From 0c4a1049cf298721eaec4553d3d5039798086e12 Mon Sep 17 00:00:00 2001 From: Sanyog Kale Date: Fri, 27 Jul 2018 14:44:13 +0530 Subject: soundwire: Add support to lock across bus instances Currently, the stream concept is limited to single Master and one or more Codecs. This patch extends the concept to support multiple Master(s) sharing the same reference clock and synchronized in the hardware. Modify sdw_stream_runtime to support a list of sdw_master_runtime for the same. The existing reference to a single m_rt is removed in the next patch. Typically to lock, one would acquire a global lock and then lock bus instances. In this case, the caller framework(ASoC DPCM) guarantees that stream operations on a card are always serialized. So, there is no race condition and hence no need for global lock. Bus lock(s) are acquired to reconfigure the bus while the stream is set-up. So, we add sdw_acquire_bus_lock()/sdw_release_bus_lock() APIs which are used only to reconfigure the bus. Signed-off-by: Sanyog Kale Signed-off-by: Shreyas NC Acked-by: Pierre-Louis Bossart Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 962971e6a9c7..ccd8dcdf06ab 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -769,6 +769,9 @@ struct sdw_stream_params { * @state: Current state of the stream * @type: Stream type PCM or PDM * @m_rt: Master runtime + * @master_list: List of Master runtime(s) in this stream. + * master_list can contain only one m_rt per Master instance + * for a stream */ struct sdw_stream_runtime { char *name; @@ -776,6 +779,7 @@ struct sdw_stream_runtime { enum sdw_stream_state state; enum sdw_stream_type type; struct sdw_master_runtime *m_rt; + struct list_head master_list; }; struct sdw_stream_runtime *sdw_alloc_stream(char *stream_name); -- cgit v1.2.3 From 48949722ced4daacfa32f13c221f173b87231ead Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Fri, 27 Jul 2018 14:44:14 +0530 Subject: soundwire: Handle multiple master instances in a stream For each SoundWire stream operation, we need to parse master list and operate upon all master runtime. This is a preparatory patch to do the boilerplate conversion of stream handling from single master runtime to handle a list of master runtime. The code to support bank switch for multiple master instances is added in the next patch. Signed-off-by: Sanyog Kale Signed-off-by: Shreyas NC Acked-by: Pierre-Louis Bossart Signed-off-by: Vinod Koul --- drivers/soundwire/stream.c | 311 +++++++++++++++++++++++++----------------- include/linux/soundwire/sdw.h | 2 - 2 files changed, 188 insertions(+), 125 deletions(-) (limited to 'include/linux') diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c index b52903fe6f31..ee024d72dd7b 100644 --- a/drivers/soundwire/stream.c +++ b/drivers/soundwire/stream.c @@ -681,35 +681,45 @@ error_1: static int do_bank_switch(struct sdw_stream_runtime *stream) { - struct sdw_master_runtime *m_rt = stream->m_rt; + struct sdw_master_runtime *m_rt = NULL; const struct sdw_master_ops *ops; - struct sdw_bus *bus = m_rt->bus; + struct sdw_bus *bus = NULL; int ret = 0; - ops = bus->ops; - /* Pre-bank switch */ - if (ops->pre_bank_switch) { - ret = ops->pre_bank_switch(bus); + list_for_each_entry(m_rt, &stream->master_list, stream_node) { + bus = m_rt->bus; + ops = bus->ops; + + /* Pre-bank switch */ + if (ops->pre_bank_switch) { + ret = ops->pre_bank_switch(bus); + if (ret < 0) { + dev_err(bus->dev, + "Pre bank switch op failed: %d", ret); + return ret; + } + } + + /* Bank switch */ + ret = sdw_bank_switch(bus); if (ret < 0) { - dev_err(bus->dev, "Pre bank switch op failed: %d", ret); + dev_err(bus->dev, "Bank switch failed: %d", ret); return ret; } } - /* Bank switch */ - ret = sdw_bank_switch(bus); - if (ret < 0) { - dev_err(bus->dev, "Bank switch failed: %d", ret); - return ret; - } + list_for_each_entry(m_rt, &stream->master_list, stream_node) { + bus = m_rt->bus; + ops = bus->ops; - /* Post-bank switch */ - if (ops->post_bank_switch) { - ret = ops->post_bank_switch(bus); - if (ret < 0) { - dev_err(bus->dev, + /* Post-bank switch */ + if (ops->post_bank_switch) { + ret = ops->post_bank_switch(bus); + if (ret < 0) { + dev_err(bus->dev, "Post bank switch op failed: %d", ret); + } } } @@ -754,6 +764,21 @@ struct sdw_stream_runtime *sdw_alloc_stream(char *stream_name) } EXPORT_SYMBOL(sdw_alloc_stream); +static struct sdw_master_runtime +*sdw_find_master_rt(struct sdw_bus *bus, + struct sdw_stream_runtime *stream) +{ + struct sdw_master_runtime *m_rt = NULL; + + /* Retrieve Bus handle if already available */ + list_for_each_entry(m_rt, &stream->master_list, stream_node) { + if (m_rt->bus == bus) + return m_rt; + } + + return NULL; +} + /** * sdw_alloc_master_rt() - Allocates and initialize Master runtime handle * @@ -770,12 +795,11 @@ static struct sdw_master_runtime { struct sdw_master_runtime *m_rt; - m_rt = stream->m_rt; - /* * check if Master is already allocated (as a result of Slave adding * it first), if so skip allocation and go to configure */ + m_rt = sdw_find_master_rt(bus, stream); if (m_rt) goto stream_config; @@ -786,7 +810,7 @@ static struct sdw_master_runtime /* Initialization of Master runtime handle */ INIT_LIST_HEAD(&m_rt->port_list); INIT_LIST_HEAD(&m_rt->slave_rt_list); - stream->m_rt = m_rt; + list_add_tail(&m_rt->stream_node, &stream->master_list); list_add_tail(&m_rt->bus_node, &bus->m_rt_list); @@ -844,17 +868,21 @@ static void sdw_slave_port_release(struct sdw_bus *bus, struct sdw_stream_runtime *stream) { struct sdw_port_runtime *p_rt, *_p_rt; - struct sdw_master_runtime *m_rt = stream->m_rt; + struct sdw_master_runtime *m_rt; struct sdw_slave_runtime *s_rt; - list_for_each_entry(s_rt, &m_rt->slave_rt_list, m_rt_node) { - if (s_rt->slave != slave) - continue; + list_for_each_entry(m_rt, &stream->master_list, stream_node) { + list_for_each_entry(s_rt, &m_rt->slave_rt_list, m_rt_node) { - list_for_each_entry_safe(p_rt, _p_rt, - &s_rt->port_list, port_node) { - list_del(&p_rt->port_node); - kfree(p_rt); + if (s_rt->slave != slave) + continue; + + list_for_each_entry_safe(p_rt, _p_rt, + &s_rt->port_list, port_node) { + + list_del(&p_rt->port_node); + kfree(p_rt); + } } } } @@ -871,16 +899,18 @@ static void sdw_release_slave_stream(struct sdw_slave *slave, struct sdw_stream_runtime *stream) { struct sdw_slave_runtime *s_rt, *_s_rt; - struct sdw_master_runtime *m_rt = stream->m_rt; - - /* Retrieve Slave runtime handle */ - list_for_each_entry_safe(s_rt, _s_rt, - &m_rt->slave_rt_list, m_rt_node) { + struct sdw_master_runtime *m_rt; - if (s_rt->slave == slave) { - list_del(&s_rt->m_rt_node); - kfree(s_rt); - return; + list_for_each_entry(m_rt, &stream->master_list, stream_node) { + /* Retrieve Slave runtime handle */ + list_for_each_entry_safe(s_rt, _s_rt, + &m_rt->slave_rt_list, m_rt_node) { + + if (s_rt->slave == slave) { + list_del(&s_rt->m_rt_node); + kfree(s_rt); + return; + } } } } @@ -888,6 +918,7 @@ static void sdw_release_slave_stream(struct sdw_slave *slave, /** * sdw_release_master_stream() - Free Master runtime handle * + * @m_rt: Master runtime node * @stream: Stream runtime handle. * * This function is to be called with bus_lock held @@ -895,9 +926,9 @@ static void sdw_release_slave_stream(struct sdw_slave *slave, * handle. If this is called first then sdw_release_slave_stream() will have * no effect as Slave(s) runtime handle would already be freed up. */ -static void sdw_release_master_stream(struct sdw_stream_runtime *stream) +static void sdw_release_master_stream(struct sdw_master_runtime *m_rt, + struct sdw_stream_runtime *stream) { - struct sdw_master_runtime *m_rt = stream->m_rt; struct sdw_slave_runtime *s_rt, *_s_rt; list_for_each_entry_safe(s_rt, _s_rt, &m_rt->slave_rt_list, m_rt_node) { @@ -905,7 +936,9 @@ static void sdw_release_master_stream(struct sdw_stream_runtime *stream) sdw_release_slave_stream(s_rt->slave, stream); } + list_del(&m_rt->stream_node); list_del(&m_rt->bus_node); + kfree(m_rt); } /** @@ -919,13 +952,22 @@ static void sdw_release_master_stream(struct sdw_stream_runtime *stream) int sdw_stream_remove_master(struct sdw_bus *bus, struct sdw_stream_runtime *stream) { + struct sdw_master_runtime *m_rt, *_m_rt; + mutex_lock(&bus->bus_lock); - sdw_release_master_stream(stream); - sdw_master_port_release(bus, stream->m_rt); - stream->state = SDW_STREAM_RELEASED; - kfree(stream->m_rt); - stream->m_rt = NULL; + list_for_each_entry_safe(m_rt, _m_rt, + &stream->master_list, stream_node) { + + if (m_rt->bus != bus) + continue; + + sdw_master_port_release(bus, m_rt); + sdw_release_master_stream(m_rt, stream); + } + + if (list_empty(&stream->master_list)) + stream->state = SDW_STREAM_RELEASED; mutex_unlock(&bus->bus_lock); @@ -1128,7 +1170,7 @@ int sdw_stream_add_master(struct sdw_bus *bus, goto unlock; stream_error: - sdw_release_master_stream(stream); + sdw_release_master_stream(m_rt, stream); unlock: mutex_unlock(&bus->bus_lock); return ret; @@ -1206,7 +1248,7 @@ stream_error: * we hit error so cleanup the stream, release all Slave(s) and * Master runtime */ - sdw_release_master_stream(stream); + sdw_release_master_stream(m_rt, stream); error: mutex_unlock(&slave->bus->bus_lock); return ret; @@ -1275,6 +1317,8 @@ static void sdw_acquire_bus_lock(struct sdw_stream_runtime *stream) * @stream: SoundWire stream * * Release the previously held bus_lock after reconfiguring the bus. + * NOTE: This function is called from SoundWire stream ops and is + * expected that a global lock is held before releasing bus_lock. */ static void sdw_release_bus_lock(struct sdw_stream_runtime *stream) { @@ -1290,31 +1334,36 @@ static void sdw_release_bus_lock(struct sdw_stream_runtime *stream) static int _sdw_prepare_stream(struct sdw_stream_runtime *stream) { - struct sdw_master_runtime *m_rt = stream->m_rt; - struct sdw_bus *bus = m_rt->bus; + struct sdw_master_runtime *m_rt = NULL; + struct sdw_bus *bus = NULL; struct sdw_master_prop *prop = NULL; struct sdw_bus_params params; int ret; - prop = &bus->prop; - memcpy(¶ms, &bus->params, sizeof(params)); + /* Prepare Master(s) and Slave(s) port(s) associated with stream */ + list_for_each_entry(m_rt, &stream->master_list, stream_node) { + bus = m_rt->bus; + prop = &bus->prop; + memcpy(¶ms, &bus->params, sizeof(params)); - /* TODO: Support Asynchronous mode */ - if ((prop->max_freq % stream->params.rate) != 0) { - dev_err(bus->dev, "Async mode not supported"); - return -EINVAL; - } + /* TODO: Support Asynchronous mode */ + if ((prop->max_freq % stream->params.rate) != 0) { + dev_err(bus->dev, "Async mode not supported"); + return -EINVAL; + } - /* Increment cumulative bus bandwidth */ - /* TODO: Update this during Device-Device support */ - bus->params.bandwidth += m_rt->stream->params.rate * - m_rt->ch_count * m_rt->stream->params.bps; + /* Increment cumulative bus bandwidth */ + /* TODO: Update this during Device-Device support */ + bus->params.bandwidth += m_rt->stream->params.rate * + m_rt->ch_count * m_rt->stream->params.bps; + + /* Program params */ + ret = sdw_program_params(bus); + if (ret < 0) { + dev_err(bus->dev, "Program params failed: %d", ret); + goto restore_params; + } - /* Program params */ - ret = sdw_program_params(bus); - if (ret < 0) { - dev_err(bus->dev, "Program params failed: %d", ret); - goto restore_params; } ret = do_bank_switch(stream); @@ -1323,12 +1372,16 @@ static int _sdw_prepare_stream(struct sdw_stream_runtime *stream) goto restore_params; } - /* Prepare port(s) on the new clock configuration */ - ret = sdw_prep_deprep_ports(m_rt, true); - if (ret < 0) { - dev_err(bus->dev, "Prepare port(s) failed ret = %d", - ret); - return ret; + list_for_each_entry(m_rt, &stream->master_list, stream_node) { + bus = m_rt->bus; + + /* Prepare port(s) on the new clock configuration */ + ret = sdw_prep_deprep_ports(m_rt, true); + if (ret < 0) { + dev_err(bus->dev, "Prepare port(s) failed ret = %d", + ret); + return ret; + } } stream->state = SDW_STREAM_PREPARED; @@ -1356,35 +1409,40 @@ int sdw_prepare_stream(struct sdw_stream_runtime *stream) return -EINVAL; } - mutex_lock(&stream->m_rt->bus->bus_lock); + sdw_acquire_bus_lock(stream); ret = _sdw_prepare_stream(stream); if (ret < 0) pr_err("Prepare for stream:%s failed: %d", stream->name, ret); - mutex_unlock(&stream->m_rt->bus->bus_lock); + sdw_release_bus_lock(stream); return ret; } EXPORT_SYMBOL(sdw_prepare_stream); static int _sdw_enable_stream(struct sdw_stream_runtime *stream) { - struct sdw_master_runtime *m_rt = stream->m_rt; - struct sdw_bus *bus = m_rt->bus; + struct sdw_master_runtime *m_rt = NULL; + struct sdw_bus *bus = NULL; int ret; - /* Program params */ - ret = sdw_program_params(bus); - if (ret < 0) { - dev_err(bus->dev, "Program params failed: %d", ret); - return ret; - } + /* Enable Master(s) and Slave(s) port(s) associated with stream */ + list_for_each_entry(m_rt, &stream->master_list, stream_node) { + bus = m_rt->bus; - /* Enable port(s) */ - ret = sdw_enable_disable_ports(m_rt, true); - if (ret < 0) { - dev_err(bus->dev, "Enable port(s) failed ret: %d", ret); - return ret; + /* Program params */ + ret = sdw_program_params(bus); + if (ret < 0) { + dev_err(bus->dev, "Program params failed: %d", ret); + return ret; + } + + /* Enable port(s) */ + ret = sdw_enable_disable_ports(m_rt, true); + if (ret < 0) { + dev_err(bus->dev, "Enable port(s) failed ret: %d", ret); + return ret; + } } ret = do_bank_switch(stream); @@ -1413,37 +1471,42 @@ int sdw_enable_stream(struct sdw_stream_runtime *stream) return -EINVAL; } - mutex_lock(&stream->m_rt->bus->bus_lock); + sdw_acquire_bus_lock(stream); ret = _sdw_enable_stream(stream); if (ret < 0) pr_err("Enable for stream:%s failed: %d", stream->name, ret); - mutex_unlock(&stream->m_rt->bus->bus_lock); + sdw_release_bus_lock(stream); return ret; } EXPORT_SYMBOL(sdw_enable_stream); static int _sdw_disable_stream(struct sdw_stream_runtime *stream) { - struct sdw_master_runtime *m_rt = stream->m_rt; - struct sdw_bus *bus = m_rt->bus; + struct sdw_master_runtime *m_rt = NULL; + struct sdw_bus *bus = NULL; int ret; - /* Disable port(s) */ - ret = sdw_enable_disable_ports(m_rt, false); - if (ret < 0) { - dev_err(bus->dev, "Disable port(s) failed: %d", ret); - return ret; + list_for_each_entry(m_rt, &stream->master_list, stream_node) { + bus = m_rt->bus; + /* Disable port(s) */ + ret = sdw_enable_disable_ports(m_rt, false); + if (ret < 0) { + dev_err(bus->dev, "Disable port(s) failed: %d", ret); + return ret; + } } - stream->state = SDW_STREAM_DISABLED; - /* Program params */ - ret = sdw_program_params(bus); - if (ret < 0) { - dev_err(bus->dev, "Program params failed: %d", ret); - return ret; + list_for_each_entry(m_rt, &stream->master_list, stream_node) { + bus = m_rt->bus; + /* Program params */ + ret = sdw_program_params(bus); + if (ret < 0) { + dev_err(bus->dev, "Program params failed: %d", ret); + return ret; + } } return do_bank_switch(stream); @@ -1465,43 +1528,46 @@ int sdw_disable_stream(struct sdw_stream_runtime *stream) return -EINVAL; } - mutex_lock(&stream->m_rt->bus->bus_lock); + sdw_acquire_bus_lock(stream); ret = _sdw_disable_stream(stream); if (ret < 0) pr_err("Disable for stream:%s failed: %d", stream->name, ret); - mutex_unlock(&stream->m_rt->bus->bus_lock); + sdw_release_bus_lock(stream); return ret; } EXPORT_SYMBOL(sdw_disable_stream); static int _sdw_deprepare_stream(struct sdw_stream_runtime *stream) { - struct sdw_master_runtime *m_rt = stream->m_rt; - struct sdw_bus *bus = m_rt->bus; + struct sdw_master_runtime *m_rt = NULL; + struct sdw_bus *bus = NULL; int ret = 0; - /* De-prepare port(s) */ - ret = sdw_prep_deprep_ports(m_rt, false); - if (ret < 0) { - dev_err(bus->dev, "De-prepare port(s) failed: %d", ret); - return ret; - } + list_for_each_entry(m_rt, &stream->master_list, stream_node) { + bus = m_rt->bus; + /* De-prepare port(s) */ + ret = sdw_prep_deprep_ports(m_rt, false); + if (ret < 0) { + dev_err(bus->dev, "De-prepare port(s) failed: %d", ret); + return ret; + } - stream->state = SDW_STREAM_DEPREPARED; + /* TODO: Update this during Device-Device support */ + bus->params.bandwidth -= m_rt->stream->params.rate * + m_rt->ch_count * m_rt->stream->params.bps; - /* TODO: Update this during Device-Device support */ - bus->params.bandwidth -= m_rt->stream->params.rate * - m_rt->ch_count * m_rt->stream->params.bps; + /* Program params */ + ret = sdw_program_params(bus); + if (ret < 0) { + dev_err(bus->dev, "Program params failed: %d", ret); + return ret; + } - /* Program params */ - ret = sdw_program_params(bus); - if (ret < 0) { - dev_err(bus->dev, "Program params failed: %d", ret); - return ret; } + stream->state = SDW_STREAM_DEPREPARED; return do_bank_switch(stream); } @@ -1521,13 +1587,12 @@ int sdw_deprepare_stream(struct sdw_stream_runtime *stream) return -EINVAL; } - mutex_lock(&stream->m_rt->bus->bus_lock); - + sdw_acquire_bus_lock(stream); ret = _sdw_deprepare_stream(stream); if (ret < 0) pr_err("De-prepare for stream:%d failed: %d", ret, ret); - mutex_unlock(&stream->m_rt->bus->bus_lock); + sdw_release_bus_lock(stream); return ret; } EXPORT_SYMBOL(sdw_deprepare_stream); diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index ccd8dcdf06ab..03df709fb8ef 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -768,7 +768,6 @@ struct sdw_stream_params { * @params: Stream parameters * @state: Current state of the stream * @type: Stream type PCM or PDM - * @m_rt: Master runtime * @master_list: List of Master runtime(s) in this stream. * master_list can contain only one m_rt per Master instance * for a stream @@ -778,7 +777,6 @@ struct sdw_stream_runtime { struct sdw_stream_params params; enum sdw_stream_state state; enum sdw_stream_type type; - struct sdw_master_runtime *m_rt; struct list_head master_list; }; -- cgit v1.2.3 From ce6e74d008ff5c8b43e3bafaa7343bf7eb69593e Mon Sep 17 00:00:00 2001 From: Shreyas NC Date: Fri, 27 Jul 2018 14:44:16 +0530 Subject: soundwire: Add support for multi link bank switch In cases of multiple Masters in a stream, synchronization between multiple Master(s) is achieved by performing bank switch together and using Master methods. Add sdw_ml_bank_switch() to wait for completion of bank switch. Signed-off-by: Sanyog Kale Signed-off-by: Shreyas NC Acked-by: Pierre-Louis Bossart Signed-off-by: Vinod Koul --- drivers/soundwire/bus.c | 5 ++ drivers/soundwire/bus.h | 2 + drivers/soundwire/stream.c | 145 ++++++++++++++++++++++++++++++++++++++---- include/linux/soundwire/sdw.h | 4 ++ 4 files changed, 144 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c index dbabd5e69343..1cbfedfc20ef 100644 --- a/drivers/soundwire/bus.c +++ b/drivers/soundwire/bus.c @@ -35,6 +35,11 @@ int sdw_add_bus_master(struct sdw_bus *bus) INIT_LIST_HEAD(&bus->slaves); INIT_LIST_HEAD(&bus->m_rt_list); + /* + * Initialize multi_link flag + * TODO: populate this flag by reading property from FW node + */ + bus->multi_link = false; if (bus->ops->read_prop) { ret = bus->ops->read_prop(bus); if (ret < 0) { diff --git a/drivers/soundwire/bus.h b/drivers/soundwire/bus.h index b6cfbdfc47d5..c77de05b8100 100644 --- a/drivers/soundwire/bus.h +++ b/drivers/soundwire/bus.h @@ -4,6 +4,8 @@ #ifndef __SDW_BUS_H #define __SDW_BUS_H +#define DEFAULT_BANK_SWITCH_TIMEOUT 3000 + #if IS_ENABLED(CONFIG_ACPI) int sdw_acpi_find_slaves(struct sdw_bus *bus); #else diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c index ee024d72dd7b..3d98f20cbd6a 100644 --- a/drivers/soundwire/stream.c +++ b/drivers/soundwire/stream.c @@ -626,9 +626,10 @@ static int sdw_program_params(struct sdw_bus *bus) return ret; } -static int sdw_bank_switch(struct sdw_bus *bus) +static int sdw_bank_switch(struct sdw_bus *bus, int m_rt_count) { int col_index, row_index; + bool multi_link; struct sdw_msg *wr_msg; u8 *wbuf = NULL; int ret = 0; @@ -638,6 +639,8 @@ static int sdw_bank_switch(struct sdw_bus *bus) if (!wr_msg) return -ENOMEM; + bus->defer_msg.msg = wr_msg; + wbuf = kzalloc(sizeof(*wbuf), GFP_KERNEL); if (!wbuf) { ret = -ENOMEM; @@ -658,17 +661,29 @@ static int sdw_bank_switch(struct sdw_bus *bus) SDW_MSG_FLAG_WRITE, wbuf); wr_msg->ssp_sync = true; - ret = sdw_transfer(bus, wr_msg); + /* + * Set the multi_link flag only when both the hardware supports + * and there is a stream handled by multiple masters + */ + multi_link = bus->multi_link && (m_rt_count > 1); + + if (multi_link) + ret = sdw_transfer_defer(bus, wr_msg, &bus->defer_msg); + else + ret = sdw_transfer(bus, wr_msg); + if (ret < 0) { dev_err(bus->dev, "Slave frame_ctrl reg write failed"); goto error; } - kfree(wr_msg); - kfree(wbuf); - bus->defer_msg.msg = NULL; - bus->params.curr_bank = !bus->params.curr_bank; - bus->params.next_bank = !bus->params.next_bank; + if (!multi_link) { + kfree(wr_msg); + kfree(wbuf); + bus->defer_msg.msg = NULL; + bus->params.curr_bank = !bus->params.curr_bank; + bus->params.next_bank = !bus->params.next_bank; + } return 0; @@ -679,36 +694,87 @@ error_1: return ret; } +/** + * sdw_ml_sync_bank_switch: Multilink register bank switch + * + * @bus: SDW bus instance + * + * Caller function should free the buffers on error + */ +static int sdw_ml_sync_bank_switch(struct sdw_bus *bus) +{ + unsigned long time_left; + + if (!bus->multi_link) + return 0; + + /* Wait for completion of transfer */ + time_left = wait_for_completion_timeout(&bus->defer_msg.complete, + bus->bank_switch_timeout); + + if (!time_left) { + dev_err(bus->dev, "Controller Timed out on bank switch"); + return -ETIMEDOUT; + } + + bus->params.curr_bank = !bus->params.curr_bank; + bus->params.next_bank = !bus->params.next_bank; + + if (bus->defer_msg.msg) { + kfree(bus->defer_msg.msg->buf); + kfree(bus->defer_msg.msg); + } + + return 0; +} + static int do_bank_switch(struct sdw_stream_runtime *stream) { struct sdw_master_runtime *m_rt = NULL; const struct sdw_master_ops *ops; struct sdw_bus *bus = NULL; + bool multi_link = false; int ret = 0; - list_for_each_entry(m_rt, &stream->master_list, stream_node) { bus = m_rt->bus; ops = bus->ops; + if (bus->multi_link) { + multi_link = true; + mutex_lock(&bus->msg_lock); + } + /* Pre-bank switch */ if (ops->pre_bank_switch) { ret = ops->pre_bank_switch(bus); if (ret < 0) { dev_err(bus->dev, "Pre bank switch op failed: %d", ret); - return ret; + goto msg_unlock; } } - /* Bank switch */ - ret = sdw_bank_switch(bus); + /* + * Perform Bank switch operation. + * For multi link cases, the actual bank switch is + * synchronized across all Masters and happens later as a + * part of post_bank_switch ops. + */ + ret = sdw_bank_switch(bus, stream->m_rt_count); if (ret < 0) { dev_err(bus->dev, "Bank switch failed: %d", ret); - return ret; + goto error; + } } + /* + * For multi link cases, it is expected that the bank switch is + * triggered by the post_bank_switch for the first Master in the list + * and for the other Masters the post_bank_switch() should return doing + * nothing. + */ list_for_each_entry(m_rt, &stream->master_list, stream_node) { bus = m_rt->bus; ops = bus->ops; @@ -719,7 +785,47 @@ static int do_bank_switch(struct sdw_stream_runtime *stream) if (ret < 0) { dev_err(bus->dev, "Post bank switch op failed: %d", ret); + goto error; } + } else if (bus->multi_link && stream->m_rt_count > 1) { + dev_err(bus->dev, + "Post bank switch ops not implemented"); + goto error; + } + + /* Set the bank switch timeout to default, if not set */ + if (!bus->bank_switch_timeout) + bus->bank_switch_timeout = DEFAULT_BANK_SWITCH_TIMEOUT; + + /* Check if bank switch was successful */ + ret = sdw_ml_sync_bank_switch(bus); + if (ret < 0) { + dev_err(bus->dev, + "multi link bank switch failed: %d", ret); + goto error; + } + + mutex_unlock(&bus->msg_lock); + } + + return ret; + +error: + list_for_each_entry(m_rt, &stream->master_list, stream_node) { + + bus = m_rt->bus; + + kfree(bus->defer_msg.msg->buf); + kfree(bus->defer_msg.msg); + } + +msg_unlock: + + if (multi_link) { + list_for_each_entry(m_rt, &stream->master_list, stream_node) { + bus = m_rt->bus; + if (mutex_is_locked(&bus->msg_lock)) + mutex_unlock(&bus->msg_lock); } } @@ -964,6 +1070,7 @@ int sdw_stream_remove_master(struct sdw_bus *bus, sdw_master_port_release(bus, m_rt); sdw_release_master_stream(m_rt, stream); + stream->m_rt_count--; } if (list_empty(&stream->master_list)) @@ -1150,6 +1257,18 @@ int sdw_stream_add_master(struct sdw_bus *bus, mutex_lock(&bus->bus_lock); + /* + * For multi link streams, add the second master only if + * the bus supports it. + * Check if bus->multi_link is set + */ + if (!bus->multi_link && stream->m_rt_count > 0) { + dev_err(bus->dev, + "Multilink not supported, link %d", bus->link_id); + ret = -EINVAL; + goto unlock; + } + m_rt = sdw_alloc_master_rt(bus, stream_config, stream); if (!m_rt) { dev_err(bus->dev, @@ -1167,6 +1286,8 @@ int sdw_stream_add_master(struct sdw_bus *bus, if (ret) goto stream_error; + stream->m_rt_count++; + goto unlock; stream_error: diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 03df709fb8ef..c6aa2bf847c7 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -678,6 +678,9 @@ struct sdw_master_ops { * @defer_msg: Defer message * @clk_stop_timeout: Clock stop timeout computed * @bank_switch_timeout: Bank switch timeout computed + * @multi_link: Store bus property that indicates if multi links + * are supported. This flag is populated by drivers after reading + * appropriate firmware (ACPI/DT). */ struct sdw_bus { struct device *dev; @@ -694,6 +697,7 @@ struct sdw_bus { struct sdw_defer defer_msg; unsigned int clk_stop_timeout; u32 bank_switch_timeout; + bool multi_link; }; int sdw_add_bus_master(struct sdw_bus *bus); -- cgit v1.2.3 From 9b5c132a1ec98895fe40ba73a19e0a17293122e5 Mon Sep 17 00:00:00 2001 From: Shreyas NC Date: Fri, 27 Jul 2018 14:44:15 +0530 Subject: soundwire: keep track of Masters in a stream A multi link bankswitch can be done if the hardware supports and the stream is handled by multiple Master(s). This preparatory patch adds support to track m_rt in a stream. Modifying m_rt_count and usage is added as part of the next patch. Signed-off-by: Shreyas NC Acked-by: Pierre-Louis Bossart Signed-off-by: Vinod Koul --- drivers/soundwire/stream.c | 1 + include/linux/soundwire/sdw.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c index 3d98f20cbd6a..bd879b1a76c8 100644 --- a/drivers/soundwire/stream.c +++ b/drivers/soundwire/stream.c @@ -865,6 +865,7 @@ struct sdw_stream_runtime *sdw_alloc_stream(char *stream_name) stream->name = stream_name; INIT_LIST_HEAD(&stream->master_list); stream->state = SDW_STREAM_ALLOCATED; + stream->m_rt_count = 0; return stream; } diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index c6aa2bf847c7..df313913e856 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -775,6 +775,7 @@ struct sdw_stream_params { * @master_list: List of Master runtime(s) in this stream. * master_list can contain only one m_rt per Master instance * for a stream + * @m_rt_count: Count of Master runtime(s) in this stream */ struct sdw_stream_runtime { char *name; @@ -782,6 +783,7 @@ struct sdw_stream_runtime { enum sdw_stream_state state; enum sdw_stream_type type; struct list_head master_list; + int m_rt_count; }; struct sdw_stream_runtime *sdw_alloc_stream(char *stream_name); -- cgit v1.2.3 From 976516404ff3fab2a8caa8bd6f5efc1437fed0b8 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 14 Aug 2018 14:02:57 +0200 Subject: y2038: remove unused time interfaces After many small patches, at least some of the deprecated interfaces have no remaining users any more and can be removed: current_kernel_time do_settimeofday get_monotonic_boottime get_monotonic_boottime64 get_monotonic_coarse get_monotonic_coarse64 getrawmonotonic64 ktime_get_real_ts timekeeping_clocktai timespec_trunc timespec_valid_strict time_to_tm For many of the remaining time functions, we are missing one or two patches that failed to make it into 4.19, they will be removed in the following merge window. The replacement functions for the removed interfaces are documented in Documentation/core-api/timekeeping.rst. Signed-off-by: Arnd Bergmann --- include/linux/time32.h | 25 ---------------------- include/linux/timekeeping.h | 12 ----------- include/linux/timekeeping32.h | 50 ------------------------------------------- kernel/time/time.c | 24 --------------------- 4 files changed, 111 deletions(-) (limited to 'include/linux') diff --git a/include/linux/time32.h b/include/linux/time32.h index d1ae43c13e25..92c0ca092d93 100644 --- a/include/linux/time32.h +++ b/include/linux/time32.h @@ -105,16 +105,6 @@ static inline bool timespec_valid(const struct timespec *ts) return true; } -static inline bool timespec_valid_strict(const struct timespec *ts) -{ - if (!timespec_valid(ts)) - return false; - /* Disallow values that could overflow ktime_t */ - if ((unsigned long long)ts->tv_sec >= KTIME_SEC_MAX) - return false; - return true; -} - /** * timespec_to_ns - Convert timespec to nanoseconds * @ts: pointer to the timespec variable to be converted @@ -149,19 +139,6 @@ static __always_inline void timespec_add_ns(struct timespec *a, u64 ns) a->tv_nsec = ns; } -/** - * time_to_tm - converts the calendar time to local broken-down time - * - * @totalsecs the number of seconds elapsed since 00:00:00 on January 1, 1970, - * Coordinated Universal Time (UTC). - * @offset offset seconds adding to totalsecs. - * @result pointer to struct tm variable to receive broken-down time - */ -static inline void time_to_tm(time_t totalsecs, int offset, struct tm *result) -{ - time64_to_tm(totalsecs, offset, result); -} - static inline unsigned long mktime(const unsigned int year, const unsigned int mon, const unsigned int day, const unsigned int hour, const unsigned int min, @@ -183,8 +160,6 @@ static inline bool timeval_valid(const struct timeval *tv) return true; } -extern struct timespec timespec_trunc(struct timespec t, unsigned int gran); - /** * timeval_to_ns - Convert timeval to nanoseconds * @ts: pointer to the timeval variable to be converted diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 5d738804e3d6..3faba06411aa 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -266,9 +266,6 @@ extern int update_persistent_clock64(struct timespec64 now); * deprecated aliases, don't use in new code */ #define getnstimeofday64(ts) ktime_get_real_ts64(ts) -#define get_monotonic_boottime64(ts) ktime_get_boottime_ts64(ts) -#define getrawmonotonic64(ts) ktime_get_raw_ts64(ts) -#define timekeeping_clocktai64(ts) ktime_get_clocktai_ts64(ts) static inline struct timespec64 current_kernel_time64(void) { @@ -279,13 +276,4 @@ static inline struct timespec64 current_kernel_time64(void) return ts; } -static inline struct timespec64 get_monotonic_coarse64(void) -{ - struct timespec64 ts; - - ktime_get_coarse_ts64(&ts); - - return ts; -} - #endif diff --git a/include/linux/timekeeping32.h b/include/linux/timekeeping32.h index 8762c2f45f8b..a4a4991160fb 100644 --- a/include/linux/timekeeping32.h +++ b/include/linux/timekeeping32.h @@ -9,26 +9,6 @@ extern void do_gettimeofday(struct timeval *tv); unsigned long get_seconds(void); -static inline struct timespec current_kernel_time(void) -{ - struct timespec64 ts64; - - ktime_get_coarse_real_ts64(&ts64); - - return timespec64_to_timespec(ts64); -} - -/** - * Deprecated. Use do_settimeofday64(). - */ -static inline int do_settimeofday(const struct timespec *ts) -{ - struct timespec64 ts64; - - ts64 = timespec_to_timespec64(*ts); - return do_settimeofday64(&ts64); -} - static inline void getnstimeofday(struct timespec *ts) { struct timespec64 ts64; @@ -45,14 +25,6 @@ static inline void ktime_get_ts(struct timespec *ts) *ts = timespec64_to_timespec(ts64); } -static inline void ktime_get_real_ts(struct timespec *ts) -{ - struct timespec64 ts64; - - ktime_get_real_ts64(&ts64); - *ts = timespec64_to_timespec(ts64); -} - static inline void getrawmonotonic(struct timespec *ts) { struct timespec64 ts64; @@ -61,15 +33,6 @@ static inline void getrawmonotonic(struct timespec *ts) *ts = timespec64_to_timespec(ts64); } -static inline struct timespec get_monotonic_coarse(void) -{ - struct timespec64 ts64; - - ktime_get_coarse_ts64(&ts64); - - return timespec64_to_timespec(ts64); -} - static inline void getboottime(struct timespec *ts) { struct timespec64 ts64; @@ -78,19 +41,6 @@ static inline void getboottime(struct timespec *ts) *ts = timespec64_to_timespec(ts64); } -/* - * Timespec interfaces utilizing the ktime based ones - */ -static inline void get_monotonic_boottime(struct timespec *ts) -{ - *ts = ktime_to_timespec(ktime_get_boottime()); -} - -static inline void timekeeping_clocktai(struct timespec *ts) -{ - *ts = ktime_to_timespec(ktime_get_clocktai()); -} - /* * Persistent clock related interfaces */ diff --git a/kernel/time/time.c b/kernel/time/time.c index ccdb351277ee..712543011106 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -342,30 +342,6 @@ unsigned int jiffies_to_usecs(const unsigned long j) } EXPORT_SYMBOL(jiffies_to_usecs); -/** - * timespec_trunc - Truncate timespec to a granularity - * @t: Timespec - * @gran: Granularity in ns. - * - * Truncate a timespec to a granularity. Always rounds down. gran must - * not be 0 nor greater than a second (NSEC_PER_SEC, or 10^9 ns). - */ -struct timespec timespec_trunc(struct timespec t, unsigned gran) -{ - /* Avoid division in the common cases 1 ns and 1 s. */ - if (gran == 1) { - /* nothing */ - } else if (gran == NSEC_PER_SEC) { - t.tv_nsec = 0; - } else if (gran > 1 && gran < NSEC_PER_SEC) { - t.tv_nsec -= t.tv_nsec % gran; - } else { - WARN(1, "illegal file time granularity: %u", gran); - } - return t; -} -EXPORT_SYMBOL(timespec_trunc); - /* * mktime64 - Converts date to seconds. * Converts Gregorian date to seconds since 1970-01-01 00:00:00. -- cgit v1.2.3 From 33e26418193f58d1895f2f968e1953b1caf8deb7 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 14 Aug 2018 15:18:20 +0200 Subject: y2038: make do_gettimeofday() and get_seconds() inline get_seconds() and do_gettimeofday() are only used by a few modules now any more (waiting for the respective patches to get accepted), and they are among the last holdouts of code that is not y2038 safe in the core kernel. Move the implementation into the timekeeping32.h header to clean up the core kernel and isolate the old interfaces further. Signed-off-by: Arnd Bergmann --- include/linux/timekeeping32.h | 15 +++++++++++++-- kernel/time/time.c | 15 +++++++++------ kernel/time/timekeeping.c | 24 ------------------------ 3 files changed, 22 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timekeeping32.h b/include/linux/timekeeping32.h index a4a4991160fb..a502616f7e1c 100644 --- a/include/linux/timekeeping32.h +++ b/include/linux/timekeeping32.h @@ -6,8 +6,19 @@ * over time so we can remove the file here. */ -extern void do_gettimeofday(struct timeval *tv); -unsigned long get_seconds(void); +static inline void do_gettimeofday(struct timeval *tv) +{ + struct timespec64 now; + + ktime_get_real_ts64(&now); + tv->tv_sec = now.tv_sec; + tv->tv_usec = now.tv_nsec/1000; +} + +static inline unsigned long get_seconds(void) +{ + return ktime_get_real_seconds(); +} static inline void getnstimeofday(struct timespec *ts) { diff --git a/kernel/time/time.c b/kernel/time/time.c index 712543011106..de332250d6fa 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -144,9 +144,11 @@ SYSCALL_DEFINE2(gettimeofday, struct timeval __user *, tv, struct timezone __user *, tz) { if (likely(tv != NULL)) { - struct timeval ktv; - do_gettimeofday(&ktv); - if (copy_to_user(tv, &ktv, sizeof(ktv))) + struct timespec64 ts; + + ktime_get_real_ts64(&ts); + if (put_user(ts.tv_sec, &tv->tv_sec) || + put_user(ts.tv_nsec / 1000, &tv->tv_usec)) return -EFAULT; } if (unlikely(tz != NULL)) { @@ -227,10 +229,11 @@ COMPAT_SYSCALL_DEFINE2(gettimeofday, struct compat_timeval __user *, tv, struct timezone __user *, tz) { if (tv) { - struct timeval ktv; + struct timespec64 ts; - do_gettimeofday(&ktv); - if (compat_put_timeval(&ktv, tv)) + ktime_get_real_ts64(&ts); + if (put_user(ts.tv_sec, &tv->tv_sec) || + put_user(ts.tv_nsec / 1000, &tv->tv_usec)) return -EFAULT; } if (tz) { diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index f3b22f456fac..2d110c948805 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1211,22 +1211,6 @@ int get_device_system_crosststamp(int (*get_time_fn) } EXPORT_SYMBOL_GPL(get_device_system_crosststamp); -/** - * do_gettimeofday - Returns the time of day in a timeval - * @tv: pointer to the timeval to be set - * - * NOTE: Users should be converted to using getnstimeofday() - */ -void do_gettimeofday(struct timeval *tv) -{ - struct timespec64 now; - - getnstimeofday64(&now); - tv->tv_sec = now.tv_sec; - tv->tv_usec = now.tv_nsec/1000; -} -EXPORT_SYMBOL(do_gettimeofday); - /** * do_settimeofday64 - Sets the time of day. * @ts: pointer to the timespec64 variable containing the new time @@ -2174,14 +2158,6 @@ void getboottime64(struct timespec64 *ts) } EXPORT_SYMBOL_GPL(getboottime64); -unsigned long get_seconds(void) -{ - struct timekeeper *tk = &tk_core.timekeeper; - - return tk->xtime_sec; -} -EXPORT_SYMBOL(get_seconds); - void ktime_get_coarse_real_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; -- cgit v1.2.3 From 9afc5eee65ca7d717a99d6fe8f4adfe32a40940a Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 13 Jul 2018 12:52:28 +0200 Subject: y2038: globally rename compat_time to old_time32 Christoph Hellwig suggested a slightly different path for handling backwards compatibility with the 32-bit time_t based system calls: Rather than simply reusing the compat_sys_* entry points on 32-bit architectures unchanged, we get rid of those entry points and the compat_time types by renaming them to something that makes more sense on 32-bit architectures (which don't have a compat mode otherwise), and then share the entry points under the new name with the 64-bit architectures that use them for implementing the compatibility. The following types and interfaces are renamed here, and moved from linux/compat_time.h to linux/time32.h: old new --- --- compat_time_t old_time32_t struct compat_timeval struct old_timeval32 struct compat_timespec struct old_timespec32 struct compat_itimerspec struct old_itimerspec32 ns_to_compat_timeval() ns_to_old_timeval32() get_compat_itimerspec64() get_old_itimerspec32() put_compat_itimerspec64() put_old_itimerspec32() compat_get_timespec64() get_old_timespec32() compat_put_timespec64() put_old_timespec32() As we already have aliases in place, this patch addresses only the instances that are relevant to the system call interface in particular, not those that occur in device drivers and other modules. Those will get handled separately, while providing the 64-bit version of the respective interfaces. I'm not renaming the timex, rusage and itimerval structures, as we are still debating what the new interface will look like, and whether we will need a replacement at all. This also doesn't change the names of the syscall entry points, which can be done more easily when we actually switch over the 32-bit architectures to use them, at that point we need to change COMPAT_SYSCALL_DEFINEx to SYSCALL_DEFINEx with a new name, e.g. with a _time32 suffix. Suggested-by: Christoph Hellwig Link: https://lore.kernel.org/lkml/20180705222110.GA5698@infradead.org/ Signed-off-by: Arnd Bergmann --- arch/arm64/include/asm/compat.h | 6 +-- arch/arm64/include/asm/stat.h | 2 +- arch/mips/include/asm/compat.h | 6 +-- arch/mips/kernel/binfmt_elfn32.c | 14 +++--- arch/mips/kernel/binfmt_elfo32.c | 14 +++--- arch/parisc/include/asm/compat.h | 6 +-- arch/powerpc/include/asm/compat.h | 6 +-- arch/powerpc/kernel/asm-offsets.c | 8 ++-- arch/powerpc/oprofile/backtrace.c | 2 +- arch/sparc/include/asm/compat.h | 6 +-- fs/aio.c | 8 ++-- fs/compat_binfmt_elf.c | 2 +- fs/select.c | 20 ++++---- fs/timerfd.c | 12 ++--- fs/utimes.c | 12 ++--- include/linux/compat.h | 96 +++++++++++++++++++-------------------- include/linux/compat_time.h | 32 ------------- include/linux/elfcore-compat.h | 8 ++-- include/linux/restart_block.h | 4 +- include/linux/syscalls.h | 2 +- include/linux/time32.h | 48 +++++++++++++++----- ipc/mqueue.c | 8 ++-- ipc/msg.c | 6 +-- ipc/sem.c | 10 ++-- ipc/shm.c | 6 +-- ipc/syscall.c | 2 +- ipc/util.h | 2 +- kernel/compat.c | 8 ++-- kernel/futex_compat.c | 2 +- kernel/sched/core.c | 4 +- kernel/signal.c | 2 +- kernel/time/hrtimer.c | 8 ++-- kernel/time/posix-stubs.c | 18 ++++---- kernel/time/posix-timers.c | 30 ++++++------ kernel/time/time.c | 58 +++++++++++------------ net/compat.c | 4 +- 36 files changed, 237 insertions(+), 245 deletions(-) delete mode 100644 include/linux/compat_time.h (limited to 'include/linux') diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h index 1a037b94eba1..4a89007db14a 100644 --- a/arch/arm64/include/asm/compat.h +++ b/arch/arm64/include/asm/compat.h @@ -86,11 +86,11 @@ struct compat_stat { compat_off_t st_size; compat_off_t st_blksize; compat_off_t st_blocks; - compat_time_t st_atime; + old_time32_t st_atime; compat_ulong_t st_atime_nsec; - compat_time_t st_mtime; + old_time32_t st_mtime; compat_ulong_t st_mtime_nsec; - compat_time_t st_ctime; + old_time32_t st_ctime; compat_ulong_t st_ctime_nsec; compat_ulong_t __unused4[2]; }; diff --git a/arch/arm64/include/asm/stat.h b/arch/arm64/include/asm/stat.h index eab738019707..397c6ccd04e7 100644 --- a/arch/arm64/include/asm/stat.h +++ b/arch/arm64/include/asm/stat.h @@ -20,7 +20,7 @@ #ifdef CONFIG_COMPAT -#include +#include #include /* diff --git a/arch/mips/include/asm/compat.h b/arch/mips/include/asm/compat.h index 78675f19440f..7dcbd855814e 100644 --- a/arch/mips/include/asm/compat.h +++ b/arch/mips/include/asm/compat.h @@ -59,11 +59,11 @@ struct compat_stat { s32 st_pad2[2]; compat_off_t st_size; s32 st_pad3; - compat_time_t st_atime; + old_time32_t st_atime; s32 st_atime_nsec; - compat_time_t st_mtime; + old_time32_t st_mtime; s32 st_mtime_nsec; - compat_time_t st_ctime; + old_time32_t st_ctime; s32 st_ctime_nsec; s32 st_blksize; s32 st_blocks; diff --git a/arch/mips/kernel/binfmt_elfn32.c b/arch/mips/kernel/binfmt_elfn32.c index 89b234844534..7a12763d553a 100644 --- a/arch/mips/kernel/binfmt_elfn32.c +++ b/arch/mips/kernel/binfmt_elfn32.c @@ -54,10 +54,10 @@ struct elf_prstatus32 pid_t pr_ppid; pid_t pr_pgrp; pid_t pr_sid; - struct compat_timeval pr_utime; /* User time */ - struct compat_timeval pr_stime; /* System time */ - struct compat_timeval pr_cutime;/* Cumulative user time */ - struct compat_timeval pr_cstime;/* Cumulative system time */ + struct old_timeval32 pr_utime; /* User time */ + struct old_timeval32 pr_stime; /* System time */ + struct old_timeval32 pr_cutime;/* Cumulative user time */ + struct old_timeval32 pr_cstime;/* Cumulative system time */ elf_gregset_t pr_reg; /* GP registers */ int pr_fpvalid; /* True if math co-processor being used. */ }; @@ -81,9 +81,9 @@ struct elf_prpsinfo32 #define elf_caddr_t u32 #define init_elf_binfmt init_elfn32_binfmt -#define jiffies_to_timeval jiffies_to_compat_timeval +#define jiffies_to_timeval jiffies_to_old_timeval32 static __inline__ void -jiffies_to_compat_timeval(unsigned long jiffies, struct compat_timeval *value) +jiffies_to_old_timeval32(unsigned long jiffies, struct old_timeval32 *value) { /* * Convert jiffies to nanoseconds and separate with @@ -101,6 +101,6 @@ jiffies_to_compat_timeval(unsigned long jiffies, struct compat_timeval *value) #define TASK_SIZE TASK_SIZE32 #undef ns_to_timeval -#define ns_to_timeval ns_to_compat_timeval +#define ns_to_timeval ns_to_old_timeval32 #include "../../../fs/binfmt_elf.c" diff --git a/arch/mips/kernel/binfmt_elfo32.c b/arch/mips/kernel/binfmt_elfo32.c index a88c59db3d48..e6db06a1d31a 100644 --- a/arch/mips/kernel/binfmt_elfo32.c +++ b/arch/mips/kernel/binfmt_elfo32.c @@ -59,10 +59,10 @@ struct elf_prstatus32 pid_t pr_ppid; pid_t pr_pgrp; pid_t pr_sid; - struct compat_timeval pr_utime; /* User time */ - struct compat_timeval pr_stime; /* System time */ - struct compat_timeval pr_cutime;/* Cumulative user time */ - struct compat_timeval pr_cstime;/* Cumulative system time */ + struct old_timeval32 pr_utime; /* User time */ + struct old_timeval32 pr_stime; /* System time */ + struct old_timeval32 pr_cutime;/* Cumulative user time */ + struct old_timeval32 pr_cstime;/* Cumulative system time */ elf_gregset_t pr_reg; /* GP registers */ int pr_fpvalid; /* True if math co-processor being used. */ }; @@ -86,9 +86,9 @@ struct elf_prpsinfo32 #define elf_caddr_t u32 #define init_elf_binfmt init_elf32_binfmt -#define jiffies_to_timeval jiffies_to_compat_timeval +#define jiffies_to_timeval jiffies_to_old_timeval32 static inline void -jiffies_to_compat_timeval(unsigned long jiffies, struct compat_timeval *value) +jiffies_to_old_timeval32(unsigned long jiffies, struct old_timeval32 *value) { /* * Convert jiffies to nanoseconds and separate with @@ -104,6 +104,6 @@ jiffies_to_compat_timeval(unsigned long jiffies, struct compat_timeval *value) #define TASK_SIZE TASK_SIZE32 #undef ns_to_timeval -#define ns_to_timeval ns_to_compat_timeval +#define ns_to_timeval ns_to_old_timeval32 #include "../../../fs/binfmt_elf.c" diff --git a/arch/parisc/include/asm/compat.h b/arch/parisc/include/asm/compat.h index ab8a54771507..32dadaf2b534 100644 --- a/arch/parisc/include/asm/compat.h +++ b/arch/parisc/include/asm/compat.h @@ -48,11 +48,11 @@ struct compat_stat { u16 st_reserved2; /* old st_gid */ compat_dev_t st_rdev; compat_off_t st_size; - compat_time_t st_atime; + old_time32_t st_atime; u32 st_atime_nsec; - compat_time_t st_mtime; + old_time32_t st_mtime; u32 st_mtime_nsec; - compat_time_t st_ctime; + old_time32_t st_ctime; u32 st_ctime_nsec; s32 st_blksize; s32 st_blocks; diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h index 85c8af2bb272..93f79d1a03c3 100644 --- a/arch/powerpc/include/asm/compat.h +++ b/arch/powerpc/include/asm/compat.h @@ -55,11 +55,11 @@ struct compat_stat { compat_off_t st_size; compat_off_t st_blksize; compat_off_t st_blocks; - compat_time_t st_atime; + old_time32_t st_atime; u32 st_atime_nsec; - compat_time_t st_mtime; + old_time32_t st_mtime; u32 st_mtime_nsec; - compat_time_t st_ctime; + old_time32_t st_ctime; u32 st_ctime_nsec; u32 __unused4[2]; }; diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 89cf15566c4e..041a115789a1 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -387,12 +387,12 @@ int main(void) OFFSET(CFG_SYSCALL_MAP64, vdso_data, syscall_map_64); OFFSET(TVAL64_TV_SEC, timeval, tv_sec); OFFSET(TVAL64_TV_USEC, timeval, tv_usec); - OFFSET(TVAL32_TV_SEC, compat_timeval, tv_sec); - OFFSET(TVAL32_TV_USEC, compat_timeval, tv_usec); + OFFSET(TVAL32_TV_SEC, old_timeval32, tv_sec); + OFFSET(TVAL32_TV_USEC, old_timeval32, tv_usec); OFFSET(TSPC64_TV_SEC, timespec, tv_sec); OFFSET(TSPC64_TV_NSEC, timespec, tv_nsec); - OFFSET(TSPC32_TV_SEC, compat_timespec, tv_sec); - OFFSET(TSPC32_TV_NSEC, compat_timespec, tv_nsec); + OFFSET(TSPC32_TV_SEC, old_timespec32, tv_sec); + OFFSET(TSPC32_TV_NSEC, old_timespec32, tv_nsec); #else OFFSET(TVAL32_TV_SEC, timeval, tv_sec); OFFSET(TVAL32_TV_USEC, timeval, tv_usec); diff --git a/arch/powerpc/oprofile/backtrace.c b/arch/powerpc/oprofile/backtrace.c index ad054dd0d666..5df6290d1ccc 100644 --- a/arch/powerpc/oprofile/backtrace.c +++ b/arch/powerpc/oprofile/backtrace.c @@ -7,7 +7,7 @@ * 2 of the License, or (at your option) any later version. **/ -#include +#include #include #include #include diff --git a/arch/sparc/include/asm/compat.h b/arch/sparc/include/asm/compat.h index 4eb51d2dae98..7018cb60beef 100644 --- a/arch/sparc/include/asm/compat.h +++ b/arch/sparc/include/asm/compat.h @@ -47,11 +47,11 @@ struct compat_stat { __compat_gid_t st_gid; compat_dev_t st_rdev; compat_off_t st_size; - compat_time_t st_atime; + old_time32_t st_atime; compat_ulong_t st_atime_nsec; - compat_time_t st_mtime; + old_time32_t st_mtime; compat_ulong_t st_mtime_nsec; - compat_time_t st_ctime; + old_time32_t st_ctime; compat_ulong_t st_ctime_nsec; compat_off_t st_blksize; compat_off_t st_blocks; diff --git a/fs/aio.c b/fs/aio.c index b9350f3360c6..301e6314183b 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -2135,12 +2135,12 @@ COMPAT_SYSCALL_DEFINE5(io_getevents, compat_aio_context_t, ctx_id, compat_long_t, min_nr, compat_long_t, nr, struct io_event __user *, events, - struct compat_timespec __user *, timeout) + struct old_timespec32 __user *, timeout) { struct timespec64 t; int ret; - if (timeout && compat_get_timespec64(&t, timeout)) + if (timeout && get_old_timespec32(&t, timeout)) return -EFAULT; ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL); @@ -2160,7 +2160,7 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents, compat_long_t, min_nr, compat_long_t, nr, struct io_event __user *, events, - struct compat_timespec __user *, timeout, + struct old_timespec32 __user *, timeout, const struct __compat_aio_sigset __user *, usig) { struct __compat_aio_sigset ksig = { NULL, }; @@ -2168,7 +2168,7 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents, struct timespec64 t; int ret; - if (timeout && compat_get_timespec64(&t, timeout)) + if (timeout && get_old_timespec32(&t, timeout)) return -EFAULT; if (usig && copy_from_user(&ksig, usig, sizeof(ksig))) diff --git a/fs/compat_binfmt_elf.c b/fs/compat_binfmt_elf.c index 504b3c3539dc..15f6e96b3bd9 100644 --- a/fs/compat_binfmt_elf.c +++ b/fs/compat_binfmt_elf.c @@ -52,7 +52,7 @@ #define elf_prpsinfo compat_elf_prpsinfo #undef ns_to_timeval -#define ns_to_timeval ns_to_compat_timeval +#define ns_to_timeval ns_to_old_timeval32 /* * To use this file, asm/elf.h must define compat_elf_check_arch. diff --git a/fs/select.c b/fs/select.c index 4a6b6e4b21cb..22b3bf89f051 100644 --- a/fs/select.c +++ b/fs/select.c @@ -1120,7 +1120,7 @@ int compat_poll_select_copy_remaining(struct timespec64 *end_time, void __user * ts.tv_sec = ts.tv_nsec = 0; if (timeval) { - struct compat_timeval rtv; + struct old_timeval32 rtv; rtv.tv_sec = ts.tv_sec; rtv.tv_usec = ts.tv_nsec / NSEC_PER_USEC; @@ -1128,7 +1128,7 @@ int compat_poll_select_copy_remaining(struct timespec64 *end_time, void __user * if (!copy_to_user(p, &rtv, sizeof(rtv))) return ret; } else { - if (!compat_put_timespec64(&ts, p)) + if (!put_old_timespec32(&ts, p)) return ret; } /* @@ -1257,10 +1257,10 @@ out_nofds: static int do_compat_select(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, - struct compat_timeval __user *tvp) + struct old_timeval32 __user *tvp) { struct timespec64 end_time, *to = NULL; - struct compat_timeval tv; + struct old_timeval32 tv; int ret; if (tvp) { @@ -1282,7 +1282,7 @@ static int do_compat_select(int n, compat_ulong_t __user *inp, COMPAT_SYSCALL_DEFINE5(select, int, n, compat_ulong_t __user *, inp, compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, - struct compat_timeval __user *, tvp) + struct old_timeval32 __user *, tvp) { return do_compat_select(n, inp, outp, exp, tvp); } @@ -1307,7 +1307,7 @@ COMPAT_SYSCALL_DEFINE1(old_select, struct compat_sel_arg_struct __user *, arg) static long do_compat_pselect(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, - struct compat_timespec __user *tsp, compat_sigset_t __user *sigmask, + struct old_timespec32 __user *tsp, compat_sigset_t __user *sigmask, compat_size_t sigsetsize) { sigset_t ksigmask, sigsaved; @@ -1315,7 +1315,7 @@ static long do_compat_pselect(int n, compat_ulong_t __user *inp, int ret; if (tsp) { - if (compat_get_timespec64(&ts, tsp)) + if (get_old_timespec32(&ts, tsp)) return -EFAULT; to = &end_time; @@ -1355,7 +1355,7 @@ static long do_compat_pselect(int n, compat_ulong_t __user *inp, COMPAT_SYSCALL_DEFINE6(pselect6, int, n, compat_ulong_t __user *, inp, compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, - struct compat_timespec __user *, tsp, void __user *, sig) + struct old_timespec32 __user *, tsp, void __user *, sig) { compat_size_t sigsetsize = 0; compat_uptr_t up = 0; @@ -1373,7 +1373,7 @@ COMPAT_SYSCALL_DEFINE6(pselect6, int, n, compat_ulong_t __user *, inp, } COMPAT_SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, - unsigned int, nfds, struct compat_timespec __user *, tsp, + unsigned int, nfds, struct old_timespec32 __user *, tsp, const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize) { sigset_t ksigmask, sigsaved; @@ -1381,7 +1381,7 @@ COMPAT_SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, int ret; if (tsp) { - if (compat_get_timespec64(&ts, tsp)) + if (get_old_timespec32(&ts, tsp)) return -EFAULT; to = &end_time; diff --git a/fs/timerfd.c b/fs/timerfd.c index d69ad801eb80..803ca070d42e 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -561,29 +561,29 @@ SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct __kernel_itimerspec __user *, #ifdef CONFIG_COMPAT_32BIT_TIME COMPAT_SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags, - const struct compat_itimerspec __user *, utmr, - struct compat_itimerspec __user *, otmr) + const struct old_itimerspec32 __user *, utmr, + struct old_itimerspec32 __user *, otmr) { struct itimerspec64 new, old; int ret; - if (get_compat_itimerspec64(&new, utmr)) + if (get_old_itimerspec32(&new, utmr)) return -EFAULT; ret = do_timerfd_settime(ufd, flags, &new, &old); if (ret) return ret; - if (otmr && put_compat_itimerspec64(&old, otmr)) + if (otmr && put_old_itimerspec32(&old, otmr)) return -EFAULT; return ret; } COMPAT_SYSCALL_DEFINE2(timerfd_gettime, int, ufd, - struct compat_itimerspec __user *, otmr) + struct old_itimerspec32 __user *, otmr) { struct itimerspec64 kotmr; int ret = do_timerfd_gettime(ufd, &kotmr); if (ret) return ret; - return put_compat_itimerspec64(&kotmr, otmr) ? -EFAULT : 0; + return put_old_itimerspec32(&kotmr, otmr) ? -EFAULT : 0; } #endif diff --git a/fs/utimes.c b/fs/utimes.c index 69d4b6ba1bfb..79a65c163f40 100644 --- a/fs/utimes.c +++ b/fs/utimes.c @@ -245,13 +245,13 @@ COMPAT_SYSCALL_DEFINE2(utime, const char __user *, filename, return do_utimes(AT_FDCWD, filename, t ? tv : NULL, 0); } -COMPAT_SYSCALL_DEFINE4(utimensat, unsigned int, dfd, const char __user *, filename, struct compat_timespec __user *, t, int, flags) +COMPAT_SYSCALL_DEFINE4(utimensat, unsigned int, dfd, const char __user *, filename, struct old_timespec32 __user *, t, int, flags) { struct timespec64 tv[2]; if (t) { - if (compat_get_timespec64(&tv[0], &t[0]) || - compat_get_timespec64(&tv[1], &t[1])) + if (get_old_timespec32(&tv[0], &t[0]) || + get_old_timespec32(&tv[1], &t[1])) return -EFAULT; if (tv[0].tv_nsec == UTIME_OMIT && tv[1].tv_nsec == UTIME_OMIT) @@ -261,7 +261,7 @@ COMPAT_SYSCALL_DEFINE4(utimensat, unsigned int, dfd, const char __user *, filena } static long do_compat_futimesat(unsigned int dfd, const char __user *filename, - struct compat_timeval __user *t) + struct old_timeval32 __user *t) { struct timespec64 tv[2]; @@ -282,12 +282,12 @@ static long do_compat_futimesat(unsigned int dfd, const char __user *filename, COMPAT_SYSCALL_DEFINE3(futimesat, unsigned int, dfd, const char __user *, filename, - struct compat_timeval __user *, t) + struct old_timeval32 __user *, t) { return do_compat_futimesat(dfd, filename, t); } -COMPAT_SYSCALL_DEFINE2(utimes, const char __user *, filename, struct compat_timeval __user *, t) +COMPAT_SYSCALL_DEFINE2(utimes, const char __user *, filename, struct old_timeval32 __user *, t) { return do_compat_futimesat(AT_FDCWD, filename, t); } diff --git a/include/linux/compat.h b/include/linux/compat.h index 1a3c4f37e908..0e058792ecf6 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -7,7 +7,7 @@ */ #include -#include +#include #include #include /* for HZ */ @@ -116,13 +116,13 @@ struct compat_sel_arg_struct; struct rusage; struct compat_utimbuf { - compat_time_t actime; - compat_time_t modtime; + old_time32_t actime; + old_time32_t modtime; }; struct compat_itimerval { - struct compat_timeval it_interval; - struct compat_timeval it_value; + struct old_timeval32 it_interval; + struct old_timeval32 it_value; }; struct itimerval; @@ -146,7 +146,7 @@ struct compat_timex { compat_long_t constant; compat_long_t precision; compat_long_t tolerance; - struct compat_timeval time; + struct old_timeval32 time; compat_long_t tick; compat_long_t ppsfreq; compat_long_t jitter; @@ -307,8 +307,8 @@ struct compat_rlimit { }; struct compat_rusage { - struct compat_timeval ru_utime; - struct compat_timeval ru_stime; + struct old_timeval32 ru_utime; + struct old_timeval32 ru_stime; compat_long_t ru_maxrss; compat_long_t ru_ixrss; compat_long_t ru_idrss; @@ -457,8 +457,8 @@ int copy_siginfo_to_user32(struct compat_siginfo __user *to, const siginfo_t *fr int get_compat_sigevent(struct sigevent *event, const struct compat_sigevent __user *u_event); -static inline int compat_timeval_compare(struct compat_timeval *lhs, - struct compat_timeval *rhs) +static inline int old_timeval32_compare(struct old_timeval32 *lhs, + struct old_timeval32 *rhs) { if (lhs->tv_sec < rhs->tv_sec) return -1; @@ -467,8 +467,8 @@ static inline int compat_timeval_compare(struct compat_timeval *lhs, return lhs->tv_usec - rhs->tv_usec; } -static inline int compat_timespec_compare(struct compat_timespec *lhs, - struct compat_timespec *rhs) +static inline int old_timespec32_compare(struct old_timespec32 *lhs, + struct old_timespec32 *rhs) { if (lhs->tv_sec < rhs->tv_sec) return -1; @@ -552,12 +552,12 @@ asmlinkage long compat_sys_io_getevents(compat_aio_context_t ctx_id, compat_long_t min_nr, compat_long_t nr, struct io_event __user *events, - struct compat_timespec __user *timeout); + struct old_timespec32 __user *timeout); asmlinkage long compat_sys_io_pgetevents(compat_aio_context_t ctx_id, compat_long_t min_nr, compat_long_t nr, struct io_event __user *events, - struct compat_timespec __user *timeout, + struct old_timespec32 __user *timeout, const struct __compat_aio_sigset __user *usig); /* fs/cookies.c */ @@ -642,11 +642,11 @@ asmlinkage long compat_sys_sendfile64(int out_fd, int in_fd, asmlinkage long compat_sys_pselect6(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, - struct compat_timespec __user *tsp, + struct old_timespec32 __user *tsp, void __user *sig); asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds, unsigned int nfds, - struct compat_timespec __user *tsp, + struct old_timespec32 __user *tsp, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize); @@ -671,15 +671,15 @@ asmlinkage long compat_sys_newfstat(unsigned int fd, /* fs/timerfd.c */ asmlinkage long compat_sys_timerfd_gettime(int ufd, - struct compat_itimerspec __user *otmr); + struct old_itimerspec32 __user *otmr); asmlinkage long compat_sys_timerfd_settime(int ufd, int flags, - const struct compat_itimerspec __user *utmr, - struct compat_itimerspec __user *otmr); + const struct old_itimerspec32 __user *utmr, + struct old_itimerspec32 __user *otmr); /* fs/utimes.c */ asmlinkage long compat_sys_utimensat(unsigned int dfd, const char __user *filename, - struct compat_timespec __user *t, + struct old_timespec32 __user *t, int flags); /* kernel/exit.c */ @@ -691,7 +691,7 @@ asmlinkage long compat_sys_waitid(int, compat_pid_t, /* kernel/futex.c */ asmlinkage long compat_sys_futex(u32 __user *uaddr, int op, u32 val, - struct compat_timespec __user *utime, u32 __user *uaddr2, + struct old_timespec32 __user *utime, u32 __user *uaddr2, u32 val3); asmlinkage long compat_sys_set_robust_list(struct compat_robust_list_head __user *head, @@ -701,8 +701,8 @@ compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr, compat_size_t __user *len_ptr); /* kernel/hrtimer.c */ -asmlinkage long compat_sys_nanosleep(struct compat_timespec __user *rqtp, - struct compat_timespec __user *rmtp); +asmlinkage long compat_sys_nanosleep(struct old_timespec32 __user *rqtp, + struct old_timespec32 __user *rmtp); /* kernel/itimer.c */ asmlinkage long compat_sys_getitimer(int which, @@ -722,19 +722,19 @@ asmlinkage long compat_sys_timer_create(clockid_t which_clock, struct compat_sigevent __user *timer_event_spec, timer_t __user *created_timer_id); asmlinkage long compat_sys_timer_gettime(timer_t timer_id, - struct compat_itimerspec __user *setting); + struct old_itimerspec32 __user *setting); asmlinkage long compat_sys_timer_settime(timer_t timer_id, int flags, - struct compat_itimerspec __user *new, - struct compat_itimerspec __user *old); + struct old_itimerspec32 __user *new, + struct old_itimerspec32 __user *old); asmlinkage long compat_sys_clock_settime(clockid_t which_clock, - struct compat_timespec __user *tp); + struct old_timespec32 __user *tp); asmlinkage long compat_sys_clock_gettime(clockid_t which_clock, - struct compat_timespec __user *tp); + struct old_timespec32 __user *tp); asmlinkage long compat_sys_clock_getres(clockid_t which_clock, - struct compat_timespec __user *tp); + struct old_timespec32 __user *tp); asmlinkage long compat_sys_clock_nanosleep(clockid_t which_clock, int flags, - struct compat_timespec __user *rqtp, - struct compat_timespec __user *rmtp); + struct old_timespec32 __user *rqtp, + struct old_timespec32 __user *rmtp); /* kernel/ptrace.c */ asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid, @@ -748,7 +748,7 @@ asmlinkage long compat_sys_sched_getaffinity(compat_pid_t pid, unsigned int len, compat_ulong_t __user *user_mask_ptr); asmlinkage long compat_sys_sched_rr_get_interval(compat_pid_t pid, - struct compat_timespec __user *interval); + struct old_timespec32 __user *interval); /* kernel/signal.c */ asmlinkage long compat_sys_sigaltstack(const compat_stack_t __user *uss_ptr, @@ -768,7 +768,7 @@ asmlinkage long compat_sys_rt_sigpending(compat_sigset_t __user *uset, compat_size_t sigsetsize); asmlinkage long compat_sys_rt_sigtimedwait(compat_sigset_t __user *uthese, struct compat_siginfo __user *uinfo, - struct compat_timespec __user *uts, compat_size_t sigsetsize); + struct old_timespec32 __user *uts, compat_size_t sigsetsize); asmlinkage long compat_sys_rt_sigqueueinfo(compat_pid_t pid, int sig, struct compat_siginfo __user *uinfo); /* No generic prototype for rt_sigreturn */ @@ -782,9 +782,9 @@ asmlinkage long compat_sys_setrlimit(unsigned int resource, asmlinkage long compat_sys_getrusage(int who, struct compat_rusage __user *ru); /* kernel/time.c */ -asmlinkage long compat_sys_gettimeofday(struct compat_timeval __user *tv, +asmlinkage long compat_sys_gettimeofday(struct old_timeval32 __user *tv, struct timezone __user *tz); -asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv, +asmlinkage long compat_sys_settimeofday(struct old_timeval32 __user *tv, struct timezone __user *tz); asmlinkage long compat_sys_adjtimex(struct compat_timex __user *utp); @@ -798,11 +798,11 @@ asmlinkage long compat_sys_mq_open(const char __user *u_name, asmlinkage long compat_sys_mq_timedsend(mqd_t mqdes, const char __user *u_msg_ptr, compat_size_t msg_len, unsigned int msg_prio, - const struct compat_timespec __user *u_abs_timeout); + const struct old_timespec32 __user *u_abs_timeout); asmlinkage ssize_t compat_sys_mq_timedreceive(mqd_t mqdes, char __user *u_msg_ptr, compat_size_t msg_len, unsigned int __user *u_msg_prio, - const struct compat_timespec __user *u_abs_timeout); + const struct old_timespec32 __user *u_abs_timeout); asmlinkage long compat_sys_mq_notify(mqd_t mqdes, const struct compat_sigevent __user *u_notification); asmlinkage long compat_sys_mq_getsetattr(mqd_t mqdes, @@ -819,7 +819,7 @@ asmlinkage long compat_sys_msgsnd(int msqid, compat_uptr_t msgp, /* ipc/sem.c */ asmlinkage long compat_sys_semctl(int semid, int semnum, int cmd, int arg); asmlinkage long compat_sys_semtimedop(int semid, struct sembuf __user *tsems, - unsigned nsems, const struct compat_timespec __user *timeout); + unsigned nsems, const struct old_timespec32 __user *timeout); /* ipc/shm.c */ asmlinkage long compat_sys_shmctl(int first, int second, void __user *uptr); @@ -876,7 +876,7 @@ asmlinkage long compat_sys_rt_tgsigqueueinfo(compat_pid_t tgid, struct compat_siginfo __user *uinfo); asmlinkage long compat_sys_recvmmsg(int fd, struct compat_mmsghdr __user *mmsg, unsigned vlen, unsigned int flags, - struct compat_timespec __user *timeout); + struct old_timespec32 __user *timeout); asmlinkage long compat_sys_wait4(compat_pid_t pid, compat_uint_t __user *stat_addr, int options, struct compat_rusage __user *ru); @@ -928,7 +928,7 @@ asmlinkage long compat_sys_pwritev64v2(unsigned long fd, asmlinkage long compat_sys_open(const char __user *filename, int flags, umode_t mode); asmlinkage long compat_sys_utimes(const char __user *filename, - struct compat_timeval __user *t); + struct old_timeval32 __user *t); /* __ARCH_WANT_SYSCALL_NO_FLAGS */ asmlinkage long compat_sys_signalfd(int ufd, @@ -942,15 +942,15 @@ asmlinkage long compat_sys_newlstat(const char __user *filename, struct compat_stat __user *statbuf); /* __ARCH_WANT_SYSCALL_DEPRECATED */ -asmlinkage long compat_sys_time(compat_time_t __user *tloc); +asmlinkage long compat_sys_time(old_time32_t __user *tloc); asmlinkage long compat_sys_utime(const char __user *filename, struct compat_utimbuf __user *t); asmlinkage long compat_sys_futimesat(unsigned int dfd, const char __user *filename, - struct compat_timeval __user *t); + struct old_timeval32 __user *t); asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, - struct compat_timeval __user *tvp); + struct old_timeval32 __user *tvp); asmlinkage long compat_sys_ustat(unsigned dev, struct compat_ustat __user *u32); asmlinkage long compat_sys_recv(int fd, void __user *buf, compat_size_t len, unsigned flags); @@ -983,7 +983,7 @@ asmlinkage long compat_sys_sigaction(int sig, #endif /* obsolete: kernel/time/time.c */ -asmlinkage long compat_sys_stime(compat_time_t __user *tptr); +asmlinkage long compat_sys_stime(old_time32_t __user *tptr); /* obsolete: net/socket.c */ asmlinkage long compat_sys_socketcall(int call, u32 __user *args); @@ -1002,15 +1002,15 @@ static inline bool in_compat_syscall(void) { return is_compat_task(); } #endif /** - * ns_to_compat_timeval - Compat version of ns_to_timeval + * ns_to_old_timeval32 - Compat version of ns_to_timeval * @nsec: the nanoseconds value to be converted * - * Returns the compat_timeval representation of the nsec parameter. + * Returns the old_timeval32 representation of the nsec parameter. */ -static inline struct compat_timeval ns_to_compat_timeval(s64 nsec) +static inline struct old_timeval32 ns_to_old_timeval32(s64 nsec) { struct timeval tv; - struct compat_timeval ctv; + struct old_timeval32 ctv; tv = ns_to_timeval(nsec); ctv.tv_sec = tv.tv_sec; diff --git a/include/linux/compat_time.h b/include/linux/compat_time.h deleted file mode 100644 index e70bfd1d2c3f..000000000000 --- a/include/linux/compat_time.h +++ /dev/null @@ -1,32 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_COMPAT_TIME_H -#define _LINUX_COMPAT_TIME_H - -#include -#include - -typedef s32 compat_time_t; - -struct compat_timespec { - compat_time_t tv_sec; - s32 tv_nsec; -}; - -struct compat_timeval { - compat_time_t tv_sec; - s32 tv_usec; -}; - -struct compat_itimerspec { - struct compat_timespec it_interval; - struct compat_timespec it_value; -}; - -extern int compat_get_timespec64(struct timespec64 *, const void __user *); -extern int compat_put_timespec64(const struct timespec64 *, void __user *); -extern int get_compat_itimerspec64(struct itimerspec64 *its, - const struct compat_itimerspec __user *uits); -extern int put_compat_itimerspec64(const struct itimerspec64 *its, - struct compat_itimerspec __user *uits); - -#endif /* _LINUX_COMPAT_TIME_H */ diff --git a/include/linux/elfcore-compat.h b/include/linux/elfcore-compat.h index b5f2efdd05e0..7a37f4ce9fd2 100644 --- a/include/linux/elfcore-compat.h +++ b/include/linux/elfcore-compat.h @@ -27,10 +27,10 @@ struct compat_elf_prstatus compat_pid_t pr_ppid; compat_pid_t pr_pgrp; compat_pid_t pr_sid; - struct compat_timeval pr_utime; - struct compat_timeval pr_stime; - struct compat_timeval pr_cutime; - struct compat_timeval pr_cstime; + struct old_timeval32 pr_utime; + struct old_timeval32 pr_stime; + struct old_timeval32 pr_cutime; + struct old_timeval32 pr_cstime; compat_elf_gregset_t pr_reg; #ifdef CONFIG_BINFMT_ELF_FDPIC compat_ulong_t pr_exec_fdpic_loadmap; diff --git a/include/linux/restart_block.h b/include/linux/restart_block.h index 5d83d0c1d06c..bba2920e9c05 100644 --- a/include/linux/restart_block.h +++ b/include/linux/restart_block.h @@ -10,7 +10,7 @@ #include struct timespec; -struct compat_timespec; +struct old_timespec32; struct pollfd; enum timespec_type { @@ -40,7 +40,7 @@ struct restart_block { enum timespec_type type; union { struct __kernel_timespec __user *rmtp; - struct compat_timespec __user *compat_rmtp; + struct old_timespec32 __user *compat_rmtp; }; u64 expires; } nanosleep; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 2ff814c92f7f..b3e27e5ee322 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -60,7 +60,7 @@ struct tms; struct utimbuf; struct mq_attr; struct compat_stat; -struct compat_timeval; +struct old_timeval32; struct robust_list_head; struct getcpu_cache; struct old_linux_dirent; diff --git a/include/linux/time32.h b/include/linux/time32.h index 92c0ca092d93..0e0d7304d1a8 100644 --- a/include/linux/time32.h +++ b/include/linux/time32.h @@ -13,6 +13,31 @@ #define TIME_T_MAX (time_t)((1UL << ((sizeof(time_t) << 3) - 1)) - 1) +typedef s32 old_time32_t; + +struct old_timespec32 { + old_time32_t tv_sec; + s32 tv_nsec; +}; + +struct old_timeval32 { + old_time32_t tv_sec; + s32 tv_usec; +}; + +struct old_itimerspec32 { + struct old_timespec32 it_interval; + struct old_timespec32 it_value; +}; + +extern int get_old_timespec32(struct timespec64 *, const void __user *); +extern int put_old_timespec32(const struct timespec64 *, void __user *); +extern int get_old_itimerspec32(struct itimerspec64 *its, + const struct old_itimerspec32 __user *uits); +extern int put_old_itimerspec32(const struct itimerspec64 *its, + struct old_itimerspec32 __user *uits); + + #if __BITS_PER_LONG == 64 /* timespec64 is defined as timespec here */ @@ -183,18 +208,17 @@ extern struct timeval ns_to_timeval(const s64 nsec); extern struct __kernel_old_timeval ns_to_kernel_old_timeval(s64 nsec); /* - * New aliases for compat time functions. These will be used to replace - * the compat code so it can be shared between 32-bit and 64-bit builds - * both of which provide compatibility with old 32-bit tasks. + * Old names for the 32-bit time_t interfaces, these will be removed + * when everything uses the new names. */ -#define old_time32_t compat_time_t -#define old_timeval32 compat_timeval -#define old_timespec32 compat_timespec -#define old_itimerspec32 compat_itimerspec -#define ns_to_old_timeval32 ns_to_compat_timeval -#define get_old_itimerspec32 get_compat_itimerspec64 -#define put_old_itimerspec32 put_compat_itimerspec64 -#define get_old_timespec32 compat_get_timespec64 -#define put_old_timespec32 compat_put_timespec64 +#define compat_time_t old_time32_t +#define compat_timeval old_timeval32 +#define compat_timespec old_timespec32 +#define compat_itimerspec old_itimerspec32 +#define ns_to_compat_timeval ns_to_old_timeval32 +#define get_compat_itimerspec64 get_old_itimerspec32 +#define put_compat_itimerspec64 put_old_itimerspec32 +#define compat_get_timespec64 get_old_timespec32 +#define compat_put_timespec64 put_old_timespec32 #endif diff --git a/ipc/mqueue.c b/ipc/mqueue.c index c0d58f390c3b..db7833370351 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -1461,10 +1461,10 @@ COMPAT_SYSCALL_DEFINE3(mq_getsetattr, mqd_t, mqdes, #endif #ifdef CONFIG_COMPAT_32BIT_TIME -static int compat_prepare_timeout(const struct compat_timespec __user *p, +static int compat_prepare_timeout(const struct old_timespec32 __user *p, struct timespec64 *ts) { - if (compat_get_timespec64(ts, p)) + if (get_old_timespec32(ts, p)) return -EFAULT; if (!timespec64_valid(ts)) return -EINVAL; @@ -1474,7 +1474,7 @@ static int compat_prepare_timeout(const struct compat_timespec __user *p, COMPAT_SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr, compat_size_t, msg_len, unsigned int, msg_prio, - const struct compat_timespec __user *, u_abs_timeout) + const struct old_timespec32 __user *, u_abs_timeout) { struct timespec64 ts, *p = NULL; if (u_abs_timeout) { @@ -1489,7 +1489,7 @@ COMPAT_SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, COMPAT_SYSCALL_DEFINE5(mq_timedreceive, mqd_t, mqdes, char __user *, u_msg_ptr, compat_size_t, msg_len, unsigned int __user *, u_msg_prio, - const struct compat_timespec __user *, u_abs_timeout) + const struct old_timespec32 __user *, u_abs_timeout) { struct timespec64 ts, *p = NULL; if (u_abs_timeout) { diff --git a/ipc/msg.c b/ipc/msg.c index 883642cf2b27..0833c6405915 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -622,9 +622,9 @@ struct compat_msqid_ds { struct compat_ipc_perm msg_perm; compat_uptr_t msg_first; compat_uptr_t msg_last; - compat_time_t msg_stime; - compat_time_t msg_rtime; - compat_time_t msg_ctime; + old_time32_t msg_stime; + old_time32_t msg_rtime; + old_time32_t msg_ctime; compat_ulong_t msg_lcbytes; compat_ulong_t msg_lqbytes; unsigned short msg_cbytes; diff --git a/ipc/sem.c b/ipc/sem.c index 26f8e37fcdcb..745dc6187e84 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -1698,8 +1698,8 @@ SYSCALL_DEFINE4(semctl, int, semid, int, semnum, int, cmd, unsigned long, arg) struct compat_semid_ds { struct compat_ipc_perm sem_perm; - compat_time_t sem_otime; - compat_time_t sem_ctime; + old_time32_t sem_otime; + old_time32_t sem_ctime; compat_uptr_t sem_base; compat_uptr_t sem_pending; compat_uptr_t sem_pending_last; @@ -2214,11 +2214,11 @@ SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops, #ifdef CONFIG_COMPAT_32BIT_TIME long compat_ksys_semtimedop(int semid, struct sembuf __user *tsems, unsigned int nsops, - const struct compat_timespec __user *timeout) + const struct old_timespec32 __user *timeout) { if (timeout) { struct timespec64 ts; - if (compat_get_timespec64(&ts, timeout)) + if (get_old_timespec32(&ts, timeout)) return -EFAULT; return do_semtimedop(semid, tsems, nsops, &ts); } @@ -2227,7 +2227,7 @@ long compat_ksys_semtimedop(int semid, struct sembuf __user *tsems, COMPAT_SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsems, unsigned int, nsops, - const struct compat_timespec __user *, timeout) + const struct old_timespec32 __user *, timeout) { return compat_ksys_semtimedop(semid, tsems, nsops, timeout); } diff --git a/ipc/shm.c b/ipc/shm.c index b0eb3757ab89..2657692199eb 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -1201,9 +1201,9 @@ SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf) struct compat_shmid_ds { struct compat_ipc_perm shm_perm; int shm_segsz; - compat_time_t shm_atime; - compat_time_t shm_dtime; - compat_time_t shm_ctime; + old_time32_t shm_atime; + old_time32_t shm_dtime; + old_time32_t shm_ctime; compat_ipc_pid_t shm_cpid; compat_ipc_pid_t shm_lpid; unsigned short shm_nattch; diff --git a/ipc/syscall.c b/ipc/syscall.c index 65d405f1ba0c..1ac06e3983c0 100644 --- a/ipc/syscall.c +++ b/ipc/syscall.c @@ -35,7 +35,7 @@ SYSCALL_DEFINE6(ipc, unsigned int, call, int, first, unsigned long, second, (const struct __kernel_timespec __user *)fifth); else if (IS_ENABLED(CONFIG_COMPAT_32BIT_TIME)) return compat_ksys_semtimedop(first, ptr, second, - (const struct compat_timespec __user *)fifth); + (const struct old_timespec32 __user *)fifth); else return -ENOSYS; diff --git a/ipc/util.h b/ipc/util.h index 0a159f69b3bb..1ee81bce25e9 100644 --- a/ipc/util.h +++ b/ipc/util.h @@ -266,7 +266,7 @@ long ksys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf); /* for CONFIG_ARCH_WANT_OLD_COMPAT_IPC */ long compat_ksys_semtimedop(int semid, struct sembuf __user *tsems, unsigned int nsops, - const struct compat_timespec __user *timeout); + const struct old_timespec32 __user *timeout); #ifdef CONFIG_COMPAT long compat_ksys_semctl(int semid, int semnum, int cmd, int arg); long compat_ksys_msgctl(int msqid, int cmd, void __user *uptr); diff --git a/kernel/compat.c b/kernel/compat.c index 8e40efc2928a..089d00d0da9c 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -93,28 +93,28 @@ int compat_put_timex(struct compat_timex __user *utp, const struct timex *txc) return 0; } -static int __compat_get_timeval(struct timeval *tv, const struct compat_timeval __user *ctv) +static int __compat_get_timeval(struct timeval *tv, const struct old_timeval32 __user *ctv) { return (!access_ok(VERIFY_READ, ctv, sizeof(*ctv)) || __get_user(tv->tv_sec, &ctv->tv_sec) || __get_user(tv->tv_usec, &ctv->tv_usec)) ? -EFAULT : 0; } -static int __compat_put_timeval(const struct timeval *tv, struct compat_timeval __user *ctv) +static int __compat_put_timeval(const struct timeval *tv, struct old_timeval32 __user *ctv) { return (!access_ok(VERIFY_WRITE, ctv, sizeof(*ctv)) || __put_user(tv->tv_sec, &ctv->tv_sec) || __put_user(tv->tv_usec, &ctv->tv_usec)) ? -EFAULT : 0; } -static int __compat_get_timespec(struct timespec *ts, const struct compat_timespec __user *cts) +static int __compat_get_timespec(struct timespec *ts, const struct old_timespec32 __user *cts) { return (!access_ok(VERIFY_READ, cts, sizeof(*cts)) || __get_user(ts->tv_sec, &cts->tv_sec) || __get_user(ts->tv_nsec, &cts->tv_nsec)) ? -EFAULT : 0; } -static int __compat_put_timespec(const struct timespec *ts, struct compat_timespec __user *cts) +static int __compat_put_timespec(const struct timespec *ts, struct old_timespec32 __user *cts) { return (!access_ok(VERIFY_WRITE, cts, sizeof(*cts)) || __put_user(ts->tv_sec, &cts->tv_sec) || diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c index 83f830acbb5f..410a77a8f6e2 100644 --- a/kernel/futex_compat.c +++ b/kernel/futex_compat.c @@ -173,7 +173,7 @@ err_unlock: } COMPAT_SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, - struct compat_timespec __user *, utime, u32 __user *, uaddr2, + struct old_timespec32 __user *, utime, u32 __user *, uaddr2, u32, val3) { struct timespec ts; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 625bc9897f62..8287b75ed961 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5257,13 +5257,13 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(sched_rr_get_interval, compat_pid_t, pid, - struct compat_timespec __user *, interval) + struct old_timespec32 __user *, interval) { struct timespec64 t; int retval = sched_rr_get_interval(pid, &t); if (retval == 0) - retval = compat_put_timespec64(&t, interval); + retval = put_old_timespec32(&t, interval); return retval; } #endif diff --git a/kernel/signal.c b/kernel/signal.c index 5843c541fda9..a4db724e14c1 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -3173,7 +3173,7 @@ SYSCALL_DEFINE4(rt_sigtimedwait, const sigset_t __user *, uthese, #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait, compat_sigset_t __user *, uthese, struct compat_siginfo __user *, uinfo, - struct compat_timespec __user *, uts, compat_size_t, sigsetsize) + struct old_timespec32 __user *, uts, compat_size_t, sigsetsize) { sigset_t s; struct timespec t; diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index e1a549c9e399..9cdd74bd2d27 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1660,7 +1660,7 @@ int nanosleep_copyout(struct restart_block *restart, struct timespec64 *ts) switch(restart->nanosleep.type) { #ifdef CONFIG_COMPAT_32BIT_TIME case TT_COMPAT: - if (compat_put_timespec64(ts, restart->nanosleep.compat_rmtp)) + if (put_old_timespec32(ts, restart->nanosleep.compat_rmtp)) return -EFAULT; break; #endif @@ -1780,12 +1780,12 @@ SYSCALL_DEFINE2(nanosleep, struct __kernel_timespec __user *, rqtp, #ifdef CONFIG_COMPAT_32BIT_TIME -COMPAT_SYSCALL_DEFINE2(nanosleep, struct compat_timespec __user *, rqtp, - struct compat_timespec __user *, rmtp) +COMPAT_SYSCALL_DEFINE2(nanosleep, struct old_timespec32 __user *, rqtp, + struct old_timespec32 __user *, rmtp) { struct timespec64 tu; - if (compat_get_timespec64(&tu, rqtp)) + if (get_old_timespec32(&tu, rqtp)) return -EFAULT; if (!timespec64_valid(&tu)) diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c index 2c6847d5d69b..989ccf028bde 100644 --- a/kernel/time/posix-stubs.c +++ b/kernel/time/posix-stubs.c @@ -162,20 +162,20 @@ COMPAT_SYS_NI(setitimer); #ifdef CONFIG_COMPAT_32BIT_TIME COMPAT_SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock, - struct compat_timespec __user *, tp) + struct old_timespec32 __user *, tp) { struct timespec64 new_tp; if (which_clock != CLOCK_REALTIME) return -EINVAL; - if (compat_get_timespec64(&new_tp, tp)) + if (get_old_timespec32(&new_tp, tp)) return -EFAULT; return do_sys_settimeofday64(&new_tp, NULL); } COMPAT_SYSCALL_DEFINE2(clock_gettime, clockid_t, which_clock, - struct compat_timespec __user *, tp) + struct old_timespec32 __user *, tp) { int ret; struct timespec64 kernel_tp; @@ -184,13 +184,13 @@ COMPAT_SYSCALL_DEFINE2(clock_gettime, clockid_t, which_clock, if (ret) return ret; - if (compat_put_timespec64(&kernel_tp, tp)) + if (put_old_timespec32(&kernel_tp, tp)) return -EFAULT; return 0; } COMPAT_SYSCALL_DEFINE2(clock_getres, clockid_t, which_clock, - struct compat_timespec __user *, tp) + struct old_timespec32 __user *, tp) { struct timespec64 rtn_tp = { .tv_sec = 0, @@ -201,7 +201,7 @@ COMPAT_SYSCALL_DEFINE2(clock_getres, clockid_t, which_clock, case CLOCK_REALTIME: case CLOCK_MONOTONIC: case CLOCK_BOOTTIME: - if (compat_put_timespec64(&rtn_tp, tp)) + if (put_old_timespec32(&rtn_tp, tp)) return -EFAULT; return 0; default: @@ -210,8 +210,8 @@ COMPAT_SYSCALL_DEFINE2(clock_getres, clockid_t, which_clock, } COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags, - struct compat_timespec __user *, rqtp, - struct compat_timespec __user *, rmtp) + struct old_timespec32 __user *, rqtp, + struct old_timespec32 __user *, rmtp) { struct timespec64 t; @@ -224,7 +224,7 @@ COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags, return -EINVAL; } - if (compat_get_timespec64(&t, rqtp)) + if (get_old_timespec32(&t, rqtp)) return -EFAULT; if (!timespec64_valid(&t)) return -EINVAL; diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 4b9127e95430..3e71921668ba 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -755,13 +755,13 @@ SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id, #ifdef CONFIG_COMPAT_32BIT_TIME COMPAT_SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id, - struct compat_itimerspec __user *, setting) + struct old_itimerspec32 __user *, setting) { struct itimerspec64 cur_setting; int ret = do_timer_gettime(timer_id, &cur_setting); if (!ret) { - if (put_compat_itimerspec64(&cur_setting, setting)) + if (put_old_itimerspec32(&cur_setting, setting)) ret = -EFAULT; } return ret; @@ -928,8 +928,8 @@ SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags, #ifdef CONFIG_COMPAT_32BIT_TIME COMPAT_SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags, - struct compat_itimerspec __user *, new, - struct compat_itimerspec __user *, old) + struct old_itimerspec32 __user *, new, + struct old_itimerspec32 __user *, old) { struct itimerspec64 new_spec, old_spec; struct itimerspec64 *rtn = old ? &old_spec : NULL; @@ -937,12 +937,12 @@ COMPAT_SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags, if (!new) return -EINVAL; - if (get_compat_itimerspec64(&new_spec, new)) + if (get_old_itimerspec32(&new_spec, new)) return -EFAULT; error = do_timer_settime(timer_id, flags, &new_spec, rtn); if (!error && old) { - if (put_compat_itimerspec64(&old_spec, old)) + if (put_old_itimerspec32(&old_spec, old)) error = -EFAULT; } return error; @@ -1115,7 +1115,7 @@ SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock, #ifdef CONFIG_COMPAT_32BIT_TIME COMPAT_SYSCALL_DEFINE2(clock_settime, clockid_t, which_clock, - struct compat_timespec __user *, tp) + struct old_timespec32 __user *, tp) { const struct k_clock *kc = clockid_to_kclock(which_clock); struct timespec64 ts; @@ -1123,14 +1123,14 @@ COMPAT_SYSCALL_DEFINE2(clock_settime, clockid_t, which_clock, if (!kc || !kc->clock_set) return -EINVAL; - if (compat_get_timespec64(&ts, tp)) + if (get_old_timespec32(&ts, tp)) return -EFAULT; return kc->clock_set(which_clock, &ts); } COMPAT_SYSCALL_DEFINE2(clock_gettime, clockid_t, which_clock, - struct compat_timespec __user *, tp) + struct old_timespec32 __user *, tp) { const struct k_clock *kc = clockid_to_kclock(which_clock); struct timespec64 ts; @@ -1141,7 +1141,7 @@ COMPAT_SYSCALL_DEFINE2(clock_gettime, clockid_t, which_clock, err = kc->clock_get(which_clock, &ts); - if (!err && compat_put_timespec64(&ts, tp)) + if (!err && put_old_timespec32(&ts, tp)) err = -EFAULT; return err; @@ -1180,7 +1180,7 @@ COMPAT_SYSCALL_DEFINE2(clock_adjtime, clockid_t, which_clock, #ifdef CONFIG_COMPAT_32BIT_TIME COMPAT_SYSCALL_DEFINE2(clock_getres, clockid_t, which_clock, - struct compat_timespec __user *, tp) + struct old_timespec32 __user *, tp) { const struct k_clock *kc = clockid_to_kclock(which_clock); struct timespec64 ts; @@ -1190,7 +1190,7 @@ COMPAT_SYSCALL_DEFINE2(clock_getres, clockid_t, which_clock, return -EINVAL; err = kc->clock_getres(which_clock, &ts); - if (!err && tp && compat_put_timespec64(&ts, tp)) + if (!err && tp && put_old_timespec32(&ts, tp)) return -EFAULT; return err; @@ -1237,8 +1237,8 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags, #ifdef CONFIG_COMPAT_32BIT_TIME COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags, - struct compat_timespec __user *, rqtp, - struct compat_timespec __user *, rmtp) + struct old_timespec32 __user *, rqtp, + struct old_timespec32 __user *, rmtp) { const struct k_clock *kc = clockid_to_kclock(which_clock); struct timespec64 t; @@ -1248,7 +1248,7 @@ COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags, if (!kc->nsleep) return -EOPNOTSUPP; - if (compat_get_timespec64(&t, rqtp)) + if (get_old_timespec32(&t, rqtp)) return -EFAULT; if (!timespec64_valid(&t)) diff --git a/kernel/time/time.c b/kernel/time/time.c index de332250d6fa..f1983f468fe3 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -104,12 +104,12 @@ SYSCALL_DEFINE1(stime, time_t __user *, tptr) #ifdef CONFIG_COMPAT #ifdef __ARCH_WANT_COMPAT_SYS_TIME -/* compat_time_t is a 32 bit "long" and needs to get converted. */ -COMPAT_SYSCALL_DEFINE1(time, compat_time_t __user *, tloc) +/* old_time32_t is a 32 bit "long" and needs to get converted. */ +COMPAT_SYSCALL_DEFINE1(time, old_time32_t __user *, tloc) { - compat_time_t i; + old_time32_t i; - i = (compat_time_t)ktime_get_real_seconds(); + i = (old_time32_t)ktime_get_real_seconds(); if (tloc) { if (put_user(i,tloc)) @@ -119,7 +119,7 @@ COMPAT_SYSCALL_DEFINE1(time, compat_time_t __user *, tloc) return i; } -COMPAT_SYSCALL_DEFINE1(stime, compat_time_t __user *, tptr) +COMPAT_SYSCALL_DEFINE1(stime, old_time32_t __user *, tptr) { struct timespec64 tv; int err; @@ -225,7 +225,7 @@ SYSCALL_DEFINE2(settimeofday, struct timeval __user *, tv, } #ifdef CONFIG_COMPAT -COMPAT_SYSCALL_DEFINE2(gettimeofday, struct compat_timeval __user *, tv, +COMPAT_SYSCALL_DEFINE2(gettimeofday, struct old_timeval32 __user *, tv, struct timezone __user *, tz) { if (tv) { @@ -244,7 +244,7 @@ COMPAT_SYSCALL_DEFINE2(gettimeofday, struct compat_timeval __user *, tv, return 0; } -COMPAT_SYSCALL_DEFINE2(settimeofday, struct compat_timeval __user *, tv, +COMPAT_SYSCALL_DEFINE2(settimeofday, struct old_timeval32 __user *, tv, struct timezone __user *, tz) { struct timespec64 new_ts; @@ -863,10 +863,10 @@ int put_timespec64(const struct timespec64 *ts, } EXPORT_SYMBOL_GPL(put_timespec64); -int __compat_get_timespec64(struct timespec64 *ts64, - const struct compat_timespec __user *cts) +int __get_old_timespec32(struct timespec64 *ts64, + const struct old_timespec32 __user *cts) { - struct compat_timespec ts; + struct old_timespec32 ts; int ret; ret = copy_from_user(&ts, cts, sizeof(ts)); @@ -879,33 +879,33 @@ int __compat_get_timespec64(struct timespec64 *ts64, return 0; } -int __compat_put_timespec64(const struct timespec64 *ts64, - struct compat_timespec __user *cts) +int __put_old_timespec32(const struct timespec64 *ts64, + struct old_timespec32 __user *cts) { - struct compat_timespec ts = { + struct old_timespec32 ts = { .tv_sec = ts64->tv_sec, .tv_nsec = ts64->tv_nsec }; return copy_to_user(cts, &ts, sizeof(ts)) ? -EFAULT : 0; } -int compat_get_timespec64(struct timespec64 *ts, const void __user *uts) +int get_old_timespec32(struct timespec64 *ts, const void __user *uts) { if (COMPAT_USE_64BIT_TIME) return copy_from_user(ts, uts, sizeof(*ts)) ? -EFAULT : 0; else - return __compat_get_timespec64(ts, uts); + return __get_old_timespec32(ts, uts); } -EXPORT_SYMBOL_GPL(compat_get_timespec64); +EXPORT_SYMBOL_GPL(get_old_timespec32); -int compat_put_timespec64(const struct timespec64 *ts, void __user *uts) +int put_old_timespec32(const struct timespec64 *ts, void __user *uts) { if (COMPAT_USE_64BIT_TIME) return copy_to_user(uts, ts, sizeof(*ts)) ? -EFAULT : 0; else - return __compat_put_timespec64(ts, uts); + return __put_old_timespec32(ts, uts); } -EXPORT_SYMBOL_GPL(compat_put_timespec64); +EXPORT_SYMBOL_GPL(put_old_timespec32); int get_itimerspec64(struct itimerspec64 *it, const struct __kernel_itimerspec __user *uit) @@ -937,23 +937,23 @@ int put_itimerspec64(const struct itimerspec64 *it, } EXPORT_SYMBOL_GPL(put_itimerspec64); -int get_compat_itimerspec64(struct itimerspec64 *its, - const struct compat_itimerspec __user *uits) +int get_old_itimerspec32(struct itimerspec64 *its, + const struct old_itimerspec32 __user *uits) { - if (__compat_get_timespec64(&its->it_interval, &uits->it_interval) || - __compat_get_timespec64(&its->it_value, &uits->it_value)) + if (__get_old_timespec32(&its->it_interval, &uits->it_interval) || + __get_old_timespec32(&its->it_value, &uits->it_value)) return -EFAULT; return 0; } -EXPORT_SYMBOL_GPL(get_compat_itimerspec64); +EXPORT_SYMBOL_GPL(get_old_itimerspec32); -int put_compat_itimerspec64(const struct itimerspec64 *its, - struct compat_itimerspec __user *uits) +int put_old_itimerspec32(const struct itimerspec64 *its, + struct old_itimerspec32 __user *uits) { - if (__compat_put_timespec64(&its->it_interval, &uits->it_interval) || - __compat_put_timespec64(&its->it_value, &uits->it_value)) + if (__put_old_timespec32(&its->it_interval, &uits->it_interval) || + __put_old_timespec32(&its->it_value, &uits->it_value)) return -EFAULT; return 0; } -EXPORT_SYMBOL_GPL(put_compat_itimerspec64); +EXPORT_SYMBOL_GPL(put_old_itimerspec32); diff --git a/net/compat.c b/net/compat.c index 3b2105f6549d..2ef160876bc1 100644 --- a/net/compat.c +++ b/net/compat.c @@ -812,7 +812,7 @@ COMPAT_SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, buf, compat_size_t, len static int __compat_sys_recvmmsg(int fd, struct compat_mmsghdr __user *mmsg, unsigned int vlen, unsigned int flags, - struct compat_timespec __user *timeout) + struct old_timespec32 __user *timeout) { int datagrams; struct timespec ktspec; @@ -834,7 +834,7 @@ static int __compat_sys_recvmmsg(int fd, struct compat_mmsghdr __user *mmsg, COMPAT_SYSCALL_DEFINE5(recvmmsg, int, fd, struct compat_mmsghdr __user *, mmsg, unsigned int, vlen, unsigned int, flags, - struct compat_timespec __user *, timeout) + struct old_timespec32 __user *, timeout) { return __compat_sys_recvmmsg(fd, mmsg, vlen, flags, timeout); } -- cgit v1.2.3 From fb3739759474d150a9927b920a80ea2afb4c2a51 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 18 Apr 2018 22:01:26 +0200 Subject: asm-generic: Move common compat types to asm-generic/compat.h While converting compat system call handlers to work on 32-bit architectures, I found a number of types used in those handlers that are identical between all architectures. Let's move all the identical ones into asm-generic/compat.h to avoid having to add even more identical definitions of those types. For unknown reasons, mips defines __compat_gid32_t, __compat_uid32_t and compat_caddr_t as signed, while all others have them unsigned. This seems to be a mistake, but I'm leaving it alone here. The other types all differ by size or alignment on at least on architecture. compat_aio_context_t is currently defined in linux/compat.h but also needed for compat_sys_io_getevents(), so let's move it into the same place. While we still have not decided whether the 32-bit time handling will always use the compat syscalls, or in which form, I think this is a useful cleanup that we can merge regardless. Reviewed-by: Christoph Hellwig Signed-off-by: Arnd Bergmann --- arch/arm64/include/asm/compat.h | 20 ++------------------ arch/mips/include/asm/compat.h | 22 ++-------------------- arch/parisc/include/asm/compat.h | 18 ++---------------- arch/powerpc/include/asm/compat.h | 18 ++---------------- arch/s390/include/asm/compat.h | 18 ++---------------- arch/sparc/include/asm/compat.h | 19 ++----------------- arch/x86/include/asm/compat.h | 19 ++----------------- include/asm-generic/compat.h | 24 +++++++++++++++++++++++- include/linux/compat.h | 2 -- 9 files changed, 37 insertions(+), 123 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h index 4a89007db14a..ee689d8a026d 100644 --- a/arch/arm64/include/asm/compat.h +++ b/arch/arm64/include/asm/compat.h @@ -25,6 +25,8 @@ #include #include +#include + #define COMPAT_USER_HZ 100 #ifdef __AARCH64EB__ #define COMPAT_UTS_MACHINE "armv8b\0\0" @@ -32,10 +34,6 @@ #define COMPAT_UTS_MACHINE "armv8l\0\0" #endif -typedef u32 compat_size_t; -typedef s32 compat_ssize_t; -typedef s32 compat_clock_t; -typedef s32 compat_pid_t; typedef u16 __compat_uid_t; typedef u16 __compat_gid_t; typedef u16 __compat_uid16_t; @@ -43,27 +41,13 @@ typedef u16 __compat_gid16_t; typedef u32 __compat_uid32_t; typedef u32 __compat_gid32_t; typedef u16 compat_mode_t; -typedef u32 compat_ino_t; typedef u32 compat_dev_t; -typedef s32 compat_off_t; -typedef s64 compat_loff_t; typedef s32 compat_nlink_t; typedef u16 compat_ipc_pid_t; -typedef s32 compat_daddr_t; typedef u32 compat_caddr_t; typedef __kernel_fsid_t compat_fsid_t; -typedef s32 compat_key_t; -typedef s32 compat_timer_t; - -typedef s16 compat_short_t; -typedef s32 compat_int_t; -typedef s32 compat_long_t; typedef s64 compat_s64; -typedef u16 compat_ushort_t; -typedef u32 compat_uint_t; -typedef u32 compat_ulong_t; typedef u64 compat_u64; -typedef u32 compat_uptr_t; struct compat_stat { #ifdef __AARCH64EB__ diff --git a/arch/mips/include/asm/compat.h b/arch/mips/include/asm/compat.h index 7dcbd855814e..c99166eadbde 100644 --- a/arch/mips/include/asm/compat.h +++ b/arch/mips/include/asm/compat.h @@ -9,43 +9,25 @@ #include #include +#include + #define COMPAT_USER_HZ 100 #define COMPAT_UTS_MACHINE "mips\0\0\0" -typedef u32 compat_size_t; -typedef s32 compat_ssize_t; -typedef s32 compat_clock_t; -typedef s32 compat_suseconds_t; - -typedef s32 compat_pid_t; typedef s32 __compat_uid_t; typedef s32 __compat_gid_t; typedef __compat_uid_t __compat_uid32_t; typedef __compat_gid_t __compat_gid32_t; typedef u32 compat_mode_t; -typedef u32 compat_ino_t; typedef u32 compat_dev_t; -typedef s32 compat_off_t; -typedef s64 compat_loff_t; typedef u32 compat_nlink_t; typedef s32 compat_ipc_pid_t; -typedef s32 compat_daddr_t; typedef s32 compat_caddr_t; typedef struct { s32 val[2]; } compat_fsid_t; -typedef s32 compat_timer_t; -typedef s32 compat_key_t; - -typedef s16 compat_short_t; -typedef s32 compat_int_t; -typedef s32 compat_long_t; typedef s64 compat_s64; -typedef u16 compat_ushort_t; -typedef u32 compat_uint_t; -typedef u32 compat_ulong_t; typedef u64 compat_u64; -typedef u32 compat_uptr_t; struct compat_stat { compat_dev_t st_dev; diff --git a/arch/parisc/include/asm/compat.h b/arch/parisc/include/asm/compat.h index 32dadaf2b534..e03e3c849f40 100644 --- a/arch/parisc/include/asm/compat.h +++ b/arch/parisc/include/asm/compat.h @@ -8,36 +8,22 @@ #include #include +#include + #define COMPAT_USER_HZ 100 #define COMPAT_UTS_MACHINE "parisc\0\0" -typedef u32 compat_size_t; -typedef s32 compat_ssize_t; -typedef s32 compat_clock_t; -typedef s32 compat_pid_t; typedef u32 __compat_uid_t; typedef u32 __compat_gid_t; typedef u32 __compat_uid32_t; typedef u32 __compat_gid32_t; typedef u16 compat_mode_t; -typedef u32 compat_ino_t; typedef u32 compat_dev_t; -typedef s32 compat_off_t; -typedef s64 compat_loff_t; typedef u16 compat_nlink_t; typedef u16 compat_ipc_pid_t; -typedef s32 compat_daddr_t; typedef u32 compat_caddr_t; -typedef s32 compat_key_t; -typedef s32 compat_timer_t; - -typedef s32 compat_int_t; -typedef s32 compat_long_t; typedef s64 compat_s64; -typedef u32 compat_uint_t; -typedef u32 compat_ulong_t; typedef u64 compat_u64; -typedef u32 compat_uptr_t; struct compat_stat { compat_dev_t st_dev; /* dev_t is 32 bits on parisc */ diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h index 93f79d1a03c3..74d0db511099 100644 --- a/arch/powerpc/include/asm/compat.h +++ b/arch/powerpc/include/asm/compat.h @@ -8,6 +8,8 @@ #include #include +#include + #define COMPAT_USER_HZ 100 #ifdef __BIG_ENDIAN__ #define COMPAT_UTS_MACHINE "ppc\0\0" @@ -15,34 +17,18 @@ #define COMPAT_UTS_MACHINE "ppcle\0\0" #endif -typedef u32 compat_size_t; -typedef s32 compat_ssize_t; -typedef s32 compat_clock_t; -typedef s32 compat_pid_t; typedef u32 __compat_uid_t; typedef u32 __compat_gid_t; typedef u32 __compat_uid32_t; typedef u32 __compat_gid32_t; typedef u32 compat_mode_t; -typedef u32 compat_ino_t; typedef u32 compat_dev_t; -typedef s32 compat_off_t; -typedef s64 compat_loff_t; typedef s16 compat_nlink_t; typedef u16 compat_ipc_pid_t; -typedef s32 compat_daddr_t; typedef u32 compat_caddr_t; typedef __kernel_fsid_t compat_fsid_t; -typedef s32 compat_key_t; -typedef s32 compat_timer_t; - -typedef s32 compat_int_t; -typedef s32 compat_long_t; typedef s64 compat_s64; -typedef u32 compat_uint_t; -typedef u32 compat_ulong_t; typedef u64 compat_u64; -typedef u32 compat_uptr_t; struct compat_stat { compat_dev_t st_dev; diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h index 97db2fba546a..63b46e30b2c3 100644 --- a/arch/s390/include/asm/compat.h +++ b/arch/s390/include/asm/compat.h @@ -9,6 +9,8 @@ #include #include +#include + #define __TYPE_IS_PTR(t) (!__builtin_types_compatible_p( \ typeof(0?