From ea279fc5619e2541a0c28196b0fa06447d9ad026 Mon Sep 17 00:00:00 2001 From: Marc Reilly Date: Fri, 16 Mar 2012 12:11:42 +1100 Subject: regmap: Add support for device with 24 data bits. Add support for devices with 24 data bits. Signed-off-by: Marc Reilly Signed-off-by: Mark Brown --- drivers/base/regmap/regmap.c | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'drivers/base') diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 7a3f535e481c..8ffce9bdb481 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -126,6 +126,15 @@ static void regmap_format_16(void *buf, unsigned int val) b[0] = cpu_to_be16(val); } +static void regmap_format_24(void *buf, unsigned int val) +{ + u8 *b = buf; + + b[0] = val >> 16; + b[1] = val >> 8; + b[2] = val; +} + static void regmap_format_32(void *buf, unsigned int val) { __be32 *b = buf; @@ -149,6 +158,16 @@ static unsigned int regmap_parse_16(void *buf) return b[0]; } +static unsigned int regmap_parse_24(void *buf) +{ + u8 *b = buf; + unsigned int ret = b[2]; + ret |= ((unsigned int)b[1]) << 8; + ret |= ((unsigned int)b[0]) << 16; + + return ret; +} + static unsigned int regmap_parse_32(void *buf) { __be32 *b = buf; @@ -273,6 +292,10 @@ struct regmap *regmap_init(struct device *dev, map->format.format_val = regmap_format_16; map->format.parse_val = regmap_parse_16; break; + case 24: + map->format.format_val = regmap_format_24; + map->format.parse_val = regmap_parse_24; + break; case 32: map->format.format_val = regmap_format_32; map->format.parse_val = regmap_parse_32; -- cgit v1.2.3 From d939fb9a78b4743bc4bc3cc415894ed42050c5cc Mon Sep 17 00:00:00 2001 From: Marc Reilly Date: Fri, 16 Mar 2012 12:11:43 +1100 Subject: regmap: Use pad_bits and reg_bits when determining register format. This change combines any padding bits into the register address bits when determining register format handlers to use the next byte-divisible register size. A reg_shift member is introduced to the regmap struct to enable fixup of the reg format. Format handlers now take an extra parameter specifying the number of bits to shift the value by. Signed-off-by: Marc Reilly Signed-off-by: Mark Brown --- drivers/base/regmap/internal.h | 7 +++++-- drivers/base/regmap/regmap.c | 27 +++++++++++++++------------ 2 files changed, 20 insertions(+), 14 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h index fcafc5b2e651..606b83d75458 100644 --- a/drivers/base/regmap/internal.h +++ b/drivers/base/regmap/internal.h @@ -26,8 +26,8 @@ struct regmap_format { size_t val_bytes; void (*format_write)(struct regmap *map, unsigned int reg, unsigned int val); - void (*format_reg)(void *buf, unsigned int reg); - void (*format_val)(void *buf, unsigned int val); + void (*format_reg)(void *buf, unsigned int reg, unsigned int shift); + void (*format_val)(void *buf, unsigned int val, unsigned int shift); unsigned int (*parse_val)(void *buf); }; @@ -52,6 +52,9 @@ struct regmap { u8 read_flag_mask; u8 write_flag_mask; + /* number of bits to (left) shift the reg value when formatting*/ + int reg_shift; + /* regcache specific members */ const struct regcache_ops *cache_ops; enum regcache_type cache_type; diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 8ffce9bdb481..178989a8949e 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -112,34 +112,36 @@ static void regmap_format_10_14_write(struct regmap *map, out[0] = reg >> 2; } -static void regmap_format_8(void *buf, unsigned int val) +static void regmap_format_8(void *buf, unsigned int val, unsigned int shift) { u8 *b = buf; - b[0] = val; + b[0] = val << shift; } -static void regmap_format_16(void *buf, unsigned int val) +static void regmap_format_16(void *buf, unsigned int val, unsigned int shift) { __be16 *b = buf; - b[0] = cpu_to_be16(val); + b[0] = cpu_to_be16(val << shift); } -static void regmap_format_24(void *buf, unsigned int val) +static void regmap_format_24(void *buf, unsigned int val, unsigned int shift) { u8 *b = buf; + val <<= shift; + b[0] = val >> 16; b[1] = val >> 8; b[2] = val; } -static void regmap_format_32(void *buf, unsigned int val) +static void regmap_format_32(void *buf, unsigned int val, unsigned int shift) { __be32 *b = buf; - b[0] = cpu_to_be32(val); + b[0] = cpu_to_be32(val << shift); } static unsigned int regmap_parse_8(void *buf) @@ -210,6 +212,7 @@ struct regmap *regmap_init(struct device *dev, map->format.pad_bytes = config->pad_bits / 8; map->format.val_bytes = DIV_ROUND_UP(config->val_bits, 8); map->format.buf_size += map->format.pad_bytes; + map->reg_shift = config->pad_bits % 8; map->dev = dev; map->bus = bus; map->max_register = config->max_register; @@ -226,7 +229,7 @@ struct regmap *regmap_init(struct device *dev, map->read_flag_mask = bus->read_flag_mask; } - switch (config->reg_bits) { + switch (config->reg_bits + map->reg_shift) { case 2: switch (config->val_bits) { case 6: @@ -454,7 +457,7 @@ static int _regmap_raw_write(struct regmap *map, unsigned int reg, } } - map->format.format_reg(map->work_buf, reg); + map->format.format_reg(map->work_buf, reg, map->reg_shift); u8[0] |= map->write_flag_mask; @@ -529,7 +532,7 @@ int _regmap_write(struct regmap *map, unsigned int reg, return ret; } else { map->format.format_val(map->work_buf + map->format.reg_bytes - + map->format.pad_bytes, val); + + map->format.pad_bytes, val, 0); return _regmap_raw_write(map, reg, map->work_buf + map->format.reg_bytes + @@ -649,7 +652,7 @@ static int _regmap_raw_read(struct regmap *map, unsigned int reg, void *val, u8 *u8 = map->work_buf; int ret; - map->format.format_reg(map->work_buf, reg); + map->format.format_reg(map->work_buf, reg, map->reg_shift); /* * Some buses or devices flag reads by setting the high bits in the @@ -757,7 +760,7 @@ int regmap_raw_read(struct regmap *map, unsigned int reg, void *val, if (ret != 0) goto out; - map->format.format_val(val + (i * val_bytes), v); + map->format.format_val(val + (i * val_bytes), v, 0); } } -- cgit v1.2.3 From 0135bbcc7a0cc056f0203ff839466236b8e3dc19 Mon Sep 17 00:00:00 2001 From: Stephen Warren Date: Wed, 4 Apr 2012 15:48:30 -0600 Subject: regmap: introduce explicit bus_context for bus callbacks The only context needed by I2C and SPI bus definitions is the device itself; this can be converted to an i2c_client or spi_device in order to perform IO on the device. However, other bus types may need more context in order to perform IO. Enable this by having regmap_init accept a bus_context parameter, and pass this to all bus callbacks. The existing callbacks simply pass the struct device here. Future bus types may pass something else. Signed-off-by: Stephen Warren Signed-off-by: Mark Brown --- drivers/base/regmap/internal.h | 1 + drivers/base/regmap/regmap-i2c.c | 13 ++++++++----- drivers/base/regmap/regmap-spi.c | 13 ++++++++----- drivers/base/regmap/regmap.c | 19 +++++++++++++------ include/linux/regmap.h | 10 +++++++--- 5 files changed, 37 insertions(+), 19 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h index fcafc5b2e651..b95fd1f25295 100644 --- a/drivers/base/regmap/internal.h +++ b/drivers/base/regmap/internal.h @@ -38,6 +38,7 @@ struct regmap { void *work_buf; /* Scratch buffer used to format I/O */ struct regmap_format format; /* Buffer format */ const struct regmap_bus *bus; + void *bus_context; #ifdef CONFIG_DEBUG_FS struct dentry *debugfs; diff --git a/drivers/base/regmap/regmap-i2c.c b/drivers/base/regmap/regmap-i2c.c index 9a3a8c564389..5f6b2478bf17 100644 --- a/drivers/base/regmap/regmap-i2c.c +++ b/drivers/base/regmap/regmap-i2c.c @@ -15,8 +15,9 @@ #include #include -static int regmap_i2c_write(struct device *dev, const void *data, size_t count) +static int regmap_i2c_write(void *context, const void *data, size_t count) { + struct device *dev = context; struct i2c_client *i2c = to_i2c_client(dev); int ret; @@ -29,10 +30,11 @@ static int regmap_i2c_write(struct device *dev, const void *data, size_t count) return -EIO; } -static int regmap_i2c_gather_write(struct device *dev, +static int regmap_i2c_gather_write(void *context, const void *reg, size_t reg_size, const void *val, size_t val_size) { + struct device *dev = context; struct i2c_client *i2c = to_i2c_client(dev); struct i2c_msg xfer[2]; int ret; @@ -62,10 +64,11 @@ static int regmap_i2c_gather_write(struct device *dev, return -EIO; } -static int regmap_i2c_read(struct device *dev, +static int regmap_i2c_read(void *context, const void *reg, size_t reg_size, void *val, size_t val_size) { + struct device *dev = context; struct i2c_client *i2c = to_i2c_client(dev); struct i2c_msg xfer[2]; int ret; @@ -107,7 +110,7 @@ static struct regmap_bus regmap_i2c = { struct regmap *regmap_init_i2c(struct i2c_client *i2c, const struct regmap_config *config) { - return regmap_init(&i2c->dev, ®map_i2c, config); + return regmap_init(&i2c->dev, ®map_i2c, &i2c->dev, config); } EXPORT_SYMBOL_GPL(regmap_init_i2c); @@ -124,7 +127,7 @@ EXPORT_SYMBOL_GPL(regmap_init_i2c); struct regmap *devm_regmap_init_i2c(struct i2c_client *i2c, const struct regmap_config *config) { - return devm_regmap_init(&i2c->dev, ®map_i2c, config); + return devm_regmap_init(&i2c->dev, ®map_i2c, &i2c->dev, config); } EXPORT_SYMBOL_GPL(devm_regmap_init_i2c); diff --git a/drivers/base/regmap/regmap-spi.c b/drivers/base/regmap/regmap-spi.c index 7c0c35a39c33..ffa46a92ad33 100644 --- a/drivers/base/regmap/regmap-spi.c +++ b/drivers/base/regmap/regmap-spi.c @@ -15,17 +15,19 @@ #include #include -static int regmap_spi_write(struct device *dev, const void *data, size_t count) +static int regmap_spi_write(void *context, const void *data, size_t count) { + struct device *dev = context; struct spi_device *spi = to_spi_device(dev); return spi_write(spi, data, count); } -static int regmap_spi_gather_write(struct device *dev, +static int regmap_spi_gather_write(void *context, const void *reg, size_t reg_len, const void *val, size_t val_len) { + struct device *dev = context; struct spi_device *spi = to_spi_device(dev); struct spi_message m; struct spi_transfer t[2] = { { .tx_buf = reg, .len = reg_len, }, @@ -38,10 +40,11 @@ static int regmap_spi_gather_write(struct device *dev, return spi_sync(spi, &m); } -static int regmap_spi_read(struct device *dev, +static int regmap_spi_read(void *context, const void *reg, size_t reg_size, void *val, size_t val_size) { + struct device *dev = context; struct spi_device *spi = to_spi_device(dev); return spi_write_then_read(spi, reg, reg_size, val, val_size); @@ -66,7 +69,7 @@ static struct regmap_bus regmap_spi = { struct regmap *regmap_init_spi(struct spi_device *spi, const struct regmap_config *config) { - return regmap_init(&spi->dev, ®map_spi, config); + return regmap_init(&spi->dev, ®map_spi, &spi->dev, config); } EXPORT_SYMBOL_GPL(regmap_init_spi); @@ -83,7 +86,7 @@ EXPORT_SYMBOL_GPL(regmap_init_spi); struct regmap *devm_regmap_init_spi(struct spi_device *spi, const struct regmap_config *config) { - return devm_regmap_init(&spi->dev, ®map_spi, config); + return devm_regmap_init(&spi->dev, ®map_spi, &spi->dev, config); } EXPORT_SYMBOL_GPL(devm_regmap_init_spi); diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 7a3f535e481c..bde30c5d5ee9 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -163,6 +163,7 @@ static unsigned int regmap_parse_32(void *buf) * * @dev: Device that will be interacted with * @bus: Bus-specific callbacks to use with device + * @bus_context: Data passed to bus-specific callbacks * @config: Configuration for register map * * The return value will be an ERR_PTR() on error or a valid pointer to @@ -171,6 +172,7 @@ static unsigned int regmap_parse_32(void *buf) */ struct regmap *regmap_init(struct device *dev, const struct regmap_bus *bus, + void *bus_context, const struct regmap_config *config) { struct regmap *map; @@ -193,6 +195,7 @@ struct regmap *regmap_init(struct device *dev, map->format.buf_size += map->format.pad_bytes; map->dev = dev; map->bus = bus; + map->bus_context = bus_context; map->max_register = config->max_register; map->writeable_reg = config->writeable_reg; map->readable_reg = config->readable_reg; @@ -316,6 +319,7 @@ static void devm_regmap_release(struct device *dev, void *res) * * @dev: Device that will be interacted with * @bus: Bus-specific callbacks to use with device + * @bus_context: Data passed to bus-specific callbacks * @config: Configuration for register map * * The return value will be an ERR_PTR() on error or a valid pointer @@ -325,6 +329,7 @@ static void devm_regmap_release(struct device *dev, void *res) */ struct regmap *devm_regmap_init(struct device *dev, const struct regmap_bus *bus, + void *bus_context, const struct regmap_config *config) { struct regmap **ptr, *regmap; @@ -333,7 +338,7 @@ struct regmap *devm_regmap_init(struct device *dev, if (!ptr) return ERR_PTR(-ENOMEM); - regmap = regmap_init(dev, bus, config); + regmap = regmap_init(dev, bus, bus_context, config); if (!IS_ERR(regmap)) { *ptr = regmap; devres_add(dev, ptr); @@ -391,6 +396,8 @@ void regmap_exit(struct regmap *map) { regcache_exit(map); regmap_debugfs_exit(map); + if (map->bus->free_context) + map->bus->free_context(map->bus_context); kfree(map->work_buf); kfree(map); } @@ -444,12 +451,12 @@ static int _regmap_raw_write(struct regmap *map, unsigned int reg, */ if (val == (map->work_buf + map->format.pad_bytes + map->format.reg_bytes)) - ret = map->bus->write(map->dev, map->work_buf, + ret = map->bus->write(map->bus_context, map->work_buf, map->format.reg_bytes + map->format.pad_bytes + val_len); else if (map->bus->gather_write) - ret = map->bus->gather_write(map->dev, map->work_buf, + ret = map->bus->gather_write(map->bus_context, map->work_buf, map->format.reg_bytes + map->format.pad_bytes, val, val_len); @@ -464,7 +471,7 @@ static int _regmap_raw_write(struct regmap *map, unsigned int reg, memcpy(buf, map->work_buf, map->format.reg_bytes); memcpy(buf + map->format.reg_bytes + map->format.pad_bytes, val, val_len); - ret = map->bus->write(map->dev, buf, len); + ret = map->bus->write(map->bus_context, buf, len); kfree(buf); } @@ -498,7 +505,7 @@ int _regmap_write(struct regmap *map, unsigned int reg, trace_regmap_hw_write_start(map->dev, reg, 1); - ret = map->bus->write(map->dev, map->work_buf, + ret = map->bus->write(map->bus_context, map->work_buf, map->format.buf_size); trace_regmap_hw_write_done(map->dev, reg, 1); @@ -639,7 +646,7 @@ static int _regmap_raw_read(struct regmap *map, unsigned int reg, void *val, trace_regmap_hw_read_start(map->dev, reg, val_len / map->format.val_bytes); - ret = map->bus->read(map->dev, map->work_buf, + ret = map->bus->read(map->bus_context, map->work_buf, map->format.reg_bytes + map->format.pad_bytes, val, val_len); diff --git a/include/linux/regmap.h b/include/linux/regmap.h index a90abb6bfa64..8fd341e613d6 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -97,14 +97,15 @@ struct regmap_config { u8 write_flag_mask; }; -typedef int (*regmap_hw_write)(struct device *dev, const void *data, +typedef int (*regmap_hw_write)(void *context, const void *data, size_t count); -typedef int (*regmap_hw_gather_write)(struct device *dev, +typedef int (*regmap_hw_gather_write)(void *context, const void *reg, size_t reg_len, const void *val, size_t val_len); -typedef int (*regmap_hw_read)(struct device *dev, +typedef int (*regmap_hw_read)(void *context, const void *reg_buf, size_t reg_size, void *val_buf, size_t val_size); +typedef void (*regmap_hw_free_context)(void *context); /** * Description of a hardware bus for the register map infrastructure. @@ -121,11 +122,13 @@ struct regmap_bus { regmap_hw_write write; regmap_hw_gather_write gather_write; regmap_hw_read read; + regmap_hw_free_context free_context; u8 read_flag_mask; }; struct regmap *regmap_init(struct device *dev, const struct regmap_bus *bus, + void *bus_context, const struct regmap_config *config); struct regmap *regmap_init_i2c(struct i2c_client *i2c, const struct regmap_config *config); @@ -134,6 +137,7 @@ struct regmap *regmap_init_spi(struct spi_device *dev, struct regmap *devm_regmap_init(struct device *dev, const struct regmap_bus *bus, + void *bus_context, const struct regmap_config *config); struct regmap *devm_regmap_init_i2c(struct i2c_client *i2c, const struct regmap_config *config); -- cgit v1.2.3 From bacdbe077342ecc9e7b3e374cc5a41995116706a Mon Sep 17 00:00:00 2001 From: Stephen Warren Date: Wed, 4 Apr 2012 15:48:28 -0600 Subject: regmap: introduce fast_io busses, and use a spinlock for them Some bus types have very fast IO. For these, acquiring a mutex for every IO operation is a significant overhead. Allow busses to indicate their IO is fast, and enhance regmap to use a spinlock for those busses. [Currently limited to native endian registers -- broonie] Signed-off-by: Stephen Warren Signed-off-by: Mark Brown --- drivers/base/regmap/internal.h | 8 ++++- drivers/base/regmap/regcache-rbtree.c | 4 +-- drivers/base/regmap/regcache.c | 20 +++++------ drivers/base/regmap/regmap.c | 62 +++++++++++++++++++++++++---------- include/linux/regmap.h | 3 ++ 5 files changed, 67 insertions(+), 30 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h index b95fd1f25295..e46c279f8280 100644 --- a/drivers/base/regmap/internal.h +++ b/drivers/base/regmap/internal.h @@ -31,8 +31,14 @@ struct regmap_format { unsigned int (*parse_val)(void *buf); }; +typedef void (*regmap_lock)(struct regmap *map); +typedef void (*regmap_unlock)(struct regmap *map); + struct regmap { - struct mutex lock; + struct mutex mutex; + spinlock_t spinlock; + regmap_lock lock; + regmap_unlock unlock; struct device *dev; /* Device we do I/O on */ void *work_buf; /* Scratch buffer used to format I/O */ diff --git a/drivers/base/regmap/regcache-rbtree.c b/drivers/base/regmap/regcache-rbtree.c index 5157fa04c2f0..cca46007d969 100644 --- a/drivers/base/regmap/regcache-rbtree.c +++ b/drivers/base/regmap/regcache-rbtree.c @@ -139,7 +139,7 @@ static int rbtree_show(struct seq_file *s, void *ignored) int nodes = 0; int registers = 0; - mutex_lock(&map->lock); + map->lock(map); for (node = rb_first(&rbtree_ctx->root); node != NULL; node = rb_next(node)) { @@ -155,7 +155,7 @@ static int rbtree_show(struct seq_file *s, void *ignored) seq_printf(s, "%d nodes, %d registers, average %d registers\n", nodes, registers, registers / nodes); - mutex_unlock(&map->lock); + map->unlock(map); return 0; } diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c index 87f54dbf601b..4ad18505e9ae 100644 --- a/drivers/base/regmap/regcache.c +++ b/drivers/base/regmap/regcache.c @@ -264,7 +264,7 @@ int regcache_sync(struct regmap *map) BUG_ON(!map->cache_ops || !map->cache_ops->sync); - mutex_lock(&map->lock); + map->lock(map); /* Remember the initial bypass state */ bypass = map->cache_bypass; dev_dbg(map->dev, "Syncing %s cache\n", @@ -296,7 +296,7 @@ out: trace_regcache_sync(map->dev, name, "stop"); /* Restore the bypass state */ map->cache_bypass = bypass; - mutex_unlock(&map->lock); + map->unlock(map); return ret; } @@ -323,7 +323,7 @@ int regcache_sync_region(struct regmap *map, unsigned int min, BUG_ON(!map->cache_ops || !map->cache_ops->sync); - mutex_lock(&map->lock); + map->lock(map); /* Remember the initial bypass state */ bypass = map->cache_bypass; @@ -342,7 +342,7 @@ out: trace_regcache_sync(map->dev, name, "stop region"); /* Restore the bypass state */ map->cache_bypass = bypass; - mutex_unlock(&map->lock); + map->unlock(map); return ret; } @@ -361,11 +361,11 @@ out: */ void regcache_cache_only(struct regmap *map, bool enable) { - mutex_lock(&map->lock); + map->lock(map); WARN_ON(map->cache_bypass && enable); map->cache_only = enable; trace_regmap_cache_only(map->dev, enable); - mutex_unlock(&map->lock); + map->unlock(map); } EXPORT_SYMBOL_GPL(regcache_cache_only); @@ -380,9 +380,9 @@ EXPORT_SYMBOL_GPL(regcache_cache_only); */ void regcache_mark_dirty(struct regmap *map) { - mutex_lock(&map->lock); + map->lock(map); map->cache_dirty = true; - mutex_unlock(&map->lock); + map->unlock(map); } EXPORT_SYMBOL_GPL(regcache_mark_dirty); @@ -399,11 +399,11 @@ EXPORT_SYMBOL_GPL(regcache_mark_dirty); */ void regcache_cache_bypass(struct regmap *map, bool enable) { - mutex_lock(&map->lock); + map->lock(map); WARN_ON(map->cache_only && enable); map->cache_bypass = enable; trace_regmap_cache_bypass(map->dev, enable); - mutex_unlock(&map->lock); + map->unlock(map); } EXPORT_SYMBOL_GPL(regcache_cache_bypass); diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index bde30c5d5ee9..6b4a775b439b 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -158,6 +158,26 @@ static unsigned int regmap_parse_32(void *buf) return b[0]; } +static void regmap_lock_mutex(struct regmap *map) +{ + mutex_lock(&map->mutex); +} + +static void regmap_unlock_mutex(struct regmap *map) +{ + mutex_unlock(&map->mutex); +} + +static void regmap_lock_spinlock(struct regmap *map) +{ + spin_lock(&map->spinlock); +} + +static void regmap_unlock_spinlock(struct regmap *map) +{ + spin_unlock(&map->spinlock); +} + /** * regmap_init(): Initialise register map * @@ -187,7 +207,15 @@ struct regmap *regmap_init(struct device *dev, goto err; } - mutex_init(&map->lock); + if (bus->fast_io) { + spin_lock_init(&map->spinlock); + map->lock = regmap_lock_spinlock; + map->unlock = regmap_unlock_spinlock; + } else { + mutex_init(&map->mutex); + map->lock = regmap_lock_mutex; + map->unlock = regmap_unlock_mutex; + } map->format.buf_size = (config->reg_bits + config->val_bits) / 8; map->format.reg_bytes = DIV_ROUND_UP(config->reg_bits, 8); map->format.pad_bytes = config->pad_bits / 8; @@ -365,7 +393,7 @@ int regmap_reinit_cache(struct regmap *map, const struct regmap_config *config) { int ret; - mutex_lock(&map->lock); + map->lock(map); regcache_exit(map); regmap_debugfs_exit(map); @@ -384,7 +412,7 @@ int regmap_reinit_cache(struct regmap *map, const struct regmap_config *config) ret = regcache_init(map, config); - mutex_unlock(&map->lock); + map->unlock(map); return ret; } @@ -536,11 +564,11 @@ int regmap_write(struct regmap *map, unsigned int reg, unsigned int val) { int ret; - mutex_lock(&map->lock); + map->lock(map); ret = _regmap_write(map, reg, val); - mutex_unlock(&map->lock); + map->unlock(map); return ret; } @@ -567,11 +595,11 @@ int regmap_raw_write(struct regmap *map, unsigned int reg, { int ret; - mutex_lock(&map->lock); + map->lock(map); ret = _regmap_raw_write(map, reg, val, val_len); - mutex_unlock(&map->lock); + map->unlock(map); return ret; } @@ -601,7 +629,7 @@ int regmap_bulk_write(struct regmap *map, unsigned int reg, const void *val, if (!map->format.parse_val) return -EINVAL; - mutex_lock(&map->lock); + map->lock(map); /* No formatting is require if val_byte is 1 */ if (val_bytes == 1) { @@ -622,7 +650,7 @@ int regmap_bulk_write(struct regmap *map, unsigned int reg, const void *val, kfree(wval); out: - mutex_unlock(&map->lock); + map->unlock(map); return ret; } EXPORT_SYMBOL_GPL(regmap_bulk_write); @@ -696,11 +724,11 @@ int regmap_read(struct regmap *map, unsigned int reg, unsigned int *val) { int ret; - mutex_lock(&map->lock); + map->lock(map); ret = _regmap_read(map, reg, val); - mutex_unlock(&map->lock); + map->unlock(map); return ret; } @@ -725,7 +753,7 @@ int regmap_raw_read(struct regmap *map, unsigned int reg, void *val, unsigned int v; int ret, i; - mutex_lock(&map->lock); + map->lock(map); if (regmap_volatile_range(map, reg, val_count) || map->cache_bypass || map->cache_type == REGCACHE_NONE) { @@ -746,7 +774,7 @@ int regmap_raw_read(struct regmap *map, unsigned int reg, void *val, } out: - mutex_unlock(&map->lock); + map->unlock(map); return ret; } @@ -799,7 +827,7 @@ static int _regmap_update_bits(struct regmap *map, unsigned int reg, int ret; unsigned int tmp, orig; - mutex_lock(&map->lock); + map->lock(map); ret = _regmap_read(map, reg, &orig); if (ret != 0) @@ -816,7 +844,7 @@ static int _regmap_update_bits(struct regmap *map, unsigned int reg, } out: - mutex_unlock(&map->lock); + map->unlock(map); return ret; } @@ -883,7 +911,7 @@ int regmap_register_patch(struct regmap *map, const struct reg_default *regs, if (map->patch) return -EBUSY; - mutex_lock(&map->lock); + map->lock(map); bypass = map->cache_bypass; @@ -911,7 +939,7 @@ int regmap_register_patch(struct regmap *map, const struct reg_default *regs, out: map->cache_bypass = bypass; - mutex_unlock(&map->lock); + map->unlock(map); return ret; } diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 8fd341e613d6..f14588a96eaf 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -110,6 +110,8 @@ typedef void (*regmap_hw_free_context)(void *context); /** * Description of a hardware bus for the register map infrastructure. * + * @fast_io: Register IO is fast. Use a spinlock instead of a mutex + * to perform locking. * @write: Write operation. * @gather_write: Write operation with split register/value, return -ENOTSUPP * if not implemented on a given device. @@ -119,6 +121,7 @@ typedef void (*regmap_hw_free_context)(void *context); * a read. */ struct regmap_bus { + bool fast_io; regmap_hw_write write; regmap_hw_gather_write gather_write; regmap_hw_read read; -- cgit v1.2.3 From 45f5ff8107a845854b1d1812ab1d9c5541f08b4d Mon Sep 17 00:00:00 2001 From: Stephen Warren Date: Wed, 4 Apr 2012 15:48:31 -0600 Subject: regmap: add MMIO bus support This is a basic memory-mapped-IO bus for regmap. It has the following features and limitations: * Registers themselves may be 8, 16, 32, or 64-bit. 64-bit is only supported on 64-bit platforms. * Register offsets are limited to precisely 32-bit. * IO is performed using readl/writel, with no provision for using the __raw_readl or readl_relaxed variants. Signed-off-by: Stephen Warren Signed-off-by: Mark Brown --- drivers/base/regmap/Kconfig | 3 + drivers/base/regmap/Makefile | 1 + drivers/base/regmap/regmap-mmio.c | 217 ++++++++++++++++++++++++++++++++++++++ include/linux/regmap.h | 6 ++ 4 files changed, 227 insertions(+) create mode 100644 drivers/base/regmap/regmap-mmio.c (limited to 'drivers/base') diff --git a/drivers/base/regmap/Kconfig b/drivers/base/regmap/Kconfig index 0f6c7fb418e8..9ef0a5326f17 100644 --- a/drivers/base/regmap/Kconfig +++ b/drivers/base/regmap/Kconfig @@ -14,5 +14,8 @@ config REGMAP_I2C config REGMAP_SPI tristate +config REGMAP_MMIO + tristate + config REGMAP_IRQ bool diff --git a/drivers/base/regmap/Makefile b/drivers/base/regmap/Makefile index defd57963c84..5e75d1b683e2 100644 --- a/drivers/base/regmap/Makefile +++ b/drivers/base/regmap/Makefile @@ -3,4 +3,5 @@ obj-$(CONFIG_REGMAP) += regcache-rbtree.o regcache-lzo.o obj-$(CONFIG_DEBUG_FS) += regmap-debugfs.o obj-$(CONFIG_REGMAP_I2C) += regmap-i2c.o obj-$(CONFIG_REGMAP_SPI) += regmap-spi.o +obj-$(CONFIG_REGMAP_MMIO) += regmap-mmio.o obj-$(CONFIG_REGMAP_IRQ) += regmap-irq.o diff --git a/drivers/base/regmap/regmap-mmio.c b/drivers/base/regmap/regmap-mmio.c new file mode 100644 index 000000000000..1a7b5ee11abc --- /dev/null +++ b/drivers/base/regmap/regmap-mmio.c @@ -0,0 +1,217 @@ +/* + * Register map access API - MMIO support + * + * Copyright (c) 2012, NVIDIA CORPORATION. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ + +#include +#include +#include +#include +#include +#include + +struct regmap_mmio_context { + void __iomem *regs; + unsigned val_bytes; +}; + +static int regmap_mmio_gather_write(void *context, + const void *reg, size_t reg_size, + const void *val, size_t val_size) +{ + struct regmap_mmio_context *ctx = context; + u32 offset; + + if (reg_size != 4) + return -EIO; + if (val_size % ctx->val_bytes) + return -EIO; + + offset = be32_to_cpup(reg); + + while (val_size) { + switch (ctx->val_bytes) { + case 1: + writeb(*(u8 *)val, ctx->regs + offset); + break; + case 2: + writew(be16_to_cpup(val), ctx->regs + offset); + break; + case 4: + writel(be32_to_cpup(val), ctx->regs + offset); + break; +#ifdef CONFIG_64BIT + case 8: + writeq(be64_to_cpup(val), ctx->regs + offset); + break; +#endif + default: + /* Should be caught by regmap_mmio_check_config */ + return -EIO; + } + val_size -= ctx->val_bytes; + val += ctx->val_bytes; + offset += ctx->val_bytes; + } + + return 0; +} + +static int regmap_mmio_write(void *context, const void *data, size_t count) +{ + if (count < 4) + return -EIO; + return regmap_mmio_gather_write(context, data, 4, data + 4, count - 4); +} + +static int regmap_mmio_read(void *context, + const void *reg, size_t reg_size, + void *val, size_t val_size) +{ + struct regmap_mmio_context *ctx = context; + u32 offset; + + if (reg_size != 4) + return -EIO; + if (val_size % ctx->val_bytes) + return -EIO; + + offset = be32_to_cpup(reg); + + while (val_size) { + switch (ctx->val_bytes) { + case 1: + *(u8 *)val = readb(ctx->regs + offset); + break; + case 2: + *(u16 *)val = cpu_to_be16(readw(ctx->regs + offset)); + break; + case 4: + *(u32 *)val = cpu_to_be32(readl(ctx->regs + offset)); + break; +#ifdef CONFIG_64BIT + case 8: + *(u64 *)val = cpu_to_be32(readq(ctx->regs + offset)); + break; +#endif + default: + /* Should be caught by regmap_mmio_check_config */ + return -EIO; + } + val_size -= ctx->val_bytes; + val += ctx->val_bytes; + offset += ctx->val_bytes; + } + + return 0; +} + +static void regmap_mmio_free_context(void *context) +{ + kfree(context); +} + +static struct regmap_bus regmap_mmio = { + .fast_io = true, + .write = regmap_mmio_write, + .gather_write = regmap_mmio_gather_write, + .read = regmap_mmio_read, + .free_context = regmap_mmio_free_context, +}; + +struct regmap_mmio_context *regmap_mmio_gen_context(void __iomem *regs, + const struct regmap_config *config) +{ + struct regmap_mmio_context *ctx; + + if (config->reg_bits != 32) + return ERR_PTR(-EINVAL); + + if (config->pad_bits) + return ERR_PTR(-EINVAL); + + switch (config->val_bits) { + case 8: + case 16: + case 32: +#ifdef CONFIG_64BIT + case 64: +#endif + break; + default: + return ERR_PTR(-EINVAL); + } + + ctx = kzalloc(GFP_KERNEL, sizeof(*ctx)); + if (!ctx) + return ERR_PTR(-ENOMEM); + + ctx->regs = regs; + ctx->val_bytes = config->val_bits / 8; + + return ctx; +} + +/** + * regmap_init_mmio(): Initialise register map + * + * @dev: Device that will be interacted with + * @regs: Pointer to memory-mapped IO region + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer to + * a struct regmap. + */ +struct regmap *regmap_init_mmio(struct device *dev, + void __iomem *regs, + const struct regmap_config *config) +{ + struct regmap_mmio_context *ctx; + + ctx = regmap_mmio_gen_context(regs, config); + if (IS_ERR(ctx)) + return ERR_CAST(ctx); + + return regmap_init(dev, ®map_mmio, ctx, config); +} +EXPORT_SYMBOL_GPL(regmap_init_mmio); + +/** + * devm_regmap_init_mmio(): Initialise managed register map + * + * @dev: Device that will be interacted with + * @regs: Pointer to memory-mapped IO region + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer + * to a struct regmap. The regmap will be automatically freed by the + * device management code. + */ +struct regmap *devm_regmap_init_mmio(struct device *dev, + void __iomem *regs, + const struct regmap_config *config) +{ + struct regmap_mmio_context *ctx; + + ctx = regmap_mmio_gen_context(regs, config); + if (IS_ERR(ctx)) + return ERR_CAST(ctx); + + return devm_regmap_init(dev, ®map_mmio, ctx, config); +} +EXPORT_SYMBOL_GPL(devm_regmap_init_mmio); + +MODULE_LICENSE("GPL v2"); diff --git a/include/linux/regmap.h b/include/linux/regmap.h index f14588a96eaf..f6abc8d33d64 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -137,6 +137,9 @@ struct regmap *regmap_init_i2c(struct i2c_client *i2c, const struct regmap_config *config); struct regmap *regmap_init_spi(struct spi_device *dev, const struct regmap_config *config); +struct regmap *regmap_init_mmio(struct device *dev, + void __iomem *regs, + const struct regmap_config *config); struct regmap *devm_regmap_init(struct device *dev, const struct regmap_bus *bus, @@ -146,6 +149,9 @@ struct regmap *devm_regmap_init_i2c(struct i2c_client *i2c, const struct regmap_config *config); struct regmap *devm_regmap_init_spi(struct spi_device *dev, const struct regmap_config *config); +struct regmap *devm_regmap_init_mmio(struct device *dev, + void __iomem *regs, + const struct regmap_config *config); void regmap_exit(struct regmap *map); int regmap_reinit_cache(struct regmap *map, -- cgit v1.2.3 From 40606dba450830e50420599c52a86cf6ce5c6a14 Mon Sep 17 00:00:00 2001 From: Stephen Warren Date: Fri, 6 Apr 2012 15:17:32 -0600 Subject: regmap: mmio: convert some error returns to BUG() Some of the error conditions detected by regmap_mmio_*() are pure internal errors, rather than user-/client-triggerable conditions. Convert these to BUG(). Signed-off-by: Stephen Warren Signed-off-by: Mark Brown --- drivers/base/regmap/regmap-mmio.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/regmap/regmap-mmio.c b/drivers/base/regmap/regmap-mmio.c index 1a7b5ee11abc..ffa0e850839e 100644 --- a/drivers/base/regmap/regmap-mmio.c +++ b/drivers/base/regmap/regmap-mmio.c @@ -35,8 +35,8 @@ static int regmap_mmio_gather_write(void *context, struct regmap_mmio_context *ctx = context; u32 offset; - if (reg_size != 4) - return -EIO; + BUG_ON(reg_size != 4); + if (val_size % ctx->val_bytes) return -EIO; @@ -60,7 +60,7 @@ static int regmap_mmio_gather_write(void *context, #endif default: /* Should be caught by regmap_mmio_check_config */ - return -EIO; + BUG(); } val_size -= ctx->val_bytes; val += ctx->val_bytes; @@ -72,8 +72,8 @@ static int regmap_mmio_gather_write(void *context, static int regmap_mmio_write(void *context, const void *data, size_t count) { - if (count < 4) - return -EIO; + BUG_ON(count < 4); + return regmap_mmio_gather_write(context, data, 4, data + 4, count - 4); } @@ -84,8 +84,8 @@ static int regmap_mmio_read(void *context, struct regmap_mmio_context *ctx = context; u32 offset; - if (reg_size != 4) - return -EIO; + BUG_ON(reg_size != 4); + if (val_size % ctx->val_bytes) return -EIO; @@ -109,7 +109,7 @@ static int regmap_mmio_read(void *context, #endif default: /* Should be caught by regmap_mmio_check_config */ - return -EIO; + BUG(); } val_size -= ctx->val_bytes; val += ctx->val_bytes; -- cgit v1.2.3 From 9878647f4349dbaa46b4026ed9bbf8acfc0de34c Mon Sep 17 00:00:00 2001 From: Stephen Warren Date: Fri, 6 Apr 2012 15:17:33 -0600 Subject: regmap: mmio: remove some error checks now in the core These error checks are implemented in regmap core. Remove the duplicate code from regmap-mmio.c Signed-off-by: Stephen Warren Signed-off-by: Mark Brown --- drivers/base/regmap/regmap-mmio.c | 6 ------ 1 file changed, 6 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/regmap/regmap-mmio.c b/drivers/base/regmap/regmap-mmio.c index ffa0e850839e..bdf4dc865293 100644 --- a/drivers/base/regmap/regmap-mmio.c +++ b/drivers/base/regmap/regmap-mmio.c @@ -37,9 +37,6 @@ static int regmap_mmio_gather_write(void *context, BUG_ON(reg_size != 4); - if (val_size % ctx->val_bytes) - return -EIO; - offset = be32_to_cpup(reg); while (val_size) { @@ -86,9 +83,6 @@ static int regmap_mmio_read(void *context, BUG_ON(reg_size != 4); - if (val_size % ctx->val_bytes) - return -EIO; - offset = be32_to_cpup(reg); while (val_size) { -- cgit v1.2.3 From 851960ba7cb38a6a108d102e4c8b0ab702972e22 Mon Sep 17 00:00:00 2001 From: Stephen Warren Date: Fri, 6 Apr 2012 15:16:03 -0600 Subject: regmap: validate regmap_raw_read/write val_len val_len should be a multiple of val_bytes. If it's not, error out early. Signed-off-by: Stephen Warren Signed-off-by: Mark Brown --- drivers/base/regmap/regmap.