; struct class_device class_dev; struct kobject ports_parent; @@ -1395,10 +1442,216 @@ static inline int ib_req_ncomp_notif(struct ib_cq *cq, int wc_cnt) * usable for DMA. * @pd: The protection domain associated with the memory region. * @mr_access_flags: Specifies the memory access rights. + * + * Note that the ib_dma_*() functions defined below must be used + * to create/destroy addresses used with the Lkey or Rkey returned + * by ib_get_dma_mr(). */ struct ib_mr *ib_get_dma_mr(struct ib_pd *pd, int mr_access_flags); /** + * ib_dma_mapping_error - check a DMA addr for error + * @dev: The device for which the dma_addr was created + * @dma_addr: The DMA address to check + */ +static inline int ib_dma_mapping_error(struct ib_device *dev, u64 dma_addr) +{ + return dev->dma_ops ? + dev->dma_ops->mapping_error(dev, dma_addr) : + dma_mapping_error(dma_addr); +} + +/** + * ib_dma_map_single - Map a kernel virtual address to DMA address + * @dev: The device for which the dma_addr is to be created + * @cpu_addr: The kernel virtual address + * @size: The size of the region in bytes + * @direction: The direction of the DMA + */ +static inline u64 ib_dma_map_single(struct ib_device *dev, + void *cpu_addr, size_t size, + enum dma_data_direction direction) +{ + return dev->dma_ops ? + dev->dma_ops->map_single(dev, cpu_addr, size, direction) : + dma_map_single(dev->dma_device, cpu_addr, size, direction); +} + +/** + * ib_dma_unmap_single - Destroy a mapping created by ib_dma_map_single() + * @dev: The device for which the DMA address was created + * @addr: The DMA address + * @size: The size of the region in bytes + * @direction: The direction of the DMA + */ +static inline void ib_dma_unmap_single(struct ib_device *dev, + u64 addr, size_t size, + enum dma_data_direction direction) +{ + dev->dma_ops ? + dev->dma_ops->unmap_single(dev, addr, size, direction) : + dma_unmap_single(dev->dma_device, addr, size, direction); +} + +/** + * ib_dma_map_page - Map a physical page to DMA address + * @dev: The device for which the dma_addr is to be created + * @page: The page to be mapped + * @offset: The offset within the page + * @size: The size of the region in bytes + * @direction: The direction of the DMA + */ +static inline u64 ib_dma_map_page(struct ib_device *dev, + struct page *page, + unsigned long offset, + size_t size, + enum dma_data_direction direction) +{ + return dev->dma_ops ? + dev->dma_ops->map_page(dev, page, offset, size, direction) : + dma_map_page(dev->dma_device, page, offset, size, direction); +} + +/** + * ib_dma_unmap_page - Destroy a mapping created by ib_dma_map_page() + * @dev: The device for which the DMA address was created + * @addr: The DMA address + * @size: The size of the region in bytes + * @direction: The direction of the DMA + */ +static inline void ib_dma_unmap_page(struct ib_device *dev, + u64 addr, size_t size, + enum dma_data_direction direction) +{ + dev->dma_ops ? + dev->dma_ops->unmap_page(dev, addr, size, direction) : + dma_unmap_page(dev->dma_device, addr, size, direction); +} + +/** + * ib_dma_map_sg - Map a scatter/gather list to DMA addresses + * @dev: The device for which the DMA addresses are to be created + * @sg: The array of scatter/gather entries + * @nents: The number of scatter/gather entries + * @direction: The direction of the DMA + */ +static inline int ib_dma_map_sg(struct ib_device *dev, + struct scatterlist *sg, int nents, + enum dma_data_direction direction) +{ + return dev->dma_ops ? + dev->dma_ops->map_sg(dev, sg, nents, direction) : + dma_map_sg(dev->dma_device, sg, nents, direction); +} + +/** + * ib_dma_unmap_sg - Unmap a scatter/gather list of DMA addresses + * @dev: The device for which the DMA addresses were created + * @sg: The array of scatter/gather entries + * @nents: The number of scatter/gather entries + * @direction: The direction of the DMA + */ +static inline void ib_dma_unmap_sg(struct ib_device *dev, + struct scatterlist *sg, int nents, + enum dma_data_direction direction) +{ + dev->dma_ops ? + dev->dma_ops->unmap_sg(dev, sg, nents, direction) : + dma_unmap_sg(dev->dma_device, sg, nents, direction); +} + +/** + * ib_sg_dma_address - Return the DMA address from a scatter/gather entry + * @dev: The device for which the DMA addresses were created + * @sg: The scatter/gather entry + */ +static inline u64 ib_sg_dma_address(struct ib_device *dev, + struct scatterlist *sg) +{ + return dev->dma_ops ? + dev->dma_ops->dma_address(dev, sg) : sg_dma_address(sg); +} + +/** + * ib_sg_dma_len - Return the DMA length from a scatter/gather entry + * @dev: The device for which the DMA addresses were created + * @sg: The scatter/gather entry + */ +static inline unsigned int ib_sg_dma_len(struct ib_device *dev, + struct scatterlist *sg) +{ + return dev->dma_ops ? + dev->dma_ops->dma_len(dev, sg) : sg_dma_len(sg); +} + +/** + * ib_dma_sync_single_for_cpu - Prepare DMA region to be accessed by CPU + * @dev: The device for which the DMA address was created + * @addr: The DMA address + * @size: The size of the region in bytes + * @dir: The direction of the DMA + */ +static inline void ib_dma_sync_single_for_cpu(struct ib_device *dev, + u64 addr, + size_t size, + enum dma_data_direction dir) +{ + dev->dma_ops ? + dev->dma_ops->sync_single_for_cpu(dev, addr, size, dir) : + dma_sync_single_for_cpu(dev->dma_device, addr, size, dir); +} + +/** + * ib_dma_sync_single_for_device - Prepare DMA region to be accessed by device + * @dev: The device for which the DMA address was created + * @addr: The DMA address + * @size: The size of the region in bytes + * @dir: The direction of the DMA + */ +static inline void ib_dma_sync_single_for_device(struct ib_device *dev, + u64 addr, + size_t size, + enum dma_data_direction dir) +{ + dev->dma_ops ? + dev->dma_ops->sync_single_for_device(dev, addr, size, dir) : + dma_sync_single_for_device(dev->dma_device, addr, size, dir); +} + +/** + * ib_dma_alloc_coherent - Allocate memory and map it for DMA + * @dev: The device for which the DMA address is requested + * @size: The size of the region to allocate in bytes + * @dma_handle: A pointer for returning the DMA address of the region + * @flag: memory allocator flags + */ +static inline void *ib_dma_alloc_coherent(struct ib_device *dev, + size_t size, + u64 *dma_handle, + gfp_t flag) +{ + return dev->dma_ops ? + dev->dma_ops->alloc_coherent(dev, size, dma_handle, flag) : + dma_alloc_coherent(dev->dma_device, size, dma_handle, flag); +} + +/** + * ib_dma_free_coherent - Free memory allocated by ib_dma_alloc_coherent() + * @dev: The device for which the DMA addresses were allocated + * @size: The size of the region + * @cpu_addr: the address returned by ib_dma_alloc_coherent() + * @dma_handle: the DMA address returned by ib_dma_alloc_coherent() + */ +static inline void ib_dma_free_coherent(struct ib_device *dev, + size_t size, void *cpu_addr, + u64 dma_handle) +{ + dev->dma_ops ? + dev->dma_ops->free_coherent(dev, size, cpu_addr, dma_handle) : + dma_free_coherent(dev->dma_device, size, cpu_addr, dma_handle); +} + +/** * ib_reg_phys_mr - Prepares a virtually addressed memory region for use * by an HCA. * @pd: The protection domain associated assigned to the registered region. diff --git a/include/rdma/rdma_cm.h b/include/rdma/rdma_cm.h index deb5a0a4cee..36cd8a8526a 100644 --- a/include/rdma/rdma_cm.h +++ b/include/rdma/rdma_cm.h @@ -77,11 +77,34 @@ struct rdma_route { int num_paths; }; +struct rdma_conn_param { + const void *private_data; + u8 private_data_len; + u8 responder_resources; + u8 initiator_depth; + u8 flow_control; + u8 retry_count; /* ignored when accepting */ + u8 rnr_retry_count; + /* Fields below ignored if