(__force t)0:0ULL), u64)) @@ -51,34 +53,18 @@ #define COMPAT_USER_HZ 100 #define COMPAT_UTS_MACHINE "s390\0\0\0\0" -typedef u32 compat_size_t; -typedef s32 compat_ssize_t; -typedef s32 compat_clock_t; -typedef s32 compat_pid_t; typedef u16 __compat_uid_t; typedef u16 __compat_gid_t; typedef u32 __compat_uid32_t; typedef u32 __compat_gid32_t; typedef u16 compat_mode_t; -typedef u32 compat_ino_t; typedef u16 compat_dev_t; -typedef s32 compat_off_t; -typedef s64 compat_loff_t; typedef u16 compat_nlink_t; typedef u16 compat_ipc_pid_t; -typedef s32 compat_daddr_t; typedef u32 compat_caddr_t; typedef __kernel_fsid_t compat_fsid_t; -typedef s32 compat_key_t; -typedef s32 compat_timer_t; - -typedef s32 compat_int_t; -typedef s32 compat_long_t; typedef s64 compat_s64; -typedef u32 compat_uint_t; -typedef u32 compat_ulong_t; typedef u64 compat_u64; -typedef u32 compat_uptr_t; typedef struct { u32 mask; diff --git a/arch/sparc/include/asm/compat.h b/arch/sparc/include/asm/compat.h index 7018cb60beef..30b1763580b1 100644 --- a/arch/sparc/include/asm/compat.h +++ b/arch/sparc/include/asm/compat.h @@ -6,38 +6,23 @@ */ #include +#include + #define COMPAT_USER_HZ 100 #define COMPAT_UTS_MACHINE "sparc\0\0" -typedef u32 compat_size_t; -typedef s32 compat_ssize_t; -typedef s32 compat_clock_t; -typedef s32 compat_pid_t; typedef u16 __compat_uid_t; typedef u16 __compat_gid_t; typedef u32 __compat_uid32_t; typedef u32 __compat_gid32_t; typedef u16 compat_mode_t; -typedef u32 compat_ino_t; typedef u16 compat_dev_t; -typedef s32 compat_off_t; -typedef s64 compat_loff_t; typedef s16 compat_nlink_t; typedef u16 compat_ipc_pid_t; -typedef s32 compat_daddr_t; typedef u32 compat_caddr_t; typedef __kernel_fsid_t compat_fsid_t; -typedef s32 compat_key_t; -typedef s32 compat_timer_t; - -typedef s32 compat_int_t; -typedef s32 compat_long_t; typedef s64 compat_s64; -typedef u32 compat_uint_t; -typedef u32 compat_ulong_t; typedef u64 compat_u64; -typedef u32 compat_uptr_t; - struct compat_stat { compat_dev_t st_dev; compat_ino_t st_ino; diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h index fb97cf7c4137..0ce6f452d334 100644 --- a/arch/x86/include/asm/compat.h +++ b/arch/x86/include/asm/compat.h @@ -12,38 +12,23 @@ #include #include +#include + #define COMPAT_USER_HZ 100 #define COMPAT_UTS_MACHINE "i686\0\0" -typedef u32 compat_size_t; -typedef s32 compat_ssize_t; -typedef s32 compat_clock_t; -typedef s32 compat_pid_t; typedef u16 __compat_uid_t; typedef u16 __compat_gid_t; typedef u32 __compat_uid32_t; typedef u32 __compat_gid32_t; typedef u16 compat_mode_t; -typedef u32 compat_ino_t; typedef u16 compat_dev_t; -typedef s32 compat_off_t; -typedef s64 compat_loff_t; typedef u16 compat_nlink_t; typedef u16 compat_ipc_pid_t; -typedef s32 compat_daddr_t; typedef u32 compat_caddr_t; typedef __kernel_fsid_t compat_fsid_t; -typedef s32 compat_timer_t; -typedef s32 compat_key_t; - -typedef s32 compat_int_t; -typedef s32 compat_long_t; typedef s64 __attribute__((aligned(4))) compat_s64; -typedef u32 compat_uint_t; -typedef u32 compat_ulong_t; -typedef u32 compat_u32; typedef u64 __attribute__((aligned(4))) compat_u64; -typedef u32 compat_uptr_t; struct compat_stat { compat_dev_t st_dev; diff --git a/include/asm-generic/compat.h b/include/asm-generic/compat.h index 28819451b6d1..a86f65bffab8 100644 --- a/include/asm-generic/compat.h +++ b/include/asm-generic/compat.h @@ -1,3 +1,25 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_GENERIC_COMPAT_H +#define __ASM_GENERIC_COMPAT_H -/* This is an empty stub for 32-bit-only architectures */ +/* These types are common across all compat ABIs */ +typedef u32 compat_size_t; +typedef s32 compat_ssize_t; +typedef s32 compat_clock_t; +typedef s32 compat_pid_t; +typedef u32 compat_ino_t; +typedef s32 compat_off_t; +typedef s64 compat_loff_t; +typedef s32 compat_daddr_t; +typedef s32 compat_timer_t; +typedef s32 compat_key_t; +typedef s16 compat_short_t; +typedef s32 compat_int_t; +typedef s32 compat_long_t; +typedef u16 compat_ushort_t; +typedef u32 compat_uint_t; +typedef u32 compat_ulong_t; +typedef u32 compat_uptr_t; +typedef u32 compat_aio_context_t; + +#endif diff --git a/include/linux/compat.h b/include/linux/compat.h index 0e058792ecf6..d376fa8be00d 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -110,8 +110,6 @@ typedef struct compat_sigaltstack { typedef __compat_uid32_t compat_uid_t; typedef __compat_gid32_t compat_gid_t; -typedef compat_ulong_t compat_aio_context_t; - struct compat_sel_arg_struct; struct rusage; -- cgit v1.2.3 From a4f7a3004630f1a0fb130ab1824942a49ce33140 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 17 Apr 2018 09:11:58 +0200 Subject: y2038: Change sys_utimensat() to use __kernel_timespec When 32-bit architectures get changed to support 64-bit time_t, utimensat() needs to use the new __kernel_timespec structure as its argument. The older utime(), utimes() and futimesat() system calls don't need a corresponding change as they are no longer used on C libraries that have 64-bit time support. As we do for the other syscalls that have timespec arguments, we reuse the 'compat' syscall entry points to implement the traditional four interfaces, and only leave the new utimensat() as a native handler, so that the same code gets used on both 32-bit and 64-bit kernels on each syscall. Signed-off-by: Arnd Bergmann --- fs/utimes.c | 2 +- include/linux/syscalls.h | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/utimes.c b/fs/utimes.c index 79a65c163f40..d30f409ecc1a 100644 --- a/fs/utimes.c +++ b/fs/utimes.c @@ -166,7 +166,7 @@ out: } SYSCALL_DEFINE4(utimensat, int, dfd, const char __user *, filename, - struct timespec __user *, utimes, int, flags) + struct __kernel_timespec __user *, utimes, int, flags) { struct timespec64 tstimes[2]; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index b3e27e5ee322..420ac881a610 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -513,7 +513,8 @@ asmlinkage long sys_timerfd_gettime(int ufd, struct __kernel_itimerspec __user * /* fs/utimes.c */ asmlinkage long sys_utimensat(int dfd, const char __user *filename, - struct timespec __user *utimes, int flags); + struct __kernel_timespec __user *utimes, + int flags); /* kernel/acct.c */ asmlinkage long sys_acct(const char __user *name); -- cgit v1.2.3 From 185cfaf7641e14af85635bb2750da302e32b04e3 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 17 Apr 2018 09:11:58 +0200 Subject: y2038: Compile utimes()/futimesat() conditionally There are four generations of utimes() syscalls: utime(), utimes(), futimesat() and utimensat(), each one being a superset of the previous one. For y2038 support, we have to add another one, which is the same as the existing utimensat() but always passes 64-bit times_t based timespec values. There are currently 10 architectures that only use utimensat(), two that use utimes(), futimesat() and utimensat() but not utime(), and 11 architectures that have all four, and those define __ARCH_WANT_SYS_UTIME in order to get a sys_utime implementation. Since all the new architectures only want utimensat(), moving all the legacy entry points into a common __ARCH_WANT_SYS_UTIME guard simplifies the logic. Only alpha and ia64 grow a tiny bit as they now also get an unused sys_utime(), but it didn't seem worth the extra complexity of adding yet another ifdef for those. Signed-off-by: Arnd Bergmann --- arch/alpha/include/asm/unistd.h | 1 + arch/arm/include/asm/unistd.h | 2 +- arch/ia64/include/asm/unistd.h | 1 + fs/utimes.c | 51 ++++++++++++++++++----------------------- include/linux/syscalls.h | 10 ++++---- 5 files changed, 31 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/include/asm/unistd.h b/arch/alpha/include/asm/unistd.h index edc090470023..9ff37aa1165f 100644 --- a/arch/alpha/include/asm/unistd.h +++ b/arch/alpha/include/asm/unistd.h @@ -14,6 +14,7 @@ #define __ARCH_WANT_SYS_GETPGRP #define __ARCH_WANT_SYS_OLDUMOUNT #define __ARCH_WANT_SYS_SIGPENDING +#define __ARCH_WANT_SYS_UTIME #define __ARCH_WANT_SYS_FORK #define __ARCH_WANT_SYS_VFORK #define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h index 8f1159c26f20..88ef2ce1f69a 100644 --- a/arch/arm/include/asm/unistd.h +++ b/arch/arm/include/asm/unistd.h @@ -26,13 +26,13 @@ #define __ARCH_WANT_SYS_SIGPROCMASK #define __ARCH_WANT_SYS_OLD_MMAP #define __ARCH_WANT_SYS_OLD_SELECT +#define __ARCH_WANT_SYS_UTIME #if !defined(CONFIG_AEABI) || defined(CONFIG_OABI_COMPAT) #define __ARCH_WANT_SYS_TIME #define __ARCH_WANT_SYS_IPC #define __ARCH_WANT_SYS_OLDUMOUNT #define __ARCH_WANT_SYS_ALARM -#define __ARCH_WANT_SYS_UTIME #define __ARCH_WANT_SYS_OLD_GETRLIMIT #define __ARCH_WANT_OLD_READDIR #define __ARCH_WANT_SYS_SOCKETCALL diff --git a/arch/ia64/include/asm/unistd.h b/arch/ia64/include/asm/unistd.h index c5b2620c4a4c..49e34db2529c 100644 --- a/arch/ia64/include/asm/unistd.h +++ b/arch/ia64/include/asm/unistd.h @@ -29,6 +29,7 @@ #define __IGNORE_umount2 /* umount() */ #define __ARCH_WANT_NEW_STAT +#define __ARCH_WANT_SYS_UTIME #if !defined(__ASSEMBLY__) && !defined(ASSEMBLER) diff --git a/fs/utimes.c b/fs/utimes.c index d30f409ecc1a..2f6f08061a26 100644 --- a/fs/utimes.c +++ b/fs/utimes.c @@ -8,35 +8,6 @@ #include #include -#ifdef __ARCH_WANT_SYS_UTIME - -/* - * sys_utime() can be implemented in user-level using sys_utimes(). - * Is this for backwards compatibility? If so, why not move it - * into the appropriate arch directory (for those architectures that - * need it). - */ - -/* If times==NULL, set access and modification to current time, - * must be owner or have write permission. - * Else, update from *times, must be owner or super user. - */ -SYSCALL_DEFINE2(utime, char __user *, filename, struct utimbuf __user *, times) -{ - struct timespec64 tv[2]; - - if (times) { - if (get_user(tv[0].tv_sec, ×->actime) || - get_user(tv[1].tv_sec, ×->modtime)) - return -EFAULT; - tv[0].tv_nsec = 0; - tv[1].tv_nsec = 0; - } - return do_utimes(AT_FDCWD, filename, times ? tv : NULL, 0); -} - -#endif - static bool nsec_valid(long nsec) { if (nsec == UTIME_OMIT || nsec == UTIME_NOW) @@ -184,6 +155,13 @@ SYSCALL_DEFINE4(utimensat, int, dfd, const char __user *, filename, return do_utimes(dfd, filename, utimes ? tstimes : NULL, flags); } +#ifdef __ARCH_WANT_SYS_UTIME +/* + * futimesat(), utimes() and utime() are older versions of utimensat() + * that are provided for compatibility with traditional C libraries. + * On modern architectures, we always use libc wrappers around + * utimensat() instead. + */ static long do_futimesat(int dfd, const char __user *filename, struct timeval __user *utimes) { @@ -225,6 +203,21 @@ SYSCALL_DEFINE2(utimes, char __user *, filename, return do_futimesat(AT_FDCWD, filename, utimes); } +SYSCALL_DEFINE2(utime, char __user *, filename, struct utimbuf __user *, times) +{ + struct timespec64 tv[2]; + + if (times) { + if (get_user(tv[0].tv_sec, ×->actime) || + get_user(tv[1].tv_sec, ×->modtime)) + return -EFAULT; + tv[0].tv_nsec = 0; + tv[1].tv_nsec = 0; + } + return do_utimes(AT_FDCWD, filename, times ? tv : NULL, 0); +} +#endif + #ifdef CONFIG_COMPAT /* * Not all architectures have sys_utime, so implement this in terms diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 420ac881a610..95e795fb0593 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -955,8 +955,6 @@ asmlinkage long sys_access(const char __user *filename, int mode); asmlinkage long sys_rename(const char __user *oldname, const char __user *newname); asmlinkage long sys_symlink(const char __user *old, const char __user *new); -asmlinkage long sys_utimes(char __user *filename, - struct timeval __user *utimes); #if defined(__ARCH_WANT_STAT64) || defined(__ARCH_WANT_COMPAT_STAT64) asmlinkage long sys_stat64(const char __user *filename, struct stat64 __user *statbuf); @@ -986,14 +984,18 @@ asmlinkage long sys_alarm(unsigned int seconds); asmlinkage long sys_getpgrp(void); asmlinkage long sys_pause(void); asmlinkage long sys_time(time_t __user *tloc); +#ifdef __ARCH_WANT_SYS_UTIME asmlinkage long sys_utime(char __user *filename, struct utimbuf __user *times); +asmlinkage long sys_utimes(char __user *filename, + struct timeval __user *utimes); +asmlinkage long sys_futimesat(int dfd, const char __user *filename, + struct timeval __user *utimes); +#endif asmlinkage long sys_creat(const char __user *pathname, umode_t mode); asmlinkage long sys_getdents(unsigned int fd, struct linux_dirent __user *dirent, unsigned int count); -asmlinkage long sys_futimesat(int dfd, const char __user *filename, - struct timeval __user *utimes); asmlinkage long sys_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timeval __user *tvp); asmlinkage long sys_poll(struct pollfd __user *ufds, unsigned int nfds, -- cgit v1.2.3 From 4faea239e529d1d6b3b93fbf08d5e90427961a41 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 17 Apr 2018 12:03:19 +0200 Subject: y2038: utimes: Rework #ifdef guards for compat syscalls After changing over to 64-bit time_t syscalls, many architectures will want compat_sys_utimensat() but not respective handlers for utime(), utimes() and futimesat(). This adds a new __ARCH_WANT_SYS_UTIME32 to complement __ARCH_WANT_SYS_UTIME. For now, all 64-bit architectures that support CONFIG_COMPAT set it, but future 64-bit architectures will not (tile would not have needed it either, but got removed). As older 32-bit architectures get converted to using CONFIG_64BIT_TIME, they will have to use __ARCH_WANT_SYS_UTIME32 instead of __ARCH_WANT_SYS_UTIME. Architectures using the generic syscall ABI don't need either of them as they never had a utime syscall. Since the compat_utimbuf structure is now required outside of CONFIG_COMPAT, I'm moving it into compat_time.h. Signed-off-by: Arnd Bergmann --- changed from last version: - renamed __ARCH_WANT_COMPAT_SYS_UTIME to __ARCH_WANT_SYS_UTIME32 --- arch/arm64/include/asm/unistd.h | 1 + arch/mips/include/asm/unistd.h | 1 + arch/parisc/include/asm/unistd.h | 1 + arch/powerpc/include/asm/unistd.h | 1 + arch/s390/include/asm/unistd.h | 1 + arch/sparc/include/asm/unistd.h | 1 + arch/x86/include/asm/unistd.h | 1 + fs/utimes.c | 8 ++++++-- include/linux/compat.h | 7 +------ include/linux/time32.h | 5 +++++ 10 files changed, 19 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index 2af308f13463..b13ca091f833 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -22,6 +22,7 @@ #define __ARCH_WANT_SYS_SIGPENDING #define __ARCH_WANT_SYS_SIGPROCMASK #define __ARCH_WANT_COMPAT_SYS_SENDFILE +#define __ARCH_WANT_SYS_UTIME32 #define __ARCH_WANT_SYS_FORK #define __ARCH_WANT_SYS_VFORK diff --git a/arch/mips/include/asm/unistd.h b/arch/mips/include/asm/unistd.h index c2174b80e50e..c68b8ae3efcb 100644 --- a/arch/mips/include/asm/unistd.h +++ b/arch/mips/include/asm/unistd.h @@ -31,6 +31,7 @@ #define __ARCH_WANT_SYS_IPC #define __ARCH_WANT_SYS_PAUSE #define __ARCH_WANT_SYS_UTIME +#define __ARCH_WANT_SYS_UTIME32 #define __ARCH_WANT_SYS_WAITPID #define __ARCH_WANT_SYS_SOCKETCALL #define __ARCH_WANT_SYS_GETPGRP diff --git a/arch/parisc/include/asm/unistd.h b/arch/parisc/include/asm/unistd.h index a0c38374fff0..bc37a4953eaa 100644 --- a/arch/parisc/include/asm/unistd.h +++ b/arch/parisc/include/asm/unistd.h @@ -152,6 +152,7 @@ type name(type1 arg1, type2 arg2, type3 arg3, type4 arg4, type5 arg5) \ #define __ARCH_WANT_COMPAT_SYS_TIME #define __ARCH_WANT_COMPAT_SYS_SCHED_RR_GET_INTERVAL #define __ARCH_WANT_SYS_UTIME +#define __ARCH_WANT_SYS_UTIME32 #define __ARCH_WANT_SYS_WAITPID #define __ARCH_WANT_SYS_SOCKETCALL #define __ARCH_WANT_SYS_FADVISE64 diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index 9326c9133516..b0de85b477e1 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -47,6 +47,7 @@ #endif #ifdef CONFIG_PPC64 #define __ARCH_WANT_COMPAT_SYS_TIME +#define __ARCH_WANT_SYS_UTIME32 #define __ARCH_WANT_SYS_NEWFSTATAT #define __ARCH_WANT_COMPAT_SYS_SENDFILE #endif diff --git a/arch/s390/include/asm/unistd.h b/arch/s390/include/asm/unistd.h index a2d583ea526d..a1fbf15d53aa 100644 --- a/arch/s390/include/asm/unistd.h +++ b/arch/s390/include/asm/unistd.h @@ -34,6 +34,7 @@ #define __ARCH_WANT_SYS_SIGPROCMASK # ifdef CONFIG_COMPAT # define __ARCH_WANT_COMPAT_SYS_TIME +# define __ARCH_WANT_SYS_UTIME32 # endif #define __ARCH_WANT_SYS_FORK #define __ARCH_WANT_SYS_VFORK diff --git a/arch/sparc/include/asm/unistd.h b/arch/sparc/include/asm/unistd.h index f7514d3eae7b..00f87dbd0b17 100644 --- a/arch/sparc/include/asm/unistd.h +++ b/arch/sparc/include/asm/unistd.h @@ -42,6 +42,7 @@ #define __ARCH_WANT_SYS_IPC #else #define __ARCH_WANT_COMPAT_SYS_TIME +#define __ARCH_WANT_SYS_UTIME32 #define __ARCH_WANT_COMPAT_SYS_SENDFILE #endif diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h index 153d2a5e6b02..dc4ed8bc2382 100644 --- a/arch/x86/include/asm/unistd.h +++ b/arch/x86/include/asm/unistd.h @@ -24,6 +24,7 @@ # include # include # define __ARCH_WANT_COMPAT_SYS_TIME +# define __ARCH_WANT_SYS_UTIME32 # define __ARCH_WANT_COMPAT_SYS_PREADV64 # define __ARCH_WANT_COMPAT_SYS_PWRITEV64 # define __ARCH_WANT_COMPAT_SYS_PREADV64V2 diff --git a/fs/utimes.c b/fs/utimes.c index 2f6f08061a26..bdcf2daf39c1 100644 --- a/fs/utimes.c +++ b/fs/utimes.c @@ -218,13 +218,14 @@ SYSCALL_DEFINE2(utime, char __user *, filename, struct utimbuf __user *, times) } #endif -#ifdef CONFIG_COMPAT +#ifdef CONFIG_COMPAT_32BIT_TIME /* * Not all architectures have sys_utime, so implement this in terms * of sys_utimes. */ +#ifdef __ARCH_WANT_SYS_UTIME32 COMPAT_SYSCALL_DEFINE2(utime, const char __user *, filename, - struct compat_utimbuf __user *, t) + struct old_utimbuf32 __user *, t) { struct timespec64 tv[2]; @@ -237,6 +238,7 @@ COMPAT_SYSCALL_DEFINE2(utime, const char __user *, filename, } return do_utimes(AT_FDCWD, filename, t ? tv : NULL, 0); } +#endif COMPAT_SYSCALL_DEFINE4(utimensat, unsigned int, dfd, const char __user *, filename, struct old_timespec32 __user *, t, int, flags) { @@ -253,6 +255,7 @@ COMPAT_SYSCALL_DEFINE4(utimensat, unsigned int, dfd, const char __user *, filena return do_utimes(dfd, filename, t ? tv : NULL, flags); } +#ifdef __ARCH_WANT_SYS_UTIME32 static long do_compat_futimesat(unsigned int dfd, const char __user *filename, struct old_timeval32 __user *t) { @@ -285,3 +288,4 @@ COMPAT_SYSCALL_DEFINE2(utimes, const char __user *, filename, struct old_timeval return do_compat_futimesat(AT_FDCWD, filename, t); } #endif +#endif diff --git a/include/linux/compat.h b/include/linux/compat.h index d376fa8be00d..6fb5abdb87be 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -113,11 +113,6 @@ typedef __compat_gid32_t compat_gid_t; struct compat_sel_arg_struct; struct rusage; -struct compat_utimbuf { - old_time32_t actime; - old_time32_t modtime; -}; - struct compat_itimerval { struct old_timeval32 it_interval; struct old_timeval32 it_value; @@ -942,7 +937,7 @@ asmlinkage long compat_sys_newlstat(const char __user *filename, /* __ARCH_WANT_SYSCALL_DEPRECATED */ asmlinkage long compat_sys_time(old_time32_t __user *tloc); asmlinkage long compat_sys_utime(const char __user *filename, - struct compat_utimbuf __user *t); + struct old_utimbuf32 __user *t); asmlinkage long compat_sys_futimesat(unsigned int dfd, const char __user *filename, struct old_timeval32 __user *t); diff --git a/include/linux/time32.h b/include/linux/time32.h index 0e0d7304d1a8..61904a6c098f 100644 --- a/include/linux/time32.h +++ b/include/linux/time32.h @@ -30,6 +30,11 @@ struct old_itimerspec32 { struct old_timespec32 it_value; }; +struct old_utimbuf32 { + old_time32_t actime; + old_time32_t modtime; +}; + extern int get_old_timespec32(struct timespec64 *, const void __user *); extern int put_old_timespec32(const struct timespec64 *, void __user *); extern int get_old_itimerspec32(struct itimerspec64 *its, -- cgit v1.2.3 From 474b9c777b20b8340a6ee0f7ba6ebbd6a4bf47e2 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 17 Apr 2018 21:59:47 +0200 Subject: y2038: sched: Change sched_rr_get_interval to use __kernel_timespec This is a preparation patch for converting sys_sched_rr_get_interval to work with 64-bit time_t on 32-bit architectures. The 'interval' argument is changed to struct __kernel_timespec, which will be redefined using 64-bit time_t in the future. The compat version of the system call in turn is enabled for compilation with CONFIG_COMPAT_32BIT_TIME so the individual 32-bit architectures can share the handling of the traditional argument with 64-bit architectures providing it for their compat mode. Signed-off-by: Arnd Bergmann --- include/linux/syscalls.h | 2 +- kernel/sched/core.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 95e795fb0593..5642016a312d 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -614,7 +614,7 @@ asmlinkage long sys_sched_yield(void); asmlinkage long sys_sched_get_priority_max(int policy); asmlinkage long sys_sched_get_priority_min(int policy); asmlinkage long sys_sched_rr_get_interval(pid_t pid, - struct timespec __user *interval); + struct __kernel_timespec __user *interval); /* kernel/signal.c */ asmlinkage long sys_restart_syscall(void); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 8287b75ed961..39af2bec2b39 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5243,7 +5243,7 @@ out_unlock: * an error code. */ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, - struct timespec __user *, interval) + struct __kernel_timespec __user *, interval) { struct timespec64 t; int retval = sched_rr_get_interval(pid, &t); @@ -5254,7 +5254,7 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, return retval; } -#ifdef CONFIG_COMPAT +#ifdef CONFIG_COMPAT_32BIT_TIME COMPAT_SYSCALL_DEFINE2(sched_rr_get_interval, compat_pid_t, pid, struct old_timespec32 __user *, interval) -- cgit v1.2.3 From c2e6c8567acdba8db1055b242c34ceb123c6a253 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 18 Apr 2018 13:42:25 +0200 Subject: y2038: socket: Change recvmmsg to use __kernel_timespec This converts the recvmmsg() system call in all its variations to use 'timespec64' internally for its timeout, and have a __kernel_timespec64 argument in the native entry point. This lets us change the type to use 64-bit time_t at a later point while using the 32-bit compat system call emulation for existing user space. Signed-off-by: Arnd Bergmann --- include/linux/socket.h | 4 ++-- include/linux/syscalls.h | 2 +- net/compat.c | 6 +++--- net/socket.c | 18 ++++++++---------- 4 files changed, 14 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 7ed4713d5337..8b571e9b9f76 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -348,7 +348,7 @@ struct ucred { extern int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr_storage *kaddr); extern int put_cmsg(struct msghdr*, int level, int type, int len, void *data); -struct timespec; +struct timespec64; /* The __sys_...msg variants allow MSG_CMSG_COMPAT iff * forbid_cmsg_compat==false @@ -358,7 +358,7 @@ extern long __sys_recvmsg(int fd, struct user_msghdr __user *msg, extern long __sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned int flags, bool forbid_cmsg_compat); extern int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, - unsigned int flags, struct timespec *timeout); + unsigned int flags, struct timespec64 *timeout); extern int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, unsigned int flags, bool forbid_cmsg_compat); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 5642016a312d..fb3a05fab8aa 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -830,7 +830,7 @@ asmlinkage long sys_perf_event_open( asmlinkage long sys_accept4(int, struct sockaddr __user *, int __user *, int); asmlinkage long sys_recvmmsg(int fd, struct mmsghdr __user *msg, unsigned int vlen, unsigned flags, - struct timespec __user *timeout); + struct __kernel_timespec __user *timeout); asmlinkage long sys_wait4(pid_t pid, int __user *stat_addr, int options, struct rusage __user *ru); diff --git a/net/compat.c b/net/compat.c index 2ef160876bc1..47a614b370cd 100644 --- a/net/compat.c +++ b/net/compat.c @@ -815,18 +815,18 @@ static int __compat_sys_recvmmsg(int fd, struct compat_mmsghdr __user *mmsg, struct old_timespec32 __user *timeout) { int datagrams; - struct timespec ktspec; + struct timespec64 ktspec; if (timeout == NULL) return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen, flags | MSG_CMSG_COMPAT, NULL); - if (compat_get_timespec(&ktspec, timeout)) + if (compat_get_timespec64(&ktspec, timeout)) return -EFAULT; datagrams = __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen, flags | MSG_CMSG_COMPAT, &ktspec); - if (datagrams > 0 && compat_put_timespec(&ktspec, timeout)) + if (datagrams > 0 && compat_put_timespec64(&ktspec, timeout)) datagrams = -EFAULT; return datagrams; diff --git a/net/socket.c b/net/socket.c index e6945e318f02..b9d71b503720 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2340,7 +2340,7 @@ SYSCALL_DEFINE3(recvmsg, int, fd, struct user_msghdr __user *, msg, */ int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, - unsigned int flags, struct timespec *timeout) + unsigned int flags, struct timespec64 *timeout) { int fput_needed, err, datagrams; struct socket *sock; @@ -2405,8 +2405,7 @@ int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, if (timeout) { ktime_get_ts64(&timeout64); - *timeout = timespec64_to_timespec( - timespec64_sub(end_time, timeout64)); + *timeout = timespec64_sub(end_time, timeout64); if (timeout->tv_sec < 0) { timeout->tv_sec = timeout->tv_nsec = 0; break; @@ -2452,10 +2451,10 @@ out_put: static int do_sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, unsigned int flags, - struct timespec __user *timeout) + struct __kernel_timespec __user *timeout) { int datagrams; - struct timespec timeout_sys; + struct timespec64 timeout_sys; if (flags & MSG_CMSG_COMPAT) return -EINVAL; @@ -2463,13 +2462,12 @@ static int do_sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, if (!timeout) return __sys_recvmmsg(fd, mmsg, vlen, flags, NULL); - if (copy_from_user(&timeout_sys, timeout, sizeof(timeout_sys))) + if (get_timespec64(&timeout_sys, timeout)) return -EFAULT; datagrams = __sys_recvmmsg(fd, mmsg, vlen, flags, &timeout_sys); - if (datagrams > 0 && - copy_to_user(timeout, &timeout_sys, sizeof(timeout_sys))) + if (datagrams > 0 && put_timespec64(&timeout_sys, timeout)) datagrams = -EFAULT; return datagrams; @@ -2477,7 +2475,7 @@ static int do_sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, SYSCALL_DEFINE5(recvmmsg, int, fd, struct mmsghdr __user *, mmsg, unsigned int, vlen, unsigned int, flags, - struct timespec __user *, timeout) + struct __kernel_timespec __user *, timeout) { return do_sys_recvmmsg(fd, mmsg, vlen, flags, timeout); } @@ -2601,7 +2599,7 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args) break; case SYS_RECVMMSG: err = do_sys_recvmmsg(a0, (struct mmsghdr __user *)a1, a[2], - a[3], (struct timespec __user *)a[4]); + a[3], (struct __kernel_timespec __user *)a[4]); break; case SYS_ACCEPT4: err = __sys_accept4(a0, (struct sockaddr __user *)a1, -- cgit v1.2.3 From 49c39f8464a9af702e9d45800c00a572753aeb06 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 18 Apr 2018 15:56:13 +0200 Subject: y2038: signal: Change rt_sigtimedwait to use __kernel_timespec This changes sys_rt_sigtimedwait() to use get_timespec64(), changing the timeout type to __kernel_timespec, which will be changed to use a 64-bit time_t in the future. Since the do_sigtimedwait() core function changes, we also have to modify the compat version of this system call in the same way. Signed-off-by: Arnd Bergmann --- include/linux/syscalls.h | 2 +- kernel/signal.c | 17 +++++++++-------- 2 files changed, 10 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index fb3a05fab8aa..2ac3d13a915b 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -635,7 +635,7 @@ asmlinkage long sys_rt_sigprocmask(int how, sigset_t __user *set, asmlinkage long sys_rt_sigpending(sigset_t __user *set, size_t sigsetsize); asmlinkage long sys_rt_sigtimedwait(const sigset_t __user *uthese, siginfo_t __user *uinfo, - const struct timespec __user *uts, + const struct __kernel_timespec __user *uts, size_t sigsetsize); asmlinkage long sys_rt_sigqueueinfo(pid_t pid, int sig, siginfo_t __user *uinfo); diff --git a/kernel/signal.c b/kernel/signal.c index a4db724e14c1..0831d56a731a 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -3082,7 +3082,7 @@ int copy_siginfo_from_user32(struct siginfo *to, * @ts: upper bound on process time suspension */ static int do_sigtimedwait(const sigset_t *which, siginfo_t *info, - const struct timespec *ts) + const struct timespec64 *ts) { ktime_t *to = NULL, timeout = KTIME_MAX; struct task_struct *tsk = current; @@ -3090,9 +3090,9 @@ static int do_sigtimedwait(const sigset_t *which, siginfo_t *info, int sig, ret = 0; if (ts) { - if (!timespec_valid(ts)) + if (!timespec64_valid(ts)) return -EINVAL; - timeout = timespec_to_ktime(*ts); + timeout = timespec64_to_ktime(*ts); to = &timeout; } @@ -3140,11 +3140,12 @@ static int do_sigtimedwait(const sigset_t *which, siginfo_t *info, * @sigsetsize: size of sigset_t type */ SYSCALL_DEFINE4(rt_sigtimedwait, const sigset_t __user *, uthese, - siginfo_t __user *, uinfo, const struct timespec __user *, uts, + siginfo_t __user *, uinfo, + const struct __kernel_timespec __user *, uts, size_t, sigsetsize) { sigset_t these; - struct timespec ts; + struct timespec64 ts; siginfo_t info; int ret; @@ -3156,7 +3157,7 @@ SYSCALL_DEFINE4(rt_sigtimedwait, const sigset_t __user *, uthese, return -EFAULT; if (uts) { - if (copy_from_user(&ts, uts, sizeof(ts))) + if (get_timespec64(&ts, uts)) return -EFAULT; } @@ -3176,7 +3177,7 @@ COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait, compat_sigset_t __user *, uthese, struct old_timespec32 __user *, uts, compat_size_t, sigsetsize) { sigset_t s; - struct timespec t; + struct timespec64 t; siginfo_t info; long ret; @@ -3187,7 +3188,7 @@ COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait, compat_sigset_t __user *, uthese, return -EFAULT; if (uts) { - if (compat_get_timespec(&t, uts)) + if (get_old_timespec32(&t, uts)) return -EFAULT; } -- cgit v1.2.3 From 6c5c9581044dd6e0cd284ab653502fb9264f08b6 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Tue, 28 Aug 2018 14:44:28 +0200 Subject: net: add napi_if_scheduled_mark_missed The function napi_if_scheduled_mark_missed is used to check if the NAPI context is scheduled, if so set NAPIF_STATE_MISSED and return true. Used by the AF_XDP zero-copy i40e Tx code implementation in order to make sure that irq affinity is honored by the napi context. Signed-off-by: Magnus Karlsson Signed-off-by: Alexei Starovoitov --- include/linux/netdevice.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ca5ab98053c8..4271f6b4e419 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -535,6 +535,32 @@ static inline void napi_synchronize(const struct napi_struct *n) barrier(); } +/** + * napi_if_scheduled_mark_missed - if napi is running, set the + * NAPIF_STATE_MISSED + * @n: NAPI context + * + * If napi is running, set the NAPIF_STATE_MISSED, and return true if + * NAPI is scheduled. + **/ +static inline bool napi_if_scheduled_mark_missed(struct napi_struct *n) +{ + unsigned long val, new; + + do { + val = READ_ONCE(n->state); + if (val & NAPIF_STATE_DISABLE) + return true; + + if (!(val & NAPIF_STATE_SCHED)) + return false; + + new = val | NAPIF_STATE_MISSED; + } while (cmpxchg(&n->state, val, new) != val); + + return true; +} + enum netdev_queue_state_t { __QUEUE_STATE_DRV_XOFF, __QUEUE_STATE_STACK_XOFF, -- cgit v1.2.3 From 679c782de14bd48c19dd74cd1af20a2bc05dd936 Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Wed, 22 Aug 2018 20:02:19 +0100 Subject: bpf/verifier: per-register parent pointers By giving each register its own liveness chain, we elide the skip_callee() logic. Instead, each register's parent is the state it inherits from; both check_func_call() and prepare_func_exit() automatically connect reg states to the correct chain since when they copy the reg state across (r1-r5 into the callee as args, and r0 out as the return value) they also copy the parent pointer. Signed-off-by: Edward Cree Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 8 +- kernel/bpf/verifier.c | 184 +++++++++++-------------------------------- 2 files changed, 47 insertions(+), 145 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 38b04f559ad3..b42b60a83e19 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -41,6 +41,7 @@ enum bpf_reg_liveness { }; struct bpf_reg_state { + /* Ordering of fields matters. See states_equal() */ enum bpf_reg_type type; union { /* valid when type == PTR_TO_PACKET */ @@ -59,7 +60,6 @@ struct bpf_reg_state { * came from, when one is tested for != NULL. */ u32 id; - /* Ordering of fields matters. See states_equal() */ /* For scalar types (SCALAR_VALUE), this represents our knowledge of * the actual value. * For pointer types, this represents the variable part of the offset @@ -76,15 +76,15 @@ struct bpf_reg_state { s64 smax_value; /* maximum possible (s64)value */ u64 umin_value; /* minimum possible (u64)value */ u64 umax_value; /* maximum possible (u64)value */ + /* parentage chain for liveness checking */ + struct bpf_reg_state *parent; /* Inside the callee two registers can be both PTR_TO_STACK like * R1=fp-8 and R2=fp-8, but one of them points to this function stack * while another to the caller's stack. To differentiate them 'frameno' * is used which is an index in bpf_verifier_state->frame[] array * pointing to bpf_func_state. - * This field must be second to last, for states_equal() reasons. */ u32 frameno; - /* This field must be last, for states_equal() reasons. */ enum bpf_reg_liveness live; }; @@ -107,7 +107,6 @@ struct bpf_stack_state { */ struct bpf_func_state { struct bpf_reg_state regs[MAX_BPF_REG]; - struct bpf_verifier_state *parent; /* index of call instruction that called into this func */ int callsite; /* stack frame number of this function state from pov of @@ -129,7 +128,6 @@ struct bpf_func_state { struct bpf_verifier_state { /* call stack tracking */ struct bpf_func_state *frame[MAX_CALL_FRAMES]; - struct bpf_verifier_state *parent; u32 curframe; }; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 92246117d2b0..68568d22d6bd 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -380,9 +380,9 @@ static int copy_stack_state(struct bpf_func_state *dst, /* do_check() starts with zero-sized stack in struct bpf_verifier_state to * make it consume minimal amount of memory. check_stack_write() access from * the program calls into realloc_func_state() to grow the stack size. - * Note there is a non-zero 'parent' pointer inside bpf_verifier_state - * which this function copies over. It points to previous bpf_verifier_state - * which is never reallocated + * Note there is a non-zero parent pointer inside each reg of bpf_verifier_state + * which this function copies over. It points to corresponding reg in previous + * bpf_verifier_state which is never reallocated */ static int realloc_func_state(struct bpf_func_state *state, int size, bool copy_old) @@ -466,7 +466,6 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state, dst_state->frame[i] = NULL; } dst_state->curframe = src->curframe; - dst_state->parent = src->parent; for (i = 0; i <= src->curframe; i++) { dst = dst_state->frame[i]; if (!dst) { @@ -732,6 +731,7 @@ static void init_reg_state(struct bpf_verifier_env *env, for (i = 0; i < MAX_BPF_REG; i++) { mark_reg_not_init(env, regs, i); regs[i].live = REG_LIVE_NONE; + regs[i].parent = NULL; } /* frame pointer */ @@ -876,74 +876,21 @@ next: return 0; } -static -struct bpf_verifier_state *skip_callee(struct bpf_verifier_env *env, - const struct bpf_verifier_state *state, - struct bpf_verifier_state *parent, - u32 regno) -{ - struct bpf_verifier_state *tmp = NULL; - - /* 'parent' could be a state of caller and - * 'state' could be a state of callee. In such case - * parent->curframe < state->curframe - * and it's ok for r1 - r5 registers - * - * 'parent' could be a callee's state after it bpf_exit-ed. - * In such case parent->curframe > state->curframe - * and it's ok for r0 only - */ - if (parent->curframe == state->curframe || - (parent->curframe < state->curframe && - regno >= BPF_REG_1 && regno <= BPF_REG_5) || - (parent->curframe > state->curframe && - regno == BPF_REG_0)) - return parent; - - if (parent->curframe > state->curframe && - regno >= BPF_REG_6) { - /* for callee saved regs we have to skip the whole chain - * of states that belong to callee and mark as LIVE_READ - * the registers before the call - */ - tmp = parent; - while (tmp && tmp->curframe != state->curframe) { - tmp = tmp->parent; - } - if (!tmp) - goto bug; - parent = tmp; - } else { - goto bug; - } - return parent; -bug: - verbose(env, "verifier bug regno %d tmp %p\n", regno, tmp); - verbose(env, "regno %d parent frame %d current frame %d\n", - regno, parent->curframe, state->curframe); - return NULL; -} - +/* Parentage chain of this register (or stack slot) should take care of all + * issues like callee-saved registers, stack slot allocation time, etc. + */ static int mark_reg_read(struct bpf_verifier_env *env, - const struct bpf_verifier_state *state, - struct bpf_verifier_state *parent, - u32 regno) + const struct bpf_reg_state *state, + struct bpf_reg_state *parent) { bool writes = parent == state->parent; /* Observe write marks */ - if (regno == BPF_REG_FP) - /* We don't need to worry about FP liveness because it's read-only */ - return 0; - while (parent) { /* if read wasn't screened by an earlier write ... */ - if (writes && state->frame[state->curframe]->regs[regno].live & REG_LIVE_WRITTEN) + if (writes && state->live & REG_LIVE_WRITTEN) break; - parent = skip_callee(env, state, parent, regno); - if (!parent) - return -EFAULT; /* ... then we depend on parent's value */ - parent->frame[parent->curframe]->regs[regno].live |= REG_LIVE_READ; + parent->live |= REG_LIVE_READ; state = parent; parent = state->parent; writes = true; @@ -969,7 +916,10 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, verbose(env, "R%d !read_ok\n", regno); return -EACCES; } - return mark_reg_read(env, vstate, vstate->parent, regno); + /* We don't need to worry about FP liveness because it's read-only */ + if (regno != BPF_REG_FP) + return mark_reg_read(env, ®s[regno], + regs[regno].parent); } else { /* check whether register used as dest operand can be written to */ if (regno == BPF_REG_FP) { @@ -1080,8 +1030,8 @@ static int check_stack_write(struct bpf_verifier_env *env, } else { u8 type = STACK_MISC; - /* regular write of data into stack */ - state->stack[spi].spilled_ptr = (struct bpf_reg_state) {}; + /* regular write of data into stack destroys any spilled ptr */ + state->stack[spi].spilled_ptr.type = NOT_INIT; /* only mark the slot as written if all 8 bytes were written * otherwise read propagation may incorrectly stop too soon @@ -1106,61 +1056,6 @@ static int check_stack_write(struct bpf_verifier_env *env, return 0; } -/* registers of every function are unique and mark_reg_read() propagates - * the liveness in the following cases: - * - from callee into caller for R1 - R5 that were used as arguments - * - from caller into callee for R0 that used as result of the call - * - from caller to the same caller skipping states of the callee for R6 - R9, - * since R6 - R9 are callee saved by implicit function prologue and - * caller's R6 != callee's R6, so when we propagate liveness up to - * parent states we need to skip callee states for R6 - R9. - * - * stack slot marking is different, since stacks of caller and callee are - * accessible in both (since caller can pass a pointer to caller's stack to - * callee which can pass it to another function), hence mark_stack_slot_read() - * has to propagate the stack liveness to all parent states at given frame number. - * Consider code: - * f1() { - * ptr = fp - 8; - * *ptr = ctx; - * call f2 { - * .. = *ptr; - * } - * .. = *ptr; - * } - * First *ptr is reading from f1's stack and mark_stack_slot_read() has - * to mark liveness at the f1's frame and not f2's frame. - * Second *ptr is also reading from f1's stack and mark_stack_slot_read() has - * to propagate liveness to f2 states at f1's frame level and further into - * f1 states at f1's frame level until write into that stack slot - */ -static void mark_stack_slot_read(struct bpf_verifier_env *env, - const struct bpf_verifier_state *state, - struct bpf_verifier_state *parent, - int slot, int frameno) -{ - bool writes = parent == state->parent; /* Observe write marks */ - - while (parent) { - if (parent->frame[frameno]->allocated_stack <= slot * BPF_REG_SIZE) - /* since LIVE_WRITTEN mark is only done for full 8-byte - * write the read marks are conservative and parent - * state may not even have the stack allocated. In such case - * end the propagation, since the loop reached beginning - * of the function - */ - break; - /* if read wasn't screened by an earlier write ... */ - if (writes && state->frame[frameno]->stack[slot].spilled_ptr.live & REG_LIVE_WRITTEN) - break; - /* ... then we depend on parent's value */ - parent->frame[frameno]->stack[slot].spilled_ptr.live |= REG_LIVE_READ; - state = parent; - parent = state->parent; - writes = true; - } -} - static int check_stack_read(struct bpf_verifier_env *env, struct bpf_func_state *reg_state /* func where register points to */, int off, int size, int value_regno) @@ -1198,8 +1093,8 @@ static int check_stack_read(struct bpf_verifier_env *env, */ state->regs[value_regno].live |= REG_LIVE_WRITTEN; } - mark_stack_slot_read(env, vstate, vstate->parent, spi, - reg_state->frameno); + mark_reg_read(env, ®_state->stack[spi].spilled_ptr, + reg_state->stack[spi].spilled_ptr.parent); return 0; } else { int zeros = 0; @@ -1215,8 +1110,8 @@ static int check_stack_read(struct bpf_verifier_env *env, off, i, size); return -EACCES; } - mark_stack_slot_read(env, vstate, vstate->parent, spi, - reg_state->frameno); + mark_reg_read(env, ®_state->stack[spi].spilled_ptr, + reg_state->stack[spi].spilled_ptr.parent); if (value_regno >= 0) { if (zeros == size) { /* any size read into register is zero extended, @@ -1908,8 +1803,8 @@ mark: /* reading any byte out of 8-byte 'spill_slot' will cause * the whole slot to be marked as 'read' */ - mark_stack_slot_read(env, env->cur_state, env->cur_state->parent, - spi, state->frameno); + mark_reg_read(env, &state->stack[spi].spilled_ptr, + state->stack[spi].spilled_ptr.parent); } return update_stack_depth(env, state, off); } @@ -2366,11 +2261,13 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, state->curframe + 1 /* frameno within this callchain */, subprog /* subprog number within this prog */); - /* copy r1 - r5 args that callee can access */ + /* copy r1 - r5 args that callee can access. The copy includes parent + * pointers, which connects us up to the liveness chain + */ for (i = BPF_REG_1; i <= BPF_REG_5; i++) callee->regs[i] = caller->regs[i]; - /* after the call regsiters r0 - r5 were scratched */ + /* after the call registers r0 - r5 were scratched */ for (i = 0; i < CALLER_SAVED_REGS; i++) { mark_reg_not_init(env, caller->regs, caller_saved[i]); check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK); @@ -4370,7 +4267,7 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, /* explored state didn't use this */ return true; - equal = memcmp(rold, rcur, offsetof(struct bpf_reg_state, frameno)) == 0; + equal = memcmp(rold, rcur, offsetof(struct bpf_reg_state, parent)) == 0; if (rold->type == PTR_TO_STACK) /* two stack pointers are equal only if they're pointing to @@ -4603,7 +4500,7 @@ static bool states_equal(struct bpf_verifier_env *env, * equivalent state (jump target or such) we didn't arrive by the straight-line * code, so read marks in the state must propagate to the parent regardless * of the state's write marks. That's what 'parent == state->parent' comparison - * in mark_reg_read() and mark_stack_slot_read() is for. + * in mark_reg_read() is for. */ static int propagate_liveness(struct bpf_verifier_env *env, const struct bpf_verifier_state *vstate, @@ -4624,7 +4521,8 @@ static int propagate_liveness(struct bpf_verifier_env *env, if (vparent->frame[vparent->curframe]->regs[i].live & REG_LIVE_READ) continue; if (vstate->frame[vstate->curframe]->regs[i].live & REG_LIVE_READ) { - err = mark_reg_read(env, vstate, vparent, i); + err = mark_reg_read(env, &vstate->frame[vstate->curframe]->regs[i], + &vparent->frame[vstate->curframe]->regs[i]); if (err) return err; } @@ -4639,7 +4537,8 @@ static int propagate_liveness(struct bpf_verifier_env *env, if (parent->stack[i].spilled_ptr.live & REG_LIVE_READ) continue; if (state->stack[i].spilled_ptr.live & REG_LIVE_READ) - mark_stack_slot_read(env, vstate, vparent, i, frame); + mark_reg_read(env, &state->stack[i].spilled_ptr, + &parent->stack[i].spilled_ptr); } } return err; @@ -4649,7 +4548,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) { struct bpf_verifier_state_list *new_sl; struct bpf_verifier_state_list *sl; - struct bpf_verifier_state *cur = env->cur_state; + struct bpf_verifier_state *cur = env->cur_state, *new; int i, j, err; sl = env->explored_states[insn_idx]; @@ -4691,16 +4590,18 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) return -ENOMEM; /* add new state to the head of linked list */ - err = copy_verifier_state(&new_sl->state, cur); + new = &new_sl->state; + err = copy_verifier_state(new, cur); if (err) { - free_verifier_state(&new_sl->state, false); + free_verifier_state(new, false); kfree(new_sl); return err; } new_sl->next = env->explored_states[insn_idx]; env->explored_states[insn_idx] = new_sl; /* connect new state to parentage chain */ - cur->parent = &new_sl->state; + for (i = 0; i < BPF_REG_FP; i++) + cur_regs(env)[i].parent = &new->frame[new->curframe]->regs[i]; /* clear write marks in current state: the writes we did are not writes * our child did, so they don't screen off its reads from us. * (There are no read marks in current state, because reads always mark @@ -4713,9 +4614,13 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) /* all stack frames are accessible from callee, clear them all */ for (j = 0; j <= cur->curframe; j++) { struct bpf_func_state *frame = cur->frame[j]; + struct bpf_func_state *newframe = new->frame[j]; - for (i = 0; i < frame->allocated_stack / BPF_REG_SIZE; i++) + for (i = 0; i < frame->allocated_stack / BPF_REG_SIZE; i++) { frame->stack[i].spilled_ptr.live = REG_LIVE_NONE; + frame->stack[i].spilled_ptr.parent = + &newframe->stack[i].spilled_ptr; + } } return 0; } @@ -4734,7 +4639,6 @@ static int do_check(struct bpf_verifier_env *env) if (!state) return -ENOMEM; state->curframe = 0; - state->parent = NULL; state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL); if (!state->frame[0]) { kfree(state); -- cgit v1.2.3 From 9b3004953503462a4fab31b85e44ae446d48f0bd Mon Sep 17 00:00:00 2001 From: Michal Kubecek Date: Tue, 28 Aug 2018 19:56:58 +0200 Subject: ethtool: drop get_settings and set_settings callbacks Since [gs]et_settings ethtool_ops callbacks have been deprecated in February 2016, all in tree NIC drivers have been converted to provide [gs]et_link_ksettings() and out of tree drivers have had enough time to do the same. Drop get_settings() and set_settings() and implement both ETHTOOL_[GS]SET and ETHTOOL_[GS]LINKSETTINGS only using [gs]et_link_ksettings(). Signed-off-by: Michal Kubecek Signed-off-by: David S. Miller --- Documentation/ABI/testing/sysfs-class-net | 4 +- include/linux/ethtool.h | 33 ++----- include/uapi/linux/ethtool.h | 15 +-- net/core/ethtool.c | 158 +++++++----------------------- 4 files changed, 50 insertions(+), 160 deletions(-) (limited to 'include/linux') diff --git a/Documentation/ABI/testing/sysfs-class-net b/Documentation/ABI/testing/sysfs-class-net index 2f1788111cd9..e2e0fe553ad8 100644 --- a/Documentation/ABI/testing/sysfs-class-net +++ b/Documentation/ABI/testing/sysfs-class-net @@ -117,7 +117,7 @@ Description: full: full duplex Note: This attribute is only valid for interfaces that implement - the ethtool get_settings method (mostly Ethernet). + the ethtool get_link_ksettings method (mostly Ethernet). What: /sys/class/net//flags Date: April 2005 @@ -224,7 +224,7 @@ Description: an integer representing the link speed in Mbits/sec. Note: this attribute is only valid for interfaces that implement - the ethtool get_settings method (mostly Ethernet ). + the ethtool get_link_ksettings method (mostly Ethernet). What: /sys/class/net//tx_queue_len Date: April 2005 diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index f8a2245b70ac..afd9596ce636 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -183,14 +183,6 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, /** * struct ethtool_ops - optional netdev operations - * @get_settings: DEPRECATED, use %get_link_ksettings/%set_link_ksettings - * API. Get various device settings including Ethernet link - * settings. The @cmd parameter is expected to have been cleared - * before get_settings is called. Returns a negative error code - * or zero. - * @set_settings: DEPRECATED, use %get_link_ksettings/%set_link_ksettings - * API. Set various device settings including Ethernet link - * settings. Returns a negative error code or zero. * @get_drvinfo: Report driver/device information. Should only set the * @driver, @version, @fw_version and @bus_info fields. If not * implemented, the @driver and @bus_info fields will be filled in @@ -297,19 +289,16 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, * a TX queue has this number, return -EINVAL. If only a RX queue or a TX * queue has this number, ignore the inapplicable fields. * Returns a negative error code or zero. - * @get_link_ksettings: When defined, takes precedence over the - * %get_settings method. Get various device settings - * including Ethernet link settings. The %cmd and - * %link_mode_masks_nwords fields should be ignored (use - * %__ETHTOOL_LINK_MODE_MASK_NBITS instead of the latter), any - * change to them will be overwritten by kernel. Returns a - * negative error code or zero. - * @set_link_ksettings: When defined, takes precedence over the - * %set_settings method. Set various device settings including - * Ethernet link settings. The %cmd and %link_mode_masks_nwords - * fields should be ignored (use %__ETHTOOL_LINK_MODE_MASK_NBITS - * instead of the latter), any change to them will be overwritten - * by kernel. Returns a negative error code or zero. + * @get_link_ksettings: Get various device settings including Ethernet link + * settings. The %cmd and %link_mode_masks_nwords fields should be + * ignored (use %__ETHTOOL_LINK_MODE_MASK_NBITS instead of the latter), + * any change to them will be overwritten by kernel. Returns a negative + * error code or zero. + * @set_link_ksettings: Set various device settings including Ethernet link + * settings. The %cmd and %link_mode_masks_nwords fields should be + * ignored (use %__ETHTOOL_LINK_MODE_MASK_NBITS instead of the latter), + * any change to them will be overwritten by kernel. Returns a negative + * error code or zero. * @get_fecparam: Get the network device Forward Error Correction parameters. * @set_fecparam: Set the network device Forward Error Correction parameters. * @get_ethtool_phy_stats: Return extended statistics about the PHY device. @@ -329,8 +318,6 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, * of the generic netdev features interface. */ struct ethtool_ops { - int (*get_settings)(struct net_device *, struct ethtool_cmd *); - int (*set_settings)(struct net_device *, struct ethtool_cmd *); void (*get_drvinfo)(struct net_device *, struct ethtool_drvinfo *); int (*get_regs_len)(struct net_device *); void (*get_regs)(struct net_device *, struct ethtool_regs *, void *); diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index dc69391d2bba..c8f8e2455bf3 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -91,10 +91,6 @@ * %ETHTOOL_GSET to get the current values before making specific * changes and then applying them with %ETHTOOL_SSET. * - * Drivers that implement set_settings() should validate all fields - * other than @cmd that are not described as read-only or deprecated, - * and must ignore all fields described as read-only. - * * Deprecated fields should be ignored by both users and drivers. */ struct ethtool_cmd { @@ -1800,14 +1796,9 @@ enum ethtool_reset_flags { * rejected. * * Deprecated %ethtool_cmd fields transceiver, maxtxpkt and maxrxpkt - * are not available in %ethtool_link_settings. Until all drivers are - * converted to ignore them or to the new %ethtool_link_settings API, - * for both queries and changes, users should always try - * %ETHTOOL_GLINKSETTINGS first, and if it fails with -ENOTSUPP stick - * only to %ETHTOOL_GSET and %ETHTOOL_SSET consistently. If it - * succeeds, then users should stick to %ETHTOOL_GLINKSETTINGS and - * %ETHTOOL_SLINKSETTINGS (which would support drivers implementing - * either %ethtool_cmd or %ethtool_link_settings). + * are not available in %ethtool_link_settings. These fields will be + * always set to zero in %ETHTOOL_GSET reply and %ETHTOOL_SSET will + * fail if any of them is set to non-zero value. * * Users should assume that all fields not marked read-only are * writable and subject to validation by the driver. They should use diff --git a/net/core/ethtool.c b/net/core/ethtool.c index c9993c6c2fd4..9d4e56d97080 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -539,47 +539,17 @@ struct ethtool_link_usettings { } link_modes; }; -/* Internal kernel helper to query a device ethtool_link_settings. - * - * Backward compatibility note: for compatibility with legacy drivers - * that implement only the ethtool_cmd API, this has to work with both - * drivers implementing get_link_ksettings API and drivers - * implementing get_settings API. When drivers implement get_settings - * and report ethtool_cmd deprecated fields - * (transceiver/maxrxpkt/maxtxpkt), these fields are silently ignored - * because the resulting struct ethtool_link_settings does not report them. - */ +/* Internal kernel helper to query a device ethtool_link_settings. */ int __ethtool_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *link_ksettings) { - int err; - struct ethtool_cmd cmd; - ASSERT_RTNL(); - if (dev->ethtool_ops->get_link_ksettings) { - memset(link_ksettings, 0, sizeof(*link_ksettings)); - return dev->ethtool_ops->get_link_ksettings(dev, - link_ksettings); - } - - /* driver doesn't support %ethtool_link_ksettings API. revert to - * legacy %ethtool_cmd API, unless it's not supported either. - * TODO: remove when ethtool_ops::get_settings disappears internally - */ - if (!dev->ethtool_ops->get_settings) + if (!dev->ethtool_ops->get_link_ksettings) return -EOPNOTSUPP; - memset(&cmd, 0, sizeof(cmd)); - cmd.cmd = ETHTOOL_GSET; - err = dev->ethtool_ops->get_settings(dev, &cmd); - if (err < 0) - return err; - - /* we ignore deprecated fields transceiver/maxrxpkt/maxtxpkt - */ - convert_legacy_settings_to_link_ksettings(link_ksettings, &cmd); - return err; + memset(link_ksettings, 0, sizeof(*link_ksettings)); + return dev->ethtool_ops->get_link_ksettings(dev, link_ksettings); } EXPORT_SYMBOL(__ethtool_get_link_ksettings); @@ -635,16 +605,7 @@ store_link_ksettings_for_user(void __user *to, return 0; } -/* Query device for its ethtool_link_settings. - * - * Backward compatibility note: this function must fail when driver - * does not implement ethtool::get_link_ksettings, even if legacy - * ethtool_ops::get_settings is implemented. This tells new versions - * of ethtool that they should use the legacy API %ETHTOOL_GSET for - * this driver, so that they can correctly access the ethtool_cmd - * deprecated fields (transceiver/maxrxpkt/maxtxpkt), until no driver - * implements ethtool_ops::get_settings anymore. - */ +/* Query device for its ethtool_link_settings. */ static int ethtool_get_link_ksettings(struct net_device *dev, void __user *useraddr) { @@ -652,7 +613,6 @@ static int ethtool_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings link_ksettings; ASSERT_RTNL(); - if (!dev->ethtool_ops->get_link_ksettings) return -EOPNOTSUPP; @@ -699,16 +659,7 @@ static int ethtool_get_link_ksettings(struct net_device *dev, return store_link_ksettings_for_user(useraddr, &link_ksettings); } -/* Update device ethtool_link_settings. - * - * Backward compatibility note: this function must fail when driver - * does not implement ethtool::set_link_ksettings, even if legacy - * ethtool_ops::set_settings is implemented. This tells new versions - * of ethtool that they should use the legacy API %ETHTOOL_SSET for - * this driver, so that they can correctly update the ethtool_cmd - * deprecated fields (transceiver/maxrxpkt/maxtxpkt), until no driver - * implements ethtool_ops::get_settings anymore. - */ +/* Update device ethtool_link_settings. */ static int ethtool_set_link_ksettings(struct net_device *dev, void __user *useraddr) { @@ -746,51 +697,31 @@ static int ethtool_set_link_ksettings(struct net_device *dev, /* Query device for its ethtool_cmd settings. * - * Backward compatibility note: for compatibility with legacy ethtool, - * this has to work with both drivers implementing get_link_ksettings - * API and drivers implementing get_settings API. When drivers - * implement get_link_ksettings and report higher link mode bits, a - * kernel warning is logged once (with name of 1st driver/device) to - * recommend user to upgrade ethtool, but the command is successful - * (only the lower link mode bits reported back to user). + * Backward compatibility note: for compatibility with legacy ethtool, this is + * now implemented via get_link_ksettings. When driver reports higher link mode + * bits, a kernel warning is logged once (with name of 1st driver/device) to + * recommend user to upgrade ethtool, but the command is successful (only the + * lower link mode bits reported back to user). Deprecated fields from + * ethtool_cmd (transceiver/maxrxpkt/maxtxpkt) are always set to zero. */ static int ethtool_get_settings(struct net_device *dev, void __user *useraddr) { + struct ethtool_link_ksettings link_ksettings; struct ethtool_cmd cmd; + int err; ASSERT_RTNL(); + if (!dev->ethtool_ops->get_link_ksettings) + return -EOPNOTSUPP; - if (dev->ethtool_ops->get_link_ksettings) { - /* First, use link_ksettings API if it is supported */ - int err; - struct ethtool_link_ksettings link_ksettings; - - memset(&link_ksettings, 0, sizeof(link_ksettings)); - err = dev->ethtool_ops->get_link_ksettings(dev, - &link_ksettings); - if (err < 0) - return err; - convert_link_ksettings_to_legacy_settings(&cmd, - &link_ksettings); - - /* send a sensible cmd tag back to user */ - cmd.cmd = ETHTOOL_GSET; - } else { - /* driver doesn't support %ethtool_link_ksettings - * API. revert to legacy %ethtool_cmd API, unless it's - * not supported either. - */ - int err; - - if (!dev->ethtool_ops->get_settings) - return -EOPNOTSUPP; + memset(&link_ksettings, 0, sizeof(link_ksettings)); + err = dev->ethtool_ops->get_link_ksettings(dev, &link_ksettings); + if (err < 0) + return err; + convert_link_ksettings_to_legacy_settings(&cmd, &link_ksettings); - memset(&cmd, 0, sizeof(cmd)); - cmd.cmd = ETHTOOL_GSET; - err = dev->ethtool_ops->get_settings(dev, &cmd); - if (err < 0) - return err; - } + /* send a sensible cmd tag back to user */ + cmd.cmd = ETHTOOL_GSET; if (copy_to_user(useraddr, &cmd, sizeof(cmd))) return -EFAULT; @@ -800,48 +731,29 @@ static int ethtool_get_settings(struct net_device *dev, void __user *useraddr) /* Update device link settings with given ethtool_cmd. * - * Backward compatibility note: for compatibility with legacy ethtool, - * this has to work with both drivers implementing set_link_ksettings - * API and drivers implementing set_settings API. When drivers - * implement set_link_ksettings and user's request updates deprecated - * ethtool_cmd fields (transceiver/maxrxpkt/maxtxpkt), a kernel - * warning is logged once (with name of 1st driver/device) to - * recommend user to upgrade ethtool, and the request is rejected. + * Backward compatibility note: for compatibility with legacy ethtool, this is + * now always implemented via set_link_settings. When user's request updates + * deprecated ethtool_cmd fields (transceiver/maxrxpkt/maxtxpkt), a kernel + * warning is logged once (with name of 1st driver/device) to recommend user to + * upgrade ethtool, and the request is rejected. */ static int ethtool_set_settings(struct net_device *dev, void __user *useraddr) { + struct ethtool_link_ksettings link_ksettings; struct ethtool_cmd cmd; ASSERT_RTNL(); if (copy_from_user(&cmd, useraddr, sizeof(cmd))) return -EFAULT; - - /* first, try new %ethtool_link_ksettings API. */ - if (dev->ethtool_ops->set_link_ksettings) { - struct ethtool_link_ksettings link_ksettings; - - if (!convert_legacy_settings_to_link_ksettings(&link_ksettings, - &cmd)) - return -EINVAL; - - link_ksettings.base.cmd = ETHTOOL_SLINKSETTINGS; - link_ksettings.base.link_mode_masks_nwords - = __ETHTOOL_LINK_MODE_MASK_NU32; - return dev->ethtool_ops->set_link_ksettings(dev, - &link_ksettings); - } - - /* legacy %ethtool_cmd API */ - - /* TODO: return -EOPNOTSUPP when ethtool_ops::get_settings - * disappears internally - */ - - if (!dev->ethtool_ops->set_settings) + if (!dev->ethtool_ops->set_link_ksettings) return -EOPNOTSUPP; - return dev->ethtool_ops->set_settings(dev, &cmd); + if (!convert_legacy_settings_to_link_ksettings(&link_ksettings, &cmd)) + return -EINVAL; + link_ksettings.base.link_mode_masks_nwords = + __ETHTOOL_LINK_MODE_MASK_NU32; + return dev->ethtool_ops->set_link_ksettings(dev, &link_ksettings); } static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev, -- cgit v1.2.3 From a4e0109a19c554e44c832958e426303781e1ad30 Mon Sep 17 00:00:00 2001 From: Harshitha Ramamurthy Date: Mon, 20 Aug 2018 08:12:32 -0700 Subject: virtchnl: use u8 type for a field in the virtchnl_filter struct The virtchnl_filter struct has a field called field_flags. A previous commit mistakenly had the type to be a __u8. What we want is for the field to be an unsigned 8 bit value, so let's just use the existing kernel type u8 for that. Signed-off-by: Harshitha Ramamurthy Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- include/linux/avf/virtchnl.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 212b3822d180..b41f7bc958ef 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -573,7 +573,7 @@ struct virtchnl_filter { enum virtchnl_flow_type flow_type; enum virtchnl_action action; u32 action_meta; - __u8 field_flags; + u8 field_flags; }; VIRTCHNL_CHECK_STRUCT_LEN(272, virtchnl_filter); -- cgit v1.2.3 From 4ac695464763ecf696eaba563eff1c2ab994f6d8 Mon Sep 17 00:00:00 2001 From: Eric Long Date: Tue, 28 Aug 2018 19:09:07 +0800 Subject: dmaengine: sprd: Support DMA link-list mode The Spreadtrum DMA can support the link-list transaction mode, which means DMA controller can do transaction one by one automatically once we linked these transaction by link-list register. Signed-off-by: Eric Long Signed-off-by: Baolin Wang Signed-off-by: Vinod Koul --- drivers/dma/sprd-dma.c | 81 ++++++++++++++++++++++++++++++++++++++++---- include/linux/dma/sprd-dma.h | 69 +++++++++++++++++++++++++++++++++++++ 2 files changed, 143 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/dma/sprd-dma.c b/drivers/dma/sprd-dma.c index 55df0d41355b..38d4e4f07c66 100644 --- a/drivers/dma/sprd-dma.c +++ b/drivers/dma/sprd-dma.c @@ -68,6 +68,7 @@ /* SPRD_DMA_CHN_CFG register definition */ #define SPRD_DMA_CHN_EN BIT(0) +#define SPRD_DMA_LINKLIST_EN BIT(4) #define SPRD_DMA_WAIT_BDONE_OFFSET 24 #define SPRD_DMA_DONOT_WAIT_BDONE 1 @@ -103,7 +104,7 @@ #define SPRD_DMA_REQ_MODE_MASK GENMASK(1, 0) #define SPRD_DMA_FIX_SEL_OFFSET 21 #define SPRD_DMA_FIX_EN_OFFSET 20 -#define SPRD_DMA_LLIST_END_OFFSET 19 +#define SPRD_DMA_LLIST_END BIT(19) #define SPRD_DMA_FRG_LEN_MASK GENMASK(16, 0) /* SPRD_DMA_CHN_BLK_LEN register definition */ @@ -164,6 +165,7 @@ struct sprd_dma_desc { struct sprd_dma_chn { struct virt_dma_chan vc; void __iomem *chn_base; + struct sprd_dma_linklist linklist; struct dma_slave_config slave_cfg; u32 chn_num; u32 dev_id; @@ -582,7 +584,8 @@ static int sprd_dma_get_step(enum dma_slave_buswidth buswidth) } static int sprd_dma_fill_desc(struct dma_chan *chan, - struct sprd_dma_desc *sdesc, + struct sprd_dma_chn_hw *hw, + unsigned int sglen, int sg_index, dma_addr_t src, dma_addr_t dst, u32 len, enum dma_transfer_direction dir, unsigned long flags, @@ -590,7 +593,6 @@ static int sprd_dma_fill_desc(struct dma_chan *chan, { struct sprd_dma_dev *sdev = to_sprd_dma_dev(chan); struct sprd_dma_chn *schan = to_sprd_dma_chan(chan); - struct sprd_dma_chn_hw *hw = &sdesc->chn_hw; u32 req_mode = (flags >> SPRD_DMA_REQ_SHIFT) & SPRD_DMA_REQ_MODE_MASK; u32 int_mode = flags & SPRD_DMA_INT_MASK; int src_datawidth, dst_datawidth, src_step, dst_step; @@ -670,12 +672,52 @@ static int sprd_dma_fill_desc(struct dma_chan *chan, temp |= (src_step & SPRD_DMA_TRSF_STEP_MASK) << SPRD_DMA_SRC_TRSF_STEP_OFFSET; hw->trsf_step = temp; + /* link-list configuration */ + if (schan->linklist.phy_addr) { + if (sg_index == sglen - 1) + hw->frg_len |= SPRD_DMA_LLIST_END; + + hw->cfg |= SPRD_DMA_LINKLIST_EN; + + /* link-list index */ + temp = (sg_index + 1) % sglen; + /* Next link-list configuration's physical address offset */ + temp = temp * sizeof(*hw) + SPRD_DMA_CHN_SRC_ADDR; + /* + * Set the link-list pointer point to next link-list + * configuration's physical address. + */ + hw->llist_ptr = schan->linklist.phy_addr + temp; + } else { + hw->llist_ptr = 0; + } + hw->frg_step = 0; hw->src_blk_step = 0; hw->des_blk_step = 0; return 0; } +static int sprd_dma_fill_linklist_desc(struct dma_chan *chan, + unsigned int sglen, int sg_index, + dma_addr_t src, dma_addr_t dst, u32 len, + enum dma_transfer_direction dir, + unsigned long flags, + struct dma_slave_config *slave_cfg) +{ + struct sprd_dma_chn *schan = to_sprd_dma_chan(chan); + struct sprd_dma_chn_hw *hw; + + if (!schan->linklist.virt_addr) + return -EINVAL; + + hw = (struct sprd_dma_chn_hw *)(schan->linklist.virt_addr + + sg_index * sizeof(*hw)); + + return sprd_dma_fill_desc(chan, hw, sglen, sg_index, src, dst, len, + dir, flags, slave_cfg); +} + static struct dma_async_tx_descriptor * sprd_dma_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src, size_t len, unsigned long flags) @@ -744,10 +786,20 @@ sprd_dma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, u32 len = 0; int ret, i; - /* TODO: now we only support one sg for each DMA configuration. */ - if (!is_slave_direction(dir) || sglen > 1) + if (!is_slave_direction(dir)) return NULL; + if (context) { + struct sprd_dma_linklist *ll_cfg = + (struct sprd_dma_linklist *)context; + + schan->linklist.phy_addr = ll_cfg->phy_addr; + schan->linklist.virt_addr = ll_cfg->virt_addr; + } else { + schan->linklist.phy_addr = 0; + schan->linklist.virt_addr = 0; + } + sdesc = kzalloc(sizeof(*sdesc), GFP_NOWAIT); if (!sdesc) return NULL; @@ -762,10 +814,25 @@ sprd_dma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, src = slave_cfg->src_addr; dst = sg_dma_address(sg); } + + /* + * The link-list mode needs at least 2 link-list + * configurations. If there is only one sg, it doesn't + * need to fill the link-list configuration. + */ + if (sglen < 2) + break; + + ret = sprd_dma_fill_linklist_desc(chan, sglen, i, src, dst, len, + dir, flags, slave_cfg); + if (ret) { + kfree(sdesc); + return NULL; + } } - ret = sprd_dma_fill_desc(chan, sdesc, src, dst, len, dir, flags, - slave_cfg); + ret = sprd_dma_fill_desc(chan, &sdesc->chn_hw, 0, 0, src, dst, len, + dir, flags, slave_cfg); if (ret) { kfree(sdesc); return NULL; diff --git a/include/linux/dma/sprd-dma.h b/include/linux/dma/sprd-dma.h index b0115e340fbc..b42b80e52cc2 100644 --- a/include/linux/dma/sprd-dma.h +++ b/include/linux/dma/sprd-dma.h @@ -58,4 +58,73 @@ enum sprd_dma_int_type { SPRD_DMA_CFGERR_INT, }; +/* + * struct sprd_dma_linklist - DMA link-list address structure + * @virt_addr: link-list virtual address to configure link-list node + * @phy_addr: link-list physical address to link DMA transfer + * + * The Spreadtrum DMA controller supports the link-list mode, that means slaves + * can supply several groups configurations (each configuration represents one + * DMA transfer) saved in memory, and DMA controller will link these groups + * configurations by writing the physical address of each configuration into the + * link-list register. + * + * Just as shown below, the link-list pointer register will be pointed to the + * physical address of 'configuration 1', and the 'configuration 1' link-list + * pointer will be pointed to 'configuration 2', and so on. + * Once trigger the DMA transfer, the DMA controller will load 'configuration + * 1' to its registers automatically, after 'configuration 1' transaction is + * done, DMA controller will load 'configuration 2' automatically, until all + * DMA transactions are done. + * + * Note: The last link-list pointer should point to the physical address + * of 'configuration 1', which can avoid DMA controller loads incorrect + * configuration when the last configuration transaction is done. + * + * DMA controller linklist memory + * ====================== ----------------------- + *| | | configuration 1 |<--- + *| DMA controller | ------->| | | + *| | | | | | + *| | | | | | + *| | | | | | + *| linklist pointer reg |---- ----| linklist pointer | | + * ====================== | ----------------------- | + * | | + * | ----------------------- | + * | | configuration 2 | | + * --->| | | + * | | | + * | | | + * | | | + * ----| linklist pointer | | + * | ----------------------- | + * | | + * | ----------------------- | + * | | configuration 3 | | + * --->| | | + * | | | + * | . | | + * . | + * . | + * . | + * | . | + * | ----------------------- | + * | | configuration n | | + * --->| | | + * | | | + * | | | + * | | | + * | linklist pointer |---- + * ----------------------- + * + * To support the link-list mode, DMA slaves should allocate one segment memory + * from always-on IRAM or dma coherent memory to store these groups of DMA + * configuration, and pass the virtual and physical address to DMA controller. + */ +struct sprd_dma_linklist { + unsigned long virt_addr; + phys_addr_t phy_addr; +}; + #endif -- cgit v1.2.3 From f3569fd613f669c95ad187208ad281995f30cc2a Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 7 Aug 2018 14:18:42 -0700 Subject: crypto: shash - Remove VLA usage in unaligned hashing In the quest to remove all stack VLA usage from the kernel[1], this uses the newly defined max alignment to perform unaligned hashing to avoid VLAs, and drops the helper function while adding sanity checks on the resulting buffer sizes. Additionally, the __aligned_largest macro is removed since this helper was the only user. [1] https://lkml.kernel.org/r/CA+55aFzCG-zNmZwX4A2FQpadafLfEzK6CC=qPXydAacU1RqZWA@mail.gmail.com Signed-off-by: Kees Cook Signed-off-by: Herbert Xu --- crypto/shash.c | 27 ++++++++++++++++----------- include/linux/compiler_types.h | 1 - 2 files changed, 16 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/crypto/shash.c b/crypto/shash.c index 86d76b5c626c..d21f04d70dce 100644 --- a/crypto/shash.c +++ b/crypto/shash.c @@ -73,13 +73,6 @@ int crypto_shash_setkey(struct crypto_shash *tfm, const u8 *key, } EXPORT_SYMBOL_GPL(crypto_shash_setkey); -static inline unsigned int shash_align_buffer_size(unsigned len, - unsigned long mask) -{ - typedef u8 __aligned_largest u8_aligned; - return len + (mask & ~(__alignof__(u8_aligned) - 1)); -} - static int shash_update_unaligned(struct shash_desc *desc, const u8 *data, unsigned int len) { @@ -88,11 +81,17 @@ static int shash_update_unaligned(struct shash_desc *desc, const u8 *data, unsigned long alignmask = crypto_shash_alignmask(tfm); unsigned int unaligned_len = alignmask + 1 - ((unsigned long)data & alignmask); - u8 ubuf[shash_align_buffer_size(unaligned_len, alignmask)] - __aligned_largest; + /* + * We cannot count on __aligned() working for large values: + * https://patchwork.kernel.org/patch/9507697/ + */ + u8 ubuf[MAX_ALGAPI_ALIGNMASK * 2]; u8 *buf = PTR_ALIGN(&ubuf[0], alignmask + 1); int err; + if (WARN_ON(buf + unaligned_len > ubuf + sizeof(ubuf))) + return -EINVAL; + if (unaligned_len > len) unaligned_len = len; @@ -124,11 +123,17 @@ static int shash_final_unaligned(struct shash_desc *desc, u8 *out) unsigned long alignmask = crypto_shash_alignmask(tfm); struct shash_alg *shash = crypto_shash_alg(tfm); unsigned int ds = crypto_shash_digestsize(tfm); - u8 ubuf[shash_align_buffer_size(ds, alignmask)] - __aligned_largest; + /* + * We cannot count on __aligned() working for large values: + * https://patchwork.kernel.org/patch/9507697/ + */ + u8 ubuf[MAX_ALGAPI_ALIGNMASK + HASH_MAX_DIGESTSIZE]; u8 *buf = PTR_ALIGN(&ubuf[0], alignmask + 1); int err; + if (WARN_ON(buf + ds > ubuf + sizeof(ubuf))) + return -EINVAL; + err = shash->final(desc, buf); if (err) goto out; diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 3525c179698c..13fee5fe734b 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -198,7 +198,6 @@ struct ftrace_likely_data { */ #define __pure __attribute__((pure)) #define __aligned(x) __attribute__((aligned(x))) -#define __aligned_largest __attribute__((aligned)) #define __printf(a, b) __attribute__((format(printf, a, b))) #define __scanf(a, b) __attribute__((format(scanf, a, b))) #define __maybe_unused __attribute__((unused)) -- cgit v1.2.3 From b76377543b738a6b58b0a7b0a42dd9e16436fee1 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Thu, 30 Aug 2018 11:00:15 -0400 Subject: crc-t10dif: Pick better transform if one becomes available T10 CRC library is linked into the kernel thanks to block and SCSI. The crypto accelerators are typically loaded later as modules and are therefore not available when the T10 CRC library is initialized. Use the crypto notifier facility to trigger a switch to a better algorithm if one becomes available after the initial hash has been registered. Use RCU to protect the original transform while the new one is being set up. Suggested-by: Ard Biesheuvel Signed-off-by: Martin K. Petersen Signed-off-by: Herbert Xu --- include/linux/crc-t10dif.h | 1 + lib/crc-t10dif.c | 46 ++++++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 45 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crc-t10dif.h b/include/linux/crc-t10dif.h index 1fe0cfcdea30..6bb0c0bf357b 100644 --- a/include/linux/crc-t10dif.h +++ b/include/linux/crc-t10dif.h @@ -6,6 +6,7 @@ #define CRC_T10DIF_DIGEST_SIZE 2 #define CRC_T10DIF_BLOCK_SIZE 1 +#define CRC_T10DIF_STRING "crct10dif" extern __u16 crc_t10dif_generic(__u16 crc, const unsigned char *buffer, size_t len); diff --git a/lib/crc-t10dif.c b/lib/crc-t10dif.c index 1ad33e555805..52f577a3868d 100644 --- a/lib/crc-t10dif.c +++ b/lib/crc-t10dif.c @@ -14,10 +14,47 @@ #include #include #include +#include #include +#include -static struct crypto_shash *crct10dif_tfm; +static struct crypto_shash __rcu *crct10dif_tfm; static struct static_key crct10dif_fallback __read_mostly; +DEFINE_MUTEX(crc_t10dif_mutex); + +static int crc_t10dif_rehash(struct notifier_block *self, unsigned long val, void *data) +{ + struct crypto_alg *alg = data; + struct crypto_shash *new, *old; + + if (val != CRYPTO_MSG_ALG_LOADED || + static_key_false(&crct10dif_fallback) || + strncmp(alg->cra_name, CRC_T10DIF_STRING, strlen(CRC_T10DIF_STRING))) + return 0; + + mutex_lock(&crc_t10dif_mutex); + old = rcu_dereference_protected(crct10dif_tfm, + lockdep_is_held(&crc_t10dif_mutex)); + if (!old) { + mutex_unlock(&crc_t10dif_mutex); + return 0; + } + new = crypto_alloc_shash("crct10dif", 0, 0); + if (IS_ERR(new)) { + mutex_unlock(&crc_t10dif_mutex); + return 0; + } + rcu_assign_pointer(crct10dif_tfm, new); + mutex_unlock(&crc_t10dif_mutex); + + synchronize_rcu(); + crypto_free_shash(old); + return 0; +} + +static struct notifier_block crc_t10dif_nb = { + .notifier_call = crc_t10dif_rehash, +}; __u16 crc_t10dif_update(__u16 crc, const unsigned char *buffer, size_t len) { @@ -30,11 +67,14 @@ __u16 crc_t10dif_update(__u16 crc, const unsigned char *buffer, size_t len) if (static_key_false(&crct10dif_fallback)) return crc_t10dif_generic(crc, buffer, len); - desc.shash.tfm = crct10dif_tfm; + rcu_read_lock(); + desc.shash.tfm = rcu_dereference(crct10dif_tfm); desc.shash.flags = 0; *(__u16 *)desc.ctx = crc; err = crypto_shash_update(&desc.shash, buffer, len); + rcu_read_unlock(); + BUG_ON(err); return *(__u16 *)desc.ctx; @@ -49,6 +89,7 @@ EXPORT_SYMBOL(crc_t10dif); static int __init crc_t10dif_mod_init(void) { + crypto_register_notifier(&crc_t10dif_nb); crct10dif_tfm = crypto_alloc_shash("crct10dif", 0, 0); if (IS_ERR(crct10dif_tfm)) { static_key_slow_inc(&crct10dif_fallback); @@ -59,6 +100,7 @@ static int __init crc_t10dif_mod_init(void) static void __exit crc_t10dif_mod_fini(void) { + crypto_unregister_notifier(&crc_t10dif_nb); crypto_free_shash(crct10dif_tfm); } -- cgit v1.2.3 From aa7e80b220f3a543eefbe4b7e2c5d2b73e2e2ef7 Mon Sep 17 00:00:00 2001 From: Moni Shoua Date: Mon, 3 Sep 2018 20:19:28 +0300 Subject: net/mlx5: Fix atomic_mode enum values The field atomic_mode is 4 bits wide and therefore can hold values from 0x0 to 0xf. Remove the unnecessary 20 bit shift that made the values be incorrect. While that, remove unused enum values. Fixes: 57cda166bbe0 ("net/mlx5: Add DCT command interface") Signed-off-by: Moni Shoua Reviewed-by: Artemy Kovalyov Signed-off-by: Leon Romanovsky --- include/linux/mlx5/driver.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 7a452716de4b..d885e9f0e054 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -163,10 +163,7 @@ enum mlx5_dcbx_oper_mode { }; enum mlx5_dct_atomic_mode { - MLX5_ATOMIC_MODE_DCT_OFF = 20, - MLX5_ATOMIC_MODE_DCT_NONE = 0 << MLX5_ATOMIC_MODE_DCT_OFF, - MLX5_ATOMIC_MODE_DCT_IB_COMP = 1 << MLX5_ATOMIC_MODE_DCT_OFF, - MLX5_ATOMIC_MODE_DCT_CX = 2 << MLX5_ATOMIC_MODE_DCT_OFF, + MLX5_ATOMIC_MODE_DCT_CX = 2, }; enum { -- cgit v1.2.3 From 8ce78257965e6cd49720e653867e766ecd38883f Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 28 Aug 2018 14:18:41 +0300 Subject: net/mlx5: Add proper NIC TX steering flow tables support Extend the ability to add steering rules to NIC TX flow tables. For now, we are only adding TX bypass (egress) which is used by the RDMA side. This will allow to shape outgoing traffic and tweak it if needed, for example performing encapsulation or rewriting headers. Signed-off-by: Mark Bloch Reviewed-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 51 +++++++++++++++++------ include/linux/mlx5/device.h | 6 +++ 3 files changed, 46 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 8e01f818021b..28c7301e08f4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -760,8 +760,8 @@ const struct mlx5_flow_cmds *mlx5_fs_cmd_get_default(enum fs_flow_table_type typ case FS_FT_FDB: case FS_FT_SNIFFER_RX: case FS_FT_SNIFFER_TX: - return mlx5_fs_cmd_get_fw_cmds(); case FS_FT_NIC_TX: + return mlx5_fs_cmd_get_fw_cmds(); default: return mlx5_fs_cmd_get_stub_cmds(); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 5624030d2ed4..b7e7eb3535c7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -76,6 +76,14 @@ FS_CAP(flow_table_properties_nic_receive.identified_miss_table_mode), \ FS_CAP(flow_table_properties_nic_receive.flow_table_modify)) +#define FS_CHAINING_CAPS_EGRESS \ + FS_REQUIRED_CAPS( \ + FS_CAP(flow_table_properties_nic_transmit.flow_modify_en), \ + FS_CAP(flow_table_properties_nic_transmit.modify_root), \ + FS_CAP(flow_table_properties_nic_transmit \ + .identified_miss_table_mode), \ + FS_CAP(flow_table_properties_nic_transmit.flow_table_modify)) + #define LEFTOVERS_NUM_LEVELS 1 #define LEFTOVERS_NUM_PRIOS 1 @@ -151,6 +159,17 @@ static struct init_tree_node { } }; +static struct init_tree_node egress_root_fs = { + .type = FS_TYPE_NAMESPACE, + .ar_size = 1, + .children = (struct init_tree_node[]) { + ADD_PRIO(0, MLX5_BY_PASS_NUM_PRIOS, 0, + FS_CHAINING_CAPS_EGRESS, + ADD_NS(ADD_MULTIPLE_PRIO(MLX5_BY_PASS_NUM_PRIOS, + BY_PASS_PRIO_NUM_LEVELS))), + } +}; + enum fs_i_lock_class { FS_LOCK_GRANDPARENT, FS_LOCK_PARENT, @@ -1978,7 +1997,7 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev, { struct mlx5_flow_steering *steering = dev->priv.steering; struct mlx5_flow_root_namespace *root_ns; - int prio; + int prio = 0; struct fs_prio *fs_prio; struct mlx5_flow_namespace *ns; @@ -1998,16 +2017,17 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev, if (steering->sniffer_tx_root_ns) return &steering->sniffer_tx_root_ns->ns; return NULL; - case MLX5_FLOW_NAMESPACE_EGRESS: - if (steering->egress_root_ns) - return &steering->egress_root_ns->ns; - return NULL; default: break; } - root_ns = steering->root_ns; - prio = type; + if (type == MLX5_FLOW_NAMESPACE_EGRESS) { + root_ns = steering->egress_root_ns; + } else { /* Must be NIC RX */ + root_ns = steering->root_ns; + prio = type; + } + if (!root_ns) return NULL; @@ -2523,16 +2543,23 @@ cleanup_root_ns: static int init_egress_root_ns(struct mlx5_flow_steering *steering) { - struct fs_prio *prio; + int err; steering->egress_root_ns = create_root_ns(steering, FS_FT_NIC_TX); if (!steering->egress_root_ns) return -ENOMEM; - /* create 1 prio*/ - prio = fs_create_prio(&steering->egress_root_ns->ns, 0, 1); - return PTR_ERR_OR_ZERO(prio); + err = init_root_tree(steering, &egress_root_fs, + &steering->egress_root_ns->ns.node); + if (err) + goto cleanup; + set_prio_attrs(steering->egress_root_ns); + return 0; +cleanup: + cleanup_root_ns(steering->egress_root_ns); + steering->egress_root_ns = NULL; + return err; } int mlx5_init_fs(struct mlx5_core_dev *dev) @@ -2600,7 +2627,7 @@ int mlx5_init_fs(struct mlx5_core_dev *dev) goto err; } - if (MLX5_IPSEC_DEV(dev)) { + if (MLX5_IPSEC_DEV(dev) || MLX5_CAP_FLOWTABLE_NIC_TX(dev, ft_support)) { err = init_egress_root_ns(steering); if (err) goto err; diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 11fa4e66afc5..f2281e69ab39 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1120,6 +1120,12 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_FLOWTABLE_NIC_RX_MAX(mdev, cap) \ MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_receive.cap) +#define MLX5_CAP_FLOWTABLE_NIC_TX(mdev, cap) \ + MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_transmit.cap) + +#define MLX5_CAP_FLOWTABLE_NIC_TX_MAX(mdev, cap) \ + MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_transmit.cap) + #define MLX5_CAP_FLOWTABLE_SNIFFER_RX(mdev, cap) \ MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive_sniffer.cap) -- cgit v1.2.3 From 90c1d1b8da67330b09893d749401a45328b51704 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 28 Aug 2018 14:18:42 +0300 Subject: net/mlx5: Export modify header alloc/dealloc functions Those functions will be used by the RDMA side to create modify header actions to be attached to flow steering rules via verbs. Signed-off-by: Mark Bloch Reviewed-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c | 2 ++ drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h | 5 ----- include/linux/mlx5/fs.h | 6 ++++++ 3 files changed, 8 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 28c7301e08f4..37bea30b68ac 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -702,6 +702,7 @@ int mlx5_modify_header_alloc(struct mlx5_core_dev *dev, kfree(in); return err; } +EXPORT_SYMBOL(mlx5_modify_header_alloc); void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev, u32 modify_header_id) { @@ -716,6 +717,7 @@ void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev, u32 modify_header_id) mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); } +EXPORT_SYMBOL(mlx5_modify_header_dealloc); static const struct mlx5_flow_cmds mlx5_flow_cmds = { .create_flow_table = mlx5_cmd_create_flow_table, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index b4134fa0bba3..649d1bd83a1a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -176,11 +176,6 @@ int mlx5_encap_alloc(struct mlx5_core_dev *dev, u32 *encap_id); void mlx5_encap_dealloc(struct mlx5_core_dev *dev, u32 encap_id); -int mlx5_modify_header_alloc(struct mlx5_core_dev *dev, - u8 namespace, u8 num_actions, - void *modify_actions, u32 *modify_header_id); -void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev, u32 modify_header_id); - bool mlx5_lag_intf_add(struct mlx5_interface *intf, struct mlx5_priv *priv); int mlx5_query_mtpps(struct mlx5_core_dev *dev, u32 *mtpps, u32 mtpps_size); diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 804516e4f483..0cbf4d5cb1ab 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -196,4 +196,10 @@ int mlx5_fc_query(struct mlx5_core_dev *dev, struct mlx5_fc *counter, int mlx5_fs_add_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn); int mlx5_fs_remove_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn); +int mlx5_modify_header_alloc(struct mlx5_core_dev *dev, + u8 namespace, u8 num_actions, + void *modify_actions, u32 *modify_header_id); +void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev, + u32 modify_header_id); + #endif -- cgit v1.2.3 From 61444b458b01c95e55003d6f0b4d4c936fde51cb Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 28 Aug 2018 14:18:44 +0300 Subject: net/mlx5: Break encap/decap into two separated flow table creation flags Today we are able to attach encap and decap actions only to the FDB. In preparation to enable those actions on the NIC flow tables, break the single flag into two. Those flags control whatever a decap or encap operations can be attached to the flow table created. For FDB, if encapsulation is required, we set both of them. Signed-off-by: Mark Bloch Reviewed-by: Saeed Mahameed Reviewed-by: Or Gerlitz Signed-off-by: Leon Romanovsky --- drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 3 ++- drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c | 7 ++++--- include/linux/mlx5/fs.h | 3 ++- 3 files changed, 8 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index f72b5c9dcfe9..ff21807a0c4b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -529,7 +529,8 @@ static int esw_create_offloads_fast_fdb_table(struct mlx5_eswitch *esw) esw_size >>= 1; if (esw->offloads.encap != DEVLINK_ESWITCH_ENCAP_MODE_NONE) - flags |= MLX5_FLOW_TABLE_TUNNEL_EN; + flags |= (MLX5_FLOW_TABLE_TUNNEL_EN_ENCAP | + MLX5_FLOW_TABLE_TUNNEL_EN_DECAP); fdb = mlx5_create_auto_grouped_flow_table(root_ns, FDB_FAST_PATH, esw_size, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 9ae777e56529..1698f325a21e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -152,7 +152,8 @@ static int mlx5_cmd_create_flow_table(struct mlx5_core_dev *dev, struct mlx5_flow_table *next_ft, unsigned int *table_id, u32 flags) { - int en_encap_decap = !!(flags & MLX5_FLOW_TABLE_TUNNEL_EN); + int en_encap = !!(flags & MLX5_FLOW_TABLE_TUNNEL_EN_ENCAP); + int en_decap = !!(flags & MLX5_FLOW_TABLE_TUNNEL_EN_DECAP); u32 out[MLX5_ST_SZ_DW(create_flow_table_out)] = {0}; u32 in[MLX5_ST_SZ_DW(create_flow_table_in)] = {0}; int err; @@ -169,9 +170,9 @@ static int mlx5_cmd_create_flow_table(struct mlx5_core_dev *dev, } MLX5_SET(create_flow_table_in, in, flow_table_context.decap_en, - en_encap_decap); + en_decap); MLX5_SET(create_flow_table_in, in, flow_table_context.encap_en, - en_encap_decap); + en_encap); switch (op_mod) { case FS_FT_OP_MOD_NORMAL: diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 0cbf4d5cb1ab..0194e62ad66a 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -45,7 +45,8 @@ enum { }; enum { - MLX5_FLOW_TABLE_TUNNEL_EN = BIT(0), + MLX5_FLOW_TABLE_TUNNEL_EN_ENCAP = BIT(0), + MLX5_FLOW_TABLE_TUNNEL_EN_DECAP = BIT(1), }; #define LEFTOVERS_RULE_NUM 2 -- cgit v1.2.3 From e0e7a3861b6c6b673dc93e291ef11cf5e746b0c2 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 28 Aug 2018 14:18:45 +0300 Subject: net/mlx5: Move header encap type to IFC header file Those bits are hardware specification and should be defined in the IFC header file. Signed-off-by: Mark Bloch Reviewed-by: Or Gerlitz Reviewed-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 5 ----- include/linux/mlx5/mlx5_ifc.h | 5 +++++ 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 9131a1376e7d..240a6fe1587e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -100,11 +100,6 @@ struct mlx5e_tc_flow_parse_attr { int mirred_ifindex; }; -enum { - MLX5_HEADER_TYPE_VXLAN = 0x0, - MLX5_HEADER_TYPE_NVGRE = 0x1, -}; - #define MLX5E_TC_TABLE_NUM_GROUPS 4 #define MLX5E_TC_TABLE_MAX_GROUP_SIZE BIT(16) diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index f043d65b9bac..bd725e0924e5 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -4848,6 +4848,11 @@ struct mlx5_ifc_alloc_encap_header_out_bits { u8 reserved_at_60[0x20]; }; +enum { + MLX5_HEADER_TYPE_VXLAN = 0x0, + MLX5_HEADER_TYPE_NVGRE = 0x1, +}; + struct mlx5_ifc_alloc_encap_header_in_bits { u8 opcode[0x10]; u8 reserved_at_10[0x10]; -- cgit v1.2.3 From 60786f0987c0d9354e5330ee11615b16cdb448fe Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 28 Aug 2018 14:18:46 +0300 Subject: {net, RDMA}/mlx5: Rename encap to reformat packet Renames all encap mlx5_{core,ib} code to use the new naming of packet reformat. This change doesn't introduce any function change and is needed to properly reflect the operation being done by this action. For example not only can we encapsulate a packet, but also decapsulate it. Signed-off-by: Mark Bloch Reviewed-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/devx.c | 6 +-- drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 8 +-- .../mellanox/mlx5/core/diag/fs_tracepoint.h | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 43 ++++++++------- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 2 +- .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 8 +-- drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c | 63 ++++++++++++---------- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 2 +- .../net/ethernet/mellanox/mlx5/core/mlx5_core.h | 13 ++--- include/linux/mlx5/fs.h | 4 +- include/linux/mlx5/mlx5_ifc.h | 50 ++++++++--------- 11 files changed, 107 insertions(+), 94 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index ac116d63e466..25dafa4ff6ca 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -284,7 +284,7 @@ static bool devx_is_obj_create_cmd(const void *in) case MLX5_CMD_OP_CREATE_FLOW_TABLE: case MLX5_CMD_OP_CREATE_FLOW_GROUP: case MLX5_CMD_OP_ALLOC_FLOW_COUNTER: - case MLX5_CMD_OP_ALLOC_ENCAP_HEADER: + case MLX5_CMD_OP_ALLOC_PACKET_REFORMAT_CONTEXT: case MLX5_CMD_OP_ALLOC_MODIFY_HEADER_CONTEXT: case MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT: case MLX5_CMD_OP_ADD_VXLAN_UDP_DPORT: @@ -627,9 +627,9 @@ static void devx_obj_build_destroy_cmd(void *in, void *out, void *din, MLX5_SET(general_obj_in_cmd_hdr, din, opcode, MLX5_CMD_OP_DEALLOC_FLOW_COUNTER); break; - case MLX5_CMD_OP_ALLOC_ENCAP_HEADER: + case MLX5_CMD_OP_ALLOC_PACKET_REFORMAT_CONTEXT: MLX5_SET(general_obj_in_cmd_hdr, din, opcode, - MLX5_CMD_OP_DEALLOC_ENCAP_HEADER); + MLX5_CMD_OP_DEALLOC_PACKET_REFORMAT_CONTEXT); break; case MLX5_CMD_OP_ALLOC_MODIFY_HEADER_CONTEXT: MLX5_SET(general_obj_in_cmd_hdr, din, opcode, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 6f589b4d33d9..39750fca371d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -308,7 +308,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op, case MLX5_CMD_OP_MODIFY_FLOW_TABLE: case MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY: case MLX5_CMD_OP_SET_FLOW_TABLE_ROOT: - case MLX5_CMD_OP_DEALLOC_ENCAP_HEADER: + case MLX5_CMD_OP_DEALLOC_PACKET_REFORMAT_CONTEXT: case MLX5_CMD_OP_DEALLOC_MODIFY_HEADER_CONTEXT: case MLX5_CMD_OP_FPGA_DESTROY_QP: case MLX5_CMD_OP_DESTROY_GENERAL_OBJECT: @@ -427,7 +427,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op, case MLX5_CMD_OP_QUERY_FLOW_TABLE_ENTRY: case MLX5_CMD_OP_ALLOC_FLOW_COUNTER: case MLX5_CMD_OP_QUERY_FLOW_COUNTER: - case MLX5_CMD_OP_ALLOC_ENCAP_HEADER: + case MLX5_CMD_OP_ALLOC_PACKET_REFORMAT_CONTEXT: case MLX5_CMD_OP_ALLOC_MODIFY_HEADER_CONTEXT: case MLX5_CMD_OP_FPGA_CREATE_QP: case MLX5_CMD_OP_FPGA_MODIFY_QP: @@ -601,8 +601,8 @@ const char *mlx5_command_str(int command) MLX5_COMMAND_STR_CASE(DEALLOC_FLOW_COUNTER); MLX5_COMMAND_STR_CASE(QUERY_FLOW_COUNTER); MLX5_COMMAND_STR_CASE(MODIFY_FLOW_TABLE); - MLX5_COMMAND_STR_CASE(ALLOC_ENCAP_HEADER); - MLX5_COMMAND_STR_CASE(DEALLOC_ENCAP_HEADER); + MLX5_COMMAND_STR_CASE(ALLOC_PACKET_REFORMAT_CONTEXT); + MLX5_COMMAND_STR_CASE(DEALLOC_PACKET_REFORMAT_CONTEXT); MLX5_COMMAND_STR_CASE(ALLOC_MODIFY_HEADER_CONTEXT); MLX5_COMMAND_STR_CASE(DEALLOC_MODIFY_HEADER_CONTEXT); MLX5_COMMAND_STR_CASE(FPGA_CREATE_QP); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h index 0240aee9189e..e83dda441a81 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h @@ -133,7 +133,7 @@ TRACE_EVENT(mlx5_fs_del_fg, {MLX5_FLOW_CONTEXT_ACTION_DROP, "DROP"},\ {MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, "FWD"},\ {MLX5_FLOW_CONTEXT_ACTION_COUNT, "CNT"},\ - {MLX5_FLOW_CONTEXT_ACTION_ENCAP, "ENCAP"},\ + {MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT, "REFORMAT"},\ {MLX5_FLOW_CONTEXT_ACTION_DECAP, "DECAP"},\ {MLX5_FLOW_CONTEXT_ACTION_MOD_HDR, "MOD_HDR"},\ {MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH, "VLAN_PUSH"},\ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 240a6fe1587e..3df8f2b90908 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -681,7 +681,7 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, .action = attr->action, .has_flow_tag = true, .flow_tag = attr->flow_tag, - .encap_id = 0, + .reformat_id = 0, }; struct mlx5_fc *counter = NULL; struct mlx5_flow_handle *rule; @@ -829,7 +829,7 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, struct mlx5e_priv *out_priv; int err; - if (attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP) { + if (attr->action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT) { out_dev = __dev_get_by_index(dev_net(priv->netdev), attr->parse_attr->mirred_ifindex); err = mlx5e_attach_encap(priv, &parse_attr->tun_info, @@ -885,7 +885,7 @@ err_add_rule: err_mod_hdr: mlx5_eswitch_del_vlan_action(esw, attr); err_add_vlan: - if (attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP) + if (attr->action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT) mlx5e_detach_encap(priv, flow); err_attach_encap: return rule; @@ -906,7 +906,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, mlx5_eswitch_del_vlan_action(esw, attr); - if (attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP) { + if (attr->action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT) { mlx5e_detach_encap(priv, flow); kvfree(attr->parse_attr); } @@ -923,9 +923,9 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow; int err; - err = mlx5_encap_alloc(priv->mdev, e->tunnel_type, - e->encap_size, e->encap_header, - &e->encap_id); + err = mlx5_packet_reformat_alloc(priv->mdev, e->tunnel_type, + e->encap_size, e->encap_header, + &e->encap_id); if (err) { mlx5_core_warn(priv->mdev, "Failed to offload cached encapsulation header, %d\n", err); @@ -979,7 +979,7 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv, if (e->flags & MLX5_ENCAP_ENTRY_VALID) { e->flags &= ~MLX5_ENCAP_ENTRY_VALID; - mlx5_encap_dealloc(priv->mdev, e->encap_id); + mlx5_packet_reformat_dealloc(priv->mdev, e->encap_id); } } @@ -1048,7 +1048,7 @@ static void mlx5e_detach_encap(struct mlx5e_priv *priv, mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e); if (e->flags & MLX5_ENCAP_ENTRY_VALID) - mlx5_encap_dealloc(priv->mdev, e->encap_id); + mlx5_packet_reformat_dealloc(priv->mdev, e->encap_id); hash_del_rcu(&e->encap_hlist); kfree(e->encap_header); @@ -2323,7 +2323,7 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv, return -ENOMEM; switch (e->tunnel_type) { - case MLX5_HEADER_TYPE_VXLAN: + case MLX5_REFORMAT_TYPE_L2_TO_VXLAN: fl4.flowi4_proto = IPPROTO_UDP; fl4.fl4_dport = tun_key->tp_dst; break; @@ -2367,7 +2367,7 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv, read_unlock_bh(&n->lock); switch (e->tunnel_type) { - case MLX5_HEADER_TYPE_VXLAN: + case MLX5_REFORMAT_TYPE_L2_TO_VXLAN: gen_vxlan_header_ipv4(out_dev, encap_header, ipv4_encap_size, e->h_dest, tos, ttl, fl4.daddr, @@ -2387,8 +2387,9 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv, goto out; } - err = mlx5_encap_alloc(priv->mdev, e->tunnel_type, - ipv4_encap_size, encap_header, &e->encap_id); + err = mlx5_packet_reformat_alloc(priv->mdev, e->tunnel_type, + ipv4_encap_size, encap_header, + &e->encap_id); if (err) goto destroy_neigh_entry; @@ -2432,7 +2433,7 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv, return -ENOMEM; switch (e->tunnel_type) { - case MLX5_HEADER_TYPE_VXLAN: + case MLX5_REFORMAT_TYPE_L2_TO_VXLAN: fl6.flowi6_proto = IPPROTO_UDP; fl6.fl6_dport = tun_key->tp_dst; break; @@ -2476,7 +2477,7 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv, read_unlock_bh(&n->lock); switch (e->tunnel_type) { - case MLX5_HEADER_TYPE_VXLAN: + case MLX5_REFORMAT_TYPE_L2_TO_VXLAN: gen_vxlan_header_ipv6(out_dev, encap_header, ipv6_encap_size, e->h_dest, tos, ttl, &fl6.daddr, @@ -2497,8 +2498,9 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv, goto out; } - err = mlx5_encap_alloc(priv->mdev, e->tunnel_type, - ipv6_encap_size, encap_header, &e->encap_id); + err = mlx5_packet_reformat_alloc(priv->mdev, e->tunnel_type, + ipv6_encap_size, encap_header, + &e->encap_id); if (err) goto destroy_neigh_entry; @@ -2546,7 +2548,7 @@ vxlan_encap_offload_err: if (mlx5_vxlan_lookup_port(priv->mdev->vxlan, be16_to_cpu(key->tp_dst)) && MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap)) { - tunnel_type = MLX5_HEADER_TYPE_VXLAN; + tunnel_type = MLX5_REFORMAT_TYPE_L2_TO_VXLAN; } else { netdev_warn(priv->netdev, "%d isn't an offloaded vxlan udp dport\n", be16_to_cpu(key->tp_dst)); @@ -2721,7 +2723,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, parse_attr->mirred_ifindex = out_dev->ifindex; parse_attr->tun_info = *info; attr->parse_attr = parse_attr; - action |= MLX5_FLOW_CONTEXT_ACTION_ENCAP | + action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT | MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_COUNT; /* attr->out_rep is resolved when we handle encap */ @@ -2867,7 +2869,8 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, flow->flags |= MLX5E_TC_FLOW_OFFLOADED; if (!(flow->flags & MLX5E_TC_FLOW_ESWITCH) || - !(flow->esw_attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP)) + !(flow->esw_attr->action & + MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT)) kvfree(parse_attr); err = rhashtable_insert_fast(tc_ht, &flow->node, tc_ht_params); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 2b252cde5cc2..525b7e43b298 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1746,7 +1746,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) esw->enabled_vports = 0; esw->mode = SRIOV_NONE; esw->offloads.inline_mode = MLX5_INLINE_MODE_NONE; - if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, encap) && + if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, reformat) && MLX5_CAP_ESW_FLOWTABLE_FDB(dev, decap)) esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_BASIC; else diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index ff21807a0c4b..00ec6dd72080 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -127,8 +127,8 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) flow_act.modify_id = attr->mod_hdr_id; - if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_ENCAP) - flow_act.encap_id = attr->encap_id; + if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT) + flow_act.reformat_id = attr->encap_id; rule = mlx5_add_flow_rules(ft, spec, &flow_act, dest, i); if (IS_ERR(rule)) @@ -529,7 +529,7 @@ static int esw_create_offloads_fast_fdb_table(struct mlx5_eswitch *esw) esw_size >>= 1; if (esw->offloads.encap != DEVLINK_ESWITCH_ENCAP_MODE_NONE) - flags |= (MLX5_FLOW_TABLE_TUNNEL_EN_ENCAP | + flags |= (MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT | MLX5_FLOW_TABLE_TUNNEL_EN_DECAP); fdb = mlx5_create_auto_grouped_flow_table(root_ns, FDB_FAST_PATH, @@ -1245,7 +1245,7 @@ int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, u8 encap) return err; if (encap != DEVLINK_ESWITCH_ENCAP_MODE_NONE && - (!MLX5_CAP_ESW_FLOWTABLE_FDB(dev, encap) || + (!MLX5_CAP_ESW_FLOWTABLE_FDB(dev, reformat) || !MLX5_CAP_ESW_FLOWTABLE_FDB(dev, decap))) return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 1698f325a21e..4539b709db20 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -152,7 +152,7 @@ static int mlx5_cmd_create_flow_table(struct mlx5_core_dev *dev, struct mlx5_flow_table *next_ft, unsigned int *table_id, u32 flags) { - int en_encap = !!(flags & MLX5_FLOW_TABLE_TUNNEL_EN_ENCAP); + int en_encap = !!(flags & MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT); int en_decap = !!