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'drivers/base') diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 6b4a775b439b..ee4fea351220 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -595,6 +595,9 @@ int regmap_raw_write(struct regmap *map, unsigned int reg, { int ret; + if (val_len % map->format.val_bytes) + return -EINVAL; + map->lock(map); ret = _regmap_raw_write(map, reg, val, val_len); @@ -753,6 +756,9 @@ int regmap_raw_read(struct regmap *map, unsigned int reg, void *val, unsigned int v; int ret, i; + if (val_len % map->format.val_bytes) + return -EINVAL; + map->lock(map); if (regmap_volatile_range(map, reg, val_count) || map->cache_bypass || -- cgit v1.2.3 From d3c242e1f22f5dfed009296ee45ce896153f0b53 Mon Sep 17 00:00:00 2001 From: Stephen Warren Date: Wed, 4 Apr 2012 15:48:29 -0600 Subject: regmap: allow regmap instances to be named Some devices have multiple separate register regions. Logically, one regmap would be created per region. One issue that prevents this is that each instance will attempt to create the same debugfs files. Avoid this by allowing regmaps to be named, and use the name to construct the debugfs directory name. Signed-off-by: Stephen Warren Signed-off-by: Mark Brown --- drivers/base/regmap/internal.h | 3 ++- drivers/base/regmap/regmap-debugfs.c | 14 +++++++++++--- drivers/base/regmap/regmap.c | 4 ++-- include/linux/regmap.h | 5 +++++ 4 files changed, 20 insertions(+), 6 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h index fcafc5b2e651..6beef6691c47 100644 --- a/drivers/base/regmap/internal.h +++ b/drivers/base/regmap/internal.h @@ -41,6 +41,7 @@ struct regmap { #ifdef CONFIG_DEBUG_FS struct dentry *debugfs; + const char *debugfs_name; #endif unsigned int max_register; @@ -101,7 +102,7 @@ int _regmap_write(struct regmap *map, unsigned int reg, #ifdef CONFIG_DEBUG_FS extern void regmap_debugfs_initcall(void); -extern void regmap_debugfs_init(struct regmap *map); +extern void regmap_debugfs_init(struct regmap *map, const char *name); extern void regmap_debugfs_exit(struct regmap *map); #else static inline void regmap_debugfs_initcall(void) { } diff --git a/drivers/base/regmap/regmap-debugfs.c b/drivers/base/regmap/regmap-debugfs.c index 58517a5dac13..9715e8e44506 100644 --- a/drivers/base/regmap/regmap-debugfs.c +++ b/drivers/base/regmap/regmap-debugfs.c @@ -248,10 +248,17 @@ static const struct file_operations regmap_access_fops = { .llseek = default_llseek, }; -void regmap_debugfs_init(struct regmap *map) +void regmap_debugfs_init(struct regmap *map, const char *name) { - map->debugfs = debugfs_create_dir(dev_name(map->dev), - regmap_debugfs_root); + if (name) { + map->debugfs_name = kasprintf(GFP_KERNEL, "%s-%s", + dev_name(map->dev), name); + name = map->debugfs_name; + } else { + name = dev_name(map->dev); + } + + map->debugfs = debugfs_create_dir(name, regmap_debugfs_root); if (!map->debugfs) { dev_warn(map->dev, "Failed to create debugfs directory\n"); return; @@ -280,6 +287,7 @@ void regmap_debugfs_init(struct regmap *map) void regmap_debugfs_exit(struct regmap *map) { debugfs_remove_recursive(map->debugfs); + kfree(map->debugfs_name); } void regmap_debugfs_initcall(void) diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 7a3f535e481c..b1dad1f9c47d 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -289,7 +289,7 @@ struct regmap *regmap_init(struct device *dev, goto err_map; } - regmap_debugfs_init(map); + regmap_debugfs_init(map, config->name); ret = regcache_init(map, config); if (ret < 0) @@ -372,7 +372,7 @@ int regmap_reinit_cache(struct regmap *map, const struct regmap_config *config) map->precious_reg = config->precious_reg; map->cache_type = config->cache_type; - regmap_debugfs_init(map); + regmap_debugfs_init(map, config->name); map->cache_bypass = false; map->cache_only = false; diff --git a/include/linux/regmap.h b/include/linux/regmap.h index a90abb6bfa64..0a27ee809ca1 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -46,6 +46,9 @@ struct reg_default { /** * Configuration for the register map of a device. * + * @name: Optional name of the regmap. Useful when a device has multiple + * register regions. + * * @reg_bits: Number of bits in a register address, mandatory. * @pad_bits: Number of bits of padding between register and value. * @val_bits: Number of bits in a register value, mandatory. @@ -77,6 +80,8 @@ struct reg_default { * @num_reg_defaults_raw: Number of elements in reg_defaults_raw. */ struct regmap_config { + const char *name; + int reg_bits; int pad_bits; int val_bits; -- cgit v1.2.3 From abec95adefaeb2229cb28de65f3d32cd149b9dd9 Mon Sep 17 00:00:00 2001 From: Stephen Warren Date: Thu, 5 Apr 2012 23:09:20 -0600 Subject: regmap: fix compilation when !CONFIG_DEBUG_FS Commit 79c64d5 "regmap: allow regmap instances to be named" changed the prototype of regmap_debugfs_init, but didn't update the dummy inline used when !CONFIG_DEBUGFS. Fix this. Signed-off-by: Stephen Warren Signed-off-by: Mark Brown --- drivers/base/regmap/internal.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/base') diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h index 6beef6691c47..8461ca7711ed 100644 --- a/drivers/base/regmap/internal.h +++ b/drivers/base/regmap/internal.h @@ -106,7 +106,7 @@ extern void regmap_debugfs_init(struct regmap *map, const char *name); extern void regmap_debugfs_exit(struct regmap *map); #else static inline void regmap_debugfs_initcall(void) { } -static inline void regmap_debugfs_init(struct regmap *map) { } +static inline void regmap_debugfs_init(struct regmap *map, const char *name) { } static inline void regmap_debugfs_exit(struct regmap *map) { } #endif -- cgit v1.2.3 From f01ee60fffa4dc6c77122121233a793f7f696e67 Mon Sep 17 00:00:00 2001 From: Stephen Warren Date: Mon, 9 Apr 2012 13:40:24 -0600 Subject: regmap: implement register striding regmap_config.reg_stride is introduced. All extant register addresses are a multiple of this value. Users of serial-oriented regmap busses will typically set this to 1. Users of the MMIO regmap bus will typically set this based on the value size of their registers, in bytes, so 4 for a 32-bit register. Throughout the regmap code, actual register addresses are used. Wherever the register address is used to index some array of values, the address is divided by the stride to determine the index, or vice-versa. Error- checking is added to all entry-points for register address data to ensure that register addresses actually satisfy the specified stride. The MMIO bus ensures that the specified stride is large enough for the register size. Signed-off-by: Stephen Warren Signed-off-by: Mark Brown --- drivers/base/regmap/internal.h | 1 + drivers/base/regmap/regcache-lzo.c | 11 +++++----- drivers/base/regmap/regcache-rbtree.c | 40 ++++++++++++++++++++--------------- drivers/base/regmap/regcache.c | 14 +++++++++--- drivers/base/regmap/regmap-debugfs.c | 4 ++-- drivers/base/regmap/regmap-irq.c | 34 +++++++++++++++++++---------- drivers/base/regmap/regmap-mmio.c | 13 ++++++++++++ drivers/base/regmap/regmap.c | 30 ++++++++++++++++++++++---- include/linux/regmap.h | 4 ++++ 9 files changed, 109 insertions(+), 42 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h index 99b28fffbd0e..d92e9b1cb83c 100644 --- a/drivers/base/regmap/internal.h +++ b/drivers/base/regmap/internal.h @@ -62,6 +62,7 @@ struct regmap { /* number of bits to (left) shift the reg value when formatting*/ int reg_shift; + int reg_stride; /* regcache specific members */ const struct regcache_ops *cache_ops; diff --git a/drivers/base/regmap/regcache-lzo.c b/drivers/base/regmap/regcache-lzo.c index 483b06d4a380..afd6aa91a0df 100644 --- a/drivers/base/regmap/regcache-lzo.c +++ b/drivers/base/regmap/regcache-lzo.c @@ -108,7 +108,7 @@ static int regcache_lzo_decompress_cache_block(struct regmap *map, static inline int regcache_lzo_get_blkindex(struct regmap *map, unsigned int reg) { - return (reg * map->cache_word_size) / + return ((reg / map->reg_stride) * map->cache_word_size) / DIV_ROUND_UP(map->cache_size_raw, regcache_lzo_block_count(map)); } @@ -116,9 +116,10 @@ static inline int regcache_lzo_get_blkindex(struct regmap *map, static inline int regcache_lzo_get_blkpos(struct regmap *map, unsigned int reg) { - return reg % (DIV_ROUND_UP(map->cache_size_raw, - regcache_lzo_block_count(map)) / - map->cache_word_size); + return (reg / map->reg_stride) % + (DIV_ROUND_UP(map->cache_size_raw, + regcache_lzo_block_count(map)) / + map->cache_word_size); } static inline int regcache_lzo_get_blksize(struct regmap *map) @@ -322,7 +323,7 @@ static int regcache_lzo_write(struct regmap *map, } /* set the bit so we know we have to sync this register */ - set_bit(reg, lzo_block->sync_bmp); + set_bit(reg / map->reg_stride, lzo_block->sync_bmp); kfree(tmp_dst); kfree(lzo_block->src); return 0; diff --git a/drivers/base/regmap/regcache-rbtree.c b/drivers/base/regmap/regcache-rbtree.c index e49e71fab184..e6732cf7c06e 100644 --- a/drivers/base/regmap/regcache-rbtree.c +++ b/drivers/base/regmap/regcache-rbtree.c @@ -39,11 +39,12 @@ struct regcache_rbtree_ctx { }; static inline void regcache_rbtree_get_base_top_reg( + struct regmap *map, struct regcache_rbtree_node *rbnode, unsigned int *base, unsigned int *top) { *base = rbnode->base_reg; - *top = rbnode->base_reg + rbnode->blklen - 1; + *top = rbnode->base_reg + ((rbnode->blklen - 1) * map->reg_stride); } static unsigned int regcache_rbtree_get_register( @@ -70,7 +71,8 @@ static struct regcache_rbtree_node *regcache_rbtree_lookup(struct regmap *map, rbnode = rbtree_ctx->cached_rbnode; if (rbnode) { - regcache_rbtree_get_base_top_reg(rbnode, &base_reg, &top_reg); + regcache_rbtree_get_base_top_reg(map, rbnode, &base_reg, + &top_reg); if (reg >= base_reg && reg <= top_reg) return rbnode; } @@ -78,7 +80,8 @@ static struct regcache_rbtree_node *regcache_rbtree_lookup(struct regmap *map, node = rbtree_ctx->root.rb_node; while (node) { rbnode = container_of(node, struct regcache_rbtree_node, node); - regcache_rbtree_get_base_top_reg(rbnode, &base_reg, &top_reg); + regcache_rbtree_get_base_top_reg(map, rbnode, &base_reg, + &top_reg); if (reg >= base_reg && reg <= top_reg) { rbtree_ctx->cached_rbnode = rbnode; return rbnode; @@ -92,7 +95,7 @@ static struct regcache_rbtree_node *regcache_rbtree_lookup(struct regmap *map, return NULL; } -static int regcache_rbtree_insert(struct rb_root *root, +static int regcache_rbtree_insert(struct regmap *map, struct rb_root *root, struct regcache_rbtree_node *rbnode) { struct rb_node **new, *parent; @@ -106,7 +109,7 @@ static int regcache_rbtree_insert(struct rb_root *root, rbnode_tmp = container_of(*new, struct regcache_rbtree_node, node); /* base and top registers of the current rbnode */ - regcache_rbtree_get_base_top_reg(rbnode_tmp, &base_reg_tmp, + regcache_rbtree_get_base_top_reg(map, rbnode_tmp, &base_reg_tmp, &top_reg_tmp); /* base register of the rbnode to be added */ base_reg = rbnode->base_reg; @@ -138,7 +141,7 @@ static int rbtree_show(struct seq_file *s, void *ignored) unsigned int base, top; int nodes = 0; int registers = 0; - int average; + int this_registers, average; map->lock(map); @@ -146,11 +149,12 @@ static int rbtree_show(struct seq_file *s, void *ignored) node = rb_next(node)) { n = container_of(node, struct regcache_rbtree_node, node); - regcache_rbtree_get_base_top_reg(n, &base, &top); - seq_printf(s, "%x-%x (%d)\n", base, top, top - base + 1); + regcache_rbtree_get_base_top_reg(map, n, &base, &top); + this_registers = ((top - base) / map->reg_stride) + 1; + seq_printf(s, "%x-%x (%d)\n", base, top, this_registers); nodes++; - registers += top - base + 1; + registers += this_registers; } if (nodes) @@ -255,7 +259,7 @@ static int regcache_rbtree_read(struct regmap *map, rbnode = regcache_rbtree_lookup(map, reg); if (rbnode) { - reg_tmp = reg - rbnode->base_reg; + reg_tmp = (reg - rbnode->base_reg) / map->reg_stride; *value = regcache_rbtree_get_register(rbnode, reg_tmp, map->cache_word_size); } else { @@ -310,7 +314,7 @@ static int regcache_rbtree_write(struct regmap *map, unsigned int reg, */ rbnode = regcache_rbtree_lookup(map, reg); if (rbnode) { - reg_tmp = reg - rbnode->base_reg; + reg_tmp = (reg - rbnode->base_reg) / map->reg_stride; val = regcache_rbtree_get_register(rbnode, reg_tmp, map->cache_word_size); if (val == value) @@ -321,13 +325,15 @@ static int regcache_rbtree_write(struct regmap *map, unsigned int reg, /* look for an adjacent register to the one we are about to add */ for (node = rb_first(&rbtree_ctx->root); node; node = rb_next(node)) { - rbnode_tmp = rb_entry(node, struct regcache_rbtree_node, node); + rbnode_tmp = rb_entry(node, struct regcache_rbtree_node, + node); for (i = 0; i < rbnode_tmp->blklen; i++) { - reg_tmp = rbnode_tmp->base_reg + i; - if (abs(reg_tmp - reg) != 1) + reg_tmp = rbnode_tmp->base_reg + + (i * map->reg_stride); + if (abs(reg_tmp - reg) != map->reg_stride) continue; /* decide where in the block to place our register */ - if (reg_tmp + 1 == reg) + if (reg_tmp + map->reg_stride == reg) pos = i + 1; else pos = i; @@ -357,7 +363,7 @@ static int regcache_rbtree_write(struct regmap *map, unsigned int reg, return -ENOMEM; } regcache_rbtree_set_register(rbnode, 0, value, map->cache_word_size); - regcache_rbtree_insert(&rbtree_ctx->root, rbnode); + regcache_rbtree_insert(map, &rbtree_ctx->root, rbnode); rbtree_ctx->cached_rbnode = rbnode; } @@ -397,7 +403,7 @@ static int regcache_rbtree_sync(struct regmap *map, unsigned int min, end = rbnode->blklen; for (i = base; i < end; i++) { - regtmp = rbnode->base_reg + i; + regtmp = rbnode->base_reg + (i * map->reg_stride); val = regcache_rbtree_get_register(rbnode, i, map->cache_word_size); diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c index d4368e8b6f9d..835883bda977 100644 --- a/drivers/base/regmap/regcache.c +++ b/drivers/base/regmap/regcache.c @@ -59,7 +59,7 @@ static int regcache_hw_init(struct regmap *map) for (count = 0, i = 0; i < map->num_reg_defaults_raw; i++) { val = regcache_get_val(map->reg_defaults_raw, i, map->cache_word_size); - if (regmap_volatile(map, i)) + if (regmap_volatile(map, i * map->reg_stride)) continue; count++; } @@ -76,9 +76,9 @@ static int regcache_hw_init(struct regmap *map) for (i = 0, j = 0; i < map->num_reg_defaults_raw; i++) { val = regcache_get_val(map->reg_defaults_raw, i, map->cache_word_size); - if (regmap_volatile(map, i)) + if (regmap_volatile(map, i * map->reg_stride)) continue; - map->reg_defaults[j].reg = i; + map->reg_defaults[j].reg = i * map->reg_stride; map->reg_defaults[j].def = val; j++; } @@ -98,6 +98,10 @@ int regcache_init(struct regmap *map, const struct regmap_config *config) int i; void *tmp_buf; + for (i = 0; i < config->num_reg_defaults; i++) + if (config->reg_defaults[i].reg % map->reg_stride) + return -EINVAL; + if (map->cache_type == REGCACHE_NONE) { map->cache_bypass = true; return 0; @@ -278,6 +282,10 @@ int regcache_sync(struct regmap *map) /* Apply any patch first */ map->cache_bypass = 1; for (i = 0; i < map->patch_regs; i++) { + if (map->patch[i].reg % map->reg_stride) { + ret = -EINVAL; + goto out; + } ret = _regmap_write(map, map->patch[i].reg, map->patch[i].def); if (ret != 0) { dev_err(map->dev, "Failed to write %x = %x: %d\n", diff --git a/drivers/base/regmap/regmap-debugfs.c b/drivers/base/regmap/regmap-debugfs.c index df97c93efa8e..bb1ff175b962 100644 --- a/drivers/base/regmap/regmap-debugfs.c +++ b/drivers/base/regmap/regmap-debugfs.c @@ -80,7 +80,7 @@ static ssize_t regmap_map_read_file(struct file *file, char __user *user_buf, val_len = 2 * map->format.val_bytes; tot_len = reg_len + val_len + 3; /* : \n */ - for (i = 0; i < map->max_register + 1; i++) { + for (i = 0; i <= map->max_register; i += map->reg_stride) { if (!regmap_readable(map, i)) continue; @@ -197,7 +197,7 @@ static ssize_t regmap_access_read_file(struct file *file, reg_len = regmap_calc_reg_len(map->max_register, buf, count); tot_len = reg_len + 10; /* ': R W V P\n' */ - for (i = 0; i < map->max_register + 1; i++) { + for (i = 0; i <= map->max_register; i += map->reg_stride) { /* Ignore registers which are neither readable nor writable */ if (!regmap_readable(map, i) && !regmap_writeable(map, i)) continue; diff --git a/drivers/base/regmap/regmap-irq.c b/drivers/base/regmap/regmap-irq.c index 1befaa7a31cb..56b8136eb36a 100644 --- a/drivers/base/regmap/regmap-irq.c +++ b/drivers/base/regmap/regmap-irq.c @@ -58,11 +58,12 @@ static void regmap_irq_sync_unlock(struct irq_data *data) * suppress pointless writes. */ for (i = 0; i < d->chip->num_regs; i++) { - ret = regmap_update_bits(d->map, d->chip->mask_base + i, + ret = regmap_update_bits(d->map, d->chip->mask_base + + (i * map->map->reg_stride), d->mask_buf_def[i], d->mask_buf[i]); if (ret != 0) dev_err(d->map->dev, "Failed to sync masks in %x\n", - d->chip->mask_base + i); + d->chip->mask_base + (i * map->reg_stride)); } mutex_unlock(&d->lock); @@ -73,7 +74,7 @@ static void regmap_irq_enable(struct irq_data *data) struct regmap_irq_chip_data *d = irq_data_get_irq_chip_data(data); const struct regmap_irq *irq_data = irq_to_regmap_irq(d, data->irq); - d->mask_buf[irq_data->reg_offset] &= ~irq_data->mask; + d->mask_buf[irq_data->reg_offset / map->reg_stride] &= ~irq_data->mask; } static void regmap_irq_disable(struct irq_data *data) @@ -81,7 +82,7 @@ static void regmap_irq_disable(struct irq_data *data) struct regmap_irq_chip_data *d = irq_data_get_irq_chip_data(data); const struct regmap_irq *irq_data = irq_to_regmap_irq(d, data->irq); - d->mask_buf[irq_data->reg_offset] |= irq_data->mask; + d->mask_buf[irq_data->reg_offset / map->reg_stride] |= irq_data->mask; } static struct irq_chip regmap_irq_chip = { @@ -136,17 +137,19 @@ static irqreturn_t regmap_irq_thread(int irq, void *d) data->status_buf[i] &= ~data->mask_buf[i]; if (data->status_buf[i] && chip->ack_base) { - ret = regmap_write(map, chip->ack_base + i, + ret = regmap_write(map, chip->ack_base + + (i * map->reg_stride), data->status_buf[i]); if (ret != 0) dev_err(map->dev, "Failed to ack 0x%x: %d\n", - chip->ack_base + i, ret); + chip->ack_base + (i * map->reg_stride), + ret); } } for (i = 0; i < chip->num_irqs; i++) { - if (data->status_buf[chip->irqs[i].reg_offset] & - chip->irqs[i].mask) { + if (data->status_buf[chip->irqs[i].reg_offset / + map->reg_stride] & chip->irqs[i].mask) { handle_nested_irq(data->irq_base + i); handled = true; } @@ -181,6 +184,14 @@ int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags, int cur_irq, i; int ret = -ENOMEM; + for (i = 0; i < chip->num_irqs; i++) { + if (chip->irqs[i].reg_offset % map->reg_stride) + return -EINVAL; + if (chip->irqs[i].reg_offset / map->reg_stride >= + chip->num_regs) + return -EINVAL; + } + irq_base = irq_alloc_descs(irq_base, 0, chip->num_irqs, 0); if (irq_base < 0) { dev_warn(map->dev, "Failed to allocate IRQs: %d\n", @@ -218,16 +229,17 @@ int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags, mutex_init(&d->lock); for (i = 0; i < chip->num_irqs; i++) - d->mask_buf_def[chip->irqs[i].reg_offset] + d->mask_buf_def[chip->irqs[i].reg_offset / map->reg_stride] |= chip->irqs[i].mask; /* Mask all the interrupts by default */ for (i = 0; i < chip->num_regs; i++) { d->mask_buf[i] = d->mask_buf_def[i]; - ret = regmap_write(map, chip->mask_base + i, d->mask_buf[i]); + ret = regmap_write(map, chip->mask_base + (i * map->reg_stride), + d->mask_buf[i]); if (ret != 0) { dev_err(map->dev, "Failed to set masks in 0x%x: %d\n", - chip->mask_base + i, ret); + chip->mask_base + (i * map->reg_stride), ret); goto err_alloc; } } diff --git a/drivers/base/regmap/regmap-mmio.c b/drivers/base/regmap/regmap-mmio.c index bdf4dc865293..febd6de6c8ac 100644 --- a/drivers/base/regmap/regmap-mmio.c +++ b/drivers/base/regmap/regmap-mmio.c @@ -130,6 +130,7 @@ struct regmap_mmio_context *regmap_mmio_gen_context(void __iomem *regs, const struct regmap_config *config) { struct regmap_mmio_context *ctx; + int min_stride; if (config->reg_bits != 32) return ERR_PTR(-EINVAL); @@ -139,16 +140,28 @@ struct regmap_mmio_context *regmap_mmio_gen_context(void __iomem *regs, switch (config->val_bits) { case 8: + /* The core treats 0 as 1 */ + min_stride = 0; + break; case 16: + min_stride = 2; + break; case 32: + min_stride = 4; + break; #ifdef CONFIG_64BIT case 64: + min_stride = 8; + break; #endif break; default: return ERR_PTR(-EINVAL); } + if (config->reg_stride < min_stride) + return ERR_PTR(-EINVAL); + ctx = kzalloc(GFP_KERNEL, sizeof(*ctx)); if (!ctx) return ERR_PTR(-ENOMEM); diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 40f910162781..8a25006b2a4d 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -243,6 +243,10 @@ struct regmap *regmap_init(struct device *dev, map->format.val_bytes = DIV_ROUND_UP(config->val_bits, 8); map->format.buf_size += map->format.pad_bytes; map->reg_shift = config->pad_bits % 8; + if (config->reg_stride) + map->reg_stride = config->reg_stride; + else + map->reg_stride = 1; map->dev = dev; map->bus = bus; map->bus_context = bus_context; @@ -469,7 +473,8 @@ static int _regmap_raw_write(struct regmap *map, unsigned int reg, /* Check for unwritable registers before we start */ if (map->writeable_reg) for (i = 0; i < val_len / map->format.val_bytes; i++) - if (!map->writeable_reg(map->dev, reg + i)) + if (!map->writeable_reg(map->dev, + reg + (i * map->reg_stride))) return -EINVAL; if (!map->cache_bypass && map->format.parse_val) { @@ -478,7 +483,8 @@ static int _regmap_raw_write(struct regmap *map, unsigned int reg, for (i = 0; i < val_len / val_bytes; i++) { memcpy(map->work_buf, val + (i * val_bytes), val_bytes); ival = map->format.parse_val(map->work_buf); - ret = regcache_write(map, reg + i, ival); + ret = regcache_write(map, reg + (i * map->reg_stride), + ival); if (ret) { dev_err(map->dev, "Error in caching of register: %u ret: %d\n", @@ -590,6 +596,9 @@ int regmap_write(struct regmap *map, unsigned int reg, unsigned int val) { int ret; + if (reg % map->reg_stride) + return -EINVAL; + map->lock(map); ret = _regmap_write(map, reg, val); @@ -623,6 +632,8 @@ int regmap_raw_write(struct regmap *map, unsigned int reg, if (val_len % map->format.val_bytes) return -EINVAL; + if (reg % map->reg_stride) + return -EINVAL; map->lock(map); @@ -657,6 +668,8 @@ int regmap_bulk_write(struct regmap *map, unsigned int reg, const void *val, if (!map->format.parse_val) return -EINVAL; + if (reg % map->reg_stride) + return -EINVAL; map->lock(map); @@ -753,6 +766,9 @@ int regmap_read(struct regmap *map, unsigned int reg, unsigned int *val) { int ret; + if (reg % map->reg_stride) + return -EINVAL; + map->lock(map); ret = _regmap_read(map, reg, val); @@ -784,6 +800,8 @@ int regmap_raw_read(struct regmap *map, unsigned int reg, void *val, if (val_len % map->format.val_bytes) return -EINVAL; + if (reg % map->reg_stride) + return -EINVAL; map->lock(map); @@ -797,7 +815,8 @@ int regmap_raw_read(struct regmap *map, unsigned int reg, void *val, * cost as we expect to hit the cache. */ for (i = 0; i < val_count; i++) { - ret = _regmap_read(map, reg + i, &v); + ret = _regmap_read(map, reg + (i * map->reg_stride), + &v); if (ret != 0) goto out; @@ -832,6 +851,8 @@ int regmap_bulk_read(struct regmap *map, unsigned int reg, void *val, if (!map->format.parse_val) return -EINVAL; + if (reg % map->reg_stride) + return -EINVAL; if (vol || map->cache_type == REGCACHE_NONE) { ret = regmap_raw_read(map, reg, val, val_bytes * val_count); @@ -842,7 +863,8 @@ int regmap_bulk_read(struct regmap *map, unsigned int reg, void *val, map->format.parse_val(val + i); } else { for (i = 0; i < val_count; i++) { - ret = regmap_read(map, reg + i, val + (i * val_bytes)); + ret = regmap_read(map, reg + (i * map->reg_stride), + val + (i * val_bytes)); if (ret != 0) return ret; } diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 680ddd7de60e..0258bcd6258d 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -50,6 +50,9 @@ struct reg_default { * register regions. * * @reg_bits: Number of bits in a register address, mandatory. + * @reg_stride: The register address stride. Valid register addresses are a + * multiple of this value. If set to 0, a value of 1 will be + * used. * @pad_bits: Number of bits of padding between register and value. * @val_bits: Number of bits in a register value, mandatory. * @@ -83,6 +86,7 @@ struct regmap_config { const char *name; int reg_bits; + int reg_stride; int pad_bits; int val_bits; -- cgit v1.2.3 From 56806555de5485d6786bf0f8df01b8ed9fc5d006 Mon Sep 17 00:00:00 2001 From: Stephen Warren Date: Tue, 10 Apr 2012 23:37:22 -0600 Subject: regmap: fix compile errors in regmap-irq.c due to stride changes Commit f01ee60fffa4 ("regmap: implement register striding") caused the compile errors below. Fix them. drivers/base/regmap/regmap-irq.c: In function 'regmap_irq_sync_unlock': drivers/base/regmap/regmap-irq.c:62:12: error: 'map' undeclared (first use in this function) drivers/base/regmap/regmap-irq.c:62:12: note: each undeclared identifier is reported only once for each function it appears in drivers/base/regmap/regmap-irq.c: In function 'regmap_irq_enable': drivers/base/regmap/regmap-irq.c:77:37: error: 'map' undeclared (first use in this function) drivers/base/regmap/regmap-irq.c: In function 'regmap_irq_disable': drivers/base/regmap/regmap-irq.c:85:37: error: 'map' undeclared (first use in this function) Signed-off-by: Stephen Warren Signed-off-by: Mark Brown --- drivers/base/regmap/regmap-irq.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'drivers/base') diff --git a/drivers/base/regmap/regmap-irq.c b/drivers/base/regmap/regmap-irq.c index 56b8136eb36a..fc69d29d272a 100644 --- a/drivers/base/regmap/regmap-irq.c +++ b/drivers/base/regmap/regmap-irq.c @@ -50,6 +50,7 @@ static void regmap_irq_lock(struct irq_data *data) static void regmap_irq_sync_unlock(struct irq_data *data) { struct regmap_irq_chip_data *d = irq_data_get_irq_chip_data(data); + struct regmap *map = d->map; int i, ret; /* @@ -59,7 +60,7 @@ static void regmap_irq_sync_unlock(struct irq_data *data) */ for (i = 0; i < d->chip->num_regs; i++) { ret = regmap_update_bits(d->map, d->chip->mask_base + - (i * map->map->reg_stride), + (i * map->reg_stride), d->mask_buf_def[i], d->mask_buf[i]); if (ret != 0) dev_err(d->map->dev, "Failed to sync masks in %x\n", @@ -72,6 +73,7 @@ static void regmap_irq_sync_unlock(struct irq_data *data) static void regmap_irq_enable(struct irq_data *data) { struct regmap_irq_chip_data *d = irq_data_get_irq_chip_data(data); + struct regmap *map = d->map; const struct regmap_irq *irq_data = irq_to_regmap_irq(d, data->irq); d->mask_buf[irq_data->reg_offset / map->reg_stride] &= ~irq_data->mask; @@ -80,6 +82,7 @@ static void regmap_irq_enable(struct irq_data *data) static void regmap_irq_disable(struct irq_data *data) { struct regmap_irq_chip_data *d = irq_data_get_irq_chip_data(data); + struct regmap *map = d->map; const struct regmap_irq *irq_data = irq_to_regmap_irq(d, data->irq); d->mask_buf[irq_data->reg_offset / map->reg_stride] |= irq_data->mask; -- cgit v1.2.3 From 02fbe5e61df654b2b39a1ddc1ae912c9e14c3ddd Mon Sep 17 00:00:00 2001 From: Peter Korsgaard Date: Tue, 17 Apr 2012 12:13:18 +0200 Subject: devtmpfs: fix 'the the' typo Signed-off-by: Peter Korsgaard Signed-off-by: Greg Kroah-Hartman --- drivers/base/devtmpfs.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c index 8493536ea55b..765c3a28077a 100644 --- a/drivers/base/devtmpfs.c +++ b/drivers/base/devtmpfs.c @@ -7,9 +7,9 @@ * devtmpfs, a tmpfs-based filesystem is created. Every driver-core * device which requests a device node, will add a node in this * filesystem. - * By default, all devices are named after the the name of the - * device, owned by root and have a default mode of 0600. Subsystems - * can overwrite the default setting if needed. + * By default, all devices are named after the name of the device, + * owned by root and have a default mode of 0600. Subsystems can + * overwrite the default setting if needed. */ #include -- cgit v1.2.3 From 0d4e293ca8271cc7d7ac1423afe5ceb7d213d0fc Mon Sep 17 00:00:00 2001 From: Peter Korsgaard Date: Tue, 17 Apr 2012 12:12:57 +0200 Subject: core.c: fix 'the the' typo Signed-off-by: Peter Korsgaard Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/core.c b/drivers/base/core.c index e28ce9898af4..6cb25f1511df 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -878,8 +878,8 @@ EXPORT_SYMBOL_GPL(dev_set_name); * to NULL prevents an entry from being created. class->dev_kobj must * be set (or cleared) before any devices are registered to the class * otherwise device_create_sys_dev_entry() and - * device_remove_sys_dev_entry() will disagree about the the presence - * of the link. + * device_remove_sys_dev_entry() will disagree about the presence of + * the link. */ static struct kobject *device_to_dev_kobj(struct device *dev) { -- cgit v1.2.3 From efb4df82ca97b3c1cadd03bb98bce7a7e206fa63 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 17 Apr 2012 17:03:30 -0700 Subject: driver core: fix dma-buf.c kernel-doc warnings Fix kernel-doc warnings in dma-buf.c: Warning(drivers/base/dma-buf.c:305): No description found for parameter 'dmabuf' Warning(drivers/base/dma-buf.c:305): Excess function parameter 'dma_buf' description in 'dma_buf_begin_cpu_access' Warning(drivers/base/dma-buf.c:332): No description found for parameter 'dmabuf' Warning(drivers/base/dma-buf.c:332): Excess function parameter 'dma_buf' description in 'dma_buf_end_cpu_access' Warning(drivers/base/dma-buf.c:350): No description found for parameter 'dmabuf' Warning(drivers/base/dma-buf.c:350): Excess function parameter 'dma_buf' description in 'dma_buf_kmap_atomic' Warning(drivers/base/dma-buf.c:367): No description found for parameter 'dmabuf' Warning(drivers/base/dma-buf.c:367): Excess function parameter 'dma_buf' description in 'dma_buf_kunmap_atomic' Warning(drivers/base/dma-buf.c:385): No description found for parameter 'dmabuf' Warning(drivers/base/dma-buf.c:385): Excess function parameter 'dma_buf' description in 'dma_buf_kmap' Warning(drivers/base/dma-buf.c:402): No description found for parameter 'dmabuf' Warning(drivers/base/dma-buf.c:402): Excess function parameter 'dma_buf' description in 'dma_buf_kunmap' Signed-off-by: Randy Dunlap Signed-off-by: Greg Kroah-Hartman --- drivers/base/dma-buf.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/dma-buf.c b/drivers/base/dma-buf.c index 07cbbc6fddb4..05c64c11bad2 100644 --- a/drivers/base/dma-buf.c +++ b/drivers/base/dma-buf.c @@ -293,7 +293,7 @@ EXPORT_SYMBOL_GPL(dma_buf_unmap_attachment); * cpu in the kernel context. Calls begin_cpu_access to allow exporter-specific * preparations. Coherency is only guaranteed in the specified range for the * specified access direction. - * @dma_buf: [in] buffer to prepare cpu access for. + * @dmabuf: [in] buffer to prepare cpu access for. * @start: [in] start of range for cpu access. * @len: [in] length of range for cpu access. * @direction: [in] length of range for cpu access. @@ -320,7 +320,7 @@ EXPORT_SYMBOL_GPL(dma_buf_begin_cpu_access); * cpu in the kernel context. Calls end_cpu_access to allow exporter-specific * actions. Coherency is only guaranteed in the specified range for the * specified access direction. - * @dma_buf: [in] buffer to complete cpu access for. + * @dmabuf: [in] buffer to complete cpu access for. * @start: [in] start of range for cpu access. * @len: [in] length of range for cpu access. * @direction: [in] length of range for cpu access. @@ -340,7 +340,7 @@ EXPORT_SYMBOL_GPL(dma_buf_end_cpu_access); /** * dma_buf_kmap_atomic - Map a page of the buffer object into kernel address * space. The same restrictions as for kmap_atomic and friends apply. - * @dma_buf: [in] buffer to map page from. + * @dmabuf: [in] buffer to map page from. * @page_num: [in] page in PAGE_SIZE units to map. * * This call must always succeed, any necessary preparations that might fail @@ -356,7 +356,7 @@ EXPORT_SYMBOL_GPL(dma_buf_kmap_atomic); /** * dma_buf_kunmap_atomic - Unmap a page obtained by dma_buf_kmap_atomic. - * @dma_buf: [in] buffer to unmap page from. + * @dmabuf: [in] buffer to unmap page from. * @page_num: [in] page in PAGE_SIZE units to unmap. * @vaddr: [in] kernel space pointer obtained from dma_buf_kmap_atomic. * @@ -375,7 +375,7 @@ EXPORT_SYMBOL_GPL(dma_buf_kunmap_atomic); /** * dma_buf_kmap - Map a page of the buffer object into kernel address space. The * same restrictions as for kmap and friends apply. - * @dma_buf: [in] buffer to map page from. + * @dmabuf: [in] buffer to map page from. * @page_num: [in] page in PAGE_SIZE units to map. * * This call must always succeed, any necessary preparations that might fail @@ -391,7 +391,7 @@ EXPORT_SYMBOL_GPL(dma_buf_kmap); /** * dma_buf_kunmap - Unmap a page obtained by dma_buf_kmap. - * @dma_buf: [in] buffer to unmap page from. + * @dmabuf: [in] buffer to unmap page from. * @page_num: [in] page in PAGE_SIZE units to unmap. * @vaddr: [in] kernel space pointer obtained from dma_buf_kmap. * -- cgit v1.2.3 From 97ec448aeadff55234368a89c4a07a7ef290a084 Mon Sep 17 00:00:00 2001 From: H Hartley Sweeten Date: Mon, 16 Apr 2012 18:14:10 -0700 Subject: drivers/base/bus.c: local variables should not be exposed globally The variable 'system_kset' is only referenced in this file and should be marked static to prevent it from being exposed globally. This quiets the sparse waring: warning: symbol 'system_kset' was not declared. Should it be static? Also, remove the comment since drivers/base/sys.c has now been deleted. Signed-off-by: H Hartley Sweeten Cc: Greg Kroah-Hartman Signed-off-by: Greg Kroah-Hartman --- drivers/base/bus.