a QP is created on the rdma_cm_id. */ + u8 srq; + u32 qp_num; +}; + +struct rdma_ud_param { + const void *private_data; + u8 private_data_len; + struct ib_ah_attr ah_attr; + u32 qp_num; + u32 qkey; +}; + struct rdma_cm_event { enum rdma_cm_event_type event; int status; - void *private_data; - u8 private_data_len; + union { + struct rdma_conn_param conn; + struct rdma_ud_param ud; + } param; }; struct rdma_cm_id; @@ -204,25 +227,17 @@ void rdma_destroy_qp(struct rdma_cm_id *id); int rdma_init_qp_attr(struct rdma_cm_id *id, struct ib_qp_attr *qp_attr, int *qp_attr_mask); -struct rdma_conn_param { - const void *private_data; - u8 private_data_len; - u8 responder_resources; - u8 initiator_depth; - u8 flow_control; - u8 retry_count; /* ignored when accepting */ - u8 rnr_retry_count; - /* Fields below ignored if a QP is created on the rdma_cm_id. */ - u8 srq; - u32 qp_num; - enum ib_qp_type qp_type; -}; - /** * rdma_connect - Initiate an active connection request. + * @id: Connection identifier to connect. + * @conn_param: Connection information used for connected QPs. * * Users must have resolved a route for the rdma_cm_id to connect with * by having called rdma_resolve_route before calling this routine. + * + * This call will either connect to a remote QP or obtain remote QP + * information for unconnected rdma_cm_id's. The actual operation is + * based on the rdma_cm_id's port space. */ int rdma_connect(struct rdma_cm_id *id, struct rdma_conn_param *conn_param); @@ -253,6 +268,21 @@ int rdma_listen(struct rdma_cm_id *id, int backlog); int rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param); /** + * rdma_notify - Notifies the RDMA CM of an asynchronous event that has + * occurred on the connection. + * @id: Connection identifier to transition to established. + * @event: Asynchronous event. + * + * This routine should be invoked by users to notify the CM of relevant + * communication events. Events that should be reported to the CM and + * when to report them are: + * + * IB_EVENT_COMM_EST - Used when a message is received on a connected + * QP before an RTU has been received. + */ +int rdma_notify(struct rdma_cm_id *id, enum ib_event_type event); + +/** * rdma_reject - Called to reject a connection request or response. */ int rdma_reject(struct rdma_cm_id *id, const void *private_data, diff --git a/include/rdma/rdma_cm_ib.h b/include/rdma/rdma_cm_ib.h index e8c3af1804d..9b176df1d66 100644 --- a/include/rdma/rdma_cm_ib.h +++ b/include/rdma/rdma_cm_ib.h @@ -44,4 +44,7 @@ int rdma_set_ib_paths(struct rdma_cm_id *id, struct ib_sa_path_rec *path_rec, int num_paths); +/* Global qkey for UD QPs and multicast groups. */ +#define RDMA_UD_QKEY 0x01234567 + #endif /* RDMA_CM_IB_H */ diff --git a/include/rdma/rdma_user_cm.h b/include/rdma/rdma_user_cm.h new file mode 100644 index 00000000000..9572ab8eeac --- /dev/null +++ b/include/rdma/rdma_user_cm.h @@ -0,0 +1,206 @@ +/* + * Copyright (c) 2005-2006 Intel Corporation. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#ifndef RDMA_USER_CM_H +#define RDMA_USER_CM_H + +#include <linux/types.h> +#include <linux/in6.h> +#include <rdma/ib_user_verbs.h> +#include <rdma/ib_user_sa.h> + +#define RDMA_USER_CM_ABI_VERSION 3 + +#define RDMA_MAX_PRIVATE_DATA 256 + +enum { + RDMA_USER_CM_CMD_CREATE_ID, + RDMA_USER_CM_CMD_DESTROY_ID, + RDMA_USER_CM_CMD_BIND_ADDR, + RDMA_USER_CM_CMD_RESOLVE_ADDR, + RDMA_USER_CM_CMD_RESOLVE_ROUTE, + RDMA_USER_CM_CMD_QUERY_ROUTE, + RDMA_USER_CM_CMD_CONNECT, + RDMA_USER_CM_CMD_LISTEN, + RDMA_USER_CM_CMD_ACCEPT, + RDMA_USER_CM_CMD_REJECT, + RDMA_USER_CM_CMD_DISCONNECT, + RDMA_USER_CM_CMD_INIT_QP_ATTR, + RDMA_USER_CM_CMD_GET_EVENT, + RDMA_USER_CM_CMD_GET_OPTION, + RDMA_USER_CM_CMD_SET_OPTION, + RDMA_USER_CM_CMD_NOTIFY +}; + +/* + * command ABI structures. + */ +struct rdma_ucm_cmd_hdr { + __u32 cmd; + __u16 