(flags & MLX5_FLOW_TABLE_TUNNEL_EN_DECAP); u32 out[MLX5_ST_SZ_DW(create_flow_table_out)] = {0}; u32 in[MLX5_ST_SZ_DW(create_flow_table_in)] = {0}; @@ -171,7 +171,7 @@ static int mlx5_cmd_create_flow_table(struct mlx5_core_dev *dev, MLX5_SET(create_flow_table_in, in, flow_table_context.decap_en, en_decap); - MLX5_SET(create_flow_table_in, in, flow_table_context.encap_en, + MLX5_SET(create_flow_table_in, in, flow_table_context.reformat_en, en_encap); switch (op_mod) { @@ -344,7 +344,8 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, MLX5_SET(flow_context, in_flow_context, flow_tag, fte->action.flow_tag); MLX5_SET(flow_context, in_flow_context, action, fte->action.action); - MLX5_SET(flow_context, in_flow_context, encap_id, fte->action.encap_id); + MLX5_SET(flow_context, in_flow_context, packet_reformat_id, + fte->action.reformat_id); MLX5_SET(flow_context, in_flow_context, modify_header_id, fte->action.modify_id); @@ -595,16 +596,16 @@ void mlx5_cmd_fc_bulk_get(struct mlx5_core_dev *dev, *bytes = MLX5_GET64(traffic_counter, stats, octets); } -int mlx5_encap_alloc(struct mlx5_core_dev *dev, - int header_type, - size_t size, - void *encap_header, - u32 *encap_id) +int mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev, + int reformat_type, + size_t size, + void *reformat_data, + u32 *packet_reformat_id) { int max_encap_size = MLX5_CAP_ESW(dev, max_encap_header_size); - u32 out[MLX5_ST_SZ_DW(alloc_encap_header_out)]; - void *encap_header_in; - void *header; + u32 out[MLX5_ST_SZ_DW(alloc_packet_reformat_context_out)]; + void *packet_reformat_context_in; + void *reformat; int inlen; int err; u32 *in; @@ -615,39 +616,47 @@ int mlx5_encap_alloc(struct mlx5_core_dev *dev, return -EINVAL; } - in = kzalloc(MLX5_ST_SZ_BYTES(alloc_encap_header_in) + size, + in = kzalloc(MLX5_ST_SZ_BYTES(alloc_packet_reformat_context_in) + size, GFP_KERNEL); if (!in) return -ENOMEM; - encap_header_in = MLX5_ADDR_OF(alloc_encap_header_in, in, encap_header); - header = MLX5_ADDR_OF(encap_header_in, encap_header_in, encap_header); - inlen = header - (void *)in + size; + packet_reformat_context_in = MLX5_ADDR_OF(alloc_packet_reformat_context_in, + in, packet_reformat_context); + reformat = MLX5_ADDR_OF(packet_reformat_context_in, + packet_reformat_context_in, + reformat_data); + inlen = reformat - (void *)in + size; memset(in, 0, inlen); - MLX5_SET(alloc_encap_header_in, in, opcode, - MLX5_CMD_OP_ALLOC_ENCAP_HEADER); - MLX5_SET(encap_header_in, encap_header_in, encap_header_size, size); - MLX5_SET(encap_header_in, encap_header_in, header_type, header_type); - memcpy(header, encap_header, size); + MLX5_SET(alloc_packet_reformat_context_in, in, opcode, + MLX5_CMD_OP_ALLOC_PACKET_REFORMAT_CONTEXT); + MLX5_SET(packet_reformat_context_in, packet_reformat_context_in, + reformat_data_size, size); + MLX5_SET(packet_reformat_context_in, packet_reformat_context_in, + reformat_type, reformat_type); + memcpy(reformat, reformat_data, size); memset(out, 0, sizeof(out)); err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out)); - *encap_id = MLX5_GET(alloc_encap_header_out, out, encap_id); + *packet_reformat_id = MLX5_GET(alloc_packet_reformat_context_out, + out, packet_reformat_id); kfree(in); return err; } -void mlx5_encap_dealloc(struct mlx5_core_dev *dev, u32 encap_id) +void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev, + u32 packet_reformat_id) { - u32 in[MLX5_ST_SZ_DW(dealloc_encap_header_in)]; - u32 out[MLX5_ST_SZ_DW(dealloc_encap_header_out)]; + u32 in[MLX5_ST_SZ_DW(dealloc_packet_reformat_context_in)]; + u32 out[MLX5_ST_SZ_DW(dealloc_packet_reformat_context_out)]; memset(in, 0, sizeof(in)); - MLX5_SET(dealloc_encap_header_in, in, opcode, - MLX5_CMD_OP_DEALLOC_ENCAP_HEADER); - MLX5_SET(dealloc_encap_header_in, in, encap_id, encap_id); + MLX5_SET(dealloc_packet_reformat_context_in, in, opcode, + MLX5_CMD_OP_DEALLOC_PACKET_REFORMAT_CONTEXT); + MLX5_SET(dealloc_packet_reformat_context_in, in, packet_reformat_id, + packet_reformat_id); mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index b7e7eb3535c7..d2b162cfe86b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1407,7 +1407,7 @@ static bool check_conflicting_actions(u32 action1, u32 action2) return false; if (xored_actions & (MLX5_FLOW_CONTEXT_ACTION_DROP | - MLX5_FLOW_CONTEXT_ACTION_ENCAP | + MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT | MLX5_FLOW_CONTEXT_ACTION_DECAP | MLX5_FLOW_CONTEXT_ACTION_MOD_HDR | MLX5_FLOW_CONTEXT_ACTION_VLAN_POP | diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 649d1bd83a1a..f3c8f51cc9c2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -169,12 +169,13 @@ struct mlx5_core_dev *mlx5_get_next_phys_dev(struct mlx5_core_dev *dev); void mlx5_dev_list_lock(void); void mlx5_dev_list_unlock(void); int mlx5_dev_list_trylock(void); -int mlx5_encap_alloc(struct mlx5_core_dev *dev, - int header_type, - size_t size, - void *encap_header, - u32 *encap_id); -void mlx5_encap_dealloc(struct mlx5_core_dev *dev, u32 encap_id); +int mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev, + int reformat_type, + size_t size, + void *reformat_data, + u32 *packet_reformat_id); +void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev, + u32 packet_reformat_id); bool mlx5_lag_intf_add(struct mlx5_interface *intf, struct mlx5_priv *priv); diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 0194e62ad66a..37d0c08d0966 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -45,7 +45,7 @@ enum { }; enum { - MLX5_FLOW_TABLE_TUNNEL_EN_ENCAP = BIT(0), + MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT = BIT(0), MLX5_FLOW_TABLE_TUNNEL_EN_DECAP = BIT(1), }; @@ -160,7 +160,7 @@ struct mlx5_flow_act { u32 action; bool has_flow_tag; u32 flow_tag; - u32 encap_id; + u32 reformat_id; u32 modify_id; uintptr_t esp_id; struct mlx5_fs_vlan vlan[MLX5_FS_VLAN_DEPTH]; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index bd725e0924e5..c79eaae28e59 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -243,8 +243,8 @@ enum { MLX5_CMD_OP_DEALLOC_FLOW_COUNTER = 0x93a, MLX5_CMD_OP_QUERY_FLOW_COUNTER = 0x93b, MLX5_CMD_OP_MODIFY_FLOW_TABLE = 0x93c, - MLX5_CMD_OP_ALLOC_ENCAP_HEADER = 0x93d, - MLX5_CMD_OP_DEALLOC_ENCAP_HEADER = 0x93e, + MLX5_CMD_OP_ALLOC_PACKET_REFORMAT_CONTEXT = 0x93d, + MLX5_CMD_OP_DEALLOC_PACKET_REFORMAT_CONTEXT = 0x93e, MLX5_CMD_OP_ALLOC_MODIFY_HEADER_CONTEXT = 0x940, MLX5_CMD_OP_DEALLOC_MODIFY_HEADER_CONTEXT = 0x941, MLX5_CMD_OP_QUERY_MODIFY_HEADER_CONTEXT = 0x942, @@ -336,7 +336,7 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 modify_root[0x1]; u8 identified_miss_table_mode[0x1]; u8 flow_table_modify[0x1]; - u8 encap[0x1]; + u8 reformat[0x1]; u8 decap[0x1]; u8 reserved_at_9[0x1]; u8 pop_vlan[0x1]; @@ -599,7 +599,7 @@ struct mlx5_ifc_e_switch_cap_bits { u8 vxlan_encap_decap[0x1]; u8 nvgre_encap_decap[0x1]; u8 reserved_at_22[0x9]; - u8 log_max_encap_headers[0x5]; + u8 log_max_packet_reformat_context[0x5]; u8 reserved_2b[0x6]; u8 max_encap_header_size[0xa]; @@ -2394,7 +2394,7 @@ enum { MLX5_FLOW_CONTEXT_ACTION_DROP = 0x2, MLX5_FLOW_CONTEXT_ACTION_FWD_DEST = 0x4, MLX5_FLOW_CONTEXT_ACTION_COUNT = 0x8, - MLX5_FLOW_CONTEXT_ACTION_ENCAP = 0x10, + MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT = 0x10, MLX5_FLOW_CONTEXT_ACTION_DECAP = 0x20, MLX5_FLOW_CONTEXT_ACTION_MOD_HDR = 0x40, MLX5_FLOW_CONTEXT_ACTION_VLAN_POP = 0x80, @@ -2427,7 +2427,7 @@ struct mlx5_ifc_flow_context_bits { u8 reserved_at_a0[0x8]; u8 flow_counter_list_size[0x18]; - u8 encap_id[0x20]; + u8 packet_reformat_id[0x20]; u8 modify_header_id[0x20]; @@ -4802,19 +4802,19 @@ struct mlx5_ifc_query_eq_in_bits { u8 reserved_at_60[0x20]; }; -struct mlx5_ifc_encap_header_in_bits { +struct mlx5_ifc_packet_reformat_context_in_bits { u8 reserved_at_0[0x5]; - u8 header_type[0x3]; + u8 reformat_type[0x3]; u8 reserved_at_8[0xe]; - u8 encap_header_size[0xa]; + u8 reformat_data_size[0xa]; u8 reserved_at_20[0x10]; - u8 encap_header[2][0x8]; + u8 reformat_data[2][0x8]; - u8 more_encap_header[0][0x8]; + u8 more_reformat_data[0][0x8]; }; -struct mlx5_ifc_query_encap_header_out_bits { +struct mlx5_ifc_query_packet_reformat_context_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; @@ -4822,38 +4822,38 @@ struct mlx5_ifc_query_encap_header_out_bits { u8 reserved_at_40[0xa0]; - struct mlx5_ifc_encap_header_in_bits encap_header[0]; + struct mlx5_ifc_packet_reformat_context_in_bits packet_reformat_context[0]; }; -struct mlx5_ifc_query_encap_header_in_bits { +struct mlx5_ifc_query_packet_reformat_context_in_bits { u8 opcode[0x10]; u8 reserved_at_10[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 encap_id[0x20]; + u8 packet_reformat_id[0x20]; u8 reserved_at_60[0xa0]; }; -struct mlx5_ifc_alloc_encap_header_out_bits { +struct mlx5_ifc_alloc_packet_reformat_context_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 encap_id[0x20]; + u8 packet_reformat_id[0x20]; u8 reserved_at_60[0x20]; }; enum { - MLX5_HEADER_TYPE_VXLAN = 0x0, - MLX5_HEADER_TYPE_NVGRE = 0x1, + MLX5_REFORMAT_TYPE_L2_TO_VXLAN = 0x0, + MLX5_REFORMAT_TYPE_L2_TO_NVGRE = 0x1, }; -struct mlx5_ifc_alloc_encap_header_in_bits { +struct mlx5_ifc_alloc_packet_reformat_context_in_bits { u8 opcode[0x10]; u8 reserved_at_10[0x10]; @@ -4862,10 +4862,10 @@ struct mlx5_ifc_alloc_encap_header_in_bits { u8 reserved_at_40[0xa0]; - struct mlx5_ifc_encap_header_in_bits encap_header; + struct mlx5_ifc_packet_reformat_context_in_bits packet_reformat_context; }; -struct mlx5_ifc_dealloc_encap_header_out_bits { +struct mlx5_ifc_dealloc_packet_reformat_context_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; @@ -4874,14 +4874,14 @@ struct mlx5_ifc_dealloc_encap_header_out_bits { u8 reserved_at_40[0x40]; }; -struct mlx5_ifc_dealloc_encap_header_in_bits { +struct mlx5_ifc_dealloc_packet_reformat_context_in_bits { u8 opcode[0x10]; u8 reserved_at_10[0x10]; u8 reserved_20[0x10]; u8 op_mod[0x10]; - u8 encap_id[0x20]; + u8 packet_reformat_id[0x20]; u8 reserved_60[0x20]; }; @@ -6983,7 +6983,7 @@ struct mlx5_ifc_create_flow_table_out_bits { }; struct mlx5_ifc_flow_table_context_bits { - u8 encap_en[0x1]; + u8 reformat_en[0x1]; u8 decap_en[0x1]; u8 reserved_at_2[0x2]; u8 table_miss_action[0x4]; -- cgit v1.2.3 From bea4e1f6c6c5744d467ebf8b0699f5e391835130 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 28 Aug 2018 14:18:47 +0300 Subject: net/mlx5: Expose new packet reformat capabilities Expose new abilities when creating a packet reformat context. The new types which can be created are: MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL: Ability to create generic encap operation to be done by the HW. MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2: Ability to create generic decap operation where the inner packet doesn't contain L2. MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL: Ability to create generic encap operation to be done by the HW. The L2 of the original packet is dropped. Signed-off-by: Mark Bloch Reviewed-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index c79eaae28e59..3a4a2e0567e9 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -344,8 +344,12 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 reserved_at_c[0x1]; u8 pop_vlan_2[0x1]; u8 push_vlan_2[0x1]; - u8 reserved_at_f[0x11]; - + u8 reformat_and_vlan_action[0x1]; + u8 reserved_at_10[0x2]; + u8 reformat_l3_tunnel_to_l2[0x1]; + u8 reformat_l2_to_l3_tunnel[0x1]; + u8 reformat_and_modify_action[0x1]; + u8 reserved_at_14[0xb]; u8 reserved_at_20[0x2]; u8 log_max_ft_size[0x6]; u8 log_max_modify_header_context[0x8]; @@ -554,7 +558,13 @@ struct mlx5_ifc_flow_table_nic_cap_bits { u8 nic_rx_multi_path_tirs[0x1]; u8 nic_rx_multi_path_tirs_fts[0x1]; u8 allow_sniffer_and_nic_rx_shared_tir[0x1]; - u8 reserved_at_3[0x1fd]; + u8 reserved_at_3[0x1d]; + u8 encap_general_header[0x1]; + u8 reserved_at_21[0xa]; + u8 log_max_packet_reformat_context[0x5]; + u8 reserved_at_30[0x6]; + u8 max_encap_header_size[0xa]; + u8 reserved_at_40[0x1c0]; struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_receive; @@ -4851,6 +4861,9 @@ struct mlx5_ifc_alloc_packet_reformat_context_out_bits { enum { MLX5_REFORMAT_TYPE_L2_TO_VXLAN = 0x0, MLX5_REFORMAT_TYPE_L2_TO_NVGRE = 0x1, + MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL = 0x2, + MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2 = 0x3, + MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL = 0x4, }; struct mlx5_ifc_alloc_packet_reformat_context_in_bits { -- cgit v1.2.3 From 50acec06f3928fc29647aecf1270e54cae583afb Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 28 Aug 2018 14:18:49 +0300 Subject: net/mlx5: Export packet reformat alloc/dealloc functions This will allow for the RDMA side to allocate packet reformat context. Signed-off-by: Mark Bloch Reviewed-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c | 2 ++ drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h | 8 -------- include/linux/mlx5/fs.h | 9 +++++++++ 3 files changed, 11 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index cc9537891e39..dc8d7f6b52c2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -651,6 +651,7 @@ int mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev, kfree(in); return err; } +EXPORT_SYMBOL(mlx5_packet_reformat_alloc); void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev, u32 packet_reformat_id) @@ -666,6 +667,7 @@ void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev, mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); } +EXPORT_SYMBOL(mlx5_packet_reformat_dealloc); int mlx5_modify_header_alloc(struct mlx5_core_dev *dev, u8 namespace, u8 num_actions, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 66a5dd5a6cbe..61a014e3f688 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -170,14 +170,6 @@ struct mlx5_core_dev *mlx5_get_next_phys_dev(struct mlx5_core_dev *dev); void mlx5_dev_list_lock(void); void mlx5_dev_list_unlock(void); int mlx5_dev_list_trylock(void); -int mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev, - int reformat_type, - size_t size, - void *reformat_data, - enum mlx5_flow_namespace_type namespace, - u32 *packet_reformat_id); -void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev, - u32 packet_reformat_id); bool mlx5_lag_intf_add(struct mlx5_interface *intf, struct mlx5_priv *priv); diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 37d0c08d0966..b1c026f1c8ba 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -203,4 +203,13 @@ int mlx5_modify_header_alloc(struct mlx5_core_dev *dev, void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev, u32 modify_header_id); +int mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev, + int reformat_type, + size_t size, + void *reformat_data, + enum mlx5_flow_namespace_type namespace, + u32 *packet_reformat_id); +void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev, + u32 packet_reformat_id); + #endif -- cgit v1.2.3 From 03512ceb60ae4be71ed3129dabb8625224c8ec40 Mon Sep 17 00:00:00 2001 From: Sara Sharon Date: Fri, 31 Aug 2018 11:31:09 +0300 Subject: ieee80211: remove redundant leading zeroes The defines of IEEE80211_HE_OPERATION_VHT_OPER_INFO and IEEE80211_HE_OPERATION_MULTI_BSSID_AP have leading zeroes that makes the number look like it is bigger than 32 bit. This is misleading, remove it. Signed-off-by: Sara Sharon Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 9c03a7d5e400..17ea51d088ae 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1963,8 +1963,8 @@ ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info) #define IEEE80211_HE_OPERATION_TWT_REQUIRED 0x00000200 #define IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK 0x000ffc00 #define IEEE80211_HE_OPERATION_RTS_THRESHOLD_OFFSET 10 -#define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR 0x000100000 -#define IEEE80211_HE_OPERATION_VHT_OPER_INFO 0x000200000 +#define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR 0x00100000 +#define IEEE80211_HE_OPERATION_VHT_OPER_INFO 0x00200000 #define IEEE80211_HE_OPERATION_MULTI_BSSID_AP 0x10000000 #define IEEE80211_HE_OPERATION_TX_BSSID_INDICATOR 0x20000000 #define IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED 0x40000000 -- cgit v1.2.3 From b0aa75f0b1b2e6bc77128fab36c8ed87e84917cc Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 31 Aug 2018 11:31:16 +0300 Subject: ieee80211: add new VHT capability fields/parsing IEEE 802.11-2016 extended the VHT capability fields to allow indicating the number of spatial streams depending on the actually used bandwidth, add support for decoding this. Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 35 ++++++++++++++- net/wireless/util.c | 109 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 142 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 17ea51d088ae..280600a10111 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1460,13 +1460,16 @@ struct ieee80211_ht_operation { * STA can receive. Rate expressed in units of 1 Mbps. * If this field is 0 this value should not be used to * consider the highest RX data rate supported. - * The top 3 bits of this field are reserved. + * The top 3 bits of this field indicate the Maximum NSTS,total + * (a beamformee capability.) * @tx_mcs_map: TX MCS map 2 bits for each stream, total 8 streams * @tx_highest: Indicates highest long GI VHT PPDU data rate * STA can transmit. Rate expressed in units of 1 Mbps. * If this field is 0 this value should not be used to * consider the highest TX data rate supported. - * The top 3 bits of this field are reserved. + * The top 2 bits of this field are reserved, the + * 3rd bit from the top indiciates VHT Extended NSS BW + * Capability. */ struct ieee80211_vht_mcs_info { __le16 rx_mcs_map; @@ -1475,6 +1478,13 @@ struct ieee80211_vht_mcs_info { __le16 tx_highest; } __packed; +/* for rx_highest */ +#define IEEE80211_VHT_MAX_NSTS_TOTAL_SHIFT 13 +#define IEEE80211_VHT_MAX_NSTS_TOTAL_MASK (7 << IEEE80211_VHT_MAX_NSTS_TOTAL_SHIFT) + +/* for tx_highest */ +#define IEEE80211_VHT_EXT_NSS_BW_CAPABLE (1 << 13) + /** * enum ieee80211_vht_mcs_support - VHT MCS support definitions * @IEEE80211_VHT_MCS_SUPPORT_0_7: MCSes 0-7 are supported for the @@ -1650,6 +1660,7 @@ struct ieee80211_mu_edca_param_set { #define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ 0x00000004 #define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ 0x00000008 #define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK 0x0000000C +#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_SHIFT 2 #define IEEE80211_VHT_CAP_RXLDPC 0x00000010 #define IEEE80211_VHT_CAP_SHORT_GI_80 0x00000020 #define IEEE80211_VHT_CAP_SHORT_GI_160 0x00000040 @@ -1678,6 +1689,26 @@ struct ieee80211_mu_edca_param_set { #define IEEE80211_VHT_CAP_VHT_LINK_ADAPTATION_VHT_MRQ_MFB 0x0c000000 #define IEEE80211_VHT_CAP_RX_ANTENNA_PATTERN 0x10000000 #define IEEE80211_VHT_CAP_TX_ANTENNA_PATTERN 0x20000000 +#define IEEE80211_VHT_CAP_EXT_NSS_BW_SHIFT 30 +#define IEEE80211_VHT_CAP_EXT_NSS_BW_MASK 0xc0000000 + +/** + * ieee80211_get_vht_max_nss - return max NSS for a given bandwidth/MCS + * @cap: VHT capabilities of the peer + * @bw: bandwidth to use + * @mcs: MCS index to use + * @ext_nss_bw_capable: indicates whether or not the local transmitter + * (rate scaling algorithm) can deal with the new logic + * (dot11VHTExtendedNSSBWCapable) + * + * Due to the VHT Extended NSS Bandwidth Support, the maximum NSS can + * vary for a given BW/MCS. This function parses the data. + * + * Note: This function is exported by cfg80211. + */ +int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, + enum ieee80211_vht_chanwidth bw, + int mcs, bool ext_nss_bw_capable); /* 802.11ax HE MAC capabilities */ #define IEEE80211_HE_MAC_CAP0_HTC_HE 0x01 diff --git a/net/wireless/util.c b/net/wireless/util.c index 4293f980e9c4..ef14d80ca03e 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -5,17 +5,20 @@ * Copyright 2007-2009 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2017 Intel Deutschland GmbH + * Copyright (C) 2018 Intel Corporation */ #include #include #include #include +#include #include #include #include #include #include #include +#include #include "core.h" #include "rdev-ops.h" @@ -1938,3 +1941,109 @@ void cfg80211_send_layer2_update(struct net_device *dev, const u8 *addr) netif_rx_ni(skb); } EXPORT_SYMBOL(cfg80211_send_layer2_update); + +int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, + enum ieee80211_vht_chanwidth bw, + int mcs, bool ext_nss_bw_capable) +{ + u16 map = le16_to_cpu(cap->supp_mcs.rx_mcs_map); + int max_vht_nss = 0; + int ext_nss_bw; + int supp_width; + int i, mcs_encoding; + + if (map == 0xffff) + return 0; + + if (WARN_ON(mcs > 9)) + return 0; + if (mcs <= 7) + mcs_encoding = 0; + else if (mcs == 8) + mcs_encoding = 1; + else + mcs_encoding = 2; + + /* find max_vht_nss for the given MCS */ + for (i = 7; i >= 0; i--) { + int supp = (map >> (2 * i)) & 3; + + if (supp == 3) + continue; + + if (supp >= mcs_encoding) { + max_vht_nss = i; + break; + } + } + + if (!(cap->supp_mcs.tx_mcs_map & + cpu_to_le16(IEEE80211_VHT_EXT_NSS_BW_CAPABLE))) + return max_vht_nss; + + ext_nss_bw = le32_get_bits(cap->vht_cap_info, + IEEE80211_VHT_CAP_EXT_NSS_BW_MASK); + supp_width = le32_get_bits(cap->vht_cap_info, + IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK); + + /* if not capable, treat ext_nss_bw as 0 */ + if (!ext_nss_bw_capable) + ext_nss_bw = 0; + + /* This is invalid */ + if (supp_width == 3) + return 0; + + /* This is an invalid combination so pretend nothing is supported */ + if (supp_width == 2 && (ext_nss_bw == 1 || ext_nss_bw == 2)) + return 0; + + /* + * Cover all the special cases according to IEEE 802.11-2016 + * Table 9-250. All other cases are either factor of 1 or not + * valid/supported. + */ + switch (bw) { + case IEEE80211_VHT_CHANWIDTH_USE_HT: + case IEEE80211_VHT_CHANWIDTH_80MHZ: + if ((supp_width == 1 || supp_width == 2) && + ext_nss_bw == 3) + return 2 * max_vht_nss; + break; + case IEEE80211_VHT_CHANWIDTH_160MHZ: + if (supp_width == 0 && + (ext_nss_bw == 1 || ext_nss_bw == 2)) + return DIV_ROUND_UP(max_vht_nss, 2); + if (supp_width == 0 && + ext_nss_bw == 3) + return DIV_ROUND_UP(3 * max_vht_nss, 4); + if (supp_width == 1 && + ext_nss_bw == 3) + return 2 * max_vht_nss; + break; + case IEEE80211_VHT_CHANWIDTH_80P80MHZ: + if (supp_width == 0 && + (ext_nss_bw == 1 || ext_nss_bw == 2)) + return 0; /* not possible */ + if (supp_width == 0 && + ext_nss_bw == 2) + return DIV_ROUND_UP(max_vht_nss, 2); + if (supp_width == 0 && + ext_nss_bw == 3) + return DIV_ROUND_UP(3 * max_vht_nss, 4); + if (supp_width == 1 && + ext_nss_bw == 0) + return 0; /* not possible */ + if (supp_width == 1 && + ext_nss_bw == 1) + return DIV_ROUND_UP(max_vht_nss, 2); + if (supp_width == 1 && + ext_nss_bw == 2) + return DIV_ROUND_UP(3 * max_vht_nss, 4); + break; + } + + /* not covered or invalid combination received */ + return max_vht_nss; +} +EXPORT_SYMBOL(ieee80211_get_vht_max_nss); -- cgit v1.2.3 From add7453ad62f05c8f1a48675bb4dfed52e6ac878 Mon Sep 17 00:00:00 2001 From: Shaul Triebitz Date: Wed, 5 Sep 2018 08:06:08 +0300 Subject: wireless: align to draft 11ax D3.0 Align to new 11ax draft D3.0. Change/add new MAC and PHY capabilities and update drivers' 11ax capabilities and mac80211's debugfs accordingly. Signed-off-by: Shaul Triebitz Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c | 51 ++++++++++---- drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 4 -- drivers/net/wireless/mac80211_hwsim.c | 18 ++--- include/linux/ieee80211.h | 72 ++++++++++++-------- net/mac80211/debugfs_sta.c | 77 +++++++++++++++------- 5 files changed, 146 insertions(+), 76 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c index 73969dbeb5c5..27db4a3ba1f8 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c @@ -476,30 +476,40 @@ static struct ieee80211_sband_iftype_data iwl_he_capa = { .has_he = true, .he_cap_elem = { .mac_cap_info[0] = - IEEE80211_HE_MAC_CAP0_HTC_HE, + IEEE80211_HE_MAC_CAP0_HTC_HE | + IEEE80211_HE_MAC_CAP0_TWT_REQ, .mac_cap_info[1] = IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US | - IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_8, + IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8, .mac_cap_info[2] = IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP | + IEEE80211_HE_MAC_CAP2_MU_CASCADING | IEEE80211_HE_MAC_CAP2_ACK_EN, .mac_cap_info[3] = - IEEE80211_HE_MAC_CAP3_GRP_ADDR_MULTI_STA_BA_DL_MU | - IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_VHT_2, - .mac_cap_info[4] = IEEE80211_HE_MAC_CAP4_AMDSU_IN_AMPDU, + IEEE80211_HE_MAC_CAP3_OMI_CONTROL | + IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_VHT_2, + .mac_cap_info[4] = + IEEE80211_HE_MAC_CAP4_AMDSU_IN_AMPDU | + IEEE80211_HE_MAC_CAP4_MULTI_TID_AGG_TX_QOS_B39, + .mac_cap_info[5] = + IEEE80211_HE_MAC_CAP5_MULTI_TID_AGG_TX_QOS_B40 | + IEEE80211_HE_MAC_CAP5_MULTI_TID_AGG_TX_QOS_B41 | + IEEE80211_HE_MAC_CAP5_UL_2x996_TONE_RU, .phy_cap_info[0] = - IEEE80211_HE_PHY_CAP0_DUAL_BAND | IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G | IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G | IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G, .phy_cap_info[1] = + IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK | IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A | IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD | - IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_MAX_NSTS, + IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS, .phy_cap_info[2] = IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US | IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ | - IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ, + IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ | + IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO | + IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO, .phy_cap_info[3] = IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_BPSK | IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_1 | @@ -511,18 +521,31 @@ static struct ieee80211_sband_iftype_data iwl_he_capa = { IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_8, .phy_cap_info[5] = IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_2 | - IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_2, + IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_2 | + IEEE80211_HE_PHY_CAP5_NG16_SU_FEEDBACK | + IEEE80211_HE_PHY_CAP5_NG16_MU_FEEDBACK, .phy_cap_info[6] = + IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_42_SU | + IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_75_MU | + IEEE80211_HE_PHY_CAP6_TRIG_SU_BEAMFORMER_FB | + IEEE80211_HE_PHY_CAP6_TRIG_MU_BEAMFORMER_FB | + IEEE80211_HE_PHY_CAP6_TRIG_CQI_FB | + IEEE80211_HE_PHY_CAP6_PARTIAL_BANDWIDTH_DL_MUMIMO | IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT, .phy_cap_info[7] = IEEE80211_HE_PHY_CAP7_POWER_BOOST_FACTOR_AR | IEEE80211_HE_PHY_CAP7_HE_SU_MU_PPDU_4XLTF_AND_08_US_GI | - IEEE80211_HE_PHY_CAP7_MAX_NC_7, + IEEE80211_HE_PHY_CAP7_MAX_NC_1, .phy_cap_info[8] = IEEE80211_HE_PHY_CAP8_HE_ER_SU_PPDU_4XLTF_AND_08_US_GI | IEEE80211_HE_PHY_CAP8_20MHZ_IN_40MHZ_HE_PPDU_IN_2G | IEEE80211_HE_PHY_CAP8_20MHZ_IN_160MHZ_HE_PPDU | - IEEE80211_HE_PHY_CAP8_80MHZ_IN_160MHZ_HE_PPDU, + IEEE80211_HE_PHY_CAP8_80MHZ_IN_160MHZ_HE_PPDU | + IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_160_OR_80P80_MHZ, + .phy_cap_info[9] = + IEEE80211_HE_PHY_CAP9_NON_TRIGGERED_CQI_FEEDBACK | + IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_COMP_SIGB | + IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_NON_COMP_SIGB, }, /* * Set default Tx/Rx HE MCS NSS Support field. Indicate support @@ -559,9 +582,11 @@ static void iwl_init_he_hw_capab(struct ieee80211_supported_band *sband, /* If not 2x2, we need to indicate 1x1 in the Midamble RX Max NSTS */ if ((tx_chains & rx_chains) != ANT_AB) { iwl_he_capa.he_cap.he_cap_elem.phy_cap_info[1] &= - ~IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_MAX_NSTS; + ~IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS; iwl_he_capa.he_cap.he_cap_elem.phy_cap_info[2] &= - ~IEEE80211_HE_PHY_CAP2_MIDAMBLE_RX_MAX_NSTS; + ~IEEE80211_HE_PHY_CAP2_MIDAMBLE_RX_TX_MAX_NSTS; + iwl_he_capa.he_cap.he_cap_elem.phy_cap_info[7] &= + ~IEEE80211_HE_PHY_CAP7_MAX_NC_MASK; } } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index b15b0d84bb7e..d46f3fbea46e 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -1978,10 +1978,6 @@ static void iwl_mvm_cfg_he_sta(struct iwl_mvm *mvm, sta_ctxt_cmd.htc_flags |= cpu_to_le32(IWL_HE_HTC_LINK_ADAP_BOTH); } - if (sta->he_cap.he_cap_elem.mac_cap_info[2] & - IEEE80211_HE_MAC_CAP2_UL_MU_RESP_SCHED) - sta_ctxt_cmd.htc_flags |= - cpu_to_le32(IWL_HE_HTC_UL_MU_RESP_SCHED); if (sta->he_cap.he_cap_elem.mac_cap_info[2] & IEEE80211_HE_MAC_CAP2_BSR) sta_ctxt_cmd.htc_flags |= cpu_to_le32(IWL_HE_HTC_BSR_SUPP); if (sta->he_cap.he_cap_elem.mac_cap_info[3] & diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 1068757ec42e..f3863101af78 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -3,6 +3,7 @@ * Copyright (c) 2008, Jouni Malinen * Copyright (c) 2011, Javier Lopez * Copyright (c) 2016 - 2017 Intel Deutschland GmbH + * Copyright (C) 2018 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -2529,23 +2530,20 @@ static const struct ieee80211_sband_iftype_data he_capa_2ghz = { IEEE80211_HE_MAC_CAP0_HTC_HE, .mac_cap_info[1] = IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US | - IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_8, + IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8, .mac_cap_info[2] = IEEE80211_HE_MAC_CAP2_BSR | IEEE80211_HE_MAC_CAP2_MU_CASCADING | IEEE80211_HE_MAC_CAP2_ACK_EN, .mac_cap_info[3] = - IEEE80211_HE_MAC_CAP3_GRP_ADDR_MULTI_STA_BA_DL_MU | IEEE80211_HE_MAC_CAP3_OMI_CONTROL | - IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_VHT_2, + IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_VHT_2, .mac_cap_info[4] = IEEE80211_HE_MAC_CAP4_AMDSU_IN_AMPDU, - .phy_cap_info[0] = - IEEE80211_HE_PHY_CAP0_DUAL_BAND, .phy_cap_info[1] = IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK | IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A | IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD | - IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_MAX_NSTS, + IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS, .phy_cap_info[2] = IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US | IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ | @@ -2579,18 +2577,16 @@ static const struct ieee80211_sband_iftype_data he_capa_5ghz = { IEEE80211_HE_MAC_CAP0_HTC_HE, .mac_cap_info[1] = IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US | - IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_8, + IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8, .mac_cap_info[2] = IEEE80211_HE_MAC_CAP2_BSR | IEEE80211_HE_MAC_CAP2_MU_CASCADING | IEEE80211_HE_MAC_CAP2_ACK_EN, .mac_cap_info[3] = - IEEE80211_HE_MAC_CAP3_GRP_ADDR_MULTI_STA_BA_DL_MU | IEEE80211_HE_MAC_CAP3_OMI_CONTROL | - IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_VHT_2, + IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_VHT_2, .mac_cap_info[4] = IEEE80211_HE_MAC_CAP4_AMDSU_IN_AMPDU, .phy_cap_info[0] = - IEEE80211_HE_PHY_CAP0_DUAL_BAND | IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G | IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G | IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G, @@ -2598,7 +2594,7 @@ static const struct ieee80211_sband_iftype_data he_capa_5ghz = { IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK | IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A | IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD | - IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_MAX_NSTS, + IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS, .phy_cap_info[2] = IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US | IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ | diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 280600a10111..c4809ad8ab46 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1555,11 +1555,11 @@ struct ieee80211_vht_operation { * struct ieee80211_he_cap_elem - HE capabilities element * * This structure is the "HE capabilities element" fixed fields as - * described in P802.11ax_D2.0 section 9.4.2.237.2 and 9.4.2.237.3 + * described in P802.11ax_D3.0 section 9.4.2.237.2 and 9.4.2.237.3 */ struct ieee80211_he_cap_elem { - u8 mac_cap_info[5]; - u8 phy_cap_info[9]; + u8 mac_cap_info[6]; + u8 phy_cap_info[11]; } __packed; #define IEEE80211_TX_RX_MCS_NSS_DESC_MAX_LEN 5 @@ -1738,15 +1738,15 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, #define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_8US 0x04 #define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US 0x08 #define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_MASK 0x0c -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_1 0x00 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_2 0x10 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_3 0x20 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_4 0x30 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_5 0x40 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_6 0x50 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_7 0x60 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_8 0x70 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_MASK 0x70 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_1 0x00 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_2 0x10 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_3 0x20 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_4 0x30 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_5 0x40 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_6 0x50 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_7 0x60 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8 0x70 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_MASK 0x70 /* Link adaptation is split between byte HE_MAC_CAP1 and * HE_MAC_CAP2. It should be set only if IEEE80211_HE_MAC_CAP0_HTC_HE @@ -1760,14 +1760,13 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, #define IEEE80211_HE_MAC_CAP2_LINK_ADAPTATION 0x01 #define IEEE80211_HE_MAC_CAP2_ALL_ACK 0x02 -#define IEEE80211_HE_MAC_CAP2_UL_MU_RESP_SCHED 0x04 +#define IEEE80211_HE_MAC_CAP2_TRS 0x04 #define IEEE80211_HE_MAC_CAP2_BSR 0x08 #define IEEE80211_HE_MAC_CAP2_BCAST_TWT 0x10 #define IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP 0x20 #define IEEE80211_HE_MAC_CAP2_MU_CASCADING 0x40 #define IEEE80211_HE_MAC_CAP2_ACK_EN 0x80 -#define IEEE80211_HE_MAC_CAP3_GRP_ADDR_MULTI_STA_BA_DL_MU 0x01 #define IEEE80211_HE_MAC_CAP3_OMI_CONTROL 0x02 #define IEEE80211_HE_MAC_CAP3_OFDMA_RA 0x04 @@ -1775,25 +1774,34 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, * A-MDPU Length Exponent field in the HT capabilities, VHT capabilities and the * same field in the HE capabilities. */ -#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_USE_VHT 0x00 -#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_VHT_1 0x08 -#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_VHT_2 0x10 -#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_RESERVED 0x18 -#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_MASK 0x18 -#define IEEE80211_HE_MAC_CAP3_A_AMSDU_FRAG 0x20 +#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_USE_VHT 0x00 +#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_VHT_1 0x08 +#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_VHT_2 0x10 +#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_RESERVED 0x18 +#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_MASK 0x18 +#define IEEE80211_HE_MAC_CAP3_AMSDU_FRAG 0x20 #define IEEE80211_HE_MAC_CAP3_FLEX_TWT_SCHED 0x40 #define IEEE80211_HE_MAC_CAP3_RX_CTRL_FRAME_TO_MULTIBSS 0x80 #define IEEE80211_HE_MAC_CAP4_BSRP_BQRP_A_MPDU_AGG 0x01 #define IEEE80211_HE_MAC_CAP4_QTP 0x02 #define IEEE80211_HE_MAC_CAP4_BQR 0x04 -#define IEEE80211_HE_MAC_CAP4_SR_RESP 0x08 +#define IEEE80211_HE_MAC_CAP4_SRP_RESP 0x08 #define IEEE80211_HE_MAC_CAP4_NDP_FB_REP 0x10 #define IEEE80211_HE_MAC_CAP4_OPS 0x20 #define IEEE80211_HE_MAC_CAP4_AMDSU_IN_AMPDU 0x40 +/* Multi TID agg TX is split between byte #4 and #5 + * The value is a combination of B39,B40,B41 + */ +#define IEEE80211_HE_MAC_CAP4_MULTI_TID_AGG_TX_QOS_B39 0x80 + +#define IEEE80211_HE_MAC_CAP5_MULTI_TID_AGG_TX_QOS_B40 0x01 +#define IEEE80211_HE_MAC_CAP5_MULTI_TID_AGG_TX_QOS_B41 0x02 +#define IEEE80211_HE_MAC_CAP5_SUBCHAN_SELECVITE_TRANSMISSION 0x04 +#define IEEE80211_HE_MAC_CAP5_UL_2x996_TONE_RU 0x08 +#define IEEE80211_HE_MAC_CAP5_OM_CTRL_UL_MU_DATA_DIS_RX 0x10 /* 802.11ax HE PHY capabilities */ -#define IEEE80211_HE_PHY_CAP0_DUAL_BAND 0x01 #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G 0x02 #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G 0x04 #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G 0x08 @@ -1810,10 +1818,10 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, #define IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A 0x10 #define IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD 0x20 #define IEEE80211_HE_PHY_CAP1_HE_LTF_AND_GI_FOR_HE_PPDUS_0_8US 0x40 -/* Midamble RX Max NSTS is split between byte #2 and byte #3 */ -#define IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_MAX_NSTS 0x80 +/* Midamble RX/TX Max NSTS is split between byte #2 and byte #3 */ +#define IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS 0x80 -#define IEEE80211_HE_PHY_CAP2_MIDAMBLE_RX_MAX_NSTS 0x01 +#define IEEE80211_HE_PHY_CAP2_MIDAMBLE_RX_TX_MAX_NSTS 0x01 #define IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US 0x02 #define IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ 0x04 #define IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ 0x08 @@ -1914,7 +1922,19 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, #define IEEE80211_HE_PHY_CAP8_20MHZ_IN_160MHZ_HE_PPDU 0x04 #define IEEE80211_HE_PHY_CAP8_80MHZ_IN_160MHZ_HE_PPDU 0x08 #define IEEE80211_HE_PHY_CAP8_HE_ER_SU_1XLTF_AND_08_US_GI 0x10 -#define IEEE80211_HE_PHY_CAP8_MIDAMBLE_RX_2X_AND_1XLTF 0x20 +#define IEEE80211_HE_PHY_CAP8_MIDAMBLE_RX_TX_2X_AND_1XLTF 0x20 +#define IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_20MHZ 0x00 +#define IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_40MHZ 0x40 +#define IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_80MHZ 0x80 +#define IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_160_OR_80P80_MHZ 0xc0 +#define IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_MASK 0xc0 + +#define IEEE80211_HE_PHY_CAP9_LONGER_THAN_16_SIGB_OFDM_SYM 0x01 +#define IEEE80211_HE_PHY_CAP9_NON_TRIGGERED_CQI_FEEDBACK 0x02 +#define IEEE80211_HE_PHY_CAP9_TX_1024_QAM_LESS_THAN_242_TONE_RU 0x04 +#define IEEE80211_HE_PHY_CAP9_RX_1024_QAM_LESS_THAN_242_TONE_RU 0x08 +#define IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_COMP_SIGB 0x10 +#define IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_NON_COMP_SIGB 0x20 /* 802.11ax HE TX/RX MCS NSS Support */ #define IEEE80211_TX_RX_MCS_NSS_SUPP_HIGHEST_MCS_POS (3) diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index 95124978947f..af5185a836e5 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -522,8 +522,8 @@ static ssize_t sta_he_capa_read(struct file *file, char __user *userbuf, cap = hec->he_cap_elem.mac_cap_info; p += scnprintf(p, buf_sz + buf - p, - "MAC-CAP: %#.2x %#.2x %#.2x %#.2x %#.2x\n", - cap[0], cap[1], cap[2], cap[3], cap[4]); + "MAC-CAP: %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x\n", + cap[0], cap[1], cap[2], cap[3], cap[4], cap[5]); #define PRINT(fmt, ...) \ p += scnprintf(p, buf_sz + buf - p, "\t\t" fmt "\n", \ @@ -563,7 +563,8 @@ static ssize_t sta_he_capa_read(struct file *file, char __user *userbuf, "MIN-FRAG-SIZE-%d", UNLIMITED, "UNLIMITED"); PFLAG_RANGE_DEFAULT(MAC, 1, TF_MAC_PAD_DUR, 0, 8, 0, "TF-MAC-PAD-DUR-%dUS", MASK, "UNKNOWN"); - PFLAG_RANGE(MAC, 1, MULTI_TID_AGG_QOS, 0, 1, 1, "MULTI-TID-AGG-QOS-%d"); + PFLAG_RANGE(MAC, 1, MULTI_TID_AGG_RX_QOS, 0, 1, 1, + "MULTI-TID-AGG-RX-QOS-%d"); if (cap[0] & IEEE80211_HE_MAC_CAP0_HTC_HE) { switch (((cap[2] << 1) | (cap[1] >> 7)) & 0x3) { @@ -583,52 +584,55 @@ static ssize_t sta_he_capa_read(struct file *file, char __user *userbuf, } PFLAG(MAC, 2, ALL_ACK, "ALL-ACK"); - PFLAG(MAC, 2, UL_MU_RESP_SCHED, "UL-MU-RESP-SCHED"); + PFLAG(MAC, 2, TRS, "TRS"); PFLAG(MAC, 2, BSR, "BSR"); PFLAG(MAC, 2, BCAST_TWT, "BCAST-TWT"); PFLAG(MAC, 2, 32BIT_BA_BITMAP, "32BIT-BA-BITMAP"); PFLAG(MAC, 2, MU_CASCADING, "MU-CASCADING"); PFLAG(MAC, 2, ACK_EN, "ACK-EN"); - PFLAG(MAC, 3, GRP_ADDR_MULTI_STA_BA_DL_MU, - "GRP-ADDR-MULTI-STA-BA-DL-MU"); PFLAG(MAC, 3, OMI_CONTROL, "OMI-CONTROL"); PFLAG(MAC, 3, OFDMA_RA, "OFDMA-RA"); - switch (cap[3] & IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_MASK) { - case IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_USE_VHT: - PRINT("MAX-A-AMPDU-LEN-EXP-USE-VHT"); + switch (cap[3] & IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_MASK) { + case IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_USE_VHT: + PRINT("MAX-AMPDU-LEN-EXP-USE-VHT"); break; - case IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_VHT_1: - PRINT("MAX-A-AMPDU-LEN-EXP-VHT-1"); + case IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_VHT_1: + PRINT("MAX-AMPDU-LEN-EXP-VHT-1"); break; - case IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_VHT_2: - PRINT("MAX-A-AMPDU-LEN-EXP-VHT-2"); + case IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_VHT_2: + PRINT("MAX-AMPDU-LEN-EXP-VHT-2"); break; - case IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_RESERVED: - PRINT("MAX-A-AMPDU-LEN-EXP-RESERVED"); + case IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_RESERVED: + PRINT("MAX-AMPDU-LEN-EXP-RESERVED"); break; } - PFLAG(MAC, 3, A_AMSDU_FRAG, "A-AMSDU-FRAG"); + PFLAG(MAC, 3, AMSDU_FRAG, "AMSDU-FRAG"); PFLAG(MAC, 3, FLEX_TWT_SCHED, "FLEX-TWT-SCHED"); PFLAG(MAC, 3, RX_CTRL_FRAME_TO_MULTIBSS, "RX-CTRL-FRAME-TO-MULTIBSS"); PFLAG(MAC, 4, BSRP_BQRP_A_MPDU_AGG, "BSRP-BQRP-A-MPDU-AGG"); PFLAG(MAC, 4, QTP, "QTP"); PFLAG(MAC, 4, BQR, "BQR"); - PFLAG(MAC, 4, SR_RESP, "SR-RESP"); + PFLAG(MAC, 4, SRP_RESP, "SRP-RESP"); PFLAG(MAC, 4, NDP_FB_REP, "NDP-FB-REP"); PFLAG(MAC, 4, OPS, "OPS"); PFLAG(MAC, 4, AMDSU_IN_AMPDU, "AMSDU-IN-AMPDU"); + PRINT("MULTI-TID-AGG-TX-QOS-%d", ((cap[5] << 1) | (cap[4] >> 7)) & 0x7); + + PFLAG(MAC, 5, SUBCHAN_SELECVITE_TRANSMISSION, + "SUBCHAN-SELECVITE-TRANSMISSION"); + PFLAG(MAC, 5, UL_2x996_TONE_RU, "UL-2x996-TONE-RU"); + PFLAG(MAC, 5, OM_CTRL_UL_MU_DATA_DIS_RX, "OM-CTRL-UL-MU-DATA-DIS-RX"); + cap = hec->he_cap_elem.phy_cap_info; p += scnprintf(p, buf_sz + buf - p, - "PHY CAP: %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x\n", + "PHY CAP: %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x\n", cap[0], cap[1], cap[2], cap[3], cap[4], cap[5], cap[6], - cap[7], cap[8]); - - PFLAG(PHY, 0, DUAL_BAND, "DUAL-BAND"); + cap[7], cap[8], cap[9], cap[10]); PFLAG(PHY, 0, CHANNEL_WIDTH_SET_40MHZ_IN_2G, "CHANNEL-WIDTH-SET-40MHZ-IN-2G"); @@ -754,7 +758,36 @@ static ssize_t sta_he_capa_read(struct file *file, char __user *userbuf, PFLAG(PHY, 8, 80MHZ_IN_160MHZ_HE_PPDU, "80MHZ-IN-160MHZ-HE-PPDU"); PFLAG(PHY, 8, HE_ER_SU_1XLTF_AND_08_US_GI, "HE-ER-SU-1XLTF-AND-08-US-GI"); - PFLAG(PHY, 8, MIDAMBLE_RX_2X_AND_1XLTF, "MIDAMBLE-RX-2X-AND-1XLTF"); + PFLAG(PHY, 8, MIDAMBLE_RX_TX_2X_AND_1XLTF, + "MIDAMBLE-RX-TX-2X-AND-1XLTF"); + + switch (cap[8] & IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_MASK) { + case IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_20MHZ: + PRINT("DDCM-MAX-BW-20MHZ"); + break; + case IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_40MHZ: + PRINT("DCM-MAX-BW-40MHZ"); + break; + case IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_80MHZ: + PRINT("DCM-MAX-BW-80MHZ"); + break; + case IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_160_OR_80P80_MHZ: + PRINT("DCM-MAX-BW-160-OR-80P80-MHZ"); + break; + } + + PFLAG(PHY, 9, LONGER_THAN_16_SIGB_OFDM_SYM, + "LONGER-THAN-16-SIGB-OFDM-SYM"); + PFLAG(PHY, 9, NON_TRIGGERED_CQI_FEEDBACK, + "NON-TRIGGERED-CQI-FEEDBACK"); + PFLAG(PHY, 9, TX_1024_QAM_LESS_THAN_242_TONE_RU, + "TX-1024-QAM-LESS-THAN-242-TONE-RU"); + PFLAG(PHY, 9, RX_1024_QAM_LESS_THAN_242_TONE_RU, + "RX-1024-QAM-LESS-THAN-242-TONE-RU"); + PFLAG(PHY, 9, RX_FULL_BW_SU_USING_MU_WITH_COMP_SIGB, + "RX-FULL-BW-SU-USING-MU-WITH-COMP-SIGB"); + PFLAG(PHY, 9, RX_FULL_BW_SU_USING_MU_WITH_NON_COMP_SIGB, + "RX-FULL-BW-SU-USING-MU-WITH-NON-COMP-SIGB"); #undef PFLAG_RANGE_DEFAULT #undef PFLAG_RANGE -- cgit v1.2.3 From 1ff2e1a44e02d4bdbb9be67c7d9acc240a67141f Mon Sep 17 00:00:00 2001 From: Harry Cutts Date: Thu, 30 Aug 2018 14:56:19 -0700 Subject: HID: input: Create a utility class for counting scroll events To avoid code duplication, this class counts high-resolution scroll movements and emits the legacy low-resolution events when appropriate. Drivers should be able to create one instance for each scroll wheel that they need to handle. Signed-off-by: Harry Cutts Reviewed-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- drivers/hid/hid-input.c | 45 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/hid.h | 28 ++++++++++++++++++++++++++++ 2 files changed, 73 insertions(+) (limited to 'include/linux') diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index 4e94ea3e280a..6e84e7b9afcb 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -1826,3 +1826,48 @@ void hidinput_disconnect(struct hid_device *hid) } EXPORT_SYMBOL_GPL(hidinput_disconnect); +/** + * hid_scroll_counter_handle_scroll() - Send high- and low-resolution scroll + * events given a high-resolution wheel + * movement. + * @counter: a hid_scroll_counter struct describing the wheel. + * @hi_res_value: the movement of the wheel, in the mouse's high-resolution + * units. + * + * Given a high-resolution movement, this function converts the movement into + * microns and emits high-resolution scroll events for the input device. It also + * uses the multiplier from &struct hid_scroll_counter to emit low-resolution + * scroll events when appropriate for backwards-compatibility with userspace + * input libraries. + */ +void hid_scroll_counter_handle_scroll(struct hid_scroll_counter *counter, + int hi_res_value) +{ + int low_res_scroll_amount; + /* Some wheels will rest 7/8ths of a notch from the previous notch + * after slow movement, so we want the threshold for low-res events to + * be in the middle of the notches (e.g. after 4/8ths) as opposed to on + * the notches themselves (8/8ths). + */ + int threshold = counter->resolution_multiplier / 2; + + input_report_rel(counter->dev, REL_WHEEL_HI_RES, + hi_res_value * counter->microns_per_hi_res_unit); + + counter->remainder += hi_res_value; + if (abs(counter->remainder) >= threshold) { + /* Add (or subtract) 1 because we want to trigger when the wheel + * is half-way to the next notch (i.e. scroll 1 notch after a + * 1/2 notch movement, 2 notches after a 1 1/2 notch movement, + * etc.). + */ + low_res_scroll_amount = + counter->remainder / counter->resolution_multiplier + + (hi_res_value > 0 ? 1 : -1); + input_report_rel(counter->dev, REL_WHEEL, + low_res_scroll_amount); + counter->remainder -= + low_res_scroll_amount * counter->resolution_multiplier; + } +} +EXPORT_SYMBOL_GPL(hid_scroll_counter_handle_scroll); diff --git a/include/linux/hid.h b/include/linux/hid.h index 834e6461a690..037e37b0b0e6 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -1138,6 +1138,34 @@ static inline u32 hid_report_len(struct hid_report *report) int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, u32 size, int interrupt); + +/** + * struct hid_scroll_counter - Utility class for processing high-resolution + * scroll events. + * @dev: the input device for which events should be reported. + * @microns_per_hi_res_unit: the amount moved by the user's finger for each + * high-resolution unit reported by the mouse, in + * microns. + * @resolution_multiplier: the wheel's resolution in high-resolution mode as a + * multiple of its lower resolution. For example, if + * moving the wheel by one "notch" would result in a + * value of 1 in low-resolution mode but 8 in + * high-resolution, the multiplier is 8. + * @remainder: counts the number of high-resolution units moved since the last + * low-resolution event (REL_WHEEL or REL_HWHEEL) was sent. Should + * only be used by class methods. + */ +struct hid_scroll_counter { + struct input_dev *dev; + int microns_per_hi_res_unit; + int resolution_multiplier; + + int remainder; +}; + +void hid_scroll_counter_handle_scroll(struct hid_scroll_counter *counter, + int hi_res_value); + /* HID quirks API */ unsigned long hid_lookup_quirk(const struct hid_device *hdev); int hid_quirks_init(char **quirks_param, __u16 bus, int count); -- cgit v1.2.3 From 83033688b7ade18d2dbbcefa810f02ff66ba549d Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Mon, 23 Jul 2018 10:55:39 +0300 Subject: net/mlx5: Change flow counters addlist type to single linked list In order to prevent flow counters stats work function from traversing whole flow counters tree while searching for deleted flow counters, new list to store deleted flow counters will be added to struct mlx5_fc_stats. However, the flow counter structure itself has no space left to store any more data in first cache line. To free space that is needed to store additional list node, convert current addlist double linked list (two pointers per node) to atomic single linked list (one pointer per node). Lockless NULL-terminated single linked list data type doesn't require any additional external synchronization for operations used by flow counters module (add single new element, remove all elements from list and traverse them). Remove addlist_lock that is no longer needed. Signed-off-by: Vlad Buslov Acked-by: Amir Vadai Reviewed-by: Paul Blakey Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.h | 3 +- .../net/ethernet/mellanox/mlx5/core/fs_counters.c | 45 ++++++++++------------ include/linux/mlx5/driver.h | 4 +- 3 files changed, 23 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 32070e5d993d..f68590291e0c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -36,6 +36,7 @@ #include #include #include +#include enum fs_node_type { FS_TYPE_NAMESPACE, @@ -139,7 +140,7 @@ struct mlx5_fc_cache { struct mlx5_fc { struct rb_node node; - struct list_head list; + struct llist_node addlist; /* last{packets,bytes} members are used when calculating the delta since * last reading diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c index 58af6be13dfa..d996d6cf9e19 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c @@ -52,7 +52,9 @@ * access to counter list: * - create (user context) * - mlx5_fc_create() only adds to an addlist to be used by - * mlx5_fc_stats_query_work(). addlist is protected by a spinlock. + * mlx5_fc_stats_query_work(). addlist is a lockless single linked list + * that doesn't require any additional synchronization when adding single + * node. * - spawn thread to do the actual destroy * * - destroy (user context) @@ -156,28 +158,29 @@ out: return node; } +static void mlx5_free_fc(struct mlx5_core_dev *dev, + struct mlx5_fc *counter) +{ + mlx5_cmd_fc_free(dev, counter->id); + kfree(counter); +} + static void mlx5_fc_stats_work(struct work_struct *work) { struct mlx5_core_dev *dev = container_of(work, struct mlx5_core_dev, priv.fc_stats.work.work); struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + struct llist_node *tmplist = llist_del_all(&fc_stats->addlist); unsigned long now = jiffies; struct mlx5_fc *counter = NULL; struct mlx5_fc *last = NULL; struct rb_node *node; - LIST_HEAD(tmplist); - - spin_lock(&fc_stats->addlist_lock); - list_splice_tail_init(&fc_stats->addlist, &tmplist); - - if (!list_empty(&tmplist) || !RB_EMPTY_ROOT(&fc_stats->counters)) + if (tmplist || !RB_EMPTY_ROOT(&fc_stats->counters)) queue_delayed_work(fc_stats->wq, &fc_stats->work, fc_stats->sampling_interval); - spin_unlock(&fc_stats->addlist_lock); - - list_for_each_entry(counter, &tmplist, list) + llist_for_each_entry(counter, tmplist, addlist) mlx5_fc_stats_insert(&fc_stats->counters, counter); node = rb_first(&fc_stats->counters); @@ -229,9 +232,7 @@ struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging) counter->cache.lastuse = jiffies; counter->aging = true; - spin_lock(&fc_stats->addlist_lock); - list_add(&counter->list, &fc_stats->addlist); - spin_unlock(&fc_stats->addlist_lock); + llist_add(&counter->addlist, &fc_stats->addlist); mod_delayed_work(fc_stats->wq, &fc_stats->work, 0); } @@ -268,8 +269,7 @@ int mlx5_init_fc_stats(struct mlx5_core_dev *dev) struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; fc_stats->counters = RB_ROOT; - INIT_LIST_HEAD(&fc_stats->addlist); - spin_lock_init(&fc_stats->addlist_lock); + init_llist_head(&fc_stats->addlist); fc_stats->wq = create_singlethread_workqueue("mlx5_fc"); if (!fc_stats->wq) @@ -284,6 +284,7 @@ int mlx5_init_fc_stats(struct mlx5_core_dev *dev) void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev) { struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + struct llist_node *tmplist; struct mlx5_fc *counter; struct mlx5_fc *tmp; struct rb_node *node; @@ -292,13 +293,9 @@ void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev) destroy_workqueue(dev->priv.fc_stats.wq); dev->priv.fc_stats.wq = NULL; - list_for_each_entry_safe(counter, tmp, &fc_stats->addlist, list) { - list_del(&counter->list); - - mlx5_cmd_fc_free(dev, counter->id); - - kfree(counter); - } + tmplist = llist_del_all(&fc_stats->addlist); + llist_for_each_entry_safe(counter, tmp, tmplist, addlist) + mlx5_free_fc(dev, counter); node = rb_first(&fc_stats->counters); while (node) { @@ -308,9 +305,7 @@ void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev) rb_erase(&counter->node, &fc_stats->counters); - mlx5_cmd_fc_free(dev, counter->id); - - kfree(counter); + mlx5_free_fc(dev, counter); } } diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 7a452716de4b..c00549293982 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -584,9 +584,7 @@ struct mlx5_irq_info { struct mlx5_fc_stats { struct rb_root counters; - struct list_head addlist; - /* protect addlist add/splice operations */ - spinlock_t addlist_lock; + struct llist_head addlist; struct workqueue_struct *wq; struct delayed_work work; -- cgit v1.2.3 From 6e5e22839136fdb466af0aa46ff2404713dff974 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Mon, 23 Jul 2018 11:32:05 +0300 Subject: net/mlx5: Add new list to store deleted flow counters In order to prevent flow counters stats work function from traversing whole flow counters tree while searching for deleted flow counters, new list to store deleted flow counters is added to struct mlx5_fc_stats. Lockless NULL-terminated single linked list data type is used due to following reasons: - This use case only needs to add single element to list and remove/iterate whole list. Lockless list doesn't require any additional synchronization for these operations. - First cache line of flow counter data structure only has space to store single additional pointer, which precludes usage of double linked list. Remove flow counter 'deleted' flag that is no longer needed. Signed-off-by: Vlad Buslov Acked-by: Amir Vadai Reviewed-by: Paul Blakey Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.h | 2 +- .../net/ethernet/mellanox/mlx5/core/fs_counters.c | 34 ++++++++-------------- include/linux/mlx5/driver.h | 1 + 3 files changed, 14 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index f68590291e0c..617d6239c5f3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -141,6 +141,7 @@ struct mlx5_fc_cache { struct mlx5_fc { struct rb_node node; struct llist_node addlist; + struct llist_node dellist; /* last{packets,bytes} members are used when calculating the delta since * last reading @@ -149,7 +150,6 @@ struct mlx5_fc { u64 lastbytes; u32 id; - bool deleted; bool aging; struct mlx5_fc_cache cache ____cacheline_aligned_in_smp; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c index d996d6cf9e19..f1266f215a31 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c @@ -58,7 +58,7 @@ * - spawn thread to do the actual destroy * * - destroy (user context) - * - mark a counter as deleted + * - add a counter to lockless dellist * - spawn thread to do the actual del * * - dump (user context) @@ -171,9 +171,8 @@ static void mlx5_fc_stats_work(struct work_struct *work) priv.fc_stats.work.work); struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; struct llist_node *tmplist = llist_del_all(&fc_stats->addlist); + struct mlx5_fc *counter = NULL, *last = NULL, *tmp; unsigned long now = jiffies; - struct mlx5_fc *counter = NULL; - struct mlx5_fc *last = NULL; struct rb_node *node; if (tmplist || !RB_EMPTY_ROOT(&fc_stats->counters)) @@ -183,26 +182,17 @@ static void mlx5_fc_stats_work(struct work_struct *work) llist_for_each_entry(counter, tmplist, addlist) mlx5_fc_stats_insert(&fc_stats->counters, counter); - node = rb_first(&fc_stats->counters); - while (node) { - counter = rb_entry(node, struct mlx5_fc, node); - - node = rb_next(node); - - if (counter->deleted) { - rb_erase(&counter->node, &fc_stats->counters); - - mlx5_cmd_fc_free(dev, counter->id); - - kfree(counter); - continue; - } + tmplist = llist_del_all(&fc_stats->dellist); + llist_for_each_entry_safe(counter, tmp, tmplist, dellist) { + rb_erase(&counter->node, &fc_stats->counters); - last = counter; + mlx5_free_fc(dev, counter); } - if (time_before(now, fc_stats->next_query) || !last) + node = rb_last(&fc_stats->counters); + if (time_before(now, fc_stats->next_query) || !node) return; + last = rb_entry(node, struct mlx5_fc, node); node = rb_first(&fc_stats->counters); while (node) { @@ -254,13 +244,12 @@ void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter) return; if (counter->aging) { - counter->deleted = true; + llist_add(&counter->dellist, &fc_stats->dellist); mod_delayed_work(fc_stats->wq, &fc_stats->work, 0); return; } - mlx5_cmd_fc_free(dev, counter->id); - kfree(counter); + mlx5_free_fc(dev, counter); } EXPORT_SYMBOL(mlx5_fc_destroy); @@ -270,6 +259,7 @@ int mlx5_init_fc_stats(struct mlx5_core_dev *dev) fc_stats->counters = RB_ROOT; init_llist_head(&fc_stats->addlist); + init_llist_head(&fc_stats->dellist); fc_stats->wq = create_singlethread_workqueue("mlx5_fc"); if (!fc_stats->wq) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index c00549293982..4b53ac64004b 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -585,6 +585,7 @@ struct mlx5_irq_info { struct mlx5_fc_stats { struct rb_root counters; struct llist_head addlist; + struct llist_head dellist; struct workqueue_struct *wq; struct delayed_work work; -- cgit v1.2.3 From 9aff93d7d0d4b3f3076d7bd12a4ad06ef1cf9804 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Tue, 24 Jul 2018 09:52:11 +0300 Subject: net/mlx5: Store flow counters in a list In order to improve performance of flow counter stats query loop that traverses all configured flow counters, replace rb_tree with double-linked list. This change improves performance of traversing flow counters by removing the tree traversal. (profiling data showed that call to rb_next was most top CPU consumer) However, lookup of flow flow counter in list becomes linear, instead of logarithmic. This problem is fixed by next patch in series, which adds idr for fast lookup. Idr is to be used because it is not an intrusive data structure and doesn't require adding any new members to struct mlx5_fc, which allows its control data part to stay <= 1 cache line in size. Signed-off-by: Vlad Buslov Acked-by: Amir Vadai Reviewed-by: Paul Blakey Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.h | 2 +- .../net/ethernet/mellanox/mlx5/core/fs_counters.c | 88 ++++++++++------------ include/linux/mlx5/driver.h | 2 +- 3 files changed, 42 insertions(+), 50 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 617d6239c5f3..a06f83c0c2b6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -139,7 +139,7 @@ struct mlx5_fc_cache { }; struct mlx5_fc { - struct rb_node node; + struct list_head list; struct llist_node addlist; struct llist_node dellist; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c index f1266f215a31..90ebfee37508 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c @@ -73,36 +73,38 @@ * elapsed, the thread will actually query the hardware. */ -static void mlx5_fc_stats_insert(struct rb_root *root, struct mlx5_fc *counter) +static struct list_head *mlx5_fc_counters_lookup_next(struct mlx5_core_dev *dev, + u32 id) { - struct rb_node **new = &root->rb_node; - struct rb_node *parent = NULL; - - while (*new) { - struct mlx5_fc *this = rb_entry(*new, struct mlx5_fc, node); - int result = counter->id - this->id; - - parent = *new; - if (result < 0) - new = &((*new)->rb_left); - else - new = &((*new)->rb_right); - } + struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + struct mlx5_fc *counter; + + list_for_each_entry(counter, &fc_stats->counters, list) + if (counter->id > id) + return &counter->list; + + return &fc_stats->counters; +} + +static void mlx5_fc_stats_insert(struct mlx5_core_dev *dev, + struct mlx5_fc *counter) +{ + struct list_head *next = mlx5_fc_counters_lookup_next(dev, counter->id); - /* Add new node and rebalance tree. */ - rb_link_node(&counter->node, parent, new); - rb_insert_color(&counter->node, root); + list_add_tail(&counter->list, next); } -/* The function returns the last node that was queried so the caller +/* The function returns the last counter that was queried so the caller * function can continue calling it till all counters are queried. */ -static struct rb_node *mlx5_fc_stats_query(struct mlx5_core_dev *dev, +static struct mlx5_fc *mlx5_fc_stats_query(struct mlx5_core_dev *dev, struct mlx5_fc *first, u32 last_id) { + struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + struct mlx5_fc *counter = NULL; struct mlx5_cmd_fc_bulk *b; - struct rb_node *node = NULL; + bool more = false; u32 afirst_id; int num; int err; @@ -132,14 +134,16 @@ static struct rb_node *mlx5_fc_stats_query(struct mlx5_core_dev *dev, goto out; } - for (node = &first->node; node; node = rb_next(node)) { - struct mlx5_fc *counter = rb_entry(node, struct mlx5_fc, node); + counter = first; + list_for_each_entry_from(counter, &fc_stats->counters, list) { struct mlx5_fc_cache *c = &counter->cache; u64 packets; u64 bytes; - if (counter->id > last_id) + if (counter->id > last_id) { + more = true; break; + } mlx5_cmd_fc_bulk_get(dev, b, counter->id, &packets, &bytes); @@ -155,7 +159,7 @@ static struct rb_node *mlx5_fc_stats_query(struct mlx5_core_dev *dev, out: mlx5_cmd_fc_bulk_free(b); - return node; + return more ? counter : NULL; } static void mlx5_free_fc(struct mlx5_core_dev *dev, @@ -173,33 +177,30 @@ static void mlx5_fc_stats_work(struct work_struct *work) struct llist_node *tmplist = llist_del_all(&fc_stats->addlist); struct mlx5_fc *counter = NULL, *last = NULL, *tmp; unsigned long now = jiffies; - struct rb_node *node; - if (tmplist || !RB_EMPTY_ROOT(&fc_stats->counters)) + if (tmplist || !list_empty(&fc_stats->counters)) queue_delayed_work(fc_stats->wq, &fc_stats->work, fc_stats->sampling_interval); llist_for_each_entry(counter, tmplist, addlist) - mlx5_fc_stats_insert(&fc_stats->counters, counter); + mlx5_fc_stats_insert(dev, counter); tmplist = llist_del_all(&fc_stats->dellist); llist_for_each_entry_safe(counter, tmp, tmplist, dellist) { - rb_erase(&counter->node, &fc_stats->counters); + list_del(&counter->list); mlx5_free_fc(dev, counter); } - node = rb_last(&fc_stats->counters); - if (time_before(now, fc_stats->next_query) || !node) + if (time_before(now, fc_stats->next_query) || + list_empty(&fc_stats->counters)) return; - last = rb_entry(node, struct mlx5_fc, node); - - node = rb_first(&fc_stats->counters); - while (node) { - counter = rb_entry(node, struct mlx5_fc, node); + last = list_last_entry(&fc_stats->counters, struct mlx5_fc, list); - node = mlx5_fc_stats_query(dev, counter, last->id); - } + counter = list_first_entry(&fc_stats->counters, struct mlx5_fc, + list); + while (counter) + counter = mlx5_fc_stats_query(dev, counter, last->id); fc_stats->next_query = now + fc_stats->sampling_interval; } @@ -257,7 +258,7 @@ int mlx5_init_fc_stats(struct mlx5_core_dev *dev) { struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; - fc_stats->counters = RB_ROOT; + INIT_LIST_HEAD(&fc_stats->counters); init_llist_head(&fc_stats->addlist); init_llist_head(&fc_stats->dellist); @@ -277,7 +278,6 @@ void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev) struct llist_node *tmplist; struct mlx5_fc *counter; struct mlx5_fc *tmp; - struct rb_node *node; cancel_delayed_work_sync(&dev->priv.fc_stats.work); destroy_workqueue(dev->priv.fc_stats.wq); @@ -287,16 +287,8 @@ void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev) llist_for_each_entry_safe(counter, tmp, tmplist, addlist) mlx5_free_fc(dev, counter); - node = rb_first(&fc_stats->counters); - while (node) { - counter = rb_entry(node, struct mlx5_fc, node); - - node = rb_next(node); - - rb_erase(&counter->node, &fc_stats->counters); - + list_for_each_entry_safe(counter, tmp, &fc_stats->counters, list) mlx5_free_fc(dev, counter); - } } int mlx5_fc_query(struct mlx5_core_dev *dev, struct mlx5_fc *counter, diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 4b53ac64004b..61bed33e6675 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -583,7 +583,7 @@ struct mlx5_irq_info { }; struct mlx5_fc_stats { - struct rb_root counters; + struct list_head counters; struct llist_head addlist; struct llist_head dellist; -- cgit v1.2.3 From 12d6066c3b29c5606c4a2466f964fbd9ede803c5 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Tue, 24 Jul 2018 16:37:40 +0300 Subject: net/mlx5: Add flow counters idr Previous patch in series changed flow counter storage structure from rb_tree to linked list in order to improve flow counter traversal performance. The drawback of such solution is that flow counter lookup by id becomes linear in complexity. Store pointers to flow counters in idr in order to improve lookup performance to logarithmic again. Idr is non-intrusive data structure and doesn't require extending flow counter struct with new elements. This means that idr can be used for lookup, while linked list from previous patch is used for traversal, and struct mlx5_fc size is <= 2 cache lines. Signed-off-by: Vlad Buslov Acked-by: Amir Vadai Reviewed-by: Paul Blakey Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/fs_counters.c | 37 +++++++++++++++++++--- include/linux/mlx5/driver.h | 2 ++ 2 files changed, 35 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c index 90ebfee37508..09206c4acd9a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c @@ -77,13 +77,18 @@ static struct list_head *mlx5_fc_counters_lookup_next(struct mlx5_core_dev *dev, u32 id) { struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + unsigned long next_id = (unsigned long)id + 1; struct mlx5_fc *counter; - list_for_each_entry(counter, &fc_stats->counters, list) - if (counter->id > id) - return &counter->list; + rcu_read_lock(); + /* skip counters that are in idr, but not yet in counters list */ + while ((counter = idr_get_next_ul(&fc_stats->counters_idr, + &next_id)) != NULL && + list_empty(&counter->list)) + next_id++; + rcu_read_unlock(); - return &fc_stats->counters; + return counter ? &counter->list : &fc_stats->counters; } static void mlx5_fc_stats_insert(struct mlx5_core_dev *dev, @@ -214,15 +219,29 @@ struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging) counter = kzalloc(sizeof(*counter), GFP_KERNEL); if (!counter) return ERR_PTR(-ENOMEM); + INIT_LIST_HEAD(&counter->list); err = mlx5_cmd_fc_alloc(dev, &counter->id); if (err) goto err_out; if (aging) { + u32 id = counter->id; + counter->cache.lastuse = jiffies; counter->aging = true; + idr_preload(GFP_KERNEL); + spin_lock(&fc_stats->counters_idr_lock); + + err = idr_alloc_u32(&fc_stats->counters_idr, counter, &id, id, + GFP_NOWAIT); + + spin_unlock(&fc_stats->counters_idr_lock); + idr_preload_end(); + if (err) + goto err_out_alloc; + llist_add(&counter->addlist, &fc_stats->addlist); mod_delayed_work(fc_stats->wq, &fc_stats->work, 0); @@ -230,6 +249,8 @@ struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging) return counter; +err_out_alloc: + mlx5_cmd_fc_free(dev, counter->id); err_out: kfree(counter); @@ -245,6 +266,10 @@ void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter) return; if (counter->aging) { + spin_lock(&fc_stats->counters_idr_lock); + WARN_ON(!idr_remove(&fc_stats->counters_idr, counter->id)); + spin_unlock(&fc_stats->counters_idr_lock); + llist_add(&counter->dellist, &fc_stats->dellist); mod_delayed_work(fc_stats->wq, &fc_stats->work, 0); return; @@ -258,6 +283,8 @@ int mlx5_init_fc_stats(struct mlx5_core_dev *dev) { struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + spin_lock_init(&fc_stats->counters_idr_lock); + idr_init(&fc_stats->counters_idr); INIT_LIST_HEAD(&fc_stats->counters); init_llist_head(&fc_stats->addlist); init_llist_head(&fc_stats->dellist); @@ -283,6 +310,8 @@ void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev) destroy_workqueue(dev->priv.fc_stats.wq); dev->priv.fc_stats.wq = NULL; + idr_destroy(&fc_stats->counters_idr); + tmplist = llist_del_all(&fc_stats->addlist); llist_for_each_entry_safe(counter, tmp, tmplist, addlist) mlx5_free_fc(dev, counter); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 61bed33e6675..2a0c845f6bdb 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -583,6 +583,8 @@ struct mlx5_irq_info { }; struct mlx5_fc_stats { + spinlock_t counters_idr_lock; /* protects counters_idr */ + struct idr counters_idr; struct list_head counters; struct llist_head addlist; struct llist_head dellist; -- cgit v1.2.3 From 64109f1dc41f25f4a9c6b114e04b6266bf4128ad Mon Sep 17 00:00:00 2001 From: Shay Agroskin Date: Tue, 5 Jun 2018 09:22:18 +0300 Subject: net/mlx5e: Replace PTP clock lock from RW lock to seq lock Changed "priv.clock.lock" lock from 'rw_lock' to 'seq_lock' in order to improve packet rate performance. Tested on Intel(R) Xeon(R) CPU E5-2660 v2 @ 2.20GHz. Sent 64b packets between two peers connected by ConnectX-5, and measured packet rate for the receiver in three modes: no time-stamping (base rate) time-stamping using rw_lock (old lock) for critical region time-stamping using seq_lock (new lock) for critical region Only the receiver time stamped its packets. The measured packet rate improvements are: Single flow (multiple TX rings to single RX ring): without timestamping: 4.26 (M packets)/sec with rw-lock (old lock): 4.1 (M packets)/sec with seq-lock (new lock): 4.16 (M packets)/sec 1.46% improvement Multiple flows (multiple TX rings to six RX rings): without timestamping: 22 (M packets)/sec with rw-lock (old lock): 11.7 (M packets)/sec with seq-lock (new lock): 21.3 (M packets)/sec 82.05% improvement The packet rate improvement is due to the lack of atomic operations for the 'readers' by the seq-lock. Since there are much more 'readers' than 'writers' contention on this lock, almost all atomic operations are saved. this results in a dramatic decrease in overall cache misses. Signed-off-by: Shay Agroskin Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/lib/clock.c | 34 +++++++++++----------- .../net/ethernet/mellanox/mlx5/core/lib/clock.h | 8 +++-- include/linux/mlx5/driver.h | 2 +- 3 files changed, 23 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index 3f767cde4c1d..0d90b1b4a3d3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -111,10 +111,10 @@ static void mlx5_pps_out(struct work_struct *work) for (i = 0; i < clock->ptp_info.n_pins; i++) { u64 tstart; - write_lock_irqsave(&clock->lock, flags); + write_seqlock_irqsave(&clock->lock, flags); tstart = clock->pps_info.start[i]; clock->pps_info.start[i] = 0; - write_unlock_irqrestore(&clock->lock, flags); + write_sequnlock_irqrestore(&clock->lock, flags); if (!tstart) continue; @@ -132,10 +132,10 @@ static void mlx5_timestamp_overflow(struct work_struct *work) overflow_work); unsigned long flags; - write_lock_irqsave(&clock->lock, flags); + write_seqlock_irqsave(&clock->lock, flags); timecounter_read(&clock->tc); mlx5_update_clock_info_page(clock->mdev); - write_unlock_irqrestore(&clock->lock, flags); + write_sequnlock_irqrestore(&clock->lock, flags); schedule_delayed_work(&clock->overflow_work, clock->overflow_period); } @@ -147,10 +147,10 @@ static int mlx5_ptp_settime(struct ptp_clock_info *ptp, u64 ns = timespec64_to_ns(ts); unsigned long flags; - write_lock_irqsave(&clock->lock, flags); + write_seqlock_irqsave(&clock->lock, flags); timecounter_init(&clock->tc, &clock->cycles, ns); mlx5_update_clock_info_page(clock->mdev); - write_unlock_irqrestore(&clock->lock, flags); + write_sequnlock_irqrestore(&clock->lock, flags); return 0; } @@ -162,9 +162,9 @@ static int mlx5_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) u64 ns; unsigned long flags; - write_lock_irqsave(&clock->lock, flags); + write_seqlock_irqsave(&clock->lock, flags); ns = timecounter_read(&clock->tc); - write_unlock_irqrestore(&clock->lock, flags); + write_sequnlock_irqrestore(&clock->lock, flags); *ts = ns_to_timespec64(ns); @@ -177,10 +177,10 @@ static int mlx5_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) ptp_info); unsigned long flags; - write_lock_irqsave(&clock->lock, flags); + write_seqlock_irqsave(&clock->lock, flags); timecounter_adjtime(&clock->tc, delta); mlx5_update_clock_info_page(clock->mdev); - write_unlock_irqrestore(&clock->lock, flags); + write_sequnlock_irqrestore(&clock->lock, flags); return 0; } @@ -203,12 +203,12 @@ static int mlx5_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta) adj *= delta; diff = div_u64(adj, 1000000000ULL); - write_lock_irqsave(&clock->lock, flags); + write_seqlock_irqsave(&clock->lock, flags); timecounter_read(&clock->tc); clock->cycles.mult = neg_adj ? clock->nominal_c_mult - diff : clock->nominal_c_mult + diff; mlx5_update_clock_info_page(clock->mdev); - write_unlock_irqrestore(&clock->lock, flags); + write_sequnlock_irqrestore(&clock->lock, flags); return 0; } @@ -307,12 +307,12 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp, ts.tv_nsec = rq->perout.start.nsec; ns = timespec64_to_ns(&ts); cycles_now = mlx5_read_internal_timer(mdev); - write_lock_irqsave(&clock->lock, flags); + write_seqlock_irqsave(&clock->lock, flags); nsec_now = timecounter_cyc2time(&clock->tc, cycles_now); nsec_delta = ns - nsec_now; cycles_delta = div64_u64(nsec_delta << clock->cycles.shift, clock->cycles.mult); - write_unlock_irqrestore(&clock->lock, flags); + write_sequnlock_irqrestore(&clock->lock, flags); time_stamp = cycles_now + cycles_delta; field_select = MLX5_MTPPS_FS_PIN_MODE | MLX5_MTPPS_FS_PATTERN | @@ -471,14 +471,14 @@ void mlx5_pps_event(struct mlx5_core_dev *mdev, ts.tv_sec += 1; ts.tv_nsec = 0; ns = timespec64_to_ns(&ts); - write_lock_irqsave(&clock->lock, flags); + write_seqlock_irqsave(&clock->lock, flags); nsec_now = timecounter_cyc2time(&clock->tc, cycles_now); nsec_delta = ns - nsec_now; cycles_delta = div64_u64(nsec_delta << clock->cycles.shift, clock->cycles.mult); clock->pps_info.start[pin] = cycles_now + cycles_delta; schedule_work(&clock->pps_info.out_work); - write_unlock_irqrestore(&clock->lock, flags); + write_sequnlock_irqrestore(&clock->lock, flags); break; default: mlx5_core_err(mdev, " Unhandled event\n"); @@ -498,7 +498,7 @@ void mlx5_init_clock(struct mlx5_core_dev *mdev) mlx5_core_warn(mdev, "invalid device_frequency_khz, aborting HW clock init\n"); return; } - rwlock_init(&clock->lock); + seqlock_init(&clock->lock); clock->cycles.read = read_internal_timer; clock->cycles.shift = MLX5_CYCLES_SHIFT; clock->cycles.mult = clocksource_khz2mult(dev_freq, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h index 02e2e4575e4f..263cb6e2aeee 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h @@ -46,11 +46,13 @@ static inline int mlx5_clock_get_ptp_index(struct mlx5_core_dev *mdev) static inline ktime_t mlx5_timecounter_cyc2time(struct mlx5_clock *clock, u64 timestamp) { + unsigned int seq; u64 nsec; - read_lock(&clock->lock); - nsec = timecounter_cyc2time(&clock->tc, timestamp); - read_unlock(&clock->lock); + do { + seq = read_seqbegin(&clock->lock); + nsec = timecounter_cyc2time(&clock->tc, timestamp); + } while (read_seqretry(&clock->lock, seq)); return ns_to_ktime(nsec); } diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 2a0c845f6bdb..b7fce2c9443d 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -805,7 +805,7 @@ struct mlx5_pps { }; struct mlx5_clock { - rwlock_t lock; + seqlock_t lock; struct cyclecounter cycles; struct timecounter tc; struct hwtstamp_config hwtstamp_config; -- cgit v1.2.3 From fa788d986a3aac5069378ed04697bd06f83d3488 Mon Sep 17 00:00:00 2001 From: Vincent Whitchurch Date: Mon, 3 Sep 2018 16:23:36 +0200 Subject: packet: add sockopt to ignore outgoing packets Currently, the only way to ignore outgoing packets on a packet socket is via the BPF filter. With MSG_ZEROCOPY, packets that are looped into AF_PACKET are copied in dev_queue_xmit_nit(), and this copy happens even if the filter run from packet_rcv() would reject them. So the presence of a packet socket on the interface takes away the benefits of MSG_ZEROCOPY, even if the packet socket is not interested in outgoing packets. (Even when MSG_ZEROCOPY is not used, the skb is unnecessarily cloned, but the cost for that is much lower.) Add a socket option to allow AF_PACKET sockets to ignore outgoing packets to solve this. Note that the *BSDs already have something similar: BIOCSSEESENT/BIOCSDIRECTION and BIOCSDIRFILT. The first intended user is lldpd. Signed-off-by: Vincent Whitchurch Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + include/uapi/linux/if_packet.h | 1 + net/core/dev.c | 3 +++ net/packet/af_packet.c | 17 +++++++++++++++++ 4 files changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 4271f6b4e419..e2b3bd750c98 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2343,6 +2343,7 @@ static inline struct sk_buff *call_gro_receive_sk(gro_receive_sk_t cb, struct packet_type { __be16 type; /* This is really htons(ether_type). */ + bool ignore_outgoing; struct net_device *dev; /* NULL is wildcarded here */ int (*func) (struct sk_buff *, struct net_device *, diff --git a/include/uapi/linux/if_packet.h b/include/uapi/linux/if_packet.h index 67b61d91d89b..467b654bd4c7 100644 --- a/include/uapi/linux/if_packet.h +++ b/include/uapi/linux/if_packet.h @@ -57,6 +57,7 @@ struct sockaddr_ll { #define PACKET_QDISC_BYPASS 20 #define PACKET_ROLLOVER_STATS 21 #define PACKET_FANOUT_DATA 22 +#define PACKET_IGNORE_OUTGOING 23 #define PACKET_FANOUT_HASH 0 #define PACKET_FANOUT_LB 1 diff --git a/net/core/dev.c b/net/core/dev.c index 82114e1111e6..ca78dc5a79a3 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1969,6 +1969,9 @@ void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) rcu_read_lock(); again: list_for_each_entry_rcu(ptype, ptype_list, list) { + if (ptype->ignore_outgoing) + continue; + /* Never send packets back to the socket * they originated from - MvS (miquels@drinkel.ow.org) */ diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 75c92a87e7b2..f85f67b5c1f4 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3805,6 +3805,20 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv return fanout_set_data(po, optval, optlen); } + case PACKET_IGNORE_OUTGOING: + { + int val; + + if (optlen != sizeof(val)) + return -EINVAL; + if (copy_from_user(&val, optval, sizeof(val))) + return -EFAULT; + if (val < 0 || val > 1) + return -EINVAL; + + po->prot_hook.ignore_outgoing = !!val; + return 0; + } case PACKET_TX_HAS_OFF: { unsigned int val; @@ -3928,6 +3942,9 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, ((u32)po->fanout->flags << 24)) : 0); break; + case PACKET_IGNORE_OUTGOING: + val = po->prot_hook.ignore_outgoing; + break; case PACKET_ROLLOVER_STATS: if (!po->rollover) return -EINVAL; -- cgit v1.2.3 From a3f723079df85eafc10c628dabdfcf374b8e1523 Mon Sep 17 00:00:00 2001 From: Denis Bolotin Date: Wed, 5 Sep 2018 18:35:55 +0300 Subject: qed*: Utilize FW 8.37.7.0 This patch adds a new qed firmware with fixes and support for new features. Fixes: - Fix a rare case of device crash with iWARP, iSCSI or FCoE offload. - Fix GRE tunneled traffic when iWARP offload is enabled. - Fix RoCE failure in ib_send_bw when using inline data. - Fix latency optimization flow for inline WQEs. - BigBear 100G fix RDMA: - Reduce task context size. - Application page sizes above 2GB support. - Performance improvements. ETH: - Tenant DCB support. - Replace RSS indirection table update interface. Misc: - Debug Tools changes. Signed-off-by: Denis Bolotin Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed.h | 1 + drivers/net/ethernet/qlogic/qed/qed_debug.c | 248 +++++++++++++---------- drivers/net/ethernet/qlogic/qed/qed_dev.c | 11 ++ drivers/net/ethernet/qlogic/qed/qed_hsi.h | 297 +++++++++++++++++++--------- include/linux/qed/common_hsi.h | 10 +- include/linux/qed/iscsi_common.h | 2 +- 6 files changed, 367 insertions(+), 202 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h index a60e1c8d470a..5f0962d353ce 100644 --- a/drivers/net/ethernet/qlogic/qed/qed.h +++ b/drivers/net/ethernet/qlogic/qed/qed.h @@ -623,6 +623,7 @@ struct qed_hwfn { void *unzip_buf; struct dbg_tools_data dbg_info; + void *dbg_user_info; /* PWM region specific data */ u16 wid_count; diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c index 1aa9fc1c5890..78a638ec7c0a 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_debug.c +++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c @@ -3454,7 +3454,8 @@ static u32 qed_grc_dump_iors(struct qed_hwfn *p_hwfn, addr = BYTES_TO_DWORDS(storm->sem_fast_mem_addr + SEM_FAST_REG_STORM_REG_FILE) + IOR_SET_OFFSET(set_id); - buf[strlen(buf) - 1] = '0' + set_id; + if (strlen(buf) > 0) + buf[strlen(buf) - 1] = '0' + set_id; offset += qed_grc_dump_mem(p_hwfn, p_ptt, dump_buf + offset, @@ -5563,35 +5564,6 @@ struct block_info { enum block_id id; }; -struct mcp_trace_format { - u32 data; -#define MCP_TRACE_FORMAT_MODULE_MASK 0x0000ffff -#define MCP_TRACE_FORMAT_MODULE_SHIFT 0 -#define MCP_TRACE_FORMAT_LEVEL_MASK 0x00030000 -#define MCP_TRACE_FORMAT_LEVEL_SHIFT 16 -#define MCP_TRACE_FORMAT_P1_SIZE_MASK 0x000c0000 -#define MCP_TRACE_FORMAT_P1_SIZE_SHIFT 18 -#define MCP_TRACE_FORMAT_P2_SIZE_MASK 0x00300000 -#define MCP_TRACE_FORMAT_P2_SIZE_SHIFT 20 -#define MCP_TRACE_FORMAT_P3_SIZE_MASK 0x00c00000 -#define MCP_TRACE_FORMAT_P3_SIZE_SHIFT 22 -#define MCP_TRACE_FORMAT_LEN_MASK 0xff000000 -#define MCP_TRACE_FORMAT_LEN_SHIFT 24 - - char *format_str; -}; - -/* Meta data structure, generated by a perl script during MFW build. therefore, - * the structs mcp_trace_meta and mcp_trace_format are duplicated in the perl - * script. - */ -struct mcp_trace_meta { - u32 modules_num; - char **modules; - u32 formats_num; - struct mcp_trace_format *formats; -}; - /* REG fifo element */ struct reg_fifo_element { u64 data; @@ -5714,6 +5686,20 @@ struct igu_fifo_addr_data { enum igu_fifo_addr_types type; }; +struct mcp_trace_meta { + u32 modules_num; + char **modules; + u32 formats_num; + struct mcp_trace_format *formats; + bool is_allocated; +}; + +/* Debug Tools user data */ +struct dbg_tools_user_data { + struct mcp_trace_meta mcp_trace_meta; + const u32 *mcp_trace_user_meta_buf; +}; + /******************************** Constants **********************************/ #define MAX_MSG_LEN 1024 @@ -6137,15 +6123,6 @@ static const struct igu_fifo_addr_data s_igu_fifo_addr_data[] = { /******************************** Variables **********************************/ -/* MCP Trace meta data array - used in case the dump doesn't contain the - * meta data (e.g. due to no NVRAM access). - */ -static struct user_dbg_array s_mcp_trace_meta_arr = { NULL, 0 }; - -/* Parsed MCP Trace meta data info, based on MCP trace meta array */ -static struct mcp_trace_meta s_mcp_trace_meta; -static bool s_mcp_trace_meta_valid; - /* Temporary buffer, used for print size calculations */ static char s_temp_buf[MAX_MSG_LEN]; @@ -6311,6 +6288,12 @@ static u32 qed_print_section_params(u32 *dump_buf, return dump_offset; } +static struct dbg_tools_user_data * +qed_dbg_get_user_data(struct qed_hwfn *p_hwfn) +{ + return (struct dbg_tools_user_data *)p_hwfn->dbg_user_info; +} + /* Parses the idle check rules and returns the number of characters printed. * In case of parsing error, returns 0. */ @@ -6570,43 +6553,26 @@ static enum dbg_status qed_parse_idle_chk_dump(u32 *dump_buf, return DBG_STATUS_OK; } -/* Frees the specified MCP Trace meta data */ -static void qed_mcp_trace_free_meta(struct qed_hwfn *p_hwfn, - struct mcp_trace_meta *meta) -{ - u32 i; - - s_mcp_trace_meta_valid = false; - - /* Release modules */ - if (meta->modules) { - for (i = 0; i < meta->modules_num; i++) - kfree(meta->modules[i]); - kfree(meta->modules); - } - - /* Release formats */ - if (meta->formats) { - for (i = 0; i < meta->formats_num; i++) - kfree(meta->formats[i].format_str); - kfree(meta->formats); - } -} - /* Allocates and fills MCP Trace meta data based on the specified meta data * dump buffer. * Returns debug status code. */ -static enum dbg_status qed_mcp_trace_alloc_meta(struct qed_hwfn *p_hwfn, - const u32 *meta_buf, - struct mcp_trace_meta *meta) +static enum dbg_status +qed_mcp_trace_alloc_meta_data(struct qed_hwfn *p_hwfn, + const u32 *meta_buf) { - u8 *meta_buf_bytes = (u8 *)meta_buf; + struct dbg_tools_user_data *dev_user_data; u32 offset = 0, signature, i; + struct mcp_trace_meta *meta; + u8 *meta_buf_bytes; + + dev_user_data = qed_dbg_get_user_data(p_hwfn); + meta = &dev_user_data->mcp_trace_meta; + meta_buf_bytes = (u8 *)meta_buf; /* Free the previous meta before loading a new one. */ - if (s_mcp_trace_meta_valid) - qed_mcp_trace_free_meta(p_hwfn, meta); + if (meta->is_allocated) + qed_mcp_trace_free_meta_data(p_hwfn); memset(meta, 0, sizeof(*meta)); @@ -6674,7 +6640,7 @@ static enum dbg_status qed_mcp_trace_alloc_meta(struct qed_hwfn *p_hwfn, format_len, format_ptr->format_str); } - s_mcp_trace_meta_valid = true; + meta->is_allocated = true; return DBG_STATUS_OK; } @@ -6687,21 +6653,26 @@ static enum dbg_status qed_mcp_trace_alloc_meta(struct qed_hwfn *p_hwfn, * buffer. * data_size - size in bytes of data to parse. * parsed_buf - destination buffer for parsed data. - * parsed_bytes - size of parsed data in bytes. + * parsed_results_bytes - size of parsed data in bytes. */ -static enum dbg_status qed_parse_mcp_trace_buf(u8 *trace_buf, +static enum dbg_status qed_parse_mcp_trace_buf(struct qed_hwfn *p_hwfn, + u8 *trace_buf, u32 trace_buf_size, u32 data_offset, u32 data_size, char *parsed_buf, - u32 *parsed_bytes) + u32 *parsed_results_bytes) { + struct dbg_tools_user_data *dev_user_data; + struct mcp_trace_meta *meta; u32 param_mask, param_shift; enum dbg_status status; - *parsed_bytes = 0; + dev_user_data = qed_dbg_get_user_data(p_hwfn); + meta = &dev_user_data->mcp_trace_meta; + *parsed_results_bytes = 0; - if (!s_mcp_trace_meta_valid) + if (!meta->is_allocated) return DBG_STATUS_MCP_TRACE_BAD_DATA; status = DBG_STATUS_OK; @@ -6723,7 +6694,7 @@ static enum dbg_status qed_parse_mcp_trace_buf(u8 *trace_buf, format_idx = header & MFW_TRACE_EVENTID_MASK; /* Skip message if its index doesn't exist in the meta data */ - if (format_idx >= s_mcp_trace_meta.formats_num) { + if (format_idx >= meta->formats_num) { u8 format_size = (u8)((header & MFW_TRACE_PRM_SIZE_MASK) >> MFW_TRACE_PRM_SIZE_SHIFT); @@ -6738,7 +6709,7 @@ static enum dbg_status qed_parse_mcp_trace_buf(u8 *trace_buf, continue; } - format_ptr = &s_mcp_trace_meta.formats[format_idx]; + format_ptr = &meta->formats[format_idx]; for (i = 0, param_mask = MCP_TRACE_FORMAT_P1_SIZE_MASK, @@ -6783,19 +6754,20 @@ static enum dbg_status qed_parse_mcp_trace_buf(u8 *trace_buf, return DBG_STATUS_MCP_TRACE_BAD_DATA; /* Print current message to results buffer */ - *parsed_bytes += - sprintf(qed_get_buf_ptr(parsed_buf, *parsed_bytes), + *parsed_results_bytes += + sprintf(qed_get_buf_ptr(parsed_buf, + *parsed_results_bytes), "%s %-8s: ", s_mcp_trace_level_str[format_level], - s_mcp_trace_meta.modules[format_module]); - *parsed_bytes += - sprintf(qed_get_buf_ptr(parsed_buf, *parsed_bytes), + meta->modules[format_module]); + *parsed_results_bytes += + sprintf(qed_get_buf_ptr(parsed_buf, *parsed_results_bytes), format_ptr->format_str, params[0], params[1], params[2]); } /* Add string NULL terminator */ - (*parsed_bytes)++; + (*parsed_results_bytes)++; return status; } @@ -6803,24 +6775,25 @@ static enum dbg_status qed_parse_mcp_trace_buf(u8 *trace_buf, /* Parses an MCP Trace dump buffer. * If result_buf is not NULL, the MCP Trace results are printed to it. * In any case, the required results buffer size is assigned to - * parsed_bytes. + * parsed_results_bytes. * The parsing status is returned. */ static enum dbg_status qed_parse_mcp_trace_dump(struct qed_hwfn *p_hwfn, u32 *dump_buf, - char *parsed_buf, - u32 *parsed_bytes) + char *results_buf, + u32 *parsed_results_bytes, + bool free_meta_data) { const char *section_name, *param_name, *param_str_val; u32 data_size, trace_data_dwords, trace_meta_dwords; - u32 offset, results_offset, parsed_buf_bytes; + u32 offset, results_offset, results_buf_bytes; u32 param_num_val, num_section_params; struct mcp_trace *trace; enum dbg_status status; const u32 *meta_buf; u8 *trace_buf; - *parsed_bytes = 0; + *parsed_results_bytes = 0; /* Read global_params section */ dump_buf += qed_read_section_hdr(dump_buf, @@ -6831,7 +6804,7 @@ static enum dbg_status qed_parse_mcp_trace_dump(struct qed_hwfn *p_hwfn, /* Print global params */ dump_buf += qed_print_section_params(dump_buf, num_section_params, - parsed_buf, &results_offset); + results_buf, &results_offset); /* Read trace_data section */ dump_buf += qed_read_section_hdr(dump_buf, @@ -6846,6 +6819,9 @@ static enum dbg_status qed_parse_mcp_trace_dump(struct qed_hwfn *p_hwfn, /* Prepare trace info */ trace = (struct mcp_trace *)dump_buf; + if (trace->signature != MFW_TRACE_SIGNATURE || !trace->size) + return DBG_STATUS_MCP_TRACE_BAD_DATA; + trace_buf = (u8 *)dump_buf + sizeof(*trace); offset = trace->trace_oldest; data_size = qed_cyclic_sub(trace->trace_prod, offset, trace->size); @@ -6865,31 +6841,39 @@ static enum dbg_status qed_parse_mcp_trace_dump(struct qed_hwfn *p_hwfn, /* Choose meta data buffer */ if (!trace_meta_dwords) { /* Dump doesn't include meta data */ - if (!s_mcp_trace_meta_arr.ptr) + struct dbg_tools_user_data *dev_user_data = + qed_dbg_get_user_data(p_hwfn); + + if (!dev_user_data->mcp_trace_user_meta_buf) return DBG_STATUS_MCP_TRACE_NO_META; - meta_buf = s_mcp_trace_meta_arr.ptr; + + meta_buf = dev_user_data->mcp_trace_user_meta_buf; } else { /* Dump includes meta data */ meta_buf = dump_buf; } /* Allocate meta data memory */ - status = qed_mcp_trace_alloc_meta(p_hwfn, meta_buf, &s_mcp_trace_meta); + status = qed_mcp_trace_alloc_meta_data(p_hwfn, meta_buf); if (status != DBG_STATUS_OK) return status; - status = qed_parse_mcp_trace_buf(trace_buf, + status = qed_parse_mcp_trace_buf(p_hwfn, + trace_buf, trace->size, offset, data_size, - parsed_buf ? - parsed_buf + results_offset : + results_buf ? + results_buf + results_offset : NULL, - &parsed_buf_bytes); + &results_buf_bytes); if (status != DBG_STATUS_OK) return status; - *parsed_bytes = results_offset + parsed_buf_bytes; + if (free_meta_data) + qed_mcp_trace_free_meta_data(p_hwfn); + + *parsed_results_bytes = results_offset + results_buf_bytes; return DBG_STATUS_OK; } @@ -7361,6 +7345,16 @@ enum dbg_status qed_dbg_user_set_bin_ptr(const u8 * const bin_ptr) return DBG_STATUS_OK; } +enum dbg_status qed_dbg_alloc_user_data(struct qed_hwfn *p_hwfn) +{ + p_hwfn->dbg_user_info = kzalloc(sizeof(struct dbg_tools_user_data), + GFP_KERNEL); + if (!p_hwfn->dbg_user_info) + return DBG_STATUS_VIRT_MEM_ALLOC_FAILED; + + return DBG_STATUS_OK; +} + const char *qed_dbg_get_status_str(enum dbg_status status) { return (status < @@ -7397,10 +7391,13 @@ enum dbg_status qed_print_idle_chk_results(struct qed_hwfn *p_hwfn, num_errors, num_warnings); } -void qed_dbg_mcp_trace_set_meta_data(u32 *data, u32 size) +void qed_dbg_mcp_trace_set_meta_data(struct qed_hwfn *p_hwfn, + const u32 *meta_buf) { - s_mcp_trace_meta_arr.ptr = data; - s_mcp_trace_meta_arr.size_in_dwords = size; + struct dbg_tools_user_data *dev_user_data = + qed_dbg_get_user_data(p_hwfn); + + dev_user_data->mcp_trace_user_meta_buf = meta_buf; } enum dbg_status qed_get_mcp_trace_results_buf_size(struct qed_hwfn *p_hwfn, @@ -7409,7 +7406,7 @@ enum dbg_status qed_get_mcp_trace_results_buf_size(struct qed_hwfn *p_hwfn, u32 *results_buf_size) { return qed_parse_mcp_trace_dump(p_hwfn, - dump_buf, NULL, results_buf_size); + dump_buf, NULL, results_buf_size, true); } enum dbg_status qed_print_mcp_trace_results(struct qed_hwfn *p_hwfn, @@ -7421,20 +7418,61 @@ enum dbg_status qed_print_mcp_trace_results(struct qed_hwfn *p_hwfn, return qed_parse_mcp_trace_dump(p_hwfn, dump_buf, - results_buf, &parsed_buf_size); + results_buf, &parsed_buf_size, true); +} + +enum dbg_status qed_print_mcp_trace_results_cont(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + char *results_buf) +{ + u32 parsed_buf_size; + + return qed_parse_mcp_trace_dump(p_hwfn, dump_buf, results_buf, + &parsed_buf_size, false); } -enum dbg_status qed_print_mcp_trace_line(u8 *dump_buf, +enum dbg_status qed_print_mcp_trace_line(struct qed_hwfn *p_hwfn, + u8 *dump_buf, u32 num_dumped_bytes, char *results_buf) { - u32 parsed_bytes; + u32 parsed_results_bytes; - return qed_parse_mcp_trace_buf(dump_buf, + return qed_parse_mcp_trace_buf(p_hwfn, + dump_buf, num_dumped_bytes, 0, num_dumped_bytes, - results_buf, &parsed_bytes); + results_buf, &parsed_results_bytes); +} + +/* Frees the specified MCP Trace meta data */ +void qed_mcp_trace_free_meta_data(struct qed_hwfn *p_hwfn) +{ + struct dbg_tools_user_data *dev_user_data; + struct mcp_trace_meta *meta; + u32 i; + + dev_user_data = qed_dbg_get_user_data(p_hwfn); + meta = &dev_user_data->mcp_trace_meta; + if (!meta->is_allocated) + return; + + /* Release modules */ + if (meta->modules) { + for (i = 0; i < meta->modules_num; i++) + kfree(meta->modules[i]); + kfree(meta->modules); + } + + /* Release formats */ + if (meta->formats) { + for (i = 0; i < meta->formats_num; i++) + kfree(meta->formats[i].format_str); + kfree(meta->formats); + } + + meta->is_allocated = false; } enum dbg_status qed_get_reg_fifo_results_buf_size(struct qed_hwfn *p_hwfn, diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index 016ca8a7ec8a..128eb63ca54a 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -144,6 +144,12 @@ static void qed_qm_info_free(struct qed_hwfn *p_hwfn) qm_info->wfq_data = NULL; } +static void qed_dbg_user_data_free(struct qed_hwfn *p_hwfn) +{ + kfree(p_hwfn->dbg_user_info); + p_hwfn->dbg_user_info = NULL; +} + void qed_resc_free(struct qed_dev *cdev) { int i; @@ -183,6 +189,7 @@ void qed_resc_free(struct qed_dev *cdev) qed_l2_free(p_hwfn); qed_dmae_info_free(p_hwfn); qed_dcbx_info_free(p_hwfn); + qed_dbg_user_data_free(p_hwfn); } } @@ -1083,6 +1090,10 @@ int qed_resc_alloc(struct qed_dev *cdev) rc = qed_dcbx_info_alloc(p_hwfn); if (rc) goto alloc_err; + + rc = qed_dbg_alloc_user_data(p_hwfn); + if (rc) + goto alloc_err; } cdev->reset_stats = kzalloc(sizeof(*cdev->reset_stats), GFP_KERNEL); diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h index 8faceb691657..21ec8091a24a 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h @@ -274,7 +274,8 @@ struct core_rx_start_ramrod_data { u8 mf_si_mcast_accept_all; struct core_rx_action_on_error action_on_error; u8 gsi_offload_flag; - u8 reserved[6]; + u8 wipe_inner_vlan_pri_en; + u8 reserved[5]; }; /* Ramrod data for rx queue stop ramrod */ @@ -351,7 +352,8 @@ struct core_tx_start_ramrod_data { __le16 pbl_size; __le16 qm_pq_id; u8 gsi_offload_flag; - u8 resrved[3]; + u8 vport_id; + u8 resrved[2]; }; /* Ramrod data for tx queue stop ramrod */ @@ -914,6 +916,16 @@ struct eth_rx_rate_limit { __le16 reserved1; }; +/* Update RSS indirection table entry command */ +struct eth_tstorm_rss_update_data { + u8 valid; + u8 vport_id; + u8 ind_table_index; + u8 reserved; + __le16 ind_table_value; + __le16 reserved1; +}; + struct eth_ustorm_per_pf_stat { struct regpair rcv_lb_ucast_bytes; struct regpair rcv_lb_mcast_bytes; @@ -1241,6 +1253,10 @@ struct rl_update_ramrod_data { u8 rl_id_first; u8 rl_id_last; u8 rl_dc_qcn_flg; + u8 dcqcn_reset_alpha_on_idle; + u8 rl_bc_stage_th; + u8 rl_timer_stage_th; + u8 reserved1; __le32 rl_bc_rate; __le16 rl_max_rate; __le16 rl_r_ai; @@ -1249,7 +1265,7 @@ struct rl_update_ramrod_data { __le32 dcqcn_k_us; __le32 dcqcn_timeuot_us; __le32 qcn_timeuot_us; - __le32 reserved[2]; + __le32 reserved2; }; /* Slowpath Element (SPQE) */ @@ -3322,6 +3338,25 @@ enum dbg_status qed_dbg_read_attn(struct qed_hwfn *p_hwfn, enum dbg_status qed_dbg_print_attn(struct qed_hwfn *p_hwfn, struct dbg_attn_block_result *results); +/******************************* Data Types **********************************/ + +struct mcp_trace_format { + u32 data; +#define MCP_TRACE_FORMAT_MODULE_MASK 0x0000ffff +#define MCP_TRACE_FORMAT_MODULE_SHIFT 0 +#define MCP_TRACE_FORMAT_LEVEL_MASK 0x00030000 +#define MCP_TRACE_FORMAT_LEVEL_SHIFT 16 +#define MCP_TRACE_FORMAT_P1_SIZE_MASK 0x000c0000 +#define MCP_TRACE_FORMAT_P1_SIZE_SHIFT 18 +#define MCP_TRACE_FORMAT_P2_SIZE_MASK 0x00300000 +#define MCP_TRACE_FORMAT_P2_SIZE_SHIFT 20 +#define MCP_TRACE_FORMAT_P3_SIZE_MASK 0x00c00000 +#define MCP_TRACE_FORMAT_P3_SIZE_SHIFT 22 +#define MCP_TRACE_FORMAT_LEN_MASK 0xff000000 +#define MCP_TRACE_FORMAT_LEN_SHIFT 24 + char *format_str; +}; + /******************************** Constants **********************************/ #define MAX_NAME_LEN 16 @@ -3336,6 +3371,13 @@ enum dbg_status qed_dbg_print_attn(struct qed_hwfn *p_hwfn, */ enum dbg_status qed_dbg_user_set_bin_ptr(const u8 * const bin_ptr); +/** + * @brief qed_dbg_alloc_user_data - Allocates user debug data. + * + * @param p_hwfn - HW device data + */ +enum dbg_status qed_dbg_alloc_user_data(struct qed_hwfn *p_hwfn); + /** * @brief qed_dbg_get_status_str - Returns a string for the specified status. * @@ -3381,8 +3423,7 @@ enum dbg_status qed_print_idle_chk_results(struct qed_hwfn *p_hwfn, u32 *num_warnings); /** - * @brief qed_dbg_mcp_trace_set_meta_data - Sets a pointer to the MCP Trace - * meta data. + * @brief qed_dbg_mcp_trace_set_meta_data - Sets the MCP Trace meta data. * * Needed in case the MCP Trace dump doesn't contain the meta data (e.g. due to * no NVRAM access). @@ -3390,7 +3431,8 @@ enum dbg_status qed_print_idle_chk_results(struct qed_hwfn *p_hwfn, * @param data - pointer to MCP Trace meta data * @param size - size of MCP Trace meta data in dwords */ -void qed_dbg_mcp_trace_set_meta_data(u32 *data, u32 size); +void qed_dbg_mcp_trace_set_meta_data(struct qed_hwfn *p_hwfn, + const u32 *meta_buf); /** * @brief qed_get_mcp_trace_results_buf_size - Returns the required buffer size @@ -3424,19 +3466,45 @@ enum dbg_status qed_print_mcp_trace_results(struct qed_hwfn *p_hwfn, u32 num_dumped_dwords, char *results_buf); +/** + * @brief qed_print_mcp_trace_results_cont - Prints MCP Trace results, and + * keeps the MCP trace meta data allocated, to support continuous MCP Trace + * parsing. After the continuous parsing ends, mcp_trace_free_meta_data should + * be called to free the meta data. + * + * @param p_hwfn - HW device data + * @param dump_buf - mcp trace dump buffer, starting from the header. + * @param results_buf - buffer for printing the mcp trace results. + * + * @return error if the parsing fails, ok otherwise. + */ +enum dbg_status qed_print_mcp_trace_results_cont(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + char *results_buf); + /** * @brief print_mcp_trace_line - Prints MCP Trace results for a single line * + * @param p_hwfn - HW device data * @param dump_buf - mcp trace dump buffer, starting from the header. * @param num_dumped_bytes - number of bytes that were dumped. * @param results_buf - buffer for printing the mcp trace results. * * @return error if the parsing fails, ok otherwise. */ -enum dbg_status qed_print_mcp_trace_line(u8 *dump_buf, +enum dbg_status qed_print_mcp_trace_line(struct qed_hwfn *p_hwfn, + u8 *dump_buf, u32 num_dumped_bytes, char *results_buf); +/** + * @brief mcp_trace_free_meta_data - Frees the MCP Trace meta data. + * Should be called after continuous MCP Trace parsing. + * + * @param p_hwfn - HW device data + */ +void qed_mcp_trace_free_meta_data(struct qed_hwfn *p_hwfn); + /** * @brief qed_get_reg_fifo_results_buf_size - Returns the required buffer size * for reg_fifo results (in bytes). @@ -4303,154 +4371,161 @@ void qed_set_rdma_error_level(struct qed_hwfn *p_hwfn, (IRO[29].base + ((pf_id) * IRO[29].m1)) #define ETH_RX_RATE_LIMIT_SIZE (IRO[29].size) +/* RSS indirection table entry update command per PF offset in TSTORM PF BAR0. + * Use eth_tstorm_rss_update_data for update. + */ +#define TSTORM_ETH_RSS_UPDATE_OFFSET(pf_id) \ + (IRO[30].base + ((pf_id) * IRO[30].m1)) +#define TSTORM_ETH_RSS_UPDATE_SIZE (IRO[30].size) + /* Xstorm queue zone */ #define XSTORM_ETH_QUEUE_ZONE_OFFSET(queue_id) \ - (IRO[30].base + ((queue_id) * IRO[30].m1)) -#define XSTORM_ETH_QUEUE_ZONE_SIZE (IRO[30].size) + (IRO[31].base + ((queue_id) * IRO[31].m1)) +#define XSTORM_ETH_QUEUE_ZONE_SIZE (IRO[31].size) /* Ystorm cqe producer */ #define YSTORM_TOE_CQ_PROD_OFFSET(rss_id) \ - (IRO[31].base + ((rss_id) * IRO[31].m1)) -#define YSTORM_TOE_CQ_PROD_SIZE (IRO[31].size) + (IRO[32].base + ((rss_id) * IRO[32].m1)) +#define YSTORM_TOE_CQ_PROD_SIZE (IRO[32].size) /* Ustorm cqe producer */ #define USTORM_TOE_CQ_PROD_OFFSET(rss_id) \ - (IRO[32].base + ((rss_id) * IRO[32].m1)) -#define USTORM_TOE_CQ_PROD_SIZE (IRO[32].size) + (IRO[33].base + ((rss_id) * IRO[33].m1)) +#define USTORM_TOE_CQ_PROD_SIZE (IRO[33].size) /* Ustorm grq producer */ #define USTORM_TOE_GRQ_PROD_OFFSET(pf_id) \ - (IRO[33].base + ((pf_id) * IRO[33].m1)) -#define USTORM_TOE_GRQ_PROD_SIZE (IRO[33].size) + (IRO[34].base + ((pf_id) * IRO[34].m1)) +#define USTORM_TOE_GRQ_PROD_SIZE (IRO[34].size) /* Tstorm cmdq-cons of given command queue-id */ #define TSTORM_SCSI_CMDQ_CONS_OFFSET(cmdq_queue_id) \ - (IRO[34].base + ((cmdq_queue_id) * IRO[34].m1)) -#define TSTORM_SCSI_CMDQ_CONS_SIZE (IRO[34].size) + (IRO[35].base + ((cmdq_queue_id) * IRO[35].m1)) +#define TSTORM_SCSI_CMDQ_CONS_SIZE (IRO[35].size) /* Tstorm (reflects M-Storm) bdq-external-producer of given function ID, * BDqueue-id. */ #define TSTORM_SCSI_BDQ_EXT_PROD_OFFSET(func_id, bdq_id) \ - (IRO[35].base + ((func_id) * IRO[35].m1) + ((bdq_id) * IRO[35].m2)) -#define TSTORM_SCSI_BDQ_EXT_PROD_SIZE (IRO[35].size) + (IRO[36].base + ((func_id) * IRO[36].m1) + ((bdq_id) * IRO[36].m2)) +#define TSTORM_SCSI_BDQ_EXT_PROD_SIZE (IRO[36].size) /* Mstorm bdq-external-producer of given BDQ resource ID, BDqueue-id */ #define MSTORM_SCSI_BDQ_EXT_PROD_OFFSET(func_id, bdq_id) \ - (IRO[36].base + ((func_id) * IRO[36].m1) + ((bdq_id) * IRO[36].m2)) -#define MSTORM_SCSI_BDQ_EXT_PROD_SIZE (IRO[36].size) + (IRO[37].base + ((func_id) * IRO[37].m1) + ((bdq_id) * IRO[37].m2)) +#define MSTORM_SCSI_BDQ_EXT_PROD_SIZE (IRO[37].size) /* Tstorm iSCSI RX stats */ #define TSTORM_ISCSI_RX_STATS_OFFSET(pf_id) \ - (IRO[37].base + ((pf_id) * IRO[37].m1)) -#define