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/bus.c b/drivers/base/bus.c index 26a06b801b5b..2bcef657a60c 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -21,8 +21,7 @@ #include "power/power.h" /* /sys/devices/system */ -/* FIXME: make static after drivers/base/sys.c is deleted */ -struct kset *system_kset; +static struct kset *system_kset; #define to_bus_attr(_attr) container_of(_attr, struct bus_attribute, attr) -- cgit v1.2.3 From a15d49fd3094cff90e5410ca454a870e0a722fe1 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Mon, 16 Apr 2012 15:06:25 +0200 Subject: driver core: check start node in klist_iter_init_node klist_iter_init_node() takes a node as a start argument. However, this node might not be valid anymore. This patch updates the klist_iter_init_node() and dependent functions to return an error if so. All calling functions have been audited to check for a return code here. Signed-off-by: Hannes Reinecke Cc: Greg Kroah-Hartmann Cc: Kay Sievers Cc: Stable Kernel Cc: Linux Kernel Signed-off-by: Greg Kroah-Hartman --- drivers/base/bus.c | 46 +++++++++++++++++++++++++++++----------------- drivers/base/class.c | 32 ++++++++++++++++++++------------ drivers/base/driver.c | 18 +++++++++++------- include/linux/device.h | 10 +++++----- include/linux/klist.h | 2 +- lib/klist.c | 14 ++++++++++---- 6 files changed, 76 insertions(+), 46 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/bus.c b/drivers/base/bus.c index 2bcef657a60c..76aed01a8b2c 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -296,11 +296,13 @@ int bus_for_each_dev(struct bus_type *bus, struct device *start, if (!bus) return -EINVAL; - klist_iter_init_node(&bus->p->klist_devices, &i, - (start ? &start->p->knode_bus : NULL)); - while ((dev = next_device(&i)) && !error) - error = fn(dev, data); - klist_iter_exit(&i); + error = klist_iter_init_node(&bus->p->klist_devices, &i, + (start ? &start->p->knode_bus : NULL)); + if (!error) { + while ((dev = next_device(&i)) && !error) + error = fn(dev, data); + klist_iter_exit(&i); + } return error; } EXPORT_SYMBOL_GPL(bus_for_each_dev); @@ -330,8 +332,10 @@ struct device *bus_find_device(struct bus_type *bus, if (!bus) return NULL; - klist_iter_init_node(&bus->p->klist_devices, &i, - (start ? &start->p->knode_bus : NULL)); + if (klist_iter_init_node(&bus->p->klist_devices, &i, + (start ? &start->p->knode_bus : NULL)) < 0) + return NULL; + while ((dev = next_device(&i))) if (match(dev, data) && get_device(dev)) break; @@ -384,7 +388,9 @@ struct device *subsys_find_device_by_id(struct bus_type *subsys, unsigned int id return NULL; if (hint) { - klist_iter_init_node(&subsys->p->klist_devices, &i, &hint->p->knode_bus); + if (klist_iter_init_node(&subsys->p->klist_devices, &i, + &hint->p->knode_bus) < 0) + return NULL; dev = next_device(&i); if (dev && dev->id == id && get_device(dev)) { klist_iter_exit(&i); @@ -446,11 +452,13 @@ int bus_for_each_drv(struct bus_type *bus, struct device_driver *start, if (!bus) return -EINVAL; - klist_iter_init_node(&bus->p->klist_drivers, &i, - start ? &start->p->knode_bus : NULL); - while ((drv = next_driver(&i)) && !error) - error = fn(drv, data); - klist_iter_exit(&i); + error = klist_iter_init_node(&bus->p->klist_drivers, &i, + start ? &start->p->knode_bus : NULL); + if (!error) { + while ((drv = next_driver(&i)) && !error) + error = fn(drv, data); + klist_iter_exit(&i); + } return error; } EXPORT_SYMBOL_GPL(bus_for_each_drv); @@ -1111,15 +1119,19 @@ EXPORT_SYMBOL_GPL(bus_sort_breadthfirst); * otherwise if it is NULL, the iteration starts at the beginning of * the list. */ -void subsys_dev_iter_init(struct subsys_dev_iter *iter, struct bus_type *subsys, - struct device *start, const struct device_type *type) +int subsys_dev_iter_init(struct subsys_dev_iter *iter, struct bus_type *subsys, + struct device *start, const struct device_type *type) { struct klist_node *start_knode = NULL; + int error; if (start) start_knode = &start->p->knode_bus; - klist_iter_init_node(&subsys->p->klist_devices, &iter->ki, start_knode); - iter->type = type; + error = klist_iter_init_node(&subsys->p->klist_devices, &iter->ki, + start_knode); + if (!error) + iter->type = type; + return error; } EXPORT_SYMBOL_GPL(subsys_dev_iter_init); diff --git a/drivers/base/class.c b/drivers/base/class.c index 03243d4002fd..23dbc661d4a0 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -301,15 +301,20 @@ void class_destroy(struct class *cls) * otherwise if it is NULL, the iteration starts at the beginning of * the list. */ -void class_dev_iter_init(struct class_dev_iter *iter, struct class *class, - struct device *start, const struct device_type *type) +int class_dev_iter_init(struct class_dev_iter *iter, struct class *class, + struct device *start, const struct device_type *type) { struct klist_node *start_knode = NULL; + int error; if (start) start_knode = &start->knode_class; - klist_iter_init_node(&class->p->klist_devices, &iter->ki, start_knode); - iter->type = type; + error = klist_iter_init_node(&class->p->klist_devices, &iter->ki, + start_knode); + if (!error) + iter->type = type; + + return error; } EXPORT_SYMBOL_GPL(class_dev_iter_init); @@ -387,14 +392,15 @@ int class_for_each_device(struct class *class, struct device *start, return -EINVAL; } - class_dev_iter_init(&iter, class, start, NULL); - while ((dev = class_dev_iter_next(&iter))) { - error = fn(dev, data); - if (error) - break; + error = class_dev_iter_init(&iter, class, start, NULL); + if (!error) { + while ((dev = class_dev_iter_next(&iter))) { + error = fn(dev, data); + if (error) + break; + } + class_dev_iter_exit(&iter); } - class_dev_iter_exit(&iter); - return error; } EXPORT_SYMBOL_GPL(class_for_each_device); @@ -434,7 +440,9 @@ struct device *class_find_device(struct class *class, struct device *start, return NULL; } - class_dev_iter_init(&iter, class, start, NULL); + if (class_dev_iter_init(&iter, class, start, NULL) < 0) + return NULL; + while ((dev = class_dev_iter_next(&iter))) { if (match(dev, data)) { get_device(dev); diff --git a/drivers/base/driver.c b/drivers/base/driver.c index 3ec3896c83a6..16f6dd2c4403 100644 --- a/drivers/base/driver.c +++ b/drivers/base/driver.c @@ -49,11 +49,13 @@ int driver_for_each_device(struct device_driver *drv, struct device *start, if (!drv) return -EINVAL; - klist_iter_init_node(&drv->p->klist_devices, &i, - start ? &start->p->knode_driver : NULL); - while ((dev = next_device(&i)) && !error) - error = fn(dev, data); - klist_iter_exit(&i); + error = klist_iter_init_node(&drv->p->klist_devices, &i, + start ? &start->p->knode_driver : NULL); + if (!error) { + while ((dev = next_device(&i)) && !error) + error = fn(dev, data); + klist_iter_exit(&i); + } return error; } EXPORT_SYMBOL_GPL(driver_for_each_device); @@ -83,8 +85,10 @@ struct device *driver_find_device(struct device_driver *drv, if (!drv) return NULL; - klist_iter_init_node(&drv->p->klist_devices, &i, - (start ? &start->p->knode_driver : NULL)); + if (klist_iter_init_node(&drv->p->klist_devices, &i, + (start ? &start->p->knode_driver : NULL)) < 0) + return NULL; + while ((dev = next_device(&i))) if (match(dev, data) && get_device(dev)) break; diff --git a/include/linux/device.h b/include/linux/device.h index 5ad17cccdd71..50429b911b21 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -128,7 +128,7 @@ struct subsys_dev_iter { struct klist_iter ki; const struct device_type *type; }; -void subsys_dev_iter_init(struct subsys_dev_iter *iter, +int subsys_dev_iter_init(struct subsys_dev_iter *iter, struct bus_type *subsys, struct device *start, const struct device_type *type); @@ -380,10 +380,10 @@ int class_compat_create_link(struct class_compat *cls, struct device *dev, void class_compat_remove_link(struct class_compat *cls, struct device *dev, struct device *device_link); -extern void class_dev_iter_init(struct class_dev_iter *iter, - struct class *class, - struct device *start, - const struct device_type *type); +extern int class_dev_iter_init(struct class_dev_iter *iter, + struct class *class, + struct device *start, + const struct device_type *type); extern struct device *class_dev_iter_next(struct class_dev_iter *iter); extern void class_dev_iter_exit(struct class_dev_iter *iter); diff --git a/include/linux/klist.h b/include/linux/klist.h index a370ce57cf1d..9f633230f189 100644 --- a/include/linux/klist.h +++ b/include/linux/klist.h @@ -60,7 +60,7 @@ struct klist_iter { extern void klist_iter_init(struct klist *k, struct klist_iter *i); -extern void klist_iter_init_node(struct klist *k, struct klist_iter *i, +extern int klist_iter_init_node(struct klist *k, struct klist_iter *i, struct klist_node *n); extern void klist_iter_exit(struct klist_iter *i); extern struct klist_node *klist_next(struct klist_iter *i); diff --git a/lib/klist.c b/lib/klist.c index 0874e41609a6..a2741a7d9784 100644 --- a/lib/klist.c +++ b/lib/klist.c @@ -278,13 +278,19 @@ EXPORT_SYMBOL_GPL(klist_node_attached); * Similar to klist_iter_init(), but starts the action off with @n, * instead of with the list head. */ -void klist_iter_init_node(struct klist *k, struct klist_iter *i, - struct klist_node *n) +int klist_iter_init_node(struct klist *k, struct klist_iter *i, + struct klist_node *n) { + if (n) { + kref_get(&n->n_ref); + if (!n->n_klist) { + kref_put(&n->n_ref); + return -ENODEV; + } + } i->i_klist = k; i->i_cur = n; - if (n) - kref_get(&n->n_ref); + return 0; } EXPORT_SYMBOL_GPL(klist_iter_init_node); -- cgit v1.2.3 From 7cd9c9bb57476167e83b7780dbc06d1dd601789d Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 19 Apr 2012 19:17:30 -0700 Subject: Revert "driver core: check start node in klist_iter_init_node" This reverts commit a15d49fd3094cff90e5410ca454a870e0a722fe1 as that patch broke the build. Cc: Hannes Reinecke Reported-by: Stephen Rothwell Signed-off-by: Greg Kroah-Hartman --- drivers/base/bus.c | 46 +++++++++++++++++----------------------------- drivers/base/class.c | 32 ++++++++++++-------------------- drivers/base/driver.c | 18 +++++++----------- include/linux/device.h | 10 +++++----- include/linux/klist.h | 2 +- lib/klist.c | 14 ++++---------- 6 files changed, 46 insertions(+), 76 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/bus.c b/drivers/base/bus.c index 76aed01a8b2c..2bcef657a60c 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -296,13 +296,11 @@ int bus_for_each_dev(struct bus_type *bus, struct device *start, if (!bus) return -EINVAL; - error = klist_iter_init_node(&bus->p->klist_devices, &i, - (start ? &start->p->knode_bus : NULL)); - if (!error) { - while ((dev = next_device(&i)) && !error) - error = fn(dev, data); - klist_iter_exit(&i); - } + klist_iter_init_node(&bus->p->klist_devices, &i, + (start ? &start->p->knode_bus : NULL)); + while ((dev = next_device(&i)) && !error) + error = fn(dev, data); + klist_iter_exit(&i); return error; } EXPORT_SYMBOL_GPL(bus_for_each_dev); @@ -332,10 +330,8 @@ struct device *bus_find_device(struct bus_type *bus, if (!bus) return NULL; - if (klist_iter_init_node(&bus->p->klist_devices, &i, - (start ? &start->p->knode_bus : NULL)) < 0) - return NULL; - + klist_iter_init_node(&bus->p->klist_devices, &i, + (start ? &start->p->knode_bus : NULL)); while ((dev = next_device(&i))) if (match(dev, data) && get_device(dev)) break; @@ -388,9 +384,7 @@ struct device *subsys_find_device_by_id(struct bus_type *subsys, unsigned int id return NULL; if (hint) { - if (klist_iter_init_node(&subsys->p->klist_devices, &i, - &hint->p->knode_bus) < 0) - return NULL; + klist_iter_init_node(&subsys->p->klist_devices, &i, &hint->p->knode_bus); dev = next_device(&i); if (dev && dev->id == id && get_device(dev)) { klist_iter_exit(&i); @@ -452,13 +446,11 @@ int bus_for_each_drv(struct bus_type *bus, struct device_driver *start, if (!bus) return -EINVAL; - error = klist_iter_init_node(&bus->p->klist_drivers, &i, - start ? &start->p->knode_bus : NULL); - if (!error) { - while ((drv = next_driver(&i)) && !error) - error = fn(drv, data); - klist_iter_exit(&i); - } + klist_iter_init_node(&bus->p->klist_drivers, &i, + start ? &start->p->knode_bus : NULL); + while ((drv = next_driver(&i)) && !error) + error = fn(drv, data); + klist_iter_exit(&i); return error; } EXPORT_SYMBOL_GPL(bus_for_each_drv); @@ -1119,19 +1111,15 @@ EXPORT_SYMBOL_GPL(bus_sort_breadthfirst); * otherwise if it is NULL, the iteration starts at the beginning of * the list. */ -int subsys_dev_iter_init(struct subsys_dev_iter *iter, struct bus_type *subsys, - struct device *start, const struct device_type *type) +void subsys_dev_iter_init(struct subsys_dev_iter *iter, struct bus_type *subsys, + struct device *start, const struct device_type *type) { struct klist_node *start_knode = NULL; - int error; if (start) start_knode = &start->p->knode_bus; - error = klist_iter_init_node(&subsys->p->klist_devices, &iter->ki, - start_knode); - if (!error) - iter->type = type; - return error; + klist_iter_init_node(&subsys->p->klist_devices, &iter->ki, start_knode); + iter->type = type; } EXPORT_SYMBOL_GPL(subsys_dev_iter_init); diff --git a/drivers/base/class.c b/drivers/base/class.c index 23dbc661d4a0..03243d4002fd 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -301,20 +301,15 @@ void class_destroy(struct class *cls) * otherwise if it is NULL, the iteration starts at the beginning of * the list. */ -int class_dev_iter_init(struct class_dev_iter *iter, struct class *class, - struct device *start, const struct device_type *type) +void class_dev_iter_init(struct class_dev_iter *iter, struct class *class, + struct device *start, const struct device_type *type) { struct klist_node *start_knode = NULL; - int error; if (start) start_knode = &start->knode_class; - error = klist_iter_init_node(&class->p->klist_devices, &iter->ki, - start_knode); - if (!error) - iter->type = type; - - return error; + klist_iter_init_node(&class->p->klist_devices, &iter->ki, start_knode); + iter->type = type; } EXPORT_SYMBOL_GPL(class_dev_iter_init); @@ -392,15 +387,14 @@ int class_for_each_device(struct class *class, struct device *start, return -EINVAL; } - error = class_dev_iter_init(&iter, class, start, NULL); - if (!error) { - while ((dev = class_dev_iter_next(&iter))) { - error = fn(dev, data); - if (error) - break; - } - class_dev_iter_exit(&iter); + class_dev_iter_init(&iter, class, start, NULL); + while ((dev = class_dev_iter_next(&iter))) { + error = fn(dev, data); + if (error) + break; } + class_dev_iter_exit(&iter); + return error; } EXPORT_SYMBOL_GPL(class_for_each_device); @@ -440,9 +434,7 @@ struct device *class_find_device(struct class *class, struct device *start, return NULL; } - if (class_dev_iter_init(&iter, class, start, NULL) < 0) - return NULL; - + class_dev_iter_init(&iter, class, start, NULL); while ((dev = class_dev_iter_next(&iter))) { if (match(dev, data)) { get_device(dev); diff --git a/drivers/base/driver.c b/drivers/base/driver.c index 16f6dd2c4403..3ec3896c83a6 100644 --- a/drivers/base/driver.c +++ b/drivers/base/driver.c @@ -49,13 +49,11 @@ int driver_for_each_device(struct device_driver *drv, struct device *start, if (!drv) return -EINVAL; - error = klist_iter_init_node(&drv->p->klist_devices, &i, - start ? &start->p->knode_driver : NULL); - if (!error) { - while ((dev = next_device(&i)) && !error) - error = fn(dev, data); - klist_iter_exit(&i); - } + klist_iter_init_node(&drv->p->klist_devices, &i, + start ? &start->p->knode_driver : NULL); + while ((dev = next_device(&i)) && !error) + error = fn(dev, data); + klist_iter_exit(&i); return error; } EXPORT_SYMBOL_GPL(driver_for_each_device); @@ -85,10 +83,8 @@ struct device *driver_find_device(struct device_driver *drv, if (!drv) return NULL; - if (klist_iter_init_node(&drv->p->klist_devices, &i, - (start ? &start->p->knode_driver : NULL)) < 0) - return NULL; - + klist_iter_init_node(&drv->p->klist_devices, &i, + (start ? &start->p->knode_driver : NULL)); while ((dev = next_device(&i))) if (match(dev, data) && get_device(dev)) break; diff --git a/include/linux/device.h b/include/linux/device.h index 50429b911b21..5ad17cccdd71 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -128,7 +128,7 @@ struct subsys_dev_iter { struct klist_iter ki; const struct device_type *type; }; -int subsys_dev_iter_init(struct subsys_dev_iter *iter, +void subsys_dev_iter_init(struct subsys_dev_iter *iter, struct bus_type *subsys, struct device *start, const struct device_type *type); @@ -380,10 +380,10 @@ int class_compat_create_link(struct class_compat *cls, struct device *dev, void class_compat_remove_link(struct class_compat *cls, struct device *dev, struct device *device_link); -extern int class_dev_iter_init(struct class_dev_iter *iter, - struct class *class, - struct device *start, - const struct device_type *type); +extern void class_dev_iter_init(struct class_dev_iter *iter, + struct class *class, + struct device *start, + const struct device_type *type); extern struct device *class_dev_iter_next(struct class_dev_iter *iter); extern void class_dev_iter_exit(struct class_dev_iter *iter); diff --git a/include/linux/klist.h b/include/linux/klist.h index 9f633230f189..a370ce57cf1d 100644 --- a/include/linux/klist.h +++ b/include/linux/klist.h @@ -60,7 +60,7 @@ struct klist_iter { extern void klist_iter_init(struct klist *k, struct klist_iter *i); -extern int klist_iter_init_node(struct klist *k, struct klist_iter *i, +extern void klist_iter_init_node(struct klist *k, struct klist_iter *i, struct klist_node *n); extern void klist_iter_exit(struct klist_iter *i); extern struct klist_node *klist_next(struct klist_iter *i); diff --git a/lib/klist.c b/lib/klist.c index a2741a7d9784..0874e41609a6 100644 --- a/lib/klist.c +++ b/lib/klist.c @@ -278,19 +278,13 @@ EXPORT_SYMBOL_GPL(klist_node_attached); * Similar to klist_iter_init(), but starts the action off with @n, * instead of with the list head. */ -int klist_iter_init_node(struct klist *k, struct klist_iter *i, - struct klist_node *n) +void klist_iter_init_node(struct klist *k, struct klist_iter *i, + struct klist_node *n) { - if (n) { - kref_get(&n->n_ref); - if (!n->n_klist) { - kref_put(&n->n_ref); - return -ENODEV; - } - } i->i_klist = k; i->i_cur = n; - return 0; + if (n) + kref_get(&n->n_ref); } EXPORT_SYMBOL_GPL(klist_iter_init_node); -- cgit v1.2.3 From 9169c01236ab29ce55c93aaf22ec6ecc65c46d1a Mon Sep 17 00:00:00 2001 From: yan Date: Fri, 20 Apr 2012 21:08:45 +0800 Subject: drivers/base/core.c: Fix a typo in comment Signed-off-by: YanHong Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/base') diff --git a/drivers/base/core.c b/drivers/base/core.c index 6cb25f1511df..33461ec35d8f 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -65,7 +65,7 @@ static inline int device_is_not_partition(struct device *dev) * @dev: struct device to get the name of * * Will return the device's driver's name if it is bound to a device. If - * the device is not bound to a device, it will return the name of the bus + * the device is not bound to a driver, it will return the name of the bus * it is attached to. If it is not attached to a bus either, an empty * string will be returned. */ -- cgit v1.2.3 From f298536728d02c19f11bda8d712ff61d767bab32 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 30 Apr 2012 21:25:05 +0100 Subject: regmap: Cache single values read from the chip If we don't have a cached value for a register and we can cache it then when we do a read a value we should add it to the cache to save rereading it later on. Do this for single register reads, for block reads the code would be a little more complex and this covers most practical usage. Signed-off-by: Mark Brown --- drivers/base/regmap/regmap.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'drivers/base') diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 178989a8949e..3e551223f4df 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -698,6 +698,9 @@ static int _regmap_read(struct regmap *map, unsigned int reg, trace_regmap_reg_read(map->dev, reg, *val); } + if (ret == 0 && !map->cache_bypass) + regcache_write(map, reg, *val); + return ret; } -- cgit v1.2.3 From 2e33caf16f7a1903d226ef7f9f5ec6a234fee18e Mon Sep 17 00:00:00 2001 From: Ashish Jangam Date: Mon, 30 Apr 2012 23:23:40 +0100 Subject: regmap: Converts group operation into single read write operations Some devices does not support bulk read and write operations, for them we have series of single write and read operations. Signed-off-by: Anthony Olech Signed-off-by: Ashish Jangam [Fixed coding style, don't check use_single_rw before assign --broonie ] Signed-off-by: Mark Brown --- drivers/base/regmap/internal.h | 3 +++ drivers/base/regmap/regmap.c | 40 ++++++++++++++++++++++++++++++++++++---- include/linux/regmap.h | 5 +++++ 3 files changed, 44 insertions(+), 4 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h index d92e9b1cb83c..2eb719704885 100644 --- a/drivers/base/regmap/internal.h +++ b/drivers/base/regmap/internal.h @@ -91,6 +91,9 @@ struct regmap { struct reg_default *patch; int patch_regs; + + /* if set, converts bulk rw to single rw */ + bool use_single_rw; }; struct regcache_ops { diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 8a25006b2a4d..0a05a706e141 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -247,6 +247,7 @@ struct regmap *regmap_init(struct device *dev, map->reg_stride = config->reg_stride; else map->reg_stride = 1; + map->use_single_rw = config->use_single_rw; map->dev = dev; map->bus = bus; map->bus_context = bus_context; @@ -686,7 +687,22 @@ int regmap_bulk_write(struct regmap *map, unsigned int reg, const void *val, for (i = 0; i < val_count * val_bytes; i += val_bytes) map->format.parse_val(wval + i); } - ret = _regmap_raw_write(map, reg, wval, val_bytes * val_count); + /* + * Some devices does not support bulk write, for + * them we have a series of single write operations. + */ + if (map->use_single_rw) { + for (i = 0; i < val_count; i++) { + ret = regmap_raw_write(map, + reg + (i * map->reg_stride), + val + (i * val_bytes), + val_bytes); + if (ret != 0) + return ret; + } + } else { + ret = _regmap_raw_write(map, reg, wval, val_bytes * val_count); + } if (val_bytes != 1) kfree(wval); @@ -855,9 +871,25 @@ int regmap_bulk_read(struct regmap *map, unsigned int reg, void *val, return -EINVAL; if (vol || map->cache_type == REGCACHE_NONE) { - ret = regmap_raw_read(map, reg, val, val_bytes * val_count); - if (ret != 0) - return ret; + /* + * Some devices does not support bulk read, for + * them we have a series of single read operations. + */ + if (map->use_single_rw) { + for (i = 0; i < val_count; i++) { + ret = regmap_raw_read(map, + reg + (i * map->reg_stride), + val + (i * val_bytes), + val_bytes); + if (ret != 0) + return ret; + } + } else { + ret = regmap_raw_read(map, reg, val, + val_bytes * val_count); + if (ret != 0) + return ret; + } for (i = 0; i < val_count * val_bytes; i += val_bytes) map->format.parse_val(val + i); diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 0258bcd6258d..ae797b142aa8 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -76,6 +76,9 @@ struct reg_default { * @write_flag_mask: Mask to be set in the top byte of the register when doing * a write. If both read_flag_mask and write_flag_mask are * empty the regmap_bus default masks are used. + * @use_single_rw: If set, converts the bulk read and write operations into + * a series of single read and write operations. This is useful + * for device that does not support bulk read and write. * * @cache_type: The actual cache type. * @reg_defaults_raw: Power on reset values for registers (for use with @@ -104,6 +107,8 @@ struct regmap_config { u8 read_flag_mask; u8 write_flag_mask; + + bool use_single_rw; }; typedef int (*regmap_hw_write)(void *context, const void *data, -- cgit v1.2.3 From 7a6476143270d947924f5bbbc124accb0e558bf4 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 30 Apr 2012 23:26:32 +0100 Subject: regmap: Devices using format_write don't support bulk operations Set the use_single_rw flag for devices that use format_write() since format_write() doesn't support any form of block operation. Signed-off-by: Mark Brown --- drivers/base/regmap/regmap.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'drivers/base') diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 0a05a706e141..fcd69ff695d5 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -341,6 +341,9 @@ struct regmap *regmap_init(struct device *dev, break; } + if (map->format.format_write) + map->use_single_rw = true; + if (!map->format.format_write && !(map->format.format_reg && map->format.format_val)) goto err_map; -- cgit v1.2.3 From 52d136cc2cf6659ee247dbcc88c9e7bd7428ad06 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 29 Apr 2012 22:52:19 +0200 Subject: PM / Sleep: Look for wakeup events in later stages of device suspend Currently, the device suspend code in drivers/base/power/main.c only checks if there have been any wakeup events, and therefore the ongoing system transition to a sleep state should be aborted, during the first (i.e. "suspend") device suspend phase. However, wakeup events may be reported later as well, so it's reasonable to look for them in the in the subsequent (i.e. "late suspend" and "suspend noirq") phases. Signed-off-by: Rafael J. Wysocki Acked-by: Greg Kroah-Hartman --- drivers/base/power/main.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'drivers/base') diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index b462c0e341cb..e0fb5b0435a3 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -889,6 +889,11 @@ static int dpm_suspend_noirq(pm_message_t state) if (!list_empty(&dev->power.entry)) list_move(&dev->power.entry, &dpm_noirq_list); put_device(dev); + + if (pm_wakeup_pending()) { + error = -EBUSY; + break; + } } mutex_unlock(&dpm_list_mtx); if (error) @@ -962,6 +967,11 @@ static int dpm_suspend_late(pm_message_t state) if (!list_empty(&dev->power.entry)) list_move(&dev->power.entry, &dpm_late_early_list); put_device(dev); + + if (pm_wakeup_pending()) { + error = -EBUSY; + break; + } } mutex_unlock(&dpm_list_mtx); if (error) -- cgit v1.2.3 From 60af1066913162c5dd13fad3b872a67b1eb7da0f Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 29 Apr 2012 22:52:34 +0200 Subject: PM / Sleep: Use wait queue to signal "no wakeup events in progress" The current wakeup source deactivation code doesn't do anything when the counter of wakeup events in progress goes down to zero, which requires pm_get_wakeup_count() to poll that counter periodically. Although this reduces the average time it takes to deactivate a wakeup source, it also may lead to a substantial amount of unnecessary polling if there are extended periods of wakeup activity. Thus it seems reasonable to use a wait queue for signaling the "no wakeup events in progress" condition and remove the polling. Signed-off-by: Rafael J. Wysocki Acked-by: mark gross Acked-by: Greg Kroah-Hartman --- drivers/base/power/wakeup.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c index 2a3e581b8dcd..92f220d89d35 100644 --- a/drivers/base/power/wakeup.c +++ b/drivers/base/power/wakeup.c @@ -17,8 +17,6 @@ #include "power.h" -#define TIMEOUT 100 - /* * If set, the suspend/hibernate code will abort transitions to a sleep state * if wakeup events are registered during or immediately before the transition. @@ -52,6 +50,8 @@ static void pm_wakeup_timer_fn(unsigned long data); static LIST_HEAD(wakeup_sources); +static DECLARE_WAIT_QUEUE_HEAD(wakeup_count_wait_queue); + /** * wakeup_source_prepare - Prepare a new wakeup source for initialization. * @ws: Wakeup source to prepare. @@ -442,6 +442,7 @@ EXPORT_SYMBOL_GPL(pm_stay_awake); */ static void wakeup_source_deactivate(struct wakeup_source *ws) { + unsigned int cnt, inpr; ktime_t duration; ktime_t now; @@ -476,6 +477,10 @@ static void wakeup_source_deactivate(struct wakeup_source *ws) * couter of wakeup events in progress simultaneously. */ atomic_add(MAX_IN_PROGRESS, &combined_event_count); + + split_counters(&cnt, &inpr); + if (!inpr && waitqueue_active(&wakeup_count_wait_queue)) + wake_up(&wakeup_count_wait_queue); } /** @@ -667,14 +672,19 @@ bool pm_wakeup_pending(void) bool pm_get_wakeup_count(unsigned int *count) { unsigned int cnt, inpr; + DEFINE_WAIT(wait); for (;;) { + prepare_to_wait(&wakeup_count_wait_queue, &wait, + TASK_INTERRUPTIBLE); split_counters(&cnt, &inpr); if (inpr == 0 || signal_pending(current)) break; pm_wakeup_update_hit_counts(); - schedule_timeout_interruptible(msecs_to_jiffies(TIMEOUT)); + + schedule(); } + finish_wait(&wakeup_count_wait_queue, &wait); split_counters(&cnt, &inpr); *count = cnt; -- cgit v1.2.3 From 30e3ce6dcbe3fc29c343b17e768b07d4a795de21 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 29 Apr 2012 22:52:52 +0200 Subject: PM / Sleep: Change wakeup source statistics to follow Android Wakeup statistics used by Android are slightly different from what we have in wakeup sources at the moment and there aren't any known users of those statistics other than Android, so modify them to make it easier for Android to switch to wakeup sources. This removes the struct wakeup_source's hit_cout field, which is very rough and therefore not very useful, and adds two new fields, wakeup_count and expire_count. The first one tracks how many times the wakeup source is activated with events_check_enabled set (which roughly corresponds to the situations when a system power transition to a sleep state is in progress and would be aborted by this wakeup source if it were the only active one at that time) and the second one is the number of times the wakeup source has been activated with a timeout that expired. Additionally, the last_time field is now updated when the wakeup source is deactivated too (previously it was only updated during the wakeup source's activation), which seems to be what Android does with the analogous counter for wakelocks. Signed-off-by: Rafael J. Wysocki Acked-by: Greg Kroah-Hartman --- Documentation/ABI/testing/sysfs-devices-power | 24 +++++++--- drivers/base/power/sysfs.c | 30 ++++++++++--- drivers/base/power/wakeup.c | 64 ++++++++++++--------------- include/linux/pm_wakeup.h | 11 +++-- 4 files changed, 77 insertions(+), 52 deletions(-) (limited to 'drivers/base') diff --git a/Documentation/ABI/testing/sysfs-devices-power b/Documentation/ABI/testing/sysfs-devices-power index 840f7d64d483..b0a5d9a6135e 100644 --- a/Documentation/ABI/testing/sysfs-devices-power +++ b/Documentation/ABI/testing/sysfs-devices-power @@ -96,16 +96,26 @@ Description: is read-only. If the device is not enabled to wake up the system from sleep states, this attribute is not present. -What: /sys/devices/.../power/wakeup_hit_count -Date: September 2010 +What: /sys/devices/.../power/wakeup_abort_count +Date: February 2012 Contact: Rafael J. Wysocki Description: - The /sys/devices/.../wakeup_hit_count attribute contains the + The /sys/devices/.../wakeup_abort_count attribute contains the number of times the processing of a wakeup event associated with - the device might prevent the system from entering a sleep state. - This attribute is read-only. If the device is not enabled to - wake up the system from sleep states, this attribute is not - present. + the device might have aborted system transition into a sleep + state in progress. This attribute is read-only. If the device + is not enabled to wake up the system from sleep states, this + attribute is not present. + +What: /sys/devices/.../power/wakeup_expire_count +Date: February 2012 +Contact: Rafael J. Wysocki +Description: + The /sys/devices/.../wakeup_expire_count attribute contains the + number of times a wakeup event associated with the device has + been reported with a timeout that expired. This attribute is + read-only. If the device is not enabled to wake up the system + from sleep states, this attribute is not present. What: /sys/devices/.../power/wakeup_active Date: September 2010 diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c index 95c12f6cb5b9..13e40b9021b9 100644 --- a/drivers/base/power/sysfs.c +++ b/drivers/base/power/sysfs.c @@ -314,22 +314,41 @@ static ssize_t wakeup_active_count_show(struct device *dev, static DEVICE_ATTR(wakeup_active_count, 0444, wakeup_active_count_show, NULL); -static ssize_t wakeup_hit_count_show(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t wakeup_abort_count_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + unsigned long count = 0; + bool enabled = false; + + spin_lock_irq(&dev->power.lock); + if (dev->power.wakeup) { + count = dev->power.wakeup->wakeup_count; + enabled = true; + } + spin_unlock_irq(&dev->power.lock); + return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n"); +} + +static DEVICE_ATTR(wakeup_abort_count, 0444, wakeup_abort_count_show, NULL); + +static ssize_t wakeup_expire_count_show(struct device *dev, + struct device_attribute *attr, + char *buf) { unsigned long count = 0; bool enabled = false; spin_lock_irq(&dev->power.lock); if (dev->power.wakeup) { - count = dev->power.wakeup->hit_count; + count = dev->power.wakeup->expire_count; enabled = true; } spin_unlock_irq(&dev->power.lock); return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n"); } -static DEVICE_ATTR(wakeup_hit_count, 0444, wakeup_hit_count_show, NULL); +static DEVICE_ATTR(wakeup_expire_count, 0444, wakeup_expire_count_show, NULL); static ssize_t wakeup_active_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -486,7 +505,8 @@ static struct attribute *wakeup_attrs[] = { &dev_attr_wakeup.attr, &dev_attr_wakeup_count.attr, &dev_attr_wakeup_active_count.attr, - &dev_attr_wakeup_hit_count.attr, + &dev_attr_wakeup_abort_count.attr, + &dev_attr_wakeup_expire_count.attr, &dev_attr_wakeup_active.attr, &dev_attr_wakeup_total_time_ms.attr, &dev_attr_wakeup_max_time_ms.attr, diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c index 92f220d89d35..7a6eada4534d 100644 --- a/drivers/base/power/wakeup.c +++ b/drivers/base/power/wakeup.c @@ -21,7 +21,7 @@ * If set, the suspend/hibernate code will abort transitions to a sleep state * if wakeup events are registered during or immediately before the transition. */ -bool events_check_enabled; +bool events_check_enabled __read_mostly; /* * Combined counters of registered wakeup events and wakeup events in progress. @@ -382,6 +382,21 @@ static void wakeup_source_activate(struct wakeup_source *ws) atomic_inc(&combined_event_count); } +/** + * wakeup_source_report_event - Report wakeup event using the given source. + * @ws: Wakeup source to report the event for. + */ +static void wakeup_source_report_event(struct wakeup_source *ws) +{ + ws->event_count++; + /* This is racy, but the counter is approximate anyway. */ + if (events_check_enabled) + ws->wakeup_count++; + + if (!ws->active) + wakeup_source_activate(ws); +} + /** * __pm_stay_awake - Notify the PM core of a wakeup event. * @ws: Wakeup source object associated with the source of the event. @@ -397,10 +412,7 @@ void __pm_stay_awake(struct wakeup_source *ws) spin_lock_irqsave(&ws->lock, flags); - ws->event_count++; - if (!ws->active) - wakeup_source_activate(ws); - + wakeup_source_report_event(ws); del_timer(&ws->timer); ws->timer_expires = 0; @@ -469,6 +481,7 @@ static void wakeup_source_deactivate(struct wakeup_source *ws) if (ktime_to_ns(duration) > ktime_to_ns(ws->max_time)) ws->max_time = duration; + ws->last_time = now; del_timer(&ws->timer); ws->timer_expires = 0; @@ -541,8 +554,10 @@ static void pm_wakeup_timer_fn(unsigned long data) spin_lock_irqsave(&ws->lock, flags); if (ws->active && ws->timer_expires - && time_after_eq(jiffies, ws->timer_expires)) + && time_after_eq(jiffies, ws->timer_expires)) { wakeup_source_deactivate(ws); + ws->expire_count++; + } spin_unlock_irqrestore(&ws->lock, flags); } @@ -569,9 +584,7 @@ void __pm_wakeup_event(struct wakeup_source *ws, unsigned int msec) spin_lock_irqsave(&ws->lock, flags); - ws->event_count++; - if (!ws->active) - wakeup_source_activate(ws); + wakeup_source_report_event(ws); if (!msec) { wakeup_source_deactivate(ws); @@ -613,24 +626,6 @@ void pm_wakeup_event(struct device *dev, unsigned int msec) } EXPORT_SYMBOL_GPL(pm_wakeup_event); -/** - * pm_wakeup_update_hit_counts - Update hit counts of all active wakeup sources. - */ -static void pm_wakeup_update_hit_counts(void) -{ - unsigned long flags; - struct wakeup_source *ws; - - rcu_read_lock(); - list_for_each_entry_rcu(ws, &wakeup_sources, entry) { - spin_lock_irqsave(&ws->lock, flags); - if (ws->active) - ws->hit_count++; - spin_unlock_irqrestore(&ws->lock, flags); - } - rcu_read_unlock(); -} - /** * pm_wakeup_pending - Check if power transition in progress should be aborted. * @@ -653,8 +648,6 @@ bool pm_wakeup_pending(void) events_check_enabled = !ret; } spin_unlock_irqrestore(&events_lock, flags); - if (ret) - pm_wakeup_update_hit_counts(); return ret; } @@ -680,7 +673,6 @@ bool pm_get_wakeup_count(unsigned int *count) split_counters(&cnt, &inpr); if (inpr == 0 || signal_pending(current)) break; - pm_wakeup_update_hit_counts(); schedule(); } @@ -713,8 +705,6 @@ bool pm_save_wakeup_count(unsigned int count) events_check_enabled = true; } spin_unlock_irq(&events_lock); - if (!events_check_enabled) - pm_wakeup_update_hit_counts(); return events_check_enabled; } @@ -749,9 +739,10 @@ static int print_wakeup_source_stats(struct seq_file *m, active_time = ktime_set(0, 0); } - ret = seq_printf(m, "%-12s\t%lu\t\t%lu\t\t%lu\t\t" + ret = seq_printf(m, "%-12s\t%lu\t\t%lu\t\t%lu\t\t%lu\t\t" "%lld\t\t%lld\t\t%lld\t\t%lld\n", - ws->name, active_count, ws->event_count, ws->hit_count, + ws->name, active_count, ws->event_count, + ws->wakeup_count, ws->expire_count, ktime_to_ms(active_time), ktime_to_ms(total_time), ktime_to_ms(max_time), ktime_to_ms(ws->last_time)); @@ -768,8 +759,9 @@ static int wakeup_sources_stats_show(struct seq_file *m, void *unused) { struct wakeup_source *ws; - seq_puts(m, "name\t\tactive_count\tevent_count\thit_count\t" - "active_since\ttotal_time\tmax_time\tlast_change\n"); + seq_puts(m, "name\t\tactive_count\tevent_count\twakeup_count\t" + "expire_count\tactive_since\ttotal_time\tmax_time\t" + "last_change\n"); rcu_read_lock(); list_for_each_entry_rcu(ws, &wakeup_sources, entry) diff --git a/include/linux/pm_wakeup.h b/include/linux/pm_wakeup.h index d9f05113e5fb..5285317a612a 100644 --- a/include/linux/pm_wakeup.h +++ b/include/linux/pm_wakeup.h @@ -33,12 +33,14 @@ * * @total_time: Total time this wakeup source has been active. * @max_time: Maximum time this wakeup source has been continuously active. - * @last_time: Monotonic clock when the wakeup source's was activated last time. + * @last_time: Monotonic clock when the wakeup source's was touched last time. * @event_count: Number of signaled wakeup events. * @active_count: Number of times the wakeup sorce was activated. * @relax_count: Number of times the wakeup sorce was deactivated. - * @hit_count: Number of times the wakeup sorce might abort system suspend. + * @expire_count: Number of times the wakeup source's timeout has expired. + * @wakeup_count: Number of times the wakeup source might abort suspend. * @active: Status of the wakeup source. + * @has_timeout: The wakeup source has been activated with a timeout. */ struct wakeup_source { const char *name; @@ -52,8 +54,9 @@ struct wakeup_source { unsigned long event_count; unsigned long active_count; unsigned long relax_count; - unsigned long hit_count; - unsigned int active:1; + unsigned long expire_count; + unsigned long wakeup_count; + bool active:1; }; #ifdef CONFIG_PM_SLEEP -- cgit v1.2.3 From 6791e36c4a40e8930e08669e60077eea6770c429 Mon Sep 17 00:00:00 2001 From: Arve HjønnevÃ¥g Date: Sun, 29 Apr 2012 22:53:02 +0200 Subject: PM / Sleep: Add wakeup_source_activate and wakeup_source_deactivate tracepoints MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add tracepoints to wakeup_source_activate and wakeup_source_deactivate. Useful for checking that specific wakeup sources overlap as expected. Signed-off-by: Arve HjønnevÃ¥g Acked-by: Greg Kroah-Hartman Signed-off-by: Rafael J. Wysocki --- drivers/base/power/wakeup.c | 12 +++++++++--- include/trace/events/power.h | 34 ++++++++++++++++++++++++++++++++++ 2 files changed, 43 insertions(+), 3 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c index 7a6eada4534d..1132799421cd 100644 --- a/drivers/base/power/wakeup.c +++ b/drivers/base/power/wakeup.c @@ -14,6 +14,7 @@ #include #include #include +#include #include "power.h" @@ -374,12 +375,16 @@ EXPORT_SYMBOL_GPL(device_set_wakeup_enable); */ static void wakeup_source_activate(struct wakeup_source *ws) { + unsigned int cec; + ws->active = true; ws->active_count++; ws->last_time = ktime_get(); /* Increment the counter of events in progress. */ - atomic_inc(&combined_event_count); + cec = atomic_inc_return(&combined_event_count); + + trace_wakeup_source_activate(ws->name, cec); } /** @@ -454,7 +459,7 @@ EXPORT_SYMBOL_GPL(pm_stay_awake); */ static void wakeup_source_deactivate(struct wakeup_source *ws) { - unsigned int cnt, inpr; + unsigned int cnt, inpr, cec; ktime_t duration; ktime_t now; @@ -489,7 +494,8 @@ static void wakeup_source_deactivate(struct wakeup_source *ws) * Increment the counter of registered wakeup events and decrement the * couter of wakeup events in progress simultaneously. */ - atomic_add(MAX_IN_PROGRESS, &combined_event_count); + cec = atomic_add_return(MAX_IN_PROGRESS, &combined_event_count); + trace_wakeup_source_deactivate(ws->name, cec); split_counters(&cnt, &inpr); if (!inpr && waitqueue_active(&wakeup_count_wait_queue)) diff --git a/include/trace/events/power.h b/include/trace/events/power.h index cae9a94f025d..0c9783841a30 100644 --- a/include/trace/events/power.h +++ b/include/trace/events/power.h @@ -65,6 +65,40 @@ TRACE_EVENT(machine_suspend, TP_printk("state=%lu", (unsigned long)__entry->state) ); +DECLARE_EVENT_CLASS(wakeup_source, + + TP_PROTO(const char *name, unsigned int