in; + __u16 out; +}; + +struct rdma_ucm_create_id { + __u64 uid; + __u64 response; + __u16 ps; + __u8 reserved[6]; +}; + +struct rdma_ucm_create_id_resp { + __u32 id; +}; + +struct rdma_ucm_destroy_id { + __u64 response; + __u32 id; + __u32 reserved; +}; + +struct rdma_ucm_destroy_id_resp { + __u32 events_reported; +}; + +struct rdma_ucm_bind_addr { + __u64 response; + struct sockaddr_in6 addr; + __u32 id; +}; + +struct rdma_ucm_resolve_addr { + struct sockaddr_in6 src_addr; + struct sockaddr_in6 dst_addr; + __u32 id; + __u32 timeout_ms; +}; + +struct rdma_ucm_resolve_route { + __u32 id; + __u32 timeout_ms; +}; + +struct rdma_ucm_query_route { + __u64 response; + __u32 id; + __u32 reserved; +}; + +struct rdma_ucm_query_route_resp { + __u64 node_guid; + struct ib_user_path_rec ib_route[2]; + struct sockaddr_in6 src_addr; + struct sockaddr_in6 dst_addr; + __u32 num_paths; + __u8 port_num; + __u8 reserved[3]; +}; + +struct rdma_ucm_conn_param { + __u32 qp_num; + __u32 reserved; + __u8 private_data[RDMA_MAX_PRIVATE_DATA]; + __u8 private_data_len; + __u8 srq; + __u8 responder_resources; + __u8 initiator_depth; + __u8 flow_control; + __u8 retry_count; + __u8 rnr_retry_count; + __u8 valid; +}; + +struct rdma_ucm_ud_param { + __u32 qp_num; + __u32 qkey; + struct ib_uverbs_ah_attr ah_attr; + __u8 private_data[RDMA_MAX_PRIVATE_DATA]; + __u8 private_data_len; + __u8 reserved[7]; +}; + +struct rdma_ucm_connect { + struct rdma_ucm_conn_param conn_param; + __u32 id; + __u32 reserved; +}; + +struct rdma_ucm_listen { + __u32 id; + __u32 backlog; +}; + +struct rdma_ucm_accept { + __u64 uid; + struct rdma_ucm_conn_param conn_param; + __u32 id; + __u32 reserved; +}; + +struct rdma_ucm_reject { + __u32 id; + __u8 private_data_len; + __u8 reserved[3]; + __u8 private_data[RDMA_MAX_PRIVATE_DATA]; +}; + +struct rdma_ucm_disconnect { + __u32 id; +}; + +struct rdma_ucm_init_qp_attr { + __u64 response; + __u32 id; + __u32 qp_state; +}; + +struct rdma_ucm_notify { + __u32 id; + __u32 event; +}; + +struct rdma_ucm_get_event { + __u64 response; +}; + +struct rdma_ucm_event_resp { + __u64 uid; + __u32 id; + __u32 event; + __u32 status; + union { + struct rdma_ucm_conn_param conn; + struct rdma_ucm_ud_param ud; + } param; +}; + +#endif /* RDMA_USER_CM_H */ diff --git a/init/Kconfig b/init/Kconfig index 9edf103b3ec..f000edb3bb7 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -348,7 +348,7 @@ config SYSCTL_SYSCALL If unsure say Y here. config KALLSYMS - bool "Load all symbols for debugging/kksymoops" if EMBEDDED + bool "Load all symbols for debugging/ksymoops" if EMBEDDED default y help Say Y here to let the kernel print out symbolic crash information and diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 0701ddda1df..818e4589f71 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -437,7 +437,7 @@ config FAIL_PAGE_ALLOC Provide fault-injection capability for alloc_pages(). config FAIL_MAKE_REQUEST - bool "Fault-injection capabilitiy for disk IO" + bool "Fault-injection capability for disk IO" depends on FAULT_INJECTION help Provide fault-injection capability for disk IO. diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 74046efdf87..8ce00d3703d 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -565,7 +565,7 @@ static void ip_frag_queue(struct ipq *qp, struct sk_buff *skb) } else { struct sk_buff *free_it = next; - /* Old fragmnet is completely overridden with + /* Old fragment is completely overridden with * new one drop it. */ next = next->next; diff --git a/sound/aoa/fabrics/Kconfig b/sound/aoa/fabrics/Kconfig index c3bc7705c86..50d7021ff67 100644 --- a/sound/aoa/fabrics/Kconfig +++ b/sound/aoa/fabrics/Kconfig @@ -1,6 +1,6 @@ config SND_AOA_FABRIC_LAYOUT tristate "layout-id fabric" - depends SND_AOA + depends on SND_AOA select SND_AOA_SOUNDBUS select SND_AOA_SOUNDBUS_I2S ---help--- |