TSTORM_ISCSI_RX_STATS_SIZE (IRO[37].size) + (IRO[38].base + ((pf_id) * IRO[38].m1)) +#define TSTORM_ISCSI_RX_STATS_SIZE (IRO[38].size) /* Mstorm iSCSI RX stats */ #define MSTORM_ISCSI_RX_STATS_OFFSET(pf_id) \ - (IRO[38].base + ((pf_id) * IRO[38].m1)) -#define MSTORM_ISCSI_RX_STATS_SIZE (IRO[38].size) + (IRO[39].base + ((pf_id) * IRO[39].m1)) +#define MSTORM_ISCSI_RX_STATS_SIZE (IRO[39].size) /* Ustorm iSCSI RX stats */ #define USTORM_ISCSI_RX_STATS_OFFSET(pf_id) \ - (IRO[39].base + ((pf_id) * IRO[39].m1)) -#define USTORM_ISCSI_RX_STATS_SIZE (IRO[39].size) + (IRO[40].base + ((pf_id) * IRO[40].m1)) +#define USTORM_ISCSI_RX_STATS_SIZE (IRO[40].size) /* Xstorm iSCSI TX stats */ #define XSTORM_ISCSI_TX_STATS_OFFSET(pf_id) \ - (IRO[40].base + ((pf_id) * IRO[40].m1)) -#define XSTORM_ISCSI_TX_STATS_SIZE (IRO[40].size) + (IRO[41].base + ((pf_id) * IRO[41].m1)) +#define XSTORM_ISCSI_TX_STATS_SIZE (IRO[41].size) /* Ystorm iSCSI TX stats */ #define YSTORM_ISCSI_TX_STATS_OFFSET(pf_id) \ - (IRO[41].base + ((pf_id) * IRO[41].m1)) -#define YSTORM_ISCSI_TX_STATS_SIZE (IRO[41].size) + (IRO[42].base + ((pf_id) * IRO[42].m1)) +#define YSTORM_ISCSI_TX_STATS_SIZE (IRO[42].size) /* Pstorm iSCSI TX stats */ #define PSTORM_ISCSI_TX_STATS_OFFSET(pf_id) \ - (IRO[42].base + ((pf_id) * IRO[42].m1)) -#define PSTORM_ISCSI_TX_STATS_SIZE (IRO[42].size) + (IRO[43].base + ((pf_id) * IRO[43].m1)) +#define PSTORM_ISCSI_TX_STATS_SIZE (IRO[43].size) /* Tstorm FCoE RX stats */ #define TSTORM_FCOE_RX_STATS_OFFSET(pf_id) \ - (IRO[43].base + ((pf_id) * IRO[43].m1)) -#define TSTORM_FCOE_RX_STATS_SIZE (IRO[43].size) + (IRO[44].base + ((pf_id) * IRO[44].m1)) +#define TSTORM_FCOE_RX_STATS_SIZE (IRO[44].size) /* Pstorm FCoE TX stats */ #define PSTORM_FCOE_TX_STATS_OFFSET(pf_id) \ - (IRO[44].base + ((pf_id) * IRO[44].m1)) -#define PSTORM_FCOE_TX_STATS_SIZE (IRO[44].size) + (IRO[45].base + ((pf_id) * IRO[45].m1)) +#define PSTORM_FCOE_TX_STATS_SIZE (IRO[45].size) /* Pstorm RDMA queue statistics */ #define PSTORM_RDMA_QUEUE_STAT_OFFSET(rdma_stat_counter_id) \ - (IRO[45].base + ((rdma_stat_counter_id) * IRO[45].m1)) -#define PSTORM_RDMA_QUEUE_STAT_SIZE (IRO[45].size) + (IRO[46].base + ((rdma_stat_counter_id) * IRO[46].m1)) +#define PSTORM_RDMA_QUEUE_STAT_SIZE (IRO[46].size) /* Tstorm RDMA queue statistics */ #define TSTORM_RDMA_QUEUE_STAT_OFFSET(rdma_stat_counter_id) \ - (IRO[46].base + ((rdma_stat_counter_id) * IRO[46].m1)) -#define TSTORM_RDMA_QUEUE_STAT_SIZE (IRO[46].size) + (IRO[47].base + ((rdma_stat_counter_id) * IRO[47].m1)) +#define TSTORM_RDMA_QUEUE_STAT_SIZE (IRO[47].size) /* Xstorm error level for assert */ #define XSTORM_RDMA_ASSERT_LEVEL_OFFSET(pf_id) \ - (IRO[47].base + ((pf_id) * IRO[47].m1)) -#define XSTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[47].size) + (IRO[48].base + ((pf_id) * IRO[48].m1)) +#define XSTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[48].size) /* Ystorm error level for assert */ #define YSTORM_RDMA_ASSERT_LEVEL_OFFSET(pf_id) \ - (IRO[48].base + ((pf_id) * IRO[48].m1)) -#define YSTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[48].size) + (IRO[49].base + ((pf_id) * IRO[49].m1)) +#define YSTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[49].size) /* Pstorm error level for assert */ #define PSTORM_RDMA_ASSERT_LEVEL_OFFSET(pf_id) \ - (IRO[49].base + ((pf_id) * IRO[49].m1)) -#define PSTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[49].size) + (IRO[50].base + ((pf_id) * IRO[50].m1)) +#define PSTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[50].size) /* Tstorm error level for assert */ #define TSTORM_RDMA_ASSERT_LEVEL_OFFSET(pf_id) \ - (IRO[50].base + ((pf_id) * IRO[50].m1)) -#define TSTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[50].size) + (IRO[51].base + ((pf_id) * IRO[51].m1)) +#define TSTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[51].size) /* Mstorm error level for assert */ #define MSTORM_RDMA_ASSERT_LEVEL_OFFSET(pf_id) \ - (IRO[51].base + ((pf_id) * IRO[51].m1)) -#define MSTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[51].size) + (IRO[52].base + ((pf_id) * IRO[52].m1)) +#define MSTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[52].size) /* Ustorm error level for assert */ #define USTORM_RDMA_ASSERT_LEVEL_OFFSET(pf_id) \ - (IRO[52].base + ((pf_id) * IRO[52].m1)) -#define USTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[52].size) + (IRO[53].base + ((pf_id) * IRO[53].m1)) +#define USTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[53].size) /* Xstorm iWARP rxmit stats */ #define XSTORM_IWARP_RXMIT_STATS_OFFSET(pf_id) \ - (IRO[53].base + ((pf_id) * IRO[53].m1)) -#define XSTORM_IWARP_RXMIT_STATS_SIZE (IRO[53].size) + (IRO[54].base + ((pf_id) * IRO[54].m1)) +#define XSTORM_IWARP_RXMIT_STATS_SIZE (IRO[54].size) /* Tstorm RoCE Event Statistics */ #define TSTORM_ROCE_EVENTS_STAT_OFFSET(roce_pf_id) \ - (IRO[54].base + ((roce_pf_id) * IRO[54].m1)) -#define TSTORM_ROCE_EVENTS_STAT_SIZE (IRO[54].size) + (IRO[55].base + ((roce_pf_id) * IRO[55].m1)) +#define TSTORM_ROCE_EVENTS_STAT_SIZE (IRO[55].size) /* DCQCN Received Statistics */ #define YSTORM_ROCE_DCQCN_RECEIVED_STATS_OFFSET(roce_pf_id) \ - (IRO[55].base + ((roce_pf_id) * IRO[55].m1)) -#define YSTORM_ROCE_DCQCN_RECEIVED_STATS_SIZE (IRO[55].size) + (IRO[56].base + ((roce_pf_id) * IRO[56].m1)) +#define YSTORM_ROCE_DCQCN_RECEIVED_STATS_SIZE (IRO[56].size) /* RoCE Error Statistics */ #define YSTORM_ROCE_ERROR_STATS_OFFSET(roce_pf_id) \ - (IRO[56].base + ((roce_pf_id) * IRO[56].m1)) -#define YSTORM_ROCE_ERROR_STATS_SIZE (IRO[56].size) + (IRO[57].base + ((roce_pf_id) * IRO[57].m1)) +#define YSTORM_ROCE_ERROR_STATS_SIZE (IRO[57].size) /* DCQCN Sent Statistics */ #define PSTORM_ROCE_DCQCN_SENT_STATS_OFFSET(roce_pf_id) \ - (IRO[57].base + ((roce_pf_id) * IRO[57].m1)) -#define PSTORM_ROCE_DCQCN_SENT_STATS_SIZE (IRO[57].size) + (IRO[58].base + ((roce_pf_id) * IRO[58].m1)) +#define PSTORM_ROCE_DCQCN_SENT_STATS_SIZE (IRO[58].size) /* RoCE CQEs Statistics */ #define USTORM_ROCE_CQE_STATS_OFFSET(roce_pf_id) \ - (IRO[58].base + ((roce_pf_id) * IRO[58].m1)) -#define USTORM_ROCE_CQE_STATS_SIZE (IRO[58].size) + (IRO[59].base + ((roce_pf_id) * IRO[59].m1)) +#define USTORM_ROCE_CQE_STATS_SIZE (IRO[59].size) -static const struct iro iro_arr[59] = { +static const struct iro iro_arr[60] = { {0x0, 0x0, 0x0, 0x0, 0x8}, {0x4cb8, 0x88, 0x0, 0x0, 0x88}, {0x6530, 0x20, 0x0, 0x0, 0x20}, @@ -4461,14 +4536,14 @@ static const struct iro iro_arr[59] = { {0x84, 0x8, 0x0, 0x0, 0x2}, {0x4c48, 0x0, 0x0, 0x0, 0x78}, {0x3e38, 0x0, 0x0, 0x0, 0x78}, - {0x2b78, 0x0, 0x0, 0x0, 0x78}, + {0x3ef8, 0x0, 0x0, 0x0, 0x78}, {0x4c40, 0x0, 0x0, 0x0, 0x78}, {0x4998, 0x0, 0x0, 0x0, 0x78}, {0x7f50, 0x0, 0x0, 0x0, 0x78}, {0xa28, 0x8, 0x0, 0x0, 0x8}, {0x6210, 0x10, 0x0, 0x0, 0x10}, {0xb820, 0x30, 0x0, 0x0, 0x30}, - {0x96c0, 0x30, 0x0, 0x0, 0x30}, + {0xa990, 0x30, 0x0, 0x0, 0x30}, {0x4b68, 0x80, 0x0, 0x0, 0x40}, {0x1f8, 0x4, 0x0, 0x0, 0x4}, {0x53a8, 0x80, 0x4, 0x0, 0x4}, @@ -4476,11 +4551,12 @@ static const struct iro iro_arr[59] = { {0x4ba8, 0x80, 0x0, 0x0, 0x20}, {0x8158, 0x40, 0x0, 0x0, 0x30}, {0xe770, 0x60, 0x0, 0x0, 0x60}, - {0x2d10, 0x80, 0x0, 0x0, 0x38}, - {0xf2b8, 0x78, 0x0, 0x0, 0x78}, + {0x4090, 0x80, 0x0, 0x0, 0x38}, + {0xfea8, 0x78, 0x0, 0x0, 0x78}, {0x1f8, 0x4, 0x0, 0x0, 0x4}, {0xaf20, 0x0, 0x0, 0x0, 0xf0}, {0xb010, 0x8, 0x0, 0x0, 0x8}, + {0xc00, 0x8, 0x0, 0x0, 0x8}, {0x1f8, 0x8, 0x0, 0x0, 0x8}, {0xac0, 0x8, 0x0, 0x0, 0x8}, {0x2578, 0x8, 0x0, 0x0, 0x8}, @@ -4492,23 +4568,23 @@ static const struct iro iro_arr[59] = { {0x12908, 0x18, 0x0, 0x0, 0x10}, {0x11aa8, 0x40, 0x0, 0x0, 0x18}, {0xa588, 0x50, 0x0, 0x0, 0x20}, - {0x8700, 0x40, 0x0, 0x0, 0x28}, - {0x10300, 0x18, 0x0, 0x0, 0x10}, + {0x8f00, 0x40, 0x0, 0x0, 0x28}, + {0x10e30, 0x18, 0x0, 0x0, 0x10}, {0xde48, 0x48, 0x0, 0x0, 0x38}, - {0x10768, 0x20, 0x0, 0x0, 0x20}, - {0x2d48, 0x80, 0x0, 0x0, 0x10}, + {0x11298, 0x20, 0x0, 0x0, 0x20}, + {0x40c8, 0x80, 0x0, 0x0, 0x10}, {0x5048, 0x10, 0x0, 0x0, 0x10}, {0xc748, 0x8, 0x0, 0x0, 0x1}, - {0xa128, 0x8, 0x0, 0x0, 0x1}, - {0x10f00, 0x8, 0x0, 0x0, 0x1}, + {0xa928, 0x8, 0x0, 0x0, 0x1}, + {0x11a30, 0x8, 0x0, 0x0, 0x1}, {0xf030, 0x8, 0x0, 0x0, 0x1}, {0x13028, 0x8, 0x0, 0x0, 0x1}, {0x12c58, 0x8, 0x0, 0x0, 0x1}, {0xc9b8, 0x30, 0x0, 0x0, 0x10}, {0xed90, 0x28, 0x0, 0x0, 0x28}, - {0xa520, 0x18, 0x0, 0x0, 0x18}, - {0xa6a0, 0x8, 0x0, 0x0, 0x8}, - {0x13108, 0x8, 0x0, 0x0, 0x8}, + {0xad20, 0x18, 0x0, 0x0, 0x18}, + {0xaea0, 0x8, 0x0, 0x0, 0x8}, + {0x13c38, 0x8, 0x0, 0x0, 0x8}, {0x13c50, 0x18, 0x0, 0x0, 0x18}, }; @@ -5661,6 +5737,14 @@ enum eth_filter_type { MAX_ETH_FILTER_TYPE }; +/* inner to inner vlan priority translation configurations */ +struct eth_in_to_in_pri_map_cfg { + u8 inner_vlan_pri_remap_en; + u8 reserved[7]; + u8 non_rdma_in_to_in_pri_map[8]; + u8 rdma_in_to_in_pri_map[8]; +}; + /* Eth IPv4 Fragment Type */ enum eth_ipv4_frag_type { ETH_IPV4_NOT_FRAG, @@ -6018,6 +6102,14 @@ struct tx_queue_update_ramrod_data { struct regpair reserved1[5]; }; +/* Inner to Inner VLAN priority map update mode */ +enum update_in_to_in_pri_map_mode_enum { + ETH_IN_TO_IN_PRI_MAP_UPDATE_DISABLED, + ETH_IN_TO_IN_PRI_MAP_UPDATE_NON_RDMA_TBL, + ETH_IN_TO_IN_PRI_MAP_UPDATE_RDMA_TBL, + MAX_UPDATE_IN_TO_IN_PRI_MAP_MODE_ENUM +}; + /* Ramrod data for vport update ramrod */ struct vport_filter_update_ramrod_data { struct eth_filter_cmd_header filter_cmd_hdr; @@ -6048,7 +6140,8 @@ struct vport_start_ramrod_data { u8 zero_placement_offset; u8 ctl_frame_mac_check_en; u8 ctl_frame_ethtype_check_en; - u8 reserved[1]; + u8 wipe_inner_vlan_pri_en; + struct eth_in_to_in_pri_map_cfg in_to_in_vlan_pri_map_cfg; }; /* Ramrod data for vport stop ramrod */ @@ -6100,7 +6193,9 @@ struct vport_update_ramrod_data_cmn { u8 update_ctl_frame_checks_en_flg; u8 ctl_frame_mac_check_en; u8 ctl_frame_ethtype_check_en; - u8 reserved[15]; + u8 update_in_to_in_pri_map_mode; + u8 in_to_in_pri_map[8]; + u8 reserved[6]; }; struct vport_update_ramrod_mcast { @@ -6929,11 +7024,6 @@ struct mstorm_rdma_task_st_ctx { struct regpair temp[4]; }; -/* The roce task context of Ustorm */ -struct ustorm_rdma_task_st_ctx { - struct regpair temp[2]; -}; - struct e4_ustorm_rdma_task_ag_ctx { u8 reserved; u8 state; @@ -7007,8 +7097,6 @@ struct e4_rdma_task_context { struct e4_mstorm_rdma_task_ag_ctx mstorm_ag_context; struct mstorm_rdma_task_st_ctx mstorm_st_context; struct rdif_task_context rdif_context; - struct ustorm_rdma_task_st_ctx ustorm_st_context; - struct regpair ustorm_st_padding[2]; struct e4_ustorm_rdma_task_ag_ctx ustorm_ag_context; }; @@ -7388,7 +7476,7 @@ struct e4_ustorm_rdma_conn_ag_ctx { #define E4_USTORM_RDMA_CONN_AG_CTX_RULE8EN_MASK 0x1 #define E4_USTORM_RDMA_CONN_AG_CTX_RULE8EN_SHIFT 7 u8 byte2; - u8 byte3; + u8 nvmf_only; __le16 conn_dpi; __le16 word1; __le32 cq_cons; @@ -7831,7 +7919,12 @@ struct roce_create_qp_req_ramrod_data { struct regpair qp_handle_for_cqe; struct regpair qp_handle_for_async; u8 stats_counter_id; - u8 reserved3[7]; + u8 reserved3[6]; + u8 flags2; +#define ROCE_CREATE_QP_REQ_RAMROD_DATA_EDPM_MODE_MASK 0x1 +#define ROCE_CREATE_QP_REQ_RAMROD_DATA_EDPM_MODE_SHIFT 0 +#define ROCE_CREATE_QP_REQ_RAMROD_DATA_RESERVED_MASK 0x7F +#define ROCE_CREATE_QP_REQ_RAMROD_DATA_RESERVED_SHIFT 1 __le16 regular_latency_phy_queue; __le16 dpi; }; @@ -7954,6 +8047,7 @@ enum roce_event_opcode { ROCE_EVENT_DESTROY_QP, ROCE_EVENT_CREATE_UD_QP, ROCE_EVENT_DESTROY_UD_QP, + ROCE_EVENT_FUNC_UPDATE, MAX_ROCE_EVENT_OPCODE }; @@ -7962,7 +8056,13 @@ struct roce_init_func_params { u8 ll2_queue_id; u8 cnp_vlan_priority; u8 cnp_dscp; - u8 reserved; + u8 flags; +#define ROCE_INIT_FUNC_PARAMS_DCQCN_NP_EN_MASK 0x1 +#define ROCE_INIT_FUNC_PARAMS_DCQCN_NP_EN_SHIFT 0 +#define ROCE_INIT_FUNC_PARAMS_DCQCN_RP_EN_MASK 0x1 +#define ROCE_INIT_FUNC_PARAMS_DCQCN_RP_EN_SHIFT 1 +#define ROCE_INIT_FUNC_PARAMS_RESERVED0_MASK 0x3F +#define ROCE_INIT_FUNC_PARAMS_RESERVED0_SHIFT 2 __le32 cnp_send_timeout; __le16 rl_offset; u8 rl_count_log; @@ -8109,9 +8209,24 @@ enum roce_ramrod_cmd_id { ROCE_RAMROD_DESTROY_QP, ROCE_RAMROD_CREATE_UD_QP, ROCE_RAMROD_DESTROY_UD_QP, + ROCE_RAMROD_FUNC_UPDATE, MAX_ROCE_RAMROD_CMD_ID }; +/* RoCE func init ramrod data */ +struct roce_update_func_params { + u8 cnp_vlan_priority; + u8 cnp_dscp; + __le16 flags; +#define ROCE_UPDATE_FUNC_PARAMS_DCQCN_NP_EN_MASK 0x1 +#define ROCE_UPDATE_FUNC_PARAMS_DCQCN_NP_EN_SHIFT 0 +#define ROCE_UPDATE_FUNC_PARAMS_DCQCN_RP_EN_MASK 0x1 +#define ROCE_UPDATE_FUNC_PARAMS_DCQCN_RP_EN_SHIFT 1 +#define ROCE_UPDATE_FUNC_PARAMS_RESERVED0_MASK 0x3FFF +#define ROCE_UPDATE_FUNC_PARAMS_RESERVED0_SHIFT 2 + __le32 cnp_send_timeout; +}; + struct e4_xstorm_roce_conn_ag_ctx_dq_ext_ld_part { u8 reserved0; u8 state; diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h index 0081fa6d1268..03f59a28fefd 100644 --- a/include/linux/qed/common_hsi.h +++ b/include/linux/qed/common_hsi.h @@ -110,7 +110,7 @@ #define FW_MAJOR_VERSION 8 #define FW_MINOR_VERSION 37 -#define FW_REVISION_VERSION 2 +#define FW_REVISION_VERSION 7 #define FW_ENGINEERING_VERSION 0 /***********************/ @@ -931,12 +931,12 @@ struct db_rdma_dpm_params { #define DB_RDMA_DPM_PARAMS_WQE_SIZE_SHIFT 16 #define DB_RDMA_DPM_PARAMS_RESERVED0_MASK 0x1 #define DB_RDMA_DPM_PARAMS_RESERVED0_SHIFT 27 -#define DB_RDMA_DPM_PARAMS_COMPLETION_FLG_MASK 0x1 -#define DB_RDMA_DPM_PARAMS_COMPLETION_FLG_SHIFT 28 +#define DB_RDMA_DPM_PARAMS_ACK_REQUEST_MASK 0x1 +#define DB_RDMA_DPM_PARAMS_ACK_REQUEST_SHIFT 28 #define DB_RDMA_DPM_PARAMS_S_FLG_MASK 0x1 #define DB_RDMA_DPM_PARAMS_S_FLG_SHIFT 29 -#define DB_RDMA_DPM_PARAMS_RESERVED1_MASK 0x1 -#define DB_RDMA_DPM_PARAMS_RESERVED1_SHIFT 30 +#define DB_RDMA_DPM_PARAMS_COMPLETION_FLG_MASK 0x1 +#define DB_RDMA_DPM_PARAMS_COMPLETION_FLG_SHIFT 30 #define DB_RDMA_DPM_PARAMS_CONN_TYPE_IS_IWARP_MASK 0x1 #define DB_RDMA_DPM_PARAMS_CONN_TYPE_IS_IWARP_SHIFT 31 }; diff --git a/include/linux/qed/iscsi_common.h b/include/linux/qed/iscsi_common.h index b34c573f2b30..66aba505ec56 100644 --- a/include/linux/qed/iscsi_common.h +++ b/include/linux/qed/iscsi_common.h @@ -896,7 +896,7 @@ struct e4_ustorm_iscsi_task_ag_ctx { __le32 exp_cont_len; __le32 total_data_acked; __le32 exp_data_acked; - u8 next_tid_valid; + u8 byte2; u8 byte3; __le16 word1; __le16 next_tid; -- cgit v1.2.3 From 00b7d1cf46676ad5e6338e80dc6230e1b6e71b86 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 29 Aug 2018 17:21:45 -0500 Subject: of: make default address and size cells sizes private Only some old OpenFirmware implementations rely on default sizes. Any FDT and modern implementation should have explicit properties. Make the OF_ROOT_NODE_*_CELLS_DEFAULT defines private so we don't get any outside users. This also gets us one step closer to removing the asm/prom.h dependency on Sparc. Cc: "David S. Miller" Cc: Frank Rowand Cc: sparclinux@vger.kernel.org Signed-off-by: Rob Herring --- arch/sparc/include/asm/prom.h | 3 --- drivers/of/of_private.h | 8 ++++++++ include/linux/of.h | 6 ------ 3 files changed, 8 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/arch/sparc/include/asm/prom.h b/arch/sparc/include/asm/prom.h index d955c8df62d6..1902db27ff4b 100644 --- a/arch/sparc/include/asm/prom.h +++ b/arch/sparc/include/asm/prom.h @@ -24,9 +24,6 @@ #include #include -#define OF_ROOT_NODE_ADDR_CELLS_DEFAULT 2 -#define OF_ROOT_NODE_SIZE_CELLS_DEFAULT 1 - #define of_compat_cmp(s1, s2, l) strncmp((s1), (s2), (l)) #define of_prop_cmp(s1, s2) strcasecmp((s1), (s2)) #define of_node_cmp(s1, s2) strcmp((s1), (s2)) diff --git a/drivers/of/of_private.h b/drivers/of/of_private.h index 216175d11d3d..5d1567025358 100644 --- a/drivers/of/of_private.h +++ b/drivers/of/of_private.h @@ -27,6 +27,14 @@ struct alias_prop { char stem[0]; }; +#if defined(CONFIG_SPARC) +#define OF_ROOT_NODE_ADDR_CELLS_DEFAULT 2 +#else +#define OF_ROOT_NODE_ADDR_CELLS_DEFAULT 1 +#endif + +#define OF_ROOT_NODE_SIZE_CELLS_DEFAULT 1 + extern struct mutex of_mutex; extern struct list_head aliases_lookup; extern struct kset *of_kset; diff --git a/include/linux/of.h b/include/linux/of.h index 99b0ebf49632..2141490b368f 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -247,12 +247,6 @@ static inline unsigned long of_read_ulong(const __be32 *cell, int size) #include #endif -/* Default #address and #size cells. Allow arch asm/prom.h to override */ -#if !defined(OF_ROOT_NODE_ADDR_CELLS_DEFAULT) -#define OF_ROOT_NODE_ADDR_CELLS_DEFAULT 1 -#define OF_ROOT_NODE_SIZE_CELLS_DEFAULT 1 -#endif - #define OF_IS_DYNAMIC(x) test_bit(OF_DYNAMIC, &x->_flags) #define OF_MARK_DYNAMIC(x) set_bit(OF_DYNAMIC, &x->_flags) -- cgit v1.2.3 From d31ca7e5d0fa066d59540859af32ab6f95adb519 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Thu, 30 Aug 2018 14:20:04 +0100 Subject: mfd: madera: Add irqchip data pointer into struct madera Put the pointer to struct regmap_irq_chip_data into the parent mfd structure so that the child irqchip driver does not need a trivial private structure to store only this pointer. As the irqchip child driver already has a pointer to the parent struct madera it can use that to store the pointer. This also means that the irqchip driver does not need a double-indirection from its local struct to get at the parent struct madera. Signed-off-by: Richard Fitzgerald Signed-off-by: Lee Jones --- include/linux/mfd/madera/core.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/madera/core.h b/include/linux/mfd/madera/core.h index c332681848ef..fe69c0f4398f 100644 --- a/include/linux/mfd/madera/core.h +++ b/include/linux/mfd/madera/core.h @@ -148,6 +148,7 @@ struct snd_soc_dapm_context; * @internal_dcvdd: true if DCVDD is supplied from the internal LDO1 * @pdata: our pdata * @irq_dev: the irqchip child driver device + * @irq_data: pointer to irqchip data for the child irqchip driver * @irq: host irq number from SPI or I2C configuration * @out_clamp: indicates output clamp state for each analogue output * @out_shorted: indicates short circuit state for each analogue output @@ -175,6 +176,7 @@ struct madera { struct madera_pdata pdata; struct device *irq_dev; + struct regmap_irq_chip_data *irq_data; int irq; unsigned int num_micbias; -- cgit v1.2.3 From 8b69bd7d8a8927d537f134c37bcca6cbfa58e1b2 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sat, 11 Aug 2018 18:43:38 -0700 Subject: ppp: Remove direct skb_queue_head list pointer access. Add a helper, __skb_peek(), and use it in ppp_mp_reconstruct(). Signed-off-by: David S. Miller --- drivers/net/ppp/ppp_generic.c | 2 +- include/linux/skbuff.h | 11 +++++++++++ 2 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 02ad03a2fab7..500bc0027c1b 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -2400,7 +2400,7 @@ ppp_mp_reconstruct(struct ppp *ppp) if (ppp->mrru == 0) /* do nothing until mrru is set */ return NULL; - head = list->next; + head = __skb_peek(list); tail = NULL; skb_queue_walk_safe(list, p, tmp) { again: diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 17a13e4785fc..89283b77294d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1592,6 +1592,17 @@ static inline struct sk_buff *skb_peek(const struct sk_buff_head *list_) return skb; } +/** + * __skb_peek - peek at the head of a non-empty &sk_buff_head + * @list_: list to peek at + * + * Like skb_peek(), but the caller knows that the list is not empty. + */ +static inline struct sk_buff *__skb_peek(const struct sk_buff_head *list_) +{ + return list_->next; +} + /** * skb_peek_next - peek skb following the given one from a queue * @skb: skb to start from -- cgit v1.2.3 From a8305bff685252e80b7c60f4f5e7dd2e63e38218 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sun, 29 Jul 2018 20:42:53 -0700 Subject: net: Add and use skb_mark_not_on_list(). An SKB is not on a list if skb->next is NULL. Codify this convention into a helper function and use it where we are dequeueing an SKB and need to mark it as such. Signed-off-by: David S. Miller --- include/linux/skbuff.h | 5 +++++ net/core/dev.c | 8 ++++---- net/core/sock.c | 2 +- net/ieee802154/6lowpan/reassembly.c | 2 +- net/ipv4/ip_fragment.c | 2 +- net/ipv4/ip_input.c | 2 +- net/ipv4/ip_output.c | 4 ++-- net/ipv6/ip6_output.c | 2 +- net/ipv6/netfilter/nf_conntrack_reasm.c | 2 +- net/ipv6/reassembly.c | 2 +- net/netfilter/nfnetlink_queue.c | 2 +- net/rxrpc/input.c | 2 +- net/sched/sch_cake.c | 6 +++--- net/sched/sch_fq.c | 2 +- net/sched/sch_fq_codel.c | 2 +- net/sched/sch_generic.c | 4 ++-- net/sched/sch_hhf.c | 2 +- net/sched/sch_netem.c | 2 +- net/sched/sch_tbf.c | 2 +- net/tipc/bearer.c | 2 +- net/xfrm/xfrm_device.c | 2 +- net/xfrm/xfrm_output.c | 2 +- 22 files changed, 33 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 89283b77294d..c4c9e3f5cd9a 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1339,6 +1339,11 @@ static inline void skb_zcopy_abort(struct sk_buff *skb) } } +static inline void skb_mark_not_on_list(struct sk_buff *skb) +{ + skb->next = NULL; +} + /** * skb_queue_empty - check if a queue is empty * @list: queue head diff --git a/net/core/dev.c b/net/core/dev.c index ca78dc5a79a3..f76dd7e14dd6 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3231,7 +3231,7 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *first, struct net_device *de while (skb) { struct sk_buff *next = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); rc = xmit_one(skb, dev, txq, next != NULL); if (unlikely(!dev_xmit_complete(rc))) { skb->next = next; @@ -3331,7 +3331,7 @@ struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *d for (; skb != NULL; skb = next) { next = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); /* in case skb wont be segmented, point to itself */ skb->prev = skb; @@ -5296,7 +5296,7 @@ static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index, if (flush_old && NAPI_GRO_CB(skb)->age == jiffies) return; list_del(&skb->list); - skb->next = NULL; + skb_mark_not_on_list(skb); napi_gro_complete(skb); napi->gro_hash[index].count--; } @@ -5482,7 +5482,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff if (pp) { list_del(&pp->list); - pp->next = NULL; + skb_mark_not_on_list(pp); napi_gro_complete(pp); napi->gro_hash[hash].count--; } diff --git a/net/core/sock.c b/net/core/sock.c index 3730eb855095..8537b6ca72c5 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2332,7 +2332,7 @@ static void __release_sock(struct sock *sk) next = skb->next; prefetch(next); WARN_ON_ONCE(skb_dst_is_noref(skb)); - skb->next = NULL; + skb_mark_not_on_list(skb); sk_backlog_rcv(sk, skb); cond_resched(); diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c index e7857a8ac86d..09ffbf5ce8fa 100644 --- a/net/ieee802154/6lowpan/reassembly.c +++ b/net/ieee802154/6lowpan/reassembly.c @@ -260,7 +260,7 @@ static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *prev, } sub_frag_mem_limit(fq->q.net, sum_truesize); - head->next = NULL; + skb_mark_not_on_list(head); head->dev = ldev; head->tstamp = fq->q.stamp; diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 330f62353b11..cab3e4a5124b 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -623,7 +623,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, sub_frag_mem_limit(qp->q.net, head->truesize); *nextp = NULL; - head->next = NULL; + skb_mark_not_on_list(head); head->prev = NULL; head->dev = dev; head->tstamp = qp->q.stamp; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 3196cf58f418..eba7f3883230 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -535,7 +535,7 @@ static void ip_sublist_rcv_finish(struct list_head *head) /* Handle ip{6}_forward case, as sch_direct_xmit have * another kind of SKB-list usage (see validate_xmit_skb_list) */ - skb->next = NULL; + skb_mark_not_on_list(skb); dst_input(skb); } } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 9c4e72e9c60a..c09219e7f230 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -278,7 +278,7 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk, struct sk_buff *nskb = segs->next; int err; - segs->next = NULL; + skb_mark_not_on_list(segs); err = ip_fragment(net, sk, segs, mtu, ip_finish_output2); if (err && ret == 0) @@ -684,7 +684,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, skb = frag; frag = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); } if (err == 0) { diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 16f200f06500..9a8934ac053b 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -727,7 +727,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, skb = frag; frag = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); } kfree(tmp_hdr); diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 2a14d8b65924..00e20004d241 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -449,7 +449,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_devic sub_frag_mem_limit(fq->q.net, head->truesize); head->ignore_df = 1; - head->next = NULL; + skb_mark_not_on_list(head); head->dev = dev; head->tstamp = fq->q.stamp; ipv6_hdr(head)->payload_len = htons(payload_len); diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 5c5b4f79296e..f1b1ff30fe5b 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -388,7 +388,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, } sub_frag_mem_limit(fq->q.net, sum_truesize); - head->next = NULL; + skb_mark_not_on_list(head); head->dev = dev; head->tstamp = fq->q.stamp; ipv6_hdr(head)->payload_len = htons(payload_len); diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index ea4ba551abb2..5207eb8a5864 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -764,7 +764,7 @@ __nfqnl_enqueue_packet_gso(struct net *net, struct nfqnl_instance *queue, return ret; } - skb->next = NULL; + skb_mark_not_on_list(skb); entry_seg = nf_queue_entry_dup(entry); if (entry_seg) { diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index cfdc199c6351..ee8e7e1d5c0f 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -259,7 +259,7 @@ static void rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, while (list) { skb = list; list = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); rxrpc_free_skb(skb, rxrpc_skb_tx_freed); } } diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index c07c30b916d5..dc539295ae65 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -812,7 +812,7 @@ static struct sk_buff *dequeue_head(struct cake_flow *flow) if (skb) { flow->head = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); } return skb; @@ -1252,7 +1252,7 @@ found: else flow->head = elig_ack->next; - elig_ack->next = NULL; + skb_mark_not_on_list(elig_ack); return elig_ack; } @@ -1675,7 +1675,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, while (segs) { nskb = segs->next; - segs->next = NULL; + skb_mark_not_on_list(segs); qdisc_skb_cb(segs)->pkt_len = segs->len; cobalt_set_enqueue_time(segs, now); get_cobalt_cb(segs)->adjusted_len = cake_overhead(q, diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 4808713c73b9..b27ba36a269c 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -319,7 +319,7 @@ static struct sk_buff *fq_dequeue_head(struct Qdisc *sch, struct fq_flow *flow) if (skb) { flow->head = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); flow->qlen--; qdisc_qstats_backlog_dec(sch, skb); sch->q.qlen--; diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 6c0a9d5dbf94..cd04d40c30b6 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -124,7 +124,7 @@ static inline struct sk_buff *dequeue_head(struct fq_codel_flow *flow) struct sk_buff *skb = flow->head; flow->head = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); return skb; } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 69078c82963e..a64132a5db36 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -184,7 +184,7 @@ static void try_bulk_dequeue_skb(struct Qdisc *q, skb = nskb; (*packets)++; /* GSO counts as one pkt */ } - skb->next = NULL; + skb_mark_not_on_list(skb); } /* This variant of try_bulk_dequeue_skb() makes sure @@ -210,7 +210,7 @@ static void try_bulk_dequeue_skb_slow(struct Qdisc *q, skb = nskb; } while (++cnt < 8); (*packets) += cnt; - skb->next = NULL; + skb_mark_not_on_list(skb); } /* Note that dequeue_skb can possibly return a SKB list (via skb->next). diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index c3a8388dcdf6..9d6a47697406 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -330,7 +330,7 @@ static struct sk_buff *dequeue_head(struct wdrr_bucket *bucket) struct sk_buff *skb = bucket->head; bucket->head = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); return skb; } diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index b9541ce4d672..506e1960ed7f 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -568,7 +568,7 @@ finish_segs: if (segs) { while (segs) { skb2 = segs->next; - segs->next = NULL; + skb_mark_not_on_list(segs); qdisc_skb_cb(segs)->pkt_len = segs->len; last_len = segs->len; rc = qdisc_enqueue(segs, sch, to_free); diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 6f74a426f159..a4530e85bd02 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -162,7 +162,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch, nb = 0; while (segs) { nskb = segs->next; - segs->next = NULL; + skb_mark_not_on_list(segs); qdisc_skb_cb(segs)->pkt_len = segs->len; len += segs->len; ret = qdisc_enqueue(segs, q->qdisc, to_free); diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 418f03d0be90..91891041e5e1 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -577,7 +577,7 @@ static int tipc_l2_rcv_msg(struct sk_buff *skb, struct net_device *dev, rcu_dereference_rtnl(orig_dev->tipc_ptr); if (likely(b && test_bit(0, &b->up) && (skb->pkt_type <= PACKET_MULTICAST))) { - skb->next = NULL; + skb_mark_not_on_list(skb); tipc_rcv(dev_net(b->pt.dev), skb, b); rcu_read_unlock(); return NET_RX_SUCCESS; diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 5611b7521020..260fbba4f03e 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -99,7 +99,7 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur do { struct sk_buff *nskb = skb2->next; - skb2->next = NULL; + skb_mark_not_on_list(skb2); xo = xfrm_offload(skb2); xo->flags |= XFRM_DEV_RESUME; diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 45ba07ab3e4f..2d42cb0c94b8 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -189,7 +189,7 @@ static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb struct sk_buff *nskb = segs->next; int err; - segs->next = NULL; + skb_mark_not_on_list(segs); err = xfrm_output2(net, sk, segs); if (unlikely(err)) { -- cgit v1.2.3 From 992cba7e276d438ac8b0a8c17b147b37c8c286f7 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 31 Jul 2018 15:27:56 -0700 Subject: net: Add and use skb_list_del_init(). It documents what is happening, and eliminates the spurious list pointer poisoning. In the long term, in order to get proper list head debugging, we might want to use the list poison value as the indicator that an SKB is a singleton and not on a list. Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 ++++++ net/core/dev.c | 6 ++---- net/ipv4/ip_input.c | 6 +----- 3 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index c4c9e3f5cd9a..e3a53ca4a9b5 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1344,6 +1344,12 @@ static inline void skb_mark_not_on_list(struct sk_buff *skb) skb->next = NULL; } +static inline void skb_list_del_init(struct sk_buff *skb) +{ + __list_del_entry(&skb->list); + skb_mark_not_on_list(skb); +} + /** * skb_queue_empty - check if a queue is empty * @list: queue head diff --git a/net/core/dev.c b/net/core/dev.c index f76dd7e14dd6..0b2d777e5b9e 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5295,8 +5295,7 @@ static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index, list_for_each_entry_safe_reverse(skb, p, head, list) { if (flush_old && NAPI_GRO_CB(skb)->age == jiffies) return; - list_del(&skb->list); - skb_mark_not_on_list(skb); + skb_list_del_init(skb); napi_gro_complete(skb); napi->gro_hash[index].count--; } @@ -5481,8 +5480,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff ret = NAPI_GRO_CB(skb)->free ? GRO_MERGED_FREE : GRO_MERGED; if (pp) { - list_del(&pp->list); - skb_mark_not_on_list(pp); + skb_list_del_init(pp); napi_gro_complete(pp); napi->gro_hash[hash].count--; } diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index eba7f3883230..35a786c0aaa0 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -531,11 +531,7 @@ static void ip_sublist_rcv_finish(struct list_head *head) struct sk_buff *skb, *next; list_for_each_entry_safe(skb, next, head, list) { - list_del(&skb->list); - /* Handle ip{6}_forward case, as sch_direct_xmit have - * another kind of SKB-list usage (see validate_xmit_skb_list) - */ - skb_mark_not_on_list(skb); + skb_list_del_init(skb); dst_input(skb); } } -- cgit v1.2.3 From 4e69817b106e4fb98f7af463d2f951e7b3603c12 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 6 Aug 2018 02:29:53 +0000 Subject: usb: ehci-sh: convert to SPDX identifiers This patch updates license to use SPDX-License-Identifier instead of verbose license text. Signed-off-by: Kuninori Morimoto Signed-off-by: Greg Kroah-Hartman --- include/linux/platform_data/ehci-sh.h | 16 ++-------------- 1 file changed, 2 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/ehci-sh.h b/include/linux/platform_data/ehci-sh.h index 5c15a738e116..219bd79dabfc 100644 --- a/include/linux/platform_data/ehci-sh.h +++ b/include/linux/platform_data/ehci-sh.h @@ -1,21 +1,9 @@ -/* +/* SPDX-License-Identifier: GPL-2.0 + * * EHCI SuperH driver platform data * * Copyright (C) 2012 Nobuhiro Iwamatsu * Copyright (C) 2012 Renesas Solutions Corp. - * - * 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; version 2 of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA */ #ifndef __USB_EHCI_SH_H -- cgit v1.2.3 From e7a3ff92eaf19eab14e8149758428e680c61706b Mon Sep 17 00:00:00 2001 From: Angelo Dureghello Date: Sun, 19 Aug 2018 19:27:16 +0200 Subject: dmaengine: fsl-edma: add ColdFire mcf5441x edma support This patch adds support for ColdFire mcf5441x-family edma module. The ColdFire edma module is slightly different from fsl-edma, so a new driver is added. But most of the code is common between fsl-edma and mcf-edma so it has been collected into a separate common module fsl-edma-common (patch 1/3). Signed-off-by: Angelo Dureghello Tested-by: Krzysztof Kozlowski Signed-off-by: Vinod Koul --- drivers/dma/Kconfig | 11 + drivers/dma/Makefile | 1 + drivers/dma/fsl-edma-common.c | 24 ++- drivers/dma/mcf-edma.c | 317 +++++++++++++++++++++++++++++ include/linux/platform_data/dma-mcf-edma.h | 38 ++++ 5 files changed, 387 insertions(+), 4 deletions(-) create mode 100644 drivers/dma/mcf-edma.c create mode 100644 include/linux/platform_data/dma-mcf-edma.h (limited to 'include/linux') diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index dacf3f42426d..05104325d685 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -321,6 +321,17 @@ config LPC18XX_DMAMUX Enable support for DMA on NXP LPC18xx/43xx platforms with PL080 and multiplexed DMA request lines. +config MCF_EDMA + tristate "Freescale eDMA engine support, ColdFire mcf5441x SoCs" + depends on M5441x || COMPILE_TEST + select DMA_ENGINE + select DMA_VIRTUAL_CHANNELS + help + Support the Freescale ColdFire eDMA engine, 64-channel + implementation that performs complex data transfers with + minimal intervention from a host processor. + This module can be found on Freescale ColdFire mcf5441x SoCs. + config MMP_PDMA bool "MMP PDMA support" depends on ARCH_MMP || ARCH_PXA || COMPILE_TEST diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile index 21db4e51b246..7fcc4d8e336d 100644 --- a/drivers/dma/Makefile +++ b/drivers/dma/Makefile @@ -32,6 +32,7 @@ obj-$(CONFIG_DW_DMAC_CORE) += dw/ obj-$(CONFIG_EP93XX_DMA) += ep93xx_dma.o obj-$(CONFIG_FSL_DMA) += fsldma.o obj-$(CONFIG_FSL_EDMA) += fsl-edma.o fsl-edma-common.o +obj-$(CONFIG_MCF_EDMA) += mcf-edma.o fsl-edma-common.o obj-$(CONFIG_FSL_RAID) += fsl_raid.o obj-$(CONFIG_HSU_DMA) += hsu/ obj-$(CONFIG_IMG_MDC_DMA) += img-mdc-dma.o diff --git a/drivers/dma/fsl-edma-common.c b/drivers/dma/fsl-edma-common.c index 227034de256e..8ba80f4b6f55 100644 --- a/drivers/dma/fsl-edma-common.c +++ b/drivers/dma/fsl-edma-common.c @@ -46,8 +46,16 @@ static void fsl_edma_enable_request(struct fsl_edma_chan *fsl_chan) struct edma_regs *regs = &fsl_chan->edma->regs; u32 ch = fsl_chan->vchan.chan.chan_id; - edma_writeb(fsl_chan->edma, EDMA_SEEI_SEEI(ch), regs->seei); - edma_writeb(fsl_chan->edma, ch, regs->serq); + if (fsl_chan->edma->version == v1) { + edma_writeb(fsl_chan->edma, EDMA_SEEI_SEEI(ch), regs->seei); + edma_writeb(fsl_chan->edma, ch, regs->serq); + } else { + /* ColdFire is big endian, and accesses natively + * big endian I/O peripherals + */ + iowrite8(EDMA_SEEI_SEEI(ch), regs->seei); + iowrite8(ch, regs->serq); + } } void fsl_edma_disable_request(struct fsl_edma_chan *fsl_chan) @@ -55,8 +63,16 @@ void fsl_edma_disable_request(struct fsl_edma_chan *fsl_chan) struct edma_regs *regs = &fsl_chan->edma->regs; u32 ch = fsl_chan->vchan.chan.chan_id; - edma_writeb(fsl_chan->edma, ch, regs->cerq); - edma_writeb(fsl_chan->edma, EDMA_CEEI_CEEI(ch), regs->ceei); + if (fsl_chan->edma->version == v1) { + edma_writeb(fsl_chan->edma, ch, regs->cerq); + edma_writeb(fsl_chan->edma, EDMA_CEEI_CEEI(ch), regs->ceei); + } else { + /* ColdFire is big endian, and accesses natively + * big endian I/O peripherals + */ + iowrite8(ch, regs->cerq); + iowrite8(EDMA_CEEI_CEEI(ch), regs->ceei); + } } EXPORT_SYMBOL_GPL(fsl_edma_disable_request); diff --git a/drivers/dma/mcf-edma.c b/drivers/dma/mcf-edma.c new file mode 100644 index 000000000000..4d30d5302649 --- /dev/null +++ b/drivers/dma/mcf-edma.c @@ -0,0 +1,317 @@ +// SPDX-License-Identifier: GPL-2.0+ +// +// Copyright (c) 2013-2014 Freescale Semiconductor, Inc +// Copyright (c) 2017 Sysam, Angelo Dureghello + +#include +#include +#include +#include +#include + +#include "fsl-edma-common.h" + +#define EDMA_CHANNELS 64 +#define EDMA_MASK_CH(x) ((x) & GENMASK(5, 0)) + +static irqreturn_t mcf_edma_tx_handler(int irq, void *dev_id) +{ + struct fsl_edma_engine *mcf_edma = dev_id; + struct edma_regs *regs = &mcf_edma->regs; + unsigned int ch; + struct fsl_edma_chan *mcf_chan; + u64 intmap; + + intmap = ioread32(regs->inth); + intmap <<= 32; + intmap |= ioread32(regs->intl); + if (!intmap) + return IRQ_NONE; + + for (ch = 0; ch < mcf_edma->n_chans; ch++) { + if (intmap & BIT(ch)) { + iowrite8(EDMA_MASK_CH(ch), regs->cint); + + mcf_chan = &mcf_edma->chans[ch]; + + spin_lock(&mcf_chan->vchan.lock); + if (!mcf_chan->edesc->iscyclic) { + list_del(&mcf_chan->edesc->vdesc.node); + vchan_cookie_complete(&mcf_chan->edesc->vdesc); + mcf_chan->edesc = NULL; + mcf_chan->status = DMA_COMPLETE; + mcf_chan->idle = true; + } else { + vchan_cyclic_callback(&mcf_chan->edesc->vdesc); + } + + if (!mcf_chan->edesc) + fsl_edma_xfer_desc(mcf_chan); + + spin_unlock(&mcf_chan->vchan.lock); + } + } + + return IRQ_HANDLED; +} + +static irqreturn_t mcf_edma_err_handler(int irq, void *dev_id) +{ + struct fsl_edma_engine *mcf_edma = dev_id; + struct edma_regs *regs = &mcf_edma->regs; + unsigned int err, ch; + + err = ioread32(regs->errl); + if (!err) + return IRQ_NONE; + + for (ch = 0; ch < (EDMA_CHANNELS / 2); ch++) { + if (err & BIT(ch)) { + fsl_edma_disable_request(&mcf_edma->chans[ch]); + iowrite8(EDMA_CERR_CERR(ch), regs->cerr); + mcf_edma->chans[ch].status = DMA_ERROR; + mcf_edma->chans[ch].idle = true; + } + } + + err = ioread32(regs->errh); + if (!err) + return IRQ_NONE; + + for (ch = (EDMA_CHANNELS / 2); ch < EDMA_CHANNELS; ch++) { + if (err & (BIT(ch - (EDMA_CHANNELS / 2)))) { + fsl_edma_disable_request(&mcf_edma->chans[ch]); + iowrite8(EDMA_CERR_CERR(ch), regs->cerr); + mcf_edma->chans[ch].status = DMA_ERROR; + mcf_edma->chans[ch].idle = true; + } + } + + return IRQ_HANDLED; +} + +static int mcf_edma_irq_init(struct platform_device *pdev, + struct fsl_edma_engine *mcf_edma) +{ + int ret = 0, i; + struct resource *res; + + res = platform_get_resource_byname(pdev, + IORESOURCE_IRQ, "edma-tx-00-15"); + if (!res) + return -1; + + for (ret = 0, i = res->start; i <= res->end; ++i) + ret |= request_irq(i, mcf_edma_tx_handler, 0, "eDMA", mcf_edma); + if (ret) + return ret; + + res = platform_get_resource_byname(pdev, + IORESOURCE_IRQ, "edma-tx-16-55"); + if (!res) + return -1; + + for (ret = 0, i = res->start; i <= res->end; ++i) + ret |= request_irq(i, mcf_edma_tx_handler, 0, "eDMA", mcf_edma); + if (ret) + return ret; + + ret = platform_get_irq_byname(pdev, "edma-tx-56-63"); + if (ret != -ENXIO) { + ret = request_irq(ret, mcf_edma_tx_handler, + 0, "eDMA", mcf_edma); + if (ret) + return ret; + } + + ret = platform_get_irq_byname(pdev, "edma-err"); + if (ret != -ENXIO) { + ret = request_irq(ret, mcf_edma_err_handler, + 0, "eDMA", mcf_edma); + if (ret) + return ret; + } + + return 0; +} + +static void mcf_edma_irq_free(struct platform_device *pdev, + struct fsl_edma_engine *mcf_edma) +{ + int irq; + struct resource *res; + + res = platform_get_resource_byname(pdev, + IORESOURCE_IRQ, "edma-tx-00-15"); + if (res) { + for (irq = res->start; irq <= res->end; irq++) + free_irq(irq, mcf_edma); + } + + res = platform_get_resource_byname(pdev, + IORESOURCE_IRQ, "edma-tx-16-55"); + if (res) { + for (irq = res->start; irq <= res->end; irq++) + free_irq(irq, mcf_edma); + } + + irq = platform_get_irq_byname(pdev, "edma-tx-56-63"); + if (irq != -ENXIO) + free_irq(irq, mcf_edma); + + irq = platform_get_irq_byname(pdev, "edma-err"); + if (irq != -ENXIO) + free_irq(irq, mcf_edma); +} + +static int mcf_edma_probe(struct platform_device *pdev) +{ + struct mcf_edma_platform_data *pdata; + struct fsl_edma_engine *mcf_edma; + struct fsl_edma_chan *mcf_chan; + struct edma_regs *regs; + struct resource *res; + int ret, i, len, chans; + + pdata = dev_get_platdata(&pdev->dev); + if (!pdata) { + dev_err(&pdev->dev, "no platform data supplied\n"); + return -EINVAL; + } + + chans = pdata->dma_channels; + len = sizeof(*mcf_edma) + sizeof(*mcf_chan) * chans; + mcf_edma = devm_kzalloc(&pdev->dev, len, GFP_KERNEL); + if (!mcf_edma) + return -ENOMEM; + + mcf_edma->n_chans = chans; + + /* Set up version for ColdFire edma */ + mcf_edma->version = v2; + mcf_edma->big_endian = 1; + + if (!mcf_edma->n_chans) { + dev_info(&pdev->dev, "setting default channel number to 64"); + mcf_edma->n_chans = 64; + } + + mutex_init(&mcf_edma->fsl_edma_mutex); + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + + mcf_edma->membase = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(mcf_edma->membase)) + return PTR_ERR(mcf_edma->membase); + + fsl_edma_setup_regs(mcf_edma); + regs = &mcf_edma->regs; + + INIT_LIST_HEAD(&mcf_edma->dma_dev.channels); + for (i = 0; i < mcf_edma->n_chans; i++) { + struct fsl_edma_chan *mcf_chan = &mcf_edma->chans[i]; + + mcf_chan->edma = mcf_edma; + mcf_chan->slave_id = i; + mcf_chan->idle = true; + mcf_chan->vchan.desc_free = fsl_edma_free_desc; + vchan_init(&mcf_chan->vchan, &mcf_edma->dma_dev); + iowrite32(0x0, ®s->tcd[i].csr); + } + + iowrite32(~0, regs->inth); + iowrite32(~0, regs->intl); + + ret = mcf_edma_irq_init(pdev, mcf_edma); + if (ret) + return ret; + + dma_cap_set(DMA_PRIVATE, mcf_edma->dma_dev.cap_mask); + dma_cap_set(DMA_SLAVE, mcf_edma->dma_dev.cap_mask); + dma_cap_set(DMA_CYCLIC, mcf_edma->dma_dev.cap_mask); + + mcf_edma->dma_dev.dev = &pdev->dev; + mcf_edma->dma_dev.device_alloc_chan_resources = + fsl_edma_alloc_chan_resources; + mcf_edma->dma_dev.device_free_chan_resources = + fsl_edma_free_chan_resources; + mcf_edma->dma_dev.device_config = fsl_edma_slave_config; + mcf_edma->dma_dev.device_prep_dma_cyclic = + fsl_edma_prep_dma_cyclic; + mcf_edma->dma_dev.device_prep_slave_sg = fsl_edma_prep_slave_sg; + mcf_edma->dma_dev.device_tx_status = fsl_edma_tx_status; + mcf_edma->dma_dev.device_pause = fsl_edma_pause; + mcf_edma->dma_dev.device_resume = fsl_edma_resume; + mcf_edma->dma_dev.device_terminate_all = fsl_edma_terminate_all; + mcf_edma->dma_dev.device_issue_pending = fsl_edma_issue_pending; + + mcf_edma->dma_dev.src_addr_widths = FSL_EDMA_BUSWIDTHS; + mcf_edma->dma_dev.dst_addr_widths = FSL_EDMA_BUSWIDTHS; + mcf_edma->dma_dev.directions = + BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV); + + mcf_edma->dma_dev.filter.fn = mcf_edma_filter_fn; + mcf_edma->dma_dev.filter.map = pdata->slave_map; + mcf_edma->dma_dev.filter.mapcnt = pdata->slavecnt; + + platform_set_drvdata(pdev, mcf_edma); + + ret = dma_async_device_register(&mcf_edma->dma_dev); + if (ret) { + dev_err(&pdev->dev, + "Can't register Freescale eDMA engine. (%d)\n", ret); + return ret; + } + + /* Enable round robin arbitration */ + iowrite32(EDMA_CR_ERGA | EDMA_CR_ERCA, regs->cr); + + return 0; +} + +static int mcf_edma_remove(struct platform_device *pdev) +{ + struct fsl_edma_engine *mcf_edma = platform_get_drvdata(pdev); + + mcf_edma_irq_free(pdev, mcf_edma); + fsl_edma_cleanup_vchan(&mcf_edma->dma_dev); + dma_async_device_unregister(&mcf_edma->dma_dev); + + return 0; +} + +static struct platform_driver mcf_edma_driver = { + .driver = { + .name = "mcf-edma", + }, + .probe = mcf_edma_probe, + .remove = mcf_edma_remove, +}; + +bool mcf_edma_filter_fn(struct dma_chan *chan, void *param) +{ + if (chan->device->dev->driver == &mcf_edma_driver.driver) { + struct fsl_edma_chan *mcf_chan = to_fsl_edma_chan(chan); + + return (mcf_chan->slave_id == (u32)param); + } + + return false; +} +EXPORT_SYMBOL(mcf_edma_filter_fn); + +static int __init mcf_edma_init(void) +{ + return platform_driver_register(&mcf_edma_driver); +} +subsys_initcall(mcf_edma_init); + +static void __exit mcf_edma_exit(void) +{ + platform_driver_unregister(&mcf_edma_driver); +} +module_exit(mcf_edma_exit); + +MODULE_ALIAS("platform:mcf-edma"); +MODULE_DESCRIPTION("Freescale eDMA engine driver, ColdFire family"); +MODULE_LICENSE("GPL v2"); diff --git a/include/linux/platform_data/dma-mcf-edma.h b/include/linux/platform_data/dma-mcf-edma.h new file mode 100644 index 000000000000..d718ccfa3421 --- /dev/null +++ b/include/linux/platform_data/dma-mcf-edma.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Freescale eDMA platform data, ColdFire SoC's family. + * + * Copyright (c) 2017 Angelo Dureghello + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __LINUX_PLATFORM_DATA_MCF_EDMA_H__ +#define __LINUX_PLATFORM_DATA_MCF_EDMA_H__ + +struct dma_slave_map; + +bool mcf_edma_filter_fn(struct dma_chan *chan, void *param); + +#define MCF_EDMA_FILTER_PARAM(ch) ((void *)ch) + +/** + * struct mcf_edma_platform_data - platform specific data for eDMA engine + * + * @ver The eDMA module version. + * @dma_channels The number of eDMA channels. + */ +struct mcf_edma_platform_data { + int dma_channels; + const struct dma_slave_map *slave_map; + int slavecnt; +}; + +#endif /* __LINUX_PLATFORM_DATA_MCF_EDMA_H__ */ -- cgit v1.2.3 From 961366a01904d460066d65a609c3c2e3051c7903 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 19 Jul 2018 21:31:13 -0500 Subject: signal: Remove the siginfo paramater from kernel_dqueue_signal None of the callers use the it so remove it. Reviewed-by: Thomas Gleixner Signed-off-by: "Eric W. Biederman" --- drivers/usb/gadget/function/f_mass_storage.c | 2 +- fs/jffs2/background.c | 2 +- include/linux/sched/signal.h | 4 ++-- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c index ca8a4b53c59f..70038a475c9f 100644 --- a/drivers/usb/gadget/function/f_mass_storage.c +++ b/drivers/usb/gadget/function/f_mass_storage.c @@ -2311,7 +2311,7 @@ static void handle_exception(struct fsg_common *common) * into a high-priority EXIT exception. */ for (;;) { - int sig = kernel_dequeue_signal(NULL); + int sig = kernel_dequeue_signal(); if (!sig) break; if (sig != SIGUSR1) { diff --git a/fs/jffs2/background.c b/fs/jffs2/background.c index 453a6a1fff34..2b4d5013dc5d 100644 --- a/fs/jffs2/background.c +++ b/fs/jffs2/background.c @@ -125,7 +125,7 @@ static int jffs2_garbage_collect_thread(void *_c) if (try_to_freeze()) goto again; - signr = kernel_dequeue_signal(NULL); + signr = kernel_dequeue_signal(); switch(signr) { case SIGSTOP: diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 1be35729c2c5..9b6968cbde14 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -272,14 +272,14 @@ extern void ignore_signals(struct task_struct *); extern void flush_signal_handlers(struct task_struct *, int force_default); extern int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info); -static inline int kernel_dequeue_signal(siginfo_t *info) +static inline int kernel_dequeue_signal(void) { struct task_struct *tsk = current; siginfo_t __info; int ret; spin_lock_irq(&tsk->sighand->siglock); - ret = dequeue_signal(tsk, &tsk->blocked, info ?: &__info); + ret = dequeue_signal(tsk, &tsk->blocked, &__info); spin_unlock_irq(&tsk->sighand->siglock); return ret; -- cgit v1.2.3 From 4ff4c31a6e85f4c49fbeebeaa28018d002884b5a Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 3 Sep 2018 10:39:04 +0200 Subject: signal: Remove SEND_SIG_FORCED There are no more users of SEND_SIG_FORCED so it may be safely removed. Remove the definition of SEND_SIG_FORCED, it's use in is_si_special, it's use in TP_STORE_SIGINFO, and it's use in __send_signal as without any users the uses of SEND_SIG_FORCED are now unncessary. This makes the code simpler, easier to understand and use. Users of signal sending functions now no longer need to ask themselves do I need to use SEND_SIG_FORCED. Reviewed-by: Thomas Gleixner Signed-off-by: "Eric W. Biederman" --- include/linux/sched/signal.h | 1 - include/trace/events/signal.h | 3 +-- kernel/signal.c | 7 +++---- 3 files changed, 4 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 9b6968cbde14..9e07f3521549 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -477,7 +477,6 @@ static inline int kill_cad_pid(int sig, int priv) /* These can be the second arg to send_sig_info/send_group_sig_info. */ #define SEND_SIG_NOINFO ((struct siginfo *) 0) #define SEND_SIG_PRIV ((struct siginfo *) 1) -#define SEND_SIG_FORCED ((struct siginfo *) 2) /* * True if we are on the alternate signal stack. diff --git a/include/trace/events/signal.h b/include/trace/events/signal.h index 86582923d51c..3deeed50ffd0 100644 --- a/include/trace/events/signal.h +++ b/include/trace/events/signal.h @@ -11,8 +11,7 @@ #define TP_STORE_SIGINFO(__entry, info) \ do { \ - if (info == SEND_SIG_NOINFO || \ - info == SEND_SIG_FORCED) { \ + if (info == SEND_SIG_NOINFO) { \ __entry->errno = 0; \ __entry->code = SI_USER; \ } else if (info == SEND_SIG_PRIV) { \ diff --git a/kernel/signal.c b/kernel/signal.c index d7d1adf735f4..ec136fda457a 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -736,7 +736,7 @@ static void flush_sigqueue_mask(sigset_t *mask, struct sigpending *s) static inline int is_si_special(const struct siginfo *info) { - return info <= SEND_SIG_FORCED; + return info <= SEND_SIG_PRIV; } static inline bool si_fromuser(const struct siginfo *info) @@ -1039,7 +1039,7 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t, result = TRACE_SIGNAL_IGNORED; if (!prepare_signal(sig, t, - from_ancestor_ns || (info == SEND_SIG_PRIV) || (info == SEND_SIG_FORCED))) + from_ancestor_ns || (info == SEND_SIG_PRIV))) goto ret; pending = (type != PIDTYPE_PID) ? &t->signal->shared_pending : &t->pending; @@ -1057,8 +1057,7 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t, * Skip useless siginfo allocation for SIGKILL SIGSTOP, * and kernel threads. */ - if ((info == SEND_SIG_FORCED) || - sig_kernel_only(sig) || (t->flags & PF_KTHREAD)) + if (sig_kernel_only(sig) || (t->flags & PF_KTHREAD)) goto out_set; /* -- cgit v1.2.3 From d765edbb301c0e196015a59b17420558088ea33f Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 10 Aug 2018 23:06:08 +0000 Subject: vmbus: add driver_override support Add support for overriding the default driver for a VMBus device in the same way that it can be done for PCI devices. This patch adds the /sys/bus/vmbus/devices/.../driver_override file and the logic for matching. This is used by driverctl tool to do driver override. https://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgitlab.com%2Fdriverctl%2Fdriverctl&data=02%7C01%7Ckys%40microsoft.com%7C42e803feb2c544ef6ea908d5fd538878%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C0%7C636693457619960040&sdata=kEyYHRIjNZCk%2B37moCSqbrZL426YccNQrsWpENcrZdw%3D&reserved=0 Signed-off-by: Stephen Hemminger Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- Documentation/ABI/testing/sysfs-bus-vmbus | 21 ++++++ drivers/hv/vmbus_drv.c | 115 +++++++++++++++++++++++++----- include/linux/hyperv.h | 1 + 3 files changed, 118 insertions(+), 19 deletions(-) create mode 100644 Documentation/ABI/testing/sysfs-bus-vmbus (limited to 'include/linux') diff --git a/Documentation/ABI/testing/sysfs-bus-vmbus b/Documentation/ABI/testing/sysfs-bus-vmbus new file mode 100644 index 000000000000..91e6c065973c --- /dev/null +++ b/Documentation/ABI/testing/sysfs-bus-vmbus @@ -0,0 +1,21 @@ +What: /sys/bus/vmbus/devices/.../driver_override +Date: August 2019 +Contact: Stephen Hemminger +Description: + This file allows the driver for a device to be specified which + will override standard static and dynamic ID matching. When + specified, only a driver with a name matching the value written + to driver_override will have an opportunity to bind to the + device. The override is specified by writing a string to the + driver_override file (echo uio_hv_generic > driver_override) and + may be cleared with an empty string (echo > driver_override). + This returns the device to standard matching rules binding. + Writing to driver_override does not automatically unbind the + device from its current driver or make any attempt to + automatically load the specified driver. If no driver with a + matching name is currently loaded in the kernel, the device + will not bind to any driver. This also allows devices to + opt-out of driver binding using a driver_override name such as + "none". Only a single driver may be specified in the override, + there is no support for parsing delimiters. + diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index b1b548a21f91..e6d8fdac6d8b 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -498,6 +498,54 @@ static ssize_t device_show(struct device *dev, } static DEVICE_ATTR_RO(device); +static ssize_t driver_override_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct hv_device *hv_dev = device_to_hv_device(dev); + char *driver_override, *old, *cp; + + /* We need to keep extra room for a newline */ + if (count >= (PAGE_SIZE - 1)) + return -EINVAL; + + driver_override = kstrndup(buf, count, GFP_KERNEL); + if (!driver_override) + return -ENOMEM; + + cp = strchr(driver_override, '\n'); + if (cp) + *cp = '\0'; + + device_lock(dev); + old = hv_dev->driver_override; + if (strlen(driver_override)) { + hv_dev->driver_override = driver_override; + } else { + kfree(driver_override); + hv_dev->driver_override = NULL; + } + device_unlock(dev); + + kfree(old); + + return count; +} + +static ssize_t driver_override_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct hv_device *hv_dev = device_to_hv_device(dev); + ssize_t len; + + device_lock(dev); + len = snprintf(buf, PAGE_SIZE, "%s\n", hv_dev->driver_override); + device_unlock(dev); + + return len; +} +static DEVICE_ATTR_RW(driver_override); + /* Set up per device attributes in /sys/bus/vmbus/devices/ */ static struct attribute *vmbus_dev_attrs[] = { &dev_attr_id.attr, @@ -528,6 +576,7 @@ static struct attribute *vmbus_dev_attrs[] = { &dev_attr_channel_vp_mapping.attr, &dev_attr_vendor.attr, &dev_attr_device.attr, + &dev_attr_driver_override.attr, NULL, }; ATTRIBUTE_GROUPS(vmbus_dev); @@ -563,17 +612,26 @@ static inline bool is_null_guid(const uuid_le *guid) return true; } -/* - * Return a matching hv_vmbus_device_id pointer. - * If there is no match, return NULL. - */ -static const struct hv_vmbus_device_id *hv_vmbus_get_id(struct hv_driver *drv, - const uuid_le *guid) +static const struct hv_vmbus_device_id * +hv_vmbus_dev_match(const struct hv_vmbus_device_id *id, const uuid_le *guid) + +{ + if (id == NULL) + return NULL; /* empty device table */ + + for (; !is_null_guid(&id->guid); id++) + if (!uuid_le_cmp(id->guid, *guid)) + return id; + + return NULL; +} + +static const struct hv_vmbus_device_id * +hv_vmbus_dynid_match(struct hv_driver *drv, const uuid_le *guid) { const struct hv_vmbus_device_id *id = NULL; struct vmbus_dynid *dynid; - /* Look at the dynamic ids first, before the static ones */ spin_lock(&drv->dynids.lock); list_for_each_entry(dynid, &drv->dynids.list, node) { if (!uuid_le_cmp(dynid->id.guid, *guid)) { @@ -583,18 +641,37 @@ static const struct hv_vmbus_device_id *hv_vmbus_get_id(struct hv_driver *drv, } spin_unlock(&drv->dynids.lock); - if (id) - return id; + return id; +} - id = drv->id_table; - if (id == NULL) - return NULL; /* empty device table */ +static const struct hv_vmbus_device_id vmbus_device_null = { + .guid = NULL_UUID_LE, +}; - for (; !is_null_guid(&id->guid); id++) - if (!uuid_le_cmp(id->guid, *guid)) - return id; +/* + * Return a matching hv_vmbus_device_id pointer. + * If there is no match, return NULL. + */ +static const struct hv_vmbus_device_id *hv_vmbus_get_id(struct hv_driver *drv, + struct hv_device *dev) +{ + const uuid_le *guid = &dev->dev_type; + const struct hv_vmbus_device_id *id; - return NULL; + /* When driver_override is set, only bind to the matching driver */ + if (dev->driver_override && strcmp(dev->driver_override, drv->name)) + return NULL; + + /* Look at the dynamic ids first, before the static ones */ + id = hv_vmbus_dynid_match(drv, guid); + if (!id) + id = hv_vmbus_dev_match(drv->id_table, guid); + + /* driver_override will always match, send a dummy id */ + if (!id && dev->driver_override) + id = &vmbus_device_null; + + return id; } /* vmbus_add_dynid - add a new device ID to this driver and re-probe devices */ @@ -643,7 +720,7 @@ static ssize_t new_id_store(struct device_driver *driver, const char *buf, if (retval) return retval; - if (hv_vmbus_get_id(drv, &guid)) + if (hv_vmbus_dynid_match(drv, &guid)) return -EEXIST; retval = vmbus_add_dynid(drv, &guid); @@ -708,7 +785,7 @@ static int vmbus_match(struct device *device, struct device_driver *driver) if (is_hvsock_channel(hv_dev->channel)) return drv->hvsock; - if (hv_vmbus_get_id(drv, &hv_dev->dev_type)) + if (hv_vmbus_get_id(drv, hv_dev)) return 1; return 0; @@ -725,7 +802,7 @@ static int vmbus_probe(struct device *child_device) struct hv_device *dev = device_to_hv_device(child_device); const struct hv_vmbus_device_id *dev_id; - dev_id = hv_vmbus_get_id(drv, &dev->dev_type); + dev_id = hv_vmbus_get_id(drv, dev); if (drv->probe) { ret = drv->probe(dev, dev_id); if (ret != 0) diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index efda23cf32c7..2c3798bcb01c 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1125,6 +1125,7 @@ struct hv_device { u16 device_id; struct device device; + char *driver_override; /* Driver name to force a match */ struct vmbus_channel *channel; struct kset *channels_kset; -- cgit v1.2.3 From 7c1a000d466235c875a989971cfda344e6bb1166 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Wed, 12 Sep 2018 09:16:07 +0800 Subject: f2fs: add SPDX license identifiers Remove the verbose license text from f2fs files and replace them with SPDX tags. This does not change the license of any of the code. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/acl.c | 5 +---- fs/f2fs/acl.h | 5 +---- fs/f2fs/checkpoint.c | 5 +---- fs/f2fs/data.c | 5 +---- fs/f2fs/debug.c | 5 +---- fs/f2fs/dir.c | 5 +---- fs/f2fs/extent_cache.c | 5 +---- fs/f2fs/f2fs.h | 5 +---- fs/f2fs/file.c | 5 +---- fs/f2fs/gc.c | 5 +---- fs/f2fs/gc.h | 5 +---- fs/f2fs/hash.c | 5 +---- fs/f2fs/inline.c | 4 +--- fs/f2fs/inode.c | 5 +---- fs/f2fs/namei.c | 5 +---- fs/f2fs/node.c | 5 +---- fs/f2fs/node.h | 5 +---- fs/f2fs/recovery.c | 5 +---- fs/f2fs/segment.c | 5 +---- fs/f2fs/segment.h | 5 +---- fs/f2fs/shrinker.c | 5 +---- fs/f2fs/super.c | 5 +---- fs/f2fs/sysfs.c | 5 +---- fs/f2fs/trace.c | 5 +---- fs/f2fs/trace.h | 5 +---- fs/f2fs/xattr.c | 5 +---- fs/f2fs/xattr.h | 5 +---- include/linux/f2fs_fs.h | 5 +---- 28 files changed, 28 insertions(+), 111 deletions(-) (limited to 'include/linux') diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c index cd82e1ce5d67..fa707cdd4120 100644 --- a/fs/f2fs/acl.c +++ b/fs/f2fs/acl.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/acl.c * @@ -7,10 +8,6 @@ * Portions of this code from linux/fs/ext2/acl.c * * Copyright (C) 2001-2003 Andreas Gruenbacher, - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include #include "f2fs.h" diff --git a/fs/f2fs/acl.h b/fs/f2fs/acl.h index 2c685185c24d..b96823c59b15 100644 --- a/fs/f2fs/acl.h +++ b/fs/f2fs/acl.h @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/acl.h * @@ -7,10 +8,6 @@ * Portions of this code from linux/fs/ext2/acl.h * * Copyright (C) 2001-2003 Andreas Gruenbacher, - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef __F2FS_ACL_H__ #define __F2FS_ACL_H__ diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 59d0472013f4..d312d2829d5a 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/checkpoint.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include #include diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 26f38b224bb2..c8c4b54e2bbf 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/data.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include #include diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c index ebe649d9793c..d3c402183e3c 100644 --- a/fs/f2fs/debug.c +++ b/fs/f2fs/debug.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * f2fs debugging statistics * @@ -5,10 +6,6 @@ * http://www.samsung.com/ * Copyright (c) 2012 Linux Foundation * Copyright (c) 2012 Greg Kroah-Hartman - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index bd0348cc860f..c77a58038709 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/dir.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include #include diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c index a70cd2580eae..904ad7ba5a45 100644 --- a/fs/f2fs/extent_cache.c +++ b/fs/f2fs/extent_cache.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * f2fs extent cache support * @@ -5,10 +6,6 @@ * Copyright (c) 2015 Samsung Electronics * Authors: Jaegeuk Kim * Chao Yu - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 88b8d5073581..079f525d5764 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/f2fs.h * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef _LINUX_F2FS_H #define _LINUX_F2FS_H diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 61f95731c858..357422a4c319 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/file.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include #include diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 5c8d00422237..a4c1a419611d 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/gc.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include #include diff --git a/fs/f2fs/gc.h b/fs/f2fs/gc.h index c8619e408009..bbac9d3787bd 100644 --- a/fs/f2fs/gc.h +++ b/fs/f2fs/gc.h @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/gc.h * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #define GC_THREAD_MIN_WB_PAGES 1 /* * a threshold to determine diff --git a/fs/f2fs/hash.c b/fs/f2fs/hash.c index eb2e031ea887..cc82f142f811 100644 --- a/fs/f2fs/hash.c +++ b/fs/f2fs/hash.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/hash.c * @@ -7,10 +8,6 @@ * Portions of this code from linux/fs/ext3/hash.c * * Copyright (C) 2002 by Theodore Ts'o - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include #include diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 115dc219344b..425d740f87fd 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -1,11 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/inline.c * Copyright (c) 2013, Intel Corporation * Authors: Huajun Li * Haicheng Li - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 959df2249875..86e7333d60c1 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/inode.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include #include diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 1f67e389169f..9ad451ac2cec 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/namei.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include #include diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index dd2e45a661aa..fa2381c0bc47 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/node.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include #include diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h index 0f4db7a61254..1c73d879a9bc 100644 --- a/fs/f2fs/node.h +++ b/fs/f2fs/node.h @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/node.h * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ /* start node id of a node block dedicated to the given node id */ #define START_NID(nid) (((nid) / NAT_ENTRY_PER_BLOCK) * NAT_ENTRY_PER_BLOCK) diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index e3aa6eee7a8b..56d34193a74b 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/recovery.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include #include diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 187c848a65b8..9a8d7d415a74 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/segment.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include #include diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index b3d9e317ff0c..086150028c6d 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/segment.h * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include #include diff --git a/fs/f2fs/shrinker.c b/fs/f2fs/shrinker.c index 36cfd816c160..9e13db994fdf 100644 --- a/fs/f2fs/shrinker.c +++ b/fs/f2fs/shrinker.c @@ -1,13 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 /* * f2fs shrinker support * the basic infra was copied from fs/ubifs/shrinker.c * * Copyright (c) 2015 Motorola Mobility * Copyright (c) 2015 Jaegeuk Kim - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include #include diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 3106da1d9be6..8c536105d5ef 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/super.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include #include diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index 81c0e5337443..c8924c02accd 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -1,13 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 /* * f2fs sysfs interface * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ * Copyright (c) 2017 Chao Yu - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include #include diff --git a/fs/f2fs/trace.c b/fs/f2fs/trace.c index a1fcd00bbb2b..ce2a5eb210b6 100644 --- a/fs/f2fs/trace.c +++ b/fs/f2fs/trace.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * f2fs IO tracer * * Copyright (c) 2014 Motorola Mobility * Copyright (c) 2014 Jaegeuk Kim - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include #include diff --git a/fs/f2fs/trace.h b/fs/f2fs/trace.h index 67db24ac1e85..e8075fc5b228 100644 --- a/fs/f2fs/trace.h +++ b/fs/f2fs/trace.h @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * f2fs IO tracer * * Copyright (c) 2014 Motorola Mobility * Copyright (c) 2014 Jaegeuk Kim - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef __F2FS_TRACE_H__ #define __F2FS_TRACE_H__ diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index 77a010e625f5..7261245c208d 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/xattr.c * @@ -13,10 +14,6 @@ * suggestion of Luka Renko . * xattr consolidation Copyright (c) 2004 James Morris , * Red Hat Inc. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include #include diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h index dbcd1d16e669..67db134da0f5 100644 --- a/fs/f2fs/xattr.h +++ b/fs/f2fs/xattr.h @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/xattr.h * @@ -9,10 +10,6 @@ * On-disk format of extended attributes for the ext2 filesystem. * * (C) 2001 Andreas Gruenbacher, - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef __F2FS_XATTR_H__ #define __F2FS_XATTR_H__ diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index f70f8ac9c4f4..1d4b196291d6 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /** * include/linux/f2fs_fs.h * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef _LINUX_F2FS_FS_H #define _LINUX_F2FS_FS_H -- cgit v1.2.3 From 41124fa64d4b298b82266b7ddbefc43540b77b44 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 12 Sep 2018 01:53:14 +0200 Subject: net: ethernet: Add helper to remove a supported link mode Some MAC hardware cannot support a subset of link modes. e.g. often 1Gbps Full duplex is supported, but Half duplex is not. Add a helper to remove such a link mode. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/ethernet/apm/xgene/xgene_enet_hw.c | 6 +++--- drivers/net/ethernet/cadence/macb_main.c | 5 ++--- drivers/net/ethernet/freescale/fec_main.c | 3 ++- drivers/net/ethernet/microchip/lan743x_main.c | 2 +- drivers/net/ethernet/renesas/ravb_main.c | 3 ++- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 12 ++++++++---- drivers/net/phy/phy_device.c | 18 ++++++++++++++++++ drivers/net/usb/lan78xx.c | 2 +- include/linux/phy.h | 1 + 9 files changed, 38 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c index 078a04dc1182..4831f9de5945 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c @@ -895,9 +895,9 @@ int xgene_enet_phy_connect(struct net_device *ndev) } pdata->phy_speed = SPEED_UNKNOWN; - phy_dev->supported &= ~SUPPORTED_10baseT_Half & - ~SUPPORTED_100baseT_Half & - ~SUPPORTED_1000baseT_Half; + phy_remove_link_mode(phy_dev, ETHTOOL_LINK_MODE_10baseT_Half_BIT); + phy_remove_link_mode(phy_dev, ETHTOOL_LINK_MODE_100baseT_Half_BIT); + phy_remove_link_mode(phy_dev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT); phy_dev->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; phy_dev->advertising = phy_dev->supported; diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index bd4095c3a031..96ae8c992810 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -549,9 +549,8 @@ static int macb_mii_probe(struct net_device *dev) phy_set_max_speed(phydev, SPEED_100); if (bp->caps & MACB_CAPS_NO_GIGABIT_HALF) - phydev->supported &= ~SUPPORTED_1000baseT_Half; - - phydev->advertising = phydev->supported; + phy_remove_link_mode(phydev, + ETHTOOL_LINK_MODE_1000baseT_Half_BIT); bp->link = 0; bp->speed = 0; diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 5e849510c689..0c6fd77b6599 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1947,7 +1947,8 @@ static int fec_enet_mii_probe(struct net_device *ndev) /* mask with MAC supported features */ if (fep->quirks & FEC_QUIRK_HAS_GBIT) { phy_set_max_speed(phy_dev, 1000); - phy_dev->supported &= ~SUPPORTED_1000baseT_Half; + phy_remove_link_mode(phy_dev, + ETHTOOL_LINK_MODE_1000baseT_Half_BIT); #if !defined(CONFIG_M5272) phy_dev->supported |= SUPPORTED_Pause; #endif diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index e7dce79ff2c9..048307959c01 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -1013,7 +1013,7 @@ static int lan743x_phy_open(struct lan743x_adapter *adapter) goto return_error; /* MAC doesn't support 1000T Half */ - phydev->supported &= ~SUPPORTED_1000baseT_Half; + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT); /* support both flow controls */ phy->fc_request_control = (FLOW_CTRL_RX | FLOW_CTRL_TX); diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index aff5516b781e..fb2a1125780d 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1074,7 +1074,8 @@ static int ravb_phy_init(struct net_device *ndev) } /* 10BASE is not supported */ - phydev->supported &= ~PHY_10BT_FEATURES; + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_10baseT_Half_BIT); + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_10baseT_Full_BIT); phy_attached_info(phydev); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 3d7aec7a050b..3715a0a4af3c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -993,10 +993,14 @@ static int stmmac_init_phy(struct net_device *dev) * Half-duplex mode not supported with multiqueue * half-duplex can only works with single queue */ - if (tx_cnt > 1) - phydev->supported &= ~(SUPPORTED_1000baseT_Half | - SUPPORTED_100baseT_Half | - SUPPORTED_10baseT_Half); + if (tx_cnt > 1) { + phy_remove_link_mode(phydev, + ETHTOOL_LINK_MODE_10baseT_Half_BIT); + phy_remove_link_mode(phydev, + ETHTOOL_LINK_MODE_100baseT_Half_BIT); + phy_remove_link_mode(phydev, + ETHTOOL_LINK_MODE_1000baseT_Half_BIT); + } /* * Broken HW is sometimes missing the pull-up resistor on the diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index db1172db1e7c..e9ca83a438b0 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1765,6 +1765,24 @@ int phy_set_max_speed(struct phy_device *phydev, u32 max_speed) } EXPORT_SYMBOL(phy_set_max_speed); +/** + * phy_remove_link_mode - Remove a supported link mode + * @phydev: phy_device structure to remove link mode from + * @link_mode: Link mode to be removed + * + * Description: Some MACs don't support all link modes which the PHY + * does. e.g. a 1G MAC often does not support 1000Half. Add a helper + * to remove a link mode. + */ +void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode) +{ + WARN_ON(link_mode > 31); + + phydev->supported &= ~BIT(link_mode); + phydev->advertising = phydev->supported; +} +EXPORT_SYMBOL(phy_remove_link_mode); + static void of_set_phy_supported(struct phy_device *phydev) { struct device_node *node = phydev->mdio.dev.of_node; diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 3ce3c66559e4..95a98a20b2e3 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -2166,7 +2166,7 @@ static int lan78xx_phy_init(struct lan78xx_net *dev) } /* MAC doesn't support 1000T Half */ - phydev->supported &= ~SUPPORTED_1000baseT_Half; + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT); /* support both flow controls */ dev->fc_request_control = (FLOW_CTRL_RX | FLOW_CTRL_TX); diff --git a/include/linux/phy.h b/include/linux/phy.h index cd6f637cbbfb..9c4c3eca8cf2 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1049,6 +1049,7 @@ int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd); int phy_start_interrupts(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); int phy_set_max_speed(struct phy_device *phydev, u32 max_speed); +void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode); int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, int (*run)(struct phy_device *)); -- cgit v1.2.3 From af8d9bb2f2f405ad541794b46f9d7bc70f13e5cb Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 12 Sep 2018 01:53:15 +0200 Subject: net: ethernet: Add helper for MACs which support asym pause Rather than have the MAC drivers manipulate phydev members to indicate they support Asym Pause, add a helper function. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c | 4 ++-- drivers/net/ethernet/apm/xgene/xgene_enet_hw.c | 4 +--- drivers/net/ethernet/broadcom/sb1250-mac.c | 5 +---- drivers/net/ethernet/broadcom/tg3.c | 8 ++------ drivers/net/ethernet/cortina/gemini.c | 3 +-- drivers/net/ethernet/dnet.c | 4 +--- drivers/net/ethernet/faraday/ftgmac100.c | 3 +-- drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 3 +-- drivers/net/ethernet/freescale/gianfar.c | 4 ++-- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c | 4 +--- drivers/net/ethernet/mediatek/mtk_eth_soc.c | 6 +----- drivers/net/ethernet/microchip/lan743x_main.c | 5 +---- drivers/net/ethernet/smsc/smsc911x.c | 3 +-- drivers/net/ethernet/smsc/smsc9420.c | 3 +-- drivers/net/ethernet/socionext/sni_ave.c | 3 ++- drivers/net/phy/phy_device.c | 13 +++++++++++++ include/linux/phy.h | 1 + 17 files changed, 33 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c index 3ceb4f95ca7c..289129011b9f 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c @@ -879,8 +879,8 @@ static bool xgbe_phy_finisar_phy_quirks(struct xgbe_prv_data *pdata) phy_write(phy_data->phydev, 0x00, 0x9140); phy_data->phydev->supported = PHY_GBIT_FEATURES; - phy_data->phydev->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; phy_data->phydev->advertising = phy_data->phydev->supported; + phy_support_asym_pause(phy_data->phydev); netif_dbg(pdata, drv, pdata->netdev, "Finisar PHY quirk in place\n"); @@ -951,8 +951,8 @@ static bool xgbe_phy_belfuse_phy_quirks(struct xgbe_prv_data *pdata) phy_write(phy_data->phydev, 0x00, reg & ~0x00800); phy_data->phydev->supported = PHY_GBIT_FEATURES; - phy_data->phydev->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; phy_data->phydev->advertising = phy_data->phydev->supported; + phy_support_asym_pause(phy_data->phydev); netif_dbg(pdata, drv, pdata->netdev, "BelFuse PHY quirk in place\n"); diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c index 4831f9de5945..e3560311711a 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c @@ -898,9 +898,7 @@ int xgene_enet_phy_connect(struct net_device *ndev) phy_remove_link_mode(phy_dev, ETHTOOL_LINK_MODE_10baseT_Half_BIT); phy_remove_link_mode(phy_dev, ETHTOOL_LINK_MODE_100baseT_Half_BIT); phy_remove_link_mode(phy_dev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT); - phy_dev->supported |= SUPPORTED_Pause | - SUPPORTED_Asym_Pause; - phy_dev->advertising = phy_dev->supported; + phy_support_asym_pause(phy_dev); return 0; } diff --git a/drivers/net/ethernet/broadcom/sb1250-mac.c b/drivers/net/ethernet/broadcom/sb1250-mac.c index 4ce4b097ec05..53acbbb36637 100644 --- a/drivers/net/ethernet/broadcom/sb1250-mac.c +++ b/drivers/net/ethernet/broadcom/sb1250-mac.c @@ -2358,13 +2358,10 @@ static int sbmac_mii_probe(struct net_device *dev) /* Remove any features not supported by the controller */ phy_set_max_speed(phy_dev, SPEED_1000); - phy_dev->supported |= SUPPORTED_Pause | - SUPPORTED_Asym_Pause; + phy_support_asym_pause(phy_dev); phy_attached_info(phy_dev); - phy_dev->advertising = phy_dev->supported; - sc->phy_dev = phy_dev; return 0; diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index eab00239a47a..193e990fac7a 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -2123,15 +2123,13 @@ static int tg3_phy_init(struct tg3 *tp) case PHY_INTERFACE_MODE_RGMII: if (!(tp->phy_flags & TG3_PHYFLG_10_100_ONLY)) { phy_set_max_speed(phydev, SPEED_1000); - phydev->supported |= (SUPPORTED_Pause | - SUPPORTED_Asym_Pause); + phy_support_asym_pause(phydev); break; } /* fallthru */ case PHY_INTERFACE_MODE_MII: phy_set_max_speed(phydev, SPEED_100); - phydev->supported |= (SUPPORTED_Pause | - SUPPORTED_Asym_Pause); + phy_support_asym_pause(phydev); break; default: phy_disconnect(mdiobus_get_phy(tp->mdio_bus, tp->phy_addr)); @@ -2140,8 +2138,6 @@ static int tg3_phy_init(struct tg3 *tp) tp->phy_flags |= TG3_PHYFLG_IS_CONNECTED; - phydev->advertising = phydev->supported; - phy_attached_info(phydev); return 0; diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 2b46c0de90d0..ceec467f590d 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -373,8 +373,7 @@ static int gmac_setup_phy(struct net_device *netdev) netdev->phydev = phy; phy_set_max_speed(phy, SPEED_1000); - phy->supported |= SUPPORTED_Asym_Pause | SUPPORTED_Pause; - phy->advertising = phy->supported; + phy_support_asym_pause(phy); /* set PHY interface type */ switch (phy->interface) { diff --git a/drivers/net/ethernet/dnet.c b/drivers/net/ethernet/dnet.c index 08b7ad1594ce..79521e27f0d1 100644 --- a/drivers/net/ethernet/dnet.c +++ b/drivers/net/ethernet/dnet.c @@ -288,9 +288,7 @@ static int dnet_mii_probe(struct net_device *dev) else phy_set_max_speed(phydev, SPEED_100); - phydev->supported |= SUPPORTED_Asym_Pause | SUPPORTED_Pause; - - phydev->advertising = phydev->supported; + phy_support_asym_pause(phydev); bp->link = 0; bp->speed = 0; diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index ed6c76d20b45..3f319ee66ab4 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -1079,8 +1079,7 @@ static int ftgmac100_mii_probe(struct ftgmac100 *priv, phy_interface_t intf) /* Indicate that we support PAUSE frames (see comment in * Documentation/networking/phy.txt) */ - phydev->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; - phydev->advertising = phydev->supported; + phy_support_asym_pause(phydev); /* Display what we found */ phy_attached_info(phydev); diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index 783134f1b779..a5131a510e8b 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -2491,8 +2491,7 @@ static int dpaa_phy_init(struct net_device *net_dev) /* Remove any features not supported by the controller */ phy_dev->supported &= mac_dev->if_support; - phy_dev->supported |= (SUPPORTED_Pause | SUPPORTED_Asym_Pause); - phy_dev->advertising = phy_dev->supported; + phy_support_asym_pause(phy_dev); mac_dev->phy_dev = phy_dev; net_dev->phydev = phy_dev; diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index f27f9bae1a4a..40a1a87cd338 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -1814,8 +1814,8 @@ static int init_phy(struct net_device *dev) phydev->supported &= (GFAR_SUPPORTED | gigabit_support); phydev->advertising = phydev->supported; - /* Add support for flow control, but don't advertise it by default */ - phydev->supported |= (SUPPORTED_Pause | SUPPORTED_Asym_Pause); + /* Add support for flow control */ + phy_support_asym_pause(phydev); /* disable EEE autoneg, EEE not supported by eTSEC */ memset(&edata, 0, sizeof(struct ethtool_eee)); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c index 05b15d254e32..24b1f2a0c32a 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c @@ -211,9 +211,7 @@ int hclge_mac_connect_phy(struct hclge_dev *hdev) } phydev->supported &= HCLGE_PHY_SUPPORTED_FEATURES; - phydev->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; - - phydev->advertising = phydev->supported; + phy_support_asym_pause(phydev); return 0; } diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index db231bda7c2a..cc1e9a96a43b 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -355,12 +355,8 @@ static int mtk_phy_connect(struct net_device *dev) dev->phydev->speed = 0; dev->phydev->duplex = 0; - if (of_phy_is_fixed_link(mac->of_node)) - dev->phydev->supported |= - SUPPORTED_Pause | SUPPORTED_Asym_Pause; - phy_set_max_speed(dev->phydev, SPEED_1000); - dev->phydev->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; + phy_support_asym_pause(dev->phydev); dev->phydev->advertising = dev->phydev->supported | ADVERTISED_Autoneg; phy_start_aneg(dev->phydev); diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index 048307959c01..b1a0e657febf 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -999,7 +999,6 @@ static int lan743x_phy_open(struct lan743x_adapter *adapter) struct phy_device *phydev; struct net_device *netdev; int ret = -EIO; - u32 mii_adv; netdev = adapter->netdev; phydev = phy_find_first(adapter->mdiobus); @@ -1016,10 +1015,8 @@ static int lan743x_phy_open(struct lan743x_adapter *adapter) phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT); /* support both flow controls */ + phy_support_asym_pause(phydev); phy->fc_request_control = (FLOW_CTRL_RX | FLOW_CTRL_TX); - phydev->advertising &= ~(ADVERTISED_Pause | ADVERTISED_Asym_Pause); - mii_adv = (u32)mii_advertise_flowctrl(phy->fc_request_control); - phydev->advertising |= mii_adv_to_ethtool_adv_t(mii_adv); phy->fc_autoneg = phydev->autoneg; phy_start(phydev); diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c index 3e34bf53f055..c009407618d9 100644 --- a/drivers/net/ethernet/smsc/smsc911x.c +++ b/drivers/net/ethernet/smsc/smsc911x.c @@ -1051,8 +1051,7 @@ static int smsc911x_mii_probe(struct net_device *dev) phy_set_max_speed(phydev, SPEED_100); /* mask with MAC supported features */ - phydev->supported |= (SUPPORTED_Pause | SUPPORTED_Asym_Pause); - phydev->advertising = phydev->supported; + phy_support_asym_pause(phydev); pdata->last_duplex = -1; pdata->last_carrier = -1; diff --git a/drivers/net/ethernet/smsc/smsc9420.c b/drivers/net/ethernet/smsc/smsc9420.c index 326177384544..9b6366b20110 100644 --- a/drivers/net/ethernet/smsc/smsc9420.c +++ b/drivers/net/ethernet/smsc/smsc9420.c @@ -1138,8 +1138,7 @@ static int smsc9420_mii_probe(struct net_device *dev) phy_set_max_speed(phydev, SPEED_100); /* mask with MAC supported features */ - phydev->supported |= (SUPPORTED_Pause | SUPPORTED_Asym_Pause); - phydev->advertising = phydev->supported; + phy_support_asym_pause(phydev); phy_attached_info(phydev); diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c index 76ff364c40e9..a50720ec109c 100644 --- a/drivers/net/ethernet/socionext/sni_ave.c +++ b/drivers/net/ethernet/socionext/sni_ave.c @@ -1225,7 +1225,8 @@ static int ave_init(struct net_device *ndev) if (!phy_interface_is_rgmii(phydev)) phy_set_max_speed(phydev, SPEED_100); - phydev->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; + + phy_support_asym_pause(phydev); phy_attached_info(phydev); diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index e9ca83a438b0..a0646a66f005 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1783,6 +1783,19 @@ void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode) } EXPORT_SYMBOL(phy_remove_link_mode); +/** + * phy_support_asym_pause - Enable support of asym pause + * @phydev: target phy_device struct + * + * Description: Called by the MAC to indicate is supports Asym Pause. + */ +void phy_support_asym_pause(struct phy_device *phydev) +{ + phydev->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; + phydev->advertising = phydev->supported; +} +EXPORT_SYMBOL(phy_support_asym_pause); + static void of_set_phy_supported(struct phy_device *phydev) { struct device_node *node = phydev->mdio.dev.of_node; diff --git a/include/linux/phy.h b/include/linux/phy.h index 9c4c3eca8cf2..e2db819807c1 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1050,6 +1050,7 @@ int phy_start_interrupts(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); int phy_set_max_speed(struct phy_device *phydev, u32 max_speed); void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode); +void phy_support_asym_pause(struct phy_device *phydev); int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, int (*run)(struct phy_device *)); -- cgit v1.2.3 From c306ad36184fb7d0bd53f45441f45c1810e88a53 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 12 Sep 2018 01:53:16 +0200 Subject: net: ethernet: Add helper for MACs which support pause Rather than have the MAC drivers manipulate phydev members, add a helper function for MACs supporting Pause, but not Asym Pause. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bcm63xx_enet.c | 2 +- drivers/net/ethernet/freescale/fec_main.c | 4 +--- drivers/net/phy/phy_device.c | 14 ++++++++++++++ include/linux/phy.h | 1 + 4 files changed, 17 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c index 2eee9459c2cf..9f25667c38e6 100644 --- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c +++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c @@ -890,7 +890,7 @@ static int bcm_enet_open(struct net_device *dev) } /* mask with MAC supported features */ - phydev->supported |= SUPPORTED_Pause; + phy_support_sym_pause(phydev); phy_set_max_speed(phydev, SPEED_100); if (priv->pause_auto && priv->pause_rx && priv->pause_tx) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 0c6fd77b6599..05ce0903391a 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1950,14 +1950,12 @@ static int fec_enet_mii_probe(struct net_device *ndev) phy_remove_link_mode(phy_dev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT); #if !defined(CONFIG_M5272) - phy_dev->supported |= SUPPORTED_Pause; + phy_support_sym_pause(phy_dev); #endif } else phy_set_max_speed(phy_dev, 100); - phy_dev->advertising = phy_dev->supported; - fep->link = 0; fep->full_duplex = 0; diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index a0646a66f005..e657d5ae2ab8 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1783,6 +1783,20 @@ void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode) } EXPORT_SYMBOL(phy_remove_link_mode); +/** + * phy_support_sym_pause - Enable support of symmetrical pause + * @phydev: target phy_device struct + * + * Description: Called by the MAC to indicate is supports symmetrical + * Pause, but not asym pause. + */ +void phy_support_sym_pause(struct phy_device *phydev) +{ + phydev->supported |= SUPPORTED_Pause; + phydev->advertising = phydev->supported; +} +EXPORT_SYMBOL(phy_support_sym_pause); + /** * phy_support_asym_pause - Enable support of asym pause * @phydev: target phy_device struct diff --git a/include/linux/phy.h b/include/linux/phy.h index e2db819807c1..bc5d6c3f1388 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1050,6 +1050,7 @@ int phy_start_interrupts(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); int phy_set_max_speed(struct phy_device *phydev, u32 max_speed); void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode); +void phy_support_sym_pause(struct phy_device *phydev); void phy_support_asym_pause(struct phy_device *phydev); int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, -- cgit v1.2.3 From 70814e819c1139e5e7faacb3700eab5eac559272 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 12 Sep 2018 01:53:17 +0200 Subject: net: ethernet: Add helper for set_pauseparam for Asym Pause ethtool can be used to enable/disable pause. Add a helper to configure the PHY when asym pause is supported. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- .../net/ethernet/apm/xgene/xgene_enet_ethtool.c | 26 ++---------- drivers/net/ethernet/aurora/nb8800.c | 9 +--- drivers/net/ethernet/broadcom/tg3.c | 43 ++++++------------- drivers/net/ethernet/faraday/ftgmac100.c | 17 ++------ drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c | 23 +--------- drivers/net/ethernet/freescale/gianfar_ethtool.c | 49 +++++++--------------- .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 8 +--- drivers/net/ethernet/socionext/sni_ave.c | 11 +---- drivers/net/phy/phy_device.c | 30 +++++++++++++ include/linux/phy.h | 1 + 10 files changed, 69 insertions(+), 148 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_ethtool.c b/drivers/net/ethernet/apm/xgene/xgene_enet_ethtool.c index 4f50f11718f4..dfe03afd00b0 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_ethtool.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_ethtool.c @@ -306,7 +306,6 @@ static int xgene_set_pauseparam(struct net_device *ndev, { struct xgene_enet_pdata *pdata = netdev_priv(ndev); struct phy_device *phydev = ndev->phydev; - u32 oldadv, newadv; if (phy_interface_mode_is_rgmii(pdata->phy_mode) || pdata->phy_mode == PHY_INTERFACE_MODE_SGMII) { @@ -322,29 +321,12 @@ static int xgene_set_pauseparam(struct net_device *ndev, pdata->tx_pause = pp->tx_pause; pdata->rx_pause = pp->rx_pause; - oldadv = phydev->advertising; - newadv = oldadv & ~(ADVERTISED_Pause | ADVERTISED_Asym_Pause); + phy_set_asym_pause(phydev, pp->rx_pause, pp->tx_pause); - if (pp->rx_pause) - newadv |= ADVERTISED_Pause | ADVERTISED_Asym_Pause; - - if (pp->tx_pause) - newadv ^= ADVERTISED_Asym_Pause; - - if (oldadv ^ newadv) { - phydev->advertising = newadv; - - if (phydev->autoneg) - return phy_start_aneg(phydev); - - if (!pp->autoneg) { - pdata->mac_ops->flowctl_tx(pdata, - pdata->tx_pause); - pdata->mac_ops->flowctl_rx(pdata, - pdata->rx_pause); - } + if (!pp->autoneg) { + pdata->mac_ops->flowctl_tx(pdata, pdata->tx_pause); + pdata->mac_ops->flowctl_rx(pdata, pdata->rx_pause); } - } else { if (pp->autoneg) return -EINVAL; diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c index c8d1f8fa4713..6f56276015a4 100644 --- a/drivers/net/ethernet/aurora/nb8800.c +++ b/drivers/net/ethernet/aurora/nb8800.c @@ -935,18 +935,11 @@ static void nb8800_pause_adv(struct net_device *dev) { struct nb8800_priv *priv = netdev_priv(dev); struct phy_device *phydev = dev->phydev; - u32 adv = 0; if (!phydev) return; - if (priv->pause_rx) - adv |= ADVERTISED_Pause | ADVERTISED_Asym_Pause; - if (priv->pause_tx) - adv ^= ADVERTISED_Asym_Pause; - - phydev->supported |= adv; - phydev->advertising |= adv; + phy_set_asym_pause(phydev, priv->pause_rx, priv->pause_tx); } static int nb8800_open(struct net_device *dev) diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 193e990fac7a..b2a3d008e1df 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -12492,7 +12492,6 @@ static int tg3_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam tg3_warn_mgmt_link_flap(tp); if (tg3_flag(tp, USE_PHYLIB)) { - u32 newadv; struct phy_device *phydev; phydev = mdiobus_get_phy(tp->mdio_bus, tp->phy_addr); @@ -12503,20 +12502,16 @@ static int tg3_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam return -EINVAL; tp->link_config.flowctrl = 0; + phy_set_asym_pause(phydev, epause->rx_pause, epause->tx_pause); if (epause->rx_pause) { tp->link_config.flowctrl |= FLOW_CTRL_RX; if (epause->tx_pause) { tp->link_config.flowctrl |= FLOW_CTRL_TX; - newadv = ADVERTISED_Pause; - } else - newadv = ADVERTISED_Pause | - ADVERTISED_Asym_Pause; + } } else if (epause->tx_pause) { tp->link_config.flowctrl |= FLOW_CTRL_TX; - newadv = ADVERTISED_Asym_Pause; - } else - newadv = 0; + } if (epause->autoneg) tg3_flag_set(tp, PAUSE_AUTONEG); @@ -12524,33 +12519,19 @@ static int tg3_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam tg3_flag_clear(tp, PAUSE_AUTONEG); if (tp->phy_flags & TG3_PHYFLG_IS_CONNECTED) { - u32 oldadv = phydev->advertising & - (ADVERTISED_Pause | ADVERTISED_Asym_Pause); - if (oldadv != newadv) { - phydev->advertising &= - ~(ADVERTISED_Pause | - ADVERTISED_Asym_Pause); - phydev->advertising |= newadv; - if (phydev->autoneg) { - /* - * Always renegotiate the link to - * inform our link partner of our - * flow control settings, even if the - * flow control is forced. Let - * tg3_adjust_link() do the final - * flow control setup. - */ - return phy_start_aneg(phydev); - } + if (phydev->autoneg) { + /* phy_set_asym_pause() will + * renegotiate the link to inform our + * link partner of our flow control + * settings, even if the flow control + * is forced. Let tg3_adjust_link() + * do the final flow control setup. + */ + return 0; } if (!epause->autoneg) tg3_setup_flow_control(tp, 0, 0); - } else { - tp->link_config.advertising &= - ~(ADVERTISED_Pause | - ADVERTISED_Asym_Pause); - tp->link_config.advertising |= newadv; } } else { int irq_sync = 0; diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index 3f319ee66ab4..d8ead7e4177e 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -1219,22 +1219,11 @@ static int ftgmac100_set_pauseparam(struct net_device *netdev, priv->tx_pause = pause->tx_pause; priv->rx_pause = pause->rx_pause; - if (phydev) { - phydev->advertising &= ~ADVERTISED_Pause; - phydev->advertising &= ~ADVERTISED_Asym_Pause; + if (phydev) + phy_set_asym_pause(phydev, pause->rx_pause, pause->tx_pause); - if (pause->rx_pause) { - phydev->advertising |= ADVERTISED_Pause; - phydev->advertising |= ADVERTISED_Asym_Pause; - } - - if (pause->tx_pause) - phydev->advertising ^= ADVERTISED_Asym_Pause; - } if (netif_running(netdev)) { - if (phydev && priv->aneg_pause) - phy_start_aneg(phydev); - else + if (!(phydev && priv->aneg_pause)) ftgmac100_config_pause(priv); } diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c index 3184c8f7cdd0..1f8cdbc4378c 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c @@ -210,29 +210,8 @@ static int dpaa_set_pauseparam(struct net_device *net_dev, /* Determine the sym/asym advertised PAUSE capabilities from the desired * rx/tx pause settings. */ - newadv = 0; - if (epause->rx_pause) - newadv = ADVERTISED_Pause | ADVERTISED_Asym_Pause; - if (epause->tx_pause) - newadv ^= ADVERTISED_Asym_Pause; - oldadv = phydev->advertising & - (ADVERTISED_Pause | ADVERTISED_Asym_Pause); - - /* If there are differences between the old and the new advertised - * values, restart PHY autonegotiation and advertise the new values. - */ - if (oldadv != newadv) { - phydev->advertising &= ~(ADVERTISED_Pause - | ADVERTISED_Asym_Pause); - phydev->advertising |= newadv; - if (phydev->autoneg) { - err = phy_start_aneg(phydev); - if (err < 0) - netdev_err(net_dev, "phy_start_aneg() = %d\n", - err); - } - } + phy_set_asym_pause(phydev, epause->rx_pause, epause->tx_pause); fman_get_pause_cfg(mac_dev, &rx_pause, &tx_pause); err = fman_set_mac_active_pause(mac_dev, rx_pause, tx_pause); diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c index 395a5266ea30..3545e8f715f2 100644 --- a/drivers/net/ethernet/freescale/gianfar_ethtool.c +++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c @@ -503,7 +503,6 @@ static int gfar_spauseparam(struct net_device *dev, struct gfar_private *priv = netdev_priv(dev); struct phy_device *phydev = dev->phydev; struct gfar __iomem *regs = priv->gfargrp[0].regs; - u32 oldadv, newadv; if (!phydev) return -ENODEV; @@ -514,54 +513,36 @@ static int gfar_spauseparam(struct net_device *dev, return -EINVAL; priv->rx_pause_en = priv->tx_pause_en = 0; + phy_set_asym_pause(phydev, epause->rx_pause, epause->tx_pause); if (epause->rx_pause) { priv->rx_pause_en = 1; if (epause->tx_pause) { priv->tx_pause_en = 1; - /* FLOW_CTRL_RX & TX */ - newadv = ADVERTISED_Pause; - } else /* FLOW_CTLR_RX */ - newadv = ADVERTISED_Pause | ADVERTISED_Asym_Pause; + } } else if (epause->tx_pause) { priv->tx_pause_en = 1; - /* FLOW_CTLR_TX */ - newadv = ADVERTISED_Asym_Pause; - } else - newadv = 0; + } if (epause->autoneg) priv->pause_aneg_en = 1; else priv->pause_aneg_en = 0; - oldadv = phydev->advertising & - (ADVERTISED_Pause | ADVERTISED_Asym_Pause); - if (oldadv != newadv) { - phydev->advertising &= - ~(ADVERTISED_Pause | ADVERTISED_Asym_Pause); - phydev->advertising |= newadv; - if (phydev->autoneg) - /* inform link partner of our - * new flow ctrl settings - */ - return phy_start_aneg(phydev); - - if (!epause->autoneg) { - u32 tempval; - tempval = gfar_read(®s->maccfg1); - tempval &= ~(MACCFG1_TX_FLOW | MACCFG1_RX_FLOW); - - priv->tx_actual_en = 0; - if (priv->tx_pause_en) { - priv->tx_actual_en = 1; - tempval |= MACCFG1_TX_FLOW; - } + if (!epause->autoneg) { + u32 tempval = gfar_read(®s->maccfg1); - if (priv->rx_pause_en) - tempval |= MACCFG1_RX_FLOW; - gfar_write(®s->maccfg1, tempval); + tempval &= ~(MACCFG1_TX_FLOW | MACCFG1_RX_FLOW); + + priv->tx_actual_en = 0; + if (priv->tx_pause_en) { + priv->tx_actual_en = 1; + tempval |= MACCFG1_TX_FLOW; } + + if (priv->rx_pause_en) + tempval |= MACCFG1_RX_FLOW; + gfar_write(®s->maccfg1, tempval); } return 0; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index c56db06b63e0..cf18608669f5 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -5228,13 +5228,7 @@ static void hclge_set_flowctrl_adv(struct hclge_dev *hdev, u32 rx_en, u32 tx_en) if (!phydev) return; - phydev->advertising &= ~(ADVERTISED_Pause | ADVERTISED_Asym_Pause); - - if (rx_en) - phydev->advertising |= ADVERTISED_Pause | ADVERTISED_Asym_Pause; - - if (tx_en) - phydev->advertising ^= ADVERTISED_Asym_Pause; + phy_set_asym_pause(phydev, rx_en, tx_en); } static int hclge_cfg_pauseparam(struct hclge_dev *hdev, u32 rx_en, u32 tx_en) diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c index a50720ec109c..61e6abb966ac 100644 --- a/drivers/net/ethernet/socionext/sni_ave.c +++ b/drivers/net/ethernet/socionext/sni_ave.c @@ -461,16 +461,7 @@ static int ave_ethtool_set_pauseparam(struct net_device *ndev, priv->pause_rx = pause->rx_pause; priv->pause_tx = pause->tx_pause; - phydev->advertising &= ~(ADVERTISED_Pause | ADVERTISED_Asym_Pause); - if (pause->rx_pause) - phydev->advertising |= ADVERTISED_Pause | ADVERTISED_Asym_Pause; - if (pause->tx_pause) - phydev->advertising ^= ADVERTISED_Asym_Pause; - - if (pause->autoneg) { - if (netif_running(ndev)) - phy_start_aneg(phydev); - } + phy_set_asym_pause(phydev, pause->rx_pause, pause->tx_pause); return 0; } diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index e657d5ae2ab8..5732d89c8e37 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1810,6 +1810,36 @@ void phy_support_asym_pause(struct phy_device *phydev) } EXPORT_SYMBOL(phy_support_asym_pause); +/** + * phy_set_asym_pause - Configure Pause and Asym Pause + * @phydev: target phy_device struct + * @rx: Receiver Pause is supported + * @tx: Transmit Pause is supported + * + * Description: Configure advertised Pause support depending on if + * transmit and receiver pause is supported. If there has been a + * change in adverting, trigger a new autoneg. Generally called from + * the set_pauseparam .ndo. + */ +void phy_set_asym_pause(struct phy_device *phydev, bool rx, bool tx) +{ + u16 oldadv = phydev->advertising; + u16 newadv = oldadv &= ~(SUPPORTED_Pause | SUPPORTED_Asym_Pause); + + if (rx) + newadv |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; + if (tx) + newadv ^= SUPPORTED_Asym_Pause; + + if (oldadv != newadv) { + phydev->advertising = newadv; + + if (phydev->autoneg) + phy_start_aneg(phydev); + } +} +EXPORT_SYMBOL(phy_set_asym_pause); + static void of_set_phy_supported(struct phy_device *phydev) { struct device_node *node = phydev->mdio.dev.of_node; diff --git a/include/linux/phy.h b/include/linux/phy.h index bc5d6c3f1388..e4062ba7472f 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1052,6 +1052,7 @@ int phy_set_max_speed(struct phy_device *phydev, u32 max_speed); void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode); void phy_support_sym_pause(struct phy_device *phydev); void phy_support_asym_pause(struct phy_device *phydev); +void phy_set_asym_pause(struct phy_device *phydev, bool rx, bool tx); int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, int (*run)(struct phy_device *)); -- cgit v1.2.3 From 0c122405d4c3ec638ba00865c872ec5a3ed1a6c0 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 12 Sep 2018 01:53:18 +0200 Subject: net: ethernet: Add helper for set_pauseparam for Pause ethtool can be used to enable/disable pause. Add a helper to configure the PHY when Pause is supported. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bcm63xx_enet.c | 7 ++----- drivers/net/ethernet/freescale/fec_main.c | 9 ++------- drivers/net/phy/phy_device.c | 23 +++++++++++++++++++++++ include/linux/phy.h | 2 ++ 4 files changed, 29 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c index 9f25667c38e6..02e7dfc1a2ef 100644 --- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c +++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c @@ -892,11 +892,8 @@ static int bcm_enet_open(struct net_device *dev) /* mask with MAC supported features */ phy_support_sym_pause(phydev); phy_set_max_speed(phydev, SPEED_100); - - if (priv->pause_auto && priv->pause_rx && priv->pause_tx) - phydev->advertising |= SUPPORTED_Pause; - else - phydev->advertising &= ~SUPPORTED_Pause; + phy_set_sym_pause(phydev, priv->pause_rx, priv->pause_rx, + priv->pause_auto); phy_attached_info(phydev); diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 05ce0903391a..2e0bb90131b6 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -2229,13 +2229,8 @@ static int fec_enet_set_pauseparam(struct net_device *ndev, fep->pause_flag |= pause->rx_pause ? FEC_PAUSE_FLAG_ENABLE : 0; fep->pause_flag |= pause->autoneg ? FEC_PAUSE_FLAG_AUTONEG : 0; - if (pause->rx_pause || pause->autoneg) { - ndev->phydev->supported |= ADVERTISED_Pause; - ndev->phydev->advertising |= ADVERTISED_Pause; - } else { - ndev->phydev->supported &= ~ADVERTISED_Pause; - ndev->phydev->advertising &= ~ADVERTISED_Pause; - } + phy_set_sym_pause(ndev->phydev, pause->rx_pause, pause->tx_pause, + pause->autoneg); if (pause->autoneg) { if (netif_running(ndev)) diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 5732d89c8e37..de95f1e072e9 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1810,6 +1810,29 @@ void phy_support_asym_pause(struct phy_device *phydev) } EXPORT_SYMBOL(phy_support_asym_pause); +/** + * phy_set_sym_pause - Configure symmetric Pause + * @phydev: target phy_device struct + * @rx: Receiver Pause is supported + * @tx: Transmit Pause is supported + * @autoneg: Auto neg should be used + * + * Description: Configure advertised Pause support depending on if + * receiver pause and pause auto neg is supported. Generally called + * from the set_pauseparam .ndo. + */ +void phy_set_sym_pause(struct phy_device *phydev, bool rx, bool tx, + bool autoneg) +{ + phydev->supported &= ~SUPPORTED_Pause; + + if (rx && tx && autoneg) + phydev->supported |= SUPPORTED_Pause; + + phydev->advertising = phydev->supported; +} +EXPORT_SYMBOL(phy_set_sym_pause); + /** * phy_set_asym_pause - Configure Pause and Asym Pause * @phydev: target phy_device struct diff --git a/include/linux/phy.h b/include/linux/phy.h index e4062ba7472f..8521391ebb20 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1052,6 +1052,8 @@ int phy_set_max_speed(struct phy_device *phydev, u32 max_speed); void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode); void phy_support_sym_pause(struct phy_device *phydev); void phy_support_asym_pause(struct phy_device *phydev); +void phy_set_sym_pause(struct phy_device *phydev, bool rx, bool tx, + bool autoneg); void phy_set_asym_pause(struct phy_device *phydev, bool rx, bool tx); int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, -- cgit v1.2.3 From 22b7d29926b577ff4f480611380d03268545b787 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 12 Sep 2018 01:53:19 +0200 Subject: net: ethernet: Add helper to determine if pause configuration is supported Rather than have MAC drivers open code the test, add a helper in phylib. This will help when we change the type of phydev->supported. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/ethernet/apm/xgene/xgene_enet_ethtool.c | 4 +--- drivers/net/ethernet/broadcom/tg3.c | 4 +--- drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c | 4 +--- drivers/net/ethernet/freescale/gianfar_ethtool.c | 4 +--- drivers/net/phy/phy_device.c | 20 ++++++++++++++++++++ include/linux/phy.h | 2 ++ 6 files changed, 26 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_ethtool.c b/drivers/net/ethernet/apm/xgene/xgene_enet_ethtool.c index dfe03afd00b0..78dd09b5beeb 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_ethtool.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_ethtool.c @@ -312,9 +312,7 @@ static int xgene_set_pauseparam(struct net_device *ndev, if (!phydev) return -EINVAL; - if (!(phydev->supported & SUPPORTED_Pause) || - (!(phydev->supported & SUPPORTED_Asym_Pause) && - pp->rx_pause != pp->tx_pause)) + if (!phy_validate_pause(phydev, pp)) return -EINVAL; pdata->pause_autoneg = pp->autoneg; diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index b2a3d008e1df..fb0e458e25b7 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -12496,9 +12496,7 @@ static int tg3_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam phydev = mdiobus_get_phy(tp->mdio_bus, tp->phy_addr); - if (!(phydev->supported & SUPPORTED_Pause) || - (!(phydev->supported & SUPPORTED_Asym_Pause) && - (epause->rx_pause != epause->tx_pause))) + if (!phy_validate_pause(phydev, epause)) return -EINVAL; tp->link_config.flowctrl = 0; diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c index 1f8cdbc4378c..5d0fdf667b82 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c @@ -194,9 +194,7 @@ static int dpaa_set_pauseparam(struct net_device *net_dev, return -ENODEV; } - if (!(phydev->supported & SUPPORTED_Pause) || - (!(phydev->supported & SUPPORTED_Asym_Pause) && - (epause->rx_pause != epause->tx_pause))) + if (!phy_validate_pause(phydev, epause)) return -EINVAL; /* The MAC should know how to handle PAUSE frame autonegotiation before diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c index 3545e8f715f2..d3662965f59d 100644 --- a/drivers/net/ethernet/freescale/gianfar_ethtool.c +++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c @@ -507,9 +507,7 @@ static int gfar_spauseparam(struct net_device *dev, if (!phydev) return -ENODEV; - if (!(phydev->supported & SUPPORTED_Pause) || - (!(phydev->supported & SUPPORTED_Asym_Pause) && - (epause->rx_pause != epause->tx_pause))) + if (!phy_validate_pause(phydev, epause)) return -EINVAL; priv->rx_pause_en = priv->tx_pause_en = 0; diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index de95f1e072e9..af64a9320fb0 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1863,6 +1863,26 @@ void phy_set_asym_pause(struct phy_device *phydev, bool rx, bool tx) } EXPORT_SYMBOL(phy_set_asym_pause); +/** + * phy_validate_pause - Test if the PHY/MAC support the pause configuration + * @phydev: phy_device struct + * @pp: requested pause configuration + * + * Description: Test if the PHY/MAC combination supports the Pause + * configuration the user is requesting. Returns True if it is + * supported, false otherwise. + */ +bool phy_validate_pause(struct phy_device *phydev, + struct ethtool_pauseparam *pp) +{ + if (!(phydev->supported & SUPPORTED_Pause) || + (!(phydev->supported & SUPPORTED_Asym_Pause) && + pp->rx_pause != pp->tx_pause)) + return false; + return true; +} +EXPORT_SYMBOL(phy_validate_pause); + static void of_set_phy_supported(struct phy_device *phydev) { struct device_node *node = phydev->mdio.dev.of_node; diff --git a/include/linux/phy.h b/include/linux/phy.h index 8521391ebb20..192a1fa0c73b 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1055,6 +1055,8 @@ void phy_support_asym_pause(struct phy_device *phydev); void phy_set_sym_pause(struct phy_device *phydev, bool rx, bool tx, bool autoneg); void phy_set_asym_pause(struct phy_device *phydev, bool rx, bool tx); +bool phy_validate_pause(struct phy_device *phydev, + struct ethtool_pauseparam *pp); int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, int (*run)(struct phy_device *)); -- cgit v1.2.3 From 15033f0457dca569b284bef0c8d3ad55fb37eacb Mon Sep 17 00:00:00 2001 From: Andre Naujoks Date: Mon, 10 Sep 2018 10:27:15 +0200 Subject: ipv6: Add sockopt IPV6_MULTICAST_ALL analogue to IP_MULTICAST_ALL The socket option will be enabled by default to ensure current behaviour is not changed. This is the same for the IPv4 version. A socket bound to in6addr_any and a specific port will receive all traffic on that port. Analogue to IP_MULTICAST_ALL, disable this behaviour, if one or more multicast groups were joined (using said socket) and only pass on multicast traffic from groups, which were explicitly joined via this socket. Without this option disabled a socket (system even) joined to multiple multicast groups is very hard to get right. Filtering by destination address has to take place in user space to avoid receiving multicast traffic from other multicast groups, which might have traffic on the same port. The extension of the IP_MULTICAST_ALL socketoption to just apply to ipv6, too, is not done to avoid changing the behaviour of current applications. Signed-off-by: Andre Naujoks Acked-By: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- include/linux/ipv6.h | 3 ++- include/uapi/linux/in6.h | 1 + net/ipv6/af_inet6.c | 1 + net/ipv6/ipv6_sockglue.c | 11 +++++++++++ net/ipv6/mcast.c | 2 +- 5 files changed, 16 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 8415bf1a9776..495e834c1367 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -274,7 +274,8 @@ struct ipv6_pinfo { */ dontfrag:1, autoflowlabel:1, - autoflowlabel_set:1; + autoflowlabel_set:1, + mc_all:1; __u8 min_hopcount; __u8 tclass; __be32 rcv_flowinfo; diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h index ed291e55f024..71d82fe15b03 100644 --- a/include/uapi/linux/in6.h +++ b/include/uapi/linux/in6.h @@ -177,6 +177,7 @@ struct in6_flowlabel_req { #define IPV6_V6ONLY 26 #define IPV6_JOIN_ANYCAST 27 #define IPV6_LEAVE_ANYCAST 28 +#define IPV6_MULTICAST_ALL 29 /* IPV6_MTU_DISCOVER values */ #define IPV6_PMTUDISC_DONT 0 diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 9a4261e50272..77ef8478234f 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -209,6 +209,7 @@ lookup_protocol: np->hop_limit = -1; np->mcast_hops = IPV6_DEFAULT_MCASTHOPS; np->mc_loop = 1; + np->mc_all = 1; np->pmtudisc = IPV6_PMTUDISC_WANT; np->repflow = net->ipv6.sysctl.flowlabel_reflect; sk->sk_ipv6only = net->ipv6.sysctl.bindv6only; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index c0cac9cc3a28..381ce38940ae 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -674,6 +674,13 @@ done: retv = ipv6_sock_ac_drop(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_acaddr); break; } + case IPV6_MULTICAST_ALL: + if (optlen < sizeof(int)) + goto e_inval; + np->mc_all = valbool; + retv = 0; + break; + case MCAST_JOIN_GROUP: case MCAST_LEAVE_GROUP: { @@ -1266,6 +1273,10 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, val = np->mcast_oif; break; + case IPV6_MULTICAST_ALL: + val = np->mc_all; + break; + case IPV6_UNICAST_IF: val = (__force int)htonl((__u32) np->ucast_oif); break; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 4ae54aaca373..6895e1dc0b03 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -636,7 +636,7 @@ bool inet6_mc_check(struct sock *sk, const struct in6_addr *mc_addr, } if (!mc) { rcu_read_unlock(); - return true; + return np->mc_all; } read_lock(&mc->sflock); psl = mc->sflist; -- cgit v1.2.3 From fe8dd45bb7556246c6b76277b1ba4296c91c2505 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Wed, 12 Sep 2018 11:17:06 +0800 Subject: tun: switch to new type of msg_control This patch introduces to a new tun/tap specific msg_control: #define TUN_MSG_UBUF 1 #define TUN_MSG_PTR 2 struct tun_msg_ctl { int type; void *ptr; }; This allows us to pass different kinds of msg_control through sendmsg(). The first supported type is ubuf (TUN_MSG_UBUF) which will be used by the existed vhost_net zerocopy code. The second is XDP buff, which allows vhost_net to pass XDP buff to TUN. This could be used to implement accepting an array of XDP buffs from vhost_net in the following patches. Signed-off-by: Jason Wang Signed-off-by: David S. Miller --- drivers/net/tap.c | 18 ++++++++++++------ drivers/net/tun.c | 6 +++++- drivers/vhost/net.c | 7 +++++-- include/linux/if_tun.h | 14 ++++++++++++++ 4 files changed, 36 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/tap.c b/drivers/net/tap.c index f0f7cd977667..7996ed7cbf18 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -619,7 +619,7 @@ static inline struct sk_buff *tap_alloc_skb(struct sock *sk, size_t prepad, #define TAP_RESERVE HH_DATA_OFF(ETH_HLEN) /* Get packet from user space buffer */ -static ssize_t tap_get_user(struct tap_queue *q, struct msghdr *m, +static ssize_t tap_get_user(struct tap_queue *q, void *msg_control, struct iov_iter *from, int noblock) { int good_linear = SKB_MAX_HEAD(TAP_RESERVE); @@ -663,7 +663,7 @@ static ssize_t tap_get_user(struct tap_queue *q, struct msghdr *m, if (unlikely(len < ETH_HLEN)) goto err; - if (m && m->msg_control && sock_flag(&q->sk, SOCK_ZEROCOPY)) { + if (msg_control && sock_flag(&q->sk, SOCK_ZEROCOPY)) { struct iov_iter i; copylen = vnet_hdr.hdr_len ? @@ -724,11 +724,11 @@ static ssize_t tap_get_user(struct tap_queue *q, struct msghdr *m, tap = rcu_dereference(q->tap); /* copy skb_ubuf_info for callback when skb has no error */ if (zerocopy) { - skb_shinfo(skb)->destructor_arg = m->msg_control; + skb_shinfo(skb)->destructor_arg = msg_control; skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY; skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; - } else if (m && m->msg_control) { - struct ubuf_info *uarg = m->msg_control; + } else if (msg_control) { + struct ubuf_info *uarg = msg_control; uarg->callback(uarg, false); } @@ -1150,7 +1150,13 @@ static int tap_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) { struct tap_queue *q = container_of(sock, struct tap_queue, sock); - return tap_get_user(q, m, &m->msg_iter, m->msg_flags & MSG_DONTWAIT); + struct tun_msg_ctl *ctl = m->msg_control; + + if (ctl && ctl->type != TUN_MSG_UBUF) + return -EINVAL; + + return tap_get_user(q, ctl ? ctl->ptr : NULL, &m->msg_iter, + m->msg_flags & MSG_DONTWAIT); } static int tap_recvmsg(struct socket *sock, struct msghdr *m, diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 3ae539374f6b..89779b58c7ca 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -2431,11 +2431,15 @@ static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) int ret; struct tun_file *tfile = container_of(sock, struct tun_file, socket); struct tun_struct *tun = tun_get(tfile); + struct tun_msg_ctl *ctl = m->msg_control; if (!tun) return -EBADFD; - ret = tun_get_user(tun, tfile, m->msg_control, &m->msg_iter, + if (ctl && ctl->type != TUN_MSG_UBUF) + return -EINVAL; + + ret = tun_get_user(tun, tfile, ctl ? ctl->ptr : NULL, &m->msg_iter, m->msg_flags & MSG_DONTWAIT, m->msg_flags & MSG_MORE); tun_put(tun); diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 4e656f89cb22..fb01ce6d981c 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -620,6 +620,7 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock) .msg_controllen = 0, .msg_flags = MSG_DONTWAIT, }; + struct tun_msg_ctl ctl; size_t len, total_len = 0; int err; struct vhost_net_ubuf_ref *uninitialized_var(ubufs); @@ -664,8 +665,10 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock) ubuf->ctx = nvq->ubufs; ubuf->desc = nvq->upend_idx; refcount_set(&ubuf->refcnt, 1); - msg.msg_control = ubuf; - msg.msg_controllen = sizeof(ubuf); + msg.msg_control = &ctl; + ctl.type = TUN_MSG_UBUF; + ctl.ptr = ubuf; + msg.msg_controllen = sizeof(ctl); ubufs = nvq->ubufs; atomic_inc(&ubufs->refcount); nvq->upend_idx = (nvq->upend_idx + 1) % UIO_MAXIOV; diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h index 3d2996dc7d85..12e3eebf0ce6 100644 --- a/include/linux/if_tun.h +++ b/include/linux/if_tun.h @@ -16,9 +16,23 @@ #define __IF_TUN_H #include +#include #define TUN_XDP_FLAG 0x1UL +#define TUN_MSG_UBUF 1 +#define TUN_MSG_PTR 2 +struct tun_msg_ctl { + unsigned short type; + unsigned short num; + void *ptr; +}; + +struct tun_xdp_hdr { + int buflen; + struct virtio_net_hdr gso; +}; + #if defined(CONFIG_TUN) || defined(CONFIG_TUN_MODULE) struct socket *tun_get_socket(struct file *); struct ptr_ring *tun_get_tx_ring(struct file *file); -- cgit v1.2.3 From e21120383f2dce32312f63ffca145ff8a87d41f5 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 11 Sep 2018 19:47:09 -0400 Subject: move compat handling of tty ioctls to tty_compat_ioctl() ioctls that are * callable only via tty_ioctl() * not driver-specific * not demand data structure conversions * either always need passing arg as is or always demand compat_ptr() get intercepted in tty_compat_ioctl() from the very beginning and redirecter to tty_ioctl(). As the result, their entries in fs/compat_ioctl.c (some of those had been missing, BTW) got removed, as well as n_tty_compat_ioctl_helper() (now it's never called with any cmd it would accept). Signed-off-by: Al Viro --- drivers/tty/tty_io.c | 78 +++++++++++++++++++++++++++++++++++++++++++++++-- drivers/tty/tty_ioctl.c | 16 ---------- fs/compat_ioctl.c | 51 -------------------------------- include/linux/tty.h | 2 -- 4 files changed, 76 insertions(+), 71 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 32bc3e3fe4d3..7bfc8afc130a 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -97,6 +97,7 @@ #include #include #include +#include #include @@ -2668,6 +2669,81 @@ static long tty_compat_ioctl(struct file *file, unsigned int cmd, struct tty_ldisc *ld; int retval = -ENOIOCTLCMD; + switch (cmd) { + case TIOCSTI: + case TIOCGWINSZ: + case TIOCSWINSZ: + case TIOCGEXCL: + case TIOCGETD: + case TIOCSETD: + case TIOCGDEV: + case TIOCMGET: + case TIOCMSET: + case TIOCMBIC: + case TIOCMBIS: + case TIOCGICOUNT: + case TIOCGPGRP: + case TIOCSPGRP: + case TIOCGSID: + case TIOCSERGETLSR: + case TIOCGRS485: + case TIOCSRS485: +#ifdef TIOCGETP + case TIOCGETP: + case TIOCSETP: + case TIOCSETN: +#endif +#ifdef TIOCGETC + case TIOCGETC: + case TIOCSETC: +#endif +#ifdef TIOCGLTC + case TIOCGLTC: + case TIOCSLTC: +#endif + case TCSETSF: + case TCSETSW: + case TCSETS: + case TCGETS: +#ifdef TCGETS2 + case TCGETS2: + case TCSETSF2: + case TCSETSW2: + case TCSETS2: +#endif + case TCGETA: + case TCSETAF: + case TCSETAW: + case TCSETA: + case TIOCGLCKTRMIOS: + case TIOCSLCKTRMIOS: +#ifdef TCGETX + case TCGETX: + case TCSETX: + case TCSETXW: + case TCSETXF: +#endif + case TIOCGSOFTCAR: + case TIOCSSOFTCAR: + return tty_ioctl(file, cmd, (unsigned long)compat_ptr(arg)); + case TIOCCONS: + case TIOCEXCL: + case TIOCNXCL: + case TIOCVHANGUP: + case TIOCSBRK: + case TIOCCBRK: + case TCSBRK: + case TCSBRKP: + case TCFLSH: + case TIOCGPTPEER: + case TIOCNOTTY: + case TIOCSCTTY: + case TCXONC: + case TIOCMIWAIT: + case TIOCSERCONFIG: + return tty_ioctl(file, cmd, arg); + } + if (tty_paranoia_check(tty, file_inode(file), "tty_ioctl")) return -EINVAL; @@ -2682,8 +2758,6 @@ static long tty_compat_ioctl(struct file *file, unsigned int cmd, return hung_up_tty_compat_ioctl(file, cmd, arg); if (ld->ops->compat_ioctl) retval = ld->ops->compat_ioctl(tty, file, cmd, arg); - else - retval = n_tty_compat_ioctl_helper(tty, file, cmd, arg); tty_ldisc_deref(ld); return retval; diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c index d99fec44036c..9245fffdbceb 100644 --- a/drivers/tty/tty_ioctl.c +++ b/drivers/tty/tty_ioctl.c @@ -941,19 +941,3 @@ int n_tty_ioctl_helper(struct tty_struct *tty, struct file *file, } } EXPORT_SYMBOL(n_tty_ioctl_helper); - -#ifdef CONFIG_COMPAT -long n_tty_compat_ioctl_helper(struct tty_struct *tty, struct file *file, - unsigned int cmd, unsigned long arg) -{ - switch (cmd) { - case TIOCGLCKTRMIOS: - case TIOCSLCKTRMIOS: - return tty_mode_ioctl(tty, file, cmd, (unsigned long) compat_ptr(arg)); - default: - return -ENOIOCTLCMD; - } -} -EXPORT_SYMBOL(n_tty_compat_ioctl_helper); -#endif - diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index 53bc3659dcef..670b8cbd0896 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -711,52 +711,9 @@ COMPATIBLE_IOCTL(0x4B50) /* KDGHWCLK - not in the kernel, but don't complain * COMPATIBLE_IOCTL(0x4B51) /* KDSHWCLK - not in the kernel, but don't complain */ /* Big T */ -COMPATIBLE_IOCTL(TCGETA) -COMPATIBLE_IOCTL(TCSETA) -COMPATIBLE_IOCTL(TCSETAW) -COMPATIBLE_IOCTL(TCSETAF) -COMPATIBLE_IOCTL(TCSBRK) -COMPATIBLE_IOCTL(TCXONC) -COMPATIBLE_IOCTL(TCFLSH) -COMPATIBLE_IOCTL(TCGETS) -COMPATIBLE_IOCTL(TCSETS) -COMPATIBLE_IOCTL(TCSETSW) -COMPATIBLE_IOCTL(TCSETSF) COMPATIBLE_IOCTL(TIOCLINUX) -COMPATIBLE_IOCTL(TIOCSBRK) -COMPATIBLE_IOCTL(TIOCGDEV) -COMPATIBLE_IOCTL(TIOCCBRK) -COMPATIBLE_IOCTL(TIOCGSID) -COMPATIBLE_IOCTL(TIOCGICOUNT) -COMPATIBLE_IOCTL(TIOCGEXCL) /* Little t */ -COMPATIBLE_IOCTL(TIOCGETD) -COMPATIBLE_IOCTL(TIOCSETD) -COMPATIBLE_IOCTL(TIOCEXCL) -COMPATIBLE_IOCTL(TIOCNXCL) -COMPATIBLE_IOCTL(TIOCCONS) -COMPATIBLE_IOCTL(TIOCGSOFTCAR) -COMPATIBLE_IOCTL(TIOCSSOFTCAR) -COMPATIBLE_IOCTL(TIOCSWINSZ) -COMPATIBLE_IOCTL(TIOCGWINSZ) -COMPATIBLE_IOCTL(TIOCMGET) -COMPATIBLE_IOCTL(TIOCMBIC) -COMPATIBLE_IOCTL(TIOCMBIS) -COMPATIBLE_IOCTL(TIOCMSET) -COMPATIBLE_IOCTL(TIOCNOTTY) -COMPATIBLE_IOCTL(TIOCSTI) COMPATIBLE_IOCTL(TIOCOUTQ) -COMPATIBLE_IOCTL(TIOCSPGRP) -COMPATIBLE_IOCTL(TIOCGPGRP) -COMPATIBLE_IOCTL(TIOCSERGETLSR) -COMPATIBLE_IOCTL(TIOCSRS485) -COMPATIBLE_IOCTL(TIOCGRS485) -#ifdef TCGETS2 -COMPATIBLE_IOCTL(TCGETS2) -COMPATIBLE_IOCTL(TCSETS2) -COMPATIBLE_IOCTL(TCSETSW2) -COMPATIBLE_IOCTL(TCSETSF2) -#endif /* Little f */ COMPATIBLE_IOCTL(FIOCLEX) COMPATIBLE_IOCTL(FIONCLEX) @@ -1219,10 +1176,6 @@ COMPATIBLE_IOCTL(JSIOCGAXES) COMPATIBLE_IOCTL(JSIOCGBUTTONS) COMPATIBLE_IOCTL(JSIOCGNAME(0)) -#ifdef TIOCGLTC -COMPATIBLE_IOCTL(TIOCGLTC) -COMPATIBLE_IOCTL(TIOCSLTC) -#endif #ifdef TIOCSTART /* * For these two we have definitions in ioctls.h and/or termios.h on @@ -1312,10 +1265,6 @@ static long do_ioctl_trans(unsigned int cmd, * so we must not do a compat_ptr() translation. */ switch (cmd) { - /* Big T */ - case TCSBRKP: - case TIOCMIWAIT: - case TIOCSCTTY: /* RAID */ case HOT_REMOVE_DISK: case HOT_ADD_DISK: diff --git a/include/linux/tty.h b/include/linux/tty.h index c56e3978b00f..414db2bce715 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -746,8 +746,6 @@ static inline int tty_audit_push(void) /* tty_ioctl.c */ extern int n_tty_ioctl_helper(struct tty_struct *tty, struct file *file, unsigned int cmd, unsigned long arg); -extern long n_tty_compat_ioctl_helper(struct tty_struct *tty, struct file *file, - unsigned int cmd, unsigned long arg); /* vt.c */ -- cgit v1.2.3 From 2f46a2c1d4eb982b82c199e1bd5cddab12681275 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 11 Sep 2018 21:53:32 -0400 Subject: tty_ioctl(): start taking TIOC[SG]SERIAL into separate methods ->set_serial() and ->get_serial() resp., both taking tty and a kernel pointer to serial_struct. Signed-off-by: Al Viro --- drivers/tty/tty_io.c | 35 ++++++++++++++++++++++++++++++----- include/linux/tty_driver.h | 3 +++ 2 files changed, 33 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index ef2a8766d34f..b96bfd051d59 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -2456,22 +2456,40 @@ static int tty_tiocgicount(struct tty_struct *tty, void __user *arg) return 0; } -static void tty_warn_deprecated_flags(struct serial_struct __user *ss) +static int tty_tiocsserial(struct tty_struct *tty, struct serial_struct __user *ss) { static DEFINE_RATELIMIT_STATE(depr_flags, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); char comm[TASK_COMM_LEN]; + struct serial_struct v; int flags; - if (get_user(flags, &ss->flags)) - return; + if (copy_from_user(&v, ss, sizeof(struct serial_struct))) + return -EFAULT; - flags &= ASYNC_DEPRECATED; + flags = v.flags & ASYNC_DEPRECATED; if (flags && __ratelimit(&depr_flags)) pr_warn("%s: '%s' is using deprecated serial flags (with no effect): %.8x\n", __func__, get_task_comm(comm, current), flags); + if (!tty->ops->set_serial) + return -ENOIOCTLCMD; + return tty->ops->set_serial(tty, &v); +} + +static int tty_tiocgserial(struct tty_struct *tty, struct serial_struct __user *ss) +{ + struct serial_struct v; + int err; + + memset(&v, 0, sizeof(struct serial_struct)); + if (!tty->ops->get_serial) + return -ENOIOCTLCMD; + err = tty->ops->get_serial(tty, &v); + if (!err && copy_to_user(ss, &v, sizeof(struct serial_struct))) + err = -EFAULT; + return err; } /* @@ -2603,7 +2621,14 @@ long tty_ioctl(struct file *file, unsigned int cmd, unsigned long arg) } break; case TIOCSSERIAL: - tty_warn_deprecated_flags(p); + retval = tty_tiocsserial(tty, p); + if (retval != -ENOIOCTLCMD) + return retval; + break; + case TIOCGSERIAL: + retval = tty_tiocgserial(tty, p); + if (retval != -ENOIOCTLCMD) + return retval; break; case TIOCGPTPEER: /* Special because the struct file is needed */ diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index 71dbc891851a..358446247ccd 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -249,6 +249,7 @@ struct tty_struct; struct tty_driver; struct serial_icounter_struct; +struct serial_struct; struct tty_operations { struct tty_struct * (*lookup)(struct tty_driver *driver, @@ -287,6 +288,8 @@ struct tty_operations { int (*set_termiox)(struct tty_struct *tty, struct termiox *tnew); int (*get_icount)(struct tty_struct *tty, struct serial_icounter_struct *icount); + int (*get_serial)(struct tty_struct *tty, struct serial_struct *p); + int (*set_serial)(struct tty_struct *tty, struct serial_struct *p); void (*show_fdinfo)(struct tty_struct *tty, struct seq_file *m); #ifdef CONFIG_CONSOLE_POLL int (*poll_init)(struct tty_driver *driver, int line, char *options); -- cgit v1.2.3 From 52bb6677d530d37055092d86b4eab69dce6c166a Mon Sep 17 00:00:00 2001 From: Li RongQing Date: Fri, 14 Sep 2018 16:00:51 +0800 Subject: net: move definition of pcpu_lstats to header file pcpu_lstats is defined in several files, so unify them as one and move to header file Signed-off-by: Zhang Yu Signed-off-by: Li RongQing Signed-off-by: David S. Miller --- drivers/net/loopback.c | 6 ------ drivers/net/nlmon.c | 6 ------ drivers/net/vsockmon.c | 14 ++++---------- include/linux/netdevice.h | 6 ++++++ 4 files changed, 10 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index 30612497643c..a7207fa7e451 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -59,12 +59,6 @@ #include #include -struct pcpu_lstats { - u64 packets; - u64 bytes; - struct u64_stats_sync syncp; -}; - /* The higher levels take care of making this non-reentrant (it's * called with bh's disabled). */ diff --git a/drivers/net/nlmon.c b/drivers/net/nlmon.c index 4b22955de191..dd0db7534cb3 100644 --- a/drivers/net/nlmon.c +++ b/drivers/net/nlmon.c @@ -6,12 +6,6 @@ #include #include -struct pcpu_lstats { - u64 packets; - u64 bytes; - struct u64_stats_sync syncp; -}; - static netdev_tx_t nlmon_xmit(struct sk_buff *skb, struct net_device *dev) { int len = skb->len; diff --git a/drivers/net/vsockmon.c b/drivers/net/vsockmon.c index c28bdce14fd5..7bad5c95551f 100644 --- a/drivers/net/vsockmon.c +++ b/drivers/net/vsockmon.c @@ -11,12 +11,6 @@ #define DEFAULT_MTU (VIRTIO_VSOCK_MAX_PKT_BUF_SIZE + \ sizeof(struct af_vsockmon_hdr)) -struct pcpu_lstats { - u64 rx_packets; - u64 rx_bytes; - struct u64_stats_sync syncp; -}; - static int vsockmon_dev_init(struct net_device *dev) { dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats); @@ -56,8 +50,8 @@ static netdev_tx_t vsockmon_xmit(struct sk_buff *skb, struct net_device *dev) struct pcpu_lstats *stats = this_cpu_ptr(dev->lstats); u64_stats_update_begin(&stats->syncp); - stats->rx_bytes += len; - stats->rx_packets++; + stats->bytes += len; + stats->packets++; u64_stats_update_end(&stats->syncp); dev_kfree_skb(skb); @@ -80,8 +74,8 @@ vsockmon_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) do { start = u64_stats_fetch_begin_irq(&vstats->syncp); - tbytes = vstats->rx_bytes; - tpackets = vstats->rx_packets; + tbytes = vstats->bytes; + tpackets = vstats->packets; } while (u64_stats_fetch_retry_irq(&vstats->syncp, start)); packets += tpackets; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e2b3bd750c98..baed5d5088c5 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2382,6 +2382,12 @@ struct pcpu_sw_netstats { struct u64_stats_sync syncp; }; +struct pcpu_lstats { + u64 packets; + u64 bytes; + struct u64_stats_sync syncp; +}; + #define __netdev_alloc_pcpu_stats(type, gfp) \ ({ \ typeof(type) __percpu *pcpu_stats = alloc_percpu_gfp(type, gfp);\ -- cgit v1.2.3 From d58e468b1112dcd1d5193c0a89ff9f98b5a3e8b9 Mon Sep 17 00:00:00 2001 From: Petar Penkov Date: Fri, 14 Sep 2018 07:46:18 -0700 Subject: flow_dissector: implements flow dissector BPF hook Adds a hook for programs of type BPF_PROG_TYPE_FLOW_DISSECTOR and attach type BPF_FLOW_DISSECTOR that is executed in the flow dissector path. The BPF program is per-network namespace. Signed-off-by: Petar Penkov Signed-off-by: Willem de Bruijn Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + include/linux/bpf_types.h | 1 + include/linux/skbuff.h | 7 +++ include/net/net_namespace.h | 3 + include/net/sch_generic.h | 12 +++- include/uapi/linux/bpf.h | 26 +++++++++ kernel/bpf/syscall.c | 8 +++ kernel/bpf/verifier.c | 32 +++++++++++ net/core/filter.c | 70 +++++++++++++++++++++++ net/core/flow_dissector.c | 134 ++++++++++++++++++++++++++++++++++++++++++++ 10 files changed, 291 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 523481a3471b..988a00797bcd 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -212,6 +212,7 @@ enum bpf_reg_type { PTR_TO_PACKET_META, /* skb->data - meta_len */ PTR_TO_PACKET, /* reg points to skb->data */ PTR_TO_PACKET_END, /* skb->data + headlen */ + PTR_TO_FLOW_KEYS, /* reg points to bpf_flow_keys */ }; /* The information passed from prog-specific *_is_valid_access diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index cd26c090e7c0..22083712dd18 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -32,6 +32,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2) #ifdef CONFIG_INET BPF_PROG_TYPE(BPF_PROG_TYPE_SK_REUSEPORT, sk_reuseport) #endif +BPF_PROG_TYPE(BPF_PROG_TYPE_FLOW_DISSECTOR, flow_dissector) BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, percpu_array_map_ops) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 17a13e4785fc..ce0e863f02a2 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -243,6 +243,8 @@ struct scatterlist; struct pipe_inode_info; struct iov_iter; struct napi_struct; +struct bpf_prog; +union bpf_attr; #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) struct nf_conntrack { @@ -1192,6 +1194,11 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector, const struct flow_dissector_key *key, unsigned int key_count); +int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr, + struct bpf_prog *prog); + +int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr); + bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 9b5fdc50519a..99d4148e0f90 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -43,6 +43,7 @@ struct ctl_table_header; struct net_generic; struct uevent_sock; struct netns_ipvs; +struct bpf_prog; #define NETDEV_HASHBITS 8 @@ -145,6 +146,8 @@ struct net { #endif struct net_generic __rcu *gen; + struct bpf_prog __rcu *flow_dissector_prog; + /* Note : following structs are cache line aligned */ #ifdef CONFIG_XFRM struct netns_xfrm xfrm; diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index a6d00093f35e..1b81ba85fd2d 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -19,6 +19,7 @@ struct Qdisc_ops; struct qdisc_walker; struct tcf_walker; struct module; +struct bpf_flow_keys; typedef int tc_setup_cb_t(enum tc_setup_type type, void *type_data, void *cb_priv); @@ -307,9 +308,14 @@ struct tcf_proto { }; struct qdisc_skb_cb { - unsigned int pkt_len; - u16 slave_dev_queue_mapping; - u16 tc_classid; + union { + struct { + unsigned int pkt_len; + u16 slave_dev_queue_mapping; + u16 tc_classid; + }; + struct bpf_flow_keys *flow_keys; + }; #define QDISC_CB_PRIV_LEN 20 unsigned char data[QDISC_CB_PRIV_LEN]; }; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 66917a4eba27..aa5ccd2385ed 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -152,6 +152,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_LWT_SEG6LOCAL, BPF_PROG_TYPE_LIRC_MODE2, BPF_PROG_TYPE_SK_REUSEPORT, + BPF_PROG_TYPE_FLOW_DISSECTOR, }; enum bpf_attach_type { @@ -172,6 +173,7 @@ enum bpf_attach_type { BPF_CGROUP_UDP4_SENDMSG, BPF_CGROUP_UDP6_SENDMSG, BPF_LIRC_MODE2, + BPF_FLOW_DISSECTOR, __MAX_BPF_ATTACH_TYPE }; @@ -2333,6 +2335,7 @@ struct __sk_buff { /* ... here. */ __u32 data_meta; + struct bpf_flow_keys *flow_keys; }; struct bpf_tunnel_key { @@ -2778,4 +2781,27 @@ enum bpf_task_fd_type { BPF_FD_TYPE_URETPROBE, /* filename + offset */ }; +struct bpf_flow_keys { + __u16 nhoff; + __u16 thoff; + __u16 addr_proto; /* ETH_P_* of valid addrs */ + __u8 is_frag; + __u8 is_first_frag; + __u8 is_encap; + __u8 ip_proto; + __be16 n_proto; + __be16 sport; + __be16 dport; + union { + struct { + __be32 ipv4_src; + __be32 ipv4_dst; + }; + struct { + __u32 ipv6_src[4]; /* in6_addr; network order */ + __u32 ipv6_dst[4]; /* in6_addr; network order */ + }; + }; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 3c9636f03bb2..b3c2d09bcf7a 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1615,6 +1615,9 @@ static int bpf_prog_attach(const union bpf_attr *attr) case BPF_LIRC_MODE2: ptype = BPF_PROG_TYPE_LIRC_MODE2; break; + case BPF_FLOW_DISSECTOR: + ptype = BPF_PROG_TYPE_FLOW_DISSECTOR; + break; default: return -EINVAL; } @@ -1636,6 +1639,9 @@ static int bpf_prog_attach(const union bpf_attr *attr) case BPF_PROG_TYPE_LIRC_MODE2: ret = lirc_prog_attach(attr, prog); break; + case BPF_PROG_TYPE_FLOW_DISSECTOR: + ret = skb_flow_dissector_bpf_prog_attach(attr, prog); + break; default: ret = cgroup_bpf_prog_attach(attr, ptype, prog); } @@ -1688,6 +1694,8 @@ static int bpf_prog_detach(const union bpf_attr *attr) return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, NULL); case BPF_LIRC_MODE2: return lirc_prog_detach(attr); + case BPF_FLOW_DISSECTOR: + return skb_flow_dissector_bpf_prog_detach(attr); default: return -EINVAL; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6ff1bac1795d..8ccbff4fff93 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -261,6 +261,7 @@ static const char * const reg_type_str[] = { [PTR_TO_PACKET] = "pkt", [PTR_TO_PACKET_META] = "pkt_meta", [PTR_TO_PACKET_END] = "pkt_end", + [PTR_TO_FLOW_KEYS] = "flow_keys", }; static char slot_type_char[] = { @@ -965,6 +966,7 @@ static bool is_spillable_regtype(enum bpf_reg_type type) case PTR_TO_PACKET: case PTR_TO_PACKET_META: case PTR_TO_PACKET_END: + case PTR_TO_FLOW_KEYS: case CONST_PTR_TO_MAP: return true; default: @@ -1238,6 +1240,7 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env, case BPF_PROG_TYPE_LWT_XMIT: case BPF_PROG_TYPE_SK_SKB: case BPF_PROG_TYPE_SK_MSG: + case BPF_PROG_TYPE_FLOW_DISSECTOR: if (meta) return meta->pkt_access; @@ -1321,6 +1324,18 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, return -EACCES; } +static int check_flow_keys_access(struct bpf_verifier_env *env, int off, + int size) +{ + if (size < 0 || off < 0 || + (u64)off + size > sizeof(struct bpf_flow_keys)) { + verbose(env, "invalid access to flow keys off=%d size=%d\n", + off, size); + return -EACCES; + } + return 0; +} + static bool __is_pointer_value(bool allow_ptr_leaks, const struct bpf_reg_state *reg) { @@ -1422,6 +1437,9 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, * right in front, treat it the very same way. */ return check_pkt_ptr_alignment(env, reg, off, size, strict); + case PTR_TO_FLOW_KEYS: + pointer_desc = "flow keys "; + break; case PTR_TO_MAP_VALUE: pointer_desc = "value "; break; @@ -1692,6 +1710,17 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn err = check_packet_access(env, regno, off, size, false); if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); + } else if (reg->type == PTR_TO_FLOW_KEYS) { + if (t == BPF_WRITE && value_regno >= 0 && + is_pointer_value(env, value_regno)) { + verbose(env, "R%d leaks addr into flow keys\n", + value_regno); + return -EACCES; + } + + err = check_flow_keys_access(env, off, size); + if (!err && t == BPF_READ && value_regno >= 0) + mark_reg_unknown(env, regs, value_regno); } else { verbose(env, "R%d invalid mem access '%s'\n", regno, reg_type_str[reg->type]); @@ -1839,6 +1868,8 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, case PTR_TO_PACKET_META: return check_packet_access(env, regno, reg->off, access_size, zero_size_allowed); + case PTR_TO_FLOW_KEYS: + return check_flow_keys_access(env, reg->off, access_size); case PTR_TO_MAP_VALUE: return check_map_access(env, regno, reg->off, access_size, zero_size_allowed); @@ -4366,6 +4397,7 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, case PTR_TO_CTX: case CONST_PTR_TO_MAP: case PTR_TO_PACKET_END: + case PTR_TO_FLOW_KEYS: /* Only valid matches are exact, which memcmp() above * would have accepted */ diff --git a/net/core/filter.c b/net/core/filter.c index bf5b6efd369a..9cc76f134ddb 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5123,6 +5123,17 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) } } +static const struct bpf_func_proto * +flow_dissector_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + switch (func_id) { + case BPF_FUNC_skb_load_bytes: + return &bpf_skb_load_bytes_proto; + default: + return bpf_base_func_proto(func_id); + } +} + static const struct bpf_func_proto * lwt_out_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -5241,6 +5252,10 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type if (size != size_default) return false; break; + case bpf_ctx_range(struct __sk_buff, flow_keys): + if (size != sizeof(struct bpf_flow_keys *)) + return false; + break; default: /* Only narrow read access allowed for now. */ if (type == BPF_WRITE) { @@ -5266,6 +5281,7 @@ static bool sk_filter_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, data): case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, data_end): + case bpf_ctx_range(struct __sk_buff, flow_keys): case bpf_ctx_range_till(struct __sk_buff, family, local_port): return false; } @@ -5291,6 +5307,7 @@ static bool lwt_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range_till(struct __sk_buff, family, local_port): case bpf_ctx_range(struct __sk_buff, data_meta): + case bpf_ctx_range(struct __sk_buff, flow_keys): return false; } @@ -5501,6 +5518,7 @@ static bool tc_cls_act_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, data_end): info->reg_type = PTR_TO_PACKET_END; break; + case bpf_ctx_range(struct __sk_buff, flow_keys): case bpf_ctx_range_till(struct __sk_buff, family, local_port): return false; } @@ -5702,6 +5720,7 @@ static bool sk_skb_is_valid_access(int off, int size, switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range(struct __sk_buff, data_meta): + case bpf_ctx_range(struct __sk_buff, flow_keys): return false; } @@ -5761,6 +5780,39 @@ static bool sk_msg_is_valid_access(int off, int size, return true; } +static bool flow_dissector_is_valid_access(int off, int size, + enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + if (type == BPF_WRITE) { + switch (off) { + case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): + break; + default: + return false; + } + } + + switch (off) { + case bpf_ctx_range(struct __sk_buff, data): + info->reg_type = PTR_TO_PACKET; + break; + case bpf_ctx_range(struct __sk_buff, data_end): + info->reg_type = PTR_TO_PACKET_END; + break; + case bpf_ctx_range(struct __sk_buff, flow_keys): + info->reg_type = PTR_TO_FLOW_KEYS; + break; + case bpf_ctx_range(struct __sk_buff, tc_classid): + case bpf_ctx_range(struct __sk_buff, data_meta): + case bpf_ctx_range_till(struct __sk_buff, family, local_port): + return false; + } + + return bpf_skb_is_valid_access(off, size, type, prog, info); +} + static u32 bpf_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, @@ -6055,6 +6107,15 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, bpf_target_off(struct sock_common, skc_num, 2, target_size)); break; + + case offsetof(struct __sk_buff, flow_keys): + off = si->off; + off -= offsetof(struct __sk_buff, flow_keys); + off += offsetof(struct sk_buff, cb); + off += offsetof(struct qdisc_skb_cb, flow_keys); + *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, + si->src_reg, off); + break; } return insn - insn_buf; @@ -7018,6 +7079,15 @@ const struct bpf_verifier_ops sk_msg_verifier_ops = { const struct bpf_prog_ops sk_msg_prog_ops = { }; +const struct bpf_verifier_ops flow_dissector_verifier_ops = { + .get_func_proto = flow_dissector_func_proto, + .is_valid_access = flow_dissector_is_valid_access, + .convert_ctx_access = bpf_convert_ctx_access, +}; + +const struct bpf_prog_ops flow_dissector_prog_ops = { +}; + int sk_detach_filter(struct sock *sk) { int ret = -ENOENT; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index ce9eeeb7c024..5c5dd74b5b3b 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -25,6 +25,9 @@ #include #include #include +#include + +static DEFINE_MUTEX(flow_dissector_mutex); static void dissector_set_key(struct flow_dissector *flow_dissector, enum flow_dissector_key_id key_id) @@ -62,6 +65,44 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector, } EXPORT_SYMBOL(skb_flow_dissector_init); +int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr, + struct bpf_prog *prog) +{ + struct bpf_prog *attached; + struct net *net; + + net = current->nsproxy->net_ns; + mutex_lock(&flow_dissector_mutex); + attached = rcu_dereference_protected(net->flow_dissector_prog, + lockdep_is_held(&flow_dissector_mutex)); + if (attached) { + /* Only one BPF program can be attached at a time */ + mutex_unlock(&flow_dissector_mutex); + return -EEXIST; + } + rcu_assign_pointer(net->flow_dissector_prog, prog); + mutex_unlock(&flow_dissector_mutex); + return 0; +} + +int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr) +{ + struct bpf_prog *attached; + struct net *net; + + net = current->nsproxy->net_ns; + mutex_lock(&flow_dissector_mutex); + attached = rcu_dereference_protected(net->flow_dissector_prog, + lockdep_is_held(&flow_dissector_mutex)); + if (!attached) { + mutex_unlock(&flow_dissector_mutex); + return -ENOENT; + } + bpf_prog_put(attached); + RCU_INIT_POINTER(net->flow_dissector_prog, NULL); + mutex_unlock(&flow_dissector_mutex); + return 0; +} /** * skb_flow_get_be16 - extract be16 entity * @skb: sk_buff to extract from @@ -588,6 +629,60 @@ static bool skb_flow_dissect_allowed(int *num_hdrs) return (*num_hdrs <= MAX_FLOW_DISSECT_HDRS); } +static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys, + struct flow_dissector *flow_dissector, + void *target_container) +{ + struct flow_dissector_key_control *key_control; + struct flow_dissector_key_basic *key_basic; + struct flow_dissector_key_addrs *key_addrs; + struct flow_dissector_key_ports *key_ports; + + key_control = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_CONTROL, + target_container); + key_control->thoff = flow_keys->thoff; + if (flow_keys->is_frag) + key_control->flags |= FLOW_DIS_IS_FRAGMENT; + if (flow_keys->is_first_frag) + key_control->flags |= FLOW_DIS_FIRST_FRAG; + if (flow_keys->is_encap) + key_control->flags |= FLOW_DIS_ENCAPSULATION; + + key_basic = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_BASIC, + target_container); + key_basic->n_proto = flow_keys->n_proto; + key_basic->ip_proto = flow_keys->ip_proto; + + if (flow_keys->addr_proto == ETH_P_IP && + dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) { + key_addrs = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_IPV4_ADDRS, + target_container); + key_addrs->v4addrs.src = flow_keys->ipv4_src; + key_addrs->v4addrs.dst = flow_keys->ipv4_dst; + key_control->addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; + } else if (flow_keys->addr_proto == ETH_P_IPV6 && + dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { + key_addrs = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_IPV6_ADDRS, + target_container); + memcpy(&key_addrs->v6addrs, &flow_keys->ipv6_src, + sizeof(key_addrs->v6addrs)); + key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; + } + + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) { + key_ports = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_PORTS, + target_container); + key_ports->src = flow_keys->sport; + key_ports->dst = flow_keys->dport; + } +} + /** * __skb_flow_dissect - extract the flow_keys struct and return it * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified @@ -619,6 +714,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector_key_vlan *key_vlan; enum flow_dissect_ret fdret; enum flow_dissector_key_id dissector_vlan = FLOW_DISSECTOR_KEY_MAX; + struct bpf_prog *attached; int num_hdrs = 0; u8 ip_proto = 0; bool ret; @@ -658,6 +754,44 @@ bool __skb_flow_dissect(const struct sk_buff *skb, FLOW_DISSECTOR_KEY_BASIC, target_container); + rcu_read_lock(); + attached = skb ? rcu_dereference(dev_net(skb->dev)->flow_dissector_prog) + : NULL; + if (attached) { + /* Note that even though the const qualifier is discarded + * throughout the execution of the BPF program, all changes(the + * control block) are reverted after the BPF program returns. + * Therefore, __skb_flow_dissect does not alter the skb. + */ + struct bpf_flow_keys flow_keys = {}; + struct bpf_skb_data_end cb_saved; + struct bpf_skb_data_end *cb; + u32 result; + + cb = (struct bpf_skb_data_end *)skb->cb; + + /* Save Control Block */ + memcpy(&cb_saved, cb, sizeof(cb_saved)); + memset(cb, 0, sizeof(cb_saved)); + + /* Pass parameters to the BPF program */ + cb->qdisc_cb.flow_keys = &flow_keys; + flow_keys.nhoff = nhoff; + + bpf_compute_data_pointers((struct sk_buff *)skb); + result = BPF_PROG_RUN(attached, skb); + + /* Restore state */ + memcpy(cb, &cb_saved, sizeof(cb_saved)); + + __skb_flow_bpf_to_target(&flow_keys, flow_dissector, + target_container); + key_control->thoff = min_t(u16, key_control->thoff, skb->len); + rcu_read_unlock(); + return result == BPF_OK; + } + rcu_read_unlock(); + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { struct ethhdr *eth = eth_hdr(skb); -- cgit v1.2.3 From 36f47383c7f9fa0fdc20a92635435ff77ff71a6f Mon Sep 17 00:00:00 2001 From: Fabien Parent Date: Fri, 10 Aug 2018 15:13:47 +0200 Subject: mfd: cros: add charger port count command definition A new more command has been added to the ChromeOS embedded controller that allows to get the number of charger port count. Unlike EC_CMD_USB_PD_PORTS, this new command also includes the dedicated port if present. This command will be used to expose the dedicated charger port in the ChromeOS charger driver. Signed-off-by: Fabien Parent Acked-for-MFD-by: Lee Jones Reviewed-by: Enric Balletbo i Serra Signed-off-by: Sebastian Reichel --- include/linux/mfd/cros_ec_commands.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/cros_ec_commands.h b/include/linux/mfd/cros_ec_commands.h index 6e1ab9bead28..20ee71f10865 100644 --- a/include/linux/mfd/cros_ec_commands.h +++ b/include/linux/mfd/cros_ec_commands.h @@ -3102,6 +3102,16 @@ struct ec_params_usb_pd_info_request { uint8_t port; } __packed; +/* + * This command will return the number of USB PD charge port + the number + * of dedicated port present. + * EC_CMD_USB_PD_PORTS does NOT include the dedicated ports + */ +#define EC_CMD_CHARGE_PORT_COUNT 0x0105 +struct ec_response_charge_port_count { + uint8_t port_count; +} __packed; + /* Read USB-PD Device discovery info */ #define EC_CMD_USB_PD_DISCOVERY 0x0113 struct ec_params_usb_pd_discovery_entry { -- cgit v1.2.3 From 8f5be0ec23bb9ef3f96659c8dff1340b876600bf Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Mon, 13 Aug 2018 09:52:09 +0300 Subject: kernfs: update comment about kernfs_path() return value Now it returns the length of the full path or error code. Signed-off-by: Konstantin Khlebnikov Fixes: 3abb1d90f5d9 ("kernfs: make kernfs_path*() behave in the style of strlcpy()") Acked-by: Tejun Heo Signed-off-by: Greg Kroah-Hartman --- include/linux/kernfs.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 814643f7ee52..5b36b1287a5a 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -477,10 +477,11 @@ static inline void kernfs_init(void) { } * @buf: buffer to copy @kn's name into * @buflen: size of @buf * - * Builds and returns the full path of @kn in @buf of @buflen bytes. The - * path is built from the end of @buf so the returned pointer usually - * doesn't match @buf. If @buf isn't long enough, @buf is nul terminated - * and %NULL is returned. + * If @kn is NULL result will be "(null)". + * + * Returns the length of the full path. If the full length is equal to or + * greater than @buflen, @buf contains the truncated path with the trailing + * '\0'. On error, -errno is returned. */ static inline int kernfs_path(struct kernfs_node *kn, char *buf, size_t buflen) { -- cgit v1.2.3 From 2953d80ff04862b26a2e628fb3948868f54d753d Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 31 Aug 2018 20:29:37 +0200 Subject: netfilter: remove obsolete need_conntrack stub as of a0ae2562c6c4b27 ("netfilter: conntrack: remove l3proto abstraction") there are no users anymore. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_conntrack_common.h | 3 --- net/netfilter/nf_conntrack_standalone.c | 7 ------- 2 files changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_common.h b/include/linux/netfilter/nf_conntrack_common.h index 03097fa70975..e142b2b5f1ea 100644 --- a/include/linux/netfilter/nf_conntrack_common.h +++ b/include/linux/netfilter/nf_conntrack_common.h @@ -19,7 +19,4 @@ struct ip_conntrack_stat { unsigned int search_restart; }; -/* call to create an explicit dependency on nf_conntrack. */ -void need_conntrack(void); - #endif /* _NF_CONNTRACK_COMMON_H */ diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 13279f683da9..e3b329ebafd3 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -720,10 +720,3 @@ static void __exit nf_conntrack_standalone_fini(void) module_init(nf_conntrack_standalone_init); module_exit(nf_conntrack_standalone_fini); - -/* Some modules need us, but don't depend directly on any symbol. - They should call this. */ -void need_conntrack(void) -{ -} -EXPORT_SYMBOL_GPL(need_conntrack); -- cgit v1.2.3 From 1ccce46c5e8b8a0d2606fb8bb72bff069ffdc3ab Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 14 Aug 2018 17:14:30 -0700 Subject: PCI: Remove unused NFP32xx IDs Defines for NFP32xx are no longer used anywhere, remove them. Signed-off-by: Jakub Kicinski Signed-off-by: Bjorn Helgaas --- include/linux/pci_ids.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index d157983b84cf..f4e278493f5b 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2539,8 +2539,6 @@ #define PCI_VENDOR_ID_HUAWEI 0x19e5 #define PCI_VENDOR_ID_NETRONOME 0x19ee -#define PCI_DEVICE_ID_NETRONOME_NFP3200 0x3200 -#define PCI_DEVICE_ID_NETRONOME_NFP3240 0x3240 #define PCI_DEVICE_ID_NETRONOME_NFP4000 0x4000 #define PCI_DEVICE_ID_NETRONOME_NFP5000 0x5000 #define PCI_DEVICE_ID_NETRONOME_NFP6000 0x6000 -- cgit v1.2.3 From 81c4b5bf30de01a0f6b43ccaa1d220f4a0a5d99c Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sat, 8 Sep 2018 09:59:01 +0200 Subject: PCI: hotplug: Constify hotplug_slot_ops Hotplug drivers cannot declare their hotplug_slot_ops const, making them attractive targets for attackers, because upon registration of a hotplug slot, __pci_hp_initialize() writes to the "owner" and "mod_name" members in that struct. Fix by moving these members to struct hotplug_slot and constify every driver's hotplug_slot_ops except for pciehp. pciehp constructs its hotplug_slot_ops at runtime based on the PCIe port's capabilities, hence cannot declare them const. It can be converted to __write_rarely once that's mainlined: http://www.openwall.com/lists/kernel-hardening/2016/11/16/3 Signed-off-by: Lukas Wunner Signed-off-by: Bjorn Helgaas Reviewed-by: Rafael J. Wysocki Acked-by: Tyrel Datwyler # drivers/pci/hotplug/rpa* Acked-by: Andy Shevchenko # drivers/platform/x86 Cc: Len Brown Cc: Scott Murray Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: Oliver OHalloran Cc: Gavin Shan Cc: Sebastian Ott Cc: Gerald Schaefer Cc: Corentin Chary Cc: Darren Hart --- drivers/pci/hotplug/acpiphp_core.c | 2 +- drivers/pci/hotplug/cpci_hotplug_core.c | 2 +- drivers/pci/hotplug/cpqphp_core.c | 2 +- drivers/pci/hotplug/ibmphp.h | 2 +- drivers/pci/hotplug/ibmphp_core.c | 2 +- drivers/pci/hotplug/pci_hotplug_core.c | 27 ++++++++++++++------------- drivers/pci/hotplug/pnv_php.c | 2 +- drivers/pci/hotplug/rpaphp.h | 2 +- drivers/pci/hotplug/rpaphp_core.c | 2 +- drivers/pci/hotplug/s390_pci_hpc.c | 2 +- drivers/pci/hotplug/sgi_hotplug.c | 2 +- drivers/pci/hotplug/shpchp_core.c | 2 +- drivers/pci/pci.c | 4 ++-- drivers/pci/slot.c | 2 +- drivers/platform/x86/asus-wmi.c | 3 +-- drivers/platform/x86/eeepc-laptop.c | 3 +-- include/linux/pci_hotplug.h | 10 +++++----- 17 files changed, 35 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/hotplug/acpiphp_core.c b/drivers/pci/hotplug/acpiphp_core.c index ad32ffbc4b91..e883cef0f3bc 100644 --- a/drivers/pci/hotplug/acpiphp_core.c +++ b/drivers/pci/hotplug/acpiphp_core.c @@ -57,7 +57,7 @@ static int get_attention_status(struct hotplug_slot *slot, u8 *value); static int get_latch_status(struct hotplug_slot *slot, u8 *value); static int get_adapter_status(struct hotplug_slot *slot, u8 *value); -static struct hotplug_slot_ops acpi_hotplug_slot_ops = { +static const struct hotplug_slot_ops acpi_hotplug_slot_ops = { .enable_slot = enable_slot, .disable_slot = disable_slot, .set_attention_status = set_attention_status, diff --git a/drivers/pci/hotplug/cpci_hotplug_core.c b/drivers/pci/hotplug/cpci_hotplug_core.c index 52a339baf06c..97c32e4c74c8 100644 --- a/drivers/pci/hotplug/cpci_hotplug_core.c +++ b/drivers/pci/hotplug/cpci_hotplug_core.c @@ -57,7 +57,7 @@ static int get_attention_status(struct hotplug_slot *slot, u8 *value); static int get_adapter_status(struct hotplug_slot *slot, u8 *value); static int get_latch_status(struct hotplug_slot *slot, u8 *value); -static struct hotplug_slot_ops cpci_hotplug_slot_ops = { +static const struct hotplug_slot_ops cpci_hotplug_slot_ops = { .enable_slot = enable_slot, .disable_slot = disable_slot, .set_attention_status = set_attention_status, diff --git a/drivers/pci/hotplug/cpqphp_core.c b/drivers/pci/hotplug/cpqphp_core.c index 5a06636e910a..3409b62fceac 100644 --- a/drivers/pci/hotplug/cpqphp_core.c +++ b/drivers/pci/hotplug/cpqphp_core.c @@ -560,7 +560,7 @@ static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value) return 0; } -static struct hotplug_slot_ops cpqphp_hotplug_slot_ops = { +static const struct hotplug_slot_ops cpqphp_hotplug_slot_ops = { .set_attention_status = set_attention_status, .enable_slot = process_SI, .disable_slot = process_SS, diff --git a/drivers/pci/hotplug/ibmphp.h b/drivers/pci/hotplug/ibmphp.h index fddb78606c74..db387e10581e 100644 --- a/drivers/pci/hotplug/ibmphp.h +++ b/drivers/pci/hotplug/ibmphp.h @@ -740,7 +740,7 @@ int ibmphp_do_disable_slot(struct slot *slot_cur); int ibmphp_update_slot_info(struct slot *); /* This function is called from HPC, so we need it to not be be static */ int ibmphp_configure_card(struct pci_func *, u8); int ibmphp_unconfigure_card(struct slot **, int); -extern struct hotplug_slot_ops ibmphp_hotplug_slot_ops; +extern const struct hotplug_slot_ops ibmphp_hotplug_slot_ops; #endif //__IBMPHP_H diff --git a/drivers/pci/hotplug/ibmphp_core.c b/drivers/pci/hotplug/ibmphp_core.c index 4ea57e9019f1..b82fdc17040d 100644 --- a/drivers/pci/hotplug/ibmphp_core.c +++ b/drivers/pci/hotplug/ibmphp_core.c @@ -1259,7 +1259,7 @@ error: goto exit; } -struct hotplug_slot_ops ibmphp_hotplug_slot_ops = { +const struct hotplug_slot_ops ibmphp_hotplug_slot_ops = { .set_attention_status = set_attention_status, .enable_slot = enable_slot, .disable_slot = ibmphp_disable_slot, diff --git a/drivers/pci/hotplug/pci_hotplug_core.c b/drivers/pci/hotplug/pci_hotplug_core.c index 90fde5f106d8..ede2ed6f4ce0 100644 --- a/drivers/pci/hotplug/pci_hotplug_core.c +++ b/drivers/pci/hotplug/pci_hotplug_core.c @@ -49,15 +49,15 @@ static DEFINE_MUTEX(pci_hp_mutex); #define GET_STATUS(name, type) \ static int get_##name(struct hotplug_slot *slot, type *value) \ { \ - struct hotplug_slot_ops *ops = slot->ops; \ + const struct hotplug_slot_ops *ops = slot->ops; \ int retval = 0; \ - if (!try_module_get(ops->owner)) \ + if (!try_module_get(slot->owner)) \ return -ENODEV; \ if (ops->get_##name) \ retval = ops->get_##name(slot, value); \ else \ *value = slot->info->name; \ - module_put(ops->owner); \ + module_put(slot->owner); \ return retval; \ } @@ -90,7 +90,7 @@ static ssize_t power_write_file(struct pci_slot *pci_slot, const char *buf, power = (u8)(lpower & 0xff); dbg("power = %d\n", power); - if (!try_module_get(slot->ops->owner)) { + if (!try_module_get(slot->owner)) { retval = -ENODEV; goto exit; } @@ -109,7 +109,7 @@ static ssize_t power_write_file(struct pci_slot *pci_slot, const char *buf, err("Illegal value specified for power\n"); retval = -EINVAL; } - module_put(slot->ops->owner); + module_put(slot->owner); exit: if (retval) @@ -138,7 +138,8 @@ static ssize_t attention_read_file(struct pci_slot *pci_slot, char *buf) static ssize_t attention_write_file(struct pci_slot *pci_slot, const char *buf, size_t count) { - struct hotplug_slot_ops *ops = pci_slot->hotplug->ops; + struct hotplug_slot *slot = pci_slot->hotplug; + const struct hotplug_slot_ops *ops = slot->ops; unsigned long lattention; u8 attention; int retval = 0; @@ -147,13 +148,13 @@ static ssize_t attention_write_file(struct pci_slot *pci_slot, const char *buf, attention = (u8)(lattention & 0xff); dbg(" - attention = %d\n", attention); - if (!try_module_get(ops->owner)) { + if (!try_module_get(slot->owner)) { retval = -ENODEV; goto exit; } if (ops->set_attention_status) - retval = ops->set_attention_status(pci_slot->hotplug, attention); - module_put(ops->owner); + retval = ops->set_attention_status(slot, attention); + module_put(slot->owner); exit: if (retval) @@ -213,13 +214,13 @@ static ssize_t test_write_file(struct pci_slot *pci_slot, const char *buf, test = (u32)(ltest & 0xffffffff); dbg("test = %d\n", test); - if (!try_module_get(slot->ops->owner)) { + if (!try_module_get(slot->owner)) { retval = -ENODEV; goto exit; } if (slot->ops->hardware_test) retval = slot->ops->hardware_test(slot, test); - module_put(slot->ops->owner); + module_put(slot->owner); exit: if (retval) @@ -447,8 +448,8 @@ int __pci_hp_initialize(struct hotplug_slot *slot, struct pci_bus *bus, if ((slot->info == NULL) || (slot->ops == NULL)) return -EINVAL; - slot->ops->owner = owner; - slot->ops->mod_name = mod_name; + slot->owner = owner; + slot->mod_name = mod_name; /* * No problems if we call this interface from both ACPI_PCI_SLOT diff --git a/drivers/pci/hotplug/pnv_php.c b/drivers/pci/hotplug/pnv_php.c index 3276a5e4c430..12b92a0ff688 100644 --- a/drivers/pci/hotplug/pnv_php.c +++ b/drivers/pci/hotplug/pnv_php.c @@ -530,7 +530,7 @@ static int pnv_php_disable_slot(struct hotplug_slot *slot) return ret; } -static struct hotplug_slot_ops php_slot_ops = { +static const struct hotplug_slot_ops php_slot_ops = { .get_power_status = pnv_php_get_power_state, .get_adapter_status = pnv_php_get_adapter_state, .set_attention_status = pnv_php_set_attention_state, diff --git a/drivers/pci/hotplug/rpaphp.h b/drivers/pci/hotplug/rpaphp.h index c8311724bd76..f83347819f7b 100644 --- a/drivers/pci/hotplug/rpaphp.h +++ b/drivers/pci/hotplug/rpaphp.h @@ -70,7 +70,7 @@ struct slot { struct hotplug_slot *hotplug_slot; }; -extern struct hotplug_slot_ops rpaphp_hotplug_slot_ops; +extern const struct hotplug_slot_ops rpaphp_hotplug_slot_ops; extern struct list_head rpaphp_slot_head; /* function prototypes */ diff --git a/drivers/pci/hotplug/rpaphp_core.c b/drivers/pci/hotplug/rpaphp_core.c index 857c358b727b..8620a3f8c987 100644 --- a/drivers/pci/hotplug/rpaphp_core.c +++ b/drivers/pci/hotplug/rpaphp_core.c @@ -477,7 +477,7 @@ static int disable_slot(struct hotplug_slot *hotplug_slot) return 0; } -struct hotplug_slot_ops rpaphp_hotplug_slot_ops = { +const struct hotplug_slot_ops rpaphp_hotplug_slot_ops = { .enable_slot = enable_slot, .disable_slot = disable_slot, .set_attention_status = set_attention_status, diff --git a/drivers/pci/hotplug/s390_pci_hpc.c b/drivers/pci/hotplug/s390_pci_hpc.c index 93b5341d282c..5bd45fd4a92a 100644 --- a/drivers/pci/hotplug/s390_pci_hpc.c +++ b/drivers/pci/hotplug/s390_pci_hpc.c @@ -130,7 +130,7 @@ static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value) return 0; } -static struct hotplug_slot_ops s390_hotplug_slot_ops = { +static const struct hotplug_slot_ops s390_hotplug_slot_ops = { .enable_slot = enable_slot, .disable_slot = disable_slot, .get_power_status = get_power_status, diff --git a/drivers/pci/hotplug/sgi_hotplug.c b/drivers/pci/hotplug/sgi_hotplug.c index babd23409f61..af4c28c574dd 100644 --- a/drivers/pci/hotplug/sgi_hotplug.c +++ b/drivers/pci/hotplug/sgi_hotplug.c @@ -80,7 +80,7 @@ static int enable_slot(struct hotplug_slot *slot); static int disable_slot(struct hotplug_slot *slot); static inline int get_power_status(struct hotplug_slot *slot, u8 *value); -static struct hotplug_slot_ops sn_hotplug_slot_ops = { +static const struct hotplug_slot_ops sn_hotplug_slot_ops = { .enable_slot = enable_slot, .disable_slot = disable_slot, .get_power_status = get_power_status, diff --git a/drivers/pci/hotplug/shpchp_core.c b/drivers/pci/hotplug/shpchp_core.c index 97cee23f3d51..26cbea04237c 100644 --- a/drivers/pci/hotplug/shpchp_core.c +++ b/drivers/pci/hotplug/shpchp_core.c @@ -51,7 +51,7 @@ static int get_attention_status(struct hotplug_slot *slot, u8 *value); static int get_latch_status(struct hotplug_slot *slot, u8 *value); static int get_adapter_status(struct hotplug_slot *slot, u8 *value); -static struct hotplug_slot_ops shpchp_hotplug_slot_ops = { +static const struct hotplug_slot_ops shpchp_hotplug_slot_ops = { .set_attention_status = set_attention_status, .enable_slot = enable_slot, .disable_slot = disable_slot, diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 1835f3a7aa8d..0e54588825cb 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -4571,13 +4571,13 @@ static int pci_reset_hotplug_slot(struct hotplug_slot *hotplug, int probe) { int rc = -ENOTTY; - if (!hotplug || !try_module_get(hotplug->ops->owner)) + if (!hotplug || !try_module_get(hotplug->owner)) return rc; if (hotplug->ops->reset_slot) rc = hotplug->ops->reset_slot(hotplug, probe); - module_put(hotplug->ops->owner); + module_put(hotplug->owner); return rc; } diff --git a/drivers/pci/slot.c b/drivers/pci/slot.c index e634229ece89..145cd953b518 100644 --- a/drivers/pci/slot.c +++ b/drivers/pci/slot.c @@ -371,7 +371,7 @@ void pci_hp_create_module_link(struct pci_slot *pci_slot) if (!slot || !slot->ops) return; - kobj = kset_find_obj(module_kset, slot->ops->mod_name); + kobj = kset_find_obj(module_kset, slot->mod_name); if (!kobj) return; ret = sysfs_create_link(&pci_slot->kobj, kobj, "module"); diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index 2d6e272315a8..a8aa2eadfd82 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -868,8 +868,7 @@ static int asus_get_adapter_status(struct hotplug_slot *hotplug_slot, return 0; } -static struct hotplug_slot_ops asus_hotplug_slot_ops = { - .owner = THIS_MODULE, +static const struct hotplug_slot_ops asus_hotplug_slot_ops = { .get_adapter_status = asus_get_adapter_status, .get_power_status = asus_get_adapter_status, }; diff --git a/drivers/platform/x86/eeepc-laptop.c b/drivers/platform/x86/eeepc-laptop.c index a4bbf6ecd1f0..41a364376e91 100644 --- a/drivers/platform/x86/eeepc-laptop.c +++ b/drivers/platform/x86/eeepc-laptop.c @@ -726,8 +726,7 @@ static int eeepc_get_adapter_status(struct hotplug_slot *hotplug_slot, return 0; } -static struct hotplug_slot_ops eeepc_hotplug_slot_ops = { - .owner = THIS_MODULE, +static const struct hotplug_slot_ops eeepc_hotplug_slot_ops = { .get_adapter_status = eeepc_get_adapter_status, .get_power_status = eeepc_get_adapter_status, }; diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index a6d6650a0490..372dbe95c207 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -16,8 +16,6 @@ /** * struct hotplug_slot_ops -the callbacks that the hotplug pci core can use - * @owner: The module owner of this structure - * @mod_name: The module name (KBUILD_MODNAME) of this structure * @enable_slot: Called when the user wants to enable a specific pci slot * @disable_slot: Called when the user wants to disable a specific pci slot * @set_attention_status: Called to set the specific slot's attention LED to @@ -46,8 +44,6 @@ * set an LED, enable / disable power, etc.) */ struct hotplug_slot_ops { - struct module *owner; - const char *mod_name; int (*enable_slot) (struct hotplug_slot *slot); int (*disable_slot) (struct hotplug_slot *slot); int (*set_attention_status) (struct hotplug_slot *slot, u8 value); @@ -82,15 +78,19 @@ struct hotplug_slot_info { * this slot. * @private: used by the hotplug pci controller driver to store whatever it * needs. + * @owner: The module owner of this structure + * @mod_name: The module name (KBUILD_MODNAME) of this structure */ struct hotplug_slot { - struct hotplug_slot_ops *ops; + const struct hotplug_slot_ops *ops; struct hotplug_slot_info *info; void *private; /* Variables below this are for use only by the hotplug pci core. */ struct list_head slot_list; struct pci_slot *pci_slot; + struct module *owner; + const char *mod_name; }; static inline const char *hotplug_slot_name(const struct hotplug_slot *slot) -- cgit v1.2.3 From a7da21613c4efcd4cc0235e6a30bec96ae47c619 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sat, 8 Sep 2018 09:59:01 +0200 Subject: PCI: hotplug: Drop hotplug_slot_info Ever since the PCI hotplug core was introduced in 2002, drivers had to allocate and register a struct hotplug_slot_info for every slot: https://git.kernel.org/tglx/history/c/a8a2069f432c Apparently the idea was that drivers furnish the hotplug core with an up-to-date card presence status, power status, latch status and attention indicator status as well as notify the hotplug core of changes thereof. However only 4 out of 12 hotplug drivers bother to notify the hotplug core with pci_hp_change_slot_info() and the hotplug core never made any use of the information: There is just a single macro in pci_hotplug_core.c, GET_STATUS(), which uses the hotplug_slot_info if the driver lacks the corresponding callback in hotplug_slot_ops. The macro is called when the user reads the attribute via sysfs. Now, if the callback isn't defined, the attribute isn't exposed in sysfs in the first place (see e.g. has_power_file()). There are only two situations when the hotplug_slot_info would actually be accessed: * If the driver defines ->enable_slot or ->disable_slot but not ->get_power_status. * If the driver defines ->set_attention_status but not ->get_attention_status. There is no driver doing the former and just a single driver doing the latter, namely pnv_php.c. Amend it with a ->get_attention_status callback. With that, the hotplug_slot_info becomes completely unused by the PCI hotplug core. But a few drivers use it internally as a cache: cpcihp uses it to cache the latch_status and adapter_status. cpqhp uses it to cache the adapter_status. pnv_php and rpaphp use it to cache the attention_status. shpchp uses it to cache all four values. Amend these drivers to cache the information in their private slot struct. shpchp's slot struct already contains members to cache the power_status and adapter_status, so additional members are only needed for the other two values. In the case of cpqphp, the cached value is only accessed in a single place, so instead of caching it, read the current value from the hardware. Caution: acpiphp, cpci, cpqhp, shpchp, asus-wmi and eeepc-laptop populate the hotplug_slot_info with initial values on probe. That code is herewith removed. There is a theoretical chance that the code has side effects without which the driver fails to function, e.g. if the ACPI method to read the adapter status needs to be executed at least once on probe. That seems unlikely to me, still maintainers should review the changes carefully for this possibility. Rafael adds: "I'm not aware of any case in which it will break anything, [...] but if that happens, it may be necessary to add the execution of the control methods in question directly to the initialization part." Signed-off-by: Lukas Wunner Signed-off-by: Bjorn Helgaas Reviewed-by: Rafael J. Wysocki Acked-by: Tyrel Datwyler # drivers/pci/hotplug/rpa* Acked-by: Sebastian Ott # drivers/pci/hotplug/s390* Acked-by: Andy Shevchenko # drivers/platform/x86 Cc: Len Brown Cc: Scott Murray Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: Oliver OHalloran Cc: Gavin Shan Cc: Gerald Schaefer Cc: Corentin Chary Cc: Darren Hart --- arch/powerpc/include/asm/pnv-pci.h | 2 +- drivers/pci/hotplug/acpiphp.h | 1 - drivers/pci/hotplug/acpiphp_core.c | 6 --- drivers/pci/hotplug/cpci_hotplug.h | 2 + drivers/pci/hotplug/cpci_hotplug_core.c | 72 +++++++-------------------------- drivers/pci/hotplug/cpqphp_core.c | 22 +--------- drivers/pci/hotplug/cpqphp_ctrl.c | 31 +------------- drivers/pci/hotplug/ibmphp_core.c | 27 +------------ drivers/pci/hotplug/ibmphp_ebda.c | 33 --------------- drivers/pci/hotplug/pci_hotplug_core.c | 26 +----------- drivers/pci/hotplug/pciehp_core.c | 8 ---- drivers/pci/hotplug/pnv_php.c | 24 ++++++++--- drivers/pci/hotplug/rpaphp.h | 1 + drivers/pci/hotplug/rpaphp_core.c | 4 +- drivers/pci/hotplug/rpaphp_pci.c | 11 +---- drivers/pci/hotplug/rpaphp_slot.c | 9 +---- drivers/pci/hotplug/s390_pci_hpc.c | 12 ------ drivers/pci/hotplug/sgi_hotplug.c | 9 ----- drivers/pci/hotplug/shpchp.h | 2 + drivers/pci/hotplug/shpchp_core.c | 31 +++++--------- drivers/pci/hotplug/shpchp_ctrl.c | 21 +++------- drivers/platform/x86/asus-wmi.c | 10 ----- drivers/platform/x86/eeepc-laptop.c | 10 ----- include/linux/pci_hotplug.h | 30 -------------- 24 files changed, 64 insertions(+), 340 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/include/asm/pnv-pci.h b/arch/powerpc/include/asm/pnv-pci.h index 7f627e3f4da4..630eb8b1b7ed 100644 --- a/arch/powerpc/include/asm/pnv-pci.h +++ b/arch/powerpc/include/asm/pnv-pci.h @@ -54,7 +54,6 @@ void pnv_cxl_release_hwirq_ranges(struct cxl_irq_ranges *irqs, struct pnv_php_slot { struct hotplug_slot slot; - struct hotplug_slot_info slot_info; uint64_t id; char *name; int slot_no; @@ -72,6 +71,7 @@ struct pnv_php_slot { struct pci_dev *pdev; struct pci_bus *bus; bool power_state_check; + u8 attention_state; void *fdt; void *dt; struct of_changeset ocs; diff --git a/drivers/pci/hotplug/acpiphp.h b/drivers/pci/hotplug/acpiphp.h index e438a2d734f2..8377e736ea69 100644 --- a/drivers/pci/hotplug/acpiphp.h +++ b/drivers/pci/hotplug/acpiphp.h @@ -35,7 +35,6 @@ struct acpiphp_slot; struct slot { struct hotplug_slot *hotplug_slot; struct acpiphp_slot *acpi_slot; - struct hotplug_slot_info info; unsigned int sun; /* ACPI _SUN (Slot User Number) value */ }; diff --git a/drivers/pci/hotplug/acpiphp_core.c b/drivers/pci/hotplug/acpiphp_core.c index e883cef0f3bc..abd4f8d7e16a 100644 --- a/drivers/pci/hotplug/acpiphp_core.c +++ b/drivers/pci/hotplug/acpiphp_core.c @@ -270,16 +270,10 @@ int acpiphp_register_hotplug_slot(struct acpiphp_slot *acpiphp_slot, if (!slot->hotplug_slot) goto error_slot; - slot->hotplug_slot->info = &slot->info; - slot->hotplug_slot->private = slot; slot->hotplug_slot->ops = &acpi_hotplug_slot_ops; slot->acpi_slot = acpiphp_slot; - slot->hotplug_slot->info->power_status = acpiphp_get_power_status(slot->acpi_slot); - slot->hotplug_slot->info->attention_status = 0; - slot->hotplug_slot->info->latch_status = acpiphp_get_latch_status(slot->acpi_slot); - slot->hotplug_slot->info->adapter_status = acpiphp_get_adapter_status(slot->acpi_slot); acpiphp_slot->slot = slot; slot->sun = sun; diff --git a/drivers/pci/hotplug/cpci_hotplug.h b/drivers/pci/hotplug/cpci_hotplug.h index 4658557be01a..a35f40a2290c 100644 --- a/drivers/pci/hotplug/cpci_hotplug.h +++ b/drivers/pci/hotplug/cpci_hotplug.h @@ -32,6 +32,8 @@ struct slot { unsigned int devfn; struct pci_bus *bus; struct pci_dev *dev; + unsigned int latch_status:1; + unsigned int adapter_status:1; unsigned int extracting; struct hotplug_slot *hotplug_slot; struct list_head slot_list; diff --git a/drivers/pci/hotplug/cpci_hotplug_core.c b/drivers/pci/hotplug/cpci_hotplug_core.c index 97c32e4c74c8..a17fb24c28cd 100644 --- a/drivers/pci/hotplug/cpci_hotplug_core.c +++ b/drivers/pci/hotplug/cpci_hotplug_core.c @@ -67,26 +67,6 @@ static const struct hotplug_slot_ops cpci_hotplug_slot_ops = { .get_latch_status = get_latch_status, }; -static int -update_latch_status(struct hotplug_slot *hotplug_slot, u8 value) -{ - struct hotplug_slot_info info; - - memcpy(&info, hotplug_slot->info, sizeof(struct hotplug_slot_info)); - info.latch_status = value; - return pci_hp_change_slot_info(hotplug_slot, &info); -} - -static int -update_adapter_status(struct hotplug_slot *hotplug_slot, u8 value) -{ - struct hotplug_slot_info info; - - memcpy(&info, hotplug_slot->info, sizeof(struct hotplug_slot_info)); - info.adapter_status = value; - return pci_hp_change_slot_info(hotplug_slot, &info); -} - static int enable_slot(struct hotplug_slot *hotplug_slot) { @@ -135,8 +115,7 @@ disable_slot(struct hotplug_slot *hotplug_slot) goto disable_error; } - if (update_adapter_status(slot->hotplug_slot, 0)) - warn("failure to update adapter file"); + slot->adapter_status = 0; if (slot->extracting) { slot->extracting = 0; @@ -184,20 +163,23 @@ set_attention_status(struct hotplug_slot *hotplug_slot, u8 status) static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value) { - *value = hotplug_slot->info->adapter_status; + struct slot *slot = hotplug_slot->private; + + *value = slot->adapter_status; return 0; } static int get_latch_status(struct hotplug_slot *hotplug_slot, u8 *value) { - *value = hotplug_slot->info->latch_status; + struct slot *slot = hotplug_slot->private; + + *value = slot->latch_status; return 0; } static void release_slot(struct slot *slot) { - kfree(slot->hotplug_slot->info); kfree(slot->hotplug_slot); pci_dev_put(slot->dev); kfree(slot); @@ -210,7 +192,6 @@ cpci_hp_register_bus(struct pci_bus *bus, u8 first, u8 last) { struct slot *slot; struct hotplug_slot *hotplug_slot; - struct hotplug_slot_info *info; char name[SLOT_NAME_SIZE]; int status; int i; @@ -237,13 +218,6 @@ cpci_hp_register_bus(struct pci_bus *bus, u8 first, u8 last) } slot->hotplug_slot = hotplug_slot; - info = kzalloc(sizeof(struct hotplug_slot_info), GFP_KERNEL); - if (!info) { - status = -ENOMEM; - goto error_hpslot; - } - hotplug_slot->info = info; - slot->bus = bus; slot->number = i; slot->devfn = PCI_DEVFN(i, 0); @@ -253,19 +227,11 @@ cpci_hp_register_bus(struct pci_bus *bus, u8 first, u8 last) hotplug_slot->private = slot; hotplug_slot->ops = &cpci_hotplug_slot_ops; - /* - * Initialize the slot info structure with some known - * good values. - */ - dbg("initializing slot %s", name); - info->power_status = cpci_get_power_status(slot); - info->attention_status = cpci_get_attention_status(slot); - dbg("registering slot %s", name); status = pci_hp_register(slot->hotplug_slot, bus, i, name); if (status) { err("pci_hp_register failed with error %d", status); - goto error_info; + goto error_hpslot; } dbg("slot registered with name: %s", slot_name(slot)); @@ -276,8 +242,6 @@ cpci_hp_register_bus(struct pci_bus *bus, u8 first, u8 last) up_write(&list_rwsem); } return 0; -error_info: - kfree(info); error_hpslot: kfree(hotplug_slot); error_slot: @@ -359,10 +323,8 @@ init_slots(int clear_ins) __func__, slot_name(slot)); dev = pci_get_slot(slot->bus, PCI_DEVFN(slot->number, 0)); if (dev) { - if (update_adapter_status(slot->hotplug_slot, 1)) - warn("failure to update adapter file"); - if (update_latch_status(slot->hotplug_slot, 1)) - warn("failure to update latch file"); + slot->adapter_status = 1; + slot->latch_status = 1; slot->dev = dev; } } @@ -424,11 +386,8 @@ check_slots(void) dbg("%s - slot %s HS_CSR (2) = %04x", __func__, slot_name(slot), hs_csr); - if (update_latch_status(slot->hotplug_slot, 1)) - warn("failure to update latch file"); - - if (update_adapter_status(slot->hotplug_slot, 1)) - warn("failure to update adapter file"); + slot->latch_status = 1; + slot->adapter_status = 1; cpci_led_off(slot); @@ -449,9 +408,7 @@ check_slots(void) __func__, slot_name(slot), hs_csr); if (!slot->extracting) { - if (update_latch_status(slot->hotplug_slot, 0)) - warn("failure to update latch file"); - + slot->latch_status = 0; slot->extracting = 1; atomic_inc(&extracting); } @@ -465,8 +422,7 @@ check_slots(void) */ err("card in slot %s was improperly removed", slot_name(slot)); - if (update_adapter_status(slot->hotplug_slot, 0)) - warn("failure to update adapter file"); + slot->adapter_status = 0; slot->extracting = 0; atomic_dec(&extracting); } diff --git a/drivers/pci/hotplug/cpqphp_core.c b/drivers/pci/hotplug/cpqphp_core.c index 3409b62fceac..bb354a7fc112 100644 --- a/drivers/pci/hotplug/cpqphp_core.c +++ b/drivers/pci/hotplug/cpqphp_core.c @@ -276,7 +276,6 @@ static int ctrl_slot_cleanup(struct controller *ctrl) while (old_slot) { next_slot = old_slot->next; pci_hp_deregister(old_slot->hotplug_slot); - kfree(old_slot->hotplug_slot->info); kfree(old_slot->hotplug_slot); kfree(old_slot); old_slot = next_slot; @@ -579,7 +578,6 @@ static int ctrl_slot_setup(struct controller *ctrl, { struct slot *slot; struct hotplug_slot *hotplug_slot; - struct hotplug_slot_info *hotplug_slot_info; struct pci_bus *bus = ctrl->pci_bus; u8 number_of_slots; u8 slot_device; @@ -613,14 +611,6 @@ static int ctrl_slot_setup(struct controller *ctrl, } hotplug_slot = slot->hotplug_slot; - hotplug_slot->info = kzalloc(sizeof(*(hotplug_slot->info)), - GFP_KERNEL); - if (!hotplug_slot->info) { - result = -ENOMEM; - goto error_hpslot; - } - hotplug_slot_info = hotplug_slot->info; - slot->ctrl = ctrl; slot->bus = ctrl->bus; slot->device = slot_device; @@ -673,14 +663,6 @@ static int ctrl_slot_setup(struct controller *ctrl, snprintf(name, SLOT_NAME_SIZE, "%u", slot->number); hotplug_slot->ops = &cpqphp_hotplug_slot_ops; - hotplug_slot_info->power_status = get_slot_enabled(ctrl, slot); - hotplug_slot_info->attention_status = - cpq_get_attention_status(ctrl, slot); - hotplug_slot_info->latch_status = - cpq_get_latch_status(ctrl, slot); - hotplug_slot_info->adapter_status = - get_presence_status(ctrl, slot); - dbg("registering bus %d, dev %d, number %d, ctrl->slot_device_offset %d, slot %d\n", slot->bus, slot->device, slot->number, ctrl->slot_device_offset, @@ -691,7 +673,7 @@ static int ctrl_slot_setup(struct controller *ctrl, name); if (result) { err("pci_hp_register failed with error %d\n", result); - goto error_info; + goto error_hpslot; } slot->next = ctrl->slot; @@ -703,8 +685,6 @@ static int ctrl_slot_setup(struct controller *ctrl, } return 0; -error_info: - kfree(hotplug_slot_info); error_hpslot: kfree(hotplug_slot); error_slot: diff --git a/drivers/pci/hotplug/cpqphp_ctrl.c b/drivers/pci/hotplug/cpqphp_ctrl.c index 616df442520b..9c4826ac6a4f 100644 --- a/drivers/pci/hotplug/cpqphp_ctrl.c +++ b/drivers/pci/hotplug/cpqphp_ctrl.c @@ -1130,9 +1130,9 @@ static u8 set_controller_speed(struct controller *ctrl, u8 adapter_speed, u8 hp_ for (slot = ctrl->slot; slot; slot = slot->next) { if (slot->device == (hp_slot + ctrl->slot_device_offset)) continue; - if (!slot->hotplug_slot || !slot->hotplug_slot->info) + if (!slot->hotplug_slot) continue; - if (slot->hotplug_slot->info->adapter_status == 0) + if (get_presence_status(ctrl, slot) == 0) continue; /* If another adapter is running on the same segment but at a * lower speed/mode, we allow the new adapter to function at @@ -1767,24 +1767,6 @@ void cpqhp_event_stop_thread(void) } -static int update_slot_info(struct controller *ctrl, struct slot *slot) -{ - struct hotplug_slot_info *info; - int result; - - info = kmalloc(sizeof(*info), GFP_KERNEL); - if (!info) - return -ENOMEM; - - info->power_status = get_slot_enabled(ctrl, slot); - info->attention_status = cpq_get_attention_status(ctrl, slot); - info->latch_status = cpq_get_latch_status(ctrl, slot); - info->adapter_status = get_presence_status(ctrl, slot); - result = pci_hp_change_slot_info(slot->hotplug_slot, info); - kfree(info); - return result; -} - static void interrupt_event_handler(struct controller *ctrl) { int loop = 0; @@ -1884,9 +1866,6 @@ static void interrupt_event_handler(struct controller *ctrl) /***********POWER FAULT */ else if (ctrl->event_queue[loop].event_type == INT_POWER_FAULT) { dbg("power fault\n"); - } else { - /* refresh notification */ - update_slot_info(ctrl, p_slot); } ctrl->event_queue[loop].event_type = 0; @@ -2057,9 +2036,6 @@ int cpqhp_process_SI(struct controller *ctrl, struct pci_func *func) if (rc) dbg("%s: rc = %d\n", __func__, rc); - if (p_slot) - update_slot_info(ctrl, p_slot); - return rc; } @@ -2125,9 +2101,6 @@ int cpqhp_process_SS(struct controller *ctrl, struct pci_func *func) rc = 1; } - if (p_slot) - update_slot_info(ctrl, p_slot); - return rc; } diff --git a/drivers/pci/hotplug/ibmphp_core.c b/drivers/pci/hotplug/ibmphp_core.c index b82fdc17040d..96e5b1f544ac 100644 --- a/drivers/pci/hotplug/ibmphp_core.c +++ b/drivers/pci/hotplug/ibmphp_core.c @@ -582,29 +582,10 @@ static int validate(struct slot *slot_cur, int opn) ****************************************************************************/ int ibmphp_update_slot_info(struct slot *slot_cur) { - struct hotplug_slot_info *info; struct pci_bus *bus = slot_cur->hotplug_slot->pci_slot->bus; - int rc; u8 bus_speed; u8 mode; - info = kmalloc(sizeof(struct hotplug_slot_info), GFP_KERNEL); - if (!info) - return -ENOMEM; - - info->power_status = SLOT_PWRGD(slot_cur->status); - info->attention_status = SLOT_ATTN(slot_cur->status, - slot_cur->ext_status); - info->latch_status = SLOT_LATCH(slot_cur->status); - if (!SLOT_PRESENT(slot_cur->status)) { - info->adapter_status = 0; -/* info->max_adapter_speed_status = MAX_ADAPTER_NONE; */ - } else { - info->adapter_status = 1; -/* get_max_adapter_speed_1(slot_cur->hotplug_slot, - &info->max_adapter_speed_status, 0); */ - } - bus_speed = slot_cur->bus_on->current_speed; mode = slot_cur->bus_on->current_bus_mode; @@ -630,9 +611,7 @@ int ibmphp_update_slot_info(struct slot *slot_cur) bus->cur_bus_speed = bus_speed; // To do: bus_names - rc = pci_hp_change_slot_info(slot_cur->hotplug_slot, info); - kfree(info); - return rc; + return 0; } @@ -684,7 +663,6 @@ static void free_slots(void) ibmphp_unconfigure_card(&slot_cur, -1); pci_hp_destroy(slot_cur->hotplug_slot); - kfree(slot_cur->hotplug_slot->info); kfree(slot_cur->hotplug_slot); kfree(slot_cur); } @@ -1095,8 +1073,7 @@ static int enable_slot(struct hotplug_slot *hs) slot_cur->func = kzalloc(sizeof(struct pci_func), GFP_KERNEL); if (!slot_cur->func) { - /* We cannot do update_slot_info here, since no memory for - * kmalloc n.e.ways, and update_slot_info allocates some */ + /* do update_slot_info here? */ rc = -ENOMEM; goto error_power; } diff --git a/drivers/pci/hotplug/ibmphp_ebda.c b/drivers/pci/hotplug/ibmphp_ebda.c index 6f8e90e3ec08..c05d066ab0d5 100644 --- a/drivers/pci/hotplug/ibmphp_ebda.c +++ b/drivers/pci/hotplug/ibmphp_ebda.c @@ -671,31 +671,6 @@ static int fillslotinfo(struct hotplug_slot *hotplug_slot) slot = hotplug_slot->private; rc = ibmphp_hpc_readslot(slot, READ_ALLSTAT, NULL); - if (rc) - return rc; - - // power - enabled:1 not:0 - hotplug_slot->info->power_status = SLOT_POWER(slot->status); - - // attention - off:0, on:1, blinking:2 - hotplug_slot->info->attention_status = SLOT_ATTN(slot->status, slot->ext_status); - - // latch - open:1 closed:0 - hotplug_slot->info->latch_status = SLOT_LATCH(slot->status); - - // pci board - present:1 not:0 - if (SLOT_PRESENT(slot->status)) - hotplug_slot->info->adapter_status = 1; - else - hotplug_slot->info->adapter_status = 0; -/* - if (slot->bus_on->supported_bus_mode - && (slot->bus_on->supported_speed == BUS_SPEED_66)) - hotplug_slot->info->max_bus_speed_status = BUS_SPEED_66PCIX; - else - hotplug_slot->info->max_bus_speed_status = slot->bus_on->supported_speed; -*/ - return rc; } @@ -877,12 +852,6 @@ static int __init ebda_rsrc_controller(void) goto error_no_hp_slot; } - hp_slot_ptr->info = kzalloc(sizeof(struct hotplug_slot_info), GFP_KERNEL); - if (!hp_slot_ptr->info) { - rc = -ENOMEM; - goto error_no_hp_info; - } - tmp_slot = kzalloc(sizeof(*tmp_slot), GFP_KERNEL); if (!tmp_slot) { rc = -ENOMEM; @@ -955,8 +924,6 @@ static int __init ebda_rsrc_controller(void) error: kfree(hp_slot_ptr->private); error_no_slot: - kfree(hp_slot_ptr->info); -error_no_hp_info: kfree(hp_slot_ptr); error_no_hp_slot: free_ebda_hpc(hpc_ptr); diff --git a/drivers/pci/hotplug/pci_hotplug_core.c b/drivers/pci/hotplug/pci_hotplug_core.c index ede2ed6f4ce0..5ac31f683b85 100644 --- a/drivers/pci/hotplug/pci_hotplug_core.c +++ b/drivers/pci/hotplug/pci_hotplug_core.c @@ -55,8 +55,6 @@ static int get_##name(struct hotplug_slot *slot, type *value) \ return -ENODEV; \ if (ops->get_##name) \ retval = ops->get_##name(slot, value); \ - else \ - *value = slot->info->name; \ module_put(slot->owner); \ return retval; \ } @@ -445,7 +443,7 @@ int __pci_hp_initialize(struct hotplug_slot *slot, struct pci_bus *bus, if (slot == NULL) return -ENODEV; - if ((slot->info == NULL) || (slot->ops == NULL)) + if (slot->ops == NULL) return -EINVAL; slot->owner = owner; @@ -560,28 +558,6 @@ void pci_hp_destroy(struct hotplug_slot *slot) } EXPORT_SYMBOL_GPL(pci_hp_destroy); -/** - * pci_hp_change_slot_info - changes the slot's information structure in the core - * @slot: pointer to the slot whose info has changed - * @info: pointer to the info copy into the slot's info structure - * - * @slot must have been registered with the pci - * hotplug subsystem previously with a call to pci_hp_register(). - * - * Returns 0 if successful, anything else for an error. - */ -int pci_hp_change_slot_info(struct hotplug_slot *slot, - struct hotplug_slot_info *info) -{ - if (!slot || !info) - return -ENODEV; - - memcpy(slot->info, info, sizeof(struct hotplug_slot_info)); - - return 0; -} -EXPORT_SYMBOL_GPL(pci_hp_change_slot_info); - static int __init pci_hotplug_init(void) { int result; diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c index 80cc7ba534bf..ac5baf887c5d 100644 --- a/drivers/pci/hotplug/pciehp_core.c +++ b/drivers/pci/hotplug/pciehp_core.c @@ -52,7 +52,6 @@ static int get_adapter_status(struct hotplug_slot *slot, u8 *value); static int init_slot(struct controller *ctrl) { struct hotplug_slot *hotplug = NULL; - struct hotplug_slot_info *info = NULL; struct hotplug_slot_ops *ops = NULL; char name[SLOT_NAME_SIZE]; int retval = -ENOMEM; @@ -61,10 +60,6 @@ static int init_slot(struct controller *ctrl) if (!hotplug) goto out; - info = kzalloc(sizeof(*info), GFP_KERNEL); - if (!info) - goto out; - /* Setup hotplug slot ops */ ops = kzalloc(sizeof(*ops), GFP_KERNEL); if (!ops) @@ -86,7 +81,6 @@ static int init_slot(struct controller *ctrl) } /* register this slot with the hotplug pci core */ - hotplug->info = info; hotplug->private = ctrl; hotplug->ops = ops; ctrl->hotplug_slot = hotplug; @@ -99,7 +93,6 @@ static int init_slot(struct controller *ctrl) out: if (retval) { kfree(ops); - kfree(info); kfree(hotplug); } return retval; @@ -111,7 +104,6 @@ static void cleanup_slot(struct controller *ctrl) pci_hp_destroy(hotplug_slot); kfree(hotplug_slot->ops); - kfree(hotplug_slot->info); kfree(hotplug_slot); } diff --git a/drivers/pci/hotplug/pnv_php.c b/drivers/pci/hotplug/pnv_php.c index 12b92a0ff688..5bb63430262e 100644 --- a/drivers/pci/hotplug/pnv_php.c +++ b/drivers/pci/hotplug/pnv_php.c @@ -328,6 +328,11 @@ out: return ret; } +static inline struct pnv_php_slot *to_pnv_php_slot(struct hotplug_slot *slot) +{ + return container_of(slot, struct pnv_php_slot, slot); +} + int pnv_php_set_slot_power_state(struct hotplug_slot *slot, uint8_t state) { @@ -378,7 +383,6 @@ static int pnv_php_get_power_state(struct hotplug_slot *slot, u8 *state) ret); } else { *state = power_state; - slot->info->power_status = power_state; } return 0; @@ -397,7 +401,6 @@ static int pnv_php_get_adapter_state(struct hotplug_slot *slot, u8 *state) ret = pnv_pci_get_presence_state(php_slot->id, &presence); if (ret >= 0) { *state = presence; - slot->info->adapter_status = presence; ret = 0; } else { pci_warn(php_slot->pdev, "Error %d getting presence\n", ret); @@ -406,10 +409,20 @@ static int pnv_php_get_adapter_state(struct hotplug_slot *slot, u8 *state) return ret; } +static int pnv_php_get_attention_state(struct hotplug_slot *slot, u8 *state) +{ + struct pnv_php_slot *php_slot = to_pnv_php_slot(slot); + + *state = php_slot->attention_state; + return 0; +} + static int pnv_php_set_attention_state(struct hotplug_slot *slot, u8 state) { + struct pnv_php_slot *php_slot = to_pnv_php_slot(slot); + /* FIXME: Make it real once firmware supports it */ - slot->info->attention_status = state; + php_slot->attention_state = state; return 0; } @@ -501,8 +514,7 @@ scan: static int pnv_php_enable_slot(struct hotplug_slot *slot) { - struct pnv_php_slot *php_slot = container_of(slot, - struct pnv_php_slot, slot); + struct pnv_php_slot *php_slot = to_pnv_php_slot(slot); return pnv_php_enable(php_slot, true); } @@ -533,6 +545,7 @@ static int pnv_php_disable_slot(struct hotplug_slot *slot) static const struct hotplug_slot_ops php_slot_ops = { .get_power_status = pnv_php_get_power_state, .get_adapter_status = pnv_php_get_adapter_state, + .get_attention_status = pnv_php_get_attention_state, .set_attention_status = pnv_php_set_attention_state, .enable_slot = pnv_php_enable_slot, .disable_slot = pnv_php_disable_slot, @@ -594,7 +607,6 @@ static struct pnv_php_slot *pnv_php_alloc_slot(struct device_node *dn) php_slot->id = id; php_slot->power_state_check = false; php_slot->slot.ops = &php_slot_ops; - php_slot->slot.info = &php_slot->slot_info; php_slot->slot.private = php_slot; INIT_LIST_HEAD(&php_slot->children); diff --git a/drivers/pci/hotplug/rpaphp.h b/drivers/pci/hotplug/rpaphp.h index f83347819f7b..26a3dd731b5e 100644 --- a/drivers/pci/hotplug/rpaphp.h +++ b/drivers/pci/hotplug/rpaphp.h @@ -63,6 +63,7 @@ struct slot { u32 index; u32 type; u32 power_domain; + u8 attention_status; char *name; struct device_node *dn; struct pci_bus *bus; diff --git a/drivers/pci/hotplug/rpaphp_core.c b/drivers/pci/hotplug/rpaphp_core.c index 8620a3f8c987..898e78dcd311 100644 --- a/drivers/pci/hotplug/rpaphp_core.c +++ b/drivers/pci/hotplug/rpaphp_core.c @@ -66,7 +66,7 @@ static int set_attention_status(struct hotplug_slot *hotplug_slot, u8 value) rc = rtas_set_indicator(DR_INDICATOR, slot->index, value); if (!rc) - hotplug_slot->info->attention_status = value; + slot->attention_status = value; return rc; } @@ -95,7 +95,7 @@ static int get_power_status(struct hotplug_slot *hotplug_slot, u8 *value) static int get_attention_status(struct hotplug_slot *hotplug_slot, u8 *value) { struct slot *slot = (struct slot *)hotplug_slot->private; - *value = slot->hotplug_slot->info->attention_status; + *value = slot->attention_status; return 0; } diff --git a/drivers/pci/hotplug/rpaphp_pci.c b/drivers/pci/hotplug/rpaphp_pci.c index 0aac33e15dab..beca61badeea 100644 --- a/drivers/pci/hotplug/rpaphp_pci.c +++ b/drivers/pci/hotplug/rpaphp_pci.c @@ -54,25 +54,21 @@ int rpaphp_get_sensor_state(struct slot *slot, int *state) * rpaphp_enable_slot - record slot state, config pci device * @slot: target &slot * - * Initialize values in the slot, and the hotplug_slot info - * structures to indicate if there is a pci card plugged into - * the slot. If the slot is not empty, run the pcibios routine + * Initialize values in the slot structure to indicate if there is a pci card + * plugged into the slot. If the slot is not empty, run the pcibios routine * to get pcibios stuff correctly set up. */ int rpaphp_enable_slot(struct slot *slot) { int rc, level, state; struct pci_bus *bus; - struct hotplug_slot_info *info = slot->hotplug_slot->info; - info->adapter_status = NOT_VALID; slot->state = EMPTY; /* Find out if the power is turned on for the slot */ rc = rtas_get_power_level(slot->power_domain, &level); if (rc) return rc; - info->power_status = level; /* Figure out if there is an adapter in the slot */ rc = rpaphp_get_sensor_state(slot, &state); @@ -85,13 +81,11 @@ int rpaphp_enable_slot(struct slot *slot) return -EINVAL; } - info->adapter_status = EMPTY; slot->bus = bus; slot->pci_devs = &bus->devices; /* if there's an adapter in the slot, go add the pci devices */ if (state == PRESENT) { - info->adapter_status = NOT_CONFIGURED; slot->state = NOT_CONFIGURED; /* non-empty slot has to have child */ @@ -105,7 +99,6 @@ int rpaphp_enable_slot(struct slot *slot) pci_hp_add_devices(bus); if (!list_empty(&bus->devices)) { - info->adapter_status = CONFIGURED; slot->state = CONFIGURED; } diff --git a/drivers/pci/hotplug/rpaphp_slot.c b/drivers/pci/hotplug/rpaphp_slot.c index b916c8e4372d..6e2658ce300b 100644 --- a/drivers/pci/hotplug/rpaphp_slot.c +++ b/drivers/pci/hotplug/rpaphp_slot.c @@ -21,7 +21,6 @@ /* free up the memory used by a slot */ void dealloc_slot_struct(struct slot *slot) { - kfree(slot->hotplug_slot->info); kfree(slot->name); kfree(slot->hotplug_slot); kfree(slot); @@ -38,13 +37,9 @@ struct slot *alloc_slot_struct(struct device_node *dn, slot->hotplug_slot = kzalloc(sizeof(struct hotplug_slot), GFP_KERNEL); if (!slot->hotplug_slot) goto error_slot; - slot->hotplug_slot->info = kzalloc(sizeof(struct hotplug_slot_info), - GFP_KERNEL); - if (!slot->hotplug_slot->info) - goto error_hpslot; slot->name = kstrdup(drc_name, GFP_KERNEL); if (!slot->name) - goto error_info; + goto error_hpslot; slot->dn = dn; slot->index = drc_index; slot->power_domain = power_domain; @@ -53,8 +48,6 @@ struct slot *alloc_slot_struct(struct device_node *dn, return (slot); -error_info: - kfree(slot->hotplug_slot->info); error_hpslot: kfree(slot->hotplug_slot); error_slot: diff --git a/drivers/pci/hotplug/s390_pci_hpc.c b/drivers/pci/hotplug/s390_pci_hpc.c index 5bd45fd4a92a..d04634b0defe 100644 --- a/drivers/pci/hotplug/s390_pci_hpc.c +++ b/drivers/pci/hotplug/s390_pci_hpc.c @@ -140,7 +140,6 @@ static const struct hotplug_slot_ops s390_hotplug_slot_ops = { int zpci_init_slot(struct zpci_dev *zdev) { struct hotplug_slot *hotplug_slot; - struct hotplug_slot_info *info; char name[SLOT_NAME_SIZE]; struct slot *slot; int rc; @@ -160,16 +159,8 @@ int zpci_init_slot(struct zpci_dev *zdev) slot->hotplug_slot = hotplug_slot; slot->zdev = zdev; - info = kzalloc(sizeof(*info), GFP_KERNEL); - if (!info) - goto error_info; - hotplug_slot->info = info; - hotplug_slot->ops = &s390_hotplug_slot_ops; - get_power_status(hotplug_slot, &info->power_status); - get_adapter_status(hotplug_slot, &info->adapter_status); - snprintf(name, SLOT_NAME_SIZE, "%08x", zdev->fid); rc = pci_hp_register(slot->hotplug_slot, zdev->bus, ZPCI_DEVFN, name); @@ -180,8 +171,6 @@ int zpci_init_slot(struct zpci_dev *zdev) return 0; error_reg: - kfree(info); -error_info: kfree(hotplug_slot); error_hp: kfree(slot); @@ -199,7 +188,6 @@ void zpci_exit_slot(struct zpci_dev *zdev) continue; list_del(&slot->slot_list); pci_hp_deregister(slot->hotplug_slot); - kfree(slot->hotplug_slot->info); kfree(slot->hotplug_slot); kfree(slot); } diff --git a/drivers/pci/hotplug/sgi_hotplug.c b/drivers/pci/hotplug/sgi_hotplug.c index af4c28c574dd..e103826c83e3 100644 --- a/drivers/pci/hotplug/sgi_hotplug.c +++ b/drivers/pci/hotplug/sgi_hotplug.c @@ -585,7 +585,6 @@ static inline int get_power_status(struct hotplug_slot *bss_hotplug_slot, static void sn_release_slot(struct hotplug_slot *bss_hotplug_slot) { - kfree(bss_hotplug_slot->info); kfree(bss_hotplug_slot->private); kfree(bss_hotplug_slot); } @@ -614,14 +613,6 @@ static int sn_hotplug_slot_register(struct pci_bus *pci_bus) goto alloc_err; } - bss_hotplug_slot->info = - kzalloc(sizeof(struct hotplug_slot_info), - GFP_KERNEL); - if (!bss_hotplug_slot->info) { - rc = -ENOMEM; - goto alloc_err; - } - if (sn_hp_slot_private_alloc(bss_hotplug_slot, pci_bus, device, name)) { rc = -ENOMEM; diff --git a/drivers/pci/hotplug/shpchp.h b/drivers/pci/hotplug/shpchp.h index 516e4835019c..a7bb816e6f25 100644 --- a/drivers/pci/hotplug/shpchp.h +++ b/drivers/pci/hotplug/shpchp.h @@ -67,7 +67,9 @@ struct slot { u32 number; u8 is_a_board; u8 state; + u8 attention_save; u8 presence_save; + u8 latch_save; u8 pwr_save; struct controller *ctrl; const struct hpc_ops *hpc_ops; diff --git a/drivers/pci/hotplug/shpchp_core.c b/drivers/pci/hotplug/shpchp_core.c index 26cbea04237c..b7181b7e7b98 100644 --- a/drivers/pci/hotplug/shpchp_core.c +++ b/drivers/pci/hotplug/shpchp_core.c @@ -65,7 +65,6 @@ static int init_slots(struct controller *ctrl) { struct slot *slot; struct hotplug_slot *hotplug_slot; - struct hotplug_slot_info *info; char name[SLOT_NAME_SIZE]; int retval; int i; @@ -84,13 +83,6 @@ static int init_slots(struct controller *ctrl) } slot->hotplug_slot = hotplug_slot; - info = kzalloc(sizeof(*info), GFP_KERNEL); - if (!info) { - retval = -ENOMEM; - goto error_hpslot; - } - hotplug_slot->info = info; - slot->hp_slot = i; slot->ctrl = ctrl; slot->bus = ctrl->pci_dev->subordinate->number; @@ -101,7 +93,7 @@ static int init_slots(struct controller *ctrl) slot->wq = alloc_workqueue("shpchp-%d", 0, 0, slot->number); if (!slot->wq) { retval = -ENOMEM; - goto error_info; + goto error_hpslot; } mutex_init(&slot->lock); @@ -124,10 +116,10 @@ static int init_slots(struct controller *ctrl) goto error_slotwq; } - get_power_status(hotplug_slot, &info->power_status); - get_attention_status(hotplug_slot, &info->attention_status); - get_latch_status(hotplug_slot, &info->latch_status); - get_adapter_status(hotplug_slot, &info->adapter_status); + get_power_status(hotplug_slot, &slot->pwr_save); + get_attention_status(hotplug_slot, &slot->attention_save); + get_latch_status(hotplug_slot, &slot->latch_save); + get_adapter_status(hotplug_slot, &slot->presence_save); list_add(&slot->slot_list, &ctrl->slot_list); } @@ -135,8 +127,6 @@ static int init_slots(struct controller *ctrl) return 0; error_slotwq: destroy_workqueue(slot->wq); -error_info: - kfree(info); error_hpslot: kfree(hotplug_slot); error_slot: @@ -154,7 +144,6 @@ void cleanup_slots(struct controller *ctrl) cancel_delayed_work(&slot->work); destroy_workqueue(slot->wq); pci_hp_deregister(slot->hotplug_slot); - kfree(slot->hotplug_slot->info); kfree(slot->hotplug_slot); kfree(slot); } @@ -170,7 +159,7 @@ static int set_attention_status(struct hotplug_slot *hotplug_slot, u8 status) ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n", __func__, slot_name(slot)); - hotplug_slot->info->attention_status = status; + slot->attention_save = status; slot->hpc_ops->set_attention_status(slot, status); return 0; @@ -206,7 +195,7 @@ static int get_power_status(struct hotplug_slot *hotplug_slot, u8 *value) retval = slot->hpc_ops->get_power_status(slot, value); if (retval < 0) - *value = hotplug_slot->info->power_status; + *value = slot->pwr_save; return 0; } @@ -221,7 +210,7 @@ static int get_attention_status(struct hotplug_slot *hotplug_slot, u8 *value) retval = slot->hpc_ops->get_attention_status(slot, value); if (retval < 0) - *value = hotplug_slot->info->attention_status; + *value = slot->attention_save; return 0; } @@ -236,7 +225,7 @@ static int get_latch_status(struct hotplug_slot *hotplug_slot, u8 *value) retval = slot->hpc_ops->get_latch_status(slot, value); if (retval < 0) - *value = hotplug_slot->info->latch_status; + *value = slot->latch_save; return 0; } @@ -251,7 +240,7 @@ static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value) retval = slot->hpc_ops->get_adapter_status(slot, value); if (retval < 0) - *value = hotplug_slot->info->adapter_status; + *value = slot->presence_save; return 0; } diff --git a/drivers/pci/hotplug/shpchp_ctrl.c b/drivers/pci/hotplug/shpchp_ctrl.c index 1267dcc5a531..078003dcde5b 100644 --- a/drivers/pci/hotplug/shpchp_ctrl.c +++ b/drivers/pci/hotplug/shpchp_ctrl.c @@ -446,23 +446,12 @@ void shpchp_queue_pushbutton_work(struct work_struct *work) mutex_unlock(&p_slot->lock); } -static int update_slot_info (struct slot *slot) +static void update_slot_info(struct slot *slot) { - struct hotplug_slot_info *info; - int result; - - info = kmalloc(sizeof(*info), GFP_KERNEL); - if (!info) - return -ENOMEM; - - slot->hpc_ops->get_power_status(slot, &(info->power_status)); - slot->hpc_ops->get_attention_status(slot, &(info->attention_status)); - slot->hpc_ops->get_latch_status(slot, &(info->latch_status)); - slot->hpc_ops->get_adapter_status(slot, &(info->adapter_status)); - - result = pci_hp_change_slot_info(slot->hotplug_slot, info); - kfree (info); - return result; + slot->hpc_ops->get_power_status(slot, &slot->pwr_save); + slot->hpc_ops->get_attention_status(slot, &slot->attention_save); + slot->hpc_ops->get_latch_status(slot, &slot->latch_save); + slot->hpc_ops->get_adapter_status(slot, &slot->presence_save); } /* diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index a8aa2eadfd82..019b037319e3 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -902,15 +902,8 @@ static int asus_setup_pci_hotplug(struct asus_wmi *asus) if (!asus->hotplug_slot) goto error_slot; - asus->hotplug_slot->info = kzalloc(sizeof(struct hotplug_slot_info), - GFP_KERNEL); - if (!asus->hotplug_slot->info) - goto error_info; - asus->hotplug_slot->private = asus; asus->hotplug_slot->ops = &asus_hotplug_slot_ops; - asus_get_adapter_status(asus->hotplug_slot, - &asus->hotplug_slot->info->adapter_status); ret = pci_hp_register(asus->hotplug_slot, bus, 0, "asus-wifi"); if (ret) { @@ -921,8 +914,6 @@ static int asus_setup_pci_hotplug(struct asus_wmi *asus) return 0; error_register: - kfree(asus->hotplug_slot->info); -error_info: kfree(asus->hotplug_slot); asus->hotplug_slot = NULL; error_slot: @@ -1055,7 +1046,6 @@ static void asus_wmi_rfkill_exit(struct asus_wmi *asus) asus_rfkill_hotplug(asus); if (asus->hotplug_slot) { pci_hp_deregister(asus->hotplug_slot); - kfree(asus->hotplug_slot->info); kfree(asus->hotplug_slot); } if (asus->hotplug_workqueue) diff --git a/drivers/platform/x86/eeepc-laptop.c b/drivers/platform/x86/eeepc-laptop.c index 41a364376e91..028b20f82962 100644 --- a/drivers/platform/x86/eeepc-laptop.c +++ b/drivers/platform/x86/eeepc-laptop.c @@ -745,15 +745,8 @@ static int eeepc_setup_pci_hotplug(struct eeepc_laptop *eeepc) if (!eeepc->hotplug_slot) goto error_slot; - eeepc->hotplug_slot->info = kzalloc(sizeof(struct hotplug_slot_info), - GFP_KERNEL); - if (!eeepc->hotplug_slot->info) - goto error_info; - eeepc->hotplug_slot->private = eeepc; eeepc->hotplug_slot->ops = &eeepc_hotplug_slot_ops; - eeepc_get_adapter_status(eeepc->hotplug_slot, - &eeepc->hotplug_slot->info->adapter_status); ret = pci_hp_register(eeepc->hotplug_slot, bus, 0, "eeepc-wifi"); if (ret) { @@ -764,8 +757,6 @@ static int eeepc_setup_pci_hotplug(struct eeepc_laptop *eeepc) return 0; error_register: - kfree(eeepc->hotplug_slot->info); -error_info: kfree(eeepc->hotplug_slot); eeepc->hotplug_slot = NULL; error_slot: @@ -831,7 +822,6 @@ static void eeepc_rfkill_exit(struct eeepc_laptop *eeepc) if (eeepc->hotplug_slot) { pci_hp_deregister(eeepc->hotplug_slot); - kfree(eeepc->hotplug_slot->info); kfree(eeepc->hotplug_slot); } diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index 372dbe95c207..6f07a4e1de8d 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -23,17 +23,9 @@ * @hardware_test: Called to run a specified hardware test on the specified * slot. * @get_power_status: Called to get the current power status of a slot. - * If this field is NULL, the value passed in the struct hotplug_slot_info - * will be used when this value is requested by a user. * @get_attention_status: Called to get the current attention status of a slot. - * If this field is NULL, the value passed in the struct hotplug_slot_info - * will be used when this value is requested by a user. * @get_latch_status: Called to get the current latch status of a slot. - * If this field is NULL, the value passed in the struct hotplug_slot_info - * will be used when this value is requested by a user. * @get_adapter_status: Called to get see if an adapter is present in the slot or not. - * If this field is NULL, the value passed in the struct hotplug_slot_info - * will be used when this value is requested by a user. * @reset_slot: Optional interface to allow override of a bus reset for the * slot for cases where a secondary bus reset can result in spurious * hotplug events or where a slot can be reset independent of the bus. @@ -55,27 +47,9 @@ struct hotplug_slot_ops { int (*reset_slot) (struct hotplug_slot *slot, int probe); }; -/** - * struct hotplug_slot_info - used to notify the hotplug pci core of the state of the slot - * @power_status: if power is enabled or not (1/0) - * @attention_status: if the attention light is enabled or not (1/0) - * @latch_status: if the latch (if any) is open or closed (1/0) - * @adapter_status: if there is a pci board present in the slot or not (1/0) - * - * Used to notify the hotplug pci core of the status of a specific slot. - */ -struct hotplug_slot_info { - u8 power_status; - u8 attention_status; - u8 latch_status; - u8 adapter_status; -}; - /** * struct hotplug_slot - used to register a physical slot with the hotplug pci core * @ops: pointer to the &struct hotplug_slot_ops to be used for this slot - * @info: pointer to the &struct hotplug_slot_info for the initial values for - * this slot. * @private: used by the hotplug pci controller driver to store whatever it * needs. * @owner: The module owner of this structure @@ -83,7 +57,6 @@ struct hotplug_slot_info { */ struct hotplug_slot { const struct hotplug_slot_ops *ops; - struct hotplug_slot_info *info; void *private; /* Variables below this are for use only by the hotplug pci core. */ @@ -110,9 +83,6 @@ void pci_hp_del(struct hotplug_slot *slot); void pci_hp_destroy(struct hotplug_slot *slot); void pci_hp_deregister(struct hotplug_slot *slot); -int __must_check pci_hp_change_slot_info(struct hotplug_slot *slot, - struct hotplug_slot_info *info); - /* use a define to avoid include chaining to get THIS_MODULE & friends */ #define pci_hp_register(slot, pbus, devnr, name) \ __pci_hp_register(slot, pbus, devnr, name, THIS_MODULE, KBUILD_MODNAME) -- cgit v1.2.3 From 125450f814418b9f889c9885831467d1b2e25a7d Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sat, 8 Sep 2018 09:59:01 +0200 Subject: PCI: hotplug: Embed hotplug_slot When the PCI hotplug core and its first user, cpqphp, were introduced in February 2002 with historic commit a8a2069f432c, cpqphp allocated a slot struct for its internal use plus a hotplug_slot struct to be registered with the hotplug core and linked the two with pointers: https://git.kernel.org/tglx/history/c/a8a2069f432c Nowadays, the predominant pattern in the tree is to embed ("subclass") such structures in one another and cast to the containing struct with container_of(). But it wasn't until July 2002 that container_of() was introduced with historic commit ec4f214232cf: https://git.kernel.org/tglx/history/c/ec4f214232cf pnv_php, introduced in 2016, did the right thing and embedded struct hotplug_slot in its internal struct pnv_php_slot, but all other drivers cargo-culted cpqphp's design and linked separate structs with pointers. Embedding structs is preferrable to linking them with pointers because it requires fewer allocations, thereby reducing overhead and simplifying error paths. Casting an embedded struct to the containing struct becomes a cheap subtraction rather than a dereference. And having fewer pointers reduces the risk of them pointing nowhere either accidentally or due to an attack. Convert all drivers to embed struct hotplug_slot in their internal slot struct. The "private" pointer in struct hotplug_slot thereby becomes unused, so drop it. Signed-off-by: Lukas Wunner Signed-off-by: Bjorn Helgaas Reviewed-by: Rafael J. Wysocki Acked-by: Tyrel Datwyler # drivers/pci/hotplug/rpa* Acked-by: Sebastian Ott # drivers/pci/hotplug/s390* Acked-by: Andy Shevchenko # drivers/platform/x86 Cc: Len Brown Cc: Scott Murray Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: Oliver OHalloran Cc: Gavin Shan Cc: Gerald Schaefer Cc: Corentin Chary Cc: Darren Hart --- drivers/pci/hotplug/acpiphp.h | 9 +++- drivers/pci/hotplug/acpiphp_core.c | 28 ++++------ drivers/pci/hotplug/acpiphp_ibm.c | 2 +- drivers/pci/hotplug/cpci_hotplug.h | 9 +++- drivers/pci/hotplug/cpci_hotplug_core.c | 37 +++++-------- drivers/pci/hotplug/cpci_hotplug_pci.c | 6 +-- drivers/pci/hotplug/cpqphp.h | 9 +++- drivers/pci/hotplug/cpqphp_core.c | 37 +++++-------- drivers/pci/hotplug/cpqphp_ctrl.c | 2 - drivers/pci/hotplug/ibmphp.h | 7 ++- drivers/pci/hotplug/ibmphp_core.c | 92 ++++++++++++++------------------- drivers/pci/hotplug/ibmphp_ebda.c | 37 ++++--------- drivers/pci/hotplug/pciehp.h | 11 ++-- drivers/pci/hotplug/pciehp_core.c | 37 +++++-------- drivers/pci/hotplug/pciehp_ctrl.c | 4 +- drivers/pci/hotplug/pciehp_hpc.c | 8 +-- drivers/pci/hotplug/pnv_php.c | 9 ++-- drivers/pci/hotplug/rpaphp.h | 7 ++- drivers/pci/hotplug/rpaphp_core.c | 14 ++--- drivers/pci/hotplug/rpaphp_slot.c | 15 ++---- drivers/pci/hotplug/s390_pci_hpc.c | 30 +++++------ drivers/pci/hotplug/sgi_hotplug.c | 52 ++++++++----------- drivers/pci/hotplug/shpchp.h | 6 +-- drivers/pci/hotplug/shpchp_core.c | 17 ++---- drivers/platform/x86/asus-wmi.c | 26 ++++------ drivers/platform/x86/eeepc-laptop.c | 30 +++++------ include/linux/pci_hotplug.h | 3 -- 27 files changed, 223 insertions(+), 321 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/hotplug/acpiphp.h b/drivers/pci/hotplug/acpiphp.h index 8377e736ea69..cf3058404f41 100644 --- a/drivers/pci/hotplug/acpiphp.h +++ b/drivers/pci/hotplug/acpiphp.h @@ -33,14 +33,19 @@ struct acpiphp_slot; * struct slot - slot information for each *physical* slot */ struct slot { - struct hotplug_slot *hotplug_slot; + struct hotplug_slot hotplug_slot; struct acpiphp_slot *acpi_slot; unsigned int sun; /* ACPI _SUN (Slot User Number) value */ }; static inline const char *slot_name(struct slot *slot) { - return hotplug_slot_name(slot->hotplug_slot); + return hotplug_slot_name(&slot->hotplug_slot); +} + +static inline struct slot *to_slot(struct hotplug_slot *hotplug_slot) +{ + return container_of(hotplug_slot, struct slot, hotplug_slot); } /* diff --git a/drivers/pci/hotplug/acpiphp_core.c b/drivers/pci/hotplug/acpiphp_core.c index abd4f8d7e16a..c9e2bd40c038 100644 --- a/drivers/pci/hotplug/acpiphp_core.c +++ b/drivers/pci/hotplug/acpiphp_core.c @@ -118,7 +118,7 @@ EXPORT_SYMBOL_GPL(acpiphp_unregister_attention); */ static int enable_slot(struct hotplug_slot *hotplug_slot) { - struct slot *slot = hotplug_slot->private; + struct slot *slot = to_slot(hotplug_slot); pr_debug("%s - physical_slot = %s\n", __func__, slot_name(slot)); @@ -135,7 +135,7 @@ static int enable_slot(struct hotplug_slot *hotplug_slot) */ static int disable_slot(struct hotplug_slot *hotplug_slot) { - struct slot *slot = hotplug_slot->private; + struct slot *slot = to_slot(hotplug_slot); pr_debug("%s - physical_slot = %s\n", __func__, slot_name(slot)); @@ -179,7 +179,7 @@ static int set_attention_status(struct hotplug_slot *hotplug_slot, u8 status) */ static int get_power_status(struct hotplug_slot *hotplug_slot, u8 *value) { - struct slot *slot = hotplug_slot->private; + struct slot *slot = to_slot(hotplug_slot); pr_debug("%s - physical_slot = %s\n", __func__, slot_name(slot)); @@ -225,7 +225,7 @@ static int get_attention_status(struct hotplug_slot *hotplug_slot, u8 *value) */ static int get_latch_status(struct hotplug_slot *hotplug_slot, u8 *value) { - struct slot *slot = hotplug_slot->private; + struct slot *slot = to_slot(hotplug_slot); pr_debug("%s - physical_slot = %s\n", __func__, slot_name(slot)); @@ -245,7 +245,7 @@ static int get_latch_status(struct hotplug_slot *hotplug_slot, u8 *value) */ static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value) { - struct slot *slot = hotplug_slot->private; + struct slot *slot = to_slot(hotplug_slot); pr_debug("%s - physical_slot = %s\n", __func__, slot_name(slot)); @@ -266,12 +266,7 @@ int acpiphp_register_hotplug_slot(struct acpiphp_slot *acpiphp_slot, if (!slot) goto error; - slot->hotplug_slot = kzalloc(sizeof(*slot->hotplug_slot), GFP_KERNEL); - if (!slot->hotplug_slot) - goto error_slot; - - slot->hotplug_slot->private = slot; - slot->hotplug_slot->ops = &acpi_hotplug_slot_ops; + slot->hotplug_slot.ops = &acpi_hotplug_slot_ops; slot->acpi_slot = acpiphp_slot; @@ -279,20 +274,18 @@ int acpiphp_register_hotplug_slot(struct acpiphp_slot *acpiphp_slot, slot->sun = sun; snprintf(name, SLOT_NAME_SIZE, "%u", sun); - retval = pci_hp_register(slot->hotplug_slot, acpiphp_slot->bus, + retval = pci_hp_register(&slot->hotplug_slot, acpiphp_slot->bus, acpiphp_slot->device, name); if (retval == -EBUSY) - goto error_hpslot; + goto error_slot; if (retval) { pr_err("pci_hp_register failed with error %d\n", retval); - goto error_hpslot; + goto error_slot; } pr_info("Slot [%s] registered\n", slot_name(slot)); return 0; -error_hpslot: - kfree(slot->hotplug_slot); error_slot: kfree(slot); error: @@ -306,8 +299,7 @@ void acpiphp_unregister_hotplug_slot(struct acpiphp_slot *acpiphp_slot) pr_info("Slot [%s] unregistered\n", slot_name(slot)); - pci_hp_deregister(slot->hotplug_slot); - kfree(slot->hotplug_slot); + pci_hp_deregister(&slot->hotplug_slot); kfree(slot); } diff --git a/drivers/pci/hotplug/acpiphp_ibm.c b/drivers/pci/hotplug/acpiphp_ibm.c index 41713f16ff97..df48b3b03ab4 100644 --- a/drivers/pci/hotplug/acpiphp_ibm.c +++ b/drivers/pci/hotplug/acpiphp_ibm.c @@ -41,7 +41,7 @@ MODULE_VERSION(DRIVER_VERSION); #define IBM_HARDWARE_ID1 "IBM37D0" #define IBM_HARDWARE_ID2 "IBM37D4" -#define hpslot_to_sun(A) (((struct slot *)((A)->private))->sun) +#define hpslot_to_sun(A) (to_slot(A)->sun) /* union apci_descriptor - allows access to the * various device descriptors that are embedded in the diff --git a/drivers/pci/hotplug/cpci_hotplug.h b/drivers/pci/hotplug/cpci_hotplug.h index a35f40a2290c..f33ff2bca414 100644 --- a/drivers/pci/hotplug/cpci_hotplug.h +++ b/drivers/pci/hotplug/cpci_hotplug.h @@ -35,7 +35,7 @@ struct slot { unsigned int latch_status:1; unsigned int adapter_status:1; unsigned int extracting; - struct hotplug_slot *hotplug_slot; + struct hotplug_slot hotplug_slot; struct list_head slot_list; }; @@ -60,7 +60,12 @@ struct cpci_hp_controller { static inline const char *slot_name(struct slot *slot) { - return hotplug_slot_name(slot->hotplug_slot); + return hotplug_slot_name(&slot->hotplug_slot); +} + +static inline struct slot *to_slot(struct hotplug_slot *hotplug_slot) +{ + return container_of(hotplug_slot, struct slot, hotplug_slot); } int cpci_hp_register_controller(struct cpci_hp_controller *controller); diff --git a/drivers/pci/hotplug/cpci_hotplug_core.c b/drivers/pci/hotplug/cpci_hotplug_core.c index a17fb24c28cd..603eadf3d965 100644 --- a/drivers/pci/hotplug/cpci_hotplug_core.c +++ b/drivers/pci/hotplug/cpci_hotplug_core.c @@ -70,7 +70,7 @@ static const struct hotplug_slot_ops cpci_hotplug_slot_ops = { static int enable_slot(struct hotplug_slot *hotplug_slot) { - struct slot *slot = hotplug_slot->private; + struct slot *slot = to_slot(hotplug_slot); int retval = 0; dbg("%s - physical_slot = %s", __func__, slot_name(slot)); @@ -83,7 +83,7 @@ enable_slot(struct hotplug_slot *hotplug_slot) static int disable_slot(struct hotplug_slot *hotplug_slot) { - struct slot *slot = hotplug_slot->private; + struct slot *slot = to_slot(hotplug_slot); int retval = 0; dbg("%s - physical_slot = %s", __func__, slot_name(slot)); @@ -139,7 +139,7 @@ cpci_get_power_status(struct slot *slot) static int get_power_status(struct hotplug_slot *hotplug_slot, u8 *value) { - struct slot *slot = hotplug_slot->private; + struct slot *slot = to_slot(hotplug_slot); *value = cpci_get_power_status(slot); return 0; @@ -148,7 +148,7 @@ get_power_status(struct hotplug_slot *hotplug_slot, u8 *value) static int get_attention_status(struct hotplug_slot *hotplug_slot, u8 *value) { - struct slot *slot = hotplug_slot->private; + struct slot *slot = to_slot(hotplug_slot); *value = cpci_get_attention_status(slot); return 0; @@ -157,13 +157,13 @@ get_attention_status(struct hotplug_slot *hotplug_slot, u8 *value) static int set_attention_status(struct hotplug_slot *hotplug_slot, u8 status) { - return cpci_set_attention_status(hotplug_slot->private, status); + return cpci_set_attention_status(to_slot(hotplug_slot), status); } static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value) { - struct slot *slot = hotplug_slot->private; + struct slot *slot = to_slot(hotplug_slot); *value = slot->adapter_status; return 0; @@ -172,7 +172,7 @@ get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value) static int get_latch_status(struct hotplug_slot *hotplug_slot, u8 *value) { - struct slot *slot = hotplug_slot->private; + struct slot *slot = to_slot(hotplug_slot); *value = slot->latch_status; return 0; @@ -180,7 +180,6 @@ get_latch_status(struct hotplug_slot *hotplug_slot, u8 *value) static void release_slot(struct slot *slot) { - kfree(slot->hotplug_slot); pci_dev_put(slot->dev); kfree(slot); } @@ -191,7 +190,6 @@ int cpci_hp_register_bus(struct pci_bus *bus, u8 first, u8 last) { struct slot *slot; - struct hotplug_slot *hotplug_slot; char name[SLOT_NAME_SIZE]; int status; int i; @@ -210,28 +208,19 @@ cpci_hp_register_bus(struct pci_bus *bus, u8 first, u8 last) goto error; } - hotplug_slot = - kzalloc(sizeof(struct hotplug_slot), GFP_KERNEL); - if (!hotplug_slot) { - status = -ENOMEM; - goto error_slot; - } - slot->hotplug_slot = hotplug_slot; - slot->bus = bus; slot->number = i; slot->devfn = PCI_DEVFN(i, 0); snprintf(name, SLOT_NAME_SIZE, "%02x:%02x", bus->number, i); - hotplug_slot->private = slot; - hotplug_slot->ops = &cpci_hotplug_slot_ops; + slot->hotplug_slot.ops = &cpci_hotplug_slot_ops; dbg("registering slot %s", name); - status = pci_hp_register(slot->hotplug_slot, bus, i, name); + status = pci_hp_register(&slot->hotplug_slot, bus, i, name); if (status) { err("pci_hp_register failed with error %d", status); - goto error_hpslot; + goto error_slot; } dbg("slot registered with name: %s", slot_name(slot)); @@ -242,8 +231,6 @@ cpci_hp_register_bus(struct pci_bus *bus, u8 first, u8 last) up_write(&list_rwsem); } return 0; -error_hpslot: - kfree(hotplug_slot); error_slot: kfree(slot); error: @@ -269,7 +256,7 @@ cpci_hp_unregister_bus(struct pci_bus *bus) slots--; dbg("deregistering slot %s", slot_name(slot)); - pci_hp_deregister(slot->hotplug_slot); + pci_hp_deregister(&slot->hotplug_slot); release_slot(slot); } } @@ -571,7 +558,7 @@ cleanup_slots(void) goto cleanup_null; list_for_each_entry_safe(slot, tmp, &slot_list, slot_list) { list_del(&slot->slot_list); - pci_hp_deregister(slot->hotplug_slot); + pci_hp_deregister(&slot->hotplug_slot); release_slot(slot); } cleanup_null: diff --git a/drivers/pci/hotplug/cpci_hotplug_pci.c b/drivers/pci/hotplug/cpci_hotplug_pci.c index 389b8fb50cd9..2c16adb7f4ec 100644 --- a/drivers/pci/hotplug/cpci_hotplug_pci.c +++ b/drivers/pci/hotplug/cpci_hotplug_pci.c @@ -194,8 +194,7 @@ int cpci_led_on(struct slot *slot) slot->devfn, hs_cap + 2, hs_csr)) { - err("Could not set LOO for slot %s", - hotplug_slot_name(slot->hotplug_slot)); + err("Could not set LOO for slot %s", slot_name(slot)); return -ENODEV; } } @@ -223,8 +222,7 @@ int cpci_led_off(struct slot *slot) slot->devfn, hs_cap + 2, hs_csr)) { - err("Could not clear LOO for slot %s", - hotplug_slot_name(slot->hotplug_slot)); + err("Could not clear LOO for slot %s", slot_name(slot)); return -ENODEV; } } diff --git a/drivers/pci/hotplug/cpqphp.h b/drivers/pci/hotplug/cpqphp.h index db78b394a075..77e4e0142fbc 100644 --- a/drivers/pci/hotplug/cpqphp.h +++ b/drivers/pci/hotplug/cpqphp.h @@ -260,7 +260,7 @@ struct slot { u8 hp_slot; struct controller *ctrl; void __iomem *p_sm_slot; - struct hotplug_slot *hotplug_slot; + struct hotplug_slot hotplug_slot; }; struct pci_resource { @@ -445,7 +445,12 @@ extern u8 cpqhp_disk_irq; static inline const char *slot_name(struct slot *slot) { - return hotplug_slot_name(slot->hotplug_slot); + return hotplug_slot_name(&slot->hotplug_slot); +} + +static inline struct slot *to_slot(struct hotplug_slot *hotplug_slot) +{ + return container_of(hotplug_slot, struct slot, hotplug_slot); } /* diff --git a/drivers/pci/hotplug/cpqphp_core.c b/drivers/pci/hotplug/cpqphp_core.c index bb354a7fc112..95b7d60cf119 100644 --- a/drivers/pci/hotplug/cpqphp_core.c +++ b/drivers/pci/hotplug/cpqphp_core.c @@ -275,8 +275,7 @@ static int ctrl_slot_cleanup(struct controller *ctrl) while (old_slot) { next_slot = old_slot->next; - pci_hp_deregister(old_slot->hotplug_slot); - kfree(old_slot->hotplug_slot); + pci_hp_deregister(&old_slot->hotplug_slot); kfree(old_slot); old_slot = next_slot; } @@ -418,7 +417,7 @@ cpqhp_set_attention_status(struct controller *ctrl, struct pci_func *func, static int set_attention_status(struct hotplug_slot *hotplug_slot, u8 status) { struct pci_func *slot_func; - struct slot *slot = hotplug_slot->private; + struct slot *slot = to_slot(hotplug_slot); struct controller *ctrl = slot->ctrl; u8 bus; u8 devfn; @@ -445,7 +444,7 @@ static int set_attention_status(struct hotplug_slot *hotplug_slot, u8 status) static int process_SI(struct hotplug_slot *hotplug_slot) { struct pci_func *slot_func; - struct slot *slot = hotplug_slot->private; + struct slot *slot = to_slot(hotplug_slot); struct controller *ctrl = slot->ctrl; u8 bus; u8 devfn; @@ -477,7 +476,7 @@ static int process_SI(struct hotplug_slot *hotplug_slot) static int process_SS(struct hotplug_slot *hotplug_slot) { struct pci_func *slot_func; - struct slot *slot = hotplug_slot->private; + struct slot *slot = to_slot(hotplug_slot); struct controller *ctrl = slot->ctrl; u8 bus; u8 devfn; @@ -504,7 +503,7 @@ static int process_SS(struct hotplug_slot *hotplug_slot) static int hardware_test(struct hotplug_slot *hotplug_slot, u32 value) { - struct slot *slot = hotplug_slot->private; + struct slot *slot = to_slot(hotplug_slot); struct controller *ctrl = slot->ctrl; dbg("%s - physical_slot = %s\n", __func__, slot_name(slot)); @@ -515,7 +514,7 @@ static int hardware_test(struct hotplug_slot *hotplug_slot, u32 value) static int get_power_status(struct hotplug_slot *hotplug_slot, u8 *value) { - struct slot *slot = hotplug_slot->private; + struct slot *slot = to_slot(hotplug_slot); struct controller *ctrl = slot->ctrl; dbg("%s - physical_slot = %s\n", __func__, slot_name(slot)); @@ -526,7 +525,7 @@ static int get_power_status(struct hotplug_slot *hotplug_slot, u8 *value) static int get_attention_status(struct hotplug_slot *hotplug_slot, u8 *value) { - struct slot *slot = hotplug_slot->private; + struct slot *slot = to_slot(hotplug_slot); struct controller *ctrl = slot->ctrl; dbg("%s - physical_slot = %s\n", __func__, slot_name(slot)); @@ -537,7 +536,7 @@ static int get_attention_status(struct hotplug_slot *hotplug_slot, u8 *value) static int get_latch_status(struct hotplug_slot *hotplug_slot, u8 *value) { - struct slot *slot = hotplug_slot->private; + struct slot *slot = to_slot(hotplug_slot); struct controller *ctrl = slot->ctrl; dbg("%s - physical_slot = %s\n", __func__, slot_name(slot)); @@ -549,7 +548,7 @@ static int get_latch_status(struct hotplug_slot *hotplug_slot, u8 *value) static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value) { - struct slot *slot = hotplug_slot->private; + struct slot *slot = to_slot(hotplug_slot); struct controller *ctrl = slot->ctrl; dbg("%s - physical_slot = %s\n", __func__, slot_name(slot)); @@ -577,7 +576,6 @@ static int ctrl_slot_setup(struct controller *ctrl, void __iomem *smbios_table) { struct slot *slot; - struct hotplug_slot *hotplug_slot; struct pci_bus *bus = ctrl->pci_bus; u8 number_of_slots; u8 slot_device; @@ -603,14 +601,6 @@ static int ctrl_slot_setup(struct controller *ctrl, goto error; } - slot->hotplug_slot = kzalloc(sizeof(*(slot->hotplug_slot)), - GFP_KERNEL); - if (!slot->hotplug_slot) { - result = -ENOMEM; - goto error_slot; - } - hotplug_slot = slot->hotplug_slot; - slot->ctrl = ctrl; slot->bus = ctrl->bus; slot->device = slot_device; @@ -659,21 +649,20 @@ static int ctrl_slot_setup(struct controller *ctrl, ((read_slot_enable(ctrl) << 2) >> ctrl_slot) & 0x04; /* register this slot with the hotplug pci core */ - hotplug_slot->private = slot; snprintf(name, SLOT_NAME_SIZE, "%u", slot->number); - hotplug_slot->ops = &cpqphp_hotplug_slot_ops; + slot->hotplug_slot.ops = &cpqphp_hotplug_slot_ops; dbg("registering bus %d, dev %d, number %d, ctrl->slot_device_offset %d, slot %d\n", slot->bus, slot->device, slot->number, ctrl->slot_device_offset, slot_number); - result = pci_hp_register(hotplug_slot, + result = pci_hp_register(&slot->hotplug_slot, ctrl->pci_dev->bus, slot->device, name); if (result) { err("pci_hp_register failed with error %d\n", result); - goto error_hpslot; + goto error_slot; } slot->next = ctrl->slot; @@ -685,8 +674,6 @@ static int ctrl_slot_setup(struct controller *ctrl, } return 0; -error_hpslot: - kfree(hotplug_slot); error_slot: kfree(slot); error: diff --git a/drivers/pci/hotplug/cpqphp_ctrl.c b/drivers/pci/hotplug/cpqphp_ctrl.c index 9c4826ac6a4f..b7f4e1f099d9 100644 --- a/drivers/pci/hotplug/cpqphp_ctrl.c +++ b/drivers/pci/hotplug/cpqphp_ctrl.c @@ -1130,8 +1130,6 @@ static u8 set_controller_speed(struct controller *ctrl, u8 adapter_speed, u8 hp_ for (slot = ctrl->slot; slot; slot = slot->next) { if (slot->device == (hp_slot + ctrl->slot_device_offset)) continue; - if (!slot->hotplug_slot) - continue; if (get_presence_status(ctrl, slot) == 0) continue; /* If another adapter is running on the same segment but at a diff --git a/drivers/pci/hotplug/ibmphp.h b/drivers/pci/hotplug/ibmphp.h index db387e10581e..b89f850c3a4e 100644 --- a/drivers/pci/hotplug/ibmphp.h +++ b/drivers/pci/hotplug/ibmphp.h @@ -698,7 +698,7 @@ struct slot { u8 supported_bus_mode; u8 flag; /* this is for disable slot and polling */ u8 ctlr_index; - struct hotplug_slot *hotplug_slot; + struct hotplug_slot hotplug_slot; struct controller *ctrl; struct pci_func *func; u8 irq[4]; @@ -742,5 +742,10 @@ int ibmphp_configure_card(struct pci_func *, u8); int ibmphp_unconfigure_card(struct slot **, int); extern const struct hotplug_slot_ops ibmphp_hotplug_slot_ops; +static inline struct slot *to_slot(struct hotplug_slot *hotplug_slot) +{ + return container_of(hotplug_slot, struct slot, hotplug_slot); +} + #endif //__IBMPHP_H diff --git a/drivers/pci/hotplug/ibmphp_core.c b/drivers/pci/hotplug/ibmphp_core.c index 96e5b1f544ac..08a58e911fc2 100644 --- a/drivers/pci/hotplug/ibmphp_core.c +++ b/drivers/pci/hotplug/ibmphp_core.c @@ -247,11 +247,8 @@ static int set_attention_status(struct hotplug_slot *hotplug_slot, u8 value) break; } if (rc == 0) { - pslot = hotplug_slot->private; - if (pslot) - rc = ibmphp_hpc_writeslot(pslot, cmd); - else - rc = -ENODEV; + pslot = to_slot(hotplug_slot); + rc = ibmphp_hpc_writeslot(pslot, cmd); } } else rc = -ENODEV; @@ -273,19 +270,15 @@ static int get_attention_status(struct hotplug_slot *hotplug_slot, u8 *value) ibmphp_lock_operations(); if (hotplug_slot) { - pslot = hotplug_slot->private; - if (pslot) { - memcpy(&myslot, pslot, sizeof(struct slot)); - rc = ibmphp_hpc_readslot(pslot, READ_SLOTSTATUS, - &(myslot.status)); - if (!rc) - rc = ibmphp_hpc_readslot(pslot, - READ_EXTSLOTSTATUS, - &(myslot.ext_status)); - if (!rc) - *value = SLOT_ATTN(myslot.status, - myslot.ext_status); - } + pslot = to_slot(hotplug_slot); + memcpy(&myslot, pslot, sizeof(struct slot)); + rc = ibmphp_hpc_readslot(pslot, READ_SLOTSTATUS, + &myslot.status); + if (!rc) + rc = ibmphp_hpc_readslot(pslot, READ_EXTSLOTSTATUS, + &myslot.ext_status); + if (!rc) + *value = SLOT_ATTN(myslot.status, myslot.ext_status); } ibmphp_unlock_operations(); @@ -303,14 +296,12 @@ static int get_latch_status(struct hotplug_slot *hotplug_slot, u8 *value) (ulong) hotplug_slot, (ulong) value); ibmphp_lock_operations(); if (hotplug_slot) { - pslot = hotplug_slot->private; - if (pslot) { - memcpy(&myslot, pslot, sizeof(struct slot)); - rc = ibmphp_hpc_readslot(pslot, READ_SLOTSTATUS, - &(myslot.status)); - if (!rc) - *value = SLOT_LATCH(myslot.status); - } + pslot = to_slot(hotplug_slot); + memcpy(&myslot, pslot, sizeof(struct slot)); + rc = ibmphp_hpc_readslot(pslot, READ_SLOTSTATUS, + &myslot.status); + if (!rc) + *value = SLOT_LATCH(myslot.status); } ibmphp_unlock_operations(); @@ -330,14 +321,12 @@ static int get_power_status(struct hotplug_slot *hotplug_slot, u8 *value) (ulong) hotplug_slot, (ulong) value); ibmphp_lock_operations(); if (hotplug_slot) { - pslot = hotplug_slot->private; - if (pslot) { - memcpy(&myslot, pslot, sizeof(struct slot)); - rc = ibmphp_hpc_readslot(pslot, READ_SLOTSTATUS, - &(myslot.status)); - if (!rc) - *value = SLOT_PWRGD(myslot.status); - } + pslot = to_slot(hotplug_slot); + memcpy(&myslot, pslot, sizeof(struct slot)); + rc = ibmphp_hpc_readslot(pslot, READ_SLOTSTATUS, + &myslot.status); + if (!rc) + *value = SLOT_PWRGD(myslot.status); } ibmphp_unlock_operations(); @@ -357,18 +346,16 @@ static int get_adapter_present(struct hotplug_slot *hotplug_slot, u8 *value) (ulong) hotplug_slot, (ulong) value); ibmphp_lock_operations(); if (hotplug_slot) { - pslot = hotplug_slot->private; - if (pslot) { - memcpy(&myslot, pslot, sizeof(struct slot)); - rc = ibmphp_hpc_readslot(pslot, READ_SLOTSTATUS, - &(myslot.status)); - if (!rc) { - present = SLOT_PRESENT(myslot.status); - if (present == HPC_SLOT_EMPTY) - *value = 0; - else - *value = 1; - } + pslot = to_slot(hotplug_slot); + memcpy(&myslot, pslot, sizeof(struct slot)); + rc = ibmphp_hpc_readslot(pslot, READ_SLOTSTATUS, + &myslot.status); + if (!rc) { + present = SLOT_PRESENT(myslot.status); + if (present == HPC_SLOT_EMPTY) + *value = 0; + else + *value = 1; } } @@ -382,7 +369,7 @@ static int get_max_bus_speed(struct slot *slot) int rc = 0; u8 mode = 0; enum pci_bus_speed speed; - struct pci_bus *bus = slot->hotplug_slot->pci_slot->bus; + struct pci_bus *bus = slot->hotplug_slot.pci_slot->bus; debug("%s - Entry slot[%p]\n", __func__, slot); @@ -582,7 +569,7 @@ static int validate(struct slot *slot_cur, int opn) ****************************************************************************/ int ibmphp_update_slot_info(struct slot *slot_cur) { - struct pci_bus *bus = slot_cur->hotplug_slot->pci_slot->bus; + struct pci_bus *bus = slot_cur->hotplug_slot.pci_slot->bus; u8 bus_speed; u8 mode; @@ -652,7 +639,7 @@ static void free_slots(void) list_for_each_entry_safe(slot_cur, next, &ibmphp_slot_head, ibm_slot_list) { - pci_hp_del(slot_cur->hotplug_slot); + pci_hp_del(&slot_cur->hotplug_slot); slot_cur->ctrl = NULL; slot_cur->bus_on = NULL; @@ -662,8 +649,7 @@ static void free_slots(void) */ ibmphp_unconfigure_card(&slot_cur, -1); - pci_hp_destroy(slot_cur->hotplug_slot); - kfree(slot_cur->hotplug_slot); + pci_hp_destroy(&slot_cur->hotplug_slot); kfree(slot_cur); } debug("%s -- exit\n", __func__); @@ -985,7 +971,7 @@ static int enable_slot(struct hotplug_slot *hs) ibmphp_lock_operations(); debug("ENABLING SLOT........\n"); - slot_cur = hs->private; + slot_cur = to_slot(hs); rc = validate(slot_cur, ENABLE); if (rc) { @@ -1146,7 +1132,7 @@ error_power: **************************************************************/ static int ibmphp_disable_slot(struct hotplug_slot *hotplug_slot) { - struct slot *slot = hotplug_slot->private; + struct slot *slot = to_slot(hotplug_slot); int rc; ibmphp_lock_operations(); diff --git a/drivers/pci/hotplug/ibmphp_ebda.c b/drivers/pci/hotplug/ibmphp_ebda.c index c05d066ab0d5..11a2661dc062 100644 --- a/drivers/pci/hotplug/ibmphp_ebda.c +++ b/drivers/pci/hotplug/ibmphp_ebda.c @@ -666,10 +666,7 @@ static int fillslotinfo(struct hotplug_slot *hotplug_slot) struct slot *slot; int rc = 0; - if (!hotplug_slot || !hotplug_slot->private) - return -EINVAL; - - slot = hotplug_slot->private; + slot = to_slot(hotplug_slot); rc = ibmphp_hpc_readslot(slot, READ_ALLSTAT, NULL); return rc; } @@ -687,7 +684,6 @@ static int __init ebda_rsrc_controller(void) u8 ctlr_id, temp, bus_index; u16 ctlr, slot, bus; u16 slot_num, bus_num, index; - struct hotplug_slot *hp_slot_ptr; struct controller *hpc_ptr; struct ebda_hpc_bus *bus_ptr; struct ebda_hpc_slot *slot_ptr; @@ -746,7 +742,7 @@ static int __init ebda_rsrc_controller(void) bus_info_ptr1 = kzalloc(sizeof(struct bus_info), GFP_KERNEL); if (!bus_info_ptr1) { rc = -ENOMEM; - goto error_no_hp_slot; + goto error_no_slot; } bus_info_ptr1->slot_min = slot_ptr->slot_num; bus_info_ptr1->slot_max = slot_ptr->slot_num; @@ -817,7 +813,7 @@ static int __init ebda_rsrc_controller(void) (hpc_ptr->u.isa_ctlr.io_end - hpc_ptr->u.isa_ctlr.io_start + 1), "ibmphp")) { rc = -ENODEV; - goto error_no_hp_slot; + goto error_no_slot; } hpc_ptr->irq = readb(io_mem + addr + 4); addr += 5; @@ -832,7 +828,7 @@ static int __init ebda_rsrc_controller(void) break; default: rc = -ENODEV; - goto error_no_hp_slot; + goto error_no_slot; } //reorganize chassis' linked list @@ -845,13 +841,6 @@ static int __init ebda_rsrc_controller(void) // register slots with hpc core as well as create linked list of ibm slot for (index = 0; index < hpc_ptr->slot_count; index++) { - - hp_slot_ptr = kzalloc(sizeof(*hp_slot_ptr), GFP_KERNEL); - if (!hp_slot_ptr) { - rc = -ENOMEM; - goto error_no_hp_slot; - } - tmp_slot = kzalloc(sizeof(*tmp_slot), GFP_KERNEL); if (!tmp_slot) { rc = -ENOMEM; @@ -878,7 +867,6 @@ static int __init ebda_rsrc_controller(void) bus_info_ptr1 = ibmphp_find_same_bus_num(hpc_ptr->slots[index].slot_bus_num); if (!bus_info_ptr1) { - kfree(tmp_slot); rc = -ENODEV; goto error; } @@ -888,22 +876,19 @@ static int __init ebda_rsrc_controller(void) tmp_slot->ctlr_index = hpc_ptr->slots[index].ctl_index; tmp_slot->number = hpc_ptr->slots[index].slot_num; - tmp_slot->hotplug_slot = hp_slot_ptr; - - hp_slot_ptr->private = tmp_slot; - rc = fillslotinfo(hp_slot_ptr); + rc = fillslotinfo(&tmp_slot->hotplug_slot); if (rc) goto error; - rc = ibmphp_init_devno((struct slot **) &hp_slot_ptr->private); + rc = ibmphp_init_devno(&tmp_slot); if (rc) goto error; - hp_slot_ptr->ops = &ibmphp_hotplug_slot_ops; + tmp_slot->hotplug_slot.ops = &ibmphp_hotplug_slot_ops; // end of registering ibm slot with hotplug core - list_add(&((struct slot *)(hp_slot_ptr->private))->ibm_slot_list, &ibmphp_slot_head); + list_add(&tmp_slot->ibm_slot_list, &ibmphp_slot_head); } print_bus_info(); @@ -913,7 +898,7 @@ static int __init ebda_rsrc_controller(void) list_for_each_entry(tmp_slot, &ibmphp_slot_head, ibm_slot_list) { snprintf(name, SLOT_NAME_SIZE, "%s", create_file_name(tmp_slot)); - pci_hp_register(tmp_slot->hotplug_slot, + pci_hp_register(&tmp_slot->hotplug_slot, pci_find_bus(0, tmp_slot->bus), tmp_slot->device, name); } @@ -922,10 +907,8 @@ static int __init ebda_rsrc_controller(void) return 0; error: - kfree(hp_slot_ptr->private); + kfree(tmp_slot); error_no_slot: - kfree(hp_slot_ptr); -error_no_hp_slot: free_ebda_hpc(hpc_ptr); error_no_hpc: iounmap(io_mem); diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h index 3cc88f3e4368..3740f1a759c5 100644 --- a/drivers/pci/hotplug/pciehp.h +++ b/drivers/pci/hotplug/pciehp.h @@ -88,7 +88,7 @@ do { \ * protects scheduling, execution and cancellation of @button_work * @button_work: work item to turn the slot on or off after 5 seconds * in response to an Attention Button press - * @hotplug_slot: pointer to the structure registered with the PCI hotplug core + * @hotplug_slot: structure registered with the PCI hotplug core * @reset_lock: prevents access to the Data Link Layer Link Active bit in the * Link Status register and to the Presence Detect State bit in the Slot * Status register during a slot reset which may cause them to flap @@ -120,7 +120,7 @@ struct controller { struct mutex state_lock; struct delayed_work button_work; - struct hotplug_slot *hotplug_slot; /* hotplug core interface */ + struct hotplug_slot hotplug_slot; /* hotplug core interface */ struct rw_semaphore reset_lock; int request_result; wait_queue_head_t requester; @@ -207,7 +207,12 @@ int pciehp_get_raw_indicator_status(struct hotplug_slot *h_slot, u8 *status); static inline const char *slot_name(struct controller *ctrl) { - return hotplug_slot_name(ctrl->hotplug_slot); + return hotplug_slot_name(&ctrl->hotplug_slot); +} + +static inline struct controller *to_ctrl(struct hotplug_slot *hotplug_slot) +{ + return container_of(hotplug_slot, struct controller, hotplug_slot); } #endif /* _PCIEHP_H */ diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c index ac5baf887c5d..68b20e667764 100644 --- a/drivers/pci/hotplug/pciehp_core.c +++ b/drivers/pci/hotplug/pciehp_core.c @@ -51,19 +51,14 @@ static int get_adapter_status(struct hotplug_slot *slot, u8 *value); static int init_slot(struct controller *ctrl) { - struct hotplug_slot *hotplug = NULL; - struct hotplug_slot_ops *ops = NULL; + struct hotplug_slot_ops *ops; char name[SLOT_NAME_SIZE]; - int retval = -ENOMEM; - - hotplug = kzalloc(sizeof(*hotplug), GFP_KERNEL); - if (!hotplug) - goto out; + int retval; /* Setup hotplug slot ops */ ops = kzalloc(sizeof(*ops), GFP_KERNEL); if (!ops) - goto out; + return -ENOMEM; ops->enable_slot = pciehp_sysfs_enable_slot; ops->disable_slot = pciehp_sysfs_disable_slot; @@ -81,30 +76,24 @@ static int init_slot(struct controller *ctrl) } /* register this slot with the hotplug pci core */ - hotplug->private = ctrl; - hotplug->ops = ops; - ctrl->hotplug_slot = hotplug; + ctrl->hotplug_slot.ops = ops; snprintf(name, SLOT_NAME_SIZE, "%u", PSN(ctrl)); - retval = pci_hp_initialize(hotplug, + retval = pci_hp_initialize(&ctrl->hotplug_slot, ctrl->pcie->port->subordinate, 0, name); - if (retval) - ctrl_err(ctrl, "pci_hp_initialize failed: error %d\n", retval); -out: if (retval) { + ctrl_err(ctrl, "pci_hp_initialize failed: error %d\n", retval); kfree(ops); - kfree(hotplug); } return retval; } static void cleanup_slot(struct controller *ctrl) { - struct hotplug_slot *hotplug_slot = ctrl->hotplug_slot; + struct hotplug_slot *hotplug_slot = &ctrl->hotplug_slot; pci_hp_destroy(hotplug_slot); kfree(hotplug_slot->ops); - kfree(hotplug_slot); } /* @@ -112,7 +101,7 @@ static void cleanup_slot(struct controller *ctrl) */ static int set_attention_status(struct hotplug_slot *hotplug_slot, u8 status) { - struct controller *ctrl = hotplug_slot->private; + struct controller *ctrl = to_ctrl(hotplug_slot); struct pci_dev *pdev = ctrl->pcie->port; pci_config_pm_runtime_get(pdev); @@ -123,7 +112,7 @@ static int set_attention_status(struct hotplug_slot *hotplug_slot, u8 status) static int get_power_status(struct hotplug_slot *hotplug_slot, u8 *value) { - struct controller *ctrl = hotplug_slot->private; + struct controller *ctrl = to_ctrl(hotplug_slot); struct pci_dev *pdev = ctrl->pcie->port; pci_config_pm_runtime_get(pdev); @@ -134,7 +123,7 @@ static int get_power_status(struct hotplug_slot *hotplug_slot, u8 *value) static int get_latch_status(struct hotplug_slot *hotplug_slot, u8 *value) { - struct controller *ctrl = hotplug_slot->private; + struct controller *ctrl = to_ctrl(hotplug_slot); struct pci_dev *pdev = ctrl->pcie->port; pci_config_pm_runtime_get(pdev); @@ -145,7 +134,7 @@ static int get_latch_status(struct hotplug_slot *hotplug_slot, u8 *value) static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value) { - struct controller *ctrl = hotplug_slot->private; + struct controller *ctrl = to_ctrl(hotplug_slot); struct pci_dev *pdev = ctrl->pcie->port; pci_config_pm_runtime_get(pdev); @@ -223,7 +212,7 @@ static int pciehp_probe(struct pcie_device *dev) } /* Publish to user space */ - rc = pci_hp_add(ctrl->hotplug_slot); + rc = pci_hp_add(&ctrl->hotplug_slot); if (rc) { ctrl_err(ctrl, "Publication to user space failed (%d)\n", rc); goto err_out_shutdown_notification; @@ -246,7 +235,7 @@ static void pciehp_remove(struct pcie_device *dev) { struct controller *ctrl = get_service_data(dev); - pci_hp_del(ctrl->hotplug_slot); + pci_hp_del(&ctrl->hotplug_slot); pcie_shutdown_notification(ctrl); cleanup_slot(ctrl); pciehp_release_ctrl(ctrl); diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c index 04f7ad9fffe1..3f3df4c29f6e 100644 --- a/drivers/pci/hotplug/pciehp_ctrl.c +++ b/drivers/pci/hotplug/pciehp_ctrl.c @@ -348,7 +348,7 @@ static int pciehp_disable_slot(struct controller *ctrl, bool safe_removal) int pciehp_sysfs_enable_slot(struct hotplug_slot *hotplug_slot) { - struct controller *ctrl = hotplug_slot->private; + struct controller *ctrl = to_ctrl(hotplug_slot); mutex_lock(&ctrl->state_lock); switch (ctrl->state) { @@ -386,7 +386,7 @@ int pciehp_sysfs_enable_slot(struct hotplug_slot *hotplug_slot) int pciehp_sysfs_disable_slot(struct hotplug_slot *hotplug_slot) { - struct controller *ctrl = hotplug_slot->private; + struct controller *ctrl = to_ctrl(hotplug_slot); mutex_lock(&ctrl->state_lock); switch (ctrl->state) { diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c index 0289a3ae4d90..7b5f9db60d9a 100644 --- a/drivers/pci/hotplug/pciehp_hpc.c +++ b/drivers/pci/hotplug/pciehp_hpc.c @@ -315,7 +315,7 @@ static int pciehp_link_enable(struct controller *ctrl) int pciehp_get_raw_indicator_status(struct hotplug_slot *hotplug_slot, u8 *status) { - struct controller *ctrl = hotplug_slot->private; + struct controller *ctrl = to_ctrl(hotplug_slot); struct pci_dev *pdev = ctrl_dev(ctrl); u16 slot_ctrl; @@ -328,7 +328,7 @@ int pciehp_get_raw_indicator_status(struct hotplug_slot *hotplug_slot, int pciehp_get_attention_status(struct hotplug_slot *hotplug_slot, u8 *status) { - struct controller *ctrl = hotplug_slot->private; + struct controller *ctrl = to_ctrl(hotplug_slot); struct pci_dev *pdev = ctrl_dev(ctrl); u16 slot_ctrl; @@ -422,7 +422,7 @@ int pciehp_query_power_fault(struct controller *ctrl) int pciehp_set_raw_indicator_status(struct hotplug_slot *hotplug_slot, u8 status) { - struct controller *ctrl = hotplug_slot->private; + struct controller *ctrl = to_ctrl(hotplug_slot); struct pci_dev *pdev = ctrl_dev(ctrl); pci_config_pm_runtime_get(pdev); @@ -758,7 +758,7 @@ void pcie_clear_hotplug_events(struct controller *ctrl) */ int pciehp_reset_slot(struct hotplug_slot *hotplug_slot, int probe) { - struct controller *ctrl = hotplug_slot->private; + struct controller *ctrl = to_ctrl(hotplug_slot); struct pci_dev *pdev = ctrl_dev(ctrl); u16 stat_mask = 0, ctrl_mask = 0; int rc; diff --git a/drivers/pci/hotplug/pnv_php.c b/drivers/pci/hotplug/pnv_php.c index 5bb63430262e..5070620a4f9f 100644 --- a/drivers/pci/hotplug/pnv_php.c +++ b/drivers/pci/hotplug/pnv_php.c @@ -336,7 +336,7 @@ static inline struct pnv_php_slot *to_pnv_php_slot(struct hotplug_slot *slot) int pnv_php_set_slot_power_state(struct hotplug_slot *slot, uint8_t state) { - struct pnv_php_slot *php_slot = slot->private; + struct pnv_php_slot *php_slot = to_pnv_php_slot(slot); struct opal_msg msg; int ret; @@ -368,7 +368,7 @@ EXPORT_SYMBOL_GPL(pnv_php_set_slot_power_state); static int pnv_php_get_power_state(struct hotplug_slot *slot, u8 *state) { - struct pnv_php_slot *php_slot = slot->private; + struct pnv_php_slot *php_slot = to_pnv_php_slot(slot); uint8_t power_state = OPAL_PCI_SLOT_POWER_ON; int ret; @@ -390,7 +390,7 @@ static int pnv_php_get_power_state(struct hotplug_slot *slot, u8 *state) static int pnv_php_get_adapter_state(struct hotplug_slot *slot, u8 *state) { - struct pnv_php_slot *php_slot = slot->private; + struct pnv_php_slot *php_slot = to_pnv_php_slot(slot); uint8_t presence = OPAL_PCI_SLOT_EMPTY; int ret; @@ -521,7 +521,7 @@ static int pnv_php_enable_slot(struct hotplug_slot *slot) static int pnv_php_disable_slot(struct hotplug_slot *slot) { - struct pnv_php_slot *php_slot = slot->private; + struct pnv_php_slot *php_slot = to_pnv_php_slot(slot); int ret; if (php_slot->state != PNV_PHP_STATE_POPULATED) @@ -607,7 +607,6 @@ static struct pnv_php_slot *pnv_php_alloc_slot(struct device_node *dn) php_slot->id = id; php_slot->power_state_check = false; php_slot->slot.ops = &php_slot_ops; - php_slot->slot.private = php_slot; INIT_LIST_HEAD(&php_slot->children); INIT_LIST_HEAD(&php_slot->link); diff --git a/drivers/pci/hotplug/rpaphp.h b/drivers/pci/hotplug/rpaphp.h index 26a3dd731b5e..bdc954d70869 100644 --- a/drivers/pci/hotplug/rpaphp.h +++ b/drivers/pci/hotplug/rpaphp.h @@ -68,12 +68,17 @@ struct slot { struct device_node *dn; struct pci_bus *bus; struct list_head *pci_devs; - struct hotplug_slot *hotplug_slot; + struct hotplug_slot hotplug_slot; }; extern const struct hotplug_slot_ops rpaphp_hotplug_slot_ops; extern struct list_head rpaphp_slot_head; +static inline struct slot *to_slot(struct hotplug_slot *hotplug_slot) +{ + return container_of(hotplug_slot, struct slot, hotplug_slot); +} + /* function prototypes */ /* rpaphp_pci.c */ diff --git a/drivers/pci/hotplug/rpaphp_core.c b/drivers/pci/hotplug/rpaphp_core.c index 898e78dcd311..bcd5d357ca23 100644 --- a/drivers/pci/hotplug/rpaphp_core.c +++ b/drivers/pci/hotplug/rpaphp_core.c @@ -52,7 +52,7 @@ module_param_named(debug, rpaphp_debug, bool, 0644); static int set_attention_status(struct hotplug_slot *hotplug_slot, u8 value) { int rc; - struct slot *slot = (struct slot *)hotplug_slot->private; + struct slot *slot = to_slot(hotplug_slot); switch (value) { case 0: @@ -79,7 +79,7 @@ static int set_attention_status(struct hotplug_slot *hotplug_slot, u8 value) static int get_power_status(struct hotplug_slot *hotplug_slot, u8 *value) { int retval, level; - struct slot *slot = (struct slot *)hotplug_slot->private; + struct slot *slot = to_slot(hotplug_slot); retval = rtas_get_power_level(slot->power_domain, &level); if (!retval) @@ -94,14 +94,14 @@ static int get_power_status(struct hotplug_slot *hotplug_slot, u8 *value) */ static int get_attention_status(struct hotplug_slot *hotplug_slot, u8 *value) { - struct slot *slot = (struct slot *)hotplug_slot->private; + struct slot *slot = to_slot(hotplug_slot); *value = slot->attention_status; return 0; } static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value) { - struct slot *slot = (struct slot *)hotplug_slot->private; + struct slot *slot = to_slot(hotplug_slot); int rc, state; rc = rpaphp_get_sensor_state(slot, &state); @@ -409,7 +409,7 @@ static void __exit cleanup_slots(void) list_for_each_entry_safe(slot, next, &rpaphp_slot_head, rpaphp_slot_list) { list_del(&slot->rpaphp_slot_list); - pci_hp_deregister(slot->hotplug_slot); + pci_hp_deregister(&slot->hotplug_slot); dealloc_slot_struct(slot); } return; @@ -434,7 +434,7 @@ static void __exit rpaphp_exit(void) static int enable_slot(struct hotplug_slot *hotplug_slot) { - struct slot *slot = (struct slot *)hotplug_slot->private; + struct slot *slot = to_slot(hotplug_slot); int state; int retval; @@ -464,7 +464,7 @@ static int enable_slot(struct hotplug_slot *hotplug_slot) static int disable_slot(struct hotplug_slot *hotplug_slot) { - struct slot *slot = (struct slot *)hotplug_slot->private; + struct slot *slot = to_slot(hotplug_slot); if (slot->state == NOT_CONFIGURED) return -EINVAL; diff --git a/drivers/pci/hotplug/rpaphp_slot.c b/drivers/pci/hotplug/rpaphp_slot.c index 6e2658ce300b..5282aa3e33c5 100644 --- a/drivers/pci/hotplug/rpaphp_slot.c +++ b/drivers/pci/hotplug/rpaphp_slot.c @@ -22,7 +22,6 @@ void dealloc_slot_struct(struct slot *slot) { kfree(slot->name); - kfree(slot->hotplug_slot); kfree(slot); } @@ -34,22 +33,16 @@ struct slot *alloc_slot_struct(struct device_node *dn, slot = kzalloc(sizeof(struct slot), GFP_KERNEL); if (!slot) goto error_nomem; - slot->hotplug_slot = kzalloc(sizeof(struct hotplug_slot), GFP_KERNEL); - if (!slot->hotplug_slot) - goto error_slot; slot->name = kstrdup(drc_name, GFP_KERNEL); if (!slot->name) - goto error_hpslot; + goto error_slot; slot->dn = dn; slot->index = drc_index; slot->power_domain = power_domain; - slot->hotplug_slot->private = slot; - slot->hotplug_slot->ops = &rpaphp_hotplug_slot_ops; + slot->hotplug_slot.ops = &rpaphp_hotplug_slot_ops; return (slot); -error_hpslot: - kfree(slot->hotplug_slot); error_slot: kfree(slot); error_nomem: @@ -70,7 +63,7 @@ static int is_registered(struct slot *slot) int rpaphp_deregister_slot(struct slot *slot) { int retval = 0; - struct hotplug_slot *php_slot = slot->hotplug_slot; + struct hotplug_slot *php_slot = &slot->hotplug_slot; dbg("%s - Entry: deregistering slot=%s\n", __func__, slot->name); @@ -86,7 +79,7 @@ EXPORT_SYMBOL_GPL(rpaphp_deregister_slot); int rpaphp_register_slot(struct slot *slot) { - struct hotplug_slot *php_slot = slot->hotplug_slot; + struct hotplug_slot *php_slot = &slot->hotplug_slot; struct device_node *child; u32 my_index; int retval; diff --git a/drivers/pci/hotplug/s390_pci_hpc.c b/drivers/pci/hotplug/s390_pci_hpc.c index d04634b0defe..30ee72268790 100644 --- a/drivers/pci/hotplug/s390_pci_hpc.c +++ b/drivers/pci/hotplug/s390_pci_hpc.c @@ -32,10 +32,15 @@ static int zpci_fn_configured(enum zpci_state state) */ struct slot { struct list_head slot_list; - struct hotplug_slot *hotplug_slot; + struct hotplug_slot hotplug_slot; struct zpci_dev *zdev; }; +static inline struct slot *to_slot(struct hotplug_slot *hotplug_slot) +{ + return container_of(hotplug_slot, struct slot, hotplug_slot); +} + static inline int slot_configure(struct slot *slot) { int ret = sclp_pci_configure(slot->zdev->fid); @@ -60,7 +65,7 @@ static inline int slot_deconfigure(struct slot *slot) static int enable_slot(struct hotplug_slot *hotplug_slot) { - struct slot *slot = hotplug_slot->private; + struct slot *slot = to_slot(hotplug_slot); int rc; if (slot->zdev->state != ZPCI_FN_STATE_STANDBY) @@ -88,7 +93,7 @@ out_deconfigure: static int disable_slot(struct hotplug_slot *hotplug_slot) { - struct slot *slot = hotplug_slot->private; + struct slot *slot = to_slot(hotplug_slot); struct pci_dev *pdev; int rc; @@ -110,7 +115,7 @@ static int disable_slot(struct hotplug_slot *hotplug_slot) static int get_power_status(struct hotplug_slot *hotplug_slot, u8 *value) { - struct slot *slot = hotplug_slot->private; + struct slot *slot = to_slot(hotplug_slot); switch (slot->zdev->state) { case ZPCI_FN_STATE_STANDBY: @@ -139,7 +144,6 @@ static const struct hotplug_slot_ops s390_hotplug_slot_ops = { int zpci_init_slot(struct zpci_dev *zdev) { - struct hotplug_slot *hotplug_slot; char name[SLOT_NAME_SIZE]; struct slot *slot; int rc; @@ -151,18 +155,11 @@ int zpci_init_slot(struct zpci_dev *zdev) if (!slot) goto error; - hotplug_slot = kzalloc(sizeof(*hotplug_slot), GFP_KERNEL); - if (!hotplug_slot) - goto error_hp; - hotplug_slot->private = slot; - - slot->hotplug_slot = hotplug_slot; slot->zdev = zdev; - - hotplug_slot->ops = &s390_hotplug_slot_ops; + slot->hotplug_slot.ops = &s390_hotplug_slot_ops; snprintf(name, SLOT_NAME_SIZE, "%08x", zdev->fid); - rc = pci_hp_register(slot->hotplug_slot, zdev->bus, + rc = pci_hp_register(&slot->hotplug_slot, zdev->bus, ZPCI_DEVFN, name); if (rc) goto error_reg; @@ -171,8 +168,6 @@ int zpci_init_slot(struct zpci_dev *zdev) return 0; error_reg: - kfree(hotplug_slot); -error_hp: kfree(slot); error: return -ENOMEM; @@ -187,8 +182,7 @@ void zpci_exit_slot(struct zpci_dev *zdev) if (slot->zdev != zdev) continue; list_del(&slot->slot_list); - pci_hp_deregister(slot->hotplug_slot); - kfree(slot->hotplug_slot); + pci_hp_deregister(&slot->hotplug_slot); kfree(slot); } } diff --git a/drivers/pci/hotplug/sgi_hotplug.c b/drivers/pci/hotplug/sgi_hotplug.c index e103826c83e3..231f5bdd3d2d 100644 --- a/drivers/pci/hotplug/sgi_hotplug.c +++ b/drivers/pci/hotplug/sgi_hotplug.c @@ -56,7 +56,7 @@ struct slot { int device_num; struct pci_bus *pci_bus; /* this struct for glue internal only */ - struct hotplug_slot *hotplug_slot; + struct hotplug_slot hotplug_slot; struct list_head hp_list; char physical_path[SN_SLOT_NAME_SIZE]; }; @@ -88,10 +88,15 @@ static const struct hotplug_slot_ops sn_hotplug_slot_ops = { static DEFINE_MUTEX(sn_hotplug_mutex); +static struct slot *to_slot(struct hotplug_slot *bss_hotplug_slot) +{ + return container_of(bss_hotplug_slot, struct slot, hotplug_slot); +} + static ssize_t path_show(struct pci_slot *pci_slot, char *buf) { int retval = -ENOENT; - struct slot *slot = pci_slot->hotplug->private; + struct slot *slot = to_slot(pci_slot->hotplug); if (!slot) return retval; @@ -156,7 +161,7 @@ static int sn_pci_bus_valid(struct pci_bus *pci_bus) return -EIO; } -static int sn_hp_slot_private_alloc(struct hotplug_slot *bss_hotplug_slot, +static int sn_hp_slot_private_alloc(struct hotplug_slot **bss_hotplug_slot, struct pci_bus *pci_bus, int device, char *name) { @@ -168,7 +173,6 @@ static int sn_hp_slot_private_alloc(struct hotplug_slot *bss_hotplug_slot, slot = kzalloc(sizeof(*slot), GFP_KERNEL); if (!slot) return -ENOMEM; - bss_hotplug_slot->private = slot; slot->device_num = device; slot->pci_bus = pci_bus; @@ -179,8 +183,8 @@ static int sn_hp_slot_private_alloc(struct hotplug_slot *bss_hotplug_slot, sn_generate_path(pci_bus, slot->physical_path); - slot->hotplug_slot = bss_hotplug_slot; list_add(&slot->hp_list, &sn_hp_list); + *bss_hotplug_slot = &slot->hotplug_slot; return 0; } @@ -192,10 +196,9 @@ static struct hotplug_slot *sn_hp_destroy(void) struct hotplug_slot *bss_hotplug_slot = NULL; list_for_each_entry(slot, &sn_hp_list, hp_list) { - bss_hotplug_slot = slot->hotplug_slot; + bss_hotplug_slot = &slot->hotplug_slot; pci_slot = bss_hotplug_slot->pci_slot; - list_del(&((struct slot *)bss_hotplug_slot->private)-> - hp_list); + list_del(&slot->hp_list); sysfs_remove_file(&pci_slot->kobj, &sn_slot_path_attr.attr); break; @@ -227,7 +230,7 @@ static void sn_bus_free_data(struct pci_dev *dev) static int sn_slot_enable(struct hotplug_slot *bss_hotplug_slot, int device_num, char **ssdt) { - struct slot *slot = bss_hotplug_slot->private; + struct slot *slot = to_slot(bss_hotplug_slot); struct pcibus_info *pcibus_info; struct pcibr_slot_enable_resp resp; int rc; @@ -267,7 +270,7 @@ static int sn_slot_enable(struct hotplug_slot *bss_hotplug_slot, static int sn_slot_disable(struct hotplug_slot *bss_hotplug_slot, int device_num, int action) { - struct slot *slot = bss_hotplug_slot->private; + struct slot *slot = to_slot(bss_hotplug_slot); struct pcibus_info *pcibus_info; struct pcibr_slot_disable_resp resp; int rc; @@ -323,7 +326,7 @@ static int sn_slot_disable(struct hotplug_slot *bss_hotplug_slot, */ static int enable_slot(struct hotplug_slot *bss_hotplug_slot) { - struct slot *slot = bss_hotplug_slot->private; + struct slot *slot = to_slot(bss_hotplug_slot); struct pci_bus *new_bus = NULL; struct pci_dev *dev; int num_funcs; @@ -469,7 +472,7 @@ static int enable_slot(struct hotplug_slot *bss_hotplug_slot) static int disable_slot(struct hotplug_slot *bss_hotplug_slot) { - struct slot *slot = bss_hotplug_slot->private; + struct slot *slot = to_slot(bss_hotplug_slot); struct pci_dev *dev, *temp; int rc; acpi_handle ssdt_hdl = NULL; @@ -571,7 +574,7 @@ static int disable_slot(struct hotplug_slot *bss_hotplug_slot) static inline int get_power_status(struct hotplug_slot *bss_hotplug_slot, u8 *value) { - struct slot *slot = bss_hotplug_slot->private; + struct slot *slot = to_slot(bss_hotplug_slot); struct pcibus_info *pcibus_info; u32 power; @@ -585,8 +588,7 @@ static inline int get_power_status(struct hotplug_slot *bss_hotplug_slot, static void sn_release_slot(struct hotplug_slot *bss_hotplug_slot) { - kfree(bss_hotplug_slot->private); - kfree(bss_hotplug_slot); + kfree(to_slot(bss_hotplug_slot)); } static int sn_hotplug_slot_register(struct pci_bus *pci_bus) @@ -606,14 +608,7 @@ static int sn_hotplug_slot_register(struct pci_bus *pci_bus) if (sn_pci_slot_valid(pci_bus, device) != 1) continue; - bss_hotplug_slot = kzalloc(sizeof(*bss_hotplug_slot), - GFP_KERNEL); - if (!bss_hotplug_slot) { - rc = -ENOMEM; - goto alloc_err; - } - - if (sn_hp_slot_private_alloc(bss_hotplug_slot, + if (sn_hp_slot_private_alloc(&bss_hotplug_slot, pci_bus, device, name)) { rc = -ENOMEM; goto alloc_err; @@ -628,7 +623,7 @@ static int sn_hotplug_slot_register(struct pci_bus *pci_bus) rc = sysfs_create_file(&pci_slot->kobj, &sn_slot_path_attr.attr); if (rc) - goto register_err; + goto alloc_err; } pci_dbg(pci_bus->self, "Registered bus with hotplug\n"); return rc; @@ -637,14 +632,11 @@ register_err: pci_dbg(pci_bus->self, "bus failed to register with err = %d\n", rc); -alloc_err: - if (rc == -ENOMEM) - pci_dbg(pci_bus->self, "Memory allocation error\n"); - /* destroy THIS element */ - if (bss_hotplug_slot) - sn_release_slot(bss_hotplug_slot); + sn_hp_destroy(); + sn_release_slot(bss_hotplug_slot); +alloc_err: /* destroy anything else on the list */ while ((bss_hotplug_slot = sn_hp_destroy())) { pci_hp_deregister(bss_hotplug_slot); diff --git a/drivers/pci/hotplug/shpchp.h b/drivers/pci/hotplug/shpchp.h index a7bb816e6f25..f7f13ee5d06e 100644 --- a/drivers/pci/hotplug/shpchp.h +++ b/drivers/pci/hotplug/shpchp.h @@ -73,7 +73,7 @@ struct slot { u8 pwr_save; struct controller *ctrl; const struct hpc_ops *hpc_ops; - struct hotplug_slot *hotplug_slot; + struct hotplug_slot hotplug_slot; struct list_head slot_list; struct delayed_work work; /* work for button event */ struct mutex lock; @@ -171,7 +171,7 @@ int shpc_init(struct controller *ctrl, struct pci_dev *pdev); static inline const char *slot_name(struct slot *slot) { - return hotplug_slot_name(slot->hotplug_slot); + return hotplug_slot_name(&slot->hotplug_slot); } struct ctrl_reg { @@ -209,7 +209,7 @@ enum ctrl_offsets { static inline struct slot *get_slot(struct hotplug_slot *hotplug_slot) { - return hotplug_slot->private; + return container_of(hotplug_slot, struct slot, hotplug_slot); } static inline struct slot *shpchp_find_slot(struct controller *ctrl, u8 device) diff --git a/drivers/pci/hotplug/shpchp_core.c b/drivers/pci/hotplug/shpchp_core.c index b7181b7e7b98..81a918d47895 100644 --- a/drivers/pci/hotplug/shpchp_core.c +++ b/drivers/pci/hotplug/shpchp_core.c @@ -76,12 +76,7 @@ static int init_slots(struct controller *ctrl) goto error; } - hotplug_slot = kzalloc(sizeof(*hotplug_slot), GFP_KERNEL); - if (!hotplug_slot) { - retval = -ENOMEM; - goto error_slot; - } - slot->hotplug_slot = hotplug_slot; + hotplug_slot = &slot->hotplug_slot; slot->hp_slot = i; slot->ctrl = ctrl; @@ -93,14 +88,13 @@ static int init_slots(struct controller *ctrl) slot->wq = alloc_workqueue("shpchp-%d", 0, 0, slot->number); if (!slot->wq) { retval = -ENOMEM; - goto error_hpslot; + goto error_slot; } mutex_init(&slot->lock); INIT_DELAYED_WORK(&slot->work, shpchp_queue_pushbutton_work); /* register this slot with the hotplug pci core */ - hotplug_slot->private = slot; snprintf(name, SLOT_NAME_SIZE, "%d", slot->number); hotplug_slot->ops = &shpchp_hotplug_slot_ops; @@ -108,7 +102,7 @@ static int init_slots(struct controller *ctrl) pci_domain_nr(ctrl->pci_dev->subordinate), slot->bus, slot->device, slot->hp_slot, slot->number, ctrl->slot_device_offset); - retval = pci_hp_register(slot->hotplug_slot, + retval = pci_hp_register(hotplug_slot, ctrl->pci_dev->subordinate, slot->device, name); if (retval) { ctrl_err(ctrl, "pci_hp_register failed with error %d\n", @@ -127,8 +121,6 @@ static int init_slots(struct controller *ctrl) return 0; error_slotwq: destroy_workqueue(slot->wq); -error_hpslot: - kfree(hotplug_slot); error_slot: kfree(slot); error: @@ -143,8 +135,7 @@ void cleanup_slots(struct controller *ctrl) list_del(&slot->slot_list); cancel_delayed_work(&slot->work); destroy_workqueue(slot->wq); - pci_hp_deregister(slot->hotplug_slot); - kfree(slot->hotplug_slot); + pci_hp_deregister(&slot->hotplug_slot); kfree(slot); } } diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index 019b037319e3..93ee2d5466f8 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -254,7 +254,7 @@ struct asus_wmi { int asus_hwmon_num_fans; int asus_hwmon_pwm; - struct hotplug_slot *hotplug_slot; + struct hotplug_slot hotplug_slot; struct mutex hotplug_lock; struct mutex wmi_lock; struct workqueue_struct *hotplug_workqueue; @@ -753,7 +753,7 @@ static void asus_rfkill_hotplug(struct asus_wmi *asus) if (asus->wlan.rfkill) rfkill_set_sw_state(asus->wlan.rfkill, blocked); - if (asus->hotplug_slot) { + if (asus->hotplug_slot.ops) { bus = pci_find_bus(0, 1); if (!bus) { pr_warn("Unable to find PCI bus 1?\n"); @@ -858,7 +858,8 @@ static void asus_unregister_rfkill_notifier(struct asus_wmi *asus, char *node) static int asus_get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value) { - struct asus_wmi *asus = hotplug_slot->private; + struct asus_wmi *asus = container_of(hotplug_slot, + struct asus_wmi, hotplug_slot); int result = asus_wmi_get_devstate_simple(asus, ASUS_WMI_DEVID_WLAN); if (result < 0) @@ -898,14 +899,9 @@ static int asus_setup_pci_hotplug(struct asus_wmi *asus) INIT_WORK(&asus->hotplug_work, asus_hotplug_work); - asus->hotplug_slot = kzalloc(sizeof(struct hotplug_slot), GFP_KERNEL); - if (!asus->hotplug_slot) - goto error_slot; + asus->hotplug_slot.ops = &asus_hotplug_slot_ops; - asus->hotplug_slot->private = asus; - asus->hotplug_slot->ops = &asus_hotplug_slot_ops; - - ret = pci_hp_register(asus->hotplug_slot, bus, 0, "asus-wifi"); + ret = pci_hp_register(&asus->hotplug_slot, bus, 0, "asus-wifi"); if (ret) { pr_err("Unable to register hotplug slot - %d\n", ret); goto error_register; @@ -914,9 +910,7 @@ static int asus_setup_pci_hotplug(struct asus_wmi *asus) return 0; error_register: - kfree(asus->hotplug_slot); - asus->hotplug_slot = NULL; -error_slot: + asus->hotplug_slot.ops = NULL; destroy_workqueue(asus->hotplug_workqueue); error_workqueue: return ret; @@ -1044,10 +1038,8 @@ static void asus_wmi_rfkill_exit(struct asus_wmi *asus) * asus_unregister_rfkill_notifier() */ asus_rfkill_hotplug(asus); - if (asus->hotplug_slot) { - pci_hp_deregister(asus->hotplug_slot); - kfree(asus->hotplug_slot); - } + if (asus->hotplug_slot.ops) + pci_hp_deregister(&asus->hotplug_slot); if (asus->hotplug_workqueue) destroy_workqueue(asus->hotplug_workqueue); diff --git a/drivers/platform/x86/eeepc-laptop.c b/drivers/platform/x86/eeepc-laptop.c index 028b20f82962..e6946a9beb5a 100644 --- a/drivers/platform/x86/eeepc-laptop.c +++ b/drivers/platform/x86/eeepc-laptop.c @@ -177,7 +177,7 @@ struct eeepc_laptop { struct rfkill *wwan3g_rfkill; struct rfkill *wimax_rfkill; - struct hotplug_slot *hotplug_slot; + struct hotplug_slot hotplug_slot; struct mutex hotplug_lock; struct led_classdev tpd_led; @@ -582,7 +582,7 @@ static void eeepc_rfkill_hotplug(struct eeepc_laptop *eeepc, acpi_handle handle) mutex_lock(&eeepc->hotplug_lock); pci_lock_rescan_remove(); - if (!eeepc->hotplug_slot) + if (!eeepc->hotplug_slot.ops) goto out_unlock; port = acpi_get_pci_dev(handle); @@ -715,8 +715,11 @@ static void eeepc_unregister_rfkill_notifier(struct eeepc_laptop *eeepc, static int eeepc_get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value) { - struct eeepc_laptop *eeepc = hotplug_slot->private; - int val = get_acpi(eeepc, CM_ASL_WLAN); + struct eeepc_laptop *eeepc; + int val; + + eeepc = container_of(hotplug_slot, struct eeepc_laptop, hotplug_slot); + val = get_acpi(eeepc, CM_ASL_WLAN); if (val == 1 || val == 0) *value = val; @@ -741,14 +744,9 @@ static int eeepc_setup_pci_hotplug(struct eeepc_laptop *eeepc) return -ENODEV; } - eeepc->hotplug_slot = kzalloc(sizeof(struct hotplug_slot), GFP_KERNEL); - if (!eeepc->hotplug_slot) - goto error_slot; + eeepc->hotplug_slot.ops = &eeepc_hotplug_slot_ops; - eeepc->hotplug_slot->private = eeepc; - eeepc->hotplug_slot->ops = &eeepc_hotplug_slot_ops; - - ret = pci_hp_register(eeepc->hotplug_slot, bus, 0, "eeepc-wifi"); + ret = pci_hp_register(&eeepc->hotplug_slot, bus, 0, "eeepc-wifi"); if (ret) { pr_err("Unable to register hotplug slot - %d\n", ret); goto error_register; @@ -757,9 +755,7 @@ static int eeepc_setup_pci_hotplug(struct eeepc_laptop *eeepc) return 0; error_register: - kfree(eeepc->hotplug_slot); - eeepc->hotplug_slot = NULL; -error_slot: + eeepc->hotplug_slot.ops = NULL; return ret; } @@ -820,10 +816,8 @@ static void eeepc_rfkill_exit(struct eeepc_laptop *eeepc) eeepc->wlan_rfkill = NULL; } - if (eeepc->hotplug_slot) { - pci_hp_deregister(eeepc->hotplug_slot); - kfree(eeepc->hotplug_slot); - } + if (eeepc->hotplug_slot.ops) + pci_hp_deregister(&eeepc->hotplug_slot); if (eeepc->bluetooth_rfkill) { rfkill_unregister(eeepc->bluetooth_rfkill); diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index 6f07a4e1de8d..7acc9f91e72b 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -50,14 +50,11 @@ struct hotplug_slot_ops { /** * struct hotplug_slot - used to register a physical slot with the hotplug pci core * @ops: pointer to the &struct hotplug_slot_ops to be used for this slot - * @private: used by the hotplug pci controller driver to store whatever it - * needs. * @owner: The module owner of this structure * @mod_name: The module name (KBUILD_MODNAME) of this structure */ struct hotplug_slot { const struct hotplug_slot_ops *ops; - void *private; /* Variables below this are for use only by the hotplug pci core. */ struct list_head slot_list; -- cgit v1.2.3 From 14d73416792afa84f6a7245ee474d2432069da56 Mon Sep 17 00:00:00 2001 From: Li RongQing Date: Mon, 17 Sep 2018 18:46:55 +0800 Subject: veth: rename pcpu_vstats as pcpu_lstats struct pcpu_vstats and pcpu_lstats have same members and usage, and pcpu_lstats is used in many files, so rename pcpu_vstats as pcpu_lstats to reduce duplicate definition Signed-off-by: Zhang Yu Signed-off-by: Li RongQing Signed-off-by: David S. Miller --- drivers/net/veth.c | 22 ++++++++-------------- include/linux/netdevice.h | 1 - 2 files changed, 8 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 8fc64b67f01e..224c56a4e2b1 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -37,12 +37,6 @@ #define VETH_XDP_TX BIT(0) #define VETH_XDP_REDIR BIT(1) -struct pcpu_vstats { - u64 packets; - u64 bytes; - struct u64_stats_sync syncp; -}; - struct veth_rq { struct napi_struct xdp_napi; struct net_device *dev; @@ -217,7 +211,7 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev) skb_tx_timestamp(skb); if (likely(veth_forward_skb(rcv, skb, rq, rcv_xdp) == NET_RX_SUCCESS)) { - struct pcpu_vstats *stats = this_cpu_ptr(dev->vstats); + struct pcpu_lstats *stats = this_cpu_ptr(dev->lstats); u64_stats_update_begin(&stats->syncp); stats->bytes += length; @@ -236,7 +230,7 @@ drop: return NETDEV_TX_OK; } -static u64 veth_stats_one(struct pcpu_vstats *result, struct net_device *dev) +static u64 veth_stats_one(struct pcpu_lstats *result, struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); int cpu; @@ -244,7 +238,7 @@ static u64 veth_stats_one(struct pcpu_vstats *result, struct net_device *dev) result->packets = 0; result->bytes = 0; for_each_possible_cpu(cpu) { - struct pcpu_vstats *stats = per_cpu_ptr(dev->vstats, cpu); + struct pcpu_lstats *stats = per_cpu_ptr(dev->lstats, cpu); u64 packets, bytes; unsigned int start; @@ -264,7 +258,7 @@ static void veth_get_stats64(struct net_device *dev, { struct veth_priv *priv = netdev_priv(dev); struct net_device *peer; - struct pcpu_vstats one; + struct pcpu_lstats one; tot->tx_dropped = veth_stats_one(&one, dev); tot->tx_bytes = one.bytes; @@ -830,13 +824,13 @@ static int veth_dev_init(struct net_device *dev) { int err; - dev->vstats = netdev_alloc_pcpu_stats(struct pcpu_vstats); - if (!dev->vstats) + dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats); + if (!dev->lstats) return -ENOMEM; err = veth_alloc_queues(dev); if (err) { - free_percpu(dev->vstats); + free_percpu(dev->lstats); return err; } @@ -846,7 +840,7 @@ static int veth_dev_init(struct net_device *dev) static void veth_dev_free(struct net_device *dev) { veth_free_queues(dev); - free_percpu(dev->vstats); + free_percpu(dev->lstats); } #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index baed5d5088c5..1cbbf77a685f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2000,7 +2000,6 @@ struct net_device { struct pcpu_lstats __percpu *lstats; struct pcpu_sw_netstats __percpu *tstats; struct pcpu_dstats __percpu *dstats; - struct pcpu_vstats __percpu *vstats; }; #if IS_ENABLED(CONFIG_GARP) -- cgit v1.2.3 From efc463adbccf709c5dbaf6cfbf84b7e94b62810a Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 16 Apr 2018 14:18:26 -0500 Subject: signal: Simplify tracehook_report_syscall_exit Replace user_single_step_siginfo with user_single_step_report that allocates siginfo structure on the stack and sends it. This allows tracehook_report_syscall_exit to become a simple if statement that calls user_single_step_report or ptrace_report_syscall depending on the value of step. Update the default helper function now called user_single_step_report to explicitly set si_code to SI_USER and to set si_uid and si_pid to 0. The default helper has always been doing this (using memset) but it was far from obvious. The powerpc helper can now just call force_sig_fault. The x86 helper can now just call send_sigtrap. Unfortunately the default implementation of user_single_step_report can not use force_sig_fault as it does not use a SIGTRAP si_code. So it has to carefully setup the siginfo and use use force_sig_info. The net result is code that is easier to understand and simpler to maintain. Ref: 85ec7fd9f8e5 ("ptrace: introduce user_single_step_siginfo() helper") Reviewed-by: Thomas Gleixner Signed-off-by: "Eric W. Biederman" --- arch/powerpc/include/asm/ptrace.h | 2 +- arch/powerpc/kernel/traps.c | 7 ++----- arch/x86/include/asm/ptrace.h | 2 +- arch/x86/kernel/ptrace.c | 11 +++++------ include/linux/ptrace.h | 17 +++++++++++------ include/linux/tracehook.h | 13 ++++--------- 6 files changed, 24 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h index 447cbd1bee99..5b480e1d5909 100644 --- a/arch/powerpc/include/asm/ptrace.h +++ b/arch/powerpc/include/asm/ptrace.h @@ -149,7 +149,7 @@ do { \ #define arch_has_single_step() (1) #define arch_has_block_step() (!cpu_has_feature(CPU_FTR_601)) -#define ARCH_HAS_USER_SINGLE_STEP_INFO +#define ARCH_HAS_USER_SINGLE_STEP_REPORT /* * kprobe-based event tracer support diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index c85adb858271..f651fa91cdc9 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -307,12 +307,9 @@ void die(const char *str, struct pt_regs *regs, long err) } NOKPROBE_SYMBOL(die); -void user_single_step_siginfo(struct task_struct *tsk, - struct pt_regs *regs, siginfo_t *info) +void user_single_step_report(struct pt_regs *regs) { - info->si_signo = SIGTRAP; - info->si_code = TRAP_TRACE; - info->si_addr = (void __user *)regs->nip; + force_sig_fault(SIGTRAP, TRAP_TRACE, (void __user *)regs->nip, current); } static void show_signal_msg(int signr, struct pt_regs *regs, int code, diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 6de1fd3d0097..e353f08b7fe2 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -263,7 +263,7 @@ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, #define arch_has_block_step() (boot_cpu_data.x86 >= 6) #endif -#define ARCH_HAS_USER_SINGLE_STEP_INFO +#define ARCH_HAS_USER_SINGLE_STEP_REPORT /* * When hitting ptrace_stop(), we cannot return using SYSRET because diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index e2ee403865eb..94bd6e89129a 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -1382,12 +1382,6 @@ static void fill_sigtrap_info(struct task_struct *tsk, info->si_addr = user_mode(regs) ? (void __user *)regs->ip : NULL; } -void user_single_step_siginfo(struct task_struct *tsk, - struct pt_regs *regs, - struct siginfo *info) -{ - fill_sigtrap_info(tsk, regs, 0, TRAP_BRKPT, info); -} void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, int error_code, int si_code) @@ -1399,3 +1393,8 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, /* Send us the fake SIGTRAP */ force_sig_info(SIGTRAP, &info, tsk); } + +void user_single_step_report(struct pt_regs *regs) +{ + send_sigtrap(current, regs, 0, TRAP_BRKPT); +} diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 4f36431c380b..1de2235511c8 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -336,14 +336,19 @@ static inline void user_enable_block_step(struct task_struct *task) extern void user_enable_block_step(struct task_struct *); #endif /* arch_has_block_step */ -#ifdef ARCH_HAS_USER_SINGLE_STEP_INFO -extern void user_single_step_siginfo(struct task_struct *tsk, - struct pt_regs *regs, siginfo_t *info); +#ifdef ARCH_HAS_USER_SINGLE_STEP_REPORT +extern void user_single_step_report(struct pt_regs *regs); #else -static inline void user_single_step_siginfo(struct task_struct *tsk, - struct pt_regs *regs, siginfo_t *info) +static inline void user_single_step_report(struct pt_regs *regs) { - info->si_signo = SIGTRAP; + siginfo_t info; + clear_siginfo(&info); + info.si_signo = SIGTRAP; + info.si_errno = 0; + info.si_code = SI_USER; + info.si_pid = 0; + info.si_uid = 0; + force_sig_info(info.si_signo, &info, current); } #endif diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 05589a3e37f4..40b0b4c1bf7b 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -123,15 +123,10 @@ static inline __must_check int tracehook_report_syscall_entry( */ static inline void tracehook_report_syscall_exit(struct pt_regs *regs, int step) { - if (step) { - siginfo_t info; - clear_siginfo(&info); - user_single_step_siginfo(current, regs, &info); - force_sig_info(SIGTRAP, &info, current); - return; - } - - ptrace_report_syscall(regs); + if (step) + user_single_step_report(regs); + else + ptrace_report_syscall(regs); } /** -- cgit v1.2.3 From 2dfd184abd38fd72d80715fa8b00c9de78490200 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Tue, 18 Sep 2018 16:20:18 -0400 Subject: flow_dissector: fix build failure without CONFIG_NET If boolean CONFIG_BPF_SYSCALL is enabled, kernel/bpf/syscall.c will call flow_dissector functions from net/core/flow_dissector.c. This causes this build failure if CONFIG_NET is disabled: kernel/bpf/syscall.o: In function `__x64_sys_bpf': syscall.c:(.text+0x3278): undefined reference to `skb_flow_dissector_bpf_prog_attach' syscall.c:(.text+0x3310): undefined reference to `skb_flow_dissector_bpf_prog_detach' kernel/bpf/syscall.o:(.rodata+0x3f0): undefined reference to `flow_dissector_prog_ops' kernel/bpf/verifier.o:(.rodata+0x250): undefined reference to `flow_dissector_verifier_ops' Analogous to other optional BPF program types in syscall.c, add stubs if the relevant functions are not compiled and move the BPF_PROG_TYPE definition in the #ifdef CONFIG_NET block. Fixes: d58e468b1112 ("flow_dissector: implements flow dissector BPF hook") Reported-by: Randy Dunlap Signed-off-by: Willem de Bruijn Acked-by: Randy Dunlap # build-tested Acked-by: Yonghong Song Signed-off-by: Daniel Borkmann --- include/linux/bpf_types.h | 2 +- include/linux/skbuff.h | 13 +++++++++++++ 2 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 22083712dd18..c9bd6fb765b0 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -16,6 +16,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_SEG6LOCAL, lwt_seg6local) BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops) BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb) BPF_PROG_TYPE(BPF_PROG_TYPE_SK_MSG, sk_msg) +BPF_PROG_TYPE(BPF_PROG_TYPE_FLOW_DISSECTOR, flow_dissector) #endif #ifdef CONFIG_BPF_EVENTS BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe) @@ -32,7 +33,6 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2) #ifdef CONFIG_INET BPF_PROG_TYPE(BPF_PROG_TYPE_SK_REUSEPORT, sk_reuseport) #endif -BPF_PROG_TYPE(BPF_PROG_TYPE_FLOW_DISSECTOR, flow_dissector) BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, percpu_array_map_ops) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ce0e863f02a2..76be85ea392a 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1194,10 +1194,23 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector, const struct flow_dissector_key *key, unsigned int key_count); +#ifdef CONFIG_NET int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog); int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr); +#else +static inline int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr, + struct bpf_prog *prog) +{ + return -EOPNOTSUPP; +} + +static inline int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr) +{ + return -EOPNOTSUPP; +} +#endif bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector *flow_dissector, -- cgit v1.2.3 From 53dd9dce6979bc54d64a3a09a2fb20187a025be7 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Thu, 13 Sep 2018 15:16:22 -0500 Subject: libfdt: Ensure INT_MAX is defined in libfdt_env.h The next update of libfdt has a new dependency on INT_MAX. Update the instances of libfdt_env.h in the kernel to either include the necessary header with the definition or define it locally. Cc: Russell King Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: linux-arm-kernel@lists.infradead.org Cc: linuxppc-dev@lists.ozlabs.org Signed-off-by: Rob Herring --- arch/arm/boot/compressed/libfdt_env.h | 2 ++ arch/powerpc/boot/libfdt_env.h | 2 ++ include/linux/libfdt_env.h | 1 + 3 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/arch/arm/boot/compressed/libfdt_env.h b/arch/arm/boot/compressed/libfdt_env.h index 07437816e098..b36c0289a308 100644 --- a/arch/arm/boot/compressed/libfdt_env.h +++ b/arch/arm/boot/compressed/libfdt_env.h @@ -6,6 +6,8 @@ #include #include +#define INT_MAX ((int)(~0U>>1)) + typedef __be16 fdt16_t; typedef __be32 fdt32_t; typedef __be64 fdt64_t; diff --git a/arch/powerpc/boot/libfdt_env.h b/arch/powerpc/boot/libfdt_env.h index 2a0c8b1bf147..2abc8e83b95e 100644 --- a/arch/powerpc/boot/libfdt_env.h +++ b/arch/powerpc/boot/libfdt_env.h @@ -5,6 +5,8 @@ #include #include +#define INT_MAX ((int)(~0U>>1)) + #include "of.h" typedef unsigned long uintptr_t; diff --git a/include/linux/libfdt_env.h b/include/linux/libfdt_env.h index c6ac1fe7ec68..edb0f0c30904 100644 --- a/include/linux/libfdt_env.h +++ b/include/linux/libfdt_env.h @@ -2,6 +2,7 @@ #ifndef LIBFDT_ENV_H #define LIBFDT_ENV_H +#include /* For INT_MAX */ #include #include -- cgit v1.2.3 From 16caf1fa37db4722d8d8c7bc26177279949d75a6 Mon Sep 17 00:00:00 2001 From: Loic Poulain Date: Tue, 4 Sep 2018 17:18:55 +0200 Subject: usb: chipidea: Add dynamic pinctrl selection Some hardware implementations require to configure pins differently according to the USB role (host/device), this can be an update of the pins routing or a simple GPIO value change. This patch introduces new optional "host" and "device" pinctrls. If these pinctrls are defined by the device, they are respectively selected on host/device role start. If a default pinctrl exist, it is restored on host/device role stop. Signed-off-by: Loic Poulain Signed-off-by: Peter Chen --- drivers/usb/chipidea/core.c | 19 +++++++++++++++++++ drivers/usb/chipidea/host.c | 9 +++++++++ drivers/usb/chipidea/udc.c | 9 +++++++++ include/linux/usb/chipidea.h | 6 ++++++ 4 files changed, 43 insertions(+) (limited to 'include/linux') diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c index 85fc6db48e44..7bfcbb23c2a4 100644 --- a/drivers/usb/chipidea/core.c +++ b/drivers/usb/chipidea/core.c @@ -53,6 +53,7 @@ #include #include #include +#include #include #include #include @@ -723,6 +724,24 @@ static int ci_get_platdata(struct device *dev, else cable->connected = false; } + + platdata->pctl = devm_pinctrl_get(dev); + if (!IS_ERR(platdata->pctl)) { + struct pinctrl_state *p; + + p = pinctrl_lookup_state(platdata->pctl, "default"); + if (!IS_ERR(p)) + platdata->pins_default = p; + + p = pinctrl_lookup_state(platdata->pctl, "host"); + if (!IS_ERR(p)) + platdata->pins_host = p; + + p = pinctrl_lookup_state(platdata->pctl, "device"); + if (!IS_ERR(p)) + platdata->pins_device = p; + } + return 0; } diff --git a/drivers/usb/chipidea/host.c b/drivers/usb/chipidea/host.c index 4638d9b066be..d858a82c4f44 100644 --- a/drivers/usb/chipidea/host.c +++ b/drivers/usb/chipidea/host.c @@ -13,6 +13,7 @@ #include #include #include +#include #include "../host/ehci.h" @@ -153,6 +154,10 @@ static int host_start(struct ci_hdrc *ci) } } + if (ci->platdata->pins_host) + pinctrl_select_state(ci->platdata->pctl, + ci->platdata->pins_host); + ret = usb_add_hcd(hcd, 0, 0); if (ret) { goto disable_reg; @@ -197,6 +202,10 @@ static void host_stop(struct ci_hdrc *ci) } ci->hcd = NULL; ci->otg.host = NULL; + + if (ci->platdata->pins_host && ci->platdata->pins_default) + pinctrl_select_state(ci->platdata->pctl, + ci->platdata->pins_default); } diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c index 9852ec5e6e01..829e947cabf5 100644 --- a/drivers/usb/chipidea/udc.c +++ b/drivers/usb/chipidea/udc.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -1965,6 +1966,10 @@ void ci_hdrc_gadget_destroy(struct ci_hdrc *ci) static int udc_id_switch_for_device(struct ci_hdrc *ci) { + if (ci->platdata->pins_device) + pinctrl_select_state(ci->platdata->pctl, + ci->platdata->pins_device); + if (ci->is_otg) /* Clear and enable BSV irq */ hw_write_otgsc(ci, OTGSC_BSVIS | OTGSC_BSVIE, @@ -1983,6 +1988,10 @@ static void udc_id_switch_for_host(struct ci_hdrc *ci) hw_write_otgsc(ci, OTGSC_BSVIE | OTGSC_BSVIS, OTGSC_BSVIS); ci->vbus_active = 0; + + if (ci->platdata->pins_device && ci->platdata->pins_default) + pinctrl_select_state(ci->platdata->pctl, + ci->platdata->pins_default); } /** diff --git a/include/linux/usb/chipidea.h b/include/linux/usb/chipidea.h index 07f99362bc90..63758c399e4e 100644 --- a/include/linux/usb/chipidea.h +++ b/include/linux/usb/chipidea.h @@ -77,6 +77,12 @@ struct ci_hdrc_platform_data { struct ci_hdrc_cable vbus_extcon; struct ci_hdrc_cable id_extcon; u32 phy_clkgate_delay_us; + + /* pins */ + struct pinctrl *pctl; + struct pinctrl_state *pins_default; + struct pinctrl_state *pins_host; + struct pinctrl_state *pins_device; }; /* Default offset of capability registers */ -- cgit v1.2.3 From 457b42f0aa1c397745ada6083bf81b9479ab19fe Mon Sep 17 00:00:00 2001 From: Liu Xiang Date: Sun, 22 Jul 2018 21:33:56 +0800 Subject: power: supply: bq27xxx: Add support for BQ27411 According to the datasheet, bq27411 is similar to bq27421. Signed-off-by: Liu Xiang Reviewed-by: Andrew F. Davis Signed-off-by: Sebastian Reichel --- Documentation/devicetree/bindings/power/supply/bq27xxx.txt | 1 + drivers/power/supply/bq27xxx_battery.c | 9 +++++++++ drivers/power/supply/bq27xxx_battery_i2c.c | 2 ++ include/linux/power/bq27xxx_battery.h | 1 + 4 files changed, 13 insertions(+) (limited to 'include/linux') diff --git a/Documentation/devicetree/bindings/power/supply/bq27xxx.txt b/Documentation/devicetree/bindings/power/supply/bq27xxx.txt index 37994fdb18ca..4fa8e08df2b6 100644 --- a/Documentation/devicetree/bindings/power/supply/bq27xxx.txt +++ b/Documentation/devicetree/bindings/power/supply/bq27xxx.txt @@ -23,6 +23,7 @@ Required properties: * "ti,bq27546" - BQ27546 * "ti,bq27742" - BQ27742 * "ti,bq27545" - BQ27545 + * "ti,bq27411" - BQ27411 * "ti,bq27421" - BQ27421 * "ti,bq27425" - BQ27425 * "ti,bq27426" - BQ27426 diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c index f022e1b550df..6dbbe95844a3 100644 --- a/drivers/power/supply/bq27xxx_battery.c +++ b/drivers/power/supply/bq27xxx_battery.c @@ -432,6 +432,7 @@ static u8 [BQ27XXX_REG_AP] = 0x18, BQ27XXX_DM_REG_ROWS, }; +#define bq27411_regs bq27421_regs #define bq27425_regs bq27421_regs #define bq27426_regs bq27421_regs #define bq27441_regs bq27421_regs @@ -665,6 +666,7 @@ static enum power_supply_property bq27421_props[] = { POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN, POWER_SUPPLY_PROP_MANUFACTURER, }; +#define bq27411_props bq27421_props #define bq27425_props bq27421_props #define bq27426_props bq27421_props #define bq27441_props bq27421_props @@ -725,6 +727,12 @@ static struct bq27xxx_dm_reg bq27545_dm_regs[] = { #define bq27545_dm_regs 0 #endif +static struct bq27xxx_dm_reg bq27411_dm_regs[] = { + [BQ27XXX_DM_DESIGN_CAPACITY] = { 82, 10, 2, 0, 32767 }, + [BQ27XXX_DM_DESIGN_ENERGY] = { 82, 12, 2, 0, 32767 }, + [BQ27XXX_DM_TERMINATE_VOLTAGE] = { 82, 16, 2, 2800, 3700 }, +}; + static struct bq27xxx_dm_reg bq27421_dm_regs[] = { [BQ27XXX_DM_DESIGN_CAPACITY] = { 82, 10, 2, 0, 8000 }, [BQ27XXX_DM_DESIGN_ENERGY] = { 82, 12, 2, 0, 32767 }, @@ -802,6 +810,7 @@ static struct { [BQ27546] = BQ27XXX_DATA(bq27546, 0 , BQ27XXX_O_OTDC), [BQ27742] = BQ27XXX_DATA(bq27742, 0 , BQ27XXX_O_OTDC), [BQ27545] = BQ27XXX_DATA(bq27545, 0x04143672, BQ27XXX_O_OTDC), + [BQ27411] = BQ27XXX_DATA(bq27411, 0x80008000, BQ27XXX_O_UTOT | BQ27XXX_O_CFGUP | BQ27XXX_O_RAM), [BQ27421] = BQ27XXX_DATA(bq27421, 0x80008000, BQ27XXX_O_UTOT | BQ27XXX_O_CFGUP | BQ27XXX_O_RAM), [BQ27425] = BQ27XXX_DATA(bq27425, 0x04143672, BQ27XXX_O_UTOT | BQ27XXX_O_CFGUP), [BQ27426] = BQ27XXX_DATA(bq27426, 0x80008000, BQ27XXX_O_UTOT | BQ27XXX_O_CFGUP | BQ27XXX_O_RAM), diff --git a/drivers/power/supply/bq27xxx_battery_i2c.c b/drivers/power/supply/bq27xxx_battery_i2c.c index 40069128ad44..2677c38a8a42 100644 --- a/drivers/power/supply/bq27xxx_battery_i2c.c +++ b/drivers/power/supply/bq27xxx_battery_i2c.c @@ -247,6 +247,7 @@ static const struct i2c_device_id bq27xxx_i2c_id_table[] = { { "bq27546", BQ27546 }, { "bq27742", BQ27742 }, { "bq27545", BQ27545 }, + { "bq27411", BQ27411 }, { "bq27421", BQ27421 }, { "bq27425", BQ27425 }, { "bq27426", BQ27426 }, @@ -279,6 +280,7 @@ static const struct of_device_id bq27xxx_battery_i2c_of_match_table[] = { { .compatible = "ti,bq27546" }, { .compatible = "ti,bq27742" }, { .compatible = "ti,bq27545" }, + { .compatible = "ti,bq27411" }, { .compatible = "ti,bq27421" }, { .compatible = "ti,bq27425" }, { .compatible = "ti,bq27426" }, diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index d6355f49fbae..507c5e214c42 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -24,6 +24,7 @@ enum bq27xxx_chip { BQ27546, BQ27742, BQ27545, /* bq27545 */ + BQ27411, BQ27421, /* bq27421, bq27441, bq27621 */ BQ27425, BQ27426, -- cgit v1.2.3 From bd93227897007bac09c44fe67626035303905900 Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Wed, 22 Aug 2018 22:43:00 +0200 Subject: USB: EHCI: ehci-mv: remove private_init It's unused. Signed-off-by: Lubomir Rintel Acked-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/ehci-mv.c | 4 ---- include/linux/platform_data/mv_usb.h | 1 - 2 files changed, 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/host/ehci-mv.c b/drivers/usb/host/ehci-mv.c index 77a4ab1dcd07..705d1b43b2dd 100644 --- a/drivers/usb/host/ehci-mv.c +++ b/drivers/usb/host/ehci-mv.c @@ -203,9 +203,6 @@ static int mv_ehci_probe(struct platform_device *pdev) device_wakeup_enable(hcd->self.controller); } - if (pdata->private_init) - pdata->private_init(ehci_mv->op_regs, ehci_mv->phy_regs); - dev_info(&pdev->dev, "successful find EHCI device with regs 0x%p irq %d" " working in %s mode\n", hcd->regs, hcd->irq, @@ -260,7 +257,6 @@ static const struct platform_device_id ehci_id_table[] = { static void mv_ehci_shutdown(struct platform_device *pdev) { struct usb_hcd *hcd = platform_get_drvdata(pdev); - struct ehci_hcd_mv *ehci_mv = hcd_to_ehci_hcd_mv(hcd); if (!hcd->rh_registered) return; diff --git a/include/linux/platform_data/mv_usb.h b/include/linux/platform_data/mv_usb.h index 98b7925f1a2d..c0f624aca81c 100644 --- a/include/linux/platform_data/mv_usb.h +++ b/include/linux/platform_data/mv_usb.h @@ -48,6 +48,5 @@ struct mv_usb_platform_data { int (*phy_init)(void __iomem *regbase); void (*phy_deinit)(void __iomem *regbase); int (*set_vbus)(unsigned int vbus); - int (*private_init)(void __iomem *opregs, void __iomem *phyregs); }; #endif -- cgit v1.2.3 From cd7753d371388e712e3ee52b693459f9b71aaac2 Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Thu, 20 Sep 2018 14:23:40 +0300 Subject: drivers: base: Helpers for adding device connection descriptions Introducing helpers for adding and removing multiple device connection descriptions at once. Acked-by: Hans de Goede Tested-by: Hans de Goede Signed-off-by: Heikki Krogerus Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 8f882549edee..3f1066a9e1c3 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -773,6 +773,30 @@ struct device *device_connection_find(struct device *dev, const char *con_id); void device_connection_add(struct device_connection *con); void device_connection_remove(struct device_connection *con); +/** + * device_connections_add - Add multiple device connections at once + * @cons: Zero terminated array of device connection descriptors + */ +static inline void device_connections_add(struct device_connection *cons) +{ + struct device_connection *c; + + for (c = cons; c->endpoint[0]; c++) + device_connection_add(c); +} + +/** + * device_connections_remove - Remove multiple device connections at once + * @cons: Zero terminated array of device connection descriptors + */ +static inline void device_connections_remove(struct device_connection *cons) +{ + struct device_connection *c; + + for (c = cons; c->endpoint[0]; c++) + device_connection_remove(c); +} + /** * enum device_link_state - Device link states. * @DL_STATE_NONE: The presence of the drivers is not being tracked. -- cgit v1.2.3 From e9158b35ef9afb3bf24e0404c8fd4cd723eafa5b Mon Sep 17 00:00:00 2001 From: Horia Geantă Date: Wed, 12 Sep 2018 11:59:26 +0300 Subject: bus: fsl-mc: add support for dpseci device type MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Horia Geantă Acked-by: Laurentiu Tudor Signed-off-by: Herbert Xu --- drivers/bus/fsl-mc/fsl-mc-bus.c | 5 +++++ include/linux/fsl/mc.h | 6 ++++++ 2 files changed, 11 insertions(+) (limited to 'include/linux') diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c index 5d8266c6571f..4552b06fe601 100644 --- a/drivers/bus/fsl-mc/fsl-mc-bus.c +++ b/drivers/bus/fsl-mc/fsl-mc-bus.c @@ -188,6 +188,10 @@ struct device_type fsl_mc_bus_dprtc_type = { .name = "fsl_mc_bus_dprtc" }; +struct device_type fsl_mc_bus_dpseci_type = { + .name = "fsl_mc_bus_dpseci" +}; + static struct device_type *fsl_mc_get_device_type(const char *type) { static const struct { @@ -203,6 +207,7 @@ static struct device_type *fsl_mc_get_device_type(const char *type) { &fsl_mc_bus_dpmcp_type, "dpmcp" }, { &fsl_mc_bus_dpmac_type, "dpmac" }, { &fsl_mc_bus_dprtc_type, "dprtc" }, + { &fsl_mc_bus_dpseci_type, "dpseci" }, { NULL, NULL } }; int i; diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index f27cb14088a4..5160f06ffbac 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -405,6 +405,7 @@ extern struct device_type fsl_mc_bus_dpcon_type; extern struct device_type fsl_mc_bus_dpmcp_type; extern struct device_type fsl_mc_bus_dpmac_type; extern struct device_type fsl_mc_bus_dprtc_type; +extern struct device_type fsl_mc_bus_dpseci_type; static inline bool is_fsl_mc_bus_dprc(const struct fsl_mc_device *mc_dev) { @@ -451,6 +452,11 @@ static inline bool is_fsl_mc_bus_dprtc(const struct fsl_mc_device *mc_dev) return mc_dev->dev.type == &fsl_mc_bus_dprtc_type; } +static inline bool is_fsl_mc_bus_dpseci(const struct fsl_mc_device *mc_dev) +{ + return mc_dev->dev.type == &fsl_mc_bus_dpseci_type; +} + /* * Data Path Buffer Pool (DPBP) API * Contains initialization APIs and runtime control APIs for DPBP -- cgit v1.2.3 From c785896b21dd8e156326ff660050b0074d3431df Mon Sep 17 00:00:00 2001 From: Stefan Agner Date: Sat, 15 Sep 2018 21:38:24 -0700 Subject: cpufeature: avoid warning when compiling with clang The table id (second) argument to MODULE_DEVICE_TABLE is often referenced otherwise. This is not the case for CPU features. This leads to warnings when building the kernel with Clang: arch/arm/crypto/aes-ce-glue.c:450:1: warning: variable 'cpu_feature_match_AES' is not needed and will not be emitted [-Wunneeded-internal-declaration] module_cpu_feature_match(AES, aes_init); ^ Avoid warnings by using __maybe_unused, similar to commit 1f318a8bafcf ("modules: mark __inittest/__exittest as __maybe_unused"). Fixes: 67bad2fdb754 ("cpu: add generic support for CPU feature based module autoloading") Signed-off-by: Stefan Agner Acked-by: Ard Biesheuvel Signed-off-by: Herbert Xu --- include/linux/cpufeature.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpufeature.h b/include/linux/cpufeature.h index 986c06c88d81..84d3c81b5978 100644 --- a/include/linux/cpufeature.h +++ b/include/linux/cpufeature.h @@ -45,7 +45,7 @@ * 'asm/cpufeature.h' of your favorite architecture. */ #define module_cpu_feature_match(x, __initfunc) \ -static struct cpu_feature const cpu_feature_match_ ## x[] = \ +static struct cpu_feature const __maybe_unused cpu_feature_match_ ## x[] = \ { { .feature = cpu_feature(x) }, { } }; \ MODULE_DEVICE_TABLE(cpu, cpu_feature_match_ ## x); \ \ -- cgit v1.2.3 From 5d773ff41a7cdf0ef6cc6647435d59f0cf53e7b1 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Mon, 17 Sep 2018 13:30:46 +0300 Subject: net/mlx5: Rename incorrect naming in IFC file Remove a trailing underscore from the multicast/unicast names. Signed-off-by: Mark Bloch Reviewed-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/qp.c | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/en_common.c | 2 +- include/linux/mlx5/mlx5_ifc.h | 4 ++-- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 6cba2a02d11b..daf1eb84cd31 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -1279,7 +1279,7 @@ static int create_raw_packet_qp_tir(struct mlx5_ib_dev *dev, if (dev->rep) MLX5_SET(tirc, tirc, self_lb_block, - MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST_); + MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST); err = mlx5_core_create_tir(dev->mdev, in, inlen, &rq->tirn); @@ -1582,7 +1582,7 @@ static int create_rss_raw_qp_tir(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, create_tir: if (dev->rep) MLX5_SET(tirc, tirc, self_lb_block, - MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST_); + MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST); err = mlx5_core_create_tir(dev->mdev, in, inlen, &qp->rss_qp.tirn); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c index db3278cc052b..3078491cc0d0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c @@ -153,7 +153,7 @@ int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb) if (enable_uc_lb) MLX5_SET(modify_tir_in, in, ctx.self_lb_block, - MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST_); + MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST); MLX5_SET(modify_tir_in, in, bitmask.self_lb_en, 1); diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 3a4a2e0567e9..4c7a1d25d73b 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -2559,8 +2559,8 @@ enum { }; enum { - MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST_ = 0x1, - MLX5_TIRC_SELF_LB_BLOCK_BLOCK_MULTICAST_ = 0x2, + MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST = 0x1, + MLX5_TIRC_SELF_LB_BLOCK_BLOCK_MULTICAST = 0x2, }; struct mlx5_ifc_tirc_bits { -- cgit v1.2.3 From 9799ccb0e984a5c1311b22a212e7ff96e8b736de Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 21 Sep 2018 08:51:49 -0700 Subject: tcp: add tcp_wstamp_ns socket field TCP will soon provide earliest departure time on TX skbs. It needs to track this in a new variable. tcp_mstamp_refresh() needs to update this variable, and became too big to stay an inline. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 2 ++ include/net/tcp.h | 12 +----------- net/ipv4/tcp_output.c | 16 ++++++++++++++++ 3 files changed, 19 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 263e37271afd..848f5b25e178 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -248,6 +248,8 @@ struct tcp_sock { syn_smc:1; /* SYN includes SMC */ u32 tlp_high_seq; /* snd_nxt at the time of TLP retransmit. */ + u64 tcp_wstamp_ns; /* departure time for next sent data packet */ + /* RTT measurement */ u64 tcp_mstamp; /* most recent packet received/sent */ u32 srtt_us; /* smoothed round trip time << 3 in usecs */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 0ca5ea10dc06..370198fdc65d 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -752,17 +752,7 @@ static inline u32 tcp_time_stamp_raw(void) return div_u64(tcp_clock_ns(), NSEC_PER_SEC / TCP_TS_HZ); } - -/* Refresh 1us clock of a TCP socket, - * ensuring monotically increasing values. - */ -static inline void tcp_mstamp_refresh(struct tcp_sock *tp) -{ - u64 val = tcp_clock_us(); - - if (val > tp->tcp_mstamp) - tp->tcp_mstamp = val; -} +void tcp_mstamp_refresh(struct tcp_sock *tp); static inline u32 tcp_stamp_us_delta(u64 t1, u64 t0) { diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index b95aa72d8823..5a8105e84f7c 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -45,6 +45,22 @@ #include +/* Refresh clocks of a TCP socket, + * ensuring monotically increasing values. + */ +void tcp_mstamp_refresh(struct tcp_sock *tp) +{ + u64 val = tcp_clock_ns(); + + /* departure time for next data packet */ + if (val > tp->tcp_wstamp_ns) + tp->tcp_wstamp_ns = val; + + val = div_u64(val, NSEC_PER_USEC); + if (val > tp->tcp_mstamp) + tp->tcp_mstamp = val; +} + static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, int push_one, gfp_t gfp); -- cgit v1.2.3 From d3edd06ea8ea9e03de6567fda80b8be57e21a537 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 21 Sep 2018 08:51:50 -0700 Subject: tcp: provide earliest departure time in skb->tstamp Switch internal TCP skb->skb_mstamp to skb->skb_mstamp_ns, from usec units to nsec units. Do not clear skb->tstamp before entering IP stacks in TX, so that qdisc or devices can implement pacing based on the earliest departure time instead of socket sk->sk_pacing_rate Packets are fed with tcp_wstamp_ns, and following patch will update tcp_wstamp_ns when both TCP and sch_fq switch to the earliest departure time mechanism. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 +- include/net/tcp.h | 6 +++--- net/ipv4/syncookies.c | 2 +- net/ipv4/tcp.c | 2 +- net/ipv4/tcp_output.c | 13 ++++++------- net/ipv4/tcp_timer.c | 2 +- 6 files changed, 13 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index e3a53ca4a9b5..86f337e9a81d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -689,7 +689,7 @@ struct sk_buff { union { ktime_t tstamp; - u64 skb_mstamp; + u64 skb_mstamp_ns; /* earliest departure time */ }; /* * This is the control buffer. It is free to use for every diff --git a/include/net/tcp.h b/include/net/tcp.h index 370198fdc65d..ff15d8e0d525 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -761,13 +761,13 @@ static inline u32 tcp_stamp_us_delta(u64 t1, u64 t0) static inline u32 tcp_skb_timestamp(const struct sk_buff *skb) { - return div_u64(skb->skb_mstamp, USEC_PER_SEC / TCP_TS_HZ); + return div_u64(skb->skb_mstamp_ns, NSEC_PER_SEC / TCP_TS_HZ); } /* provide the departure time in us unit */ static inline u64 tcp_skb_timestamp_us(const struct sk_buff *skb) { - return skb->skb_mstamp; + return div_u64(skb->skb_mstamp_ns, NSEC_PER_USEC); } @@ -813,7 +813,7 @@ struct tcp_skb_cb { #define TCPCB_SACKED_RETRANS 0x02 /* SKB retransmitted */ #define TCPCB_LOST 0x04 /* SKB is lost */ #define TCPCB_TAGBITS 0x07 /* All tag bits */ -#define TCPCB_REPAIRED 0x10 /* SKB repaired (no skb_mstamp) */ +#define TCPCB_REPAIRED 0x10 /* SKB repaired (no skb_mstamp_ns) */ #define TCPCB_EVER_RETRANS 0x80 /* Ever retransmitted frame */ #define TCPCB_RETRANS (TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS| \ TCPCB_REPAIRED) diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index c3387dfd725b..606f868d9f3f 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -88,7 +88,7 @@ u64 cookie_init_timestamp(struct request_sock *req) ts <<= TSBITS; ts |= options; } - return (u64)ts * (USEC_PER_SEC / TCP_TS_HZ); + return (u64)ts * (NSEC_PER_SEC / TCP_TS_HZ); } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 67670fac7c8d..69c236943f56 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1295,7 +1295,7 @@ new_segment: copy = size_goal; /* All packets are restored as if they have - * already been sent. skb_mstamp isn't set to + * already been sent. skb_mstamp_ns isn't set to * avoid wrong rtt estimation. */ if (tp->repair) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 5a8105e84f7c..957f7a0e21c0 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1014,7 +1014,7 @@ static void tcp_internal_pacing(struct sock *sk, const struct sk_buff *skb) static void tcp_update_skb_after_send(struct tcp_sock *tp, struct sk_buff *skb) { - skb->skb_mstamp = tp->tcp_mstamp; + skb->skb_mstamp_ns = tp->tcp_wstamp_ns; list_move_tail(&skb->tcp_tsorted_anchor, &tp->tsorted_sent_queue); } @@ -1061,7 +1061,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, if (unlikely(!skb)) return -ENOBUFS; } - skb->skb_mstamp = tp->tcp_mstamp; + skb->skb_mstamp_ns = tp->tcp_wstamp_ns; inet = inet_sk(sk); tcb = TCP_SKB_CB(skb); @@ -1165,8 +1165,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, skb_shinfo(skb)->gso_segs = tcp_skb_pcount(skb); skb_shinfo(skb)->gso_size = tcp_skb_mss(skb); - /* Our usage of tstamp should remain private */ - skb->tstamp = 0; + /* Leave earliest departure time in skb->tstamp (skb->skb_mstamp_ns) */ /* Cleanup our debris for IP stacks */ memset(skb->cb, 0, max(sizeof(struct inet_skb_parm), @@ -3221,10 +3220,10 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, memset(&opts, 0, sizeof(opts)); #ifdef CONFIG_SYN_COOKIES if (unlikely(req->cookie_ts)) - skb->skb_mstamp = cookie_init_timestamp(req); + skb->skb_mstamp_ns = cookie_init_timestamp(req); else #endif - skb->skb_mstamp = tcp_clock_us(); + skb->skb_mstamp_ns = tcp_clock_ns(); #ifdef CONFIG_TCP_MD5SIG rcu_read_lock(); @@ -3440,7 +3439,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) err = tcp_transmit_skb(sk, syn_data, 1, sk->sk_allocation); - syn->skb_mstamp = syn_data->skb_mstamp; + syn->skb_mstamp_ns = syn_data->skb_mstamp_ns; /* Now full SYN+DATA was cloned and sent (or not), * remove the SYN from the original skb (syn_data) diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 7fdf222a0bdf..61023d50cd60 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -360,7 +360,7 @@ static void tcp_probe_timer(struct sock *sk) */ start_ts = tcp_skb_timestamp(skb); if (!start_ts) - skb->skb_mstamp = tp->tcp_mstamp; + skb->skb_mstamp_ns = tp->tcp_wstamp_ns; else if (icsk->icsk_user_timeout && (s32)(tcp_time_stamp(tp) - start_ts) > icsk->icsk_user_timeout) goto abort; -- cgit v1.2.3 From c798c88f3962ddff89c7aa818986caeecd46ab4c Mon Sep 17 00:00:00 2001 From: Fan Wu Date: Wed, 19 Sep 2018 01:59:00 +0000 Subject: EDAC, ghes: Use CPER module handles to locate DIMMs Use SMBIOS module handle type 17, on platforms which provide valid ones, to locate the corresponding DIMM and thus have per-DIMM error counter updates. Signed-off-by: Fan Wu [ Massage commit message. ] Signed-off-by: Borislav Petkov Reviewed-by: Tyler Baicar Reviewed-by: James Morse Tested-by: Toshi Kani Cc: Mauro Carvalho Chehab Cc: baicar.tyler@gmail.com Cc: john.garry@huawei.com Cc: linux-arm-kernel@lists.infradead.org Cc: linux-edac Cc: shiju.jose@huawei.com Cc: tanxiaofei@huawei.com Cc: wanghuiqiang@huawei.com Link: http://lkml.kernel.org/r/1537322340-1860-1-git-send-email-wufan@codeaurora.org --- drivers/edac/ghes_edac.c | 23 +++++++++++++++++++++++ include/linux/edac.h | 2 ++ 2 files changed, 25 insertions(+) (limited to 'include/linux') diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c index 473aeec4b1da..49396bf6ad88 100644 --- a/drivers/edac/ghes_edac.c +++ b/drivers/edac/ghes_edac.c @@ -81,6 +81,18 @@ static void ghes_edac_count_dimms(const struct dmi_header *dh, void *arg) (*num_dimm)++; } +static int get_dimm_smbios_index(u16 handle) +{ + struct mem_ctl_info *mci = ghes_pvt->mci; + int i; + + for (i = 0; i < mci->tot_dimms; i++) { + if (mci->dimms[i]->smbios_handle == handle) + return i; + } + return -1; +} + static void ghes_edac_dmidecode(const struct dmi_header *dh, void *arg) { struct ghes_edac_dimm_fill *dimm_fill = arg; @@ -177,6 +189,8 @@ static void ghes_edac_dmidecode(const struct dmi_header *dh, void *arg) entry->total_width, entry->data_width); } + dimm->smbios_handle = entry->handle; + dimm_fill->count++; } } @@ -327,12 +341,21 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err) p += sprintf(p, "bit_pos:%d ", mem_err->bit_pos); if (mem_err->validation_bits & CPER_MEM_VALID_MODULE_HANDLE) { const char *bank = NULL, *device = NULL; + int index = -1; + dmi_memdev_name(mem_err->mem_dev_handle, &bank, &device); if (bank != NULL && device != NULL) p += sprintf(p, "DIMM location:%s %s ", bank, device); else p += sprintf(p, "DIMM DMI handle: 0x%.4x ", mem_err->mem_dev_handle); + + index = get_dimm_smbios_index(mem_err->mem_dev_handle); + if (index >= 0) { + e->top_layer = index; + e->enable_per_layer_report = true; + } + } if (p > e->location) *(p - 1) = '\0'; diff --git a/include/linux/edac.h b/include/linux/edac.h index bffb97828ed6..a45ce1f84bfc 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -451,6 +451,8 @@ struct dimm_info { u32 nr_pages; /* number of pages on this dimm */ unsigned csrow, cschannel; /* Points to the old API data */ + + u16 smbios_handle; /* Handle for SMBIOS type 17 */ }; /** -- cgit v1.2.3 From 808c43b7c7f70360ed7b9e43e2cf980f388e71fa Mon Sep 17 00:00:00 2001 From: Andrey Ignatov Date: Fri, 21 Sep 2018 17:03:27 -0700 Subject: cgroup: Simplify cgroup_ancestor Simplify cgroup_ancestor function. This is follow-up for commit 7723628101aa ("bpf: Introduce bpf_skb_ancestor_cgroup_id helper") Suggested-by: Tejun Heo Signed-off-by: Andrey Ignatov Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 15 +++------------ 1 file changed, 3 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 32c553556bbd..e03a92430383 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -567,20 +567,11 @@ static inline bool cgroup_is_descendant(struct cgroup *cgrp, static inline struct cgroup *cgroup_ancestor(struct cgroup *cgrp, int ancestor_level) { - struct cgroup *ptr; - if (cgrp->level < ancestor_level) return NULL; - - for (ptr = cgrp; - ptr && ptr->level > ancestor_level; - ptr = cgroup_parent(ptr)) - ; - - if (ptr && ptr->level == ancestor_level) - return ptr; - - return NULL; + while (cgrp && cgrp->level > ancestor_level) + cgrp = cgroup_parent(cgrp); + return cgrp; } /** -- cgit v1.2.3 From 9ba481e2eb3b932ae5b6278342b256e4f92d2793 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 20 Sep 2018 21:35:20 +0300 Subject: net/mlx5: Set uid as part of CQ commands Set uid as part of CQ commands so that the firmware can manage the CQ object in a secured way. The firmware should mark this CQ with the given uid so that it can be used later on only by objects with the same uid. Upon DEVX flows that use this CQ (e.g. create QP command), the pointed CQ must have the same uid as of the issuer uid command. When a command is issued with uid=0 it means that the issuer of the command is trusted (i.e. kernel), in that case any pointed object can be used regardless of its uid. Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- drivers/net/ethernet/mellanox/mlx5/core/cq.c | 4 ++++ include/linux/mlx5/cq.h | 1 + include/linux/mlx5/mlx5_ifc.h | 6 +++--- 3 files changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c index a4179122a279..4b85abb5c9f7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c @@ -109,6 +109,7 @@ int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, cq->cons_index = 0; cq->arm_sn = 0; cq->eq = eq; + cq->uid = MLX5_GET(create_cq_in, in, uid); refcount_set(&cq->refcount, 1); init_completion(&cq->free); if (!cq->comp) @@ -144,6 +145,7 @@ err_cmd: memset(dout, 0, sizeof(dout)); MLX5_SET(destroy_cq_in, din, opcode, MLX5_CMD_OP_DESTROY_CQ); MLX5_SET(destroy_cq_in, din, cqn, cq->cqn); + MLX5_SET(destroy_cq_in, din, uid, cq->uid); mlx5_cmd_exec(dev, din, sizeof(din), dout, sizeof(dout)); return err; } @@ -165,6 +167,7 @@ int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq) MLX5_SET(destroy_cq_in, in, opcode, MLX5_CMD_OP_DESTROY_CQ); MLX5_SET(destroy_cq_in, in, cqn, cq->cqn); + MLX5_SET(destroy_cq_in, in, uid, cq->uid); err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); if (err) return err; @@ -196,6 +199,7 @@ int mlx5_core_modify_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, u32 out[MLX5_ST_SZ_DW(modify_cq_out)] = {0}; MLX5_SET(modify_cq_in, in, opcode, MLX5_CMD_OP_MODIFY_CQ); + MLX5_SET(modify_cq_in, in, uid, cq->uid); return mlx5_cmd_exec(dev, in, inlen, out, sizeof(out)); } EXPORT_SYMBOL(mlx5_core_modify_cq); diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index 0ef6138eca49..31a750570c38 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -61,6 +61,7 @@ struct mlx5_core_cq { int reset_notify_added; struct list_head reset_notify; struct mlx5_eq *eq; + u16 uid; }; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 4c7a1d25d73b..1a412b355054 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -5629,7 +5629,7 @@ enum { struct mlx5_ifc_modify_cq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6404,7 +6404,7 @@ struct mlx5_ifc_destroy_cq_out_bits { struct mlx5_ifc_destroy_cq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -7164,7 +7164,7 @@ struct mlx5_ifc_create_cq_out_bits { struct mlx5_ifc_create_cq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; -- cgit v1.2.3 From 4ac63ec72587f7426aae15ddfe78e8ab785724dc Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 20 Sep 2018 21:35:21 +0300 Subject: net/mlx5: Set uid as part of QP commands Set uid as part of QP commands so that the firmware can manage the QP object in a secured way. That will enable using a QP that was created by verbs application to be used by the DEVX flow in case the uid is equal. Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- drivers/net/ethernet/mellanox/mlx5/core/qp.c | 45 +++++++++++++++++----------- include/linux/mlx5/mlx5_ifc.h | 22 +++++++------- include/linux/mlx5/qp.h | 1 + 3 files changed, 39 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c index 4ca07bfb6b14..4e2ab3c916bf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c @@ -240,6 +240,7 @@ int mlx5_core_create_qp(struct mlx5_core_dev *dev, if (err) return err; + qp->uid = MLX5_GET(create_qp_in, in, uid); qp->qpn = MLX5_GET(create_qp_out, out, qpn); mlx5_core_dbg(dev, "qpn = 0x%x\n", qp->qpn); @@ -261,6 +262,7 @@ err_cmd: memset(dout, 0, sizeof(dout)); MLX5_SET(destroy_qp_in, din, opcode, MLX5_CMD_OP_DESTROY_QP); MLX5_SET(destroy_qp_in, din, qpn, qp->qpn); + MLX5_SET(destroy_qp_in, din, uid, qp->uid); mlx5_cmd_exec(dev, din, sizeof(din), dout, sizeof(dout)); return err; } @@ -320,6 +322,7 @@ int mlx5_core_destroy_qp(struct mlx5_core_dev *dev, MLX5_SET(destroy_qp_in, in, opcode, MLX5_CMD_OP_DESTROY_QP); MLX5_SET(destroy_qp_in, in, qpn, qp->qpn); + MLX5_SET(destroy_qp_in, in, uid, qp->uid); err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); if (err) return err; @@ -373,7 +376,7 @@ static void mbox_free(struct mbox_info *mbox) static int modify_qp_mbox_alloc(struct mlx5_core_dev *dev, u16 opcode, int qpn, u32 opt_param_mask, void *qpc, - struct mbox_info *mbox) + struct mbox_info *mbox, u16 uid) { mbox->out = NULL; mbox->in = NULL; @@ -381,26 +384,32 @@ static int modify_qp_mbox_alloc(struct mlx5_core_dev *dev, u16 opcode, int qpn, #define MBOX_ALLOC(mbox, typ) \ mbox_alloc(mbox, MLX5_ST_SZ_BYTES(typ##_in), MLX5_ST_SZ_BYTES(typ##_out)) -#define MOD_QP_IN_SET(typ, in, _opcode, _qpn) \ - MLX5_SET(typ##_in, in, opcode, _opcode); \ - MLX5_SET(typ##_in, in, qpn, _qpn) - -#define MOD_QP_IN_SET_QPC(typ, in, _opcode, _qpn, _opt_p, _qpc) \ - MOD_QP_IN_SET(typ, in, _opcode, _qpn); \ - MLX5_SET(typ##_in, in, opt_param_mask, _opt_p); \ - memcpy(MLX5_ADDR_OF(typ##_in, in, qpc), _qpc, MLX5_ST_SZ_BYTES(qpc)) +#define MOD_QP_IN_SET(typ, in, _opcode, _qpn, _uid) \ + do { \ + MLX5_SET(typ##_in, in, opcode, _opcode); \ + MLX5_SET(typ##_in, in, qpn, _qpn); \ + MLX5_SET(typ##_in, in, uid, _uid); \ + } while (0) + +#define MOD_QP_IN_SET_QPC(typ, in, _opcode, _qpn, _opt_p, _qpc, _uid) \ + do { \ + MOD_QP_IN_SET(typ, in, _opcode, _qpn, _uid); \ + MLX5_SET(typ##_in, in, opt_param_mask, _opt_p); \ + memcpy(MLX5_ADDR_OF(typ##_in, in, qpc), _qpc, \ + MLX5_ST_SZ_BYTES(qpc)); \ + } while (0) switch (opcode) { /* 2RST & 2ERR */ case MLX5_CMD_OP_2RST_QP: if (MBOX_ALLOC(mbox, qp_2rst)) return -ENOMEM; - MOD_QP_IN_SET(qp_2rst, mbox->in, opcode, qpn); + MOD_QP_IN_SET(qp_2rst, mbox->in, opcode, qpn, uid); break; case MLX5_CMD_OP_2ERR_QP: if (MBOX_ALLOC(mbox, qp_2err)) return -ENOMEM; - MOD_QP_IN_SET(qp_2err, mbox->in, opcode, qpn); + MOD_QP_IN_SET(qp_2err, mbox->in, opcode, qpn, uid); break; /* MODIFY with QPC */ @@ -408,37 +417,37 @@ static int modify_qp_mbox_alloc(struct mlx5_core_dev *dev, u16 opcode, int qpn, if (MBOX_ALLOC(mbox, rst2init_qp)) return -ENOMEM; MOD_QP_IN_SET_QPC(rst2init_qp, mbox->in, opcode, qpn, - opt_param_mask, qpc); + opt_param_mask, qpc, uid); break; case MLX5_CMD_OP_INIT2RTR_QP: if (MBOX_ALLOC(mbox, init2rtr_qp)) return -ENOMEM; MOD_QP_IN_SET_QPC(init2rtr_qp, mbox->in, opcode, qpn, - opt_param_mask, qpc); + opt_param_mask, qpc, uid); break; case MLX5_CMD_OP_RTR2RTS_QP: if (MBOX_ALLOC(mbox, rtr2rts_qp)) return -ENOMEM; MOD_QP_IN_SET_QPC(rtr2rts_qp, mbox->in, opcode, qpn, - opt_param_mask, qpc); + opt_param_mask, qpc, uid); break; case MLX5_CMD_OP_RTS2RTS_QP: if (MBOX_ALLOC(mbox, rts2rts_qp)) return -ENOMEM; MOD_QP_IN_SET_QPC(rts2rts_qp, mbox->in, opcode, qpn, - opt_param_mask, qpc); + opt_param_mask, qpc, uid); break; case MLX5_CMD_OP_SQERR2RTS_QP: if (MBOX_ALLOC(mbox, sqerr2rts_qp)) return -ENOMEM; MOD_QP_IN_SET_QPC(sqerr2rts_qp, mbox->in, opcode, qpn, - opt_param_mask, qpc); + opt_param_mask, qpc, uid); break; case MLX5_CMD_OP_INIT2INIT_QP: if (MBOX_ALLOC(mbox, init2init_qp)) return -ENOMEM; MOD_QP_IN_SET_QPC(init2init_qp, mbox->in, opcode, qpn, - opt_param_mask, qpc); + opt_param_mask, qpc, uid); break; default: mlx5_core_err(dev, "Unknown transition for modify QP: OP(0x%x) QPN(0x%x)\n", @@ -456,7 +465,7 @@ int mlx5_core_qp_modify(struct mlx5_core_dev *dev, u16 opcode, int err; err = modify_qp_mbox_alloc(dev, opcode, qp->qpn, - opt_param_mask, qpc, &mbox); + opt_param_mask, qpc, &mbox, qp->uid); if (err) return err; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 1a412b355054..3b6a612787ac 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -3394,7 +3394,7 @@ struct mlx5_ifc_sqerr2rts_qp_out_bits { struct mlx5_ifc_sqerr2rts_qp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -3424,7 +3424,7 @@ struct mlx5_ifc_sqd2rts_qp_out_bits { struct mlx5_ifc_sqd2rts_qp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -3629,7 +3629,7 @@ struct mlx5_ifc_rts2rts_qp_out_bits { struct mlx5_ifc_rts2rts_qp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -3659,7 +3659,7 @@ struct mlx5_ifc_rtr2rts_qp_out_bits { struct mlx5_ifc_rtr2rts_qp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -3689,7 +3689,7 @@ struct mlx5_ifc_rst2init_qp_out_bits { struct mlx5_ifc_rst2init_qp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -5192,7 +5192,7 @@ struct mlx5_ifc_qp_2rst_out_bits { struct mlx5_ifc_qp_2rst_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -5214,7 +5214,7 @@ struct mlx5_ifc_qp_2err_out_bits { struct mlx5_ifc_qp_2err_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -5789,7 +5789,7 @@ struct mlx5_ifc_init2rtr_qp_out_bits { struct mlx5_ifc_init2rtr_qp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -5819,7 +5819,7 @@ struct mlx5_ifc_init2init_qp_out_bits { struct mlx5_ifc_init2init_qp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6230,7 +6230,7 @@ struct mlx5_ifc_destroy_qp_out_bits { struct mlx5_ifc_destroy_qp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6895,7 +6895,7 @@ struct mlx5_ifc_create_qp_out_bits { struct mlx5_ifc_create_qp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index 4778d41085d4..fbe322c966bc 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -471,6 +471,7 @@ struct mlx5_core_qp { int qpn; struct mlx5_rsc_debug *dbg; int pid; + u16 uid; }; struct mlx5_core_dct { -- cgit v1.2.3 From d269b3afffcb107375d9cf73127fc2e0181bc90b Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 20 Sep 2018 21:35:22 +0300 Subject: net/mlx5: Set uid as part of RQ commands Set uid as part of RQ commands so that the firmware can manage the RQ object in a secured way. That will enable using an RQ that was created by verbs application to be used by the DEVX flow in case the uid is equal. Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- drivers/net/ethernet/mellanox/mlx5/core/qp.c | 16 ++++++++++++++-- include/linux/mlx5/mlx5_ifc.h | 6 +++--- 2 files changed, 17 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c index 4e2ab3c916bf..f57e08d4f970 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c @@ -540,6 +540,17 @@ int mlx5_core_xrcd_dealloc(struct mlx5_core_dev *dev, u32 xrcdn) } EXPORT_SYMBOL_GPL(mlx5_core_xrcd_dealloc); +static void destroy_rq_tracked(struct mlx5_core_dev *dev, u32 rqn, u16 uid) +{ + u32 in[MLX5_ST_SZ_DW(destroy_rq_in)] = {}; + u32 out[MLX5_ST_SZ_DW(destroy_rq_out)] = {}; + + MLX5_SET(destroy_rq_in, in, opcode, MLX5_CMD_OP_DESTROY_RQ); + MLX5_SET(destroy_rq_in, in, rqn, rqn); + MLX5_SET(destroy_rq_in, in, uid, uid); + mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); +} + int mlx5_core_create_rq_tracked(struct mlx5_core_dev *dev, u32 *in, int inlen, struct mlx5_core_qp *rq) { @@ -550,6 +561,7 @@ int mlx5_core_create_rq_tracked(struct mlx5_core_dev *dev, u32 *in, int inlen, if (err) return err; + rq->uid = MLX5_GET(create_rq_in, in, uid); rq->qpn = rqn; err = create_resource_common(dev, rq, MLX5_RES_RQ); if (err) @@ -558,7 +570,7 @@ int mlx5_core_create_rq_tracked(struct mlx5_core_dev *dev, u32 *in, int inlen, return 0; err_destroy_rq: - mlx5_core_destroy_rq(dev, rq->qpn); + destroy_rq_tracked(dev, rq->qpn, rq->uid); return err; } @@ -568,7 +580,7 @@ void mlx5_core_destroy_rq_tracked(struct mlx5_core_dev *dev, struct mlx5_core_qp *rq) { destroy_resource_common(dev, rq); - mlx5_core_destroy_rq(dev, rq->qpn); + destroy_rq_tracked(dev, rq->qpn, rq->uid); } EXPORT_SYMBOL(mlx5_core_destroy_rq_tracked); diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 3b6a612787ac..689631ca27b8 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -5488,7 +5488,7 @@ enum { struct mlx5_ifc_modify_rq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6164,7 +6164,7 @@ struct mlx5_ifc_destroy_rq_out_bits { struct mlx5_ifc_destroy_rq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6847,7 +6847,7 @@ struct mlx5_ifc_create_rq_out_bits { struct mlx5_ifc_create_rq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; -- cgit v1.2.3 From 430ae0d5a3ce1350375690cb6ab29ab6fae4a9ac Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 20 Sep 2018 21:35:23 +0300 Subject: net/mlx5: Set uid as part of SQ commands Set uid as part of SQ commands so that the firmware can manage the SQ object in a secured way. That will enable using an SQ that was created by verbs application to be used by the DEVX flow in case the uid is equal. Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- drivers/net/ethernet/mellanox/mlx5/core/qp.c | 16 ++++++++++++++-- include/linux/mlx5/mlx5_ifc.h | 6 +++--- 2 files changed, 17 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c index f57e08d4f970..d9b12136cbfd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c @@ -584,6 +584,17 @@ void mlx5_core_destroy_rq_tracked(struct mlx5_core_dev *dev, } EXPORT_SYMBOL(mlx5_core_destroy_rq_tracked); +static void destroy_sq_tracked(struct mlx5_core_dev *dev, u32 sqn, u16 uid) +{ + u32 in[MLX5_ST_SZ_DW(destroy_sq_in)] = {}; + u32 out[MLX5_ST_SZ_DW(destroy_sq_out)] = {}; + + MLX5_SET(destroy_sq_in, in, opcode, MLX5_CMD_OP_DESTROY_SQ); + MLX5_SET(destroy_sq_in, in, sqn, sqn); + MLX5_SET(destroy_sq_in, in, uid, uid); + mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); +} + int mlx5_core_create_sq_tracked(struct mlx5_core_dev *dev, u32 *in, int inlen, struct mlx5_core_qp *sq) { @@ -594,6 +605,7 @@ int mlx5_core_create_sq_tracked(struct mlx5_core_dev *dev, u32 *in, int inlen, if (err) return err; + sq->uid = MLX5_GET(create_sq_in, in, uid); sq->qpn = sqn; err = create_resource_common(dev, sq, MLX5_RES_SQ); if (err) @@ -602,7 +614,7 @@ int mlx5_core_create_sq_tracked(struct mlx5_core_dev *dev, u32 *in, int inlen, return 0; err_destroy_sq: - mlx5_core_destroy_sq(dev, sq->qpn); + destroy_sq_tracked(dev, sq->qpn, sq->uid); return err; } @@ -612,7 +624,7 @@ void mlx5_core_destroy_sq_tracked(struct mlx5_core_dev *dev, struct mlx5_core_qp *sq) { destroy_resource_common(dev, sq); - mlx5_core_destroy_sq(dev, sq->qpn); + destroy_sq_tracked(dev, sq->qpn, sq->uid); } EXPORT_SYMBOL(mlx5_core_destroy_sq_tracked); diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 689631ca27b8..72dd1e49a799 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -5381,7 +5381,7 @@ struct mlx5_ifc_modify_sq_out_bits { struct mlx5_ifc_modify_sq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6096,7 +6096,7 @@ struct mlx5_ifc_destroy_sq_out_bits { struct mlx5_ifc_destroy_sq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6769,7 +6769,7 @@ struct mlx5_ifc_create_sq_out_bits { struct mlx5_ifc_create_sq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; -- cgit v1.2.3 From a0d8c054318976927493ffd26055d9d183c9beec Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 20 Sep 2018 21:35:24 +0300 Subject: net/mlx5: Set uid as part of SRQ commands Set uid as part of SRQ commands so that the firmware can manage the SRQ object in a secured way. That will enable using an SRQ that was created by verbs application to be used by the DEVX flow in case the uid is equal. Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- drivers/net/ethernet/mellanox/mlx5/core/srq.c | 30 ++++++++++++++++++++++++--- include/linux/mlx5/driver.h | 1 + include/linux/mlx5/mlx5_ifc.h | 22 ++++++++++---------- include/linux/mlx5/srq.h | 1 + 4 files changed, 40 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/srq.c b/drivers/net/ethernet/mellanox/mlx5/core/srq.c index 23cc337a96c9..5c519615fb1c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/srq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/srq.c @@ -166,6 +166,7 @@ static int create_srq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq, if (!create_in) return -ENOMEM; + MLX5_SET(create_srq_in, create_in, uid, in->uid); srqc = MLX5_ADDR_OF(create_srq_in, create_in, srq_context_entry); pas = MLX5_ADDR_OF(create_srq_in, create_in, pas); @@ -178,8 +179,10 @@ static int create_srq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq, err = mlx5_cmd_exec(dev, create_in, inlen, create_out, sizeof(create_out)); kvfree(create_in); - if (!err) + if (!err) { srq->srqn = MLX5_GET(create_srq_out, create_out, srqn); + srq->uid = in->uid; + } return err; } @@ -193,6 +196,7 @@ static int destroy_srq_cmd(struct mlx5_core_dev *dev, MLX5_SET(destroy_srq_in, srq_in, opcode, MLX5_CMD_OP_DESTROY_SRQ); MLX5_SET(destroy_srq_in, srq_in, srqn, srq->srqn); + MLX5_SET(destroy_srq_in, srq_in, uid, srq->uid); return mlx5_cmd_exec(dev, srq_in, sizeof(srq_in), srq_out, sizeof(srq_out)); @@ -208,6 +212,7 @@ static int arm_srq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq, MLX5_SET(arm_rq_in, srq_in, op_mod, MLX5_ARM_RQ_IN_OP_MOD_SRQ); MLX5_SET(arm_rq_in, srq_in, srq_number, srq->srqn); MLX5_SET(arm_rq_in, srq_in, lwm, lwm); + MLX5_SET(arm_rq_in, srq_in, uid, srq->uid); return mlx5_cmd_exec(dev, srq_in, sizeof(srq_in), srq_out, sizeof(srq_out)); @@ -260,6 +265,7 @@ static int create_xrc_srq_cmd(struct mlx5_core_dev *dev, if (!create_in) return -ENOMEM; + MLX5_SET(create_xrc_srq_in, create_in, uid, in->uid); xrc_srqc = MLX5_ADDR_OF(create_xrc_srq_in, create_in, xrc_srq_context_entry); pas = MLX5_ADDR_OF(create_xrc_srq_in, create_in, pas); @@ -277,6 +283,7 @@ static int create_xrc_srq_cmd(struct mlx5_core_dev *dev, goto out; srq->srqn = MLX5_GET(create_xrc_srq_out, create_out, xrc_srqn); + srq->uid = in->uid; out: kvfree(create_in); return err; @@ -291,6 +298,7 @@ static int destroy_xrc_srq_cmd(struct mlx5_core_dev *dev, MLX5_SET(destroy_xrc_srq_in, xrcsrq_in, opcode, MLX5_CMD_OP_DESTROY_XRC_SRQ); MLX5_SET(destroy_xrc_srq_in, xrcsrq_in, xrc_srqn, srq->srqn); + MLX5_SET(destroy_xrc_srq_in, xrcsrq_in, uid, srq->uid); return mlx5_cmd_exec(dev, xrcsrq_in, sizeof(xrcsrq_in), xrcsrq_out, sizeof(xrcsrq_out)); @@ -306,6 +314,7 @@ static int arm_xrc_srq_cmd(struct mlx5_core_dev *dev, MLX5_SET(arm_xrc_srq_in, xrcsrq_in, op_mod, MLX5_ARM_XRC_SRQ_IN_OP_MOD_XRC_SRQ); MLX5_SET(arm_xrc_srq_in, xrcsrq_in, xrc_srqn, srq->srqn); MLX5_SET(arm_xrc_srq_in, xrcsrq_in, lwm, lwm); + MLX5_SET(arm_xrc_srq_in, xrcsrq_in, uid, srq->uid); return mlx5_cmd_exec(dev, xrcsrq_in, sizeof(xrcsrq_in), xrcsrq_out, sizeof(xrcsrq_out)); @@ -365,10 +374,13 @@ static int create_rmp_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq, wq = MLX5_ADDR_OF(rmpc, rmpc, wq); MLX5_SET(rmpc, rmpc, state, MLX5_RMPC_STATE_RDY); + MLX5_SET(create_rmp_in, create_in, uid, in->uid); set_wq(wq, in); memcpy(MLX5_ADDR_OF(rmpc, rmpc, wq.pas), in->pas, pas_size); err = mlx5_core_create_rmp(dev, create_in, inlen, &srq->srqn); + if (!err) + srq->uid = in->uid; kvfree(create_in); return err; @@ -377,7 +389,13 @@ static int create_rmp_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq, static int destroy_rmp_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq) { - return mlx5_core_destroy_rmp(dev, srq->srqn); + u32 in[MLX5_ST_SZ_DW(destroy_rmp_in)] = {}; + u32 out[MLX5_ST_SZ_DW(destroy_rmp_out)] = {}; + + MLX5_SET(destroy_rmp_in, in, opcode, MLX5_CMD_OP_DESTROY_RMP); + MLX5_SET(destroy_rmp_in, in, rmpn, srq->srqn); + MLX5_SET(destroy_rmp_in, in, uid, srq->uid); + return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); } static int arm_rmp_cmd(struct mlx5_core_dev *dev, @@ -400,6 +418,7 @@ static int arm_rmp_cmd(struct mlx5_core_dev *dev, MLX5_SET(modify_rmp_in, in, rmp_state, MLX5_RMPC_STATE_RDY); MLX5_SET(modify_rmp_in, in, rmpn, srq->srqn); + MLX5_SET(modify_rmp_in, in, uid, srq->uid); MLX5_SET(wq, wq, lwm, lwm); MLX5_SET(rmp_bitmask, bitmask, lwm, 1); MLX5_SET(rmpc, rmpc, state, MLX5_RMPC_STATE_RDY); @@ -469,11 +488,14 @@ static int create_xrq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq, MLX5_SET(xrqc, xrqc, user_index, in->user_index); MLX5_SET(xrqc, xrqc, cqn, in->cqn); MLX5_SET(create_xrq_in, create_in, opcode, MLX5_CMD_OP_CREATE_XRQ); + MLX5_SET(create_xrq_in, create_in, uid, in->uid); err = mlx5_cmd_exec(dev, create_in, inlen, create_out, sizeof(create_out)); kvfree(create_in); - if (!err) + if (!err) { srq->srqn = MLX5_GET(create_xrq_out, create_out, xrqn); + srq->uid = in->uid; + } return err; } @@ -485,6 +507,7 @@ static int destroy_xrq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq) MLX5_SET(destroy_xrq_in, in, opcode, MLX5_CMD_OP_DESTROY_XRQ); MLX5_SET(destroy_xrq_in, in, xrqn, srq->srqn); + MLX5_SET(destroy_xrq_in, in, uid, srq->uid); return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); } @@ -500,6 +523,7 @@ static int arm_xrq_cmd(struct mlx5_core_dev *dev, MLX5_SET(arm_rq_in, in, op_mod, MLX5_ARM_RQ_IN_OP_MOD_XRQ); MLX5_SET(arm_rq_in, in, srq_number, srq->srqn); MLX5_SET(arm_rq_in, in, lwm, lwm); + MLX5_SET(arm_rq_in, in, uid, srq->uid); return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); } diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index d885e9f0e054..8fb072aa8671 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -474,6 +474,7 @@ struct mlx5_core_srq { atomic_t refcount; struct completion free; + u16 uid; }; struct mlx5_eq_table { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 72dd1e49a799..85f1237d80db 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -5524,7 +5524,7 @@ struct mlx5_ifc_rmp_bitmask_bits { struct mlx5_ifc_modify_rmp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -5986,7 +5986,7 @@ struct mlx5_ifc_destroy_xrq_out_bits { struct mlx5_ifc_destroy_xrq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6008,7 +6008,7 @@ struct mlx5_ifc_destroy_xrc_srq_out_bits { struct mlx5_ifc_destroy_xrc_srq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6074,7 +6074,7 @@ struct mlx5_ifc_destroy_srq_out_bits { struct mlx5_ifc_destroy_srq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6208,7 +6208,7 @@ struct mlx5_ifc_destroy_rmp_out_bits { struct mlx5_ifc_destroy_rmp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6641,7 +6641,7 @@ struct mlx5_ifc_create_xrq_out_bits { struct mlx5_ifc_create_xrq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6665,7 +6665,7 @@ struct mlx5_ifc_create_xrc_srq_out_bits { struct mlx5_ifc_create_xrc_srq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6741,7 +6741,7 @@ struct mlx5_ifc_create_srq_out_bits { struct mlx5_ifc_create_srq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6871,7 +6871,7 @@ struct mlx5_ifc_create_rmp_out_bits { struct mlx5_ifc_create_rmp_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -7272,7 +7272,7 @@ enum { struct mlx5_ifc_arm_xrc_srq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -7300,7 +7300,7 @@ enum { struct mlx5_ifc_arm_rq_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; diff --git a/include/linux/mlx5/srq.h b/include/linux/mlx5/srq.h index 24ff23e27c8a..1b1f3c20c6a3 100644 --- a/include/linux/mlx5/srq.h +++ b/include/linux/mlx5/srq.h @@ -61,6 +61,7 @@ struct mlx5_srq_attr { u32 tm_next_tag; u32 tm_hw_phase_cnt; u32 tm_sw_phase_cnt; + u16 uid; }; struct mlx5_core_dev; -- cgit v1.2.3 From 774ea6eea29025218f75bc94c764df9a641db471 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 20 Sep 2018 21:35:25 +0300 Subject: net/mlx5: Set uid as part of DCT commands Set uid as part of DCT commands so that the firmware can manage the DCT object in a secured way. That will enable using a DCT that was created by verbs application to be used by the DEVX flow in case the uid is equal. Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- drivers/net/ethernet/mellanox/mlx5/core/qp.c | 4 ++++ include/linux/mlx5/mlx5_ifc.h | 6 +++--- 2 files changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c index d9b12136cbfd..91b8139a388d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c @@ -211,6 +211,7 @@ int mlx5_core_create_dct(struct mlx5_core_dev *dev, } qp->qpn = MLX5_GET(create_dct_out, out, dctn); + qp->uid = MLX5_GET(create_dct_in, in, uid); err = create_resource_common(dev, qp, MLX5_RES_DCT); if (err) goto err_cmd; @@ -219,6 +220,7 @@ int mlx5_core_create_dct(struct mlx5_core_dev *dev, err_cmd: MLX5_SET(destroy_dct_in, din, opcode, MLX5_CMD_OP_DESTROY_DCT); MLX5_SET(destroy_dct_in, din, dctn, qp->qpn); + MLX5_SET(destroy_dct_in, din, uid, qp->uid); mlx5_cmd_exec(dev, (void *)&in, sizeof(din), (void *)&out, sizeof(dout)); return err; @@ -277,6 +279,7 @@ static int mlx5_core_drain_dct(struct mlx5_core_dev *dev, MLX5_SET(drain_dct_in, in, opcode, MLX5_CMD_OP_DRAIN_DCT); MLX5_SET(drain_dct_in, in, dctn, qp->qpn); + MLX5_SET(drain_dct_in, in, uid, qp->uid); return mlx5_cmd_exec(dev, (void *)&in, sizeof(in), (void *)&out, sizeof(out)); } @@ -303,6 +306,7 @@ destroy: destroy_resource_common(dev, &dct->mqp); MLX5_SET(destroy_dct_in, in, opcode, MLX5_CMD_OP_DESTROY_DCT); MLX5_SET(destroy_dct_in, in, dctn, qp->qpn); + MLX5_SET(destroy_dct_in, in, uid, qp->uid); err = mlx5_cmd_exec(dev, (void *)&in, sizeof(in), (void *)&out, sizeof(out)); return err; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 85f1237d80db..62c0592a9fdb 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -5918,7 +5918,7 @@ struct mlx5_ifc_drain_dct_out_bits { struct mlx5_ifc_drain_dct_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6382,7 +6382,7 @@ struct mlx5_ifc_destroy_dct_out_bits { struct mlx5_ifc_destroy_dct_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -7138,7 +7138,7 @@ struct mlx5_ifc_create_dct_out_bits { struct mlx5_ifc_create_dct_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; -- cgit v1.2.3 From bd37197554eb28a7fc38e44e005e303c77f788ed Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Thu, 20 Sep 2018 21:35:26 +0300 Subject: net/mlx5: Update mlx5_ifc with DEVX UID bits Add DEVX information to WQ, SRQ, CQ, TIR, TIS, QP, RQ, XRCD, PD, MKEY and MCG. Each object that is created/destroyed/modified via verbs will be stamped with a UID based on its user context. This is already done for DEVX objects commands. This will enable the firmware to enforce the usage of kernel objects from the DEVX flow by validating that the same UID is used and the resources are really related to the same user. The addition of *_valid fields are needed to distinguish how various addresses are passed. For non-DEVX callers, all those fields will be zero. Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 67 +++++++++++++++++++++++++++---------------- 1 file changed, 43 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 62c0592a9fdb..68f4d5f9d929 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1290,7 +1290,9 @@ struct mlx5_ifc_wq_bits { u8 reserved_at_118[0x3]; u8 log_wq_sz[0x5]; - u8 reserved_at_120[0x3]; + u8 dbr_umem_valid[0x1]; + u8 wq_umem_valid[0x1]; + u8 reserved_at_122[0x1]; u8 log_hairpin_num_packets[0x5]; u8 reserved_at_128[0x3]; u8 log_hairpin_data_sz[0x5]; @@ -2364,7 +2366,10 @@ struct mlx5_ifc_qpc_bits { u8 dc_access_key[0x40]; - u8 reserved_at_680[0xc0]; + u8 reserved_at_680[0x3]; + u8 dbr_umem_valid[0x1]; + + u8 reserved_at_684[0xbc]; }; struct mlx5_ifc_roce_addr_layout_bits { @@ -2464,7 +2469,7 @@ struct mlx5_ifc_xrc_srqc_bits { u8 wq_signature[0x1]; u8 cont_srq[0x1]; - u8 reserved_at_22[0x1]; + u8 dbr_umem_valid[0x1]; u8 rlky[0x1]; u8 basic_cyclic_rcv_wqe[0x1]; u8 log_rq_stride[0x3]; @@ -3128,7 +3133,9 @@ enum { struct mlx5_ifc_cqc_bits { u8 status[0x4]; - u8 reserved_at_4[0x4]; + u8 reserved_at_4[0x2]; + u8 dbr_umem_valid[0x1]; + u8 reserved_at_7[0x1]; u8 cqe_sz[0x3]; u8 cc[0x1]; u8 reserved_at_c[0x1]; @@ -5314,7 +5321,7 @@ struct mlx5_ifc_modify_tis_bitmask_bits { struct mlx5_ifc_modify_tis_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -5353,7 +5360,7 @@ struct mlx5_ifc_modify_tir_out_bits { struct mlx5_ifc_modify_tir_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -5454,7 +5461,7 @@ struct mlx5_ifc_rqt_bitmask_bits { struct mlx5_ifc_modify_rqt_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -5641,7 +5648,10 @@ struct mlx5_ifc_modify_cq_in_bits { struct mlx5_ifc_cqc_bits cq_context; - u8 reserved_at_280[0x600]; + u8 reserved_at_280[0x40]; + + u8 cq_umem_valid[0x1]; + u8 reserved_at_2c1[0x5bf]; u8 pas[0][0x40]; }; @@ -5962,7 +5972,7 @@ struct mlx5_ifc_detach_from_mcg_out_bits { struct mlx5_ifc_detach_from_mcg_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6030,7 +6040,7 @@ struct mlx5_ifc_destroy_tis_out_bits { struct mlx5_ifc_destroy_tis_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6052,7 +6062,7 @@ struct mlx5_ifc_destroy_tir_out_bits { struct mlx5_ifc_destroy_tir_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6142,7 +6152,7 @@ struct mlx5_ifc_destroy_rqt_out_bits { struct mlx5_ifc_destroy_rqt_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6507,7 +6517,7 @@ struct mlx5_ifc_dealloc_xrcd_out_bits { struct mlx5_ifc_dealloc_xrcd_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6595,7 +6605,7 @@ struct mlx5_ifc_dealloc_pd_out_bits { struct mlx5_ifc_dealloc_pd_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6674,7 +6684,9 @@ struct mlx5_ifc_create_xrc_srq_in_bits { struct mlx5_ifc_xrc_srqc_bits xrc_srq_context_entry; - u8 reserved_at_280[0x600]; + u8 reserved_at_280[0x40]; + u8 xrc_srq_umem_valid[0x1]; + u8 reserved_at_2c1[0x5bf]; u8 pas[0][0x40]; }; @@ -6693,7 +6705,7 @@ struct mlx5_ifc_create_tis_out_bits { struct mlx5_ifc_create_tis_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6717,7 +6729,7 @@ struct mlx5_ifc_create_tir_out_bits { struct mlx5_ifc_create_tir_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6823,7 +6835,7 @@ struct mlx5_ifc_create_rqt_out_bits { struct mlx5_ifc_create_rqt_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -6908,7 +6920,10 @@ struct mlx5_ifc_create_qp_in_bits { struct mlx5_ifc_qpc_bits qpc; - u8 reserved_at_800[0x80]; + u8 reserved_at_800[0x60]; + + u8 wq_umem_valid[0x1]; + u8 reserved_at_861[0x1f]; u8 pas[0][0x40]; }; @@ -6970,7 +6985,8 @@ struct mlx5_ifc_create_mkey_in_bits { u8 reserved_at_40[0x20]; u8 pg_access[0x1]; - u8 reserved_at_61[0x1f]; + u8 mkey_umem_valid[0x1]; + u8 reserved_at_62[0x1e]; struct mlx5_ifc_mkc_bits memory_key_mkey_entry; @@ -7173,7 +7189,10 @@ struct mlx5_ifc_create_cq_in_bits { struct mlx5_ifc_cqc_bits cq_context; - u8 reserved_at_280[0x600]; + u8 reserved_at_280[0x60]; + + u8 cq_umem_valid[0x1]; + u8 reserved_at_2e1[0x59f]; u8 pas[0][0x40]; }; @@ -7221,7 +7240,7 @@ struct mlx5_ifc_attach_to_mcg_out_bits { struct mlx5_ifc_attach_to_mcg_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -7348,7 +7367,7 @@ struct mlx5_ifc_alloc_xrcd_out_bits { struct mlx5_ifc_alloc_xrcd_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -7436,7 +7455,7 @@ struct mlx5_ifc_alloc_pd_out_bits { struct mlx5_ifc_alloc_pd_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; -- cgit v1.2.3 From 2a6db719c92dbfe43c9eea7e4358ea2e51b5004e Mon Sep 17 00:00:00 2001 From: Nipun Gupta Date: Mon, 10 Sep 2018 19:19:16 +0530 Subject: iommu/of: make of_pci_map_rid() available for other devices too iommu-map property is also used by devices with fsl-mc. This patch moves the of_pci_map_rid to generic location, so that it can be used by other busses too. 'of_pci_map_rid' is renamed here to 'of_map_rid' and there is no functional change done in the API. Signed-off-by: Nipun Gupta Reviewed-by: Rob Herring Reviewed-by: Robin Murphy Acked-by: Bjorn Helgaas Signed-off-by: Joerg Roedel --- drivers/iommu/of_iommu.c | 5 +-- drivers/of/base.c | 102 +++++++++++++++++++++++++++++++++++++++++++++++ drivers/of/irq.c | 5 +-- drivers/pci/of.c | 101 ---------------------------------------------- include/linux/of.h | 11 +++++ include/linux/of_pci.h | 10 ----- 6 files changed, 117 insertions(+), 117 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c index f7787e757244..c13eecac0e8a 100644 --- a/drivers/iommu/of_iommu.c +++ b/drivers/iommu/of_iommu.c @@ -132,9 +132,8 @@ static int of_pci_iommu_init(struct pci_dev *pdev, u16 alias, void *data) struct of_phandle_args iommu_spec = { .args_count = 1 }; int err; - err = of_pci_map_rid(info->np, alias, "iommu-map", - "iommu-map-mask", &iommu_spec.np, - iommu_spec.args); + err = of_map_rid(info->np, alias, "iommu-map", "iommu-map-mask", + &iommu_spec.np, iommu_spec.args); if (err) return err == -ENODEV ? NO_IOMMU : err; diff --git a/drivers/of/base.c b/drivers/of/base.c index 74eaedd5b860..90bf7d9fa17b 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -2045,3 +2045,105 @@ int of_find_last_cache_level(unsigned int cpu) return cache_level; } + +/** + * of_map_rid - Translate a requester ID through a downstream mapping. + * @np: root complex device node. + * @rid: device requester ID to map. + * @map_name: property name of the map to use. + * @map_mask_name: optional property name of the mask to use. + * @target: optional pointer to a target device node. + * @id_out: optional pointer to receive the translated ID. + * + * Given a device requester ID, look up the appropriate implementation-defined + * platform ID and/or the target device which receives transactions on that + * ID, as per the "iommu-map" and "msi-map" bindings. Either of @target or + * @id_out may be NULL if only the other is required. If @target points to + * a non-NULL device node pointer, only entries targeting that node will be + * matched; if it points to a NULL value, it will receive the device node of + * the first matching target phandle, with a reference held. + * + * Return: 0 on success or a standard error code on failure. + */ +int of_map_rid(struct device_node *np, u32 rid, + const char *map_name, const char *map_mask_name, + struct device_node **target, u32 *id_out) +{ + u32 map_mask, masked_rid; + int map_len; + const __be32 *map = NULL; + + if (!np || !map_name || (!target && !id_out)) + return -EINVAL; + + map = of_get_property(np, map_name, &map_len); + if (!map) { + if (target) + return -ENODEV; + /* Otherwise, no map implies no translation */ + *id_out = rid; + return 0; + } + + if (!map_len || map_len % (4 * sizeof(*map))) { + pr_err("%pOF: Error: Bad %s length: %d\n", np, + map_name, map_len); + return -EINVAL; + } + + /* The default is to select all bits. */ + map_mask = 0xffffffff; + + /* + * Can be overridden by "{iommu,msi}-map-mask" property. + * If of_property_read_u32() fails, the default is used. + */ + if (map_mask_name) + of_property_read_u32(np, map_mask_name, &map_mask); + + masked_rid = map_mask & rid; + for ( ; map_len > 0; map_len -= 4 * sizeof(*map), map += 4) { + struct device_node *phandle_node; + u32 rid_base = be32_to_cpup(map + 0); + u32 phandle = be32_to_cpup(map + 1); + u32 out_base = be32_to_cpup(map + 2); + u32 rid_len = be32_to_cpup(map + 3); + + if (rid_base & ~map_mask) { + pr_err("%pOF: Invalid %s translation - %s-mask (0x%x) ignores rid-base (0x%x)\n", + np, map_name, map_name, + map_mask, rid_base); + return -EFAULT; + } + + if (masked_rid < rid_base || masked_rid >= rid_base + rid_len) + continue; + + phandle_node = of_find_node_by_phandle(phandle); + if (!phandle_node) + return -ENODEV; + + if (target) { + if (*target) + of_node_put(phandle_node); + else + *target = phandle_node; + + if (*target != phandle_node) + continue; + } + + if (id_out) + *id_out = masked_rid - rid_base + out_base; + + pr_debug("%pOF: %s, using mask %08x, rid-base: %08x, out-base: %08x, length: %08x, rid: %08x -> %08x\n", + np, map_name, map_mask, rid_base, out_base, + rid_len, rid, masked_rid - rid_base + out_base); + return 0; + } + + pr_err("%pOF: Invalid %s translation - no match for rid 0x%x on %pOF\n", + np, map_name, rid, target && *target ? *target : NULL); + return -EFAULT; +} +EXPORT_SYMBOL_GPL(of_map_rid); diff --git a/drivers/of/irq.c b/drivers/of/irq.c index 02ad93a304a4..e1f6f392a4c0 100644 --- a/drivers/of/irq.c +++ b/drivers/of/irq.c @@ -22,7 +22,6 @@ #include #include #include -#include #include #include @@ -588,8 +587,8 @@ static u32 __of_msi_map_rid(struct device *dev, struct device_node **np, * "msi-map" property. */ for (parent_dev = dev; parent_dev; parent_dev = parent_dev->parent) - if (!of_pci_map_rid(parent_dev->of_node, rid_in, "msi-map", - "msi-map-mask", np, &rid_out)) + if (!of_map_rid(parent_dev->of_node, rid_in, "msi-map", + "msi-map-mask", np, &rid_out)) break; return rid_out; } diff --git a/drivers/pci/of.c b/drivers/pci/of.c index 1836b8ddf292..4c4217d0c3f1 100644 --- a/drivers/pci/of.c +++ b/drivers/pci/of.c @@ -355,107 +355,6 @@ failed: EXPORT_SYMBOL_GPL(devm_of_pci_get_host_bridge_resources); #endif /* CONFIG_OF_ADDRESS */ -/** - * of_pci_map_rid - Translate a requester ID through a downstream mapping. - * @np: root complex device node. - * @rid: PCI requester ID to map. - * @map_name: property name of the map to use. - * @map_mask_name: optional property name of the mask to use. - * @target: optional pointer to a target device node. - * @id_out: optional pointer to receive the translated ID. - * - * Given a PCI requester ID, look up the appropriate implementation-defined - * platform ID and/or the target device which receives transactions on that - * ID, as per the "iommu-map" and "msi-map" bindings. Either of @target or - * @id_out may be NULL if only the other is required. If @target points to - * a non-NULL device node pointer, only entries targeting that node will be - * matched; if it points to a NULL value, it will receive the device node of - * the first matching target phandle, with a reference held. - * - * Return: 0 on success or a standard error code on failure. - */ -int of_pci_map_rid(struct device_node *np, u32 rid, - const char *map_name, const char *map_mask_name, - struct device_node **target, u32 *id_out) -{ - u32 map_mask, masked_rid; - int map_len; - const __be32 *map = NULL; - - if (!np || !map_name || (!target && !id_out)) - return -EINVAL; - - map = of_get_property(np, map_name, &map_len); - if (!map) { - if (target) - return -ENODEV; - /* Otherwise, no map implies no translation */ - *id_out = rid; - return 0; - } - - if (!map_len || map_len % (4 * sizeof(*map))) { - pr_err("%pOF: Error: Bad %s length: %d\n", np, - map_name, map_len); - return -EINVAL; - } - - /* The default is to select all bits. */ - map_mask = 0xffffffff; - - /* - * Can be overridden by "{iommu,msi}-map-mask" property. - * If of_property_read_u32() fails, the default is used. - */ - if (map_mask_name) - of_property_read_u32(np, map_mask_name, &map_mask); - - masked_rid = map_mask & rid; - for ( ; map_len > 0; map_len -= 4 * sizeof(*map), map += 4) { - struct device_node *phandle_node; - u32 rid_base = be32_to_cpup(map + 0); - u32 phandle = be32_to_cpup(map + 1); - u32 out_base = be32_to_cpup(map + 2); - u32 rid_len = be32_to_cpup(map + 3); - - if (rid_base & ~map_mask) { - pr_err("%pOF: Invalid %s translation - %s-mask (0x%x) ignores rid-base (0x%x)\n", - np, map_name, map_name, - map_mask, rid_base); - return -EFAULT; - } - - if (masked_rid < rid_base || masked_rid >= rid_base + rid_len) - continue; - - phandle_node = of_find_node_by_phandle(phandle); - if (!phandle_node) - return -ENODEV; - - if (target) { - if (*target) - of_node_put(phandle_node); - else - *target = phandle_node; - - if (*target != phandle_node) - continue; - } - - if (id_out) - *id_out = masked_rid - rid_base + out_base; - - pr_debug("%pOF: %s, using mask %08x, rid-base: %08x, out-base: %08x, length: %08x, rid: %08x -> %08x\n", - np, map_name, map_mask, rid_base, out_base, - rid_len, rid, masked_rid - rid_base + out_base); - return 0; - } - - pr_err("%pOF: Invalid %s translation - no match for rid 0x%x on %pOF\n", - np, map_name, rid, target && *target ? *target : NULL); - return -EFAULT; -} - #if IS_ENABLED(CONFIG_OF_IRQ) /** * of_irq_parse_pci - Resolve the interrupt for a PCI device diff --git a/include/linux/of.h b/include/linux/of.h index 99b0ebf49632..bf577ca3c8e7 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -550,6 +550,10 @@ bool of_console_check(struct device_node *dn, char *name, int index); extern int of_cpu_node_to_id(struct device_node *np); +int of_map_rid(struct device_node *np, u32 rid, + const char *map_name, const char *map_mask_name, + struct device_node **target, u32 *id_out); + #else /* CONFIG_OF */ static inline void of_core_init(void) @@ -952,6 +956,13 @@ static inline int of_cpu_node_to_id(struct device_node *np) return -ENODEV; } +static inline int of_map_rid(struct device_node *np, u32 rid, + const char *map_name, const char *map_mask_name, + struct device_node **target, u32 *id_out) +{ + return -EINVAL; +} + #define of_match_ptr(_ptr) NULL #define of_match_node(_matches, _node) NULL #endif /* CONFIG_OF */ diff --git a/include/linux/of_pci.h b/include/linux/of_pci.h index e83d87fc5673..21a89c4880fa 100644 --- a/include/linux/of_pci.h +++ b/include/linux/of_pci.h @@ -14,9 +14,6 @@ struct device_node *of_pci_find_child_device(struct device_node *parent, unsigned int devfn); int of_pci_get_devfn(struct device_node *np); void of_pci_check_probe_only(void); -int of_pci_map_rid(struct device_node *np, u32 rid, - const char *map_name, const char *map_mask_name, - struct device_node **target, u32 *id_out); #else static inline struct device_node *of_pci_find_child_device(struct device_node *parent, unsigned int devfn) @@ -29,13 +26,6 @@ static inline int of_pci_get_devfn(struct device_node *np) return -EINVAL; } -static inline int of_pci_map_rid(struct device_node *np, u32 rid, - const char *map_name, const char *map_mask_name, - struct device_node **target, u32 *id_out) -{ - return -EINVAL; -} - static inline void of_pci_check_probe_only(void) { } #endif -- cgit v1.2.3 From eab03e2a1a3d9d354943aff5ae5e4254ee1ec967 Mon Sep 17 00:00:00 2001 From: Nipun Gupta Date: Mon, 10 Sep 2018 19:19:18 +0530 Subject: iommu/arm-smmu: Add support for the fsl-mc bus Implement bus specific support for the fsl-mc bus including registering arm_smmu_ops and bus specific device add operations. Signed-off-by: Nipun Gupta Reviewed-by: Robin Murphy Signed-off-by: Joerg Roedel --- drivers/iommu/arm-smmu.c | 7 +++++++ drivers/iommu/iommu.c | 13 +++++++++++++ include/linux/fsl/mc.h | 8 ++++++++ include/linux/iommu.h | 2 ++ 4 files changed, 30 insertions(+) (limited to 'include/linux') diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index fd1b80ef9490..7baf4b03e8ef 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -52,6 +52,7 @@ #include #include +#include #include "io-pgtable.h" #include "arm-smmu-regs.h" @@ -1459,6 +1460,8 @@ static struct iommu_group *arm_smmu_device_group(struct device *dev) if (dev_is_pci(dev)) group = pci_device_group(dev); + else if (dev_is_fsl_mc(dev)) + group = fsl_mc_device_group(dev); else group = generic_device_group(dev); @@ -2036,6 +2039,10 @@ static void arm_smmu_bus_init(void) bus_set_iommu(&pci_bus_type, &arm_smmu_ops); } #endif +#ifdef CONFIG_FSL_MC_BUS + if (!iommu_present(&fsl_mc_bus_type)) + bus_set_iommu(&fsl_mc_bus_type, &arm_smmu_ops); +#endif } static int arm_smmu_device_probe(struct platform_device *pdev) diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 8c15c5980299..7e5cb7cf2bbe 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -32,6 +32,7 @@ #include #include #include +#include #include static struct kset *iommu_group_kset; @@ -1024,6 +1025,18 @@ struct iommu_group *pci_device_group(struct device *dev) return iommu_group_alloc(); } +/* Get the IOMMU group for device on fsl-mc bus */ +struct iommu_group *fsl_mc_device_group(struct device *dev) +{ + struct device *cont_dev = fsl_mc_cont_dev(dev); + struct iommu_group *group; + + group = iommu_group_get(cont_dev); + if (!group) + group = iommu_group_alloc(); + return group; +} + /** * iommu_group_get_for_dev - Find or create the IOMMU group for a device * @dev: target device diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index f27cb14088a4..dddaca17d684 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -351,6 +351,14 @@ int mc_send_command(struct fsl_mc_io *mc_io, struct fsl_mc_command *cmd); #define dev_is_fsl_mc(_dev) (0) #endif +/* Macro to check if a device is a container device */ +#define fsl_mc_is_cont_dev(_dev) (to_fsl_mc_device(_dev)->flags & \ + FSL_MC_IS_DPRC) + +/* Macro to get the container device of a MC device */ +#define fsl_mc_cont_dev(_dev) (fsl_mc_is_cont_dev(_dev) ? \ + (_dev) : (_dev)->parent) + /* * module_fsl_mc_driver() - Helper macro for drivers that don't do * anything special in module init/exit. This eliminates a lot of diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 87994c265bf5..70102df4b994 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -377,6 +377,8 @@ static inline void iommu_tlb_sync(struct iommu_domain *domain) extern struct iommu_group *pci_device_group(struct device *dev); /* Generic device grouping function */ extern struct iommu_group *generic_device_group(struct device *dev); +/* FSL-MC device grouping function */ +struct iommu_group *fsl_mc_device_group(struct device *dev); /** * struct iommu_fwspec - per-device IOMMU instance data -- cgit v1.2.3 From bee60e94a1e20ec0b8ffdafae270731d8fda4551 Mon Sep 17 00:00:00 2001 From: Ganapatrao Kulkarni Date: Wed, 5 Sep 2018 09:57:36 +0530 Subject: iommu/iova: Optimise attempts to allocate iova from 32bit address range As an optimisation for PCI devices, there is always first attempt been made to allocate iova from SAC address range. This will lead to unnecessary attempts, when there are no free ranges available. Adding fix to track recently failed iova address size and allow further attempts, only if requested size is lesser than a failed size. The size is updated when any replenish happens. Reviewed-by: Robin Murphy Signed-off-by: Ganapatrao Kulkarni Signed-off-by: Joerg Roedel --- drivers/iommu/iova.c | 22 +++++++++++++++------- include/linux/iova.h | 1 + 2 files changed, 16 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c index 83fe2621effe..f8d3ba247523 100644 --- a/drivers/iommu/iova.c +++ b/drivers/iommu/iova.c @@ -56,6 +56,7 @@ init_iova_domain(struct iova_domain *iovad, unsigned long granule, iovad->granule = granule; iovad->start_pfn = start_pfn; iovad->dma_32bit_pfn = 1UL << (32 - iova_shift(iovad)); + iovad->max32_alloc_size = iovad->dma_32bit_pfn; iovad->flush_cb = NULL; iovad->fq = NULL; iovad->anchor.pfn_lo = iovad->anchor.pfn_hi = IOVA_ANCHOR; @@ -139,8 +140,10 @@ __cached_rbnode_delete_update(struct iova_domain *iovad, struct iova *free) cached_iova = rb_entry(iovad->cached32_node, struct iova, node); if (free->pfn_hi < iovad->dma_32bit_pfn && - free->pfn_lo >= cached_iova->pfn_lo) + free->pfn_lo >= cached_iova->pfn_lo) { iovad->cached32_node = rb_next(&free->node); + iovad->max32_alloc_size = iovad->dma_32bit_pfn; + } cached_iova = rb_entry(iovad->cached_node, struct iova, node); if (free->pfn_lo >= cached_iova->pfn_lo) @@ -190,6 +193,10 @@ static int __alloc_and_insert_iova_range(struct iova_domain *iovad, /* Walk the tree backwards */ spin_lock_irqsave(&iovad->iova_rbtree_lock, flags); + if (limit_pfn <= iovad->dma_32bit_pfn && + size >= iovad->max32_alloc_size) + goto iova32_full; + curr = __get_cached_rbnode(iovad, limit_pfn); curr_iova = rb_entry(curr, struct iova, node); do { @@ -200,10 +207,8 @@ static int __alloc_and_insert_iova_range(struct iova_domain *iovad, curr_iova = rb_entry(curr, struct iova, node); } while (curr && new_pfn <= curr_iova->pfn_hi); - if (limit_pfn < size || new_pfn < iovad->start_pfn) { - spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags); - return -ENOMEM; - } + if (limit_pfn < size || new_pfn < iovad->start_pfn) + goto iova32_full; /* pfn_lo will point to size aligned address if size_aligned is set */ new->pfn_lo = new_pfn; @@ -214,9 +219,12 @@ static int __alloc_and_insert_iova_range(struct iova_domain *iovad, __cached_rbnode_insert_update(iovad, new); spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags); - - return 0; + +iova32_full: + iovad->max32_alloc_size = size; + spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags); + return -ENOMEM; } static struct kmem_cache *iova_cache; diff --git a/include/linux/iova.h b/include/linux/iova.h index 928442dda565..0b93bf96693e 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -75,6 +75,7 @@ struct iova_domain { unsigned long granule; /* pfn granularity for this domain */ unsigned long start_pfn; /* Lower limit for this domain */ unsigned long dma_32bit_pfn; + unsigned long max32_alloc_size; /* Size of last failed allocation */ struct iova anchor; /* rbtree lookup anchor */ struct iova_rcache rcaches[IOVA_RANGE_CACHE_MAX_SIZE]; /* IOVA range caches */ -- cgit v1.2.3 From 6af588fed39178c8e118fcf9cb6664e58a1fbe88 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Wed, 12 Sep 2018 16:24:12 +0100 Subject: iommu: Add fast hook for getting DMA domains While iommu_get_domain_for_dev() is the robust way for arbitrary IOMMU API callers to retrieve the domain pointer, for DMA ops domains it doesn't scale well for large systems and multi-queue devices, since the momentary refcount adjustment will lead to exclusive cacheline contention when multiple CPUs are operating in parallel on different mappings for the same device. In the case of DMA ops domains, however, this refcounting is actually unnecessary, since they already imply that the group exists and is managed by platform code and IOMMU internals (by virtue of iommu_group_get_for_dev()) such that a reference will already be held for the lifetime of the device. Thus we can avoid the bottleneck by providing a fast lookup specifically for the DMA code to retrieve the default domain it already knows it has set up - a simple read-only dereference plays much nicer with cache-coherency protocols. Signed-off-by: Robin Murphy Tested-by: Will Deacon Signed-off-by: Joerg Roedel --- drivers/iommu/iommu.c | 9 +++++++++ include/linux/iommu.h | 1 + 2 files changed, 10 insertions(+) (limited to 'include/linux') diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 8c15c5980299..9d70344204fe 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -1415,6 +1415,15 @@ struct iommu_domain *iommu_get_domain_for_dev(struct device *dev) } EXPORT_SYMBOL_GPL(iommu_get_domain_for_dev); +/* + * For IOMMU_DOMAIN_DMA implementations which already provide their own + * guarantees that the group and its default domain are valid and correct. + */ +struct iommu_domain *iommu_get_dma_domain(struct device *dev) +{ + return dev->iommu_group->default_domain; +} + /* * IOMMU groups are really the natrual working unit of the IOMMU, but * the IOMMU API works on domains and devices. Bridge that gap by diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 87994c265bf5..c783648d4060 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -293,6 +293,7 @@ extern int iommu_attach_device(struct iommu_domain *domain, extern void iommu_detach_device(struct iommu_domain *domain, struct device *dev); extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev); +extern struct iommu_domain *iommu_get_dma_domain(struct device *dev); extern int iommu_map(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t size, int prot); extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, -- cgit v1.2.3 From 26b86092c4650311256fa2372ced7e1e17d97d7b Mon Sep 17 00:00:00 2001 From: Sohil Mehta Date: Tue, 11 Sep 2018 17:11:36 -0700 Subject: iommu/vt-d: Relocate struct/function declarations to its header files To reuse the static functions and the struct declarations, move them to corresponding header files and export the needed functions. Cc: Lu Baolu Cc: Fenghua Yu Cc: Jacob Pan Cc: Ashok Raj Reviewed-by: Andy Shevchenko Signed-off-by: Gayatri Kammela Signed-off-by: Sohil Mehta Signed-off-by: Joerg Roedel --- arch/x86/include/asm/irq_remapping.h | 2 ++ drivers/iommu/intel-iommu.c | 31 +++---------------------------- drivers/iommu/intel_irq_remapping.c | 2 +- include/linux/intel-iommu.h | 30 ++++++++++++++++++++++++++++++ 4 files changed, 36 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h index 5f26962eff42..67ed72f31cc2 100644 --- a/arch/x86/include/asm/irq_remapping.h +++ b/arch/x86/include/asm/irq_remapping.h @@ -45,6 +45,8 @@ struct vcpu_data { #ifdef CONFIG_IRQ_REMAP +extern raw_spinlock_t irq_2_ir_lock; + extern bool irq_remapping_cap(enum irq_remap_cap cap); extern void set_irq_remapping_broken(void); extern int irq_remapping_prepare(void); diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 5f3f10cf9d9d..b5868c757995 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -185,16 +185,6 @@ static int rwbf_quirk; static int force_on = 0; int intel_iommu_tboot_noforce; -/* - * 0: Present - * 1-11: Reserved - * 12-63: Context Ptr (12 - (haw-1)) - * 64-127: Reserved - */ -struct root_entry { - u64 lo; - u64 hi; -}; #define ROOT_ENTRY_NR (VTD_PAGE_SIZE/sizeof(struct root_entry)) /* @@ -220,21 +210,6 @@ static phys_addr_t root_entry_uctp(struct root_entry *re) return re->hi & VTD_PAGE_MASK; } -/* - * low 64 bits: - * 0: present - * 1: fault processing disable - * 2-3: translation type - * 12-63: address space root - * high 64 bits: - * 0-2: address width - * 3-6: aval - * 8-23: domain id - */ -struct context_entry { - u64 lo; - u64 hi; -}; static inline void context_clear_pasid_enable(struct context_entry *context) { @@ -261,7 +236,7 @@ static inline bool __context_present(struct context_entry *context) return (context->lo & 1); } -static inline bool context_present(struct context_entry *context) +bool context_present(struct context_entry *context) { return context_pasid_enabled(context) ? __context_present(context) : @@ -788,8 +763,8 @@ static void domain_update_iommu_cap(struct dmar_domain *domain) domain->iommu_superpage = domain_update_iommu_superpage(NULL); } -static inline struct context_entry *iommu_context_addr(struct intel_iommu *iommu, - u8 bus, u8 devfn, int alloc) +struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus, + u8 devfn, int alloc) { struct root_entry *root = &iommu->root_entry[bus]; struct context_entry *context; diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c index 967450bd421a..c2d6c11431de 100644 --- a/drivers/iommu/intel_irq_remapping.c +++ b/drivers/iommu/intel_irq_remapping.c @@ -76,7 +76,7 @@ static struct hpet_scope ir_hpet[MAX_HPET_TBS]; * in single-threaded environment with interrupt disabled, so no need to tabke * the dmar_global_lock. */ -static DEFINE_RAW_SPINLOCK(irq_2_ir_lock); +DEFINE_RAW_SPINLOCK(irq_2_ir_lock); static const struct irq_domain_ops intel_ir_domain_ops; static void iommu_disable_irq_remapping(struct intel_iommu *iommu); diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 28004d74ae04..b7cf32e8ae1f 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -389,6 +389,33 @@ struct pasid_entry; struct pasid_state_entry; struct page_req_dsc; +/* + * 0: Present + * 1-11: Reserved + * 12-63: Context Ptr (12 - (haw-1)) + * 64-127: Reserved + */ +struct root_entry { + u64 lo; + u64 hi; +}; + +/* + * low 64 bits: + * 0: present + * 1: fault processing disable + * 2-3: translation type + * 12-63: address space root + * high 64 bits: + * 0-2: address width + * 3-6: aval + * 8-23: domain id + */ +struct context_entry { + u64 lo; + u64 hi; +}; + struct dmar_domain { int nid; /* node id */ @@ -559,5 +586,8 @@ extern struct intel_iommu *intel_svm_device_to_iommu(struct device *dev); #endif extern const struct attribute_group *intel_iommu_groups[]; +bool context_present(struct context_entry *context); +struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus, + u8 devfn, int alloc); #endif -- cgit v1.2.3 From 4a2d80dbadb72b998641af32d8dd4b7b39e72aa0 Mon Sep 17 00:00:00 2001 From: Sohil Mehta Date: Tue, 11 Sep 2018 17:11:37 -0700 Subject: iommu/vt-d: Update register definitions to VT-d 3.0 specification Add new register definitions added in the VT-d 3.0 specification. Also include registers that were missing previously. Cc: Lu Baolu Cc: Fenghua Yu Cc: Jacob Pan Cc: Ashok Raj Cc: Gayatri Kammela Signed-off-by: Sohil Mehta Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index b7cf32e8ae1f..3bdb9aa198af 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -72,6 +72,42 @@ #define DMAR_PEDATA_REG 0xe4 /* Page request event interrupt data register */ #define DMAR_PEADDR_REG 0xe8 /* Page request event interrupt addr register */ #define DMAR_PEUADDR_REG 0xec /* Page request event Upper address register */ +#define DMAR_MTRRCAP_REG 0x100 /* MTRR capability register */ +#define DMAR_MTRRDEF_REG 0x108 /* MTRR default type register */ +#define DMAR_MTRR_FIX64K_00000_REG 0x120 /* MTRR Fixed range registers */ +#define DMAR_MTRR_FIX16K_80000_REG 0x128 +#define DMAR_MTRR_FIX16K_A0000_REG 0x130 +#define DMAR_MTRR_FIX4K_C0000_REG 0x138 +#define DMAR_MTRR_FIX4K_C8000_REG 0x140 +#define DMAR_MTRR_FIX4K_D0000_REG 0x148 +#define DMAR_MTRR_FIX4K_D8000_REG 0x150 +#define DMAR_MTRR_FIX4K_E0000_REG 0x158 +#define DMAR_MTRR_FIX4K_E8000_REG 0x160 +#define DMAR_MTRR_FIX4K_F0000_REG 0x168 +#define DMAR_MTRR_FIX4K_F8000_REG 0x170 +#define DMAR_MTRR_PHYSBASE0_REG 0x180 /* MTRR Variable range registers */ +#define DMAR_MTRR_PHYSMASK0_REG 0x188 +#define DMAR_MTRR_PHYSBASE1_REG 0x190 +#define DMAR_MTRR_PHYSMASK1_REG 0x198 +#define DMAR_MTRR_PHYSBASE2_REG 0x1a0 +#define DMAR_MTRR_PHYSMASK2_REG 0x1a8 +#define DMAR_MTRR_PHYSBASE3_REG 0x1b0 +#define DMAR_MTRR_PHYSMASK3_REG 0x1b8 +#define DMAR_MTRR_PHYSBASE4_REG 0x1c0 +#define DMAR_MTRR_PHYSMASK4_REG 0x1c8 +#define DMAR_MTRR_PHYSBASE5_REG 0x1d0 +#define DMAR_MTRR_PHYSMASK5_REG 0x1d8 +#define DMAR_MTRR_PHYSBASE6_REG 0x1e0 +#define DMAR_MTRR_PHYSMASK6_REG 0x1e8 +#define DMAR_MTRR_PHYSBASE7_REG 0x1f0 +#define DMAR_MTRR_PHYSMASK7_REG 0x1f8 +#define DMAR_MTRR_PHYSBASE8_REG 0x200 +#define DMAR_MTRR_PHYSMASK8_REG 0x208 +#define DMAR_MTRR_PHYSBASE9_REG 0x210 +#define DMAR_MTRR_PHYSMASK9_REG 0x218 +#define DMAR_VCCAP_REG 0xe00 /* Virtual command capability register */ +#define DMAR_VCMD_REG 0xe10 /* Virtual command register */ +#define DMAR_VCRSP_REG 0xe20 /* Virtual command response register */ #define OFFSET_STRIDE (9) -- cgit v1.2.3 From ee2636b8670b1ab2a02a65923a9bef59e9199c37 Mon Sep 17 00:00:00 2001 From: Sohil Mehta Date: Tue, 11 Sep 2018 17:11:38 -0700 Subject: iommu/vt-d: Enable base Intel IOMMU debugfs support Add a new config option CONFIG_INTEL_IOMMU_DEBUGFS and do the base enabling for Intel IOMMU debugfs. Cc: Lu Baolu Cc: Fenghua Yu Cc: Ashok Raj Cc: Jacob Pan Co-Developed-by: Gayatri Kammela Signed-off-by: Gayatri Kammela Reviewed-by: Andy Shevchenko Reviewed-by: Lu Baolu Signed-off-by: Sohil Mehta Signed-off-by: Joerg Roedel --- drivers/iommu/Kconfig | 13 +++++++++++++ drivers/iommu/Makefile | 1 + drivers/iommu/intel-iommu-debugfs.c | 20 ++++++++++++++++++++ drivers/iommu/intel-iommu.c | 1 + include/linux/intel-iommu.h | 6 ++++++ 5 files changed, 41 insertions(+) create mode 100644 drivers/iommu/intel-iommu-debugfs.c (limited to 'include/linux') diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index c60395b7470f..51ba19c8847b 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -186,6 +186,19 @@ config INTEL_IOMMU and include PCI device scope covered by these DMA remapping devices. +config INTEL_IOMMU_DEBUGFS + bool "Export Intel IOMMU internals in Debugfs" + depends on INTEL_IOMMU && IOMMU_DEBUGFS + help + !!!WARNING!!! + + DO NOT ENABLE THIS OPTION UNLESS YOU REALLY KNOW WHAT YOU ARE DOING!!! + + Expose Intel IOMMU internals in Debugfs. + + This option is -NOT- intended for production environments, and should + only be enabled for debugging Intel IOMMU. + config INTEL_IOMMU_SVM bool "Support for Shared Virtual Memory with Intel IOMMU" depends on INTEL_IOMMU && X86 diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile index ab5eba6edf82..a158a68c8ea8 100644 --- a/drivers/iommu/Makefile +++ b/drivers/iommu/Makefile @@ -17,6 +17,7 @@ obj-$(CONFIG_ARM_SMMU) += arm-smmu.o obj-$(CONFIG_ARM_SMMU_V3) += arm-smmu-v3.o obj-$(CONFIG_DMAR_TABLE) += dmar.o obj-$(CONFIG_INTEL_IOMMU) += intel-iommu.o intel-pasid.o +obj-$(CONFIG_INTEL_IOMMU_DEBUGFS) += intel-iommu-debugfs.o obj-$(CONFIG_INTEL_IOMMU_SVM) += intel-svm.o obj-$(CONFIG_IPMMU_VMSA) += ipmmu-vmsa.o obj-$(CONFIG_IRQ_REMAP) += intel_irq_remapping.o irq_remapping.o diff --git a/drivers/iommu/intel-iommu-debugfs.c b/drivers/iommu/intel-iommu-debugfs.c new file mode 100644 index 000000000000..33e0a6c12d92 --- /dev/null +++ b/drivers/iommu/intel-iommu-debugfs.c @@ -0,0 +1,20 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright © 2018 Intel Corporation. + * + * Authors: Gayatri Kammela + * Sohil Mehta + * Jacob Pan + */ + +#include +#include +#include +#include + +#include + +void __init intel_iommu_debugfs_init(void) +{ + debugfs_create_dir("intel", iommu_debugfs_dir); +} diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index b5868c757995..b9cf7c8c1616 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -4837,6 +4837,7 @@ int __init intel_iommu_init(void) cpuhp_setup_state(CPUHP_IOMMU_INTEL_DEAD, "iommu/intel:dead", NULL, intel_iommu_cpu_dead); intel_iommu_enabled = 1; + intel_iommu_debugfs_init(); return 0; diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 3bdb9aa198af..b0ae25837361 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -621,6 +621,12 @@ extern int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_ extern struct intel_iommu *intel_svm_device_to_iommu(struct device *dev); #endif +#ifdef CONFIG_INTEL_IOMMU_DEBUGFS +void intel_iommu_debugfs_init(void); +#else +static inline void intel_iommu_debugfs_init(void) {} +#endif /* CONFIG_INTEL_IOMMU_DEBUGFS */ + extern const struct attribute_group *intel_iommu_groups[]; bool context_present(struct context_entry *context); struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus, -- cgit v1.2.3 From 5131e08cd0f8a3faa30c1cdaf53940d6bce1715a Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Wed, 19 Sep 2018 11:12:58 +0100 Subject: iommu: Remove .domain_{get,set}_windows Since these are trivially handled by the .domain_{get,set}_attr callbacks when relevant, we can streamline struct iommu_ops for everyone. Signed-off-by: Robin Murphy Signed-off-by: Joerg Roedel --- drivers/iommu/fsl_pamu_domain.c | 125 ++++++++++++++++------------------------ include/linux/iommu.h | 6 -- 2 files changed, 51 insertions(+), 80 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/fsl_pamu_domain.c b/drivers/iommu/fsl_pamu_domain.c index f83965ee3095..a906ce8cf83b 100644 --- a/drivers/iommu/fsl_pamu_domain.c +++ b/drivers/iommu/fsl_pamu_domain.c @@ -814,11 +814,59 @@ static int configure_domain_dma_state(struct fsl_dma_domain *dma_domain, bool en return 0; } +static int fsl_pamu_set_windows(struct iommu_domain *domain, u32 w_count) +{ + struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain); + unsigned long flags; + int ret; + + spin_lock_irqsave(&dma_domain->domain_lock, flags); + /* Ensure domain is inactive i.e. DMA should be disabled for the domain */ + if (dma_domain->enabled) { + pr_debug("Can't set geometry attributes as domain is active\n"); + spin_unlock_irqrestore(&dma_domain->domain_lock, flags); + return -EBUSY; + } + + /* Ensure that the geometry has been set for the domain */ + if (!dma_domain->geom_size) { + pr_debug("Please configure geometry before setting the number of windows\n"); + spin_unlock_irqrestore(&dma_domain->domain_lock, flags); + return -EINVAL; + } + + /* + * Ensure we have valid window count i.e. it should be less than + * maximum permissible limit and should be a power of two. + */ + if (w_count > pamu_get_max_subwin_cnt() || !is_power_of_2(w_count)) { + pr_debug("Invalid window count\n"); + spin_unlock_irqrestore(&dma_domain->domain_lock, flags); + return -EINVAL; + } + + ret = pamu_set_domain_geometry(dma_domain, &domain->geometry, + w_count > 1 ? w_count : 0); + if (!ret) { + kfree(dma_domain->win_arr); + dma_domain->win_arr = kcalloc(w_count, + sizeof(*dma_domain->win_arr), + GFP_ATOMIC); + if (!dma_domain->win_arr) { + spin_unlock_irqrestore(&dma_domain->domain_lock, flags); + return -ENOMEM; + } + dma_domain->win_cnt = w_count; + } + spin_unlock_irqrestore(&dma_domain->domain_lock, flags); + + return ret; +} + static int fsl_pamu_set_domain_attr(struct iommu_domain *domain, enum iommu_attr attr_type, void *data) { struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain); - u32 *count; int ret = 0; switch (attr_type) { @@ -832,13 +880,7 @@ static int fsl_pamu_set_domain_attr(struct iommu_domain *domain, ret = configure_domain_dma_state(dma_domain, *(int *)data); break; case DOMAIN_ATTR_WINDOWS: - count = data; - - if (domain->ops->domain_set_windows != NULL) - ret = domain->ops->domain_set_windows(domain, *count); - else - ret = -ENODEV; - + ret = fsl_pamu_set_windows(domain, *(u32 *)data); break; default: pr_debug("Unsupported attribute type\n"); @@ -853,7 +895,6 @@ static int fsl_pamu_get_domain_attr(struct iommu_domain *domain, enum iommu_attr attr_type, void *data) { struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain); - u32 *count; int ret = 0; switch (attr_type) { @@ -868,13 +909,7 @@ static int fsl_pamu_get_domain_attr(struct iommu_domain *domain, *(int *)data = DOMAIN_ATTR_FSL_PAMUV1; break; case DOMAIN_ATTR_WINDOWS: - count = data; - - if (domain->ops->domain_get_windows != NULL) - *count = domain->ops->domain_get_windows(domain); - else - ret = -ENODEV; - + *(u32 *)data = dma_domain->win_cnt; break; default: pr_debug("Unsupported attribute type\n"); @@ -1014,62 +1049,6 @@ static void fsl_pamu_remove_device(struct device *dev) iommu_group_remove_device(dev); } -static int fsl_pamu_set_windows(struct iommu_domain *domain, u32 w_count) -{ - struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain); - unsigned long flags; - int ret; - - spin_lock_irqsave(&dma_domain->domain_lock, flags); - /* Ensure domain is inactive i.e. DMA should be disabled for the domain */ - if (dma_domain->enabled) { - pr_debug("Can't set geometry attributes as domain is active\n"); - spin_unlock_irqrestore(&dma_domain->domain_lock, flags); - return -EBUSY; - } - - /* Ensure that the geometry has been set for the domain */ - if (!dma_domain->geom_size) { - pr_debug("Please configure geometry before setting the number of windows\n"); - spin_unlock_irqrestore(&dma_domain->domain_lock, flags); - return -EINVAL; - } - - /* - * Ensure we have valid window count i.e. it should be less than - * maximum permissible limit and should be a power of two. - */ - if (w_count > pamu_get_max_subwin_cnt() || !is_power_of_2(w_count)) { - pr_debug("Invalid window count\n"); - spin_unlock_irqrestore(&dma_domain->domain_lock, flags); - return -EINVAL; - } - - ret = pamu_set_domain_geometry(dma_domain, &domain->geometry, - w_count > 1 ? w_count : 0); - if (!ret) { - kfree(dma_domain->win_arr); - dma_domain->win_arr = kcalloc(w_count, - sizeof(*dma_domain->win_arr), - GFP_ATOMIC); - if (!dma_domain->win_arr) { - spin_unlock_irqrestore(&dma_domain->domain_lock, flags); - return -ENOMEM; - } - dma_domain->win_cnt = w_count; - } - spin_unlock_irqrestore(&dma_domain->domain_lock, flags); - - return ret; -} - -static u32 fsl_pamu_get_windows(struct iommu_domain *domain) -{ - struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain); - - return dma_domain->win_cnt; -} - static const struct iommu_ops fsl_pamu_ops = { .capable = fsl_pamu_capable, .domain_alloc = fsl_pamu_domain_alloc, @@ -1078,8 +1057,6 @@ static const struct iommu_ops fsl_pamu_ops = { .detach_dev = fsl_pamu_detach_device, .domain_window_enable = fsl_pamu_window_enable, .domain_window_disable = fsl_pamu_window_disable, - .domain_get_windows = fsl_pamu_get_windows, - .domain_set_windows = fsl_pamu_set_windows, .iova_to_phys = fsl_pamu_iova_to_phys, .domain_set_attr = fsl_pamu_set_domain_attr, .domain_get_attr = fsl_pamu_get_domain_attr, diff --git a/include/linux/iommu.h b/include/linux/iommu.h index c783648d4060..c08ba5d2d451 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -181,8 +181,6 @@ struct iommu_resv_region { * @apply_resv_region: Temporary helper call-back for iova reserved ranges * @domain_window_enable: Configure and enable a particular window for a domain * @domain_window_disable: Disable a particular window for a domain - * @domain_set_windows: Set the number of windows for a domain - * @domain_get_windows: Return the number of windows for a domain * @of_xlate: add OF master IDs to iommu grouping * @pgsize_bitmap: bitmap of all possible supported page sizes */ @@ -223,10 +221,6 @@ struct iommu_ops { int (*domain_window_enable)(struct iommu_domain *domain, u32 wnd_nr, phys_addr_t paddr, u64 size, int prot); void (*domain_window_disable)(struct iommu_domain *domain, u32 wnd_nr); - /* Set the number of windows per domain */ - int (*domain_set_windows)(struct iommu_domain *domain, u32 w_count); - /* Get the number of windows per domain */ - u32 (*domain_get_windows)(struct iommu_domain *domain); int (*of_xlate)(struct device *dev, struct of_phandle_args *args); bool (*is_attach_deferred)(struct iommu_domain *domain, struct device *dev); -- cgit v1.2.3 From c2c729415b2d21329104fecaa86878d295f1041f Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Thu, 20 Sep 2018 13:17:42 -0600 Subject: coresight: platform: Cleanup coresight connection handling The platform code parses the component connections and populates a platform-description of the output connections in arrays of fields (which is never freed). This is later copied in the coresight_register to a newly allocated area, represented by coresight_connection(s). This patch cleans up the code dealing with connections by making use of the "coresight_connection" structure right at the platform code and lets the generic driver simply re-use information provided by the platform. Thus making it reader friendly as well as avoiding the wastage of unused memory. Signed-off-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight.c | 21 +----------- drivers/hwtracing/coresight/of_coresight.c | 53 +++++++++++------------------- include/linux/coresight.h | 9 ++--- 3 files changed, 22 insertions(+), 61 deletions(-) (limited to 'include/linux') diff --git a/drivers/hwtracing/coresight/coresight.c b/drivers/hwtracing/coresight/coresight.c index 9fd0c387e678..5e8880ca8078 100644 --- a/drivers/hwtracing/coresight/coresight.c +++ b/drivers/hwtracing/coresight/coresight.c @@ -995,13 +995,11 @@ postcore_initcall(coresight_init); struct coresight_device *coresight_register(struct coresight_desc *desc) { - int i; int ret; int link_subtype; int nr_refcnts = 1; atomic_t *refcnts = NULL; struct coresight_device *csdev; - struct coresight_connection *conns = NULL; csdev = kzalloc(sizeof(*csdev), GFP_KERNEL); if (!csdev) { @@ -1030,22 +1028,7 @@ struct coresight_device *coresight_register(struct coresight_desc *desc) csdev->nr_inport = desc->pdata->nr_inport; csdev->nr_outport = desc->pdata->nr_outport; - /* Initialise connections if there is at least one outport */ - if (csdev->nr_outport) { - conns = kcalloc(csdev->nr_outport, sizeof(*conns), GFP_KERNEL); - if (!conns) { - ret = -ENOMEM; - goto err_free_refcnts; - } - - for (i = 0; i < csdev->nr_outport; i++) { - conns[i].outport = desc->pdata->outports[i]; - conns[i].child_name = desc->pdata->child_names[i]; - conns[i].child_port = desc->pdata->child_ports[i]; - } - } - - csdev->conns = conns; + csdev->conns = desc->pdata->conns; csdev->type = desc->type; csdev->subtype = desc->subtype; @@ -1078,8 +1061,6 @@ struct coresight_device *coresight_register(struct coresight_desc *desc) return csdev; -err_free_refcnts: - kfree(refcnts); err_free_csdev: kfree(csdev); err_out: diff --git a/drivers/hwtracing/coresight/of_coresight.c b/drivers/hwtracing/coresight/of_coresight.c index 44903d35009f..e8fb4e124744 100644 --- a/drivers/hwtracing/coresight/of_coresight.c +++ b/drivers/hwtracing/coresight/of_coresight.c @@ -75,29 +75,13 @@ static void of_coresight_get_ports(const struct device_node *node, static int of_coresight_alloc_memory(struct device *dev, struct coresight_platform_data *pdata) { - /* List of output port on this component */ - pdata->outports = devm_kcalloc(dev, - pdata->nr_outport, - sizeof(*pdata->outports), - GFP_KERNEL); - if (!pdata->outports) - return -ENOMEM; - - /* Children connected to this component via @outports */ - pdata->child_names = devm_kcalloc(dev, - pdata->nr_outport, - sizeof(*pdata->child_names), - GFP_KERNEL); - if (!pdata->child_names) - return -ENOMEM; - - /* Port number on the child this component is connected to */ - pdata->child_ports = devm_kcalloc(dev, - pdata->nr_outport, - sizeof(*pdata->child_ports), - GFP_KERNEL); - if (!pdata->child_ports) - return -ENOMEM; + if (pdata->nr_outport) { + pdata->conns = devm_kzalloc(dev, pdata->nr_outport * + sizeof(*pdata->conns), + GFP_KERNEL); + if (!pdata->conns) + return -ENOMEM; + } return 0; } @@ -121,7 +105,7 @@ EXPORT_SYMBOL_GPL(of_coresight_get_cpu); /* * of_coresight_parse_endpoint : Parse the given output endpoint @ep - * and fill the connection information in @pdata[@i]. + * and fill the connection information in @conn * * Parses the local port, remote device name and the remote port. * @@ -133,8 +117,7 @@ EXPORT_SYMBOL_GPL(of_coresight_get_cpu); */ static int of_coresight_parse_endpoint(struct device *dev, struct device_node *ep, - struct coresight_platform_data *pdata, - int i) + struct coresight_connection *conn) { int ret = 0; struct of_endpoint endpoint, rendpoint; @@ -166,11 +149,11 @@ static int of_coresight_parse_endpoint(struct device *dev, break; } - pdata->outports[i] = endpoint.port; - pdata->child_names[i] = devm_kstrdup(dev, - dev_name(rdev), - GFP_KERNEL); - pdata->child_ports[i] = rendpoint.port; + conn->outport = endpoint.port; + conn->child_name = devm_kstrdup(dev, + dev_name(rdev), + GFP_KERNEL); + conn->child_port = rendpoint.port; /* Connection record updated */ ret = 1; } while (0); @@ -189,8 +172,9 @@ struct coresight_platform_data * of_get_coresight_platform_data(struct device *dev, const struct device_node *node) { - int i = 0, ret = 0; + int ret = 0; struct coresight_platform_data *pdata; + struct coresight_connection *conn; struct device_node *ep = NULL; pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL); @@ -212,6 +196,7 @@ of_get_coresight_platform_data(struct device *dev, if (ret) return ERR_PTR(ret); + conn = pdata->conns; /* Iterate through each port to discover topology */ while ((ep = of_graph_get_next_endpoint(node, ep))) { /* @@ -221,10 +206,10 @@ of_get_coresight_platform_data(struct device *dev, if (of_coresight_ep_is_input(ep)) continue; - ret = of_coresight_parse_endpoint(dev, ep, pdata, i); + ret = of_coresight_parse_endpoint(dev, ep, conn); switch (ret) { case 1: - i++; /* Fall through */ + conn++; /* Fall through */ case 0: break; default: diff --git a/include/linux/coresight.h b/include/linux/coresight.h index d828a6efe0b1..41e1f4333bf2 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -94,20 +94,15 @@ union coresight_dev_subtype { * @cpu: the CPU a source belongs to. Only applicable for ETM/PTMs. * @name: name of the component as shown under sysfs. * @nr_inport: number of input ports for this component. - * @outports: list of remote endpoint port number. - * @child_names:name of all child components connected to this device. - * @child_ports:child component port number the current component is - connected to. * @nr_outport: number of output ports for this component. + * @conns: Array of nr_outport connections from this component */ struct coresight_platform_data { int cpu; const char *name; int nr_inport; - int *outports; - const char **child_names; - int *child_ports; int nr_outport; + struct coresight_connection *conns; }; /** -- cgit v1.2.3 From 7ec786ad193beb5579223174e119805569a7af3b Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Thu, 20 Sep 2018 13:17:54 -0600 Subject: coresight: perf: Remove reset_buffer call back for sinks Right now we issue an update_buffer() and reset_buffer() call backs in succession when we stop tracing an event. The update_buffer is supposed to check the status of the buffer and make sure the ring buffer is updated with the trace data. And we store information about the size of the data collected only to be consumed by the reset_buffer callback which always follows the update_buffer. This was originally designed for handling future IPs which could trigger a buffer overflow interrupt. This patch gets rid of the reset_buffer callback altogether and performs the actions in update_buffer, making it return the size collected. We can always add the support for handling the overflow interrupt case later. This removes some not-so pretty hack (storing the new head in the size field for snapshot mode) and cleans it up a little bit. Cc: Mathieu Poirier Signed-off-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight-etb10.c | 56 +++++------------------ drivers/hwtracing/coresight/coresight-etm-perf.c | 9 +--- drivers/hwtracing/coresight/coresight-tmc-etf.c | 58 +++++------------------- include/linux/coresight.h | 6 +-- 4 files changed, 26 insertions(+), 103 deletions(-) (limited to 'include/linux') diff --git a/drivers/hwtracing/coresight/coresight-etb10.c b/drivers/hwtracing/coresight/coresight-etb10.c index 3d4b6df32a06..dba75c905e57 100644 --- a/drivers/hwtracing/coresight/coresight-etb10.c +++ b/drivers/hwtracing/coresight/coresight-etb10.c @@ -319,37 +319,7 @@ static int etb_set_buffer(struct coresight_device *csdev, return ret; } -static unsigned long etb_reset_buffer(struct coresight_device *csdev, - struct perf_output_handle *handle, - void *sink_config) -{ - unsigned long size = 0; - struct cs_buffers *buf = sink_config; - - if (buf) { - /* - * In snapshot mode ->data_size holds the new address of the - * ring buffer's head. The size itself is the whole address - * range since we want the latest information. - */ - if (buf->snapshot) - handle->head = local_xchg(&buf->data_size, - buf->nr_pages << PAGE_SHIFT); - - /* - * Tell the tracer PMU how much we got in this run and if - * something went wrong along the way. Nobody else can use - * this cs_buffers instance until we are done. As such - * resetting parameters here and squaring off with the ring - * buffer API in the tracer PMU is fine. - */ - size = local_xchg(&buf->data_size, 0); - } - - return size; -} - -static void etb_update_buffer(struct coresight_device *csdev, +static unsigned long etb_update_buffer(struct coresight_device *csdev, struct perf_output_handle *handle, void *sink_config) { @@ -358,13 +328,13 @@ static void etb_update_buffer(struct coresight_device *csdev, u8 *buf_ptr; const u32 *barrier; u32 read_ptr, write_ptr, capacity; - u32 status, read_data, to_read; - unsigned long offset; + u32 status, read_data; + unsigned long offset, to_read; struct cs_buffers *buf = sink_config; struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); if (!buf) - return; + return 0; capacity = drvdata->buffer_depth * ETB_FRAME_SIZE_WORDS; @@ -469,18 +439,17 @@ static void etb_update_buffer(struct coresight_device *csdev, writel_relaxed(0x0, drvdata->base + ETB_RAM_WRITE_POINTER); /* - * In snapshot mode all we have to do is communicate to - * perf_aux_output_end() the address of the current head. In full - * trace mode the same function expects a size to move rb->aux_head - * forward. + * In snapshot mode we have to update the handle->head to point + * to the new location. */ - if (buf->snapshot) - local_set(&buf->data_size, (cur * PAGE_SIZE) + offset); - else - local_add(to_read, &buf->data_size); - + if (buf->snapshot) { + handle->head = (cur * PAGE_SIZE) + offset; + to_read = buf->nr_pages << PAGE_SHIFT; + } etb_enable_hw(drvdata); CS_LOCK(drvdata->base); + + return to_read; } static const struct coresight_ops_sink etb_sink_ops = { @@ -489,7 +458,6 @@ static const struct coresight_ops_sink etb_sink_ops = { .alloc_buffer = etb_alloc_buffer, .free_buffer = etb_free_buffer, .set_buffer = etb_set_buffer, - .reset_buffer = etb_reset_buffer, .update_buffer = etb_update_buffer, }; diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index 6db76ce6ba5f..ad87441f65d7 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -369,15 +369,8 @@ static void etm_event_stop(struct perf_event *event, int mode) if (!sink_ops(sink)->update_buffer) return; - sink_ops(sink)->update_buffer(sink, handle, + size = sink_ops(sink)->update_buffer(sink, handle, event_data->snk_config); - - if (!sink_ops(sink)->reset_buffer) - return; - - size = sink_ops(sink)->reset_buffer(sink, handle, - event_data->snk_config); - perf_aux_output_end(handle, size); } diff --git a/drivers/hwtracing/coresight/coresight-tmc-etf.c b/drivers/hwtracing/coresight/coresight-tmc-etf.c index 434003a43346..31a98f915641 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etf.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etf.c @@ -349,36 +349,7 @@ static int tmc_set_etf_buffer(struct coresight_device *csdev, return ret; } -static unsigned long tmc_reset_etf_buffer(struct coresight_device *csdev, - struct perf_output_handle *handle, - void *sink_config) -{ - long size = 0; - struct cs_buffers *buf = sink_config; - - if (buf) { - /* - * In snapshot mode ->data_size holds the new address of the - * ring buffer's head. The size itself is the whole address - * range since we want the latest information. - */ - if (buf->snapshot) - handle->head = local_xchg(&buf->data_size, - buf->nr_pages << PAGE_SHIFT); - /* - * Tell the tracer PMU how much we got in this run and if - * something went wrong along the way. Nobody else can use - * this cs_buffers instance until we are done. As such - * resetting parameters here and squaring off with the ring - * buffer API in the tracer PMU is fine. - */ - size = local_xchg(&buf->data_size, 0); - } - - return size; -} - -static void tmc_update_etf_buffer(struct coresight_device *csdev, +static unsigned long tmc_update_etf_buffer(struct coresight_device *csdev, struct perf_output_handle *handle, void *sink_config) { @@ -387,17 +358,17 @@ static void tmc_update_etf_buffer(struct coresight_device *csdev, const u32 *barrier; u32 *buf_ptr; u64 read_ptr, write_ptr; - u32 status, to_read; - unsigned long offset; + u32 status; + unsigned long offset, to_read; struct cs_buffers *buf = sink_config; struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); if (!buf) - return; + return 0; /* This shouldn't happen */ if (WARN_ON_ONCE(drvdata->mode != CS_MODE_PERF)) - return; + return 0; CS_UNLOCK(drvdata->base); @@ -486,18 +457,14 @@ static void tmc_update_etf_buffer(struct coresight_device *csdev, } } - /* - * In snapshot mode all we have to do is communicate to - * perf_aux_output_end() the address of the current head. In full - * trace mode the same function expects a size to move rb->aux_head - * forward. - */ - if (buf->snapshot) - local_set(&buf->data_size, (cur * PAGE_SIZE) + offset); - else - local_add(to_read, &buf->data_size); - + /* In snapshot mode we have to update the head */ + if (buf->snapshot) { + handle->head = (cur * PAGE_SIZE) + offset; + to_read = buf->nr_pages << PAGE_SHIFT; + } CS_LOCK(drvdata->base); + + return to_read; } static const struct coresight_ops_sink tmc_etf_sink_ops = { @@ -506,7 +473,6 @@ static const struct coresight_ops_sink tmc_etf_sink_ops = { .alloc_buffer = tmc_alloc_etf_buffer, .free_buffer = tmc_free_etf_buffer, .set_buffer = tmc_set_etf_buffer, - .reset_buffer = tmc_reset_etf_buffer, .update_buffer = tmc_update_etf_buffer, }; diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 41e1f4333bf2..8e52682b1e90 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -186,7 +186,6 @@ struct coresight_device { * @alloc_buffer: initialises perf's ring buffer for trace collection. * @free_buffer: release memory allocated in @get_config. * @set_buffer: initialises buffer mechanic before a trace session. - * @reset_buffer: finalises buffer mechanic after a trace session. * @update_buffer: update buffer pointers after a trace session. */ struct coresight_ops_sink { @@ -198,10 +197,7 @@ struct coresight_ops_sink { int (*set_buffer)(struct coresight_device *csdev, struct perf_output_handle *handle, void *sink_config); - unsigned long (*reset_buffer)(struct coresight_device *csdev, - struct perf_output_handle *handle, - void *sink_config); - void (*update_buffer)(struct coresight_device *csdev, + unsigned long (*update_buffer)(struct coresight_device *csdev, struct perf_output_handle *handle, void *sink_config); }; -- cgit v1.2.3 From 3d6e8935758392179645e1b105789b3da329ad38 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Thu, 20 Sep 2018 13:17:56 -0600 Subject: coresight: perf: Remove set_buffer call back In coresight perf mode, we need to prepare the sink before starting a session, which is done via set_buffer call back. We then proceed to enable the tracing. If we fail to start the session successfully, we leave the sink configuration unchanged. In order to make the operation atomic and to avoid yet another call back to clear the buffer, we get rid of the "set_buffer" call back and pass the buffer details via enable() call back to the sink. Cc: Mathieu Poirier Signed-off-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight-etb10.c | 32 ++++++++++++++++++------ drivers/hwtracing/coresight/coresight-etm-perf.c | 9 ++----- drivers/hwtracing/coresight/coresight-priv.h | 2 +- drivers/hwtracing/coresight/coresight-tmc-etf.c | 28 ++++++++++++++------- drivers/hwtracing/coresight/coresight-tmc-etr.c | 7 +++--- drivers/hwtracing/coresight/coresight-tpiu.c | 2 +- drivers/hwtracing/coresight/coresight.c | 11 ++++---- include/linux/coresight.h | 6 +---- 8 files changed, 59 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/drivers/hwtracing/coresight/coresight-etb10.c b/drivers/hwtracing/coresight/coresight-etb10.c index dba75c905e57..9fd77fdc1244 100644 --- a/drivers/hwtracing/coresight/coresight-etb10.c +++ b/drivers/hwtracing/coresight/coresight-etb10.c @@ -28,6 +28,7 @@ #include "coresight-priv.h" +#include "coresight-etm-perf.h" #define ETB_RAM_DEPTH_REG 0x004 #define ETB_STATUS_REG 0x00c @@ -90,6 +91,9 @@ struct etb_drvdata { u32 trigger_cntr; }; +static int etb_set_buffer(struct coresight_device *csdev, + struct perf_output_handle *handle); + static unsigned int etb_get_buffer_depth(struct etb_drvdata *drvdata) { u32 depth = 0; @@ -131,12 +135,24 @@ static void etb_enable_hw(struct etb_drvdata *drvdata) CS_LOCK(drvdata->base); } -static int etb_enable(struct coresight_device *csdev, u32 mode) +static int etb_enable(struct coresight_device *csdev, u32 mode, void *data) { + int ret = 0; u32 val; unsigned long flags; struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + /* + * We don't have an internal state to clean up if we fail to setup + * the perf buffer. So we can perform the step before we turn the + * ETB on and leave without cleaning up. + */ + if (mode == CS_MODE_PERF) { + ret = etb_set_buffer(csdev, (struct perf_output_handle *)data); + if (ret) + goto out; + } + val = local_cmpxchg(&drvdata->mode, CS_MODE_DISABLED, mode); /* @@ -160,8 +176,9 @@ static int etb_enable(struct coresight_device *csdev, u32 mode) spin_unlock_irqrestore(&drvdata->spinlock, flags); out: - dev_dbg(drvdata->dev, "ETB enabled\n"); - return 0; + if (!ret) + dev_dbg(drvdata->dev, "ETB enabled\n"); + return ret; } static void etb_disable_hw(struct etb_drvdata *drvdata) @@ -298,12 +315,14 @@ static void etb_free_buffer(void *config) } static int etb_set_buffer(struct coresight_device *csdev, - struct perf_output_handle *handle, - void *sink_config) + struct perf_output_handle *handle) { int ret = 0; unsigned long head; - struct cs_buffers *buf = sink_config; + struct cs_buffers *buf = etm_perf_sink_config(handle); + + if (!buf) + return -EINVAL; /* wrap head around to the amount of space we have */ head = handle->head & ((buf->nr_pages << PAGE_SHIFT) - 1); @@ -457,7 +476,6 @@ static const struct coresight_ops_sink etb_sink_ops = { .disable = etb_disable, .alloc_buffer = etb_alloc_buffer, .free_buffer = etb_free_buffer, - .set_buffer = etb_set_buffer, .update_buffer = etb_update_buffer, }; diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index 16b83d8b2ac2..abe8249b893b 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -286,16 +286,11 @@ static void etm_event_start(struct perf_event *event, int flags) path = etm_event_cpu_path(event_data, cpu); /* We need a sink, no need to continue without one */ sink = coresight_get_sink(path); - if (WARN_ON_ONCE(!sink || !sink_ops(sink)->set_buffer)) - goto fail_end_stop; - - /* Configure the sink */ - if (sink_ops(sink)->set_buffer(sink, handle, - event_data->snk_config)) + if (WARN_ON_ONCE(!sink)) goto fail_end_stop; /* Nothing will happen without a path */ - if (coresight_enable_path(path, CS_MODE_PERF)) + if (coresight_enable_path(path, CS_MODE_PERF, handle)) goto fail_end_stop; /* Tell the perf core the event is alive */ diff --git a/drivers/hwtracing/coresight/coresight-priv.h b/drivers/hwtracing/coresight/coresight-priv.h index 1a6cf3589866..c11da5564a67 100644 --- a/drivers/hwtracing/coresight/coresight-priv.h +++ b/drivers/hwtracing/coresight/coresight-priv.h @@ -137,7 +137,7 @@ static inline void coresight_write_reg_pair(void __iomem *addr, u64 val, } void coresight_disable_path(struct list_head *path); -int coresight_enable_path(struct list_head *path, u32 mode); +int coresight_enable_path(struct list_head *path, u32 mode, void *sink_data); struct coresight_device *coresight_get_sink(struct list_head *path); struct coresight_device *coresight_get_enabled_sink(bool reset); struct list_head *coresight_build_path(struct coresight_device *csdev, diff --git a/drivers/hwtracing/coresight/coresight-tmc-etf.c b/drivers/hwtracing/coresight/coresight-tmc-etf.c index 31a98f915641..4156c95ce1bb 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etf.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etf.c @@ -10,6 +10,10 @@ #include #include "coresight-priv.h" #include "coresight-tmc.h" +#include "coresight-etm-perf.h" + +static int tmc_set_etf_buffer(struct coresight_device *csdev, + struct perf_output_handle *handle); static void tmc_etb_enable_hw(struct tmc_drvdata *drvdata) { @@ -182,11 +186,12 @@ out: return ret; } -static int tmc_enable_etf_sink_perf(struct coresight_device *csdev) +static int tmc_enable_etf_sink_perf(struct coresight_device *csdev, void *data) { int ret = 0; unsigned long flags; struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + struct perf_output_handle *handle = data; spin_lock_irqsave(&drvdata->spinlock, flags); if (drvdata->reading) { @@ -204,15 +209,19 @@ static int tmc_enable_etf_sink_perf(struct coresight_device *csdev) goto out; } - drvdata->mode = CS_MODE_PERF; - tmc_etb_enable_hw(drvdata); + ret = tmc_set_etf_buffer(csdev, handle); + if (!ret) { + drvdata->mode = CS_MODE_PERF; + tmc_etb_enable_hw(drvdata); + } out: spin_unlock_irqrestore(&drvdata->spinlock, flags); return ret; } -static int tmc_enable_etf_sink(struct coresight_device *csdev, u32 mode) +static int tmc_enable_etf_sink(struct coresight_device *csdev, + u32 mode, void *data) { int ret; struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); @@ -222,7 +231,7 @@ static int tmc_enable_etf_sink(struct coresight_device *csdev, u32 mode) ret = tmc_enable_etf_sink_sysfs(csdev); break; case CS_MODE_PERF: - ret = tmc_enable_etf_sink_perf(csdev); + ret = tmc_enable_etf_sink_perf(csdev, data); break; /* We shouldn't be here */ default: @@ -328,12 +337,14 @@ static void tmc_free_etf_buffer(void *config) } static int tmc_set_etf_buffer(struct coresight_device *csdev, - struct perf_output_handle *handle, - void *sink_config) + struct perf_output_handle *handle) { int ret = 0; unsigned long head; - struct cs_buffers *buf = sink_config; + struct cs_buffers *buf = etm_perf_sink_config(handle); + + if (!buf) + return -EINVAL; /* wrap head around to the amount of space we have */ head = handle->head & ((buf->nr_pages << PAGE_SHIFT) - 1); @@ -472,7 +483,6 @@ static const struct coresight_ops_sink tmc_etf_sink_ops = { .disable = tmc_disable_etf_sink, .alloc_buffer = tmc_alloc_etf_buffer, .free_buffer = tmc_free_etf_buffer, - .set_buffer = tmc_set_etf_buffer, .update_buffer = tmc_update_etf_buffer, }; diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c index 5e9bb2f0e9c0..1aedfc3629c0 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etr.