state), + + TP_ARGS(name, state), + + TP_STRUCT__entry( + __string( name, name ) + __field( u64, state ) + ), + + TP_fast_assign( + __assign_str(name, name); + __entry->state = state; + ), + + TP_printk("%s state=0x%lx", __get_str(name), + (unsigned long)__entry->state) +); + +DEFINE_EVENT(wakeup_source, wakeup_source_activate, + + TP_PROTO(const char *name, unsigned int state), + + TP_ARGS(name, state) +); + +DEFINE_EVENT(wakeup_source, wakeup_source_deactivate, + + TP_PROTO(const char *name, unsigned int state), + + TP_ARGS(name, state) +); + #ifdef CONFIG_EVENT_POWER_TRACING_DEPRECATED /* -- cgit v1.2.3 From 7483b4a4d9abf9dcf1ffe6e805ead2847ec3264e Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 29 Apr 2012 22:53:22 +0200 Subject: PM / Sleep: Implement opportunistic sleep, v2 Introduce a mechanism by which the kernel can trigger global transitions to a sleep state chosen by user space if there are no active wakeup sources. It consists of a new sysfs attribute, /sys/power/autosleep, that can be written one of the strings returned by reads from /sys/power/state, an ordered workqueue and a work item carrying out the "suspend" operations. If a string representing the system's sleep state is written to /sys/power/autosleep, the work item triggering transitions to that state is queued up and it requeues itself after every execution until user space writes "off" to /sys/power/autosleep. That work item enables the detection of wakeup events using the functions already defined in drivers/base/power/wakeup.c (with one small modification) and calls either pm_suspend(), or hibernate() to put the system into a sleep state. If a wakeup event is reported while the transition is in progress, it will abort the transition and the "system suspend" work item will be queued up again. Signed-off-by: Rafael J. Wysocki Acked-by: Greg Kroah-Hartman Reviewed-by: NeilBrown --- Documentation/ABI/testing/sysfs-power | 17 +++++ drivers/base/power/wakeup.c | 34 +++++----- include/linux/suspend.h | 13 +++- kernel/power/Kconfig | 8 +++ kernel/power/Makefile | 1 + kernel/power/autosleep.c | 123 ++++++++++++++++++++++++++++++++++ kernel/power/main.c | 119 ++++++++++++++++++++++++++------ kernel/power/power.h | 18 +++++ 8 files changed, 298 insertions(+), 35 deletions(-) create mode 100644 kernel/power/autosleep.c (limited to 'drivers/base') diff --git a/Documentation/ABI/testing/sysfs-power b/Documentation/ABI/testing/sysfs-power index b464d12761ba..237c735db6c9 100644 --- a/Documentation/ABI/testing/sysfs-power +++ b/Documentation/ABI/testing/sysfs-power @@ -172,3 +172,20 @@ Description: Reading from this file will display the current value, which is set to 1 MB by default. + +What: /sys/power/autosleep +Date: April 2012 +Contact: Rafael J. Wysocki +Description: + The /sys/power/autosleep file can be written one of the strings + returned by reads from /sys/power/state. If that happens, a + work item attempting to trigger a transition of the system to + the sleep state represented by that string is queued up. This + attempt will only succeed if there are no active wakeup sources + in the system at that time. After every execution, regardless + of whether or not the attempt to put the system to sleep has + succeeded, the work item requeues itself until user space + writes "off" to /sys/power/autosleep. + + Reading from this file causes the last string successfully + written to it to be returned. diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c index 1132799421cd..cf1706df7610 100644 --- a/drivers/base/power/wakeup.c +++ b/drivers/base/power/wakeup.c @@ -660,29 +660,33 @@ bool pm_wakeup_pending(void) /** * pm_get_wakeup_count - Read the number of registered wakeup events. * @count: Address to store the value at. + * @block: Whether or not to block. * - * Store the number of registered wakeup events at the address in @count. Block - * if the current number of wakeup events being processed is nonzero. + * Store the number of registered wakeup events at the address in @count. If + * @block is set, block until the current number of wakeup events being + * processed is zero. * - * Return 'false' if the wait for the number of wakeup events being processed to - * drop down to zero has been interrupted by a signal (and the current number - * of wakeup events being processed is still nonzero). Otherwise return 'true'. + * Return 'false' if the current number of wakeup events being processed is + * nonzero. Otherwise return 'true'. */ -bool pm_get_wakeup_count(unsigned int *count) +bool pm_get_wakeup_count(unsigned int *count, bool block) { unsigned int cnt, inpr; - DEFINE_WAIT(wait); - for (;;) { - prepare_to_wait(&wakeup_count_wait_queue, &wait, - TASK_INTERRUPTIBLE); - split_counters(&cnt, &inpr); - if (inpr == 0 || signal_pending(current)) - break; + if (block) { + DEFINE_WAIT(wait); + + for (;;) { + prepare_to_wait(&wakeup_count_wait_queue, &wait, + TASK_INTERRUPTIBLE); + split_counters(&cnt, &inpr); + if (inpr == 0 || signal_pending(current)) + break; - schedule(); + schedule(); + } + finish_wait(&wakeup_count_wait_queue, &wait); } - finish_wait(&wakeup_count_wait_queue, &wait); split_counters(&cnt, &inpr); *count = cnt; diff --git a/include/linux/suspend.h b/include/linux/suspend.h index ac1c114c499d..76b7ec7d3a81 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -356,7 +356,7 @@ extern int unregister_pm_notifier(struct notifier_block *nb); extern bool events_check_enabled; extern bool pm_wakeup_pending(void); -extern bool pm_get_wakeup_count(unsigned int *count); +extern bool pm_get_wakeup_count(unsigned int *count, bool block); extern bool pm_save_wakeup_count(unsigned int count); static inline void lock_system_sleep(void) @@ -407,6 +407,17 @@ static inline void unlock_system_sleep(void) {} #endif /* !CONFIG_PM_SLEEP */ +#ifdef CONFIG_PM_AUTOSLEEP + +/* kernel/power/autosleep.c */ +void queue_up_suspend_work(void); + +#else /* !CONFIG_PM_AUTOSLEEP */ + +static inline void queue_up_suspend_work(void) {} + +#endif /* !CONFIG_PM_AUTOSLEEP */ + #ifdef CONFIG_ARCH_SAVE_PAGE_KEYS /* * The ARCH_SAVE_PAGE_KEYS functions can be used by an architecture diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index deb5461e3216..67947083f842 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -103,6 +103,14 @@ config PM_SLEEP_SMP select HOTPLUG select HOTPLUG_CPU +config PM_AUTOSLEEP + bool "Opportunistic sleep" + depends on PM_SLEEP + default n + ---help--- + Allow the kernel to trigger a system transition into a global sleep + state automatically whenever there are no active wakeup sources. + config PM_RUNTIME bool "Run-time PM core functionality" depends on !IA64_HP_SIM diff --git a/kernel/power/Makefile b/kernel/power/Makefile index 66d808ec5252..010b2f7e148c 100644 --- a/kernel/power/Makefile +++ b/kernel/power/Makefile @@ -9,5 +9,6 @@ obj-$(CONFIG_SUSPEND) += suspend.o obj-$(CONFIG_PM_TEST_SUSPEND) += suspend_test.o obj-$(CONFIG_HIBERNATION) += hibernate.o snapshot.o swap.o user.o \ block_io.o +obj-$(CONFIG_PM_AUTOSLEEP) += autosleep.o obj-$(CONFIG_MAGIC_SYSRQ) += poweroff.o diff --git a/kernel/power/autosleep.c b/kernel/power/autosleep.c new file mode 100644 index 000000000000..42348e3589d3 --- /dev/null +++ b/kernel/power/autosleep.c @@ -0,0 +1,123 @@ +/* + * kernel/power/autosleep.c + * + * Opportunistic sleep support. + * + * Copyright (C) 2012 Rafael J. Wysocki + */ + +#include +#include +#include + +#include "power.h" + +static suspend_state_t autosleep_state; +static struct workqueue_struct *autosleep_wq; +/* + * Note: it is only safe to mutex_lock(&autosleep_lock) if a wakeup_source + * is active, otherwise a deadlock with try_to_suspend() is possible. + * Alternatively mutex_lock_interruptible() can be used. This will then fail + * if an auto_sleep cycle tries to freeze processes. + */ +static DEFINE_MUTEX(autosleep_lock); +static struct wakeup_source *autosleep_ws; + +static void try_to_suspend(struct work_struct *work) +{ + unsigned int initial_count, final_count; + + if (!pm_get_wakeup_count(&initial_count, true)) + goto out; + + mutex_lock(&autosleep_lock); + + if (!pm_save_wakeup_count(initial_count)) { + mutex_unlock(&autosleep_lock); + goto out; + } + + if (autosleep_state == PM_SUSPEND_ON) { + mutex_unlock(&autosleep_lock); + return; + } + if (autosleep_state >= PM_SUSPEND_MAX) + hibernate(); + else + pm_suspend(autosleep_state); + + mutex_unlock(&autosleep_lock); + + if (!pm_get_wakeup_count(&final_count, false)) + goto out; + + /* + * If the wakeup occured for an unknown reason, wait to prevent the + * system from trying to suspend and waking up in a tight loop. + */ + if (final_count == initial_count) + schedule_timeout_uninterruptible(HZ / 2); + + out: + queue_up_suspend_work(); +} + +static DECLARE_WORK(suspend_work, try_to_suspend); + +void queue_up_suspend_work(void) +{ + if (!work_pending(&suspend_work) && autosleep_state > PM_SUSPEND_ON) + queue_work(autosleep_wq, &suspend_work); +} + +suspend_state_t pm_autosleep_state(void) +{ + return autosleep_state; +} + +int pm_autosleep_lock(void) +{ + return mutex_lock_interruptible(&autosleep_lock); +} + +void pm_autosleep_unlock(void) +{ + mutex_unlock(&autosleep_lock); +} + +int pm_autosleep_set_state(suspend_state_t state) +{ + +#ifndef CONFIG_HIBERNATION + if (state >= PM_SUSPEND_MAX) + return -EINVAL; +#endif + + __pm_stay_awake(autosleep_ws); + + mutex_lock(&autosleep_lock); + + autosleep_state = state; + + __pm_relax(autosleep_ws); + + if (state > PM_SUSPEND_ON) + queue_up_suspend_work(); + + mutex_unlock(&autosleep_lock); + return 0; +} + +int __init pm_autosleep_init(void) +{ + autosleep_ws = wakeup_source_register("autosleep"); + if (!autosleep_ws) + return -ENOMEM; + + autosleep_wq = alloc_ordered_workqueue("autosleep", 0); + if (autosleep_wq) + return 0; + + wakeup_source_unregister(autosleep_ws); + return -ENOMEM; +} diff --git a/kernel/power/main.c b/kernel/power/main.c index 1c12581f1c62..ba6a5645952d 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -269,8 +269,7 @@ static ssize_t state_show(struct kobject *kobj, struct kobj_attribute *attr, return (s - buf); } -static ssize_t state_store(struct kobject *kobj, struct kobj_attribute *attr, - const char *buf, size_t n) +static suspend_state_t decode_state(const char *buf, size_t n) { #ifdef CONFIG_SUSPEND suspend_state_t state = PM_SUSPEND_STANDBY; @@ -278,27 +277,48 @@ static ssize_t state_store(struct kobject *kobj, struct kobj_attribute *attr, #endif char *p; int len; - int error = -EINVAL; p = memchr(buf, '\n', n); len = p ? p - buf : n; - /* First, check if we are requested to hibernate */ - if (len == 4 && !strncmp(buf, "disk", len)) { - error = hibernate(); - goto Exit; - } + /* Check hibernation first. */ + if (len == 4 && !strncmp(buf, "disk", len)) + return PM_SUSPEND_MAX; #ifdef CONFIG_SUSPEND - for (s = &pm_states[state]; state < PM_SUSPEND_MAX; s++, state++) { - if (*s && len == strlen(*s) && !strncmp(buf, *s, len)) { - error = pm_suspend(state); - break; - } - } + for (s = &pm_states[state]; state < PM_SUSPEND_MAX; s++, state++) + if (*s && len == strlen(*s) && !strncmp(buf, *s, len)) + return state; #endif - Exit: + return PM_SUSPEND_ON; +} + +static ssize_t state_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t n) +{ + suspend_state_t state; + int error; + + error = pm_autosleep_lock(); + if (error) + return error; + + if (pm_autosleep_state() > PM_SUSPEND_ON) { + error = -EBUSY; + goto out; + } + + state = decode_state(buf, n); + if (state < PM_SUSPEND_MAX) + error = pm_suspend(state); + else if (state == PM_SUSPEND_MAX) + error = hibernate(); + else + error = -EINVAL; + + out: + pm_autosleep_unlock(); return error ? error : n; } @@ -339,7 +359,8 @@ static ssize_t wakeup_count_show(struct kobject *kobj, { unsigned int val; - return pm_get_wakeup_count(&val) ? sprintf(buf, "%u\n", val) : -EINTR; + return pm_get_wakeup_count(&val, true) ? + sprintf(buf, "%u\n", val) : -EINTR; } static ssize_t wakeup_count_store(struct kobject *kobj, @@ -347,15 +368,69 @@ static ssize_t wakeup_count_store(struct kobject *kobj, const char *buf, size_t n) { unsigned int val; + int error; + + error = pm_autosleep_lock(); + if (error) + return error; + if (pm_autosleep_state() > PM_SUSPEND_ON) { + error = -EBUSY; + goto out; + } + + error = -EINVAL; if (sscanf(buf, "%u", &val) == 1) { if (pm_save_wakeup_count(val)) - return n; + error = n; } - return -EINVAL; + + out: + pm_autosleep_unlock(); + return error; } power_attr(wakeup_count); + +#ifdef CONFIG_PM_AUTOSLEEP +static ssize_t autosleep_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + suspend_state_t state = pm_autosleep_state(); + + if (state == PM_SUSPEND_ON) + return sprintf(buf, "off\n"); + +#ifdef CONFIG_SUSPEND + if (state < PM_SUSPEND_MAX) + return sprintf(buf, "%s\n", valid_state(state) ? + pm_states[state] : "error"); +#endif +#ifdef CONFIG_HIBERNATION + return sprintf(buf, "disk\n"); +#else + return sprintf(buf, "error"); +#endif +} + +static ssize_t autosleep_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t n) +{ + suspend_state_t state = decode_state(buf, n); + int error; + + if (state == PM_SUSPEND_ON + && !(strncmp(buf, "off", 3) && strncmp(buf, "off\n", 4))) + return -EINVAL; + + error = pm_autosleep_set_state(state); + return error ? error : n; +} + +power_attr(autosleep); +#endif /* CONFIG_PM_AUTOSLEEP */ #endif /* CONFIG_PM_SLEEP */ #ifdef CONFIG_PM_TRACE @@ -409,6 +484,9 @@ static struct attribute * g[] = { #ifdef CONFIG_PM_SLEEP &pm_async_attr.attr, &wakeup_count_attr.attr, +#ifdef CONFIG_PM_AUTOSLEEP + &autosleep_attr.attr, +#endif #ifdef CONFIG_PM_DEBUG &pm_test_attr.attr, #endif @@ -444,7 +522,10 @@ static int __init pm_init(void) power_kobj = kobject_create_and_add("power", NULL); if (!power_kobj) return -ENOMEM; - return sysfs_create_group(power_kobj, &attr_group); + error = sysfs_create_group(power_kobj, &attr_group); + if (error) + return error; + return pm_autosleep_init(); } core_initcall(pm_init); diff --git a/kernel/power/power.h b/kernel/power/power.h index 98f3622d7407..4cf80fa115d9 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -264,3 +264,21 @@ static inline void suspend_thaw_processes(void) { } #endif + +#ifdef CONFIG_PM_AUTOSLEEP + +/* kernel/power/autosleep.c */ +extern int pm_autosleep_init(void); +extern int pm_autosleep_lock(void); +extern void pm_autosleep_unlock(void); +extern suspend_state_t pm_autosleep_state(void); +extern int pm_autosleep_set_state(suspend_state_t state); + +#else /* !CONFIG_PM_AUTOSLEEP */ + +static inline int pm_autosleep_init(void) { return 0; } +static inline int pm_autosleep_lock(void) { return 0; } +static inline void pm_autosleep_unlock(void) {} +static inline suspend_state_t pm_autosleep_state(void) { return PM_SUSPEND_ON; } + +#endif /* !CONFIG_PM_AUTOSLEEP */ -- cgit v1.2.3 From 55850945e872531644f31fefd217d61dd15dcab8 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 29 Apr 2012 22:53:32 +0200 Subject: PM / Sleep: Add "prevent autosleep time" statistics to wakeup sources Android uses one wakelock statistics that is only necessary for opportunistic sleep. Namely, the prevent_suspend_time field accumulates the total time the given wakelock has been locked while "automatic suspend" was enabled. Add an analogous field, prevent_sleep_time, to wakeup sources and make it behave in a similar way. Signed-off-by: Rafael J. Wysocki Acked-by: Greg Kroah-Hartman --- Documentation/ABI/testing/sysfs-devices-power | 11 +++++ drivers/base/power/sysfs.c | 24 +++++++++++ drivers/base/power/wakeup.c | 61 +++++++++++++++++++++++++-- include/linux/pm_wakeup.h | 4 ++ include/linux/suspend.h | 1 + kernel/power/autosleep.c | 6 ++- 6 files changed, 102 insertions(+), 5 deletions(-) (limited to 'drivers/base') diff --git a/Documentation/ABI/testing/sysfs-devices-power b/Documentation/ABI/testing/sysfs-devices-power index b0a5d9a6135e..45000f0db4d4 100644 --- a/Documentation/ABI/testing/sysfs-devices-power +++ b/Documentation/ABI/testing/sysfs-devices-power @@ -158,6 +158,17 @@ Description: not enabled to wake up the system from sleep states, this attribute is not present. +What: /sys/devices/.../power/wakeup_prevent_sleep_time_ms +Date: February 2012 +Contact: Rafael J. Wysocki +Description: + The /sys/devices/.../wakeup_prevent_sleep_time_ms attribute + contains the total time the device has been preventing + opportunistic transitions to sleep states from occuring. + This attribute is read-only. If the device is not enabled to + wake up the system from sleep states, this attribute is not + present. + What: /sys/devices/.../power/autosuspend_delay_ms Date: September 2010 Contact: Alan Stern diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c index 13e40b9021b9..48be2ad4dd2c 100644 --- a/drivers/base/power/sysfs.c +++ b/drivers/base/power/sysfs.c @@ -417,6 +417,27 @@ static ssize_t wakeup_last_time_show(struct device *dev, } static DEVICE_ATTR(wakeup_last_time_ms, 0444, wakeup_last_time_show, NULL); + +#ifdef CONFIG_PM_AUTOSLEEP +static ssize_t wakeup_prevent_sleep_time_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + s64 msec = 0; + bool enabled = false; + + spin_lock_irq(&dev->power.lock); + if (dev->power.wakeup) { + msec = ktime_to_ms(dev->power.wakeup->prevent_sleep_time); + enabled = true; + } + spin_unlock_irq(&dev->power.lock); + return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n"); +} + +static DEVICE_ATTR(wakeup_prevent_sleep_time_ms, 0444, + wakeup_prevent_sleep_time_show, NULL); +#endif /* CONFIG_PM_AUTOSLEEP */ #endif /* CONFIG_PM_SLEEP */ #ifdef CONFIG_PM_ADVANCED_DEBUG @@ -511,6 +532,9 @@ static struct attribute *wakeup_attrs[] = { &dev_attr_wakeup_total_time_ms.attr, &dev_attr_wakeup_max_time_ms.attr, &dev_attr_wakeup_last_time_ms.attr, +#ifdef CONFIG_PM_AUTOSLEEP + &dev_attr_wakeup_prevent_sleep_time_ms.attr, +#endif #endif NULL, }; diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c index cf1706df7610..2595b8d8fe1f 100644 --- a/drivers/base/power/wakeup.c +++ b/drivers/base/power/wakeup.c @@ -380,6 +380,8 @@ static void wakeup_source_activate(struct wakeup_source *ws) ws->active = true; ws->active_count++; ws->last_time = ktime_get(); + if (ws->autosleep_enabled) + ws->start_prevent_time = ws->last_time; /* Increment the counter of events in progress. */ cec = atomic_inc_return(&combined_event_count); @@ -449,6 +451,17 @@ void pm_stay_awake(struct device *dev) } EXPORT_SYMBOL_GPL(pm_stay_awake); +#ifdef CONFIG_PM_AUTOSLEEP +static void update_prevent_sleep_time(struct wakeup_source *ws, ktime_t now) +{ + ktime_t delta = ktime_sub(now, ws->start_prevent_time); + ws->prevent_sleep_time = ktime_add(ws->prevent_sleep_time, delta); +} +#else +static inline void update_prevent_sleep_time(struct wakeup_source *ws, + ktime_t now) {} +#endif + /** * wakup_source_deactivate - Mark given wakeup source as inactive. * @ws: Wakeup source to handle. @@ -490,6 +503,9 @@ static void wakeup_source_deactivate(struct wakeup_source *ws) del_timer(&ws->timer); ws->timer_expires = 0; + if (ws->autosleep_enabled) + update_prevent_sleep_time(ws, now); + /* * Increment the counter of registered wakeup events and decrement the * couter of wakeup events in progress simultaneously. @@ -718,6 +734,34 @@ bool pm_save_wakeup_count(unsigned int count) return events_check_enabled; } +#ifdef CONFIG_PM_AUTOSLEEP +/** + * pm_wakep_autosleep_enabled - Modify autosleep_enabled for all wakeup sources. + * @enabled: Whether to set or to clear the autosleep_enabled flags. + */ +void pm_wakep_autosleep_enabled(bool set) +{ + struct wakeup_source *ws; + ktime_t now = ktime_get(); + + rcu_read_lock(); + list_for_each_entry_rcu(ws, &wakeup_sources, entry) { + spin_lock_irq(&ws->lock); + if (ws->autosleep_enabled != set) { + ws->autosleep_enabled = set; + if (ws->active) { + if (set) + ws->start_prevent_time = now; + else + update_prevent_sleep_time(ws, now); + } + } + spin_unlock_irq(&ws->lock); + } + rcu_read_unlock(); +} +#endif /* CONFIG_PM_AUTOSLEEP */ + static struct dentry *wakeup_sources_stats_dentry; /** @@ -733,28 +777,37 @@ static int print_wakeup_source_stats(struct seq_file *m, ktime_t max_time; unsigned long active_count; ktime_t active_time; + ktime_t prevent_sleep_time; int ret; spin_lock_irqsave(&ws->lock, flags); total_time = ws->total_time; max_time = ws->max_time; + prevent_sleep_time = ws->prevent_sleep_time; active_count = ws->active_count; if (ws->active) { - active_time = ktime_sub(ktime_get(), ws->last_time); + ktime_t now = ktime_get(); + + active_time = ktime_sub(now, ws->last_time); total_time = ktime_add(total_time, active_time); if (active_time.tv64 > max_time.tv64) max_time = active_time; + + if (ws->autosleep_enabled) + prevent_sleep_time = ktime_add(prevent_sleep_time, + ktime_sub(now, ws->start_prevent_time)); } else { active_time = ktime_set(0, 0); } ret = seq_printf(m, "%-12s\t%lu\t\t%lu\t\t%lu\t\t%lu\t\t" - "%lld\t\t%lld\t\t%lld\t\t%lld\n", + "%lld\t\t%lld\t\t%lld\t\t%lld\t\t%lld\n", ws->name, active_count, ws->event_count, ws->wakeup_count, ws->expire_count, ktime_to_ms(active_time), ktime_to_ms(total_time), - ktime_to_ms(max_time), ktime_to_ms(ws->last_time)); + ktime_to_ms(max_time), ktime_to_ms(ws->last_time), + ktime_to_ms(prevent_sleep_time)); spin_unlock_irqrestore(&ws->lock, flags); @@ -771,7 +824,7 @@ static int wakeup_sources_stats_show(struct seq_file *m, void *unused) seq_puts(m, "name\t\tactive_count\tevent_count\twakeup_count\t" "expire_count\tactive_since\ttotal_time\tmax_time\t" - "last_change\n"); + "last_change\tprevent_suspend_time\n"); rcu_read_lock(); list_for_each_entry_rcu(ws, &wakeup_sources, entry) diff --git a/include/linux/pm_wakeup.h b/include/linux/pm_wakeup.h index 5285317a612a..569781faa504 100644 --- a/include/linux/pm_wakeup.h +++ b/include/linux/pm_wakeup.h @@ -34,6 +34,7 @@ * @total_time: Total time this wakeup source has been active. * @max_time: Maximum time this wakeup source has been continuously active. * @last_time: Monotonic clock when the wakeup source's was touched last time. + * @prevent_sleep_time: Total time this source has been preventing autosleep. * @event_count: Number of signaled wakeup events. * @active_count: Number of times the wakeup sorce was activated. * @relax_count: Number of times the wakeup sorce was deactivated. @@ -51,12 +52,15 @@ struct wakeup_source { ktime_t total_time; ktime_t max_time; ktime_t last_time; + ktime_t start_prevent_time; + ktime_t prevent_sleep_time; unsigned long event_count; unsigned long active_count; unsigned long relax_count; unsigned long expire_count; unsigned long wakeup_count; bool active:1; + bool autosleep_enabled:1; }; #ifdef CONFIG_PM_SLEEP diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 76b7ec7d3a81..cd83059fb592 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -358,6 +358,7 @@ extern bool events_check_enabled; extern bool pm_wakeup_pending(void); extern bool pm_get_wakeup_count(unsigned int *count, bool block); extern bool pm_save_wakeup_count(unsigned int count); +extern void pm_wakep_autosleep_enabled(bool set); static inline void lock_system_sleep(void) { diff --git a/kernel/power/autosleep.c b/kernel/power/autosleep.c index 42348e3589d3..ca304046d9e2 100644 --- a/kernel/power/autosleep.c +++ b/kernel/power/autosleep.c @@ -101,8 +101,12 @@ int pm_autosleep_set_state(suspend_state_t state) __pm_relax(autosleep_ws); - if (state > PM_SUSPEND_ON) + if (state > PM_SUSPEND_ON) { + pm_wakep_autosleep_enabled(true); queue_up_suspend_work(); + } else { + pm_wakep_autosleep_enabled(false); + } mutex_unlock(&autosleep_lock); return 0; -- cgit v1.2.3 From b86ff9820fd5df69295273b9aa68e58786ffc23f Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 29 Apr 2012 22:53:42 +0200 Subject: PM / Sleep: Add user space interface for manipulating wakeup sources, v3 Android allows user space to manipulate wakelocks using two sysfs file located in /sys/power/, wake_lock and wake_unlock. Writing a wakelock name and optionally a timeout to the wake_lock file causes the wakelock whose name was written to be acquired (it is created before is necessary), optionally with the given timeout. Writing the name of a wakelock to wake_unlock causes that wakelock to be released. Implement an analogous interface for user space using wakeup sources. Add the /sys/power/wake_lock and /sys/power/wake_unlock files allowing user space to create, activate and deactivate wakeup sources, such that writing a name and optionally a timeout to wake_lock causes the wakeup source of that name to be activated, optionally with the given timeout. If that wakeup source doesn't exist, it will be created and then activated. Writing a name to wake_unlock causes the wakeup source of that name, if there is one, to be deactivated. Wakeup sources created with the help of wake_lock that haven't been used for more than 5 minutes are garbage collected and destroyed. Moreover, there can be only WL_NUMBER_LIMIT wakeup sources created with the help of wake_lock present at a time. The data type used to track wakeup sources created by user space is called "struct wakelock" to indicate the origins of this feature. This version of the patch includes an rbtree manipulation fix from John Stultz. Signed-off-by: Rafael J. Wysocki Acked-by: Greg Kroah-Hartman Reviewed-by: NeilBrown --- Documentation/ABI/testing/sysfs-power | 42 +++++++ drivers/base/power/wakeup.c | 1 + kernel/power/Kconfig | 8 ++ kernel/power/Makefile | 1 + kernel/power/main.c | 41 +++++++ kernel/power/power.h | 9 ++ kernel/power/wakelock.c | 215 ++++++++++++++++++++++++++++++++++ 7 files changed, 317 insertions(+) create mode 100644 kernel/power/wakelock.c (limited to 'drivers/base') diff --git a/Documentation/ABI/testing/sysfs-power b/Documentation/ABI/testing/sysfs-power index 237c735db6c9..31725ffeeb3a 100644 --- a/Documentation/ABI/testing/sysfs-power +++ b/Documentation/ABI/testing/sysfs-power @@ -189,3 +189,45 @@ Description: Reading from this file causes the last string successfully written to it to be returned. + +What: /sys/power/wake_lock +Date: February 2012 +Contact: Rafael J. Wysocki +Description: + The /sys/power/wake_lock file allows user space to create + wakeup source objects and activate them on demand (if one of + those wakeup sources is active, reads from the + /sys/power/wakeup_count file block or return false). When a + string without white space is written to /sys/power/wake_lock, + it will be assumed to represent a wakeup source name. If there + is a wakeup source object with that name, it will be activated + (unless active already). Otherwise, a new wakeup source object + will be registered, assigned the given name and activated. + If a string written to /sys/power/wake_lock contains white + space, the part of the string preceding the white space will be + regarded as a wakeup source name and handled as descrived above. + The other part of the string will be regarded as a timeout (in + nanoseconds) such that the wakeup source will be automatically + deactivated after it has expired. The timeout, if present, is + set regardless of the current state of the wakeup source object + in question. + + Reads from this file return a string consisting of the names of + wakeup sources created with the help of it that are active at + the moment, separated with spaces. + + +What: /sys/power/wake_unlock +Date: February 2012 +Contact: Rafael J. Wysocki +Description: + The /sys/power/wake_unlock file allows user space to deactivate + wakeup sources created with the help of /sys/power/wake_lock. + When a string is written to /sys/power/wake_unlock, it will be + assumed to represent the name of a wakeup source to deactivate. + If a wakeup source object of that name exists and is active at + the moment, it will be deactivated. + + Reads from this file return a string consisting of the names of + wakeup sources created with the help of /sys/power/wake_lock + that are inactive at the moment, separated with spaces. diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c index 2595b8d8fe1f..cbb463b3a750 100644 --- a/drivers/base/power/wakeup.c +++ b/drivers/base/power/wakeup.c @@ -133,6 +133,7 @@ void wakeup_source_add(struct wakeup_source *ws) spin_lock_init(&ws->lock); setup_timer(&ws->timer, pm_wakeup_timer_fn, (unsigned long)ws); ws->active = false; + ws->last_time = ktime_get(); spin_lock_irq(&events_lock); list_add_rcu(&ws->entry, &wakeup_sources); diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index 67947083f842..1d534076d33a 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -111,6 +111,14 @@ config PM_AUTOSLEEP Allow the kernel to trigger a system transition into a global sleep state automatically whenever there are no active wakeup sources. +config PM_WAKELOCKS + bool "User space wakeup sources interface" + depends on PM_SLEEP + default n + ---help--- + Allow user space to create, activate and deactivate wakeup source + objects with the help of a sysfs-based interface. + config PM_RUNTIME bool "Run-time PM core functionality" depends on !IA64_HP_SIM diff --git a/kernel/power/Makefile b/kernel/power/Makefile index 010b2f7e148c..29472bff11ef 100644 --- a/kernel/power/Makefile +++ b/kernel/power/Makefile @@ -10,5 +10,6 @@ obj-$(CONFIG_PM_TEST_SUSPEND) += suspend_test.o obj-$(CONFIG_HIBERNATION) += hibernate.o snapshot.o swap.o user.o \ block_io.o obj-$(CONFIG_PM_AUTOSLEEP) += autosleep.o +obj-$(CONFIG_PM_WAKELOCKS) += wakelock.o obj-$(CONFIG_MAGIC_SYSRQ) += poweroff.o diff --git a/kernel/power/main.c b/kernel/power/main.c index ba6a5645952d..54ec071de337 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -431,6 +431,43 @@ static ssize_t autosleep_store(struct kobject *kobj, power_attr(autosleep); #endif /* CONFIG_PM_AUTOSLEEP */ + +#ifdef CONFIG_PM_WAKELOCKS +static ssize_t wake_lock_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return pm_show_wakelocks(buf, true); +} + +static ssize_t wake_lock_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t n) +{ + int error = pm_wake_lock(buf); + return error ? error : n; +} + +power_attr(wake_lock); + +static ssize_t wake_unlock_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return pm_show_wakelocks(buf, false); +} + +static ssize_t wake_unlock_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t n) +{ + int error = pm_wake_unlock(buf); + return error ? error : n; +} + +power_attr(wake_unlock); + +#endif /* CONFIG_PM_WAKELOCKS */ #endif /* CONFIG_PM_SLEEP */ #ifdef CONFIG_PM_TRACE @@ -487,6 +524,10 @@ static struct attribute * g[] = { #ifdef CONFIG_PM_AUTOSLEEP &autosleep_attr.attr, #endif +#ifdef CONFIG_PM_WAKELOCKS + &wake_lock_attr.attr, + &wake_unlock_attr.attr, +#endif #ifdef CONFIG_PM_DEBUG &pm_test_attr.attr, #endif diff --git a/kernel/power/power.h b/kernel/power/power.h index 4cf80fa115d9..b0bd4beaebfe 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -282,3 +282,12 @@ static inline void pm_autosleep_unlock(void) {} static inline suspend_state_t pm_autosleep_state(void) { return PM_SUSPEND_ON; } #endif /* !CONFIG_PM_AUTOSLEEP */ + +#ifdef CONFIG_PM_WAKELOCKS + +/* kernel/power/wakelock.c */ +extern ssize_t pm_show_wakelocks(char *buf, bool show_active); +extern int pm_wake_lock(const char *buf); +extern int pm_wake_unlock(const char *buf); + +#endif /* !CONFIG_PM_WAKELOCKS */ diff --git a/kernel/power/wakelock.c b/kernel/power/wakelock.c new file mode 100644 index 000000000000..579700665e8c --- /dev/null +++ b/kernel/power/wakelock.c @@ -0,0 +1,215 @@ +/* + * kernel/power/wakelock.c + * + * User space wakeup sources support. + * + * Copyright (C) 2012 Rafael J. Wysocki + * + * This code is based on the analogous interface allowing user space to + * manipulate wakelocks on Android. + */ + +#include +#include +#include +#include +#include +#include +#include + +#define WL_NUMBER_LIMIT 100 +#define WL_GC_COUNT_MAX 100 +#define WL_GC_TIME_SEC 300 + +static DEFINE_MUTEX(wakelocks_lock); + +struct wakelock { + char *name; + struct rb_node node; + struct wakeup_source ws; + struct list_head lru; +}; + +static struct rb_root wakelocks_tree = RB_ROOT; +static LIST_HEAD(wakelocks_lru_list); +static unsigned int number_of_wakelocks; +static unsigned int wakelocks_gc_count; + +ssize_t pm_show_wakelocks(char *buf, bool show_active) +{ + struct rb_node *node; + struct wakelock *wl; + char *str = buf; + char *end = buf + PAGE_SIZE; + + mutex_lock(&wakelocks_lock); + + for (node = rb_first(&wakelocks_tree); node; node = rb_next(node)) { + wl = rb_entry(node, struct wakelock, node); + if (wl->ws.active == show_active) + str += scnprintf(str, end - str, "%s ", wl->name); + } + if (str > buf) + str--; + + str += scnprintf(str, end - str, "\n"); + + mutex_unlock(&wakelocks_lock); + return (str - buf); +} + +static struct wakelock *wakelock_lookup_add(const char *name, size_t len, + bool add_if_not_found) +{ + struct rb_node **node = &wakelocks_tree.rb_node; + struct rb_node *parent = *node; + struct wakelock *wl; + + while (*node) { + int diff; + + parent = *node; + wl = rb_entry(*node, struct wakelock, node); + diff = strncmp(name, wl->name, len); + if (diff == 0) { + if (wl->name[len]) + diff = -1; + else + return wl; + } + if (diff < 0) + node = &(*node)->rb_left; + else + node = &(*node)->rb_right; + } + if (!add_if_not_found) + return ERR_PTR(-EINVAL); + + if (number_of_wakelocks > WL_NUMBER_LIMIT) + return ERR_PTR(-ENOSPC); + + /* Not found, we have to add a new one. */ + wl = kzalloc(sizeof(*wl), GFP_KERNEL); + if (!wl) + return ERR_PTR(-ENOMEM); + + wl->name = kstrndup(name, len, GFP_KERNEL); + if (!wl->name) { + kfree(wl); + return ERR_PTR(-ENOMEM); + } + wl->ws.name = wl->name; + wakeup_source_add(&wl->ws); + rb_link_node(&wl->node, parent, node); + rb_insert_color(&wl->node, &wakelocks_tree); + list_add(&wl->lru, &wakelocks_lru_list); + number_of_wakelocks++; + return wl; +} + +int pm_wake_lock(const char *buf) +{ + const char *str = buf; + struct wakelock *wl; + u64 timeout_ns = 0; + size_t len; + int ret = 0; + + while (*str && !isspace(*str)) + str++; + + len = str - buf; + if (!len) + return -EINVAL; + + if (*str && *str != '\n') { + /* Find out if there's a valid timeout string appended. */ + ret = kstrtou64(skip_spaces(str), 10, &timeout_ns); + if (ret) + return -EINVAL; + } + + mutex_lock(&wakelocks_lock); + + wl = wakelock_lookup_add(buf, len, true); + if (IS_ERR(wl)) { + ret = PTR_ERR(wl); + goto out; + } + if (timeout_ns) { + u64 timeout_ms = timeout_ns + NSEC_PER_MSEC - 1; + + do_div(timeout_ms, NSEC_PER_MSEC); + __pm_wakeup_event(&wl->ws, timeout_ms); + } else { + __pm_stay_awake(&wl->ws); + } + + list_move(&wl->lru, &wakelocks_lru_list); + + out: + mutex_unlock(&wakelocks_lock); + return ret; +} + +static void wakelocks_gc(void) +{ + struct wakelock *wl, *aux; + ktime_t now = ktime_get(); + + list_for_each_entry_safe_reverse(wl, aux, &wakelocks_lru_list, lru) { + u64 idle_time_ns; + bool active; + + spin_lock_irq(&wl->ws.lock); + idle_time_ns = ktime_to_ns(ktime_sub(now, wl->ws.last_time)); + active = wl->ws.active; + spin_unlock_irq(&wl->ws.lock); + + if (idle_time_ns < ((u64)WL_GC_TIME_SEC * NSEC_PER_SEC)) + break; + + if (!active) { + wakeup_source_remove(&wl->ws); + rb_erase(&wl->node, &wakelocks_tree); + list_del(&wl->lru); + kfree(wl->name); + kfree(wl); + number_of_wakelocks--; + } + } + wakelocks_gc_count = 0; +} + +int pm_wake_unlock(const char *buf) +{ + struct wakelock *wl; + size_t len; + int ret = 0; + + len = strlen(buf); + if (!len) + return -EINVAL; + + if (buf[len-1] == '\n') + len--; + + if (!len) + return -EINVAL; + + mutex_lock(&wakelocks_lock); + + wl = wakelock_lookup_add(buf, len, false); + if (IS_ERR(wl)) { + ret = PTR_ERR(wl); + goto out; + } + __pm_relax(&wl->ws); + list_move(&wl->lru, &wakelocks_lru_list); + if (++wakelocks_gc_count > WL_GC_COUNT_MAX) + wakelocks_gc(); + + out: + mutex_unlock(&wakelocks_lock); + return ret; +} -- cgit v1.2.3 From a5bef810ad9816a3a8e500d8832be77d52903a12 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 29 Apr 2012 22:54:17 +0200 Subject: PM / Domains: Rework default device stop governor function, v2 The existing default device stop governor function for PM domains, default_stop_ok(), is supposed to check whether or not the device's PM QoS latency constraint will be violated if the device is stopped by pm_genpd_runtime_suspend(). However, the computations carried out by it don't reflect the definition of the PM QoS latency constrait in Documentation/ABI/testing/sysfs-devices-power. Make default_stop_ok() follow the definition of the PM QoS latency constrait. In particular, make it take the device's start and stop latencies correctly. Add a new field, effective_constraint_ns, to struct gpd_timing_data and use it to store the difference between the device's PM QoS constraint and its resume latency for use by the device's parent (the effective_constraint_ns values for the children are used for computing the parent's one along with its PM QoS constraint). Remove the break_even_ns field from struct gpd_timing_data, because it's not used any more. Signed-off-by: Rafael J. Wysocki --- drivers/base/power/domain.c | 1 + drivers/base/power/domain_governor.c | 53 +++++++++++++++++++++++++++++++++--- include/linux/pm_domain.h | 2 +- 3 files changed, 51 insertions(+), 5 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index 73ce9fbe9839..3c6e94fe058a 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -506,6 +506,7 @@ static int pm_genpd_runtime_suspend(struct device *dev) if (dev_gpd_data(dev)->always_on) return -EBUSY; + dev_gpd_data(dev)->td.effective_constraint_ns = -1; stop_ok = genpd->gov ? genpd->gov->stop_ok : NULL; if (stop_ok && !stop_ok(dev)) return -EBUSY; diff --git a/drivers/base/power/domain_governor.c b/drivers/base/power/domain_governor.c index 66a265bf5867..a67f157a7a74 100644 --- a/drivers/base/power/domain_governor.c +++ b/drivers/base/power/domain_governor.c @@ -14,6 +14,31 @@ #ifdef CONFIG_PM_RUNTIME +static int dev_update_qos_constraint(struct device *dev, void *data) +{ + s64 *constraint_ns_p = data; + s32 constraint_ns = -1; + + if (dev->power.subsys_data && dev->power.subsys_data->domain_data) + constraint_ns = dev_gpd_data(dev)->td.effective_constraint_ns; + + if (constraint_ns < 0) { + constraint_ns = dev_pm_qos_read_value(dev); + constraint_ns *= NSEC_PER_USEC; + } + if (constraint_ns == 0) + return 0; + + /* + * constraint_ns cannot be negative here, because the device has been + * suspended. + */ + if (constraint_ns < *constraint_ns_p || *constraint_ns_p == 0) + *constraint_ns_p = constraint_ns; + + return 0; +} + /** * default_stop_ok - Default PM domain governor routine for stopping devices. * @dev: Device to check. @@ -21,14 +46,34 @@ bool default_stop_ok(struct device *dev) { struct gpd_timing_data *td = &dev_gpd_data(dev)->td; + s64 constraint_ns; dev_dbg(dev, "%s()\n", __func__); - if (dev->power.max_time_suspended_ns < 0 || td->break_even_ns == 0) - return true; + constraint_ns = dev_pm_qos_read_value(dev); + if (constraint_ns < 0) + return false; + + constraint_ns *= NSEC_PER_USEC; + /* + * We can walk the children without any additional locking, because + * they all have been suspended at this point. + */ + if (!dev->power.ignore_children) + device_for_each_child(dev, &constraint_ns, + dev_update_qos_constraint); - return td->stop_latency_ns + td->start_latency_ns < td->break_even_ns - && td->break_even_ns < dev->power.max_time_suspended_ns; + if (constraint_ns > 0) { + constraint_ns -= td->start_latency_ns; + if (constraint_ns == 0) + return false; + } + td->effective_constraint_ns = constraint_ns; + /* + * The children have been suspended already, so we don't need to take + * their stop latencies into account here. + */ + return constraint_ns > td->stop_latency_ns || constraint_ns == 0; } /** diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 91f8286106ea..9c25219458c2 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -93,7 +93,7 @@ struct gpd_timing_data { s64 start_latency_ns; s64 save_state_latency_ns; s64 restore_state_latency_ns; - s64 break_even_ns; + s64 effective_constraint_ns; }; struct generic_pm_domain_data { -- cgit v1.2.3 From dd8683e97f12609fb3f8c4318628f0d246542f89 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 29 Apr 2012 22:54:30 +0200 Subject: PM / Domains: Rework default domain power off governor function, v2 The existing default domain power down governor function for PM domains, default_power_down_ok(), is supposed to check whether or not the PM QoS latency constraints of the devices in the domain will be violated if the domain is turned off by pm_genpd_poweroff(). However, the computations carried out by it don't reflect the definition of the PM QoS latency constrait in Documentation/ABI/testing/sysfs-devices-power. Make default_power_down_ok() follow the definition of the PM QoS latency constrait. In particular, make it only take latencies into account, because it doesn't matter how much time has elapsed since the domain's devices were suspended for the computation. Remove the break_even_ns and power_off_time fields from struct generic_pm_domain, because they are not necessary any more. Signed-off-by: Rafael J. Wysocki --- drivers/base/power/domain.c | 2 +- drivers/base/power/domain_governor.c | 69 ++++++++++++++++++------------------ include/linux/pm_domain.h | 2 -- 3 files changed, 35 insertions(+), 38 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index 3c6e94fe058a..d03a8c7ad847 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -381,6 +381,7 @@ static int pm_genpd_poweroff(struct generic_pm_domain *genpd) return 0; } + genpd->max_off_time_ns = -1; if (genpd->gov && genpd->gov->power_down_ok) { if (!genpd->gov->power_down_ok(&genpd->domain)) return -EAGAIN; @@ -443,7 +444,6 @@ static int pm_genpd_poweroff(struct generic_pm_domain *genpd) } genpd->status = GPD_STATE_POWER_OFF; - genpd->power_off_time = ktime_get(); /* Update PM QoS information for devices in the domain. */ list_for_each_entry_reverse(pdd, &genpd->dev_list, list_node) { diff --git a/drivers/base/power/domain_governor.c b/drivers/base/power/domain_governor.c index a67f157a7a74..2aae623fd840 100644 --- a/drivers/base/power/domain_governor.c +++ b/drivers/base/power/domain_governor.c @@ -89,7 +89,6 @@ static bool default_power_down_ok(struct dev_pm_domain *pd) struct pm_domain_data *pdd; s64 min_dev_off_time_ns; s64 off_on_time_ns; - ktime_t time_now = ktime_get(); off_on_time_ns = genpd->power_off_latency_ns + genpd->power_on_latency_ns; @@ -118,8 +117,6 @@ static bool default_power_down_ok(struct dev_pm_domain *pd) if (sd_max_off_ns < 0) continue; - sd_max_off_ns -= ktime_to_ns(ktime_sub(time_now, - sd->power_off_time)); /* * Check if the subdomain is allowed to be off long enough for * the current domain to turn off and on (that's how much time @@ -135,52 +132,54 @@ static bool default_power_down_ok(struct dev_pm_domain *pd) min_dev_off_time_ns = -1; list_for_each_entry(pdd, &genpd->dev_list, list_node) { struct gpd_timing_data *td; - struct device *dev = pdd->dev; - s64 dev_off_time_ns; + s64 constraint_ns; - if (!dev->driver || dev->power.max_time_suspended_ns < 0) + if (!pdd->dev->driver) continue; + /* + * Check if the device is allowed to be off long enough for the + * domain to turn off and on (that's how much time it will + * have to wait worst case). + */ td = &to_gpd_data(pdd)->td; - dev_off_time_ns = dev->power.max_time_suspended_ns - - (td->start_latency_ns + td->restore_state_latency_ns + - ktime_to_ns(ktime_sub(time_now, - dev->power.suspend_time))); - if (dev_off_time_ns <= off_on_time_ns) - return false; - - if (min_dev_off_time_ns > dev_off_time_ns - || min_dev_off_time_ns < 0) - min_dev_off_time_ns = dev_off_time_ns; - } + constraint_ns = td->effective_constraint_ns; + /* default_stop_ok() need not be called before us. */ + if (constraint_ns < 0) { + constraint_ns = dev_pm_qos_read_value(pdd->dev); + constraint_ns *= NSEC_PER_USEC; + } + if (constraint_ns == 0) + continue; - if (min_dev_off_time_ns < 0) { /* - * There are no latency constraints, so the domain can spend - * arbitrary time in the "off" state. + * constraint_ns cannot be negative here, because the device has + * been suspended. */ - genpd->max_off_time_ns = -1; - return true; + constraint_ns -= td->restore_state_latency_ns; + if (constraint_ns <= off_on_time_ns) + return false; + + if (min_dev_off_time_ns > constraint_ns + || min_dev_off_time_ns < 0) + min_dev_off_time_ns = constraint_ns; } /* - * The difference between the computed minimum delta and the time needed - * to turn the domain on is the maximum theoretical time this domain can - * spend in the "off" state. + * If the computed minimum device off time is negative, there are no + * latency constraints, so the domain can spend arbitrary time in the + * "off" state. */ - min_dev_off_time_ns -= genpd->power_on_latency_ns; + if (min_dev_off_time_ns < 0) + return true; /* - * If the difference between the computed minimum delta and the time - * needed to turn the domain off and back on on is smaller than the - * domain's power break even time, removing power from the domain is not - * worth it. + * The difference between the computed minimum device off time and the + * time needed to turn the domain on is the maximum theoretical time + * this domain can spend in the "off" state. */ - if (genpd->break_even_ns > - min_dev_off_time_ns - genpd->power_off_latency_ns) - return false; - - genpd->max_off_time_ns = min_dev_off_time_ns; + genpd->max_off_time_ns = min_dev_off_time_ns - + genpd->power_on_latency_ns; return true; } diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 9c25219458c2..e7ada5ccdfc2 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -70,9 +70,7 @@ struct generic_pm_domain { int (*power_on)(struct generic_pm_domain *domain); s64 power_on_latency_ns; struct gpd_dev_ops dev_ops; - s64 break_even_ns; /* Power break even for the entire domain. */ s64 max_off_time_ns; /* Maximum allowed "suspended" time. */ - ktime_t power_off_time; struct device_node *of_node; /* Node in device tree */ }; -- cgit v1.2.3 From 76e267d822f2913893ad210ba431607aa8e2af94 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 29 Apr 2012 22:54:36 +0200 Subject: PM / Runtime: Remove device fields related to suspend time, v2 After the previous changes in default_stop_ok() and default_power_down_ok() for PM domains, there are two fields in struct dev_pm_info that aren't necessary any more, suspend_time and max_time_suspended_ns. Remove those fields along with all of the code that accesses them, which simplifies the runtime PM framework quite a bit. Signed-off-by: Rafael J. Wysocki --- drivers/base/power/domain.c | 13 ------ drivers/base/power/runtime.c | 103 +------------------------------------------ include/linux/pm.h | 2 - include/linux/pm_runtime.h | 3 -- 4 files changed, 2 insertions(+), 119 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index d03a8c7ad847..45c2b7f0fe3b 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -445,16 +445,6 @@ static int pm_genpd_poweroff(struct generic_pm_domain *genpd) genpd->status = GPD_STATE_POWER_OFF; - /* Update PM QoS information for devices in the domain. */ - list_for_each_entry_reverse(pdd, &genpd->dev_list, list_node) { - struct gpd_timing_data *td = &to_gpd_data(pdd)->td; - - pm_runtime_update_max_time_suspended(pdd->dev, - td->start_latency_ns + - td->restore_state_latency_ns + - genpd->power_on_latency_ns); - } - list_for_each_entry(link, &genpd->slave_links, slave_node) { genpd_sd_counter_dec(link->master); genpd_queue_power_off_work(link->master); @@ -515,9 +505,6 @@ static int pm_genpd_runtime_suspend(struct device *dev) if (ret) return ret; - pm_runtime_update_max_time_suspended(dev, - dev_gpd_data(dev)->td.start_latency_ns); - /* * If power.irq_safe is set, this routine will be run with interrupts * off, so it can't use mutexes. diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index bd0f3949bcf9..59894873a3b3 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -282,47 +282,6 @@ static int rpm_callback(int (*cb)(struct device *), struct device *dev) return retval != -EACCES ? retval : -EIO; } -struct rpm_qos_data { - ktime_t time_now; - s64 constraint_ns; -}; - -/** - * rpm_update_qos_constraint - Update a given PM QoS constraint data. - * @dev: Device whose timing data to use. - * @data: PM QoS constraint data to update. - * - * Use the suspend timing data of @dev to update PM QoS constraint data pointed - * to by @data. - */ -static int rpm_update_qos_constraint(struct device *dev, void *data) -{ - struct rpm_qos_data *qos = data; - unsigned long flags; - s64 delta_ns; - int ret = 0; - - spin_lock_irqsave(&dev->power.lock, flags); - - if (dev->power.max_time_suspended_ns < 0) - goto out; - - delta_ns = dev->power.max_time_suspended_ns - - ktime_to_ns(ktime_sub(qos->time_now, dev->power.suspend_time)); - if (delta_ns <= 0) { - ret = -EBUSY; - goto out; - } - - if (qos->constraint_ns > delta_ns || qos->constraint_ns == 0) - qos->constraint_ns = delta_ns; - - out: - spin_unlock_irqrestore(&dev->power.lock, flags); - - return ret; -} - /** * rpm_suspend - Carry out runtime suspend of given device. * @dev: Device to suspend. @@ -349,7 +308,6 @@ static int rpm_suspend(struct device *dev, int rpmflags) { int (*callback)(struct device *); struct device *parent = NULL; - struct rpm_qos_data qos; int retval; trace_rpm_suspend(dev, rpmflags); @@ -445,38 +403,14 @@ static int rpm_suspend(struct device *dev, int rpmflags) goto out; } - qos.constraint_ns = __dev_pm_qos_read_value(dev); - if (qos.constraint_ns < 0) { - /* Negative constraint means "never suspend". */ + if (__dev_pm_qos_read_value(dev) < 0) { + /* Negative PM QoS constraint means "never suspend". */ retval = -EPERM; goto out; } - qos.constraint_ns *= NSEC_PER_USEC; - qos.time_now = ktime_get(); __update_runtime_status(dev, RPM_SUSPENDING); - if (!dev->power.ignore_children) { - if (dev->power.irq_safe) - spin_unlock(&dev->power.lock); - else - spin_unlock_irq(&dev->power.lock); - - retval = device_for_each_child(dev, &qos, - rpm_update_qos_constraint); - - if (dev->power.irq_safe) - spin_lock(&dev->power.lock); - else - spin_lock_irq(&dev->power.lock); - - if (retval) - goto fail; - } - - dev->power.suspend_time = qos.time_now; - dev->power.max_time_suspended_ns = qos.constraint_ns ? : -1; - if (dev->pm_domain) callback = dev->pm_domain->ops.runtime_suspend; else if (dev->type && dev->type->pm) @@ -529,8 +463,6 @@ static int rpm_suspend(struct device *dev, int rpmflags) fail: __update_runtime_status(dev, RPM_ACTIVE); - dev->power.suspend_time = ktime_set(0, 0); - dev->power.max_time_suspended_ns = -1; dev->power.deferred_resume = false; wake_up_all(&dev->power.wait_queue); @@ -704,9 +636,6 @@ static int rpm_resume(struct device *dev, int rpmflags) if (dev->power.no_callbacks) goto no_callback; /* Assume success. */ - dev->power.suspend_time = ktime_set(0, 0); - dev->power.max_time_suspended_ns = -1; - __update_runtime_status(dev, RPM_RESUMING); if (dev->pm_domain) @@ -1369,9 +1298,6 @@ void pm_runtime_init(struct device *dev) setup_timer(&dev->power.suspend_timer, pm_suspend_timer_fn, (unsigned long)dev); - dev->power.suspend_time = ktime_set(0, 0); - dev->power.max_time_suspended_ns = -1; - init_waitqueue_head(&dev->power.wait_queue); } @@ -1389,28 +1315,3 @@ void pm_runtime_remove(struct device *dev) if (dev->power.irq_safe && dev->parent) pm_runtime_put_sync(dev->parent); } - -/** - * pm_runtime_update_max_time_suspended - Update device's suspend time data. - * @dev: Device to handle. - * @delta_ns: Value to subtract from the device's max_time_suspended_ns field. - * - * Update the device's power.max_time_suspended_ns field by subtracting - * @delta_ns from it. The resulting value of power.max_time_suspended_ns is - * never negative. - */ -void pm_runtime_update_max_time_suspended(struct device *dev, s64 delta_ns) -{ - unsigned long flags; - - spin_lock_irqsave(&dev->power.lock, flags); - - if (delta_ns > 0 && dev->power.max_time_suspended_ns > 0) { - if (dev->power.max_time_suspended_ns > delta_ns) - dev->power.max_time_suspended_ns -= delta_ns; - else - dev->power.max_time_suspended_ns = 0; - } - - spin_unlock_irqrestore(&dev->power.lock, flags); -} diff --git a/include/linux/pm.h b/include/linux/pm.h index 715305e05123..f067e60a3832 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -544,8 +544,6 @@ struct dev_pm_info { unsigned long active_jiffies; unsigned long suspended_jiffies; unsigned long accounting_timestamp; - ktime_t suspend_time; - s64 max_time_suspended_ns; struct dev_pm_qos_request *pq_req; #endif struct pm_subsys_data *subsys_data; /* Owned by the subsystem. */ diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 609daae7a014..f271860c78d5 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -150,9 +150,6 @@ static inline void pm_runtime_set_autosuspend_delay(struct device *dev, static inline unsigned long pm_runtime_autosuspend_expiration( struct device *dev) { return 0; } -static inline void pm_runtime_update_max_time_suspended(struct device *dev, - s64 delta_ns) {} - #endif /* !CONFIG_PM_RUNTIME */ static inline int pm_runtime_idle(struct device *dev) -- cgit v1.2.3 From 23e0fc5ae64925e0ff1b6221b83dff1b217545df Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 29 Apr 2012 22:54:47 +0200 Subject: PM / QoS: Create device constraints objects on notifier registration The current behavior of dev_pm_qos_add_notifier() makes device PM QoS notifiers less than useful. Namely, it silently returns success when called before any PM QoS constraints are added for the device, so the caller will assume that the notifier has been registered, but when someone actually adds some nontrivial constraints for the device eventually, the previous callers of dev_pm_qos_add_notifier() will not know about that and their notifier routines will not be executed (contrary to their expectations). To address this problem make dev_pm_qos_add_notifier() create the constraints object for the device if it is not present when the routine is called. Signed-off-by: Rafael J. Wysocki Acked-by : markgross --- drivers/base/power/qos.c | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c index 71855570922d..fd849a2c4fa8 100644 --- a/drivers/base/power/qos.c +++ b/drivers/base/power/qos.c @@ -352,21 +352,26 @@ EXPORT_SYMBOL_GPL(dev_pm_qos_remove_request); * * Will register the notifier into a notification chain that gets called * upon changes to the target value for the device. + * + * If the device's constraints object doesn't exist when this routine is called, + * it will be created (or error code will be returned if that fails). */ int dev_pm_qos_add_notifier(struct device *dev, struct notifier_block *notifier) { - int retval = 0; + int ret = 0; mutex_lock(&dev_pm_qos_mtx); - /* Silently return if the constraints object is not present. */ - if (dev->power.constraints) - retval = blocking_notifier_chain_register( - dev->power.constraints->notifiers, - notifier); + if (!dev->power.constraints) + ret = dev->power.power_state.event != PM_EVENT_INVALID ? + dev_pm_qos_constraints_allocate(dev) : -ENODEV; + + if (!ret) + ret = blocking_notifier_chain_register( + dev->power.constraints->notifiers, notifier); mutex_unlock(&dev_pm_qos_mtx); - return retval; + return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_add_notifier); -- cgit v1.2.3 From 698cd2ddd851b34e7200b4f846ae68306e11bae4 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 3 May 2012 18:15:12 +0100 Subject: devres: Clarify documentation for devres_destroy() It's not massively obvious (at least to me) that removing and freeing a resource does not involve calling the release function for the resource but rather only removes the management of it. Make the documentation more explicit. Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/base/devres.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'drivers/base') diff --git a/drivers/base/devres.c b/drivers/base/devres.c index 524bf96c289f..1741a60de117 100644 --- a/drivers/base/devres.c +++ b/drivers/base/devres.c @@ -309,6 +309,10 @@ EXPORT_SYMBOL_GPL(devres_remove); * which @match returns 1. If @match is NULL, it's considered to * match all. If found, the resource is removed atomically and freed. * + * Note that the release function for the resource will not be called, + * only the devres-allocated data will be freed. The caller becomes + * responsible for freeing any other data. + * * RETURNS: * 0 if devres is found and freed, -ENOENT if not found. */ -- cgit v1.2.3 From d926d0e4c74cfcb42a05e91d1cdf698b41e1e118 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 3 May 2012 18:15:13 +0100 Subject: devres: Add devres_release() APIs using devres frequently want to implement a "remove and free the resource" operation so it seems sensible that they should be able to just have devres do the freeing for them since that's a big part of what devres is all about. Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- drivers/base/devres.c | 31 +++++++++++++++++++++++++++++++ include/linux/device.h | 2 ++ 2 files changed, 33 insertions(+) (limited to 'drivers/base') diff --git a/drivers/base/devres.c b/drivers/base/devres.c index 1741a60de117..2360adb7a58f 100644 --- a/drivers/base/devres.c +++ b/drivers/base/devres.c @@ -330,6 +330,37 @@ int devres_destroy(struct device *dev, dr_release_t release, } EXPORT_SYMBOL_GPL(devres_destroy); + +/** + * devres_release - Find a device resource and destroy it, calling release + * @dev: Device to find resource from + * @release: Look for resources associated with this release function + * @match: Match function (optional) + * @match_data: Data for the match function + * + * Find the latest devres of @dev associated with @release and for + * which @match returns 1. If @match is NULL, it's considered to + * match all. If found, the resource is removed atomically, the + * release function called and the resource freed. + * + * RETURNS: + * 0 if devres is found and freed, -ENOENT if not found. + */ +int devres_release(struct device *dev, dr_release_t release, + dr_match_t match, void *match_data) +{ + void *res; + + res = devres_remove(dev, release, match, match_data); + if (unlikely(!res)) + return -ENOENT; + + (*release)(dev, res); + devres_free(res); + return 0; +} +EXPORT_SYMBOL_GPL(devres_release); + static int remove_nodes(struct device *dev, struct list_head *first, struct list_head *end, struct list_head *todo) diff --git a/include/linux/device.h b/include/linux/device.h index 3ab4d63609b6..863acf8a0dce 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -541,6 +541,8 @@ extern void *devres_remove(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); extern int devres_destroy(struct device *dev, dr_release_t release, dr_match_t match, void *match_data); +extern int devres_release(struct device *dev, dr_release_t release, + dr_match_t match, void *match_data); /* devres group */ extern void * __must_check devres_open_group(struct device *dev, void *id, -- cgit v1.2.3 From efa6902501ffc87d69bfb10b8a09b7d6ee222d77 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 1 May 2012 21:33:53 +0200 Subject: PM / Domains: Make device removal more straightforward The removal of a device from a PM domain doesn't have to browse the domain's device list, because it can check directly if the device belongs to the given domain. Moreover, it should clear the domain_data pointer in dev->power.subsys_data, because dev_pm_put_subsys_data(dev) may not remove dev->power.subsys_data and the stale domain data pointer may cause problems to happen. Rework pm_genpd_remove_device() taking the above observations into account. Signed-off-by: Rafael J. Wysocki --- drivers/base/power/domain.c | 27 +++++++++++---------------- 1 file changed, 11 insertions(+), 16 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index 45c2b7f0fe3b..6ae5672c35ab 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -1279,11 +1279,13 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd, struct device *dev) { struct pm_domain_data *pdd; - int ret = -EINVAL; + int ret = 0; dev_dbg(dev, "%s()\n", __func__); - if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(dev)) + if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(dev) + || IS_ERR_OR_NULL(dev->pm_domain) + || pd_to_genpd(dev->pm_domain) != genpd) return -EINVAL; genpd_acquire_lock(genpd); @@ -1293,21 +1295,14 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd, goto out; } - list_for_each_entry(pdd, &genpd->dev_list, list_node) { - if (pdd->dev != dev) - continue; - - list_del_init(&pdd->list_node); - pdd->dev = NULL; - dev_pm_put_subsys_data(dev); - dev->pm_domain = NULL; - kfree(to_gpd_data(pdd)); - - genpd->device_count--; + dev->pm_domain = NULL; + pdd = dev->power.subsys_data->domain_data; + list_del_init(&pdd->list_node); + dev->power.subsys_data->domain_data = NULL; + dev_pm_put_subsys_data(dev); + kfree(to_gpd_data(pdd)); - ret = 0; - break; - } + genpd->device_count--; out: genpd_release_lock(genpd); -- cgit v1.2.3 From 6ff7bb0d02f82968be13937c03e93b6c090229df Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 1 May 2012 21:34:07 +0200 Subject: PM / Domains: Cache device stop and domain power off governor results, v3 The results of the default device stop and domain power off governor functions for generic PM domains, default_stop_ok() and default_power_down_ok(), depend only on the timing data of devices, which are static, and on their PM QoS constraints. Thus, in theory, these functions only need to carry out their computations, which may be time consuming in general, when it is known that the PM QoS constraint of at least one of the devices in question has changed. Use the PM QoS notifiers of devices to implement that. First, introduce new fields, constraint_changed and max_off_time_changed, into struct gpd_timing_data and struct generic_pm_domain, respectively, and register a PM QoS notifier function when adding a device into a domain that will set those fields to 'true' whenever the device's PM QoS constraint is modified. Second, make default_stop_ok() and default_power_down_ok() use those fields to decide whether or not to carry out their computations from scratch. The device and PM domain hierarchies are taken into account in that and the expense is that the changes of PM QoS constraints of suspended devices will not be taken into account immediately, which isn't guaranteed anyway in general. Signed-off-by: Rafael J. Wysocki --- drivers/base/power/domain.c | 120 ++++++++++++++++++++++++++++++----- drivers/base/power/domain_governor.c | 45 ++++++++++++- include/linux/pm_domain.h | 7 ++ 3 files changed, 153 insertions(+), 19 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index 6ae5672c35ab..cde5983de6c2 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -38,11 +39,13 @@ ktime_t __start = ktime_get(); \ type __retval = GENPD_DEV_CALLBACK(genpd, type, callback, dev); \ s64 __elapsed = ktime_to_ns(ktime_sub(ktime_get(), __start)); \ - struct generic_pm_domain_data *__gpd_data = dev_gpd_data(dev); \ - if (__elapsed > __gpd_data->td.field) { \ - __gpd_data->td.field = __elapsed; \ + struct gpd_timing_data *__td = &dev_gpd_data(dev)->td; \ + if (!__retval && __elapsed > __td->field) { \ + __td->field = __elapsed; \ dev_warn(dev, name " latency exceeded, new value %lld ns\n", \ __elapsed); \ + genpd->max_off_time_changed = true; \ + __td->constraint_changed = true; \ } \ __retval; \ }) @@ -211,6 +214,7 @@ int __pm_genpd_poweron(struct generic_pm_domain *genpd) elapsed_ns = ktime_to_ns(ktime_sub(ktime_get(), time_start)); if (elapsed_ns > genpd->power_on_latency_ns) { genpd->power_on_latency_ns = elapsed_ns; + genpd->max_off_time_changed = true; if (genpd->name) pr_warning("%s: Power-on latency exceeded, " "new value %lld ns\n", genpd->name, @@ -247,6 +251,53 @@ int pm_genpd_poweron(struct generic_pm_domain *genpd) #ifdef CONFIG_PM_RUNTIME +static int genpd_dev_pm_qos_notifier(struct notifier_block *nb, + unsigned long val, void *ptr) +{ + struct generic_pm_domain_data *gpd_data; + struct device *dev; + + gpd_data = container_of(nb, struct generic_pm_domain_data, nb); + + mutex_lock(&gpd_data->lock); + dev = gpd_data->base.dev; + if (!dev) { + mutex_unlock(&gpd_data->lock); + return NOTIFY_DONE; + } + mutex_unlock(&gpd_data->lock); + + for (;;) { + struct generic_pm_domain *genpd; + struct pm_domain_data *pdd; + + spin_lock_irq(&dev->power.lock); + + pdd = dev->power.subsys_data ? + dev->power.subsys_data->domain_data : NULL; + if (pdd) { + to_gpd_data(pdd)->td.constraint_changed = true; + genpd = dev_to_genpd(dev); + } else { + genpd = ERR_PTR(-ENODATA); + } + + spin_unlock_irq(&dev->power.lock); + + if (!IS_ERR(genpd)) { + mutex_lock(&genpd->lock); + genpd->max_off_time_changed = true; + mutex_unlock(&genpd->lock); + } + + dev = dev->parent; + if (!dev || dev->power.ignore_children) + break; + } + + return NOTIFY_DONE; +} + /** * __pm_genpd_save_device - Save the pre-suspend state of a device. * @pdd: Domain data of the device to save the state of. @@ -381,7 +432,6 @@ static int pm_genpd_poweroff(struct generic_pm_domain *genpd) return 0; } - genpd->max_off_time_ns = -1; if (genpd->gov && genpd->gov->power_down_ok) { if (!genpd->gov->power_down_ok(&genpd->domain)) return -EAGAIN; @@ -436,6 +486,7 @@ static int pm_genpd_poweroff(struct generic_pm_domain *genpd) elapsed_ns = ktime_to_ns(ktime_sub(ktime_get(), time_start)); if (elapsed_ns > genpd->power_off_latency_ns) { genpd->power_off_latency_ns = elapsed_ns; + genpd->max_off_time_changed = true; if (genpd->name) pr_warning("%s: Power-off latency exceeded, " "new value %lld ns\n", genpd->name, @@ -496,7 +547,6 @@ static int pm_genpd_runtime_suspend(struct device *dev) if (dev_gpd_data(dev)->always_on) return -EBUSY; - dev_gpd_data(dev)->td.effective_constraint_ns = -1; stop_ok = genpd->gov ? genpd->gov->stop_ok : NULL; if (stop_ok && !stop_ok(dev)) return -EBUSY; @@ -601,6 +651,12 @@ void pm_genpd_poweroff_unused(void) #else +static inline int genpd_dev_pm_qos_notifier(struct notifier_block *nb, + unsigned long val, void *ptr) +{ + return NOTIFY_DONE; +} + static inline void genpd_power_off_work_fn(struct work_struct *work) {} #define pm_genpd_runtime_suspend NULL @@ -1197,6 +1253,14 @@ int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev, if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(dev)) return -EINVAL; + gpd_data = kzalloc(sizeof(*gpd_data), GFP_KERNEL); + if (!gpd_data) + return -ENOMEM; + + mutex_init(&gpd_data->lock); + gpd_data->nb.notifier_call = genpd_dev_pm_qos_notifier; + dev_pm_qos_add_notifier(dev, &gpd_data->nb); + genpd_acquire_lock(genpd); if (genpd->status == GPD_STATE_POWER_OFF) { @@ -1215,26 +1279,35 @@ int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev, goto out; } - gpd_data = kzalloc(sizeof(*gpd_data), GFP_KERNEL); - if (!gpd_data) { - ret = -ENOMEM; - goto out; - } - genpd->device_count++; + genpd->max_off_time_changed = true; - dev->pm_domain = &genpd->domain; dev_pm_get_subsys_data(dev); + + mutex_lock(&gpd_data->lock); + spin_lock_irq(&dev->power.lock); + dev->pm_domain = &genpd->domain; dev->power.subsys_data->domain_data = &gpd_data->base; gpd_data->base.dev = dev; - gpd_data->need_restore = false; list_add_tail(&gpd_data->base.list_node, &genpd->dev_list); + gpd_data->need_restore = false; if (td) gpd_data->td = *td; + gpd_data->td.constraint_changed = true; + gpd_data->td.effective_constraint_ns = -1; + spin_unlock_irq(&dev->power.lock); + mutex_unlock(&gpd_data->lock); + + genpd_release_lock(genpd); + + return 0; + out: genpd_release_lock(genpd); + dev_pm_qos_remove_notifier(dev, &gpd_data->nb); + kfree(gpd_data); return ret; } @@ -1278,6 +1351,7 @@ int __pm_genpd_of_add_device(struct device_node *genpd_node, struct device *dev, int pm_genpd_remove_device(struct generic_pm_domain *genpd, struct device *dev) { + struct generic_pm_domain_data *gpd_data; struct pm_domain_data *pdd; int ret = 0; @@ -1295,14 +1369,27 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd, goto out; } + genpd->device_count--; + genpd->max_off_time_changed = true; + + spin_lock_irq(&dev->power.lock); dev->pm_domain = NULL; pdd = dev->power.subsys_data->domain_data; list_del_init(&pdd->list_node); dev->power.subsys_data->domain_data = NULL; - dev_pm_put_subsys_data(dev); - kfree(to_gpd_data(pdd)); + spin_unlock_irq(&dev->power.lock); - genpd->device_count--; + gpd_data = to_gpd_data(pdd); + mutex_lock(&gpd_data->lock); + pdd->dev = NULL; + mutex_unlock(&gpd_data->lock); + + genpd_release_lock(genpd); + + dev_pm_qos_remove_notifier(dev, &gpd_data->nb); + kfree(gpd_data); + dev_pm_put_subsys_data(dev); + return 0; out: genpd_release_lock(genpd); @@ -1673,6 +1760,7 @@ void pm_genpd_init(struct generic_pm_domain *genpd, genpd->resume_count = 0; genpd->device_count = 0; genpd->max_off_time_ns = -1; + genpd->max_off_time_changed = true; genpd->domain.ops.runtime_suspend = pm_genpd_runtime_suspend; genpd->domain.ops.runtime_resume = pm_genpd_runtime_resume; genpd->domain.ops.runtime_idle = pm_generic_runtime_idle; diff --git a/drivers/base/power/domain_governor.c b/drivers/base/power/domain_governor.c index 2aae623fd840..3a5c5346bc47 100644 --- a/drivers/base/power/domain_governor.c +++ b/drivers/base/power/domain_governor.c @@ -46,18 +46,34 @@ static int dev_update_qos_constraint(struct device *dev, void *data) bool default_stop_ok(struct device *dev) { struct gpd_timing_data *td = &dev_gpd_data(dev)->td; + unsigned long flags; s64 constraint_ns; dev_dbg(dev, "%s()\n", __func__); - constraint_ns = dev_pm_qos_read_value(dev); + spin_lock_irqsave(&dev->power.lock, flags); + + if (!td->constraint_changed) { + bool ret = td->cached_stop_ok; + + spin_unlock_irqrestore(&dev->power.lock, flags); + return ret; + } + td->constraint_changed = false; + td->cached_stop_ok = false; + td->effective_constraint_ns = -1; + constraint_ns = __dev_pm_qos_read_value(dev); + + spin_unlock_irqrestore(&dev->power.lock, flags); + if (constraint_ns < 0) return false; constraint_ns *= NSEC_PER_USEC; /* * We can walk the children without any additional locking, because - * they all have been suspended at this point. + * they all have been suspended at this point and their + * effective_constraint_ns fields won't be modified in parallel with us. */ if (!dev->power.ignore_children) device_for_each_child(dev, &constraint_ns, @@ -69,11 +85,13 @@ bool default_stop_ok(struct device *dev) return false; } td->effective_constraint_ns = constraint_ns; + td->cached_stop_ok = constraint_ns > td->stop_latency_ns || + constraint_ns == 0; /* * The children have been suspended already, so we don't need to take * their stop latencies into account here. */ - return constraint_ns > td->stop_latency_ns || constraint_ns == 0; + return td->cached_stop_ok; } /** @@ -90,6 +108,25 @@ static bool default_power_down_ok(struct dev_pm_domain *pd) s64 min_dev_off_time_ns; s64 off_on_time_ns; + if (genpd->max_off_time_changed) { + struct gpd_link *link; + + /* + * We have to invalidate the cached results for the masters, so + * use the observation that default_power_down_ok() is not + * going to be called for any master until this instance + * returns. + */ + list_for_each_entry(link, &genpd->slave_links, slave_node) + link->master->max_off_time_changed = true; + + genpd->max_off_time_changed = false; + genpd->cached_power_down_ok = false; + genpd->max_off_time_ns = -1; + } else { + return genpd->cached_power_down_ok; + } + off_on_time_ns = genpd->power_off_latency_ns + genpd->power_on_latency_ns; /* @@ -165,6 +202,8 @@ static bool default_power_down_ok(struct dev_pm_domain *pd) min_dev_off_time_ns = constraint_ns; } + genpd->cached_power_down_ok = true; + /* * If the computed minimum device off time is negative, there are no * latency constraints, so the domain can spend arbitrary time in the diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index e7ada5ccdfc2..1e994eeacdf3 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -14,6 +14,7 @@ #include #include #include +#include enum gpd_status { GPD_STATE_ACTIVE = 0, /* PM domain is active */ @@ -71,6 +72,8 @@ struct generic_pm_domain { s64 power_on_latency_ns; struct gpd_dev_ops dev_ops; s64 max_off_time_ns; /* Maximum allowed "suspended" time. */ + bool max_off_time_changed; + bool cached_power_down_ok; struct device_node *of_node; /* Node in device tree */ }; @@ -92,12 +95,16 @@ struct gpd_timing_data { s64 save_state_latency_ns; s64 restore_state_latency_ns; s64 effective_constraint_ns; + bool constraint_changed; + bool cached_stop_ok; }; struct generic_pm_domain_data { struct pm_domain_data base; struct gpd_dev_ops ops; struct gpd_timing_data td; + struct notifier_block nb; + struct mutex lock; bool need_restore; bool always_on; }; -- cgit v1.2.3 From c4e00daaa96d3a0786f1f4fe6456281c60ef9a16 Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Thu, 3 May 2012 02:29:59 +0200 Subject: driver-core: extend dev_printk() to pass structured data Extends dev_printk() to attach a dictionary with a device identifier and the driver core subsystem name to logged messages, which makes dev_prink() reliable machine-readable. In addition to the printed plain text message, it creates these properties: SUBSYSTEM= - the driver-core subsytem name DEVICE= b12:8 - block dev_t c127:3 - char dev_t n8 - netdev ifindex +sound:card0 - subsystem:devname Tested-by: William Douglas Signed-off-by: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 52 +++++++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 49 insertions(+), 3 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/core.c b/drivers/base/core.c index 33461ec35d8f..346be8b78b24 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -25,6 +25,7 @@ #include #include #include +#include #include "base.h" #include "power/power.h" @@ -1843,15 +1844,60 @@ void device_shutdown(void) */ #ifdef CONFIG_PRINTK - int __dev_printk(const char *level, const struct device *dev, struct va_format *vaf) { + char dict[128]; + size_t dictlen = 0; + const char *subsys; + if (!dev) return printk("%s(NULL device *): %pV", level, vaf); - return printk("%s%s %s: %pV", - level, dev_driver_string(dev), dev_name(dev), vaf); + if (dev->class) + subsys = dev->class->name; + else if (dev->bus) + subsys = dev->bus->name; + else + goto skip; + + dictlen += snprintf(dict + dictlen, sizeof(dict) - dictlen, + "SUBSYSTEM=%s", subsys); + + /* + * Add device identifier DEVICE=: + * b12:8 block dev_t + * c127:3 char dev_t + * n8 netdev ifindex + * +sound:card0 subsystem:devname + */ + if (MAJOR(dev->devt)) { + char c; + + if (strcmp(subsys, "block") == 0) + c = 'b'; + else + c = 'c'; + dictlen++; + dictlen += snprintf(dict + dictlen, sizeof(dict) - dictlen, + "DEVICE=%c%u:%u", + c, MAJOR(dev->devt), MINOR(dev->devt)); + } else if (strcmp(subsys, "net") == 0) { + struct net_device *net = to_net_dev(dev); + + dictlen++; + dictlen += snprintf(dict + dictlen, sizeof(dict) - dictlen, + "DEVICE=n%u", net->ifindex); + } else { + dictlen++; + dictlen += snprintf(dict + dictlen, sizeof(dict) - dictlen, + "DEVICE=+%s:%s", subsys, dev_name(dev)); + } +skip: + return printk_emit(0, level[1] - '0', + dictlen ? dict : NULL, dictlen, + "%s %s: %pV", + dev_driver_string(dev), dev_name(dev), vaf); } EXPORT_SYMBOL(__dev_printk); -- cgit v1.2.3 From 72b39f6f2b5a6b0beff14b80bed9756f151218a9 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 8 May 2012 17:44:40 +0100 Subject: regmap: Implement dev_get_regmap() Use devres to implement dev_get_regmap(). This should mean that in almost all cases devices wishing to take advantage of framework features based on regmap shouldn't need to explicitly pass the regmap into the framework. This simplifies device setup a bit. Signed-off-by: Mark Brown --- drivers/base/regmap/internal.h | 1 + drivers/base/regmap/regmap.c | 61 +++++++++++++++++++++++++++++++++++++++++- include/linux/regmap.h | 8 ++++++ 3 files changed, 69 insertions(+), 1 deletion(-) (limited to 'drivers/base') diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h index e46c279f8280..c994bc9bc04f 100644 --- a/drivers/base/regmap/internal.h +++ b/drivers/base/regmap/internal.h @@ -45,6 +45,7 @@ struct regmap { struct regmap_format format; /* Buffer format */ const struct regmap_bus *bus; void *bus_context; + const char *name; #ifdef CONFIG_DEBUG_FS struct dentry *debugfs; diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index ee4fea351220..618173e4c2b1 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -178,6 +178,15 @@ static void regmap_unlock_spinlock(struct regmap *map) spin_unlock(&map->spinlock); } +static void dev_get_regmap_release(struct device *dev, void *res) +{ + /* + * We don't actually have anything to do here; the goal here + * is not to manage the regmap but to provide a simple way to + * get the regmap back given a struct device. + */ +} + /** * regmap_init(): Initialise register map * @@ -195,7 +204,7 @@ struct regmap *regmap_init(struct device *dev, void *bus_context, const struct regmap_config *config) { - struct regmap *map; + struct regmap *map, **m; int ret = -EINVAL; if (!bus || !config) @@ -230,6 +239,7 @@ struct regmap *regmap_init(struct device *dev, map->volatile_reg = config->volatile_reg; map->precious_reg = config->precious_reg; map->cache_type = config->cache_type; + map->name = config->name; if (config->read_flag_mask || config->write_flag_mask) { map->read_flag_mask = config->read_flag_mask; @@ -326,8 +336,19 @@ struct regmap *regmap_init(struct device *dev, if (ret < 0) goto err_free_workbuf; + /* Add a devres resource for dev_get_regmap() */ + m = devres_alloc(dev_get_regmap_release, sizeof(*m), GFP_KERNEL); + if (!m) { + ret = -ENOMEM; + goto err_cache; + } + *m = map; + devres_add(dev, m); + return map; +err_cache: + regcache_exit(map); err_free_workbuf: kfree(map->work_buf); err_map: @@ -431,6 +452,44 @@ void regmap_exit(struct regmap *map) } EXPORT_SYMBOL_GPL(regmap_exit); +static int dev_get_regmap_match(struct device *dev, void *res, void *data) +{ + struct regmap **r = res; + if (!r || !*r) { + WARN_ON(!r || !*r); + return 0; + } + + /* If the user didn't specify a name match any */ + if (data) + return (*r)->name == data; + else + return 1; +} + +/** + * dev_get_regmap(): Obtain the regmap (if any) for a device + * + * @dev: Device to retrieve the map for + * @name: Optional name for the register map, usually NULL. + * + * Returns the regmap for the device if one is present, or NULL. If + * name is specified then it must match the name specified when + * registering the device, if it is NULL then the first regmap found + * will be used. Devices with multiple register maps are very rare, + * generic code should normally not need to specify a name. + */ +struct regmap *dev_get_regmap(struct device *dev, const char *name) +{ + struct regmap **r = devres_find(dev, dev_get_regmap_release, + dev_get_regmap_match, (void *)name); + + if (!r) + return NULL; + return *r; +} +EXPORT_SYMBOL_GPL(dev_get_regmap); + static int _regmap_raw_write(struct regmap *map, unsigned int reg, const void *val, size_t val_len) { diff --git a/include/linux/regmap.h b/include/linux/regmap.h index f6abc8d33d64..90a4652eaaea 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -156,6 +156,7 @@ struct regmap *devm_regmap_init_mmio(struct device *dev, void regmap_exit(struct regmap *map); int regmap_reinit_cache(struct regmap *map, const struct regmap_config *config); +struct regmap *dev_get_regmap(struct device *dev, const char *name); int regmap_write(struct regmap *map, unsigned int reg, unsigned int val); int regmap_raw_write(struct regmap *map, unsigned int reg, const void *val, size_t val_len); @@ -340,6 +341,13 @@ static inline int regmap_register_patch(struct regmap *map, return -EINVAL; } +static inline struct regmap *dev_get_regmap(struct device *dev, + const char *name) +{ + WARN_ONCE(1, "regmap API is disabled"); + return NULL; +} + #endif #endif -- cgit v1.2.3 From 4fcac10d28e7a046120b51a106b19082d2e57401 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Mon, 7 May 2012 21:35:45 +0200 Subject: PM / Domains: Fix link checking when add subdomain Current pm_genpd_add_subdomain() will allow duplicated link between master and slave domain. This patch fixed it. Because when current pm_genpd_add_subdomain() checks whether the link between the master and slave generic PM domain already exists, slave_links instead of master_links of master domain is used. Signed-off-by: Huang Ying Signed-off-by: Rafael J. Wysocki --- drivers/base/power/domain.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/base') diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index cde5983de6c2..c3eaa08a8f96 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -1448,7 +1448,7 @@ int pm_genpd_add_subdomain(struct generic_pm_domain *genpd, goto out; } - list_for_each_entry(link, &genpd->slave_links, slave_node) { + list_for_each_entry(link, &genpd->master_links, master_node) { if (link->slave == subdomain && link->master == genpd) { ret = -EINVAL; goto out; -- cgit v1.2.3 From b723b0eb91e08a0ee9a401c0b22c0d52966d9daa Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 7 May 2012 22:00:59 +0200 Subject: PM / Domains: Fix computation of maximum domain off time The default domain power off governor function for generic PM domains, default_power_down_ok(), may violate subdomain maximum off time limit by allowing the master domain to be off for too long. Namely, it only finds the minium of all device maximum off times over the domain's devices and uses that to compute the domain's maximum off time, but it should do the same for the subdomains. Fix this problem by modifying default_power_down_ok() to compute the given domain's maximum off time as the difference between the minimum off time over all devices and subdomains in the domain and its power on latency. Signed-off-by: Rafael J. Wysocki --- drivers/base/power/domain_governor.c | 23 ++++++++++++----------- 1 file changed, 12 insertions(+), 11 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/power/domain_governor.c b/drivers/base/power/domain_governor.c index 3a5c5346bc47..28dee3053f1f 100644 --- a/drivers/base/power/domain_governor.c +++ b/drivers/base/power/domain_governor.c @@ -105,7 +105,7 @@ static bool default_power_down_ok(struct dev_pm_domain *pd) struct generic_pm_domain *genpd = pd_to_genpd(pd); struct gpd_link *link; struct pm_domain_data *pdd; - s64 min_dev_off_time_ns; + s64 min_off_time_ns; s64 off_on_time_ns; if (genpd->max_off_time_changed) { @@ -142,6 +142,7 @@ static bool default_power_down_ok(struct dev_pm_domain *pd) to_gpd_data(pdd)->td.save_state_latency_ns; } + min_off_time_ns = -1; /* * Check if subdomains can be off for enough time. * @@ -161,12 +162,14 @@ static bool default_power_down_ok(struct dev_pm_domain *pd) */ if (sd_max_off_ns <= off_on_time_ns) return false; + + if (min_off_time_ns > sd_max_off_ns || min_off_time_ns < 0) + min_off_time_ns = sd_max_off_ns; } /* * Check if the devices in the domain can be off enough time. */ - min_dev_off_time_ns = -1; list_for_each_entry(pdd, &genpd->dev_list, list_node) { struct gpd_timing_data *td; s64 constraint_ns; @@ -197,9 +200,8 @@ static bool default_power_down_ok(struct dev_pm_domain *pd) if (constraint_ns <= off_on_time_ns) return false; - if (min_dev_off_time_ns > constraint_ns - || min_dev_off_time_ns < 0) - min_dev_off_time_ns = constraint_ns; + if (min_off_time_ns > constraint_ns || min_off_time_ns < 0) + min_off_time_ns = constraint_ns; } genpd->cached_power_down_ok = true; @@ -209,16 +211,15 @@ static bool default_power_down_ok(struct dev_pm_domain *pd) * latency constraints, so the domain can spend arbitrary time in the * "off" state. */ - if (min_dev_off_time_ns < 0) + if (min_off_time_ns < 0) return true; /* - * The difference between the computed minimum device off time and the - * time needed to turn the domain on is the maximum theoretical time - * this domain can spend in the "off" state. + * The difference between the computed minimum subdomain or device off + * time and the time needed to turn the domain on is the maximum + * theoretical time this domain can spend in the "off" state. */ - genpd->max_off_time_ns = min_dev_off_time_ns - - genpd->power_on_latency_ns; + genpd->max_off_time_ns = min_off_time_ns - genpd->power_on_latency_ns; return true; } -- cgit v1.2.3 From 2431d0a1d68aabefeee02b93971ee73e8b215697 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Sun, 13 May 2012 11:18:34 +0100 Subject: regmap: Pass back the allocated regmap IRQ controller data It's needed for freeing and for obtaining the IRQ base later on. Signed-off-by: Mark Brown --- drivers/base/regmap/regmap-irq.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'drivers/base') diff --git a/drivers/base/regmap/regmap-irq.c b/drivers/base/regmap/regmap-irq.c index 1befaa7a31cb..f4e6dcfc8504 100644 --- a/drivers/base/regmap/regmap-irq.c +++ b/drivers/base/regmap/regmap-irq.c @@ -192,6 +192,8 @@ int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags, if (!d) return -ENOMEM; + *data = d; + d->status_buf = kzalloc(sizeof(unsigned int) * chip->num_regs, GFP_KERNEL); if (!d->status_buf) -- cgit v1.2.3 From 4af8be67fd9989f4e63a8d1defc1895ed0f7d341 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Sun, 13 May 2012 10:59:56 +0100 Subject: regmap: Convert regmap_irq to use irq_domain This gets us up to date with the recommended current kernel infrastructure and should transparently give us device tree interrupt bindings for any devices using the framework. If an explicit IRQ mapping is passed in then a legacy interrupt range is created, otherwise a simple linear mapping is used. Previously a mapping was mandatory so existing drivers should not be affected. A function regmap_irq_get_virq() is provided to allow drivers to map individual IRQs which should be used in preference to the existing regmap_irq_chip_get_base() which is only valid if a legacy IRQ range is provided. Signed-off-by: Mark Brown --- drivers/base/regmap/regmap-irq.c | 97 +++++++++++++++++++++++++++++----------- drivers/mfd/Kconfig | 3 ++ include/linux/regmap.h | 1 + 3 files changed, 74 insertions(+), 27 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/regmap/regmap-irq.c b/drivers/base/regmap/regmap-irq.c index 0d233cc1c7fa..db5305b37c9d 100644 --- a/drivers/base/regmap/regmap-irq.c +++ b/drivers/base/regmap/regmap-irq.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include "internal.h" @@ -26,6 +27,7 @@ struct regmap_irq_chip_data { struct regmap_irq_chip *chip; int irq_base; + struct irq_domain *domain; void *status_reg_buf; unsigned int *status_buf; @@ -37,7 +39,7 @@ static inline const struct regmap_irq *irq_to_regmap_irq(struct regmap_irq_chip_data *data, int irq) { - return &data->chip->irqs[irq - data->irq_base]; + return &data->chip->irqs[irq]; } static void regmap_irq_lock(struct irq_data *data) @@ -74,7 +76,7 @@ static void regmap_irq_enable(struct irq_data *data) { struct regmap_irq_chip_data *d = irq_data_get_irq_chip_data(data); struct regmap *map = d->map; - const struct regmap_irq *irq_data = irq_to_regmap_irq(d, data->irq); + const struct regmap_irq *irq_data = irq_to_regmap_irq(d, data->hwirq); d->mask_buf[irq_data->reg_offset / map->reg_stride] &= ~irq_data->mask; } @@ -83,7 +85,7 @@ static void regmap_irq_disable(struct irq_data *data) { struct regmap_irq_chip_data *d = irq_data_get_irq_chip_data(data); struct regmap *map = d->map; - const struct regmap_irq *irq_data = irq_to_regmap_irq(d, data->irq); + const struct regmap_irq *irq_data = irq_to_regmap_irq(d, data->hwirq); d->mask_buf[irq_data->reg_offset / map->reg_stride] |= irq_data->mask; } @@ -153,7 +155,7 @@ static irqreturn_t regmap_irq_thread(int irq, void *d) for (i = 0; i < chip->num_irqs; i++) { if (data->status_buf[chip->irqs[i].reg_offset / map->reg_stride] & chip->irqs[i].mask) { - handle_nested_irq(data->irq_base + i); + handle_nested_irq(irq_find_mapping(data->domain, i)); handled = true; } } @@ -164,6 +166,31 @@ static irqreturn_t regmap_irq_thread(int irq, void *d) return IRQ_NONE; } +static int regmap_irq_map(struct irq_domain *h, unsigned int virq, + irq_hw_number_t hw) +{ + struct regmap_irq_chip_data *data = h->host_data; + + irq_set_chip_data(virq, data); + irq_set_chip_and_handler(virq, ®map_irq_chip, handle_edge_irq); + irq_set_nested_thread(virq, 1); + + /* ARM needs us to explicitly flag the IRQ as valid + * and will set them noprobe when we do so. */ +#ifdef CONFIG_ARM + set_irq_flags(virq, IRQF_VALID); +#else + irq_set_noprobe(virq); +#endif + + return 0; +} + +static struct irq_domain_ops regmap_domain_ops = { + .map = regmap_irq_map, + .xlate = irq_domain_xlate_twocell, +}; + /** * regmap_add_irq_chip(): Use standard regmap IRQ controller handling * @@ -184,7 +211,7 @@ int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags, struct regmap_irq_chip_data **data) { struct regmap_irq_chip_data *d; - int cur_irq, i; + int i; int ret = -ENOMEM; for (i = 0; i < chip->num_irqs; i++) { @@ -195,11 +222,13 @@ int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags, return -EINVAL; } - irq_base = irq_alloc_descs(irq_base, 0, chip->num_irqs, 0); - if (irq_base < 0) { - dev_warn(map->dev, "Failed to allocate IRQs: %d\n", - irq_base); - return irq_base; + if (irq_base) { + irq_base = irq_alloc_descs(irq_base, 0, chip->num_irqs, 0); + if (irq_base < 0) { + dev_warn(map->dev, "Failed to allocate IRQs: %d\n", + irq_base); + return irq_base; + } } d = kzalloc(sizeof(*d), GFP_KERNEL); @@ -249,33 +278,31 @@ int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags, } } - /* Register them with genirq */ - for (cur_irq = irq_base; - cur_irq < chip->num_irqs + irq_base; - cur_irq++) { - irq_set_chip_data(cur_irq, d); - irq_set_chip_and_handler(cur_irq, ®map_irq_chip, - handle_edge_irq); - irq_set_nested_thread(cur_irq, 1); - - /* ARM needs us to explicitly flag the IRQ as valid - * and will set them noprobe when we do so. */ -#ifdef CONFIG_ARM - set_irq_flags(cur_irq, IRQF_VALID); -#else - irq_set_noprobe(cur_irq); -#endif + if (irq_base) + d->domain = irq_domain_add_legacy(map->dev->of_node, + chip->num_irqs, irq_base, 0, + ®map_domain_ops, d); + else + d->domain = irq_domain_add_linear(map->dev->of_node, + chip->num_irqs, + ®map_domain_ops, d); + if (!d->domain) { + dev_err(map->dev, "Failed to create IRQ domain\n"); + ret = -ENOMEM; + goto err_alloc; } ret = request_threaded_irq(irq, NULL, regmap_irq_thread, irq_flags, chip->name, d); if (ret != 0) { dev_err(map->dev, "Failed to request IRQ %d: %d\n", irq, ret); - goto err_alloc; + goto err_domain; } return 0; +err_domain: + /* Should really dispose of the domain but... */ err_alloc: kfree(d->mask_buf_def); kfree(d->mask_buf); @@ -298,6 +325,7 @@ void regmap_del_irq_chip(int irq, struct regmap_irq_chip_data *d) return; free_irq(irq, d); + /* We should unmap the domain but... */ kfree(d->mask_buf_def); kfree(d->mask_buf); kfree(d->status_reg_buf); @@ -315,6 +343,21 @@ EXPORT_SYMBOL_GPL(regmap_del_irq_chip); */ int regmap_irq_chip_get_base(struct regmap_irq_chip_data *data) { + WARN_ON(!data->irq_base); return data->irq_base; } EXPORT_SYMBOL_GPL(regmap_irq_chip_get_base); + +/** + * regmap_irq_get_virq(): Map an interrupt on a chip to a virtual IRQ + * + * Useful for drivers to request their own IRQs. + * + * @data: regmap_irq controller to operate on. + * @irq: index of the interrupt requested in the chip IRQs + */ +int regmap_irq_get_virq(struct regmap_irq_chip_data *data, int irq) +{ + return irq_create_mapping(data->domain, irq); +} +EXPORT_SYMBOL_GPL(regmap_irq_get_virq); diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index 11e44386fa9b..697d686927f8 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -376,6 +376,7 @@ config PMIC_DA9052 config MFD_DA9052_SPI bool "Support Dialog Semiconductor DA9052/53 PMIC variants with SPI" + select IRQ_DOMAIN select REGMAP_SPI select REGMAP_IRQ select PMIC_DA9052 @@ -388,6 +389,7 @@ config MFD_DA9052_SPI config MFD_DA9052_I2C bool "Support Dialog Semiconductor DA9052/53 PMIC variants with I2C" + select IRQ_DOMAIN select REGMAP_I2C select REGMAP_IRQ select PMIC_DA9052 @@ -558,6 +560,7 @@ config MFD_WM8994 bool "Support Wolfson Microelectronics WM8994" select MFD_CORE select REGMAP_I2C + select IRQ_DOMAIN select REGMAP_IRQ depends on I2C=y && GENERIC_HARDIRQS help diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 9dbc9a1bec43..720866887ae3 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -245,6 +245,7 @@ int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags, struct regmap_irq_chip_data **data); void regmap_del_irq_chip(int irq, struct regmap_irq_chip_data *data); int regmap_irq_chip_get_base(struct regmap_irq_chip_data *data); +int regmap_irq_get_virq(struct regmap_irq_chip_data *data, int irq); #else -- cgit v1.2.3 From 094e47e9fa79e28f0e51e37400ea6eea35a4ee1f Mon Sep 17 00:00:00 2001 From: Hiroshi DOYU Date: Fri, 11 May 2012 11:03:09 +0300 Subject: Driver Core: don't oops with unregistered driver in driver_find_device() driver_find_device() can be called with an unregistered driver. Need to check driver_private to see if it's populated or not, especially under deferrable probe. In the case that there are 2 drivers, one depends on the other. With -EPROBE_DEFER, two drivers can use deferred probe to ensure that their relative probe order doesn't matter. If dependee driver is probed first, then the dependant's driver_find_device('dependee') succeeds. If the dependant is probed first, then the dependant's driver_find_device('dependee') should return NULL, and the dependant should get -EPROBE_DEFER. driver_find_device() needs to return NULL if it's not populated. In [PATCHv5 2/3] ARM: tegra: Add SMMU enabler in AHB: http://article.gmane.org/gmane.linux.ports.tegra/4658 "tegra_ahb_driver" may not be populated when it's called. For more SMMU/AHB specific discussion, refer to the following thread: https://lkml.org/lkml/2012/5/10/21 Signed-off-by: Hiroshi DOYU Cc: Stephen Warren Signed-off-by: Greg Kroah-Hartman --- drivers/base/driver.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/base') diff --git a/drivers/base/driver.c b/drivers/base/driver.c index 3ec3896c83a6..207c27ddf828 100644 --- a/drivers/base/driver.c +++ b/drivers/base/driver.c @@ -80,7 +80,7 @@ struct device *driver_find_device(struct device_driver *drv, struct klist_iter i; struct device *dev; - if (!drv) + if (!drv || !drv->p) return NULL; klist_iter_init_node(&drv->p->klist_devices, &i, -- cgit v1.2.3 From 022f926a2401c80ed36ebb48a1bffbac08f34d98 Mon Sep 17 00:00:00 2001 From: Graeme Gregory Date: Mon, 14 May 2012 22:40:43 +0900 Subject: regmap: add support for non contiguous status to regmap-irq In some chips the IRQ status registers are not contiguous in the register map but spaced at even spaces. This is an easy case to handle with minor changes. It is assume for this purpose that the stride for status is equal to the stride for mask/ack registers as well. Signed-off-by: Graeme Gregory Signed-off-by: Mark Brown --- drivers/base/regmap/regmap-irq.c | 54 ++++++++++++++++------------------------ include/linux/regmap.h | 2 ++ 2 files changed, 23 insertions(+), 33 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/regmap/regmap-irq.c b/drivers/base/regmap/regmap-irq.c index db5305b37c9d..502cbdbab638 100644 --- a/drivers/base/regmap/regmap-irq.c +++ b/drivers/base/regmap/regmap-irq.c @@ -29,10 +29,11 @@ struct regmap_irq_chip_data { int irq_base; struct irq_domain *domain; - void *status_reg_buf; unsigned int *status_buf; unsigned int *mask_buf; unsigned int *mask_buf_def; + + unsigned int irq_reg_stride; }; static inline const @@ -62,7 +63,8 @@ static void regmap_irq_sync_unlock(struct irq_data *data) */ for (i = 0; i < d->chip->num_regs; i++) { ret = regmap_update_bits(d->map, d->chip->mask_base + - (i * map->reg_stride), + (i * map->reg_stride * + d->irq_reg_stride), d->mask_buf_def[i], d->mask_buf[i]); if (ret != 0) dev_err(d->map->dev, "Failed to sync masks in %x\n", @@ -104,18 +106,8 @@ static irqreturn_t regmap_irq_thread(int irq, void *d) struct regmap_irq_chip *chip = data->chip; struct regmap *map = data->map; int ret, i; - u8 *buf8 = data->status_reg_buf; - u16 *buf16 = data->status_reg_buf; - u32 *buf32 = data->status_reg_buf; bool handled = false; - ret = regmap_bulk_read(map, chip->status_base, data->status_reg_buf, - chip->num_regs); - if (ret != 0) { - dev_err(map->dev, "Failed to read IRQ status: %d\n", ret); - return IRQ_NONE; - } - /* * Ignore masked IRQs and ack if we need to; we ack early so * there is no race between handling and acknowleding the @@ -124,18 +116,13 @@ static irqreturn_t regmap_irq_thread(int irq, void *d) * doing a write per register. */ for (i = 0; i < data->chip->num_regs; i++) { - switch (map->format.val_bytes) { - case 1: - data->status_buf[i] = buf8[i]; - break; - case 2: - data->status_buf[i] = buf16[i]; - break; - case 4: - data->status_buf[i] = buf32[i]; - break; - default: - BUG(); + ret = regmap_read(map, chip->mask_base + (i * map->reg_stride + * data->irq_reg_stride), + &data->status_buf[i]); + + if (ret != 0) { + dev_err(map->dev, "Failed to read IRQ status: %d\n", + ret); return IRQ_NONE; } @@ -143,7 +130,8 @@ static irqreturn_t regmap_irq_thread(int irq, void *d) if (data->status_buf[i] && chip->ack_base) { ret = regmap_write(map, chip->ack_base + - (i * map->reg_stride), + (i * map->reg_stride * + data->irq_reg_stride), data->status_buf[i]); if (ret != 0) dev_err(map->dev, "Failed to ack 0x%x: %d\n", @@ -242,11 +230,6 @@ int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags, if (!d->status_buf) goto err_alloc; - d->status_reg_buf = kzalloc(map->format.val_bytes * chip->num_regs, - GFP_KERNEL); - if (!d->status_reg_buf) - goto err_alloc; - d->mask_buf = kzalloc(sizeof(unsigned int) * chip->num_regs, GFP_KERNEL); if (!d->mask_buf) @@ -260,6 +243,12 @@ int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags, d->map = map; d->chip = chip; d->irq_base = irq_base; + + if (chip->irq_reg_stride) + d->irq_reg_stride = chip->irq_reg_stride; + else + d->irq_reg_stride = 1; + mutex_init(&d->lock); for (i = 0; i < chip->num_irqs; i++) @@ -269,7 +258,8 @@ int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags, /* Mask all the interrupts by default */ for (i = 0; i < chip->num_regs; i++) { d->mask_buf[i] = d->mask_buf_def[i]; - ret = regmap_write(map, chip->mask_base + (i * map->reg_stride), + ret = regmap_write(map, chip->mask_base + (i * map->reg_stride + * d->irq_reg_stride), d->mask_buf[i]); if (ret != 0) { dev_err(map->dev, "Failed to set masks in 0x%x: %d\n", @@ -306,7 +296,6 @@ err_domain: err_alloc: kfree(d->mask_buf_def); kfree(d->mask_buf); - kfree(d->status_reg_buf); kfree(d->status_buf); kfree(d); return ret; @@ -328,7 +317,6 @@ void regmap_del_irq_chip(int irq, struct regmap_irq_chip_data *d) /* We should unmap the domain but... */ kfree(d->mask_buf_def); kfree(d->mask_buf); - kfree(d->status_reg_buf); kfree(d->status_buf); kfree(d); } diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 720866887ae3..56af22ec9aba 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -219,6 +219,7 @@ struct regmap_irq { * @status_base: Base status register address. * @mask_base: Base mask register address. * @ack_base: Base ack address. If zero then the chip is clear on read. + * @irq_reg_stride: Stride to use for chips where registers are not contiguous. * * @num_regs: Number of registers in each control bank. * @irqs: Descriptors for individual IRQs. Interrupt numbers are @@ -231,6 +232,7 @@ struct regmap_irq_chip { unsigned int status_base; unsigned int mask_base; unsigned int ack_base; + unsigned int irq_reg_stride; int num_regs; -- cgit v1.2.3 From 8e7fbcbc22c12414bcc9dfdd683637f58fb32759 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 9 Jan 2012 11:28:35 +0100 Subject: sched: Remove stale power aware scheduling remnants and dysfunctional knobs It's been broken forever (i.e. it's not scheduling in a power aware fashion), as reported by Suresh and others sending patches, and nobody cares enough to fix it properly ... so remove it to make space free for something better. There's various problems with the code as it stands today, first and foremost the user interface which is bound to topology levels and has multiple values per level. This results in a state explosion which the administrator or distro needs to master and almost nobody does. Furthermore large configuration state spaces aren't good, it means the thing doesn't just work right because it's either under so many impossibe to meet constraints, or even if there's an achievable state workloads have to be aware of it precisely and can never meet it for dynamic workloads. So pushing this kind of decision to user-space was a bad idea even with a single knob - it's exponentially worse with knobs on every node of the topology. There is a proposal to replace the user interface with a single 3 state knob: sched_balance_policy := { performance, power, auto } where 'auto' would be the preferred default which looks at things like Battery/AC mode and possible cpufreq state or whatever the hw exposes to show us power use expectations - but there's been no progress on it in the past many months. Aside from that, the actual implementation of the various knobs is known to be broken. There have been sporadic attempts at fixing things but these always stop short of reaching a mergable state. Therefore this wholesale removal with the hopes of spurring people who care to come forward once again and work on a coherent replacement. Signed-off-by: Peter Zijlstra Cc: Suresh Siddha Cc: Arjan van de Ven Cc: Vincent Guittot Cc: Vaidyanathan Srinivasan Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/1326104915.2442.53.camel@twins Signed-off-by: Ingo Molnar --- Documentation/ABI/testing/sysfs-devices-system-cpu | 25 -- Documentation/scheduler/sched-domains.txt | 4 - arch/x86/kernel/smpboot.c | 3 +- drivers/base/cpu.c | 4 - include/linux/cpu.h | 2 - include/linux/sched.h | 47 ---- include/linux/topology.h | 5 - kernel/sched/core.c | 94 ------- kernel/sched/fair.c | 275 +-------------------- tools/power/cpupower/man/cpupower-set.1 | 9 - tools/power/cpupower/utils/helpers/sysfs.c | 35 +-- 11 files changed, 5 insertions(+), 498 deletions(-) (limited to 'drivers/base') diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index e7be75b96e4b..5dab36448b44 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -9,31 +9,6 @@ Description: /sys/devices/system/cpu/cpu#/ -What: /sys/devices/system/cpu/sched_mc_power_savings - /sys/devices/system/cpu/sched_smt_power_savings -Date: June 2006 -Contact: Linux kernel mailing list -Description: Discover and adjust the kernel's multi-core scheduler support. - - Possible values are: - - 0 - No power saving load balance (default value) - 1 - Fill one thread/core/package first for long running threads - 2 - Also bias task wakeups to semi-idle cpu package for power - savings - - sched_mc_power_savings is dependent upon SCHED_MC, which is - itself architecture dependent. - - sched_smt_power_savings is dependent upon SCHED_SMT, which - is itself architecture dependent. - - The two files are independent of each other. It is possible - that one file may be present without the other. - - Introduced by git commit 5c45bf27. - - What: /sys/devices/system/cpu/kernel_max /sys/devices/system/cpu/offline /sys/devices/system/cpu/online diff --git a/Documentation/scheduler/sched-domains.txt b/Documentation/scheduler/sched-domains.txt index b7ee379b651b..443f0c76bab4 100644 --- a/Documentation/scheduler/sched-domains.txt +++ b/Documentation/scheduler/sched-domains.txt @@ -61,10 +61,6 @@ The implementor should read comments in include/linux/sched.h: struct sched_domain fields, SD_FLAG_*, SD_*_INIT to get an idea of the specifics and what to tune. -For SMT, the architecture must define CONFIG_SCHED_SMT and provide a -cpumask_t cpu_sibling_map[NR_CPUS], where cpu_sibling_map[i] is the mask of -all "i"'s siblings as well as "i" itself. - Architectures may retain the regular override the default SD_*_INIT flags while using the generic domain builder in kernel/sched.c if they wish to retain the traditional SMT->SMP->NUMA topology (or some subset of that). This diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index e84c1bbea339..256c20cc5e96 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -429,8 +429,7 @@ const struct cpumask *cpu_coregroup_mask(int cpu) * For perf, we return last level cache shared map. * And for power savings, we return cpu_core_map */ - if ((sched_mc_power_savings || sched_smt_power_savings) && - !(cpu_has(c, X86_FEATURE_AMD_DCM))) + if (!(cpu_has(c, X86_FEATURE_AMD_DCM))) return cpu_core_mask(cpu); else return cpu_llc_shared_mask(cpu); diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index adf937bf4091..63452943abd1 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -330,8 +330,4 @@ void __init cpu_dev_init(void) panic("Failed to register CPU subsystem"); cpu_dev_register_generic(); - -#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) - sched_create_sysfs_power_savings_entries(cpu_subsys.dev_root); -#endif } diff --git a/include/linux/cpu.h b/include/linux/cpu.h index ee28844ae68e..7230bb59a06f 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -36,8 +36,6 @@ extern void cpu_remove_dev_attr(struct device_attribute *attr); extern int cpu_add_dev_attr_group(struct attribute_group *attrs); extern void cpu_remove_dev_attr_group(struct attribute_group *attrs); -extern int sched_create_sysfs_power_savings_entries(struct device *dev); - #ifdef CONFIG_HOTPLUG_CPU extern void unregister_cpu(struct cpu *cpu); extern ssize_t arch_cpu_probe(const char *, size_t); diff --git a/include/linux/sched.h b/include/linux/sched.h index 4a559bf0622f..3d644809c9db 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -855,61 +855,14 @@ enum cpu_idle_type { #define SD_WAKE_AFFINE 0x0020 /* Wake task to waking CPU */ #define SD_PREFER_LOCAL 0x0040 /* Prefer to keep tasks local to this domain */ #define SD_SHARE_CPUPOWER 0x0080 /* Domain members share cpu power */ -#define SD_POWERSAVINGS_BALANCE 0x0100 /* Balance for power savings */ #define SD_SHARE_PKG_RESOURCES 0x0200 /* Domain members share cpu pkg resources */ #define SD_SERIALIZE 0x0400 /* Only a single load balancing instance */ #define SD_ASYM_PACKING 0x0800 /* Place busy groups earlier in the domain */ #define SD_PREFER_SIBLING 0x1000 /* Prefer to place tasks in a sibling domain */ #define SD_OVERLAP 0x2000 /* sched_domains of this level overlap */ -enum powersavings_balance_level { - POWERSAVINGS_BALANCE_NONE = 0, /* No power saving load balance */ - POWERSAVINGS_BALANCE_BASIC, /* Fill one thread/core/package - * first for long running threads - */ - POWERSAVINGS_BALANCE_WAKEUP, /* Also bias task wakeups to semi-idle - * cpu package for power savings - */ - MAX_POWERSAVINGS_BALANCE_LEVELS -}; - -extern int sched_mc_power_savings, sched_smt_power_savings; - -static inline int sd_balance_for_mc_power(void) -{ - if (sched_smt_power_savings) - return SD_POWERSAVINGS_BALANCE; - - if (!sched_mc_power_savings) - return SD_PREFER_SIBLING; - - return 0; -} - -static inline int sd_balance_for_package_power(void) -{ - if (sched_mc_power_savings | sched_smt_power_savings) - return SD_POWERSAVINGS_BALANCE; - - return SD_PREFER_SIBLING; -} - extern int __weak arch_sd_sibiling_asym_packing(void); -/* - * Optimise SD flags for power savings: - * SD_BALANCE_NEWIDLE helps aggressive task consolidation and power savings. - * Keep default SD flags if sched_{smt,mc}_power_saving=0 - */ - -static inline int sd_power_saving_flags(void) -{ - if (sched_mc_power_savings | sched_smt_power_savings) - return SD_BALANCE_NEWIDLE; - - return 0; -} - struct sched_group_power { atomic_t ref; /* diff --git a/include/linux/topology.h b/include/linux/topology.h index 4f59bf36f0af..09558d1daacd 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -98,7 +98,6 @@ int arch_update_cpu_topology(void); | 0*SD_BALANCE_WAKE \ | 1*SD_WAKE_AFFINE \ | 1*SD_SHARE_CPUPOWER \ - | 0*SD_POWERSAVINGS_BALANCE \ | 1*SD_SHARE_PKG_RESOURCES \ | 0*SD_SERIALIZE \ | 0*SD_PREFER_SIBLING \ @@ -134,8 +133,6 @@ int arch_update_cpu_topology(void); | 0*SD_SHARE_CPUPOWER \ | 1*SD_SHARE_PKG_RESOURCES \ | 0*SD_SERIALIZE \ - | sd_balance_for_mc_power() \ - | sd_power_saving_flags() \ , \ .last_balance = jiffies, \ .balance_interval = 1, \ @@ -167,8 +164,6 @@ int arch_update_cpu_topology(void); | 0*SD_SHARE_CPUPOWER \ | 0*SD_SHARE_PKG_RESOURCES \ | 0*SD_SERIALIZE \ - | sd_balance_for_package_power() \ - | sd_power_saving_flags() \ , \ .last_balance = jiffies, \ .balance_interval = 1, \ diff --git a/kernel/sched/core.c b/kernel/sched/core.c index bd314d7cd9f8..24ca677b5457 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5929,8 +5929,6 @@ static const struct cpumask *cpu_cpu_mask(int cpu) return cpumask_of_node(cpu_to_node(cpu)); } -int sched_smt_power_savings = 0, sched_mc_power_savings = 0; - struct sd_data { struct sched_domain **__percpu sd; struct sched_group **__percpu sg; @@ -6322,7 +6320,6 @@ sd_numa_init(struct sched_domain_topology_level *tl, int cpu) | 0*SD_WAKE_AFFINE | 0*SD_PREFER_LOCAL | 0*SD_SHARE_CPUPOWER - | 0*SD_POWERSAVINGS_BALANCE | 0*SD_SHARE_PKG_RESOURCES | 1*SD_SERIALIZE | 0*SD_PREFER_SIBLING @@ -6819,97 +6816,6 @@ match2: mutex_unlock(&sched_domains_mutex); } -#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) -static void reinit_sched_domains(void) -{ - get_online_cpus(); - - /* Destroy domains first to force the rebuild */ - partition_sched_domains(0, NULL, NULL); - - rebuild_sched_domains(); - put_online_cpus(); -} - -static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt) -{ - unsigned int level = 0; - - if (sscanf(buf, "%u", &level) != 1) - return -EINVAL; - - /* - * level is always be positive so don't check for - * level < POWERSAVINGS_BALANCE_NONE which is 0 - * What happens on 0 or 1 byte write, - * need to check for count as well? - */ - - if (level >= MAX_POWERSAVINGS_BALANCE_LEVELS) - return -EINVAL; - - if (smt) - sched_smt_power_savings = level; - else - sched_mc_power_savings = level; - - reinit_sched_domains(); - - return count; -} - -#ifdef CONFIG_SCHED_MC -static ssize_t sched_mc_power_savings_show(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - return sprintf(buf, "%u\n", sched_mc_power_savings); -} -static ssize_t sched_mc_power_savings_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - return sched_power_savings_store(buf, count, 0); -} -static DEVICE_ATTR(sched_mc_power_savings, 0644, - sched_mc_power_savings_show, - sched_mc_power_savings_store); -#endif - -#ifdef CONFIG_SCHED_SMT -static ssize_t sched_smt_power_savings_show(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - return sprintf(buf, "%u\n", sched_smt_power_savings); -} -static ssize_t sched_smt_power_savings_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - return sched_power_savings_store(buf, count, 1); -} -static DEVICE_ATTR(sched_smt_power_savings, 0644, - sched_smt_power_savings_show, - sched_smt_power_savings_store); -#endif - -int __init sched_create_sysfs_power_savings_entries(struct device *dev) -{ - int err = 0; - -#ifdef CONFIG_SCHED_SMT - if (smt_capable()) - err = device_create_file(dev, &dev_attr_sched_smt_power_savings); -#endif -#ifdef CONFIG_SCHED_MC - if (!err && mc_capable()) - err = device_create_file(dev, &dev_attr_sched_mc_power_savings); -#endif - return err; -} -#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */ - /* * Update cpusets according to cpu_active mask. If cpusets are * disabled, cpuset_update_active_cpus() becomes a simple wrapper diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 0b42f4487329..940e6d17cf96 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2721,7 +2721,7 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags) * If power savings logic is enabled for a domain, see if we * are not overloaded, if so, don't balance wider. */ - if (tmp->flags & (SD_POWERSAVINGS_BALANCE|SD_PREFER_LOCAL)) { + if (tmp->flags & (SD_PREFER_LOCAL)) { unsigned long power = 0; unsigned long nr_running = 0; unsigned long capacity; @@ -2734,9 +2734,6 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags) capacity = DIV_ROUND_CLOSEST(power, SCHED_POWER_SCALE); - if (tmp->flags & SD_POWERSAVINGS_BALANCE) - nr_running /= 2; - if (nr_running < capacity) want_sd = 0; } @@ -3435,14 +3432,6 @@ struct sd_lb_stats { unsigned int busiest_group_weight; int group_imb; /* Is there imbalance in this sd */ -#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) - int power_savings_balance; /* Is powersave balance needed for this sd */ - struct sched_group *group_min; /* Least loaded group in sd */ - struct sched_group *group_leader; /* Group which relieves group_min */ - unsigned long min_load_per_task; /* load_per_task in group_min */ - unsigned long leader_nr_running; /* Nr running of group_leader */ - unsigned long min_nr_running; /* Nr running of group_min */ -#endif }; /* @@ -3486,147 +3475,6 @@ static inline int get_sd_load_idx(struct sched_domain *sd, return load_idx; } - -#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) -/** - * init_sd_power_savings_stats - Initialize power savings statistics for - * the given sched_domain, during load balancing. - * - * @sd: Sched domain whose power-savings statistics are to be initialized. - * @sds: Variable containing the statistics for sd. - * @idle: Idle status of the CPU at which we're performing load-balancing. - */ -static inline void init_sd_power_savings_stats(struct sched_domain *sd, - struct sd_lb_stats *sds, enum cpu_idle_type idle) -{ - /* - * Busy processors will not participate in power savings - * balance. - */ - if (idle == CPU_NOT_IDLE || !(sd->flags & SD_POWERSAVINGS_BALANCE)) - sds->power_savings_balance = 0; - else { - sds->power_savings_balance = 1; - sds->min_nr_running = ULONG_MAX; - sds->leader_nr_running = 0; - } -} - -/** - * update_sd_power_savings_stats - Update the power saving stats for a - * sched_domain while performing load balancing. - * - * @group: sched_group belonging to the sched_domain under consideration. - * @sds: Variable containing the statistics of the sched_domain - * @local_group: Does group contain the CPU for which we're performing - * load balancing ? - * @sgs: Variable containing the statistics of the group. - */ -static inline void update_sd_power_savings_stats(struct sched_group *group, - struct sd_lb_stats *sds, int local_group, struct sg_lb_stats *sgs) -{ - - if (!sds->power_savings_balance) - return; - - /* - * If the local group is idle or completely loaded - * no need to do power savings balance at this domain - */ - if (local_group && (sds->this_nr_running >= sgs->group_capacity || - !sds->this_nr_running)) - sds->power_savings_balance = 0; - - /* - * If a group is already running at full capacity or idle, - * don't include that group in power savings calculations - */ - if (!sds->power_savings_balance || - sgs->sum_nr_running >= sgs->group_capacity || - !sgs->sum_nr_running) - return; - - /* - * Calculate the group which has the least non-idle load. - * This is the group from where we need to pick up the load - * for saving power - */ - if ((sgs->sum_nr_running < sds->min_nr_running) || - (sgs->sum_nr_running == sds->min_nr_running && - group_first_cpu(group) > group_first_cpu(sds->group_min))) { - sds->group_min = group; - sds->min_nr_running = sgs->sum_nr_running; - sds->min_load_per_task = sgs->sum_weighted_load / - sgs->sum_nr_running; - } - - /* - * Calculate the group which is almost near its - * capacity but still has some space to pick up some load - * from other group and save more power - */ - if (sgs->sum_nr_running + 1 > sgs->group_capacity) - return; - - if (sgs->sum_nr_running > sds->leader_nr_running || - (sgs->sum_nr_running == sds->leader_nr_running && - group_first_cpu(group) < group_first_cpu(sds->group_leader))) { - sds->group_leader = group; - sds->leader_nr_running = sgs->sum_nr_running; - } -} - -/** - * check_power_save_busiest_group - see if there is potential for some power-savings balance - * @env: load balance environment - * @sds: Variable containing the statistics of the sched_domain - * under consideration. - * - * Description: - * Check if we have potential to perform some power-savings balance. - * If yes, set the busiest group to be the least loaded group in the - * sched_domain, so that it's CPUs can be put to idle. - * - * Returns 1 if there is potential to perform power-savings balance. - * Else returns 0. - */ -static inline -int check_power_save_busiest_group(struct lb_env *env, struct sd_lb_stats *sds) -{ - if (!sds->power_savings_balance) - return 0; - - if (sds->this != sds->group_leader || - sds->group_leader == sds->group_min) - return 0; - - env->imbalance = sds->min_load_per_task; - sds->busiest = sds->group_min; - - return 1; - -} -#else /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */ -static inline void init_sd_power_savings_stats(struct sched_domain *sd, - struct sd_lb_stats *sds, enum cpu_idle_type idle) -{ - return; -} - -static inline void update_sd_power_savings_stats(struct sched_group *group, - struct sd_lb_stats *sds, int local_group, struct sg_lb_stats *sgs) -{ - return; -} - -static inline -int check_power_save_busiest_group(struct lb_env *env, struct sd_lb_stats *sds) -{ - return 0; -} -#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */ - - unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu) { return SCHED_POWER_SCALE; @@ -3932,7 +3780,6 @@ static inline void update_sd_lb_stats(struct lb_env *env, if (child && child->flags & SD_PREFER_SIBLING) prefer_sibling = 1; - init_sd_power_savings_stats(env->sd, sds, env->idle); load_idx = get_sd_load_idx(env->sd, env->idle); do { @@ -3981,7 +3828,6 @@ static inline void update_sd_lb_stats(struct lb_env *env, sds->group_imb = sgs.group_imb; } - update_sd_power_savings_stats(sg, sds, local_group, &sgs); sg = sg->next; } while (sg != env->sd->groups); } @@ -4276,12 +4122,6 @@ force_balance: return sds.busiest; out_balanced: - /* - * There is no obvious imbalance. But check if we can do some balancing - * to save power. - */ - if (check_power_save_busiest_group(env, &sds)) - return sds.busiest; ret: env->imbalance = 0; return NULL; @@ -4359,28 +4199,6 @@ static int need_active_balance(struct lb_env *env) */ if ((sd->flags & SD_ASYM_PACKING) && env->src_cpu > env->dst_cpu) return 1; - - /* - * The only task running in a non-idle cpu can be moved to this - * cpu in an attempt to completely freeup the other CPU - * package. - * - * The package power saving logic comes from - * find_busiest_group(). If there are no imbalance, then - * f_b_g() will return NULL. However when sched_mc={1,2} then - * f_b_g() will select a group from which a running task may be - * pulled to this cpu in order to make the other package idle. - * If there is no opportunity to make a package idle and if - * there are no imbalance, then f_b_g() will return NULL and no - * action will be taken in load_balance_newidle(). - * - * Under normal task pull operation due to imbalance, there - * will be more than one task in the source run queue and - * move_tasks() will succeed. ld_moved will be true and this - * active balance code will not be triggered. - */ - if (sched_mc_power_savings < POWERSAVINGS_BALANCE_WAKEUP) - return 0; } return unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2); @@ -4700,104 +4518,15 @@ static struct { unsigned long next_balance; /* in jiffy units */ } nohz ____cacheline_aligned; -#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) -/** - * lowest_flag_domain - Return lowest sched_domain containing flag. - * @cpu: The cpu whose lowest level of sched domain is to - * be returned. - * @flag: The flag to check for the lowest sched_domain - * for the given cpu. - * - * Returns the lowest sched_domain of a cpu which contains the given flag. - */ -static inline struct sched_domain *lowest_flag_domain(int cpu, int flag) -{ - struct sched_domain *sd; - - for_each_domain(cpu, sd) - if (sd->flags & flag) - break; - - return sd; -} - -/** - * for_each_flag_domain - Iterates over sched_domains containing the flag. - * @cpu: The cpu whose domains we're iterating over. - * @sd: variable holding the value of the power_savings_sd - * for cpu. - * @flag: The flag to filter the sched_domains to be iterated. - * - * Iterates over all the scheduler domains for a given cpu that has the 'flag' - * set, starting from the lowest sched_domain to the highest. - */ -#define for_each_flag_domain(cpu, sd, flag) \ - for (sd = lowest_flag_domain(cpu, flag); \ - (sd && (sd->flags & flag)); sd = sd->parent) - -/** - * find_new_ilb - Finds the optimum idle load balancer for nomination. - * @cpu: The cpu which is nominating a new idle_load_balancer. - * - * Returns: Returns the id of the idle load balancer if it exists, - * Else, returns >= nr_cpu_ids. - * - * This algorithm picks the idle load balancer such that it belongs to a - * semi-idle powersavings sched_domain. The idea is to try and avoid - * completely idle packages/cores just for the purpose of idle load balancing - * when there are other idle cpu's which are better suited for that job. - */ -static int find_new_ilb(int cpu) +static inline int find_new_ilb(int call_cpu) { int ilb = cpumask_first(nohz.idle_cpus_mask); - struct sched_group *ilbg; - struct sched_domain *sd; - /* - * Have idle load balancer selection from semi-idle packages only - * when power-aware load balancing is enabled - */ - if (!(sched_smt_power_savings || sched_mc_power_savings)) - goto out_done; - - /* - * Optimize for the case when we have no idle CPUs or only one - * idle CPU. Don't walk the sched_domain hierarchy in such cases - */ - if (cpumask_weight(nohz.idle_cpus_mask) < 2) - goto out_done; - - rcu_read_lock(); - for_each_flag_domain(cpu, sd, SD_POWERSAVINGS_BALANCE) { - ilbg = sd->groups; - - do { - if (ilbg->group_weight != - atomic_read(&ilbg->sgp->nr_busy_cpus)) { - ilb = cpumask_first_and(nohz.idle_cpus_mask, - sched_group_cpus(ilbg)); - goto unlock; - } - - ilbg = ilbg->next; - - } while (ilbg != sd->groups); - } -unlock: - rcu_read_unlock(); - -out_done: if (ilb < nr_cpu_ids && idle_cpu(ilb)) return ilb; return nr_cpu_ids; } -#else /* (CONFIG_SCHED_MC || CONFIG_SCHED_SMT) */ -static inline int find_new_ilb(int call_cpu) -{ - return nr_cpu_ids; -} -#endif /* * Kick a CPU to do the nohz balancing, if it is time for it. We pick the diff --git a/tools/power/cpupower/man/cpupower-set.1 b/tools/power/cpupower/man/cpupower-set.1 index c4954a9fe4e7..9dbd536518ab 100644 --- a/tools/power/cpupower/man/cpupower-set.1 +++ b/tools/power/cpupower/man/cpupower-set.1 @@ -85,15 +85,6 @@ Possible values are: savings .RE -sched_mc_power_savings is dependent upon SCHED_MC, which is -itself architecture dependent. - -sched_smt_power_savings is dependent upon SCHED_SMT, which -is itself architecture dependent. - -The two files are independent of each other. It is possible -that one file may be present without the other. - .SH "SEE ALSO" cpupower-info(1), cpupower-monitor(1), powertop(1) .PP diff --git a/tools/power/cpupower/utils/helpers/sysfs.c b/tools/power/cpupower/utils/helpers/sysfs.c index c6343024a611..96e28c124b5c 100644 --- a/tools/power/cpupower/utils/helpers/sysfs.c +++ b/tools/power/cpupower/utils/helpers/sysfs.c @@ -362,22 +362,7 @@ char *sysfs_get_cpuidle_driver(void) */ int sysfs_get_sched(const char *smt_mc) { - unsigned long value; - char linebuf[MAX_LINE_LEN]; - char *endp; - char path[SYSFS_PATH_MAX]; - - if (strcmp("mc", smt_mc) && strcmp("smt", smt_mc)) - return -EINVAL; - - snprintf(path, sizeof(path), - PATH_TO_CPU "sched_%s_power_savings", smt_mc); - if (sysfs_read_file(path, linebuf, MAX_LINE_LEN) == 0) - return -1; - value = strtoul(linebuf, &endp, 0); - if (endp == linebuf || errno == ERANGE) - return -1; - return value; + return -ENODEV; } /* @@ -388,21 +373,5 @@ int sysfs_get_sched(const char *smt_mc) */ int sysfs_set_sched(const char *smt_mc, int val) { - char linebuf[MAX_LINE_LEN]; - char path[SYSFS_PATH_MAX]; - struct stat statbuf; - - if (strcmp("mc", smt_mc) && strcmp("smt", smt_mc)) - return -EINVAL; - - snprintf(path, sizeof(path), - PATH_TO_CPU "sched_%s_power_savings", smt_mc); - sprintf(linebuf, "%d", val); - - if (stat(path, &statbuf) != 0) - return -ENODEV; - - if (sysfs_write_file(path, linebuf, MAX_LINE_LEN) == 0) - return -1; - return 0; + return -ENODEV; } -- cgit v1.2.3 From 38e7f5d1b73e71f87745a9c3e5806a6c28c34a53 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 17 May 2012 13:59:40 +0100 Subject: regmap: Fix typo in IRQ register striding Signed-off-by: Mark Brown --- drivers/base/regmap/regmap-irq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/base') diff --git a/drivers/base/regmap/regmap-irq.c b/drivers/base/regmap/regmap-irq.c index 502cbdbab638..4fac4b9be88f 100644 --- a/drivers/base/regmap/regmap-irq.c +++ b/drivers/base/regmap/regmap-irq.c @@ -116,7 +116,7 @@ static irqreturn_t regmap_irq_thread(int irq, void *d) * doing a write per register. */ for (i = 0; i < data->chip->num_regs; i++) { - ret = regmap_read(map, chip->mask_base + (i * map->reg_stride + ret = regmap_read(map, chip->status_base + (i * map->reg_stride * data->irq_reg_stride), &data->status_buf[i]); -- cgit v1.2.3 From ca1d72f033d4a89e60db25f680896c76c721062b Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 14 May 2012 21:45:52 +0200 Subject: PM / Domains: Make it possible to add devices to inactive domains The generic PM domains core code currently requires domains to be in the "power on" state for adding devices to them, but this limitation turns out to be inconvenient in some situations, so remove it. For this purpose, make __pm_genpd_add_device() set the device's need_restore flag if the domain is in the "power off" state, so that the device's "restore state" (usually .runtime_resume()) callback is executed when it is resumed after the domain has been turned on. If the domain is in the "power on" state, the device's need_restore flag will be cleared by __pm_genpd_add_device(), so that its "save state" (usually .runtime_suspend()) callback is executed when the domain is about to be turned off. However, since that default behavior need not be always desirable, add a helper function pm_genpd_dev_need_restore() allowing a device's need_restore flag to be set/unset at any time. Signed-off-by: Rafael J. Wysocki --- drivers/base/power/domain.c | 27 +++++++++++++++++++++------ include/linux/pm_domain.h | 2 ++ 2 files changed, 23 insertions(+), 6 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index c3eaa08a8f96..83aa694a8efe 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -1263,11 +1263,6 @@ int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev, genpd_acquire_lock(genpd); - if (genpd->status == GPD_STATE_POWER_OFF) { - ret = -EINVAL; - goto out; - } - if (genpd->prepared_count > 0) { ret = -EAGAIN; goto out; @@ -1290,7 +1285,7 @@ int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev, dev->power.subsys_data->domain_data = &gpd_data->base; gpd_data->base.dev = dev; list_add_tail(&gpd_data->base.list_node, &genpd->dev_list); - gpd_data->need_restore = false; + gpd_data->need_restore = genpd->status == GPD_STATE_POWER_OFF; if (td) gpd_data->td = *td; @@ -1417,6 +1412,26 @@ void pm_genpd_dev_always_on(struct device *dev, bool val) } EXPORT_SYMBOL_GPL(pm_genpd_dev_always_on); +/** + * pm_genpd_dev_need_restore - Set/unset the device's "need restore" flag. + * @dev: Device to set/unset the flag for. + * @val: The new value of the device's "need restore" flag. + */ +void pm_genpd_dev_need_restore(struct device *dev, bool val) +{ + struct pm_subsys_data *psd; + unsigned long flags; + + spin_lock_irqsave(&dev->power.lock, flags); + + psd = dev_to_psd(dev); + if (psd && psd->domain_data) + to_gpd_data(psd->domain_data)->need_restore = val; + + spin_unlock_irqrestore(&dev->power.lock, flags); +} +EXPORT_SYMBOL_GPL(pm_genpd_dev_need_restore); + /** * pm_genpd_add_subdomain - Add a subdomain to an I/O PM domain. * @genpd: Master PM domain to add the subdomain to. diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 1e994eeacdf3..30f794eb3826 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -146,6 +146,7 @@ static inline int pm_genpd_of_add_device(struct device_node *genpd_node, extern int pm_genpd_remove_device(struct generic_pm_domain *genpd, struct device *dev); extern void pm_genpd_dev_always_on(struct device *dev, bool val); +extern void pm_genpd_dev_need_restore(struct device *dev, bool val); extern int pm_genpd_add_subdomain(struct generic_pm_domain *genpd, struct generic_pm_domain *new_subdomain); extern int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, @@ -189,6 +190,7 @@ static inline int pm_genpd_remove_device(struct generic_pm_domain *genpd, return -ENOSYS; } static inline void pm_genpd_dev_always_on(struct device *dev, bool val) {} +static inline void pm_genpd_dev_need_restore(struct device *dev, bool val) {} static inline int pm_genpd_add_subdomain(struct generic_pm_domain *genpd, struct generic_pm_domain *new_sd) { -- cgit v1.2.3 From bca0fa5f12a6744a2b2e53154af65a51402b3426 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Fri, 23 Mar 2012 13:05:14 +0100 Subject: common: add dma_mmap_from_coherent() function Add a common helper for dma-mapping core for mapping a coherent buffer to userspace. Reported-by: Subash Patel Signed-off-by: Marek Szyprowski Acked-by: Kyungmin Park Tested-By: Subash Patel --- drivers/base/dma-coherent.c | 42 ++++++++++++++++++++++++++++++++++++++ include/asm-generic/dma-coherent.h | 4 +++- 2 files changed, 45 insertions(+), 1 deletion(-) (limited to 'drivers/base') diff --git a/drivers/base/dma-coherent.c b/drivers/base/dma-coherent.c index bb0025c510b3..1b85949e3d2f 100644 --- a/drivers/base/dma-coherent.c +++ b/drivers/base/dma-coherent.c @@ -10,6 +10,7 @@ struct dma_coherent_mem { void *virt_base; dma_addr_t device_base; + phys_addr_t pfn_base; int size; int flags; unsigned long *bitmap; @@ -44,6 +45,7 @@ int dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr, dev->dma_mem->virt_base = mem_base; dev->dma_mem->device_base = device_addr; + dev->dma_mem->pfn_base = PFN_DOWN(bus_addr); dev->dma_mem->size = pages; dev->dma_mem->flags = flags; @@ -176,3 +178,43 @@ int dma_release_from_coherent(struct device *dev, int order, void *vaddr) return 0; } EXPORT_SYMBOL(dma_release_from_coherent); + +/** + * dma_mmap_from_coherent() - try to mmap the memory allocated from + * per-device coherent memory pool to userspace + * @dev: device from which the memory was allocated + * @vma: vm_area for the userspace memory + * @vaddr: cpu address returned by dma_alloc_from_coherent + * @size: size of the memory buffer allocated by dma_alloc_from_coherent + * + * This checks whether the memory was allocated from the per-device + * coherent memory pool and if so, maps that memory to the provided vma. + * + * Returns 1 if we correctly mapped the memory, or 0 if + * dma_release_coherent() should proceed with mapping memory from + * generic pools. + */ +int dma_mmap_from_coherent(struct device *dev, struct vm_area_struct *vma, + void *vaddr, size_t size, int *ret) +{ + struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL; + + if (mem && vaddr >= mem->virt_base && vaddr + size <= + (mem->virt_base + (mem->size << PAGE_SHIFT))) { + unsigned long off = vma->vm_pgoff; + int start = (vaddr - mem->virt_base) >> PAGE_SHIFT; + int user_count = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; + int count = size >> PAGE_SHIFT; + + *ret = -ENXIO; + if (off < count && user_count <= count - off) { + unsigned pfn = mem->pfn_base + start + off; + *ret = remap_pfn_range(vma, vma->vm_start, pfn, + user_count << PAGE_SHIFT, + vma->vm_page_prot); + } + return 1; + } + return 0; +} +EXPORT_SYMBOL(dma_mmap_from_coherent); diff --git a/include/asm-generic/dma-coherent.h b/include/asm-generic/dma-coherent.h index 85a3ffaa0242..abfb2682de7f 100644 --- a/include/asm-generic/dma-coherent.h +++ b/include/asm-generic/dma-coherent.h @@ -3,13 +3,15 @@ #ifdef CONFIG_HAVE_GENERIC_DMA_COHERENT /* - * These two functions are only for dma allocator. + * These three functions are only for dma allocator. * Don't use them in device drivers. */ int dma_alloc_from_coherent(struct device *dev, ssize_t size, dma_addr_t *dma_handle, void **ret); int dma_release_from_coherent(struct device *dev, int order, void *vaddr); +int dma_mmap_from_coherent(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, size_t size, int *ret); /* * Standard interface */ -- cgit v1.2.3 From c64be2bb1c6eb43c838b2c6d57b074078be208dd Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Thu, 29 Dec 2011 13:09:51 +0100 Subject: drivers: add Contiguous Memory Allocator The Contiguous Memory Allocator is a set of helper functions for DMA mapping framework that improves allocations of contiguous memory chunks. CMA grabs memory on system boot, marks it with MIGRATE_CMA migrate type and gives back to the system. Kernel is allowed to allocate only movable pages within CMA's managed memory so that it can be used for example for page cache when DMA mapping do not use it. On dma_alloc_from_contiguous() request such pages are migrated out of CMA area to free required contiguous block and fulfill the request. This allows to allocate large contiguous chunks of memory at any time assuming that there is enough free memory available in the system. This code is heavily based on earlier works by Michal Nazarewicz. Signed-off-by: Marek Szyprowski Signed-off-by: Kyungmin Park Signed-off-by: Michal Nazarewicz Acked-by: Arnd Bergmann Tested-by: Rob Clark Tested-by: Ohad Ben-Cohen Tested-by: Benjamin Gaignard Tested-by: Robert Nelson Tested-by: Barry Song --- Documentation/kernel-parameters.txt | 5 + arch/Kconfig | 3 + drivers/base/Kconfig | 89 ++++++++ drivers/base/Makefile | 1 + drivers/base/dma-contiguous.c | 401 +++++++++++++++++++++++++++++++++++ include/asm-generic/dma-contiguous.h | 28 +++ include/linux/device.h | 4 + include/linux/dma-contiguous.h | 110 ++++++++++ 8 files changed, 641 insertions(+) create mode 100644 drivers/base/dma-contiguous.c create mode 100644 include/asm-generic/dma-contiguous.h create mode 100644 include/linux/dma-contiguous.h (limited to 'drivers/base') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index c1601e5a8b71..669e8bb52b94 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -508,6 +508,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted. Also note the kernel might malfunction if you disable some critical bits. + cma=nn[MG] [ARM,KNL] + Sets the size of kernel global memory area for contiguous + memory allocations. For more information, see + include/linux/dma-contiguous.h + cmo_free_hint= [PPC] Format: { yes | no } Specify whether pages are marked as being inactive when they are freed. This is used in CMO environments diff --git a/arch/Kconfig b/arch/Kconfig index 684eb5af439d..0a3ffe46e567 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -142,6 +142,9 @@ config HAVE_ARCH_TRACEHOOK config HAVE_DMA_ATTRS bool +config HAVE_DMA_CONTIGUOUS + bool + config USE_GENERIC_SMP_HELPERS bool diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig index 9aa618acfe97..9b21469482ae 100644 --- a/drivers/base/Kconfig +++ b/drivers/base/Kconfig @@ -192,4 +192,93 @@ config DMA_SHARED_BUFFER APIs extension; the file's descriptor can then be passed on to other driver. +config CMA + bool "Contiguous Memory Allocator (EXPERIMENTAL)" + depends on HAVE_DMA_CONTIGUOUS && HAVE_MEMBLOCK && EXPERIMENTAL + select MIGRATION + help + This enables the Contiguous Memory Allocator which allows drivers + to allocate big physically-contiguous blocks of memory for use with + hardware components that do not support I/O map nor scatter-gather. + + For more information see . + If unsure, say "n". + +if CMA + +config CMA_DEBUG + bool "CMA debug messages (DEVELOPMENT)" + depends on DEBUG_KERNEL + help + Turns on debug messages in CMA. This produces KERN_DEBUG + messages for every CMA call as well as various messages while + processing calls such as dma_alloc_from_contiguous(). + This option does not affect warning and error messages. + +comment "Default contiguous memory area size:" + +config CMA_SIZE_MBYTES + int "Size in Mega Bytes" + depends on !CMA_SIZE_SEL_PERCENTAGE + default 16 + help + Defines the size (in MiB) of the default memory area for Contiguous + Memory Allocator. + +config CMA_SIZE_PERCENTAGE + int "Percentage of total memory" + depends on !CMA_SIZE_SEL_MBYTES + default 10 + help + Defines the size of the default memory area for Contiguous Memory + Allocator as a percentage of the total memory in the system. + +choice + prompt "Selected region size" + default CMA_SIZE_SEL_ABSOLUTE + +config CMA_SIZE_SEL_MBYTES + bool "Use mega bytes value only" + +config CMA_SIZE_SEL_PERCENTAGE + bool "Use percentage value only" + +config CMA_SIZE_SEL_MIN + bool "Use lower value (minimum)" + +config CMA_SIZE_SEL_MAX + bool "Use higher value (maximum)" + +endchoice + +config CMA_ALIGNMENT + int "Maximum PAGE_SIZE order of alignment for contiguous buffers" + range 4 9 + default 8 + help + DMA mapping framework by default aligns all buffers to the smallest + PAGE_SIZE order which is greater than or equal to the requested buffer + size. This works well for buffers up to a few hundreds kilobytes, but + for larger buffers it just a memory waste. With this parameter you can + specify the maximum PAGE_SIZE order for contiguous buffers. Larger + buffers will be aligned only to this specified order. The order is + expressed as a power of two multiplied by the PAGE_SIZE. + + For example, if your system defaults to 4KiB pages, the order value + of 8 means that the buffers will be aligned up to 1MiB only. + + If unsure, leave the default value "8". + +config CMA_AREAS + int "Maximum count of the CMA device-private areas" + default 7 + help + CMA allows to create CMA areas for particular devices. This parameter + sets the maximum number of such device private CMA areas in the + system. + + If unsure, leave the default value "7". + +endif + endmenu diff --git a/drivers/base/Makefile b/drivers/base/Makefile index b6d1b9c4200c..5aa2d703d19f 100644 --- a/drivers/base/Makefile +++ b/drivers/base/Makefile @@ -6,6 +6,7 @@ obj-y := core.o bus.o dd.o syscore.o \ attribute_container.o transport_class.o \ topology.o obj-$(CONFIG_DEVTMPFS) += devtmpfs.o +obj-$(CONFIG_CMA) += dma-contiguous.o obj-y += power/ obj-$(CONFIG_HAS_DMA) += dma-mapping.o obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o diff --git a/drivers/base/dma-contiguous.c b/drivers/base/dma-contiguous.c new file mode 100644 index 000000000000..78efb0306a44 --- /dev/null +++ b/drivers/base/dma-contiguous.c @@ -0,0 +1,401 @@ +/* + * Contiguous Memory Allocator for DMA mapping framework + * Copyright (c) 2010-2011 by Samsung Electronics. + * Written by: + * Marek Szyprowski + * Michal Nazarewicz + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 of the + * License or (at your optional) any later version of the license. + */ + +#define pr_fmt(fmt) "cma: " fmt + +#ifdef CONFIG_CMA_DEBUG +#ifndef DEBUG +# define DEBUG +#endif +#endif + +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#ifndef SZ_1M +#define SZ_1M (1 << 20) +#endif + +struct cma { + unsigned long base_pfn; + unsigned long count; + unsigned long *bitmap; +}; + +struct cma *dma_contiguous_default_area; + +#ifdef CONFIG_CMA_SIZE_MBYTES +#define CMA_SIZE_MBYTES CONFIG_CMA_SIZE_MBYTES +#else +#define CMA_SIZE_MBYTES 0 +#endif + +/* + * Default global CMA area size can be defined in kernel's .config. + * This is usefull mainly for distro maintainers to create a kernel + * that works correctly for most supported systems. + * The size can be set in bytes or as a percentage of the total memory + * in the system. + * + * Users, who want to set the size of global CMA area for their system + * should use cma= kernel parameter. + */ +static const unsigned long size_bytes = CMA_SIZE_MBYTES * SZ_1M; +static long size_cmdline = -1; + +static int __init early_cma(char *p) +{ + pr_debug("%s(%s)\n", __func__, p); + size_cmdline = memparse(p, &p); + return 0; +} +early_param("cma", early_cma); + +#ifdef CONFIG_CMA_SIZE_PERCENTAGE + +static unsigned long __init __maybe_unused cma_early_percent_memory(void) +{ + struct memblock_region *reg; + unsigned long total_pages = 0; + + /* + * We cannot use memblock_phys_mem_size() here, because + * memblock_analyze() has not been called yet. + */ + for_each_memblock(memory, reg) + total_pages += memblock_region_memory_end_pfn(reg) - + memblock_region_memory_base_pfn(reg); + + return (total_pages * CONFIG_CMA_SIZE_PERCENTAGE / 100) << PAGE_SHIFT; +} + +#else + +static inline __maybe_unused unsigned long cma_early_percent_memory(void) +{ + return 0; +} + +#endif + +/** + * dma_contiguous_reserve() - reserve area for contiguous memory handling + * @limit: End address of the reserved memory (optional, 0 for any). + * + * This function reserves memory from early allocator. It should be + * called by arch specific code once the early allocator (memblock or bootmem) + * has been activated and all other subsystems have already allocated/reserved + * memory. + */ +void __init dma_contiguous_reserve(phys_addr_t limit) +{ + unsigned long selected_size = 0; + + pr_debug("%s(limit %08lx)\n", __func__, (unsigned long)limit); + + if (size_cmdline != -1) { + selected_size = size_cmdline; + } else { +#ifdef CONFIG_CMA_SIZE_SEL_MBYTES + selected_size = size_bytes; +#elif defined(CONFIG_CMA_SIZE_SEL_PERCENTAGE) + selected_size = cma_early_percent_memory(); +#elif defined(CONFIG_CMA_SIZE_SEL_MIN) + selected_size = min(size_bytes, cma_early_percent_memory()); +#elif defined(CONFIG_CMA_SIZE_SEL_MAX) + selected_size = max(size_bytes, cma_early_percent_memory()); +#endif + } + + if (selected_size) { + pr_debug("%s: reserving %ld MiB for global area\n", __func__, + selected_size / SZ_1M); + + dma_declare_contiguous(NULL, selected_size, 0, limit); + } +}; + +static DEFINE_MUTEX(cma_mutex); + +static __init int cma_activate_area(unsigned long base_pfn, unsigned long count) +{ + unsigned long pfn = base_pfn; + unsigned i = count >> pageblock_order; + struct zone *zone; + + WARN_ON_ONCE(!pfn_valid(pfn)); + zone = page_zone(pfn_to_page(pfn)); + + do { + unsigned j; + base_pfn = pfn; + for (j = pageblock_nr_pages; j; --j, pfn++) { + WARN_ON_ONCE(!pfn_valid(pfn)); + if (page_zone(pfn_to_page(pfn)) != zone) + return -EINVAL; + } + init_cma_reserved_pageblock(pfn_to_page(base_pfn)); + } while (--i); + return 0; +} + +static __init struct cma *cma_create_area(unsigned long base_pfn, + unsigned long count) +{ + int bitmap_size = BITS_TO_LONGS(count) * sizeof(long); + struct cma *cma; + int ret = -ENOMEM; + + pr_debug("%s(base %08lx, count %lx)\n", __func__, base_pfn, count); + + cma = kmalloc(sizeof *cma, GFP_KERNEL); + if (!cma) + return ERR_PTR(-ENOMEM); + + cma->base_pfn = base_pfn; + cma->count = count; + cma->bitmap = kzalloc(bitmap_size, GFP_KERNEL); + + if (!cma->bitmap) + goto no_mem; + + ret = cma_activate_area(base_pfn, count); + if (ret) + goto error; + + pr_debug("%s: returned %p\n", __func__, (void *)cma); + return cma; + +error: + kfree(cma->bitmap); +no_mem: + kfree(cma); + return ERR_PTR(ret); +} + +static struct cma_reserved { + phys_addr_t start; + unsigned long size; + struct device *dev; +} cma_reserved[MAX_CMA_AREAS] __initdata; +static unsigned cma_reserved_count __initdata; + +static int __init cma_init_reserved_areas(void) +{ + struct cma_reserved *r = cma_reserved; + unsigned i = cma_reserved_count; + + pr_debug("%s()\n", __func__); + + for (; i; --i, ++r) { + struct cma *cma; + cma = cma_create_area(PFN_DOWN(r->start), + r->size >> PAGE_SHIFT); + if (!IS_ERR(cma)) + dev_set_cma_area(r->dev, cma); + } + return 0; +} +core_initcall(cma_init_reserved_areas); + +/** + * dma_declare_contiguous() - reserve area for contiguous memory handling + * for particular device + * @dev: Pointer to device structure. + * @size: Size of the reserved memory. + * @base: Start address of the reserved memory (optional, 0 for any). + * @limit: End address of the reserved memory (optional, 0 for any). + * + * This function reserves memory for specified device. It should be + * called by board specific code when early allocator (memblock or bootmem) + * is still activate. + */ +int __init dma_declare_contiguous(struct device *dev, unsigned long size, + phys_addr_t base, phys_addr_t limit) +{ + struct cma_reserved *r = &cma_reserved[cma_reserved_count]; + unsigned long alignment; + + pr_debug("%s(size %lx, base %08lx, limit %08lx)\n", __func__, + (unsigned long)size, (unsigned long)base, + (unsigned long)limit); + + /* Sanity checks */ + if (cma_reserved_count == ARRAY_SIZE(cma_reserved)) { + pr_err("Not enough slots for CMA reserved regions!\n"); + return -ENOSPC; + } + + if (!size) + return -EINVAL; + + /* Sanitise input arguments */ + alignment = PAGE_SIZE << max(MAX_ORDER, pageblock_order); + base = ALIGN(base, alignment); + size = ALIGN(size, alignment); + limit &= ~(alignment - 1); + + /* Reserve memory */ + if (base) { + if (memblock_is_region_reserved(base, size) || + memblock_reserve(base, size) < 0) { + base = -EBUSY; + goto err; + } + } else { + /* + * Use __memblock_alloc_base() since + * memblock_alloc_base() panic()s. + */ + phys_addr_t addr = __memblock_alloc_base(size, alignment, limit); + if (!addr) { + base = -ENOMEM; + goto err; + } else if (addr + size > ~(unsigned long)0) { + memblock_free(addr, size); + base = -EINVAL; + goto err; + } else { + base = addr; + } + } + + /* + * Each reserved area must be initialised later, when more kernel + * subsystems (like slab allocator) are available. + */ + r->start = base; + r->size = size; + r->dev = dev; + cma_reserved_count++; + pr_info("CMA: reserved %ld MiB at %08lx\n", size / SZ_1M, + (unsigned long)base); + + /* Architecture specific contiguous memory fixup. */ + dma_contiguous_early_fixup(base, size); + return 0; +err: + pr_err("CMA: failed to reserve %ld MiB\n", size / SZ_1M); + return base; +} + +/** + * dma_alloc_from_contiguous() - allocate pages from contiguous area + * @dev: Pointer to device for which the allocation is performed. + * @count: Requested number of pages. + * @align: Requested alignment of pages (in PAGE_SIZE order). + * + * This function allocates memory buffer for specified device. It uses + * device specific contiguous memory area if available or the default + * global one. Requires architecture specific get_dev_cma_area() helper + * function. + */ +struct page *dma_alloc_from_contiguous(struct device *dev, int count, + unsigned int align) +{ + unsigned long mask, pfn, pageno, start = 0; + struct cma *cma = dev_get_cma_area(dev); + int ret; + + if (!cma || !cma->count) + return NULL; + + if (align > CONFIG_CMA_ALIGNMENT) + align = CONFIG_CMA_ALIGNMENT; + + pr_debug("%s(cma %p, count %d, align %d)\n", __func__, (void *)cma, + count, align); + + if (!count) + return NULL; + + mask = (1 << align) - 1; + + mutex_lock(&cma_mutex); + + for (;;) { + pageno = bitmap_find_next_zero_area(cma->bitmap, cma->count, + start, count, mask); + if (pageno >= cma->count) { + ret = -ENOMEM; + goto error; + } + + pfn = cma->base_pfn + pageno; + ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA); + if (ret == 0) { + bitmap_set(cma->bitmap, pageno, count); + break; + } else if (ret != -EBUSY) { + goto error; + } + pr_debug("%s(): memory range at %p is busy, retrying\n", + __func__, pfn_to_page(pfn)); + /* try again with a bit different memory target */ + start = pageno + mask + 1; + } + + mutex_unlock(&cma_mutex); + + pr_debug("%s(): returned %p\n", __func__, pfn_to_page(pfn)); + return pfn_to_page(pfn); +error: + mutex_unlock(&cma_mutex); + return NULL; +} + +/** + * dma_release_from_contiguous() - release allocated pages + * @dev: Pointer to device for which the pages were allocated. + * @pages: Allocated pages. + * @count: Number of allocated pages. + * + * This function releases memory allocated by dma_alloc_from_contiguous(). + * It returns false when provided pages do not belong to contiguous area and + * true otherwise. + */ +bool dma_release_from_contiguous(struct device *dev, struct page *pages, + int count) +{ + struct cma *cma = dev_get_cma_area(dev); + unsigned long pfn; + + if (!cma || !pages) + return false; + + pr_debug("%s(page %p)\n", __func__, (void *)pages); + + pfn = page_to_pfn(pages); + + if (pfn < cma->base_pfn || pfn >= cma->base_pfn + cma->count) + return false; + + VM_BUG_ON(pfn + count > cma->base_pfn + cma->count); + + mutex_lock(&cma_mutex); + bitmap_clear(cma->bitmap, pfn - cma->base_pfn, count); + free_contig_range(pfn, count); + mutex_unlock(&cma_mutex); + + return true; +} diff --git a/include/asm-generic/dma-contiguous.h b/include/asm-generic/dma-contiguous.h new file mode 100644 index 000000000000..c544356b374b --- /dev/null +++ b/include/asm-generic/dma-contiguous.h @@ -0,0 +1,28 @@ +#ifndef ASM_DMA_CONTIGUOUS_H +#define ASM_DMA_CONTIGUOUS_H + +#ifdef __KERNEL__ +#ifdef CONFIG_CMA + +#include +#include + +static inline struct cma *dev_get_cma_area(struct device *dev) +{ + if (dev && dev->cma_area) + return dev->cma_area; + return dma_contiguous_default_area; +} + +static inline void dev_set_cma_area(struct device *dev, struct cma *cma) +{ + if (dev) + dev->cma_area = cma; + if (!dev || !dma_contiguous_default_area) + dma_contiguous_default_area = cma; +} + +#endif +#endif + +#endif diff --git a/include/linux/device.h b/include/linux/device.h index 5ad17cccdd71..e3399290436e 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -661,6 +661,10 @@ struct device { struct dma_coherent_mem *dma_mem; /* internal for coherent mem override */ +#ifdef CONFIG_CMA + struct cma *cma_area; /* contiguous memory area for dma + allocations */ +#endif /* arch specific additions */ struct dev_archdata archdata; diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h new file mode 100644 index 000000000000..2f303e4b7ed3 --- /dev/null +++ b/include/linux/dma-contiguous.h @@ -0,0 +1,110 @@ +#ifndef __LINUX_CMA_H +#define __LINUX_CMA_H + +/* + * Contiguous Memory Allocator for DMA mapping framework + * Copyright (c) 2010-2011 by Samsung Electronics. + * Written by: + * Marek Szyprowski + * Michal Nazarewicz + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 of the + * License or (at your optional) any later version of the license. + */ + +/* + * Contiguous Memory Allocator + * + * The Contiguous Memory Allocator (CMA) makes it possible to + * allocate big contiguous chunks of memory after the system has + * booted. + * + * Why is it needed? + * + * Various devices on embedded systems have no scatter-getter and/or + * IO map support and require contiguous blocks of memory to + * operate. They include devices such as cameras, hardware video + * coders, etc. + * + * Such devices often require big memory buffers (a full HD frame + * is, for instance, more then 2 mega pixels large, i.e. more than 6 + * MB of memory), which makes mechanisms such as kmalloc() or + * alloc_page() ineffective. + * + * At the same time, a solution where a big memory region is + * reserved for a device is suboptimal since often more memory is + * reserved then strictly required and, moreover, the memory is + * inaccessible to page system even if device drivers don't use it. + * + * CMA tries to solve this issue by operating on memory regions + * where only movable pages can be allocated from. This way, kernel + * can use the memory for pagecache and when device driver requests + * it, allocated pages can be migrated. + * + * Driver usage + * + * CMA should not be used by the device drivers directly. It is + * only a helper framework for dma-mapping subsystem. + * + * For more information, see kernel-docs in drivers/base/dma-contiguous.c + */ + +#ifdef __KERNEL__ + +struct cma; +struct page; +struct device; + +#ifdef CONFIG_CMA + +/* + * There is always at least global CMA area and a few optional device + * private areas configured in kernel .config. + */ +#define MAX_CMA_AREAS (1 + CONFIG_CMA_AREAS) + +extern struct cma *dma_contiguous_default_area; + +void dma_contiguous_reserve(phys_addr_t addr_limit); +int dma_declare_contiguous(struct device *dev, unsigned long size, + phys_addr_t base, phys_addr_t limit); + +struct page *dma_alloc_from_contiguous(struct device *dev, int count, + unsigned int order); +bool dma_release_from_contiguous(struct device *dev, struct page *pages, + int count); + +#else + +#define MAX_CMA_AREAS (0) + +static inline void dma_contiguous_reserve(phys_addr_t limit) { } + +static inline +int dma_declare_contiguous(struct device *dev, unsigned long size, + phys_addr_t base, phys_addr_t limit) +{ + return -ENOSYS; +} + +static inline +struct page *dma_alloc_from_contiguous(struct device *dev, int count, + unsigned int order) +{ + return NULL; +} + +static inline +bool dma_release_from_contiguous(struct device *dev, struct page *pages, + int count) +{ + return false; +} + +#endif + +#endif + +#endif -- cgit v1.2.3 From 18d5eacb52291faaa430fc50b435b3bb204dba88 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 23 May 2012 10:15:42 +0100 Subject: regmap: Use select .. if to get IRQ_DOMAIN enabled Ensure that we can't get randconfig breakage by doing the IRQ_DOMAIN select automatically. Don't just do the select from REGMAP_IRQ to ensure that the select actually gets noticed. Reported-by: Randy Dunlap Signed-off-by: Mark Brown --- drivers/base/regmap/Kconfig | 1 + drivers/mfd/Kconfig | 3 --- 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/regmap/Kconfig b/drivers/base/regmap/Kconfig index 9ef0a5326f17..6be390bd8bd1 100644 --- a/drivers/base/regmap/Kconfig +++ b/drivers/base/regmap/Kconfig @@ -6,6 +6,7 @@ config REGMAP default y if (REGMAP_I2C || REGMAP_SPI) select LZO_COMPRESS select LZO_DECOMPRESS + select IRQ_DOMAIN if REGMAP_IRQ bool config REGMAP_I2C diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index e35cb6bc9003..213304de181e 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -376,7 +376,6 @@ config PMIC_DA9052 config MFD_DA9052_SPI bool "Support Dialog Semiconductor DA9052/53 PMIC variants with SPI" - select IRQ_DOMAIN select REGMAP_SPI select REGMAP_IRQ select PMIC_DA9052 @@ -389,7 +388,6 @@ config MFD_DA9052_SPI config MFD_DA9052_I2C bool "Support Dialog Semiconductor DA9052/53 PMIC variants with I2C" - select IRQ_DOMAIN select REGMAP_I2C select REGMAP_IRQ select PMIC_DA9052 @@ -560,7 +558,6 @@ config MFD_WM8994 bool "Support Wolfson Microelectronics WM8994" select MFD_CORE select REGMAP_I2C - select IRQ_DOMAIN select REGMAP_IRQ depends on I2C=y && GENERIC_HARDIRQS help -- cgit v1.2.3 From 4c78513e457f72d5554a0f6e2eabfad7b98e4f19 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Tue, 24 Apr 2012 14:38:52 +0530 Subject: dma-buf: mmap support Compared to Rob Clark's RFC I've ditched the prepare/finish hooks and corresponding ioctls on the dma_buf file. The major reason for that is that many people seem to be under the impression that this is also for synchronization with outstanding asynchronous processsing. I'm pretty massively opposed to this because: - It boils down reinventing a new rather general-purpose userspace synchronization interface. If we look at things like futexes, this is hard to get right. - Furthermore a lot of kernel code has to interact with this synchronization primitive. This smells a look like the dri1 hw_lock, a horror show I prefer not to reinvent. - Even more fun is that multiple different subsystems would interact here, so we have plenty of opportunities to create funny deadlock scenarios. I think synchronization is a wholesale different problem from data sharing and should be tackled as an orthogonal problem. Now we could demand that prepare/finish may only ensure cache coherency (as Rob intended), but that runs up into the next problem: We not only need mmap support to facilitate sw-only processing nodes in a pipeline (without jumping through hoops by importing the dma_buf into some sw-access only importer), which allows for a nicer ION->dma-buf upgrade path for existing Android userspace. We also need mmap support for existing importing subsystems to support existing userspace libraries. And a loot of these subsystems are expected to export coherent userspace mappings. So prepare/finish can only ever be optional and the exporter /needs/ to support coherent mappings. Given that mmap access is always somewhat fallback-y in nature I've decided to drop this optimization, instead of just making it optional. If we demonstrate a clear need for this, supported by benchmark results, we can always add it in again later as an optional extension. Other differences compared to Rob's RFC is the above mentioned support for mapping a dma-buf through facilities provided by the importer. Which results in mmap support no longer being optional. Note that this dma-buf mmap patch does _not_ support every possible insanity an existing subsystem could pull of with mmap: Because it does not allow to intercept pagefaults and shoot down ptes importing subsystems can't add some magic of their own at these points (e.g. to automatically synchronize with outstanding rendering or set up some special resources). I've done a cursory read through a few mmap implementions of various subsytems and I'm hopeful that we can avoid this (and the complexity it'd bring with it). Additonally I've extended the documentation a bit to explain the hows and whys of this mmap extension. In case we ever want to add support for explicitly cache maneged userspace mmap with a prepare/finish ioctl pair, we could specify that userspace needs to mmap a different part of the dma_buf, e.g. the range starting at dma_buf->size up to dma_buf->size*2. This works because the size of a dma_buf is invariant over it's lifetime. The exporter would obviously need to fall back to coherent mappings for both ranges if a legacy clients maps the coherent range and the architecture cannot suppor conflicting caching policies. Also, this would obviously be optional and userspace needs to be able to fall back to coherent mappings. v2: - Spelling fixes from Rob Clark. - Compile fix for !DMA_BUF from Rob Clark. - Extend commit message to explain how explicitly cache managed mmap support could be added later. - Extend the documentation with implementations notes for exporters that need to manually fake coherency. v3: - dma_buf pointer initialization goof-up noticed by Rebecca Schultz Zavin. Cc: Rob Clark Cc: Rebecca Schultz Zavin Acked-by: Rob Clark Signed-Off-by: Daniel Vetter Signed-off-by: Sumit Semwal --- Documentation/dma-buf-sharing.txt | 98 ++++++++++++++++++++++++++++++++++++--- drivers/base/dma-buf.c | 64 ++++++++++++++++++++++++- include/linux/dma-buf.h | 16 +++++++ 3 files changed, 170 insertions(+), 8 deletions(-) (limited to 'drivers/base') diff --git a/Documentation/dma-buf-sharing.txt b/Documentation/dma-buf-sharing.txt index 3bbd5c51605a..5ff4d2b84f72 100644 --- a/Documentation/dma-buf-sharing.txt +++ b/Documentation/dma-buf-sharing.txt @@ -29,13 +29,6 @@ The buffer-user in memory, mapped into its own address space, so it can access the same area of memory. -*IMPORTANT*: [see https://lkml.org/lkml/2011/12/20/211 for more details] -For this first version, A buffer shared using the dma_buf sharing API: -- *may* be exported to user space using "mmap" *ONLY* by exporter, outside of - this framework. -- with this new iteration of the dma-buf api cpu access from the kernel has been - enable, see below for the details. - dma-buf operations for device dma only -------------------------------------- @@ -313,6 +306,83 @@ Access to a dma_buf from the kernel context involves three steps: enum dma_data_direction dir); +Direct Userspace Access/mmap Support +------------------------------------ + +Being able to mmap an export dma-buf buffer object has 2 main use-cases: +- CPU fallback processing in a pipeline and +- supporting existing mmap interfaces in importers. + +1. CPU fallback processing in a pipeline + + In many processing pipelines it is sometimes required that the cpu can access + the data in a dma-buf (e.g. for thumbnail creation, snapshots, ...). To avoid + the need to handle this specially in userspace frameworks for buffer sharing + it's ideal if the dma_buf fd itself can be used to access the backing storage + from userspace using mmap. + + Furthermore Android's ION framework already supports this (and is otherwise + rather similar to dma-buf from a userspace consumer side with using fds as + handles, too). So it's beneficial to support this in a similar fashion on + dma-buf to have a good transition path for existing Android userspace. + + No special interfaces, userspace simply calls mmap on the dma-buf fd. + +2. Supporting existing mmap interfaces in exporters + + Similar to the motivation for kernel cpu access it is again important that + the userspace code of a given importing subsystem can use the same interfaces + with a imported dma-buf buffer object as with a native buffer object. This is + especially important for drm where the userspace part of contemporary OpenGL, + X, and other drivers is huge, and reworking them to use a different way to + mmap a buffer rather invasive. + + The assumption in the current dma-buf interfaces is that redirecting the + initial mmap is all that's needed. A survey of some of the existing + subsystems shows that no driver seems to do any nefarious thing like syncing + up with outstanding asynchronous processing on the device or allocating + special resources at fault time. So hopefully this is good enough, since + adding interfaces to intercept pagefaults and allow pte shootdowns would + increase the complexity quite a bit. + + Interface: + int dma_buf_mmap(struct dma_buf *, struct vm_area_struct *, + unsigned long); + + If the importing subsystem simply provides a special-purpose mmap call to set + up a mapping in userspace, calling do_mmap with dma_buf->file will equally + achieve that for a dma-buf object. + +3. Implementation notes for exporters + + Because dma-buf buffers have invariant size over their lifetime, the dma-buf + core checks whether a vma is too large and rejects such mappings. The + exporter hence does not need to duplicate this check. + + Because existing importing subsystems might presume coherent mappings for + userspace, the exporter needs to set up a coherent mapping. If that's not + possible, it needs to fake coherency by manually shooting down ptes when + leaving the cpu domain and flushing caches at fault time. Note that all the + dma_buf files share the same anon inode, hence the exporter needs to replace + the dma_buf file stored in vma->vm_file with it's own if pte shootdown is + requred. This is because the kernel uses the underlying inode's address_space + for vma tracking (and hence pte tracking at shootdown time with + unmap_mapping_range). + + If the above shootdown dance turns out to be too expensive in certain + scenarios, we can extend dma-buf with a more explicit cache tracking scheme + for userspace mappings. But the current assumption is that using mmap is + always a slower path, so some inefficiencies should be acceptable. + + Exporters that shoot down mappings (for any reasons) shall not do any + synchronization at fault time with outstanding device operations. + Synchronization is an orthogonal issue to sharing the backing storage of a + buffer and hence should not be handled by dma-buf itself. This is explictly + mentioned here because many people seem to want something like this, but if + different exporters handle this differently, buffer sharing can fail in + interesting ways depending upong the exporter (if userspace starts depending + upon this implicit synchronization). + Miscellaneous notes ------------------- @@ -336,6 +406,20 @@ Miscellaneous notes the exporting driver to create a dmabuf fd must provide a way to let userspace control setting of O_CLOEXEC flag passed in to dma_buf_fd(). +- If an exporter needs to manually flush caches and hence needs to fake + coherency for mmap support, it needs to be able to zap all the ptes pointing + at the backing storage. Now linux mm needs a struct address_space associated + with the struct file stored in vma->vm_file to do that with the function + unmap_mapping_range. But the dma_buf framework only backs every dma_buf fd + with the anon_file struct file, i.e. all dma_bufs share the same file. + + Hence exporters need to setup their own file (and address_space) association + by setting vma->vm_file and adjusting vma->vm_pgoff in the dma_buf mmap + callback. In the specific case of a gem driver the exporter could use the + shmem file already provided by gem (and set vm_pgoff = 0). Exporters can then + zap ptes by unmapping the corresponding range of the struct address_space + associated with their own file. + References: [1] struct dma_buf_ops in include/linux/dma-buf.h [2] All interfaces mentioned above defined in include/linux/dma-buf.h diff --git a/drivers/base/dma-buf.c b/drivers/base/dma-buf.c index 07cbbc6fddb4..7cfb405b1ad5 100644 --- a/drivers/base/dma-buf.c +++ b/drivers/base/dma-buf.c @@ -44,8 +44,26 @@ static int dma_buf_release(struct inode *inode, struct file *file) return 0; } +static int dma_buf_mmap_internal(struct file *file, struct vm_area_struct *vma) +{ + struct dma_buf *dmabuf; + + if (!is_dma_buf_file(file)) + return -EINVAL; + + dmabuf = file->private_data; + + /* check for overflowing the buffer's size */ + if (vma->vm_pgoff + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) > + dmabuf->size >> PAGE_SHIFT) + return -EINVAL; + + return dmabuf->ops->mmap(dmabuf, vma); +} + static const struct file_operations dma_buf_fops = { .release = dma_buf_release, + .mmap = dma_buf_mmap_internal, }; /* @@ -82,7 +100,8 @@ struct dma_buf *dma_buf_export(void *priv, const struct dma_buf_ops *ops, || !ops->unmap_dma_buf || !ops->release || !ops->kmap_atomic - || !ops->kmap)) { + || !ops->kmap + || !ops->mmap)) { return ERR_PTR(-EINVAL); } @@ -406,3 +425,46 @@ void dma_buf_kunmap(struct dma_buf *dmabuf, unsigned long page_num, dmabuf->ops->kunmap(dmabuf, page_num, vaddr); } EXPORT_SYMBOL_GPL(dma_buf_kunmap); + + +/** + * dma_buf_mmap - Setup up a userspace mmap with the given vma + * @dma_buf: [in] buffer that should back the vma + * @vma: [in] vma for the mmap + * @pgoff: [in] offset in pages where this mmap should start within the + * dma-buf buffer. + * + * This function adjusts the passed in vma so that it points at the file of the + * dma_buf operation. It alsog adjusts the starting pgoff and does bounds + * checking on the size of the vma. Then it calls the exporters mmap function to + * set up the mapping. + * + * Can return negative error values, returns 0 on success. + */ +int dma_buf_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma, + unsigned long pgoff) +{ + if (WARN_ON(!dmabuf || !vma)) + return -EINVAL; + + /* check for offset overflow */ + if (pgoff + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) < pgoff) + return -EOVERFLOW; + + /* check for overflowing the buffer's size */ + if (pgoff + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) > + dmabuf->size >> PAGE_SHIFT) + return -EINVAL; + + /* readjust the vma */ + if (vma->vm_file) + fput(vma->vm_file); + + vma->vm_file = dmabuf->file; + get_file(vma->vm_file); + + vma->vm_pgoff = pgoff; + + return dmabuf->ops->mmap(dmabuf, vma); +} +EXPORT_SYMBOL_GPL(dma_buf_mmap); diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 3efbfc2145c3..1f78d1594cc7 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -61,6 +61,10 @@ struct dma_buf_attachment; * This Callback must not sleep. * @kmap: maps a page from the buffer into kernel address space. * @kunmap: [optional] unmaps a page from the buffer. + * @mmap: used to expose the backing storage to userspace. Note that the + * mapping needs to be coherent - if the exporter doesn't directly + * support this, it needs to fake coherency by shooting down any ptes + * when transitioning away from the cpu domain. */ struct dma_buf_ops { int (*attach)(struct dma_buf *, struct device *, @@ -92,6 +96,8 @@ struct dma_buf_ops { void (*kunmap_atomic)(struct dma_buf *, unsigned long, void *); void *(*kmap)(struct dma_buf *, unsigned long); void (*kunmap)(struct dma_buf *, unsigned long, void *); + + int (*mmap)(struct dma_buf *, struct vm_area_struct *vma); }; /** @@ -167,6 +173,9 @@ void *dma_buf_kmap_atomic(struct dma_buf *, unsigned long); void dma_buf_kunmap_atomic(struct dma_buf *, unsigned long, void *); void *dma_buf_kmap(struct dma_buf *, unsigned long); void dma_buf_kunmap(struct dma_buf *, unsigned long, void *); + +int dma_buf_mmap(struct dma_buf *, struct vm_area_struct *, + unsigned long); #else static inline struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf, @@ -248,6 +257,13 @@ static inline void dma_buf_kunmap(struct dma_buf *dmabuf, unsigned long pnum, void *vaddr) { } + +static inline int dma_buf_mmap(struct dma_buf *dmabuf, + struct vm_area_struct *vma, + unsigned long pgoff) +{ + return -ENODEV; +} #endif /* CONFIG_DMA_SHARED_BUFFER */ #endif /* __DMA_BUF_H__ */ -- cgit v1.2.3 From 98f86c9e4ae3205e4c85c535691a5d36426360ee Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Sun, 20 May 2012 12:33:56 +0530 Subject: dma-buf: add vmap interface The main requirement I have for this interface is for scanning out using the USB gpu devices. Since these devices have to read the framebuffer on updates and linearly compress it, using kmaps is a major overhead for every update. v2: fix warn issues pointed out by Sylwester Nawrocki. v3: fix compile !CONFIG_DMA_SHARED_BUFFER and add _GPL for now Signed-off-by: Dave Airlie Reviewed-by: Rob Clark Signed-off-by: Sumit Semwal --- drivers/base/dma-buf.c | 34 ++++++++++++++++++++++++++++++++++ include/linux/dma-buf.h | 14 ++++++++++++++ 2 files changed, 48 insertions(+) (limited to 'drivers/base') diff --git a/drivers/base/dma-buf.c b/drivers/base/dma-buf.c index 7cfb405b1ad5..d43d80256fda 100644 --- a/drivers/base/dma-buf.c +++ b/drivers/base/dma-buf.c @@ -468,3 +468,37 @@ int dma_buf_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma, return dmabuf->ops->mmap(dmabuf, vma); } EXPORT_SYMBOL_GPL(dma_buf_mmap); + +/** + * dma_buf_vmap - Create virtual mapping for the buffer object into kernel address space. Same restrictions as for vmap and friends apply. + * @dma_buf: [in] buffer to vmap + * + * This call may fail due to lack of virtual mapping address space. + * These calls are optional in drivers. The intended use for them + * is for mapping objects linear in kernel space for high use objects. + * Please attempt to use kmap/kunmap before thinking about these interfaces. + */ +void *dma_buf_vmap(struct dma_buf *dmabuf) +{ + if (WARN_ON(!dmabuf)) + return NULL; + + if (dmabuf->ops->vmap) + return dmabuf->ops->vmap(dmabuf); + return NULL; +} +EXPORT_SYMBOL_GPL(dma_buf_vmap); + +/** + * dma_buf_vunmap - Unmap a vmap obtained by dma_buf_vmap. + * @dma_buf: [in] buffer to vmap + */ +void dma_buf_vunmap(struct dma_buf *dmabuf, void *vaddr) +{ + if (WARN_ON(!dmabuf)) + return; + + if (dmabuf->ops->vunmap) + dmabuf->ops->vunmap(dmabuf, vaddr); +} +EXPORT_SYMBOL_GPL(dma_buf_vunmap); diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 1f78d1594cc7..a02b1ff6488e 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -98,6 +98,9 @@ struct dma_buf_ops { void (*kunmap)(struct dma_buf *, unsigned long, void *); int (*mmap)(struct dma_buf *, struct vm_area_struct *vma); + + void *(*vmap)(struct dma_buf *); + void (*vunmap)(struct dma_buf *, void *vaddr); }; /** @@ -176,6 +179,8 @@ void dma_buf_kunmap(struct dma_buf *, unsigned long, void *); int dma_buf_mmap(struct dma_buf *, struct vm_area_struct *, unsigned long); +void *dma_buf_vmap(struct dma_buf *); +void dma_buf_vunmap(struct dma_buf *, void *vaddr); #else static inline struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf, @@ -264,6 +269,15 @@ static inline int dma_buf_mmap(struct dma_buf *dmabuf, { return -ENODEV; } + +static inline void *dma_buf_vmap(struct dma_buf *dmabuf) +{ + return NULL; +} + +static inline void dma_buf_vunmap(struct dma_buf *dmabuf, void *vaddr) +{ +} #endif /* CONFIG_DMA_SHARED_BUFFER */ #endif /* __DMA_BUF_H__ */ -- cgit v1.2.3 From 12c4727e1d5370270a7df781d2ba0a76e05c1137 Mon Sep 17 00:00:00 2001 From: Sumit Semwal Date: Wed, 23 May 2012 15:27:40 +0530 Subject: dma-buf: minor documentation fixes. Some minor inline documentation fixes for gaps resulting from new patches. Signed-off-by: Sumit Semwal Signed-off-by: Sumit Semwal --- drivers/base/dma-buf.c | 9 +++++---- include/linux/dma-buf.h | 3 +++ 2 files changed, 8 insertions(+), 4 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/dma-buf.c b/drivers/base/dma-buf.c index d43d80256fda..20258e179211 100644 --- a/drivers/base/dma-buf.c +++ b/drivers/base/dma-buf.c @@ -429,7 +429,7 @@ EXPORT_SYMBOL_GPL(dma_buf_kunmap); /** * dma_buf_mmap - Setup up a userspace mmap with the given vma - * @dma_buf: [in] buffer that should back the vma + * @dmabuf: [in] buffer that should back the vma * @vma: [in] vma for the mmap * @pgoff: [in] offset in pages where this mmap should start within the * dma-buf buffer. @@ -470,8 +470,9 @@ int dma_buf_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma, EXPORT_SYMBOL_GPL(dma_buf_mmap); /** - * dma_buf_vmap - Create virtual mapping for the buffer object into kernel address space. Same restrictions as for vmap and friends apply. - * @dma_buf: [in] buffer to vmap + * dma_buf_vmap - Create virtual mapping for the buffer object into kernel + * address space. Same restrictions as for vmap and friends apply. + * @dmabuf: [in] buffer to vmap * * This call may fail due to lack of virtual mapping address space. * These calls are optional in drivers. The intended use for them @@ -491,7 +492,7 @@ EXPORT_SYMBOL_GPL(dma_buf_vmap); /** * dma_buf_vunmap - Unmap a vmap obtained by dma_buf_vmap. - * @dma_buf: [in] buffer to vmap + * @dmabuf: [in] buffer to vunmap */ void dma_buf_vunmap(struct dma_buf *dmabuf, void *vaddr) { diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index a02b1ff6488e..eb48f3816df9 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -65,6 +65,9 @@ struct dma_buf_attachment; * mapping needs to be coherent - if the exporter doesn't directly * support this, it needs to fake coherency by shooting down any ptes * when transitioning away from the cpu domain. + * @vmap: [optional] creates a virtual mapping for the buffer into kernel + * address space. Same restrictions as for vmap and friends apply. + * @vunmap: [optional] unmaps a vmap from the buffer */ struct dma_buf_ops { int (*attach)(struct dma_buf *, struct device *, -- cgit v1.2.3 From f62388187207bea83f1865d507bf892a1f9152c3 Mon Sep 17 00:00:00 2001 From: Ryota Ozaki Date: Tue, 29 May 2012 15:06:20 -0700 Subject: mm: fix off-by-one bug in print_nodes_state() /sys/devices/system/node/{online,possible} outputs a garbage byte because print_nodes_state() returns content size + 1. To fix the bug, the patch changes the use of cpuset_sprintf_cpulist to follow the use at other places, which is clearer and safer. This bug was introduced in v2.6.24 (commit bde631a51876: "mm: add node states sysfs class attributeS"). Signed-off-by: Ryota Ozaki Cc: Lee Schermerhorn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/node.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/node.c b/drivers/base/node.c index 90aa2a11a933..af1a177216f1 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -592,11 +592,9 @@ static ssize_t print_nodes_state(enum node_states state, char *buf) { int n; - n = nodelist_scnprintf(buf, PAGE_SIZE, node_states[state]); - if (n > 0 && PAGE_SIZE > n + 1) { - *(buf + n++) = '\n'; - *(buf + n++) = '\0'; - } + n = nodelist_scnprintf(buf, PAGE_SIZE-2, node_states[state]); + buf[n++] = '\n'; + buf[n] = '\0'; return n; } -- cgit v1.2.3 From 726592a9be0bdf919399d3dfa633f8e2d69cbf13 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 19 May 2012 10:00:52 -0400 Subject: mode_t whack-a-mole: ->is_visible() returns umode_t... Signed-off-by: Al Viro --- drivers/base/soc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/base') diff --git a/drivers/base/soc.c b/drivers/base/soc.c index ba29b2e73d48..72b5e7280d14 100644 --- a/drivers/base/soc.c +++ b/drivers/base/soc.c @@ -42,7 +42,7 @@ struct device *soc_device_to_device(struct soc_device *soc_dev) return &soc_dev->dev; } -static mode_t soc_attribute_mode(struct kobject *kobj, +static umode_t soc_attribute_mode(struct kobject *kobj, struct attribute *attr, int index) { -- cgit v1.2.3 From 14674e70119ea01549ce593d8901a797f8a90f74 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 30 May 2012 10:55:34 +0200 Subject: i2c: Split I2C_M_NOSTART support out of I2C_FUNC_PROTOCOL_MANGLING Since there are uses for I2C_M_NOSTART which are much more sensible and standard than most of the protocol mangling functionality (the main one being gather writes to devices where something like a register address needs to be inserted before a block of data) create a new I2C_FUNC_NOSTART for this feature and update all the users to use it. Also strengthen the disrecommendation of the protocol mangling while we're at it. In the case of regmap-i2c we remove the requirement for mangling as I2C_M_NOSTART is the only mangling feature which is being used. Signed-off-by: Mark Brown Acked-by: Wolfram Sang Signed-off-by: Jean Delvare --- Documentation/i2c/functionality | 9 ++++++--- Documentation/i2c/i2c-protocol | 9 ++++++++- drivers/base/regmap/regmap-i2c.c | 2 +- drivers/i2c/algos/i2c-algo-bit.c | 2 +- drivers/i2c/busses/i2c-nuc900.c | 3 ++- drivers/i2c/busses/i2c-s3c2410.c | 3 ++- drivers/input/joystick/as5011.c | 1 + drivers/video/matrox/matroxfb_maven.c | 1 + include/linux/i2c.h | 5 +++-- 9 files changed, 25 insertions(+), 10 deletions(-) (limited to 'drivers/base') diff --git a/Documentation/i2c/functionality b/Documentation/i2c/functionality index 42c17c1fb3cd..b0ff2ab596ce 100644 --- a/Documentation/i2c/functionality +++ b/Documentation/i2c/functionality @@ -18,9 +18,9 @@ For the most up-to-date list of functionality constants, please check adapters typically can not do these) I2C_FUNC_10BIT_ADDR Handles the 10-bit address extensions I2C_FUNC_PROTOCOL_MANGLING Knows about the I2C_M_IGNORE_NAK, - I2C_M_REV_DIR_ADDR, I2C_M_NOSTART and - I2C_M_NO_RD_ACK flags (which modify the - I2C protocol!) + I2C_M_REV_DIR_ADDR and I2C_M_NO_RD_ACK + flags (which modify the I2C protocol!) + I2C_FUNC_NOSTART Can skip repeated start sequence I2C_FUNC_SMBUS_QUICK Handles the SMBus write_quick command I2C_FUNC_SMBUS_READ_BYTE Handles the SMBus read_byte command I2C_FUNC_SMBUS_WRITE_BYTE Handles the SMBus write_byte command @@ -50,6 +50,9 @@ A few combinations of the above flags are also defined for your convenience: emulated by a real I2C adapter (using the transparent emulation layer) +In kernel versions prior to 3.5 I2C_FUNC_NOSTART was implemented as +part of I2C_FUNC_PROTOCOL_MANGLING. + ADAPTER IMPLEMENTATION ---------------------- diff --git a/Documentation/i2c/i2c-protocol b/Documentation/i2c/i2c-protocol index 10518dd58814..0b3e62d1f77a 100644 --- a/Documentation/i2c/i2c-protocol +++ b/Documentation/i2c/i2c-protocol @@ -49,7 +49,9 @@ a byte read, followed by a byte write: Modified transactions ===================== -We have found some I2C devices that needs the following modifications: +The following modifications to the I2C protocol can also be generated, +with the exception of I2C_M_NOSTART these are usually only needed to +work around device issues: Flag I2C_M_NOSTART: In a combined transaction, no 'S Addr Wr/Rd [A]' is generated at some @@ -60,6 +62,11 @@ We have found some I2C devices that needs the following modifications: we do not generate Addr, but we do generate the startbit S. This will probably confuse all other clients on your bus, so don't try this. + This is often used to gather transmits from multiple data buffers in + system memory into something that appears as a single transfer to the + I2C device but may also be used between direction changes by some + rare devices. + Flags I2C_M_REV_DIR_ADDR This toggles the Rd/Wr flag. That is, if you want to do a write, but need to emit an Rd instead of a Wr, or vice versa, you set this diff --git a/drivers/base/regmap/regmap-i2c.c b/drivers/base/regmap/regmap-i2c.c index 5f6b2478bf17..fa6bf5279d28 100644 --- a/drivers/base/regmap/regmap-i2c.c +++ b/drivers/base/regmap/regmap-i2c.c @@ -42,7 +42,7 @@ static int regmap_i2c_gather_write(void *context, /* If the I2C controller can't do a gather tell the core, it * will substitute in a linear write for us. */ - if (!i2c_check_functionality(i2c->adapter, I2C_FUNC_PROTOCOL_MANGLING)) + if (!i2c_check_functionality(i2c->adapter, I2C_FUNC_NOSTART)) return -ENOTSUPP; xfer[0].addr = i2c->addr; diff --git a/drivers/i2c/algos/i2c-algo-bit.c b/drivers/i2c/algos/i2c-algo-bit.c index 7f0b83219744..fad22b0bb5b0 100644 --- a/drivers/i2c/algos/i2c-algo-bit.c +++ b/drivers/i2c/algos/i2c-algo-bit.c @@ -608,7 +608,7 @@ bailout: static u32 bit_func(struct i2c_adapter *adap) { - return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL | + return I2C_FUNC_I2C | I2C_FUNC_NOSTART | I2C_FUNC_SMBUS_EMUL | I2C_FUNC_SMBUS_READ_BLOCK_DATA | I2C_FUNC_SMBUS_BLOCK_PROC_CALL | I2C_FUNC_10BIT_ADDR | I2C_FUNC_PROTOCOL_MANGLING; diff --git a/drivers/i2c/busses/i2c-nuc900.c b/drivers/i2c/busses/i2c-nuc900.c index 03b615778887..a26dfb8cd586 100644 --- a/drivers/i2c/busses/i2c-nuc900.c +++ b/drivers/i2c/busses/i2c-nuc900.c @@ -502,7 +502,8 @@ static int nuc900_i2c_xfer(struct i2c_adapter *adap, /* declare our i2c functionality */ static u32 nuc900_i2c_func(struct i2c_adapter *adap) { - return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL | I2C_FUNC_PROTOCOL_MANGLING; + return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL | I2C_FUNC_NOSTART | + I2C_FUNC_PROTOCOL_MANGLING; } /* i2c bus registration info */ diff --git a/drivers/i2c/busses/i2c-s3c2410.c b/drivers/i2c/busses/i2c-s3c2410.c index fa0b13490873..01959154572d 100644 --- a/drivers/i2c/busses/i2c-s3c2410.c +++ b/drivers/i2c/busses/i2c-s3c2410.c @@ -626,7 +626,8 @@ static int s3c24xx_i2c_xfer(struct i2c_adapter *adap, /* declare our i2c functionality */ static u32 s3c24xx_i2c_func(struct i2c_adapter *adap) { - return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL | I2C_FUNC_PROTOCOL_MANGLING; + return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL | I2C_FUNC_NOSTART | + I2C_FUNC_PROTOCOL_MANGLING; } /* i2c bus registration info */ diff --git a/drivers/input/joystick/as5011.c b/drivers/input/joystick/as5011.c index 3063464474bf..57d19d4e0a2d 100644 --- a/drivers/input/joystick/as5011.c +++ b/drivers/input/joystick/as5011.c @@ -231,6 +231,7 @@ static int __devinit as5011_probe(struct i2c_client *client, } if (!i2c_check_functionality(client->adapter, + I2C_FUNC_NOSTART | I2C_FUNC_PROTOCOL_MANGLING)) { dev_err(&client->dev, "need i2c bus that supports protocol mangling\n"); diff --git a/drivers/video/matrox/matroxfb_maven.c b/drivers/video/matrox/matroxfb_maven.c index 31b8f67477b7..217678e0b983 100644 --- a/drivers/video/matrox/matroxfb_maven.c +++ b/drivers/video/matrox/matroxfb_maven.c @@ -1243,6 +1243,7 @@ static int maven_probe(struct i2c_client *client, if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_WRITE_WORD_DATA | I2C_FUNC_SMBUS_BYTE_DATA | + I2C_FUNC_NOSTART | I2C_FUNC_PROTOCOL_MANGLING)) goto ERROR0; if (!(data = kzalloc(sizeof(*data), GFP_KERNEL))) { diff --git a/include/linux/i2c.h b/include/linux/i2c.h index b66cb601435f..ddfa04108baf 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -541,7 +541,7 @@ struct i2c_msg { __u16 flags; #define I2C_M_TEN 0x0010 /* this is a ten bit chip address */ #define I2C_M_RD 0x0001 /* read data, from slave to master */ -#define I2C_M_NOSTART 0x4000 /* if I2C_FUNC_PROTOCOL_MANGLING */ +#define I2C_M_NOSTART 0x4000 /* if I2C_FUNC_NOSTART */ #define I2C_M_REV_DIR_ADDR 0x2000 /* if I2C_FUNC_PROTOCOL_MANGLING */ #define I2C_M_IGNORE_NAK 0x1000 /* if I2C_FUNC_PROTOCOL_MANGLING */ #define I2C_M_NO_RD_ACK 0x0800 /* if I2C_FUNC_PROTOCOL_MANGLING */ @@ -554,8 +554,9 @@ struct i2c_msg { #define I2C_FUNC_I2C 0x00000001 #define I2C_FUNC_10BIT_ADDR 0x00000002 -#define I2C_FUNC_PROTOCOL_MANGLING 0x00000004 /* I2C_M_NOSTART etc. */ +#define I2C_FUNC_PROTOCOL_MANGLING 0x00000004 /* I2C_M_IGNORE_NAK etc. */ #define I2C_FUNC_SMBUS_PEC 0x00000008 +#define I2C_FUNC_NOSTART 0x00000010 /* I2C_M_NOSTART */ #define I2C_FUNC_SMBUS_BLOCK_PROC_CALL 0x00008000 /* SMBus 2.0 */ #define I2C_FUNC_SMBUS_QUICK 0x00010000 #define I2C_FUNC_SMBUS_READ_BYTE 0x00020000 -- cgit v1.2.3