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c @@ -1103,19 +1103,20 @@ out: return ret; } -static int tmc_enable_etr_sink_perf(struct coresight_device *csdev) +static int tmc_enable_etr_sink_perf(struct coresight_device *csdev, void *data) { /* We don't support perf mode yet ! */ return -EINVAL; } -static int tmc_enable_etr_sink(struct coresight_device *csdev, u32 mode) +static int tmc_enable_etr_sink(struct coresight_device *csdev, + u32 mode, void *data) { switch (mode) { case CS_MODE_SYSFS: return tmc_enable_etr_sink_sysfs(csdev); case CS_MODE_PERF: - return tmc_enable_etr_sink_perf(csdev); + return tmc_enable_etr_sink_perf(csdev, data); } /* We shouldn't be here */ diff --git a/drivers/hwtracing/coresight/coresight-tpiu.c b/drivers/hwtracing/coresight/coresight-tpiu.c index ce0b84583861..b2f72a1fa402 100644 --- a/drivers/hwtracing/coresight/coresight-tpiu.c +++ b/drivers/hwtracing/coresight/coresight-tpiu.c @@ -68,7 +68,7 @@ static void tpiu_enable_hw(struct tpiu_drvdata *drvdata) CS_LOCK(drvdata->base); } -static int tpiu_enable(struct coresight_device *csdev, u32 mode) +static int tpiu_enable(struct coresight_device *csdev, u32 mode, void *__unused) { struct tpiu_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); diff --git a/drivers/hwtracing/coresight/coresight.c b/drivers/hwtracing/coresight/coresight.c index 07382c55b31d..e73ca6af4765 100644 --- a/drivers/hwtracing/coresight/coresight.c +++ b/drivers/hwtracing/coresight/coresight.c @@ -128,7 +128,8 @@ static int coresight_find_link_outport(struct coresight_device *csdev, return -ENODEV; } -static int coresight_enable_sink(struct coresight_device *csdev, u32 mode) +static int coresight_enable_sink(struct coresight_device *csdev, + u32 mode, void *data) { int ret; @@ -137,7 +138,7 @@ static int coresight_enable_sink(struct coresight_device *csdev, u32 mode) * existing "mode" of operation. */ if (sink_ops(csdev)->enable) { - ret = sink_ops(csdev)->enable(csdev, mode); + ret = sink_ops(csdev)->enable(csdev, mode, data); if (ret) return ret; csdev->enable = true; @@ -315,7 +316,7 @@ void coresight_disable_path(struct list_head *path) } } -int coresight_enable_path(struct list_head *path, u32 mode) +int coresight_enable_path(struct list_head *path, u32 mode, void *sink_data) { int ret = 0; @@ -340,7 +341,7 @@ int coresight_enable_path(struct list_head *path, u32 mode) switch (type) { case CORESIGHT_DEV_TYPE_SINK: - ret = coresight_enable_sink(csdev, mode); + ret = coresight_enable_sink(csdev, mode, sink_data); /* * Sink is the first component turned on. If we * failed to enable the sink, there are no components @@ -643,7 +644,7 @@ int coresight_enable(struct coresight_device *csdev) goto out; } - ret = coresight_enable_path(path, CS_MODE_SYSFS); + ret = coresight_enable_path(path, CS_MODE_SYSFS, NULL); if (ret) goto err_path; diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 8e52682b1e90..53535821dc25 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -185,18 +185,14 @@ struct coresight_device { * @disable: disables the sink. * @alloc_buffer: initialises perf's ring buffer for trace collection. * @free_buffer: release memory allocated in @get_config. - * @set_buffer: initialises buffer mechanic before a trace session. * @update_buffer: update buffer pointers after a trace session. */ struct coresight_ops_sink { - int (*enable)(struct coresight_device *csdev, u32 mode); + int (*enable)(struct coresight_device *csdev, u32 mode, void *data); void (*disable)(struct coresight_device *csdev); void *(*alloc_buffer)(struct coresight_device *csdev, int cpu, void **pages, int nr_pages, bool overwrite); void (*free_buffer)(void *config); - int (*set_buffer)(struct coresight_device *csdev, - struct perf_output_handle *handle, - void *sink_config); unsigned long (*update_buffer)(struct coresight_device *csdev, struct perf_output_handle *handle, void *sink_config); -- cgit v1.2.3 From 2478a6ae4a6a4c8e3f7e9f6f849dffe92e5238e1 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Thu, 20 Sep 2018 13:18:11 -0600 Subject: coresight: Add support for CLAIM tag protocol Coresight architecture defines CLAIM tags for a device to negotiate control of the components (external agent vs self-hosted). Each device has a pair of registers (CLAIMSET & CLAIMCLR) for managing the CLAIM tags. However, the protocol for the CLAIM tags is IMPLEMENTATION DEFINED. PSCI has recommendations for the use of the CLAIM tags to negotiate controls for external agent vs self-hosted use. This patch implements the recommended protocol by PSCI. The claim/disclaim operations are performed from the device specific drivers. The disadvantage is that the calls are sprinkled in each driver, but this makes the operation much simpler. Cc: Mathieu Poirier Signed-off-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight-priv.h | 7 +++ drivers/hwtracing/coresight/coresight.c | 86 ++++++++++++++++++++++++++++ include/linux/coresight.h | 20 +++++++ 3 files changed, 113 insertions(+) (limited to 'include/linux') diff --git a/drivers/hwtracing/coresight/coresight-priv.h b/drivers/hwtracing/coresight/coresight-priv.h index c11da5564a67..579f34943bf1 100644 --- a/drivers/hwtracing/coresight/coresight-priv.h +++ b/drivers/hwtracing/coresight/coresight-priv.h @@ -25,6 +25,13 @@ #define CORESIGHT_DEVID 0xfc8 #define CORESIGHT_DEVTYPE 0xfcc + +/* + * Coresight device CLAIM protocol. + * See PSCI - ARM DEN 0022D, Section: 6.8.1 Debug and Trace save and restore. + */ +#define CORESIGHT_CLAIM_SELF_HOSTED BIT(1) + #define TIMEOUT_US 100 #define BMVAL(val, lsb, msb) ((val & GENMASK(msb, lsb)) >> lsb) diff --git a/drivers/hwtracing/coresight/coresight.c b/drivers/hwtracing/coresight/coresight.c index f4f50753cf75..2b0df1a0a8df 100644 --- a/drivers/hwtracing/coresight/coresight.c +++ b/drivers/hwtracing/coresight/coresight.c @@ -128,6 +128,92 @@ static int coresight_find_link_outport(struct coresight_device *csdev, return -ENODEV; } +static inline u32 coresight_read_claim_tags(void __iomem *base) +{ + return readl_relaxed(base + CORESIGHT_CLAIMCLR); +} + +static inline bool coresight_is_claimed_self_hosted(void __iomem *base) +{ + return coresight_read_claim_tags(base) == CORESIGHT_CLAIM_SELF_HOSTED; +} + +static inline bool coresight_is_claimed_any(void __iomem *base) +{ + return coresight_read_claim_tags(base) != 0; +} + +static inline void coresight_set_claim_tags(void __iomem *base) +{ + writel_relaxed(CORESIGHT_CLAIM_SELF_HOSTED, base + CORESIGHT_CLAIMSET); + isb(); +} + +static inline void coresight_clear_claim_tags(void __iomem *base) +{ + writel_relaxed(CORESIGHT_CLAIM_SELF_HOSTED, base + CORESIGHT_CLAIMCLR); + isb(); +} + +/* + * coresight_claim_device_unlocked : Claim the device for self-hosted usage + * to prevent an external tool from touching this device. As per PSCI + * standards, section "Preserving the execution context" => "Debug and Trace + * save and Restore", DBGCLAIM[1] is reserved for Self-hosted debug/trace and + * DBGCLAIM[0] is reserved for external tools. + * + * Called with CS_UNLOCKed for the component. + * Returns : 0 on success + */ +int coresight_claim_device_unlocked(void __iomem *base) +{ + if (coresight_is_claimed_any(base)) + return -EBUSY; + + coresight_set_claim_tags(base); + if (coresight_is_claimed_self_hosted(base)) + return 0; + /* There was a race setting the tags, clean up and fail */ + coresight_clear_claim_tags(base); + return -EBUSY; +} + +int coresight_claim_device(void __iomem *base) +{ + int rc; + + CS_UNLOCK(base); + rc = coresight_claim_device_unlocked(base); + CS_LOCK(base); + + return rc; +} + +/* + * coresight_disclaim_device_unlocked : Clear the claim tags for the device. + * Called with CS_UNLOCKed for the component. + */ +void coresight_disclaim_device_unlocked(void __iomem *base) +{ + + if (coresight_is_claimed_self_hosted(base)) + coresight_clear_claim_tags(base); + else + /* + * The external agent may have not honoured our claim + * and has manipulated it. Or something else has seriously + * gone wrong in our driver. + */ + WARN_ON_ONCE(1); +} + +void coresight_disclaim_device(void __iomem *base) +{ + CS_UNLOCK(base); + coresight_disclaim_device_unlocked(base); + CS_LOCK(base); +} + static int coresight_enable_sink(struct coresight_device *csdev, u32 mode, void *data) { diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 53535821dc25..46c67a764877 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -257,6 +257,13 @@ extern int coresight_enable(struct coresight_device *csdev); extern void coresight_disable(struct coresight_device *csdev); extern int coresight_timeout(void __iomem *addr, u32 offset, int position, int value); + +extern int coresight_claim_device(void __iomem *base); +extern int coresight_claim_device_unlocked(void __iomem *base); + +extern void coresight_disclaim_device(void __iomem *base); +extern void coresight_disclaim_device_unlocked(void __iomem *base); + #else static inline struct coresight_device * coresight_register(struct coresight_desc *desc) { return NULL; } @@ -266,6 +273,19 @@ coresight_enable(struct coresight_device *csdev) { return -ENOSYS; } static inline void coresight_disable(struct coresight_device *csdev) {} static inline int coresight_timeout(void __iomem *addr, u32 offset, int position, int value) { return 1; } +static inline int coresight_claim_device_unlocked(void __iomem *base) +{ + return -EINVAL; +} + +static inline int coresight_claim_device(void __iomem *base) +{ + return -EINVAL; +} + +static inline void coresight_disclaim_device(void __iomem *base) {} +static inline void coresight_disclaim_device_unlocked(void __iomem *base) {} + #endif #ifdef CONFIG_OF -- cgit v1.2.3 From 800b932969c53c4044ff9f9fd1ee793a87fa8ef0 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 14 Sep 2018 09:10:15 -0700 Subject: vmbus: pass channel to hv_process_channel_removal Rather than passing relid and then looking up the channel. Pass the channel directly, since caller already knows it. Signed-off-by: Stephen Hemminger Signed-off-by: Greg Kroah-Hartman --- drivers/hv/channel.c | 3 +-- drivers/hv/channel_mgmt.c | 17 +++++------------ drivers/hv/vmbus_drv.c | 3 +-- include/linux/hyperv.h | 2 +- 4 files changed, 8 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index 741857d80da1..33e6db02dbab 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -690,8 +690,7 @@ void vmbus_close(struct vmbus_channel *channel) wait_for_completion(&cur_channel->rescind_event); mutex_lock(&vmbus_connection.channel_mutex); vmbus_close_internal(cur_channel); - hv_process_channel_removal( - cur_channel->offermsg.child_relid); + hv_process_channel_removal(cur_channel); } else { mutex_lock(&vmbus_connection.channel_mutex); vmbus_close_internal(cur_channel); diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index 0f0e091c117c..b7c48ebdf6a1 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -385,21 +385,14 @@ static void vmbus_release_relid(u32 relid) trace_vmbus_release_relid(&msg, ret); } -void hv_process_channel_removal(u32 relid) +void hv_process_channel_removal(struct vmbus_channel *channel) { + struct vmbus_channel *primary_channel; unsigned long flags; - struct vmbus_channel *primary_channel, *channel; BUG_ON(!mutex_is_locked(&vmbus_connection.channel_mutex)); - - /* - * Make sure channel is valid as we may have raced. - */ - channel = relid2channel(relid); - if (!channel) - return; - BUG_ON(!channel->rescind); + if (channel->target_cpu != get_cpu()) { put_cpu(); smp_call_function_single(channel->target_cpu, @@ -429,7 +422,7 @@ void hv_process_channel_removal(u32 relid) cpumask_clear_cpu(channel->target_cpu, &primary_channel->alloced_cpus_in_node); - vmbus_release_relid(relid); + vmbus_release_relid(channel->offermsg.child_relid); free_channel(channel); } @@ -943,7 +936,7 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr) * The channel is currently not open; * it is safe for us to cleanup the channel. */ - hv_process_channel_removal(rescind->child_relid); + hv_process_channel_removal(channel); } else { complete(&channel->rescind_event); } diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 4bbc420d1213..283d184280af 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -864,10 +864,9 @@ static void vmbus_device_release(struct device *device) struct vmbus_channel *channel = hv_dev->channel; mutex_lock(&vmbus_connection.channel_mutex); - hv_process_channel_removal(channel->offermsg.child_relid); + hv_process_channel_removal(channel); mutex_unlock(&vmbus_connection.channel_mutex); kfree(hv_dev); - } /* The one and only one */ diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 2c3798bcb01c..6c4575c7f46b 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1443,7 +1443,7 @@ extern bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp, u8 *buf, const int *srv_version, int srv_vercnt, int *nego_fw_version, int *nego_srv_version); -void hv_process_channel_removal(u32 relid); +void hv_process_channel_removal(struct vmbus_channel *channel); void vmbus_setevent(struct vmbus_channel *channel); /* -- cgit v1.2.3 From 52a42c2a90226dc61c99bbd0cb096deeb52c334b Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 14 Sep 2018 09:10:16 -0700 Subject: vmbus: keep pointer to ring buffer page Avoid going from struct page to virt address (and back) by just keeping pointer to the allocated pages instead of virt address. Signed-off-by: Stephen Hemminger Signed-off-by: Greg Kroah-Hartman --- drivers/hv/channel.c | 20 +++++++++----------- drivers/uio/uio_hv_generic.c | 5 +++-- include/linux/hyperv.h | 2 +- 3 files changed, 13 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index 33e6db02dbab..56ec0d96d876 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -91,11 +91,14 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size, unsigned long flags; int ret, err = 0; struct page *page; + unsigned int order; if (send_ringbuffer_size % PAGE_SIZE || recv_ringbuffer_size % PAGE_SIZE) return -EINVAL; + order = get_order(send_ringbuffer_size + recv_ringbuffer_size); + spin_lock_irqsave(&newchannel->lock, flags); if (newchannel->state == CHANNEL_OPEN_STATE) { newchannel->state = CHANNEL_OPENING_STATE; @@ -110,21 +113,17 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size, /* Allocate the ring buffer */ page = alloc_pages_node(cpu_to_node(newchannel->target_cpu), - GFP_KERNEL|__GFP_ZERO, - get_order(send_ringbuffer_size + - recv_ringbuffer_size)); + GFP_KERNEL|__GFP_ZERO, order); if (!page) - page = alloc_pages(GFP_KERNEL|__GFP_ZERO, - get_order(send_ringbuffer_size + - recv_ringbuffer_size)); + page = alloc_pages(GFP_KERNEL|__GFP_ZERO, order); if (!page) { err = -ENOMEM; goto error_set_chnstate; } - newchannel->ringbuffer_pages = page_address(page); + newchannel->ringbuffer_page = page; newchannel->ringbuffer_pagecount = (send_ringbuffer_size + recv_ringbuffer_size) >> PAGE_SHIFT; @@ -239,8 +238,7 @@ error_free_gpadl: error_free_pages: hv_ringbuffer_cleanup(&newchannel->outbound); hv_ringbuffer_cleanup(&newchannel->inbound); - __free_pages(page, - get_order(send_ringbuffer_size + recv_ringbuffer_size)); + __free_pages(page, order); error_set_chnstate: newchannel->state = CHANNEL_OPEN_STATE; return err; @@ -658,8 +656,8 @@ static int vmbus_close_internal(struct vmbus_channel *channel) hv_ringbuffer_cleanup(&channel->outbound); hv_ringbuffer_cleanup(&channel->inbound); - free_pages((unsigned long)channel->ringbuffer_pages, - get_order(channel->ringbuffer_pagecount * PAGE_SIZE)); + __free_pages(channel->ringbuffer_page, + get_order(channel->ringbuffer_pagecount << PAGE_SHIFT)); out: return ret; diff --git a/drivers/uio/uio_hv_generic.c b/drivers/uio/uio_hv_generic.c index a08860260f55..ba67a5267557 100644 --- a/drivers/uio/uio_hv_generic.c +++ b/drivers/uio/uio_hv_generic.c @@ -130,11 +130,12 @@ static int hv_uio_ring_mmap(struct file *filp, struct kobject *kobj, = container_of(kobj, struct vmbus_channel, kobj); struct hv_device *dev = channel->primary_channel->device_obj; u16 q_idx = channel->offermsg.offer.sub_channel_index; + void *ring_buffer = page_address(channel->ringbuffer_page); dev_dbg(&dev->device, "mmap channel %u pages %#lx at %#lx\n", q_idx, vma_pages(vma), vma->vm_pgoff); - return vm_iomap_memory(vma, virt_to_phys(channel->ringbuffer_pages), + return vm_iomap_memory(vma, virt_to_phys(ring_buffer), channel->ringbuffer_pagecount << PAGE_SHIFT); } @@ -223,7 +224,7 @@ hv_uio_probe(struct hv_device *dev, /* mem resources */ pdata->info.mem[TXRX_RING_MAP].name = "txrx_rings"; pdata->info.mem[TXRX_RING_MAP].addr - = (uintptr_t)dev->channel->ringbuffer_pages; + = (uintptr_t)page_address(dev->channel->ringbuffer_page); pdata->info.mem[TXRX_RING_MAP].size = dev->channel->ringbuffer_pagecount << PAGE_SHIFT; pdata->info.mem[TXRX_RING_MAP].memtype = UIO_MEM_LOGICAL; diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 6c4575c7f46b..a6c32d2d090b 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -739,7 +739,7 @@ struct vmbus_channel { u32 ringbuffer_gpadlhandle; /* Allocated memory for ring buffer */ - void *ringbuffer_pages; + struct page *ringbuffer_page; u32 ringbuffer_pagecount; struct hv_ring_buffer_info outbound; /* send to parent */ struct hv_ring_buffer_info inbound; /* receive from parent */ -- cgit v1.2.3 From ae6935ed7d424ffa74d634da00767e7b03c98fd3 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 14 Sep 2018 09:10:17 -0700 Subject: vmbus: split ring buffer allocation from open The UIO driver needs the ring buffer to be persistent(reused) across open/close. Split the allocation and setup of ring buffer out of vmbus_open. For normal usage vmbus_open/vmbus_close there are no changes; only impacts uio_hv_generic which needs to keep ring buffer memory and reuse when application restarts. Signed-off-by: Stephen Hemminger Signed-off-by: Greg Kroah-Hartman --- drivers/hv/channel.c | 267 +++++++++++++++++++++++++++-------------------- drivers/hv/ring_buffer.c | 1 + include/linux/hyperv.h | 9 ++ 3 files changed, 162 insertions(+), 115 deletions(-) (limited to 'include/linux') diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index 56ec0d96d876..ddadb7efd1cc 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -79,84 +79,96 @@ void vmbus_setevent(struct vmbus_channel *channel) } EXPORT_SYMBOL_GPL(vmbus_setevent); -/* - * vmbus_open - Open the specified channel. - */ -int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size, - u32 recv_ringbuffer_size, void *userdata, u32 userdatalen, - void (*onchannelcallback)(void *context), void *context) +/* vmbus_free_ring - drop mapping of ring buffer */ +void vmbus_free_ring(struct vmbus_channel *channel) { - struct vmbus_channel_open_channel *open_msg; - struct vmbus_channel_msginfo *open_info = NULL; - unsigned long flags; - int ret, err = 0; - struct page *page; - unsigned int order; + hv_ringbuffer_cleanup(&channel->outbound); + hv_ringbuffer_cleanup(&channel->inbound); - if (send_ringbuffer_size % PAGE_SIZE || - recv_ringbuffer_size % PAGE_SIZE) - return -EINVAL; + if (channel->ringbuffer_page) { + __free_pages(channel->ringbuffer_page, + get_order(channel->ringbuffer_pagecount + << PAGE_SHIFT)); + channel->ringbuffer_page = NULL; + } +} +EXPORT_SYMBOL_GPL(vmbus_free_ring); - order = get_order(send_ringbuffer_size + recv_ringbuffer_size); +/* vmbus_alloc_ring - allocate and map pages for ring buffer */ +int vmbus_alloc_ring(struct vmbus_channel *newchannel, + u32 send_size, u32 recv_size) +{ + struct page *page; + int order; - spin_lock_irqsave(&newchannel->lock, flags); - if (newchannel->state == CHANNEL_OPEN_STATE) { - newchannel->state = CHANNEL_OPENING_STATE; - } else { - spin_unlock_irqrestore(&newchannel->lock, flags); + if (send_size % PAGE_SIZE || recv_size % PAGE_SIZE) return -EINVAL; - } - spin_unlock_irqrestore(&newchannel->lock, flags); - - newchannel->onchannel_callback = onchannelcallback; - newchannel->channel_callback_context = context; /* Allocate the ring buffer */ + order = get_order(send_size + recv_size); page = alloc_pages_node(cpu_to_node(newchannel->target_cpu), GFP_KERNEL|__GFP_ZERO, order); if (!page) page = alloc_pages(GFP_KERNEL|__GFP_ZERO, order); - if (!page) { - err = -ENOMEM; - goto error_set_chnstate; - } + if (!page) + return -ENOMEM; newchannel->ringbuffer_page = page; - newchannel->ringbuffer_pagecount = (send_ringbuffer_size + - recv_ringbuffer_size) >> PAGE_SHIFT; + newchannel->ringbuffer_pagecount = (send_size + recv_size) >> PAGE_SHIFT; + newchannel->ringbuffer_send_offset = send_size >> PAGE_SHIFT; - ret = hv_ringbuffer_init(&newchannel->outbound, page, - send_ringbuffer_size >> PAGE_SHIFT); + return 0; +} +EXPORT_SYMBOL_GPL(vmbus_alloc_ring); - if (ret != 0) { - err = ret; - goto error_free_pages; - } +static int __vmbus_open(struct vmbus_channel *newchannel, + void *userdata, u32 userdatalen, + void (*onchannelcallback)(void *context), void *context) +{ + struct vmbus_channel_open_channel *open_msg; + struct vmbus_channel_msginfo *open_info = NULL; + struct page *page = newchannel->ringbuffer_page; + u32 send_pages, recv_pages; + unsigned long flags; + int err; - ret = hv_ringbuffer_init(&newchannel->inbound, - &page[send_ringbuffer_size >> PAGE_SHIFT], - recv_ringbuffer_size >> PAGE_SHIFT); - if (ret != 0) { - err = ret; - goto error_free_pages; + if (userdatalen > MAX_USER_DEFINED_BYTES) + return -EINVAL; + + send_pages = newchannel->ringbuffer_send_offset; + recv_pages = newchannel->ringbuffer_pagecount - send_pages; + + spin_lock_irqsave(&newchannel->lock, flags); + if (newchannel->state != CHANNEL_OPEN_STATE) { + spin_unlock_irqrestore(&newchannel->lock, flags); + return -EINVAL; } + spin_unlock_irqrestore(&newchannel->lock, flags); + newchannel->state = CHANNEL_OPENING_STATE; + newchannel->onchannel_callback = onchannelcallback; + newchannel->channel_callback_context = context; + + err = hv_ringbuffer_init(&newchannel->outbound, page, send_pages); + if (err) + goto error_clean_ring; + + err = hv_ringbuffer_init(&newchannel->inbound, + &page[send_pages], recv_pages); + if (err) + goto error_clean_ring; /* Establish the gpadl for the ring buffer */ newchannel->ringbuffer_gpadlhandle = 0; - ret = vmbus_establish_gpadl(newchannel, - page_address(page), - send_ringbuffer_size + - recv_ringbuffer_size, + err = vmbus_establish_gpadl(newchannel, + page_address(newchannel->ringbuffer_page), + (send_pages + recv_pages) << PAGE_SHIFT, &newchannel->ringbuffer_gpadlhandle); - - if (ret != 0) { - err = ret; - goto error_free_pages; - } + if (err) + goto error_clean_ring; /* Create and init the channel open message */ open_info = kmalloc(sizeof(*open_info) + @@ -175,15 +187,9 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size, open_msg->openid = newchannel->offermsg.child_relid; open_msg->child_relid = newchannel->offermsg.child_relid; open_msg->ringbuffer_gpadlhandle = newchannel->ringbuffer_gpadlhandle; - open_msg->downstream_ringbuffer_pageoffset = send_ringbuffer_size >> - PAGE_SHIFT; + open_msg->downstream_ringbuffer_pageoffset = newchannel->ringbuffer_send_offset; open_msg->target_vp = newchannel->target_vp; - if (userdatalen > MAX_USER_DEFINED_BYTES) { - err = -EINVAL; - goto error_free_gpadl; - } - if (userdatalen) memcpy(open_msg->userdata, userdata, userdatalen); @@ -194,18 +200,16 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size, if (newchannel->rescind) { err = -ENODEV; - goto error_free_gpadl; + goto error_free_info; } - ret = vmbus_post_msg(open_msg, + err = vmbus_post_msg(open_msg, sizeof(struct vmbus_channel_open_channel), true); - trace_vmbus_open(open_msg, ret); + trace_vmbus_open(open_msg, err); - if (ret != 0) { - err = ret; + if (err != 0) goto error_clean_msglist; - } wait_for_completion(&open_info->waitevent); @@ -215,12 +219,12 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size, if (newchannel->rescind) { err = -ENODEV; - goto error_free_gpadl; + goto error_free_info; } if (open_info->response.open_result.status) { err = -EAGAIN; - goto error_free_gpadl; + goto error_free_info; } newchannel->state = CHANNEL_OPENED_STATE; @@ -231,18 +235,50 @@ error_clean_msglist: spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags); list_del(&open_info->msglistentry); spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags); - +error_free_info: + kfree(open_info); error_free_gpadl: vmbus_teardown_gpadl(newchannel, newchannel->ringbuffer_gpadlhandle); - kfree(open_info); -error_free_pages: + newchannel->ringbuffer_gpadlhandle = 0; +error_clean_ring: hv_ringbuffer_cleanup(&newchannel->outbound); hv_ringbuffer_cleanup(&newchannel->inbound); - __free_pages(page, order); -error_set_chnstate: newchannel->state = CHANNEL_OPEN_STATE; return err; } + +/* + * vmbus_connect_ring - Open the channel but reuse ring buffer + */ +int vmbus_connect_ring(struct vmbus_channel *newchannel, + void (*onchannelcallback)(void *context), void *context) +{ + return __vmbus_open(newchannel, NULL, 0, onchannelcallback, context); +} +EXPORT_SYMBOL_GPL(vmbus_connect_ring); + +/* + * vmbus_open - Open the specified channel. + */ +int vmbus_open(struct vmbus_channel *newchannel, + u32 send_ringbuffer_size, u32 recv_ringbuffer_size, + void *userdata, u32 userdatalen, + void (*onchannelcallback)(void *context), void *context) +{ + int err; + + err = vmbus_alloc_ring(newchannel, send_ringbuffer_size, + recv_ringbuffer_size); + if (err) + return err; + + err = __vmbus_open(newchannel, userdata, userdatalen, + onchannelcallback, context); + if (err) + vmbus_free_ring(newchannel); + + return err; +} EXPORT_SYMBOL_GPL(vmbus_open); /* Used for Hyper-V Socket: a guest client's connect() to the host */ @@ -610,10 +646,8 @@ static int vmbus_close_internal(struct vmbus_channel *channel) * in Hyper-V Manager), the driver's remove() invokes vmbus_close(): * here we should skip most of the below cleanup work. */ - if (channel->state != CHANNEL_OPENED_STATE) { - ret = -EINVAL; - goto out; - } + if (channel->state != CHANNEL_OPENED_STATE) + return -EINVAL; channel->state = CHANNEL_OPEN_STATE; @@ -635,11 +669,10 @@ static int vmbus_close_internal(struct vmbus_channel *channel) * If we failed to post the close msg, * it is perhaps better to leak memory. */ - goto out; } /* Tear down the gpadl for the channel's ring buffer */ - if (channel->ringbuffer_gpadlhandle) { + else if (channel->ringbuffer_gpadlhandle) { ret = vmbus_teardown_gpadl(channel, channel->ringbuffer_gpadlhandle); if (ret) { @@ -648,59 +681,63 @@ static int vmbus_close_internal(struct vmbus_channel *channel) * If we failed to teardown gpadl, * it is perhaps better to leak memory. */ - goto out; } - } - - /* Cleanup the ring buffers for this channel */ - hv_ringbuffer_cleanup(&channel->outbound); - hv_ringbuffer_cleanup(&channel->inbound); - __free_pages(channel->ringbuffer_page, - get_order(channel->ringbuffer_pagecount << PAGE_SHIFT)); + channel->ringbuffer_gpadlhandle = 0; + } -out: return ret; } -/* - * vmbus_close - Close the specified channel - */ -void vmbus_close(struct vmbus_channel *channel) +/* disconnect ring - close all channels */ +int vmbus_disconnect_ring(struct vmbus_channel *channel) { - struct list_head *cur, *tmp; - struct vmbus_channel *cur_channel; + struct vmbus_channel *cur_channel, *tmp; + unsigned long flags; + LIST_HEAD(list); + int ret; - if (channel->primary_channel != NULL) { - /* - * We will only close sub-channels when - * the primary is closed. - */ - return; - } - /* - * Close all the sub-channels first and then close the - * primary channel. - */ - list_for_each_safe(cur, tmp, &channel->sc_list) { - cur_channel = list_entry(cur, struct vmbus_channel, sc_list); - if (cur_channel->rescind) { + if (channel->primary_channel != NULL) + return -EINVAL; + + /* Snapshot the list of subchannels */ + spin_lock_irqsave(&channel->lock, flags); + list_splice_init(&channel->sc_list, &list); + channel->num_sc = 0; + spin_unlock_irqrestore(&channel->lock, flags); + + list_for_each_entry_safe(cur_channel, tmp, &list, sc_list) { + if (cur_channel->rescind) wait_for_completion(&cur_channel->rescind_event); - mutex_lock(&vmbus_connection.channel_mutex); - vmbus_close_internal(cur_channel); - hv_process_channel_removal(cur_channel); - } else { - mutex_lock(&vmbus_connection.channel_mutex); - vmbus_close_internal(cur_channel); + + mutex_lock(&vmbus_connection.channel_mutex); + if (vmbus_close_internal(cur_channel) == 0) { + vmbus_free_ring(cur_channel); + + if (cur_channel->rescind) + hv_process_channel_removal(cur_channel); } mutex_unlock(&vmbus_connection.channel_mutex); } + /* * Now close the primary. */ mutex_lock(&vmbus_connection.channel_mutex); - vmbus_close_internal(channel); + ret = vmbus_close_internal(channel); mutex_unlock(&vmbus_connection.channel_mutex); + + return ret; +} +EXPORT_SYMBOL_GPL(vmbus_disconnect_ring); + +/* + * vmbus_close - Close the specified channel + */ +void vmbus_close(struct vmbus_channel *channel) +{ + if (vmbus_disconnect_ring(channel) == 0) + vmbus_free_ring(channel); } EXPORT_SYMBOL_GPL(vmbus_close); diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c index 3e90eb91db45..64d0c85d5161 100644 --- a/drivers/hv/ring_buffer.c +++ b/drivers/hv/ring_buffer.c @@ -241,6 +241,7 @@ int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info, void hv_ringbuffer_cleanup(struct hv_ring_buffer_info *ring_info) { vunmap(ring_info->ring_buffer); + ring_info->ring_buffer = NULL; } /* Write to the ring buffer. */ diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index a6c32d2d090b..b3e24368930a 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -741,6 +741,7 @@ struct vmbus_channel { /* Allocated memory for ring buffer */ struct page *ringbuffer_page; u32 ringbuffer_pagecount; + u32 ringbuffer_send_offset; struct hv_ring_buffer_info outbound; /* send to parent */ struct hv_ring_buffer_info inbound; /* receive from parent */ @@ -1021,6 +1022,14 @@ struct vmbus_packet_mpb_array { struct hv_mpb_array range; } __packed; +int vmbus_alloc_ring(struct vmbus_channel *channel, + u32 send_size, u32 recv_size); +void vmbus_free_ring(struct vmbus_channel *channel); + +int vmbus_connect_ring(struct vmbus_channel *channel, + void (*onchannel_callback)(void *context), + void *context); +int vmbus_disconnect_ring(struct vmbus_channel *channel); extern int vmbus_open(struct vmbus_channel *channel, u32 send_ringbuffersize, -- cgit v1.2.3 From bfddabfa230452cea32aae82f9cd85ab22601acf Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 14 Sep 2018 09:10:18 -0700 Subject: uio: introduce UIO_MEM_IOVA Introduce the concept of mapping physical memory locations that are normal memory. The new type UIO_MEM_IOVA are similar to existing UIO_MEM_PHYS but the backing memory is not marked as uncached. Also, indent related switch to the currently used style. Signed-off-by: Stephen Hemminger Signed-off-by: Greg Kroah-Hartman --- drivers/uio/uio.c | 24 +++++++++++++----------- include/linux/uio_driver.h | 1 + 2 files changed, 14 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c index 0ffb324aa038..e601bd3fbae1 100644 --- a/drivers/uio/uio.c +++ b/drivers/uio/uio.c @@ -738,7 +738,8 @@ static int uio_mmap_physical(struct vm_area_struct *vma) return -EINVAL; vma->vm_ops = &uio_physical_vm_ops; - vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); + if (idev->info->mem[mi].memtype == UIO_MEM_PHYS) + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); /* * We cannot use the vm_iomap_memory() helper here, @@ -795,18 +796,19 @@ static int uio_mmap(struct file *filep, struct vm_area_struct *vma) } switch (idev->info->mem[mi].memtype) { - case UIO_MEM_PHYS: - ret = uio_mmap_physical(vma); - break; - case UIO_MEM_LOGICAL: - case UIO_MEM_VIRTUAL: - ret = uio_mmap_logical(vma); - break; - default: - ret = -EINVAL; + case UIO_MEM_IOVA: + case UIO_MEM_PHYS: + ret = uio_mmap_physical(vma); + break; + case UIO_MEM_LOGICAL: + case UIO_MEM_VIRTUAL: + ret = uio_mmap_logical(vma); + break; + default: + ret = -EINVAL; } -out: + out: mutex_unlock(&idev->info_lock); return ret; } diff --git a/include/linux/uio_driver.h b/include/linux/uio_driver.h index 6f8b68cd460f..a3cd7cb67a69 100644 --- a/include/linux/uio_driver.h +++ b/include/linux/uio_driver.h @@ -133,6 +133,7 @@ extern void uio_event_notify(struct uio_info *info); #define UIO_MEM_PHYS 1 #define UIO_MEM_LOGICAL 2 #define UIO_MEM_VIRTUAL 3 +#define UIO_MEM_IOVA 4 /* defines for uio_port->porttype */ #define UIO_PORT_NONE 0 -- cgit v1.2.3 From 6f99528e9797794b91b43321fbbc93fe772b0803 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Mon, 24 Sep 2018 19:22:49 +0300 Subject: net: core: netlink: add helper refcount dec and lock function Rtnl lock is encapsulated in netlink and cannot be accessed by other modules directly. This means that reference counted objects that rely on rtnl lock cannot use it with refcounter helper function that atomically releases decrements reference and obtains mutex. This patch implements simple wrapper function around refcount_dec_and_lock that obtains rtnl lock if reference counter value reached 0. Signed-off-by: Vlad Buslov Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 2 ++ net/core/rtnetlink.c | 6 ++++++ 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 5225832bd6ff..9cdd76348d9a 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -6,6 +6,7 @@ #include #include #include +#include #include extern int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, u32 group, int echo); @@ -34,6 +35,7 @@ extern void rtnl_unlock(void); extern int rtnl_trylock(void); extern int rtnl_is_locked(void); extern int rtnl_lock_killable(void); +extern bool refcount_dec_and_rtnl_lock(refcount_t *r); extern wait_queue_head_t netdev_unregistering_wq; extern struct rw_semaphore pernet_ops_rwsem; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 80a7e18c65fb..35162e1b06ad 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -130,6 +130,12 @@ int rtnl_is_locked(void) } EXPORT_SYMBOL(rtnl_is_locked); +bool refcount_dec_and_rtnl_lock(refcount_t *r) +{ + return refcount_dec_and_mutex_lock(r, &rtnl_mutex); +} +EXPORT_SYMBOL(refcount_dec_and_rtnl_lock); + #ifdef CONFIG_PROVE_LOCKING bool lockdep_rtnl_is_held(void) { -- cgit v1.2.3 From 3a7d0d07a386716b459b00783b11a8211cefcc0f Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Mon, 24 Sep 2018 19:22:51 +0300 Subject: net: sched: extend Qdisc with rcu Currently, Qdisc API functions assume that users have rtnl lock taken. To implement rtnl unlocked classifiers update interface, Qdisc API must be extended with functions that do not require rtnl lock. Extend Qdisc structure with rcu. Implement special version of put function qdisc_put_unlocked() that is called without rtnl lock taken. This function only takes rtnl lock if Qdisc reference counter reached zero and is intended to be used as optimization. Signed-off-by: Vlad Buslov Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 5 +++++ include/net/pkt_sched.h | 1 + include/net/sch_generic.h | 2 ++ net/sched/sch_api.c | 18 ++++++++++++++++++ net/sched/sch_generic.c | 25 ++++++++++++++++++++++++- 5 files changed, 50 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 9cdd76348d9a..bb9cb84114c1 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -85,6 +85,11 @@ static inline struct netdev_queue *dev_ingress_queue(struct net_device *dev) return rtnl_dereference(dev->ingress_queue); } +static inline struct netdev_queue *dev_ingress_queue_rcu(struct net_device *dev) +{ + return rcu_dereference(dev->ingress_queue); +} + struct netdev_queue *dev_ingress_queue_create(struct net_device *dev); #ifdef CONFIG_NET_INGRESS diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 7dc769e5452b..a16fbe9a2a67 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -102,6 +102,7 @@ int qdisc_set_default(const char *id); void qdisc_hash_add(struct Qdisc *q, bool invisible); void qdisc_hash_del(struct Qdisc *q); struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle); +struct Qdisc *qdisc_lookup_rcu(struct net_device *dev, u32 handle); struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, struct nlattr *tab, struct netlink_ext_ack *extack); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index fadb1a4d4ee8..091b40c198ff 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -105,6 +105,7 @@ struct Qdisc { spinlock_t busylock ____cacheline_aligned_in_smp; spinlock_t seqlock; + struct rcu_head rcu; }; static inline void qdisc_refcount_inc(struct Qdisc *qdisc) @@ -555,6 +556,7 @@ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, struct Qdisc *qdisc); void qdisc_reset(struct Qdisc *qdisc); void qdisc_put(struct Qdisc *qdisc); +void qdisc_put_unlocked(struct Qdisc *qdisc); void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, unsigned int n, unsigned int len); struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 2096138c4bf6..22e9799e5b69 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -314,6 +314,24 @@ out: return q; } +struct Qdisc *qdisc_lookup_rcu(struct net_device *dev, u32 handle) +{ + struct netdev_queue *nq; + struct Qdisc *q; + + if (!handle) + return NULL; + q = qdisc_match_from_root(dev->qdisc, handle); + if (q) + goto out; + + nq = dev_ingress_queue_rcu(dev); + if (nq) + q = qdisc_match_from_root(nq->qdisc_sleeping, handle); +out: + return q; +} + static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid) { unsigned long cl; diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 3e7696f3e053..531fac1d2875 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -941,6 +941,13 @@ void qdisc_free(struct Qdisc *qdisc) kfree((char *) qdisc - qdisc->padded); } +void qdisc_free_cb(struct rcu_head *head) +{ + struct Qdisc *q = container_of(head, struct Qdisc, rcu); + + qdisc_free(q); +} + static void qdisc_destroy(struct Qdisc *qdisc) { const struct Qdisc_ops *ops = qdisc->ops; @@ -970,7 +977,7 @@ static void qdisc_destroy(struct Qdisc *qdisc) kfree_skb_list(skb); } - qdisc_free(qdisc); + call_rcu(&qdisc->rcu, qdisc_free_cb); } void qdisc_put(struct Qdisc *qdisc) @@ -983,6 +990,22 @@ void qdisc_put(struct Qdisc *qdisc) } EXPORT_SYMBOL(qdisc_put); +/* Version of qdisc_put() that is called with rtnl mutex unlocked. + * Intended to be used as optimization, this function only takes rtnl lock if + * qdisc reference counter reached zero. + */ + +void qdisc_put_unlocked(struct Qdisc *qdisc) +{ + if (qdisc->flags & TCQ_F_BUILTIN || + !refcount_dec_and_rtnl_lock(&qdisc->refcnt)) + return; + + qdisc_destroy(qdisc); + rtnl_unlock(); +} +EXPORT_SYMBOL(qdisc_put_unlocked); + /* Attach toplevel qdisc to device queue. */ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, struct Qdisc *qdisc) -- cgit v1.2.3 From 2ba3c43f09c50eb1c0472decdfba71010d8694dc Mon Sep 17 00:00:00 2001 From: Vivek Gautam Date: Tue, 4 Sep 2018 15:47:17 +0530 Subject: phy: qcom-ufs: Remove stale methods that handle ref clk Remove ufs_qcom_phy_enable/(disable)_dev_ref_clk() that are not being used by any code. Signed-off-by: Vivek Gautam Reviewed-by: Bjorn Andersson Signed-off-by: Kishon Vijay Abraham I --- drivers/phy/qualcomm/phy-qcom-ufs.c | 50 ------------------------------------- include/linux/phy/phy-qcom-ufs.h | 14 ----------- 2 files changed, 64 deletions(-) (limited to 'include/linux') diff --git a/drivers/phy/qualcomm/phy-qcom-ufs.c b/drivers/phy/qualcomm/phy-qcom-ufs.c index c5493ea51282..f2979ccad00a 100644 --- a/drivers/phy/qualcomm/phy-qcom-ufs.c +++ b/drivers/phy/qualcomm/phy-qcom-ufs.c @@ -431,56 +431,6 @@ static void ufs_qcom_phy_disable_ref_clk(struct ufs_qcom_phy *phy) } } -#define UFS_REF_CLK_EN (1 << 5) - -static void ufs_qcom_phy_dev_ref_clk_ctrl(struct phy *generic_phy, bool enable) -{ - struct ufs_qcom_phy *phy = get_ufs_qcom_phy(generic_phy); - - if (phy->dev_ref_clk_ctrl_mmio && - (enable ^ phy->is_dev_ref_clk_enabled)) { - u32 temp = readl_relaxed(phy->dev_ref_clk_ctrl_mmio); - - if (enable) - temp |= UFS_REF_CLK_EN; - else - temp &= ~UFS_REF_CLK_EN; - - /* - * If we are here to disable this clock immediately after - * entering into hibern8, we need to make sure that device - * ref_clk is active atleast 1us after the hibern8 enter. - */ - if (!enable) - udelay(1); - - writel_relaxed(temp, phy->dev_ref_clk_ctrl_mmio); - /* ensure that ref_clk is enabled/disabled before we return */ - wmb(); - /* - * If we call hibern8 exit after this, we need to make sure that - * device ref_clk is stable for atleast 1us before the hibern8 - * exit command. - */ - if (enable) - udelay(1); - - phy->is_dev_ref_clk_enabled = enable; - } -} - -void ufs_qcom_phy_enable_dev_ref_clk(struct phy *generic_phy) -{ - ufs_qcom_phy_dev_ref_clk_ctrl(generic_phy, true); -} -EXPORT_SYMBOL_GPL(ufs_qcom_phy_enable_dev_ref_clk); - -void ufs_qcom_phy_disable_dev_ref_clk(struct phy *generic_phy) -{ - ufs_qcom_phy_dev_ref_clk_ctrl(generic_phy, false); -} -EXPORT_SYMBOL_GPL(ufs_qcom_phy_disable_dev_ref_clk); - /* Turn ON M-PHY RMMI interface clocks */ static int ufs_qcom_phy_enable_iface_clk(struct ufs_qcom_phy *phy) { diff --git a/include/linux/phy/phy-qcom-ufs.h b/include/linux/phy/phy-qcom-ufs.h index 0a2c18a9771d..9dd85071bcce 100644 --- a/include/linux/phy/phy-qcom-ufs.h +++ b/include/linux/phy/phy-qcom-ufs.h @@ -17,20 +17,6 @@ #include "phy.h" -/** - * ufs_qcom_phy_enable_dev_ref_clk() - Enable the device - * ref clock. - * @phy: reference to a generic phy. - */ -void ufs_qcom_phy_enable_dev_ref_clk(struct phy *phy); - -/** - * ufs_qcom_phy_disable_dev_ref_clk() - Disable the device - * ref clock. - * @phy: reference to a generic phy. - */ -void ufs_qcom_phy_disable_dev_ref_clk(struct phy *phy); - int ufs_qcom_phy_set_tx_lane_enable(struct phy *phy, u32 tx_lanes); void ufs_qcom_phy_save_controller_version(struct phy *phy, u8 major, u16 minor, u16 step); -- cgit v1.2.3 From 1e1e465c6d23aa7d1858eb2894408f15770af16c Mon Sep 17 00:00:00 2001 From: Vivek Gautam Date: Tue, 4 Sep 2018 15:47:18 +0530 Subject: scsi/ufs: qcom: Remove ufs_qcom_phy_*() calls from host The host makes direct calls into phy using ufs_qcom_phy_*() APIs. These APIs are only defined for 20nm qcom-ufs-qmp phy which is not being used by any architecture as yet. Future architectures too are not going to use 20nm ufs phy. So remove these ufs_qcom_phy_*() calls from host to let further change declare the 20nm phy as broken. Also remove couple of stale enum defines for ufs phy. Signed-off-by: Vivek Gautam Acked-by: Martin K. Petersen Signed-off-by: Kishon Vijay Abraham I --- drivers/phy/qualcomm/phy-qcom-ufs-i.h | 2 +- drivers/scsi/ufs/ufs-qcom.c | 28 +--------------------------- drivers/scsi/ufs/ufs-qcom.h | 5 ----- include/linux/phy/phy-qcom-ufs.h | 24 ------------------------ 4 files changed, 2 insertions(+), 57 deletions(-) delete mode 100644 include/linux/phy/phy-qcom-ufs.h (limited to 'include/linux') diff --git a/drivers/phy/qualcomm/phy-qcom-ufs-i.h b/drivers/phy/qualcomm/phy-qcom-ufs-i.h index 822c83b8efcd..681644e43248 100644 --- a/drivers/phy/qualcomm/phy-qcom-ufs-i.h +++ b/drivers/phy/qualcomm/phy-qcom-ufs-i.h @@ -17,9 +17,9 @@ #include #include +#include #include #include -#include #include #include #include diff --git a/drivers/scsi/ufs/ufs-qcom.c b/drivers/scsi/ufs/ufs-qcom.c index 75ee5906b966..3dc4501c6945 100644 --- a/drivers/scsi/ufs/ufs-qcom.c +++ b/drivers/scsi/ufs/ufs-qcom.c @@ -16,7 +16,6 @@ #include #include #include -#include #include "ufshcd.h" #include "ufshcd-pltfrm.h" @@ -189,22 +188,9 @@ out: static int ufs_qcom_link_startup_post_change(struct ufs_hba *hba) { - struct ufs_qcom_host *host = ufshcd_get_variant(hba); - struct phy *phy = host->generic_phy; u32 tx_lanes; - int err = 0; - - err = ufs_qcom_get_connected_tx_lanes(hba, &tx_lanes); - if (err) - goto out; - err = ufs_qcom_phy_set_tx_lane_enable(phy, tx_lanes); - if (err) - dev_err(hba->dev, "%s: ufs_qcom_phy_set_tx_lane_enable failed\n", - __func__); - -out: - return err; + return ufs_qcom_get_connected_tx_lanes(hba, &tx_lanes); } static int ufs_qcom_check_hibern8(struct ufs_hba *hba) @@ -932,10 +918,8 @@ static int ufs_qcom_pwr_change_notify(struct ufs_hba *hba, { u32 val; struct ufs_qcom_host *host = ufshcd_get_variant(hba); - struct phy *phy = host->generic_phy; struct ufs_qcom_dev_params ufs_qcom_cap; int ret = 0; - int res = 0; if (!dev_req_params) { pr_err("%s: incoming dev_req_params is NULL\n", __func__); @@ -1002,12 +986,6 @@ static int ufs_qcom_pwr_change_notify(struct ufs_hba *hba, } val = ~(MAX_U32 << dev_req_params->lane_tx); - res = ufs_qcom_phy_set_tx_lane_enable(phy, val); - if (res) { - dev_err(hba->dev, "%s: ufs_qcom_phy_set_tx_lane_enable() failed res = %d\n", - __func__, res); - ret = res; - } /* cache the power mode parameters to use internally */ memcpy(&host->dev_req_params, @@ -1264,10 +1242,6 @@ static int ufs_qcom_init(struct ufs_hba *hba) } } - /* update phy revision information before calling phy_init() */ - ufs_qcom_phy_save_controller_version(host->generic_phy, - host->hw_ver.major, host->hw_ver.minor, host->hw_ver.step); - err = ufs_qcom_init_lane_clks(host); if (err) goto out_variant_clear; diff --git a/drivers/scsi/ufs/ufs-qcom.h b/drivers/scsi/ufs/ufs-qcom.h index 295f4bef6a0e..c114826316eb 100644 --- a/drivers/scsi/ufs/ufs-qcom.h +++ b/drivers/scsi/ufs/ufs-qcom.h @@ -129,11 +129,6 @@ enum { MASK_CLK_NS_REG = 0xFFFC00, }; -enum ufs_qcom_phy_init_type { - UFS_PHY_INIT_FULL, - UFS_PHY_INIT_CFG_RESTORE, -}; - /* QCOM UFS debug print bit mask */ #define UFS_QCOM_DBG_PRINT_REGS_EN BIT(0) #define UFS_QCOM_DBG_PRINT_ICE_REGS_EN BIT(1) diff --git a/include/linux/phy/phy-qcom-ufs.h b/include/linux/phy/phy-qcom-ufs.h deleted file mode 100644 index 9dd85071bcce..000000000000 --- a/include/linux/phy/phy-qcom-ufs.h +++ /dev/null @@ -1,24 +0,0 @@ -/* - * Copyright (c) 2013-2015, Linux Foundation. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 and - * only version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - */ - -#ifndef PHY_QCOM_UFS_H_ -#define PHY_QCOM_UFS_H_ - -#include "phy.h" - -int ufs_qcom_phy_set_tx_lane_enable(struct phy *phy, u32 tx_lanes); -void ufs_qcom_phy_save_controller_version(struct phy *phy, - u8 major, u16 minor, u16 step); - -#endif /* PHY_QCOM_UFS_H_ */ -- cgit v1.2.3 From 6b58859419554fb824e09cfdd73151a195473cbc Mon Sep 17 00:00:00 2001 From: Justin Ernst Date: Tue, 25 Sep 2018 09:34:49 -0500 Subject: EDAC: Raise the maximum number of memory controllers We observe an oops in the skx_edac module during boot: EDAC MC0: Giving out device to module skx_edac controller Skylake Socket#0 IMC#0 EDAC MC1: Giving out device to module skx_edac controller Skylake Socket#0 IMC#1 EDAC MC2: Giving out device to module skx_edac controller Skylake Socket#1 IMC#0 ... EDAC MC13: Giving out device to module skx_edac controller Skylake Socket#0 IMC#1 EDAC MC14: Giving out device to module skx_edac controller Skylake Socket#1 IMC#0 EDAC MC15: Giving out device to module skx_edac controller Skylake Socket#1 IMC#1 Too many memory controllers: 16 EDAC MC: Removed device 0 for skx_edac Skylake Socket#0 IMC#0 We observe there are two memory controllers per socket, with a limit of 16. Raise the maximum number of memory controllers from 16 to 2 * MAX_NUMNODES (1024). [ bp: This is just a band-aid fix until we've sorted out the whole issue with the bus_type association and handling in EDAC and can get rid of this arbitrary limit. ] Signed-off-by: Justin Ernst Signed-off-by: Borislav Petkov Acked-by: Russ Anderson Cc: Mauro Carvalho Chehab Cc: linux-edac@vger.kernel.org Link: https://lkml.kernel.org/r/20180925143449.284634-1-justin.ernst@hpe.com --- include/linux/edac.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/edac.h b/include/linux/edac.h index a45ce1f84bfc..1d0c9ea8825d 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -17,6 +17,7 @@ #include #include #include +#include #define EDAC_DEVICE_NAME_LEN 31 @@ -672,6 +673,6 @@ struct mem_ctl_info { /* * Maximum number of memory controllers in the coherent fabric. */ -#define EDAC_MAX_MCS 16 +#define EDAC_MAX_MCS 2 * MAX_NUMNODES #endif -- cgit v1.2.3 From e9e575b8f29445bcde67f421891efa4d6527d987 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 18 Sep 2018 19:10:39 -0700 Subject: gss_krb5: Remove VLA usage of skcipher In the quest to remove all stack VLA usage from the kernel[1], this replaces struct crypto_skcipher and SKCIPHER_REQUEST_ON_STACK() usage with struct crypto_sync_skcipher and SYNC_SKCIPHER_REQUEST_ON_STACK(), which uses a fixed stack size. [1] https://lkml.kernel.org/r/CA+55aFzCG-zNmZwX4A2FQpadafLfEzK6CC=qPXydAacU1RqZWA@mail.gmail.com Cc: Trond Myklebust Cc: Anna Schumaker Cc: "J. Bruce Fields" Cc: Jeff Layton Cc: YueHaibing Cc: linux-nfs@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: Herbert Xu --- include/linux/sunrpc/gss_krb5.h | 30 ++++++------ net/sunrpc/auth_gss/gss_krb5_crypto.c | 87 ++++++++++++++++++----------------- net/sunrpc/auth_gss/gss_krb5_keys.c | 9 ++-- net/sunrpc/auth_gss/gss_krb5_mech.c | 53 ++++++++++----------- net/sunrpc/auth_gss/gss_krb5_seqnum.c | 18 ++++---- net/sunrpc/auth_gss/gss_krb5_wrap.c | 20 ++++---- 6 files changed, 108 insertions(+), 109 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index 7df625d41e35..f6e8ceafafd8 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -71,10 +71,10 @@ struct gss_krb5_enctype { const u32 keyed_cksum; /* is it a keyed cksum? */ const u32 keybytes; /* raw key len, in bytes */ const u32 keylength; /* final key len, in bytes */ - u32 (*encrypt) (struct crypto_skcipher *tfm, + u32 (*encrypt) (struct crypto_sync_skcipher *tfm, void *iv, void *in, void *out, int length); /* encryption function */ - u32 (*decrypt) (struct crypto_skcipher *tfm, + u32 (*decrypt) (struct crypto_sync_skcipher *tfm, void *iv, void *in, void *out, int length); /* decryption function */ u32 (*mk_key) (const struct gss_krb5_enctype *gk5e, @@ -98,12 +98,12 @@ struct krb5_ctx { u32 enctype; u32 flags; const struct gss_krb5_enctype *gk5e; /* enctype-specific info */ - struct crypto_skcipher *enc; - struct crypto_skcipher *seq; - struct crypto_skcipher *acceptor_enc; - struct crypto_skcipher *initiator_enc; - struct crypto_skcipher *acceptor_enc_aux; - struct crypto_skcipher *initiator_enc_aux; + struct crypto_sync_skcipher *enc; + struct crypto_sync_skcipher *seq; + struct crypto_sync_skcipher *acceptor_enc; + struct crypto_sync_skcipher *initiator_enc; + struct crypto_sync_skcipher *acceptor_enc_aux; + struct crypto_sync_skcipher *initiator_enc_aux; u8 Ksess[GSS_KRB5_MAX_KEYLEN]; /* session key */ u8 cksum[GSS_KRB5_MAX_KEYLEN]; s32 endtime; @@ -262,24 +262,24 @@ gss_unwrap_kerberos(struct gss_ctx *ctx_id, int offset, u32 -krb5_encrypt(struct crypto_skcipher *key, +krb5_encrypt(struct crypto_sync_skcipher *key, void *iv, void *in, void *out, int length); u32 -krb5_decrypt(struct crypto_skcipher *key, +krb5_decrypt(struct crypto_sync_skcipher *key, void *iv, void *in, void *out, int length); int -gss_encrypt_xdr_buf(struct crypto_skcipher *tfm, struct xdr_buf *outbuf, +gss_encrypt_xdr_buf(struct crypto_sync_skcipher *tfm, struct xdr_buf *outbuf, int offset, struct page **pages); int -gss_decrypt_xdr_buf(struct crypto_skcipher *tfm, struct xdr_buf *inbuf, +gss_decrypt_xdr_buf(struct crypto_sync_skcipher *tfm, struct xdr_buf *inbuf, int offset); s32 krb5_make_seq_num(struct krb5_ctx *kctx, - struct crypto_skcipher *key, + struct crypto_sync_skcipher *key, int direction, u32 seqnum, unsigned char *cksum, unsigned char *buf); @@ -320,12 +320,12 @@ gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, int krb5_rc4_setup_seq_key(struct krb5_ctx *kctx, - struct crypto_skcipher *cipher, + struct crypto_sync_skcipher *cipher, unsigned char *cksum); int krb5_rc4_setup_enc_key(struct krb5_ctx *kctx, - struct crypto_skcipher *cipher, + struct crypto_sync_skcipher *cipher, s32 seqnum); void gss_krb5_make_confounder(char *p, u32 conflen); diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index 0220e1ca5280..4f43383971ba 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -53,7 +53,7 @@ u32 krb5_encrypt( - struct crypto_skcipher *tfm, + struct crypto_sync_skcipher *tfm, void * iv, void * in, void * out, @@ -62,24 +62,24 @@ krb5_encrypt( u32 ret = -EINVAL; struct scatterlist sg[1]; u8 local_iv[GSS_KRB5_MAX_BLOCKSIZE] = {0}; - SKCIPHER_REQUEST_ON_STACK(req, tfm); + SYNC_SKCIPHER_REQUEST_ON_STACK(req, tfm); - if (length % crypto_skcipher_blocksize(tfm) != 0) + if (length % crypto_sync_skcipher_blocksize(tfm) != 0) goto out; - if (crypto_skcipher_ivsize(tfm) > GSS_KRB5_MAX_BLOCKSIZE) { + if (crypto_sync_skcipher_ivsize(tfm) > GSS_KRB5_MAX_BLOCKSIZE) { dprintk("RPC: gss_k5encrypt: tfm iv size too large %d\n", - crypto_skcipher_ivsize(tfm)); + crypto_sync_skcipher_ivsize(tfm)); goto out; } if (iv) - memcpy(local_iv, iv, crypto_skcipher_ivsize(tfm)); + memcpy(local_iv, iv, crypto_sync_skcipher_ivsize(tfm)); memcpy(out, in, length); sg_init_one(sg, out, length); - skcipher_request_set_tfm(req, tfm); + skcipher_request_set_sync_tfm(req, tfm); skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, sg, sg, length, local_iv); @@ -92,7 +92,7 @@ out: u32 krb5_decrypt( - struct crypto_skcipher *tfm, + struct crypto_sync_skcipher *tfm, void * iv, void * in, void * out, @@ -101,23 +101,23 @@ krb5_decrypt( u32 ret = -EINVAL; struct scatterlist sg[1]; u8 local_iv[GSS_KRB5_MAX_BLOCKSIZE] = {0}; - SKCIPHER_REQUEST_ON_STACK(req, tfm); + SYNC_SKCIPHER_REQUEST_ON_STACK(req, tfm); - if (length % crypto_skcipher_blocksize(tfm) != 0) + if (length % crypto_sync_skcipher_blocksize(tfm) != 0) goto out; - if (crypto_skcipher_ivsize(tfm) > GSS_KRB5_MAX_BLOCKSIZE) { + if (crypto_sync_skcipher_ivsize(tfm) > GSS_KRB5_MAX_BLOCKSIZE) { dprintk("RPC: gss_k5decrypt: tfm iv size too large %d\n", - crypto_skcipher_ivsize(tfm)); + crypto_sync_skcipher_ivsize(tfm)); goto out; } if (iv) - memcpy(local_iv,iv, crypto_skcipher_ivsize(tfm)); + memcpy(local_iv, iv, crypto_sync_skcipher_ivsize(tfm)); memcpy(out, in, length); sg_init_one(sg, out, length); - skcipher_request_set_tfm(req, tfm); + skcipher_request_set_sync_tfm(req, tfm); skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, sg, sg, length, local_iv); @@ -466,7 +466,8 @@ encryptor(struct scatterlist *sg, void *data) { struct encryptor_desc *desc = data; struct xdr_buf *outbuf = desc->outbuf; - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(desc->req); + struct crypto_sync_skcipher *tfm = + crypto_sync_skcipher_reqtfm(desc->req); struct page *in_page; int thislen = desc->fraglen + sg->length; int fraglen, ret; @@ -492,7 +493,7 @@ encryptor(struct scatterlist *sg, void *data) desc->fraglen += sg->length; desc->pos += sg->length; - fraglen = thislen & (crypto_skcipher_blocksize(tfm) - 1); + fraglen = thislen & (crypto_sync_skcipher_blocksize(tfm) - 1); thislen -= fraglen; if (thislen == 0) @@ -526,16 +527,16 @@ encryptor(struct scatterlist *sg, void *data) } int -gss_encrypt_xdr_buf(struct crypto_skcipher *tfm, struct xdr_buf *buf, +gss_encrypt_xdr_buf(struct crypto_sync_skcipher *tfm, struct xdr_buf *buf, int offset, struct page **pages) { int ret; struct encryptor_desc desc; - SKCIPHER_REQUEST_ON_STACK(req, tfm); + SYNC_SKCIPHER_REQUEST_ON_STACK(req, tfm); - BUG_ON((buf->len - offset) % crypto_skcipher_blocksize(tfm) != 0); + BUG_ON((buf->len - offset) % crypto_sync_skcipher_blocksize(tfm) != 0); - skcipher_request_set_tfm(req, tfm); + skcipher_request_set_sync_tfm(req, tfm); skcipher_request_set_callback(req, 0, NULL, NULL); memset(desc.iv, 0, sizeof(desc.iv)); @@ -567,7 +568,8 @@ decryptor(struct scatterlist *sg, void *data) { struct decryptor_desc *desc = data; int thislen = desc->fraglen + sg->length; - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(desc->req); + struct crypto_sync_skcipher *tfm = + crypto_sync_skcipher_reqtfm(desc->req); int fraglen, ret; /* Worst case is 4 fragments: head, end of page 1, start @@ -578,7 +580,7 @@ decryptor(struct scatterlist *sg, void *data) desc->fragno++; desc->fraglen += sg->length; - fraglen = thislen & (crypto_skcipher_blocksize(tfm) - 1); + fraglen = thislen & (crypto_sync_skcipher_blocksize(tfm) - 1); thislen -= fraglen; if (thislen == 0) @@ -608,17 +610,17 @@ decryptor(struct scatterlist *sg, void *data) } int -gss_decrypt_xdr_buf(struct crypto_skcipher *tfm, struct xdr_buf *buf, +gss_decrypt_xdr_buf(struct crypto_sync_skcipher *tfm, struct xdr_buf *buf, int offset) { int ret; struct decryptor_desc desc; - SKCIPHER_REQUEST_ON_STACK(req, tfm); + SYNC_SKCIPHER_REQUEST_ON_STACK(req, tfm); /* XXXJBF: */ - BUG_ON((buf->len - offset) % crypto_skcipher_blocksize(tfm) != 0); + BUG_ON((buf->len - offset) % crypto_sync_skcipher_blocksize(tfm) != 0); - skcipher_request_set_tfm(req, tfm); + skcipher_request_set_sync_tfm(req, tfm); skcipher_request_set_callback(req, 0, NULL, NULL); memset(desc.iv, 0, sizeof(desc.iv)); @@ -672,12 +674,12 @@ xdr_extend_head(struct xdr_buf *buf, unsigned int base, unsigned int shiftlen) } static u32 -gss_krb5_cts_crypt(struct crypto_skcipher *cipher, struct xdr_buf *buf, +gss_krb5_cts_crypt(struct crypto_sync_skcipher *cipher, struct xdr_buf *buf, u32 offset, u8 *iv, struct page **pages, int encrypt) { u32 ret; struct scatterlist sg[1]; - SKCIPHER_REQUEST_ON_STACK(req, cipher); + SYNC_SKCIPHER_REQUEST_ON_STACK(req, cipher); u8 *data; struct page **save_pages; u32 len = buf->len - offset; @@ -706,7 +708,7 @@ gss_krb5_cts_crypt(struct crypto_skcipher *cipher, struct xdr_buf *buf, sg_init_one(sg, data, len); - skcipher_request_set_tfm(req, cipher); + skcipher_request_set_sync_tfm(req, cipher); skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, sg, sg, len, iv); @@ -735,7 +737,7 @@ gss_krb5_aes_encrypt(struct krb5_ctx *kctx, u32 offset, struct xdr_netobj hmac; u8 *cksumkey; u8 *ecptr; - struct crypto_skcipher *cipher, *aux_cipher; + struct crypto_sync_skcipher *cipher, *aux_cipher; int blocksize; struct page **save_pages; int nblocks, nbytes; @@ -754,7 +756,7 @@ gss_krb5_aes_encrypt(struct krb5_ctx *kctx, u32 offset, cksumkey = kctx->acceptor_integ; usage = KG_USAGE_ACCEPTOR_SEAL; } - blocksize = crypto_skcipher_blocksize(cipher); + blocksize = crypto_sync_skcipher_blocksize(cipher); /* hide the gss token header and insert the confounder */ offset += GSS_KRB5_TOK_HDR_LEN; @@ -807,7 +809,7 @@ gss_krb5_aes_encrypt(struct krb5_ctx *kctx, u32 offset, memset(desc.iv, 0, sizeof(desc.iv)); if (cbcbytes) { - SKCIPHER_REQUEST_ON_STACK(req, aux_cipher); + SYNC_SKCIPHER_REQUEST_ON_STACK(req, aux_cipher); desc.pos = offset + GSS_KRB5_TOK_HDR_LEN; desc.fragno = 0; @@ -816,7 +818,7 @@ gss_krb5_aes_encrypt(struct krb5_ctx *kctx, u32 offset, desc.outbuf = buf; desc.req = req; - skcipher_request_set_tfm(req, aux_cipher); + skcipher_request_set_sync_tfm(req, aux_cipher); skcipher_request_set_callback(req, 0, NULL, NULL); sg_init_table(desc.infrags, 4); @@ -855,7 +857,7 @@ gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf, struct xdr_buf subbuf; u32 ret = 0; u8 *cksum_key; - struct crypto_skcipher *cipher, *aux_cipher; + struct crypto_sync_skcipher *cipher, *aux_cipher; struct xdr_netobj our_hmac_obj; u8 our_hmac[GSS_KRB5_MAX_CKSUM_LEN]; u8 pkt_hmac[GSS_KRB5_MAX_CKSUM_LEN]; @@ -874,7 +876,7 @@ gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf, cksum_key = kctx->initiator_integ; usage = KG_USAGE_INITIATOR_SEAL; } - blocksize = crypto_skcipher_blocksize(cipher); + blocksize = crypto_sync_skcipher_blocksize(cipher); /* create a segment skipping the header and leaving out the checksum */ @@ -891,13 +893,13 @@ gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf, memset(desc.iv, 0, sizeof(desc.iv)); if (cbcbytes) { - SKCIPHER_REQUEST_ON_STACK(req, aux_cipher); + SYNC_SKCIPHER_REQUEST_ON_STACK(req, aux_cipher); desc.fragno = 0; desc.fraglen = 0; desc.req = req; - skcipher_request_set_tfm(req, aux_cipher); + skcipher_request_set_sync_tfm(req, aux_cipher); skcipher_request_set_callback(req, 0, NULL, NULL); sg_init_table(desc.frags, 4); @@ -946,7 +948,8 @@ out_err: * Set the key of the given cipher. */ int -krb5_rc4_setup_seq_key(struct krb5_ctx *kctx, struct crypto_skcipher *cipher, +krb5_rc4_setup_seq_key(struct krb5_ctx *kctx, + struct crypto_sync_skcipher *cipher, unsigned char *cksum) { struct crypto_shash *hmac; @@ -994,7 +997,7 @@ krb5_rc4_setup_seq_key(struct krb5_ctx *kctx, struct crypto_skcipher *cipher, if (err) goto out_err; - err = crypto_skcipher_setkey(cipher, Kseq, kctx->gk5e->keylength); + err = crypto_sync_skcipher_setkey(cipher, Kseq, kctx->gk5e->keylength); if (err) goto out_err; @@ -1012,7 +1015,8 @@ out_err: * Set the key of cipher kctx->enc. */ int -krb5_rc4_setup_enc_key(struct krb5_ctx *kctx, struct crypto_skcipher *cipher, +krb5_rc4_setup_enc_key(struct krb5_ctx *kctx, + struct crypto_sync_skcipher *cipher, s32 seqnum) { struct crypto_shash *hmac; @@ -1069,7 +1073,8 @@ krb5_rc4_setup_enc_key(struct krb5_ctx *kctx, struct crypto_skcipher *cipher, if (err) goto out_err; - err = crypto_skcipher_setkey(cipher, Kcrypt, kctx->gk5e->keylength); + err = crypto_sync_skcipher_setkey(cipher, Kcrypt, + kctx->gk5e->keylength); if (err) goto out_err; diff --git a/net/sunrpc/auth_gss/gss_krb5_keys.c b/net/sunrpc/auth_gss/gss_krb5_keys.c index f7fe2d2b851f..550fdf18d3b3 100644 --- a/net/sunrpc/auth_gss/gss_krb5_keys.c +++ b/net/sunrpc/auth_gss/gss_krb5_keys.c @@ -147,7 +147,7 @@ u32 krb5_derive_key(const struct gss_krb5_enctype *gk5e, size_t blocksize, keybytes, keylength, n; unsigned char *inblockdata, *outblockdata, *rawkey; struct xdr_netobj inblock, outblock; - struct crypto_skcipher *cipher; + struct crypto_sync_skcipher *cipher; u32 ret = EINVAL; blocksize = gk5e->blocksize; @@ -157,11 +157,10 @@ u32 krb5_derive_key(const struct gss_krb5_enctype *gk5e, if ((inkey->len != keylength) || (outkey->len != keylength)) goto err_return; - cipher = crypto_alloc_skcipher(gk5e->encrypt_name, 0, - CRYPTO_ALG_ASYNC); + cipher = crypto_alloc_sync_skcipher(gk5e->encrypt_name, 0, 0); if (IS_ERR(cipher)) goto err_return; - if (crypto_skcipher_setkey(cipher, inkey->data, inkey->len)) + if (crypto_sync_skcipher_setkey(cipher, inkey->data, inkey->len)) goto err_return; /* allocate and set up buffers */ @@ -238,7 +237,7 @@ err_free_in: memset(inblockdata, 0, blocksize); kfree(inblockdata); err_free_cipher: - crypto_free_skcipher(cipher); + crypto_free_sync_skcipher(cipher); err_return: return ret; } diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index 7bb2514aadd9..7f0424dfa8f6 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -218,7 +218,7 @@ simple_get_netobj(const void *p, const void *end, struct xdr_netobj *res) static inline const void * get_key(const void *p, const void *end, - struct krb5_ctx *ctx, struct crypto_skcipher **res) + struct krb5_ctx *ctx, struct crypto_sync_skcipher **res) { struct xdr_netobj key; int alg; @@ -246,15 +246,14 @@ get_key(const void *p, const void *end, if (IS_ERR(p)) goto out_err; - *res = crypto_alloc_skcipher(ctx->gk5e->encrypt_name, 0, - CRYPTO_ALG_ASYNC); + *res = crypto_alloc_sync_skcipher(ctx->gk5e->encrypt_name, 0, 0); if (IS_ERR(*res)) { printk(KERN_WARNING "gss_kerberos_mech: unable to initialize " "crypto algorithm %s\n", ctx->gk5e->encrypt_name); *res = NULL; goto out_err_free_key; } - if (crypto_skcipher_setkey(*res, key.data, key.len)) { + if (crypto_sync_skcipher_setkey(*res, key.data, key.len)) { printk(KERN_WARNING "gss_kerberos_mech: error setting key for " "crypto algorithm %s\n", ctx->gk5e->encrypt_name); goto out_err_free_tfm; @@ -264,7 +263,7 @@ get_key(const void *p, const void *end, return p; out_err_free_tfm: - crypto_free_skcipher(*res); + crypto_free_sync_skcipher(*res); out_err_free_key: kfree(key.data); p = ERR_PTR(-EINVAL); @@ -336,30 +335,30 @@ gss_import_v1_context(const void *p, const void *end, struct krb5_ctx *ctx) return 0; out_err_free_key2: - crypto_free_skcipher(ctx->seq); + crypto_free_sync_skcipher(ctx->seq); out_err_free_key1: - crypto_free_skcipher(ctx->enc); + crypto_free_sync_skcipher(ctx->enc); out_err_free_mech: kfree(ctx->mech_used.data); out_err: return PTR_ERR(p); } -static struct crypto_skcipher * +static struct crypto_sync_skcipher * context_v2_alloc_cipher(struct krb5_ctx *ctx, const char *cname, u8 *key) { - struct crypto_skcipher *cp; + struct crypto_sync_skcipher *cp; - cp = crypto_alloc_skcipher(cname, 0, CRYPTO_ALG_ASYNC); + cp = crypto_alloc_sync_skcipher(cname, 0, 0); if (IS_ERR(cp)) { dprintk("gss_kerberos_mech: unable to initialize " "crypto algorithm %s\n", cname); return NULL; } - if (crypto_skcipher_setkey(cp, key, ctx->gk5e->keylength)) { + if (crypto_sync_skcipher_setkey(cp, key, ctx->gk5e->keylength)) { dprintk("gss_kerberos_mech: error setting key for " "crypto algorithm %s\n", cname); - crypto_free_skcipher(cp); + crypto_free_sync_skcipher(cp); return NULL; } return cp; @@ -413,9 +412,9 @@ context_derive_keys_des3(struct krb5_ctx *ctx, gfp_t gfp_mask) return 0; out_free_enc: - crypto_free_skcipher(ctx->enc); + crypto_free_sync_skcipher(ctx->enc); out_free_seq: - crypto_free_skcipher(ctx->seq); + crypto_free_sync_skcipher(ctx->seq); out_err: return -EINVAL; } @@ -469,17 +468,15 @@ context_derive_keys_rc4(struct krb5_ctx *ctx) /* * allocate hash, and skciphers for data and seqnum encryption */ - ctx->enc = crypto_alloc_skcipher(ctx->gk5e->encrypt_name, 0, - CRYPTO_ALG_ASYNC); + ctx->enc = crypto_alloc_sync_skcipher(ctx->gk5e->encrypt_name, 0, 0); if (IS_ERR(ctx->enc)) { err = PTR_ERR(ctx->enc); goto out_err_free_hmac; } - ctx->seq = crypto_alloc_skcipher(ctx->gk5e->encrypt_name, 0, - CRYPTO_ALG_ASYNC); + ctx->seq = crypto_alloc_sync_skcipher(ctx->gk5e->encrypt_name, 0, 0); if (IS_ERR(ctx->seq)) { - crypto_free_skcipher(ctx->enc); + crypto_free_sync_skcipher(ctx->enc); err = PTR_ERR(ctx->seq); goto out_err_free_hmac; } @@ -591,7 +588,7 @@ context_derive_keys_new(struct krb5_ctx *ctx, gfp_t gfp_mask) context_v2_alloc_cipher(ctx, "cbc(aes)", ctx->acceptor_seal); if (ctx->acceptor_enc_aux == NULL) { - crypto_free_skcipher(ctx->initiator_enc_aux); + crypto_free_sync_skcipher(ctx->initiator_enc_aux); goto out_free_acceptor_enc; } } @@ -599,9 +596,9 @@ context_derive_keys_new(struct krb5_ctx *ctx, gfp_t gfp_mask) return 0; out_free_acceptor_enc: - crypto_free_skcipher(ctx->acceptor_enc); + crypto_free_sync_skcipher(ctx->acceptor_enc); out_free_initiator_enc: - crypto_free_skcipher(ctx->initiator_enc); + crypto_free_sync_skcipher(ctx->initiator_enc); out_err: return -EINVAL; } @@ -713,12 +710,12 @@ static void gss_delete_sec_context_kerberos(void *internal_ctx) { struct krb5_ctx *kctx = internal_ctx; - crypto_free_skcipher(kctx->seq); - crypto_free_skcipher(kctx->enc); - crypto_free_skcipher(kctx->acceptor_enc); - crypto_free_skcipher(kctx->initiator_enc); - crypto_free_skcipher(kctx->acceptor_enc_aux); - crypto_free_skcipher(kctx->initiator_enc_aux); + crypto_free_sync_skcipher(kctx->seq); + crypto_free_sync_skcipher(kctx->enc); + crypto_free_sync_skcipher(kctx->acceptor_enc); + crypto_free_sync_skcipher(kctx->initiator_enc); + crypto_free_sync_skcipher(kctx->acceptor_enc_aux); + crypto_free_sync_skcipher(kctx->initiator_enc_aux); kfree(kctx->mech_used.data); kfree(kctx); } diff --git a/net/sunrpc/auth_gss/gss_krb5_seqnum.c b/net/sunrpc/auth_gss/gss_krb5_seqnum.c index c8b9082f4a9d..fb6656295204 100644 --- a/net/sunrpc/auth_gss/gss_krb5_seqnum.c +++ b/net/sunrpc/auth_gss/gss_krb5_seqnum.c @@ -43,13 +43,12 @@ static s32 krb5_make_rc4_seq_num(struct krb5_ctx *kctx, int direction, s32 seqnum, unsigned char *cksum, unsigned char *buf) { - struct crypto_skcipher *cipher; + struct crypto_sync_skcipher *cipher; unsigned char plain[8]; s32 code; dprintk("RPC: %s:\n", __func__); - cipher = crypto_alloc_skcipher(kctx->gk5e->encrypt_name, 0, - CRYPTO_ALG_ASYNC); + cipher = crypto_alloc_sync_skcipher(kctx->gk5e->encrypt_name, 0, 0); if (IS_ERR(cipher)) return PTR_ERR(cipher); @@ -68,12 +67,12 @@ krb5_make_rc4_seq_num(struct krb5_ctx *kctx, int direction, s32 seqnum, code = krb5_encrypt(cipher, cksum, plain, buf, 8); out: - crypto_free_skcipher(cipher); + crypto_free_sync_skcipher(cipher); return code; } s32 krb5_make_seq_num(struct krb5_ctx *kctx, - struct crypto_skcipher *key, + struct crypto_sync_skcipher *key, int direction, u32 seqnum, unsigned char *cksum, unsigned char *buf) @@ -101,13 +100,12 @@ static s32 krb5_get_rc4_seq_num(struct krb5_ctx *kctx, unsigned char *cksum, unsigned char *buf, int *direction, s32 *seqnum) { - struct crypto_skcipher *cipher; + struct crypto_sync_skcipher *cipher; unsigned char plain[8]; s32 code; dprintk("RPC: %s:\n", __func__); - cipher = crypto_alloc_skcipher(kctx->gk5e->encrypt_name, 0, - CRYPTO_ALG_ASYNC); + cipher = crypto_alloc_sync_skcipher(kctx->gk5e->encrypt_name, 0, 0); if (IS_ERR(cipher)) return PTR_ERR(cipher); @@ -130,7 +128,7 @@ krb5_get_rc4_seq_num(struct krb5_ctx *kctx, unsigned char *cksum, *seqnum = ((plain[0] << 24) | (plain[1] << 16) | (plain[2] << 8) | (plain[3])); out: - crypto_free_skcipher(cipher); + crypto_free_sync_skcipher(cipher); return code; } @@ -142,7 +140,7 @@ krb5_get_seq_num(struct krb5_ctx *kctx, { s32 code; unsigned char plain[8]; - struct crypto_skcipher *key = kctx->seq; + struct crypto_sync_skcipher *key = kctx->seq; dprintk("RPC: krb5_get_seq_num:\n"); diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c index 39a2e672900b..3d975a4013d2 100644 --- a/net/sunrpc/auth_gss/gss_krb5_wrap.c +++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c @@ -174,7 +174,7 @@ gss_wrap_kerberos_v1(struct krb5_ctx *kctx, int offset, now = get_seconds(); - blocksize = crypto_skcipher_blocksize(kctx->enc); + blocksize = crypto_sync_skcipher_blocksize(kctx->enc); gss_krb5_add_padding(buf, offset, blocksize); BUG_ON((buf->len - offset) % blocksize); plainlen = conflen + buf->len - offset; @@ -239,10 +239,10 @@ gss_wrap_kerberos_v1(struct krb5_ctx *kctx, int offset, return GSS_S_FAILURE; if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC) { - struct crypto_skcipher *cipher; + struct crypto_sync_skcipher *cipher; int err; - cipher = crypto_alloc_skcipher(kctx->gk5e->encrypt_name, 0, - CRYPTO_ALG_ASYNC); + cipher = crypto_alloc_sync_skcipher(kctx->gk5e->encrypt_name, + 0, 0); if (IS_ERR(cipher)) return GSS_S_FAILURE; @@ -250,7 +250,7 @@ gss_wrap_kerberos_v1(struct krb5_ctx *kctx, int offset, err = gss_encrypt_xdr_buf(cipher, buf, offset + headlen - conflen, pages); - crypto_free_skcipher(cipher); + crypto_free_sync_skcipher(cipher); if (err) return GSS_S_FAILURE; } else { @@ -327,18 +327,18 @@ gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) return GSS_S_BAD_SIG; if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC) { - struct crypto_skcipher *cipher; + struct crypto_sync_skcipher *cipher; int err; - cipher = crypto_alloc_skcipher(kctx->gk5e->encrypt_name, 0, - CRYPTO_ALG_ASYNC); + cipher = crypto_alloc_sync_skcipher(kctx->gk5e->encrypt_name, + 0, 0); if (IS_ERR(cipher)) return GSS_S_FAILURE; krb5_rc4_setup_enc_key(kctx, cipher, seqnum); err = gss_decrypt_xdr_buf(cipher, buf, crypt_offset); - crypto_free_skcipher(cipher); + crypto_free_sync_skcipher(cipher); if (err) return GSS_S_DEFECTIVE_TOKEN; } else { @@ -371,7 +371,7 @@ gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) /* Copy the data back to the right position. XXX: Would probably be * better to copy and encrypt at the same time. */ - blocksize = crypto_skcipher_blocksize(kctx->enc); + blocksize = crypto_sync_skcipher_blocksize(kctx->enc); data_start = ptr + (GSS_KRB5_TOK_HDR_LEN + kctx->gk5e->cksumlength) + conflen; orig_start = buf->head[0].iov_base + offset; -- cgit v1.2.3 From cac5818c25d0423bda73e2b6997404ed0a7ed9e3 Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Wed, 19 Sep 2018 10:10:54 +0000 Subject: crypto: user - Implement a generic crypto statistics This patch implement a generic way to get statistics about all crypto usages. Signed-off-by: Corentin Labbe Signed-off-by: Herbert Xu --- crypto/Kconfig | 11 + crypto/Makefile | 1 + crypto/ahash.c | 21 +- crypto/algapi.c | 8 + crypto/crypto_user.c | 566 ---------------------------------- crypto/crypto_user_base.c | 571 +++++++++++++++++++++++++++++++++++ crypto/crypto_user_stat.c | 463 ++++++++++++++++++++++++++++ crypto/rng.c | 1 + include/crypto/acompress.h | 38 ++- include/crypto/aead.h | 51 +++- include/crypto/akcipher.h | 76 ++++- include/crypto/hash.h | 32 +- include/crypto/internal/cryptouser.h | 8 + include/crypto/kpp.h | 51 +++- include/crypto/rng.h | 29 +- include/crypto/skcipher.h | 44 ++- include/linux/crypto.h | 110 ++++++- include/uapi/linux/cryptouser.h | 52 ++++ 18 files changed, 1534 insertions(+), 599 deletions(-) delete mode 100644 crypto/crypto_user.c create mode 100644 crypto/crypto_user_base.c create mode 100644 crypto/crypto_user_stat.c create mode 100644 include/crypto/internal/cryptouser.h (limited to 'include/linux') diff --git a/crypto/Kconfig b/crypto/Kconfig index 90f2811fac5f..4ef95b0b25a3 100644 --- a/crypto/Kconfig +++ b/crypto/Kconfig @@ -1799,6 +1799,17 @@ config CRYPTO_USER_API_AEAD This option enables the user-spaces interface for AEAD cipher algorithms. +config CRYPTO_STATS + bool "Crypto usage statistics for User-space" + help + This option enables the gathering of crypto stats. + This will collect: + - encrypt/decrypt size and numbers of symmeric operations + - compress/decompress size and numbers of compress operations + - size and numbers of hash operations + - encrypt/decrypt/sign/verify numbers for asymmetric operations + - generate/seed numbers for rng operations + config CRYPTO_HASH_INFO bool diff --git a/crypto/Makefile b/crypto/Makefile index d719843f8b6e..ff5c2bbda04a 100644 --- a/crypto/Makefile +++ b/crypto/Makefile @@ -54,6 +54,7 @@ cryptomgr-y := algboss.o testmgr.o obj-$(CONFIG_CRYPTO_MANAGER2) += cryptomgr.o obj-$(CONFIG_CRYPTO_USER) += crypto_user.o +crypto_user-y := crypto_user_base.o crypto_user_stat.o obj-$(CONFIG_CRYPTO_CMAC) += cmac.o obj-$(CONFIG_CRYPTO_HMAC) += hmac.o obj-$(CONFIG_CRYPTO_VMAC) += vmac.o diff --git a/crypto/ahash.c b/crypto/ahash.c index 78aaf2158c43..e21667b4e10a 100644 --- a/crypto/ahash.c +++ b/crypto/ahash.c @@ -364,24 +364,35 @@ static int crypto_ahash_op(struct ahash_request *req, int crypto_ahash_final(struct ahash_request *req) { - return crypto_ahash_op(req, crypto_ahash_reqtfm(req)->final); + int ret; + + ret = crypto_ahash_op(req, crypto_ahash_reqtfm(req)->final); + crypto_stat_ahash_final(req, ret); + return ret; } EXPORT_SYMBOL_GPL(crypto_ahash_final); int crypto_ahash_finup(struct ahash_request *req) { - return crypto_ahash_op(req, crypto_ahash_reqtfm(req)->finup); + int ret; + + ret = crypto_ahash_op(req, crypto_ahash_reqtfm(req)->finup); + crypto_stat_ahash_final(req, ret); + return ret; } EXPORT_SYMBOL_GPL(crypto_ahash_finup); int crypto_ahash_digest(struct ahash_request *req) { struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); + int ret; if (crypto_ahash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY) - return -ENOKEY; - - return crypto_ahash_op(req, tfm->digest); + ret = -ENOKEY; + else + ret = crypto_ahash_op(req, tfm->digest); + crypto_stat_ahash_final(req, ret); + return ret; } EXPORT_SYMBOL_GPL(crypto_ahash_digest); diff --git a/crypto/algapi.c b/crypto/algapi.c index 38daa8677da9..2545c5f89c4c 100644 --- a/crypto/algapi.c +++ b/crypto/algapi.c @@ -258,6 +258,14 @@ static struct crypto_larval *__crypto_register_alg(struct crypto_alg *alg) list_add(&alg->cra_list, &crypto_alg_list); list_add(&larval->alg.cra_list, &crypto_alg_list); + atomic_set(&alg->encrypt_cnt, 0); + atomic_set(&alg->decrypt_cnt, 0); + atomic64_set(&alg->encrypt_tlen, 0); + atomic64_set(&alg->decrypt_tlen, 0); + atomic_set(&alg->verify_cnt, 0); + atomic_set(&alg->cipher_err_cnt, 0); + atomic_set(&alg->sign_cnt, 0); + out: return larval; diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c deleted file mode 100644 index 0e89b5457cab..000000000000 --- a/crypto/crypto_user.c +++ /dev/null @@ -1,566 +0,0 @@ -/* - * Crypto user configuration API. - * - * Copyright (C) 2011 secunet Security Networks AG - * Copyright (C) 2011 Steffen Klassert - * - * 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, write to the Free Software Foundation, Inc., - * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "internal.h" - -#define null_terminated(x) (strnlen(x, sizeof(x)) < sizeof(x)) - -static DEFINE_MUTEX(crypto_cfg_mutex); - -/* The crypto netlink socket */ -static struct sock *crypto_nlsk; - -struct crypto_dump_info { - struct sk_buff *in_skb; - struct sk_buff *out_skb; - u32 nlmsg_seq; - u16 nlmsg_flags; -}; - -static struct crypto_alg *crypto_alg_match(struct crypto_user_alg *p, int exact) -{ - struct crypto_alg *q, *alg = NULL; - - down_read(&crypto_alg_sem); - - list_for_each_entry(q, &crypto_alg_list, cra_list) { - int match = 0; - - if ((q->cra_flags ^ p->cru_type) & p->cru_mask) - continue; - - if (strlen(p->cru_driver_name)) - match = !strcmp(q->cra_driver_name, - p->cru_driver_name); - else if (!exact) - match = !strcmp(q->cra_name, p->cru_name); - - if (!match) - continue; - - if (unlikely(!crypto_mod_get(q))) - continue; - - alg = q; - break; - } - - up_read(&crypto_alg_sem); - - return alg; -} - -static int crypto_report_cipher(struct sk_buff *skb, struct crypto_alg *alg) -{ - struct crypto_report_cipher rcipher; - - strlcpy(rcipher.type, "cipher", sizeof(rcipher.type)); - - rcipher.blocksize = alg->cra_blocksize; - rcipher.min_keysize = alg->cra_cipher.cia_min_keysize; - rcipher.max_keysize = alg->cra_cipher.cia_max_keysize; - - if (nla_put(skb, CRYPTOCFGA_REPORT_CIPHER, - sizeof(struct crypto_report_cipher), &rcipher)) - goto nla_put_failure; - return 0; - -nla_put_failure: - return -EMSGSIZE; -} - -static int crypto_report_comp(struct sk_buff *skb, struct crypto_alg *alg) -{ - struct crypto_report_comp rcomp; - - strlcpy(rcomp.type, "compression", sizeof(rcomp.type)); - if (nla_put(skb, CRYPTOCFGA_REPORT_COMPRESS, - sizeof(struct crypto_report_comp), &rcomp)) - goto nla_put_failure; - return 0; - -nla_put_failure: - return -EMSGSIZE; -} - -static int crypto_report_acomp(struct sk_buff *skb, struct crypto_alg *alg) -{ - struct crypto_report_acomp racomp; - - strlcpy(racomp.type, "acomp", sizeof(racomp.type)); - - if (nla_put(skb, CRYPTOCFGA_REPORT_ACOMP, - sizeof(struct crypto_report_acomp), &racomp)) - goto nla_put_failure; - return 0; - -nla_put_failure: - return -EMSGSIZE; -} - -static int crypto_report_akcipher(struct sk_buff *skb, struct crypto_alg *alg) -{ - struct crypto_report_akcipher rakcipher; - - strlcpy(rakcipher.type, "akcipher", sizeof(rakcipher.type)); - - if (nla_put(skb, CRYPTOCFGA_REPORT_AKCIPHER, - sizeof(struct crypto_report_akcipher), &rakcipher)) - goto nla_put_failure; - return 0; - -nla_put_failure: - return -EMSGSIZE; -} - -static int crypto_report_kpp(struct sk_buff *skb, struct crypto_alg *alg) -{ - struct crypto_report_kpp rkpp; - - strlcpy(rkpp.type, "kpp", sizeof(rkpp.type)); - - if (nla_put(skb, CRYPTOCFGA_REPORT_KPP, - sizeof(struct crypto_report_kpp), &rkpp)) - goto nla_put_failure; - return 0; - -nla_put_failure: - return -EMSGSIZE; -} - -static int crypto_report_one(struct crypto_alg *alg, - struct crypto_user_alg *ualg, struct sk_buff *skb) -{ - strlcpy(ualg->cru_name, alg->cra_name, sizeof(ualg->cru_name)); - strlcpy(ualg->cru_driver_name, alg->cra_driver_name, - sizeof(ualg->cru_driver_name)); - strlcpy(ualg->cru_module_name, module_name(alg->cra_module), - sizeof(ualg->cru_module_name)); - - ualg->cru_type = 0; - ualg->cru_mask = 0; - ualg->cru_flags = alg->cra_flags; - ualg->cru_refcnt = refcount_read(&alg->cra_refcnt); - - if (nla_put_u32(skb, CRYPTOCFGA_PRIORITY_VAL, alg->cra_priority)) - goto nla_put_failure; - if (alg->cra_flags & CRYPTO_ALG_LARVAL) { - struct crypto_report_larval rl; - - strlcpy(rl.type, "larval", sizeof(rl.type)); - if (nla_put(skb, CRYPTOCFGA_REPORT_LARVAL, - sizeof(struct crypto_report_larval), &rl)) - goto nla_put_failure; - goto out; - } - - if (alg->cra_type && alg->cra_type->report) { - if (alg->cra_type->report(skb, alg)) - goto nla_put_failure; - - goto out; - } - - switch (alg->cra_flags & (CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_LARVAL)) { - case CRYPTO_ALG_TYPE_CIPHER: - if (crypto_report_cipher(skb, alg)) - goto nla_put_failure; - - break; - case CRYPTO_ALG_TYPE_COMPRESS: - if (crypto_report_comp(skb, alg)) - goto nla_put_failure; - - break; - case CRYPTO_ALG_TYPE_ACOMPRESS: - if (crypto_report_acomp(skb, alg)) - goto nla_put_failure; - - break; - case CRYPTO_ALG_TYPE_AKCIPHER: - if (crypto_report_akcipher(skb, alg)) - goto nla_put_failure; - - break; - case CRYPTO_ALG_TYPE_KPP: - if (crypto_report_kpp(skb, alg)) - goto nla_put_failure; - break; - } - -out: - return 0; - -nla_put_failure: - return -EMSGSIZE; -} - -static int crypto_report_alg(struct crypto_alg *alg, - struct crypto_dump_info *info) -{ - struct sk_buff *in_skb = info->in_skb; - struct sk_buff *skb = info->out_skb; - struct nlmsghdr *nlh; - struct crypto_user_alg *ualg; - int err = 0; - - nlh = nlmsg_put(skb, NETLINK_CB(in_skb).portid, info->nlmsg_seq, - CRYPTO_MSG_GETALG, sizeof(*ualg), info->nlmsg_flags); - if (!nlh) { - err = -EMSGSIZE; - goto out; - } - - ualg = nlmsg_data(nlh); - - err = crypto_report_one(alg, ualg, skb); - if (err) { - nlmsg_cancel(skb, nlh); - goto out; - } - - nlmsg_end(skb, nlh); - -out: - return err; -} - -static int crypto_report(struct sk_buff *in_skb, struct nlmsghdr *in_nlh, - struct nlattr **attrs) -{ - struct crypto_user_alg *p = nlmsg_data(in_nlh); - struct crypto_alg *alg; - struct sk_buff *skb; - struct crypto_dump_info info; - int err; - - if (!null_terminated(p->cru_name) || !null_terminated(p->cru_driver_name)) - return -EINVAL; - - alg = crypto_alg_match(p, 0); - if (!alg) - return -ENOENT; - - err = -ENOMEM; - skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!skb) - goto drop_alg; - - info.in_skb = in_skb; - info.out_skb = skb; - info.nlmsg_seq = in_nlh->nlmsg_seq; - info.nlmsg_flags = 0; - - err = crypto_report_alg(alg, &info); - -drop_alg: - crypto_mod_put(alg); - - if (err) - return err; - - return nlmsg_unicast(crypto_nlsk, skb, NETLINK_CB(in_skb).portid); -} - -static int crypto_dump_report(struct sk_buff *skb, struct netlink_callback *cb) -{ - struct crypto_alg *alg; - struct crypto_dump_info info; - int err; - - if (cb->args[0]) - goto out; - - cb->args[0] = 1; - - info.in_skb = cb->skb; - info.out_skb = skb; - info.nlmsg_seq = cb->nlh->nlmsg_seq; - info.nlmsg_flags = NLM_F_MULTI; - - list_for_each_entry(alg, &crypto_alg_list, cra_list) { - err = crypto_report_alg(alg, &info); - if (err) - goto out_err; - } - -out: - return skb->len; -out_err: - return err; -} - -static int crypto_dump_report_done(struct netlink_callback *cb) -{ - return 0; -} - -static int crypto_update_alg(struct sk_buff *skb, struct nlmsghdr *nlh, - struct nlattr **attrs) -{ - struct crypto_alg *alg; - struct crypto_user_alg *p = nlmsg_data(nlh); - struct nlattr *priority = attrs[CRYPTOCFGA_PRIORITY_VAL]; - LIST_HEAD(list); - - if (!netlink_capable(skb, CAP_NET_ADMIN)) - return -EPERM; - - if (!null_terminated(p->cru_name) || !null_terminated(p->cru_driver_name)) - return -EINVAL; - - if (priority && !strlen(p->cru_driver_name)) - return -EINVAL; - - alg = crypto_alg_match(p, 1); - if (!alg) - return -ENOENT; - - down_write(&crypto_alg_sem); - - crypto_remove_spawns(alg, &list, NULL); - - if (priority) - alg->cra_priority = nla_get_u32(priority); - - up_write(&crypto_alg_sem); - - crypto_mod_put(alg); - crypto_remove_final(&list); - - return 0; -} - -static int crypto_del_alg(struct sk_buff *skb, struct nlmsghdr *nlh, - struct nlattr **attrs) -{ - struct crypto_alg *alg; - struct crypto_user_alg *p = nlmsg_data(nlh); - int err; - - if (!netlink_capable(skb, CAP_NET_ADMIN)) - return -EPERM; - - if (!null_terminated(p->cru_name) || !null_terminated(p->cru_driver_name)) - return -EINVAL; - - alg = crypto_alg_match(p, 1); - if (!alg) - return -ENOENT; - - /* We can not unregister core algorithms such as aes-generic. - * We would loose the reference in the crypto_alg_list to this algorithm - * if we try to unregister. Unregistering such an algorithm without - * removing the module is not possible, so we restrict to crypto - * instances that are build from templates. */ - err = -EINVAL; - if (!(alg->cra_flags & CRYPTO_ALG_INSTANCE)) - goto drop_alg; - - err = -EBUSY; - if (refcount_read(&alg->cra_refcnt) > 2) - goto drop_alg; - - err = crypto_unregister_instance((struct crypto_instance *)alg); - -drop_alg: - crypto_mod_put(alg); - return err; -} - -static int crypto_add_alg(struct sk_buff *skb, struct nlmsghdr *nlh, - struct nlattr **attrs) -{ - int exact = 0; - const char *name; - struct crypto_alg *alg; - struct crypto_user_alg *p = nlmsg_data(nlh); - struct nlattr *priority = attrs[CRYPTOCFGA_PRIORITY_VAL]; - - if (!netlink_capable(skb, CAP_NET_ADMIN)) - return -EPERM; - - if (!null_terminated(p->cru_name) || !null_terminated(p->cru_driver_name)) - return -EINVAL; - - if (strlen(p->cru_driver_name)) - exact = 1; - - if (priority && !exact) - return -EINVAL; - - alg = crypto_alg_match(p, exact); - if (alg) { - crypto_mod_put(alg); - return -EEXIST; - } - - if (strlen(p->cru_driver_name)) - name = p->cru_driver_name; - else - name = p->cru_name; - - alg = crypto_alg_mod_lookup(name, p->cru_type, p->cru_mask); - if (IS_ERR(alg)) - return PTR_ERR(alg); - - down_write(&crypto_alg_sem); - - if (priority) - alg->cra_priority = nla_get_u32(priority); - - up_write(&crypto_alg_sem); - - crypto_mod_put(alg); - - return 0; -} - -static int crypto_del_rng(struct sk_buff *skb, struct nlmsghdr *nlh, - struct nlattr **attrs) -{ - if (!netlink_capable(skb, CAP_NET_ADMIN)) - return -EPERM; - return crypto_del_default_rng(); -} - -#define MSGSIZE(type) sizeof(struct type) - -static const int crypto_msg_min[CRYPTO_NR_MSGTYPES] = { - [CRYPTO_MSG_NEWALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), - [CRYPTO_MSG_DELALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), - [CRYPTO_MSG_UPDATEALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), - [CRYPTO_MSG_GETALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), - [CRYPTO_MSG_DELRNG - CRYPTO_MSG_BASE] = 0, -}; - -static const struct nla_policy crypto_policy[CRYPTOCFGA_MAX+1] = { - [CRYPTOCFGA_PRIORITY_VAL] = { .type = NLA_U32}, -}; - -#undef MSGSIZE - -static const struct crypto_link { - int (*doit)(struct sk_buff *, struct nlmsghdr *, struct nlattr **); - int (*dump)(struct sk_buff *, struct netlink_callback *); - int (*done)(struct netlink_callback *); -} crypto_dispatch[CRYPTO_NR_MSGTYPES] = { - [CRYPTO_MSG_NEWALG - CRYPTO_MSG_BASE] = { .doit = crypto_add_alg}, - [CRYPTO_MSG_DELALG - CRYPTO_MSG_BASE] = { .doit = crypto_del_alg}, - [CRYPTO_MSG_UPDATEALG - CRYPTO_MSG_BASE] = { .doit = crypto_update_alg}, - [CRYPTO_MSG_GETALG - CRYPTO_MSG_BASE] = { .doit = crypto_report, - .dump = crypto_dump_report, - .done = crypto_dump_report_done}, - [CRYPTO_MSG_DELRNG - CRYPTO_MSG_BASE] = { .doit = crypto_del_rng }, -}; - -static int crypto_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, - struct netlink_ext_ack *extack) -{ - struct nlattr *attrs[CRYPTOCFGA_MAX+1]; - const struct crypto_link *link; - int type, err; - - type = nlh->nlmsg_type; - if (type > CRYPTO_MSG_MAX) - return -EINVAL; - - type -= CRYPTO_MSG_BASE; - link = &crypto_dispatch[type]; - - if ((type == (CRYPTO_MSG_GETALG - CRYPTO_MSG_BASE) && - (nlh->nlmsg_flags & NLM_F_DUMP))) { - struct crypto_alg *alg; - u16 dump_alloc = 0; - - if (link->dump == NULL) - return -EINVAL; - - down_read(&crypto_alg_sem); - list_for_each_entry(alg, &crypto_alg_list, cra_list) - dump_alloc += CRYPTO_REPORT_MAXSIZE; - - { - struct netlink_dump_control c = { - .dump = link->dump, - .done = link->done, - .min_dump_alloc = dump_alloc, - }; - err = netlink_dump_start(crypto_nlsk, skb, nlh, &c); - } - up_read(&crypto_alg_sem); - - return err; - } - - err = nlmsg_parse(nlh, crypto_msg_min[type], attrs, CRYPTOCFGA_MAX, - crypto_policy, extack); - if (err < 0) - return err; - - if (link->doit == NULL) - return -EINVAL; - - return link->doit(skb, nlh, attrs); -} - -static void crypto_netlink_rcv(struct sk_buff *skb) -{ - mutex_lock(&crypto_cfg_mutex); - netlink_rcv_skb(skb, &crypto_user_rcv_msg); - mutex_unlock(&crypto_cfg_mutex); -} - -static int __init crypto_user_init(void) -{ - struct netlink_kernel_cfg cfg = { - .input = crypto_netlink_rcv, - }; - - crypto_nlsk = netlink_kernel_create(&init_net, NETLINK_CRYPTO, &cfg); - if (!crypto_nlsk) - return -ENOMEM; - - return 0; -} - -static void __exit crypto_user_exit(void) -{ - netlink_kernel_release(crypto_nlsk); -} - -module_init(crypto_user_init); -module_exit(crypto_user_exit); -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Steffen Klassert "); -MODULE_DESCRIPTION("Crypto userspace configuration API"); -MODULE_ALIAS("net-pf-16-proto-21"); diff --git a/crypto/crypto_user_base.c b/crypto/crypto_user_base.c new file mode 100644 index 000000000000..e41f6cc33fff --- /dev/null +++ b/crypto/crypto_user_base.c @@ -0,0 +1,571 @@ +/* + * Crypto user configuration API. + * + * Copyright (C) 2011 secunet Security Networks AG + * Copyright (C) 2011 Steffen Klassert + * + * 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, write to the Free Software Foundation, Inc., + * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "internal.h" + +#define null_terminated(x) (strnlen(x, sizeof(x)) < sizeof(x)) + +static DEFINE_MUTEX(crypto_cfg_mutex); + +/* The crypto netlink socket */ +struct sock *crypto_nlsk; + +struct crypto_dump_info { + struct sk_buff *in_skb; + struct sk_buff *out_skb; + u32 nlmsg_seq; + u16 nlmsg_flags; +}; + +struct crypto_alg *crypto_alg_match(struct crypto_user_alg *p, int exact) +{ + struct crypto_alg *q, *alg = NULL; + + down_read(&crypto_alg_sem); + + list_for_each_entry(q, &crypto_alg_list, cra_list) { + int match = 0; + + if ((q->cra_flags ^ p->cru_type) & p->cru_mask) + continue; + + if (strlen(p->cru_driver_name)) + match = !strcmp(q->cra_driver_name, + p->cru_driver_name); + else if (!exact) + match = !strcmp(q->cra_name, p->cru_name); + + if (!match) + continue; + + if (unlikely(!crypto_mod_get(q))) + continue; + + alg = q; + break; + } + + up_read(&crypto_alg_sem); + + return alg; +} + +static int crypto_report_cipher(struct sk_buff *skb, struct crypto_alg *alg) +{ + struct crypto_report_cipher rcipher; + + strlcpy(rcipher.type, "cipher", sizeof(rcipher.type)); + + rcipher.blocksize = alg->cra_blocksize; + rcipher.min_keysize = alg->cra_cipher.cia_min_keysize; + rcipher.max_keysize = alg->cra_cipher.cia_max_keysize; + + if (nla_put(skb, CRYPTOCFGA_REPORT_CIPHER, + sizeof(struct crypto_report_cipher), &rcipher)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static int crypto_report_comp(struct sk_buff *skb, struct crypto_alg *alg) +{ + struct crypto_report_comp rcomp; + + strlcpy(rcomp.type, "compression", sizeof(rcomp.type)); + if (nla_put(skb, CRYPTOCFGA_REPORT_COMPRESS, + sizeof(struct crypto_report_comp), &rcomp)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static int crypto_report_acomp(struct sk_buff *skb, struct crypto_alg *alg) +{ + struct crypto_report_acomp racomp; + + strlcpy(racomp.type, "acomp", sizeof(racomp.type)); + + if (nla_put(skb, CRYPTOCFGA_REPORT_ACOMP, + sizeof(struct crypto_report_acomp), &racomp)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static int crypto_report_akcipher(struct sk_buff *skb, struct crypto_alg *alg) +{ + struct crypto_report_akcipher rakcipher; + + strlcpy(rakcipher.type, "akcipher", sizeof(rakcipher.type)); + + if (nla_put(skb, CRYPTOCFGA_REPORT_AKCIPHER, + sizeof(struct crypto_report_akcipher), &rakcipher)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static int crypto_report_kpp(struct sk_buff *skb, struct crypto_alg *alg) +{ + struct crypto_report_kpp rkpp; + + strlcpy(rkpp.type, "kpp", sizeof(rkpp.type)); + + if (nla_put(skb, CRYPTOCFGA_REPORT_KPP, + sizeof(struct crypto_report_kpp), &rkpp)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static int crypto_report_one(struct crypto_alg *alg, + struct crypto_user_alg *ualg, struct sk_buff *skb) +{ + strlcpy(ualg->cru_name, alg->cra_name, sizeof(ualg->cru_name)); + strlcpy(ualg->cru_driver_name, alg->cra_driver_name, + sizeof(ualg->cru_driver_name)); + strlcpy(ualg->cru_module_name, module_name(alg->cra_module), + sizeof(ualg->cru_module_name)); + + ualg->cru_type = 0; + ualg->cru_mask = 0; + ualg->cru_flags = alg->cra_flags; + ualg->cru_refcnt = refcount_read(&alg->cra_refcnt); + + if (nla_put_u32(skb, CRYPTOCFGA_PRIORITY_VAL, alg->cra_priority)) + goto nla_put_failure; + if (alg->cra_flags & CRYPTO_ALG_LARVAL) { + struct crypto_report_larval rl; + + strlcpy(rl.type, "larval", sizeof(rl.type)); + if (nla_put(skb, CRYPTOCFGA_REPORT_LARVAL, + sizeof(struct crypto_report_larval), &rl)) + goto nla_put_failure; + goto out; + } + + if (alg->cra_type && alg->cra_type->report) { + if (alg->cra_type->report(skb, alg)) + goto nla_put_failure; + + goto out; + } + + switch (alg->cra_flags & (CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_LARVAL)) { + case CRYPTO_ALG_TYPE_CIPHER: + if (crypto_report_cipher(skb, alg)) + goto nla_put_failure; + + break; + case CRYPTO_ALG_TYPE_COMPRESS: + if (crypto_report_comp(skb, alg)) + goto nla_put_failure; + + break; + case CRYPTO_ALG_TYPE_ACOMPRESS: + if (crypto_report_acomp(skb, alg)) + goto nla_put_failure; + + break; + case CRYPTO_ALG_TYPE_AKCIPHER: + if (crypto_report_akcipher(skb, alg)) + goto nla_put_failure; + + break; + case CRYPTO_ALG_TYPE_KPP: + if (crypto_report_kpp(skb, alg)) + goto nla_put_failure; + break; + } + +out: + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static int crypto_report_alg(struct crypto_alg *alg, + struct crypto_dump_info *info) +{ + struct sk_buff *in_skb = info->in_skb; + struct sk_buff *skb = info->out_skb; + struct nlmsghdr *nlh; + struct crypto_user_alg *ualg; + int err = 0; + + nlh = nlmsg_put(skb, NETLINK_CB(in_skb).portid, info->nlmsg_seq, + CRYPTO_MSG_GETALG, sizeof(*ualg), info->nlmsg_flags); + if (!nlh) { + err = -EMSGSIZE; + goto out; + } + + ualg = nlmsg_data(nlh); + + err = crypto_report_one(alg, ualg, skb); + if (err) { + nlmsg_cancel(skb, nlh); + goto out; + } + + nlmsg_end(skb, nlh); + +out: + return err; +} + +static int crypto_report(struct sk_buff *in_skb, struct nlmsghdr *in_nlh, + struct nlattr **attrs) +{ + struct crypto_user_alg *p = nlmsg_data(in_nlh); + struct crypto_alg *alg; + struct sk_buff *skb; + struct crypto_dump_info info; + int err; + + if (!null_terminated(p->cru_name) || !null_terminated(p->cru_driver_name)) + return -EINVAL; + + alg = crypto_alg_match(p, 0); + if (!alg) + return -ENOENT; + + err = -ENOMEM; + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!skb) + goto drop_alg; + + info.in_skb = in_skb; + info.out_skb = skb; + info.nlmsg_seq = in_nlh->nlmsg_seq; + info.nlmsg_flags = 0; + + err = crypto_report_alg(alg, &info); + +drop_alg: + crypto_mod_put(alg); + + if (err) + return err; + + return nlmsg_unicast(crypto_nlsk, skb, NETLINK_CB(in_skb).portid); +} + +static int crypto_dump_report(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct crypto_alg *alg; + struct crypto_dump_info info; + int err; + + if (cb->args[0]) + goto out; + + cb->args[0] = 1; + + info.in_skb = cb->skb; + info.out_skb = skb; + info.nlmsg_seq = cb->nlh->nlmsg_seq; + info.nlmsg_flags = NLM_F_MULTI; + + list_for_each_entry(alg, &crypto_alg_list, cra_list) { + err = crypto_report_alg(alg, &info); + if (err) + goto out_err; + } + +out: + return skb->len; +out_err: + return err; +} + +static int crypto_dump_report_done(struct netlink_callback *cb) +{ + return 0; +} + +static int crypto_update_alg(struct sk_buff *skb, struct nlmsghdr *nlh, + struct nlattr **attrs) +{ + struct crypto_alg *alg; + struct crypto_user_alg *p = nlmsg_data(nlh); + struct nlattr *priority = attrs[CRYPTOCFGA_PRIORITY_VAL]; + LIST_HEAD(list); + + if (!netlink_capable(skb, CAP_NET_ADMIN)) + return -EPERM; + + if (!null_terminated(p->cru_name) || !null_terminated(p->cru_driver_name)) + return -EINVAL; + + if (priority && !strlen(p->cru_driver_name)) + return -EINVAL; + + alg = crypto_alg_match(p, 1); + if (!alg) + return -ENOENT; + + down_write(&crypto_alg_sem); + + crypto_remove_spawns(alg, &list, NULL); + + if (priority) + alg->cra_priority = nla_get_u32(priority); + + up_write(&crypto_alg_sem); + + crypto_mod_put(alg); + crypto_remove_final(&list); + + return 0; +} + +static int crypto_del_alg(struct sk_buff *skb, struct nlmsghdr *nlh, + struct nlattr **attrs) +{ + struct crypto_alg *alg; + struct crypto_user_alg *p = nlmsg_data(nlh); + int err; + + if (!netlink_capable(skb, CAP_NET_ADMIN)) + return -EPERM; + + if (!null_terminated(p->cru_name) || !null_terminated(p->cru_driver_name)) + return -EINVAL; + + alg = crypto_alg_match(p, 1); + if (!alg) + return -ENOENT; + + /* We can not unregister core algorithms such as aes-generic. + * We would loose the reference in the crypto_alg_list to this algorithm + * if we try to unregister. Unregistering such an algorithm without + * removing the module is not possible, so we restrict to crypto + * instances that are build from templates. */ + err = -EINVAL; + if (!(alg->cra_flags & CRYPTO_ALG_INSTANCE)) + goto drop_alg; + + err = -EBUSY; + if (refcount_read(&alg->cra_refcnt) > 2) + goto drop_alg; + + err = crypto_unregister_instance((struct crypto_instance *)alg); + +drop_alg: + crypto_mod_put(alg); + return err; +} + +static int crypto_add_alg(struct sk_buff *skb, struct nlmsghdr *nlh, + struct nlattr **attrs) +{ + int exact = 0; + const char *name; + struct crypto_alg *alg; + struct crypto_user_alg *p = nlmsg_data(nlh); + struct nlattr *priority = attrs[CRYPTOCFGA_PRIORITY_VAL]; + + if (!netlink_capable(skb, CAP_NET_ADMIN)) + return -EPERM; + + if (!null_terminated(p->cru_name) || !null_terminated(p->cru_driver_name)) + return -EINVAL; + + if (strlen(p->cru_driver_name)) + exact = 1; + + if (priority && !exact) + return -EINVAL; + + alg = crypto_alg_match(p, exact); + if (alg) { + crypto_mod_put(alg); + return -EEXIST; + } + + if (strlen(p->cru_driver_name)) + name = p->cru_driver_name; + else + name = p->cru_name; + + alg = crypto_alg_mod_lookup(name, p->cru_type, p->cru_mask); + if (IS_ERR(alg)) + return PTR_ERR(alg); + + down_write(&crypto_alg_sem); + + if (priority) + alg->cra_priority = nla_get_u32(priority); + + up_write(&crypto_alg_sem); + + crypto_mod_put(alg); + + return 0; +} + +static int crypto_del_rng(struct sk_buff *skb, struct nlmsghdr *nlh, + struct nlattr **attrs) +{ + if (!netlink_capable(skb, CAP_NET_ADMIN)) + return -EPERM; + return crypto_del_default_rng(); +} + +#define MSGSIZE(type) sizeof(struct type) + +static const int crypto_msg_min[CRYPTO_NR_MSGTYPES] = { + [CRYPTO_MSG_NEWALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), + [CRYPTO_MSG_DELALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), + [CRYPTO_MSG_UPDATEALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), + [CRYPTO_MSG_GETALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), + [CRYPTO_MSG_DELRNG - CRYPTO_MSG_BASE] = 0, + [CRYPTO_MSG_GETSTAT - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), +}; + +static const struct nla_policy crypto_policy[CRYPTOCFGA_MAX+1] = { + [CRYPTOCFGA_PRIORITY_VAL] = { .type = NLA_U32}, +}; + +#undef MSGSIZE + +static const struct crypto_link { + int (*doit)(struct sk_buff *, struct nlmsghdr *, struct nlattr **); + int (*dump)(struct sk_buff *, struct netlink_callback *); + int (*done)(struct netlink_callback *); +} crypto_dispatch[CRYPTO_NR_MSGTYPES] = { + [CRYPTO_MSG_NEWALG - CRYPTO_MSG_BASE] = { .doit = crypto_add_alg}, + [CRYPTO_MSG_DELALG - CRYPTO_MSG_BASE] = { .doit = crypto_del_alg}, + [CRYPTO_MSG_UPDATEALG - CRYPTO_MSG_BASE] = { .doit = crypto_update_alg}, + [CRYPTO_MSG_GETALG - CRYPTO_MSG_BASE] = { .doit = crypto_report, + .dump = crypto_dump_report, + .done = crypto_dump_report_done}, + [CRYPTO_MSG_DELRNG - CRYPTO_MSG_BASE] = { .doit = crypto_del_rng }, + [CRYPTO_MSG_GETSTAT - CRYPTO_MSG_BASE] = { .doit = crypto_reportstat, + .dump = crypto_dump_reportstat, + .done = crypto_dump_reportstat_done}, +}; + +static int crypto_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct nlattr *attrs[CRYPTOCFGA_MAX+1]; + const struct crypto_link *link; + int type, err; + + type = nlh->nlmsg_type; + if (type > CRYPTO_MSG_MAX) + return -EINVAL; + + type -= CRYPTO_MSG_BASE; + link = &crypto_dispatch[type]; + + if ((type == (CRYPTO_MSG_GETALG - CRYPTO_MSG_BASE) && + (nlh->nlmsg_flags & NLM_F_DUMP))) { + struct crypto_alg *alg; + u16 dump_alloc = 0; + + if (link->dump == NULL) + return -EINVAL; + + down_read(&crypto_alg_sem); + list_for_each_entry(alg, &crypto_alg_list, cra_list) + dump_alloc += CRYPTO_REPORT_MAXSIZE; + + { + struct netlink_dump_control c = { + .dump = link->dump, + .done = link->done, + .min_dump_alloc = dump_alloc, + }; + err = netlink_dump_start(crypto_nlsk, skb, nlh, &c); + } + up_read(&crypto_alg_sem); + + return err; + } + + err = nlmsg_parse(nlh, crypto_msg_min[type], attrs, CRYPTOCFGA_MAX, + crypto_policy, extack); + if (err < 0) + return err; + + if (link->doit == NULL) + return -EINVAL; + + return link->doit(skb, nlh, attrs); +} + +static void crypto_netlink_rcv(struct sk_buff *skb) +{ + mutex_lock(&crypto_cfg_mutex); + netlink_rcv_skb(skb, &crypto_user_rcv_msg); + mutex_unlock(&crypto_cfg_mutex); +} + +static int __init crypto_user_init(void) +{ + struct netlink_kernel_cfg cfg = { + .input = crypto_netlink_rcv, + }; + + crypto_nlsk = netlink_kernel_create(&init_net, NETLINK_CRYPTO, &cfg); + if (!crypto_nlsk) + return -ENOMEM; + + return 0; +} + +static void __exit crypto_user_exit(void) +{ + netlink_kernel_release(crypto_nlsk); +} + +module_init(crypto_user_init); +module_exit(crypto_user_exit); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Steffen Klassert "); +MODULE_DESCRIPTION("Crypto userspace configuration API"); +MODULE_ALIAS("net-pf-16-proto-21"); diff --git a/crypto/crypto_user_stat.c b/crypto/crypto_user_stat.c new file mode 100644 index 000000000000..021ad06bbb62 --- /dev/null +++ b/crypto/crypto_user_stat.c @@ -0,0 +1,463 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Crypto user configuration API. + * + * Copyright (C) 2017-2018 Corentin Labbe + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "internal.h" + +#define null_terminated(x) (strnlen(x, sizeof(x)) < sizeof(x)) + +static DEFINE_MUTEX(crypto_cfg_mutex); + +extern struct sock *crypto_nlsk; + +struct crypto_dump_info { + struct sk_buff *in_skb; + struct sk_buff *out_skb; + u32 nlmsg_seq; + u16 nlmsg_flags; +}; + +static int crypto_report_aead(struct sk_buff *skb, struct crypto_alg *alg) +{ + struct crypto_stat raead; + u64 v64; + u32 v32; + + strncpy(raead.type, "aead", sizeof(raead.type)); + + v32 = atomic_read(&alg->encrypt_cnt); + raead.stat_encrypt_cnt = v32; + v64 = atomic64_read(&alg->encrypt_tlen); + raead.stat_encrypt_tlen = v64; + v32 = atomic_read(&alg->decrypt_cnt); + raead.stat_decrypt_cnt = v32; + v64 = atomic64_read(&alg->decrypt_tlen); + raead.stat_decrypt_tlen = v64; + v32 = atomic_read(&alg->aead_err_cnt); + raead.stat_aead_err_cnt = v32; + + if (nla_put(skb, CRYPTOCFGA_STAT_AEAD, + sizeof(struct crypto_stat), &raead)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static int crypto_report_cipher(struct sk_buff *skb, struct crypto_alg *alg) +{ + struct crypto_stat rcipher; + u64 v64; + u32 v32; + + strlcpy(rcipher.type, "cipher", sizeof(rcipher.type)); + + v32 = atomic_read(&alg->encrypt_cnt); + rcipher.stat_encrypt_cnt = v32; + v64 = atomic64_read(&alg->encrypt_tlen); + rcipher.stat_encrypt_tlen = v64; + v32 = atomic_read(&alg->decrypt_cnt); + rcipher.stat_decrypt_cnt = v32; + v64 = atomic64_read(&alg->decrypt_tlen); + rcipher.stat_decrypt_tlen = v64; + v32 = atomic_read(&alg->cipher_err_cnt); + rcipher.stat_cipher_err_cnt = v32; + + if (nla_put(skb, CRYPTOCFGA_STAT_CIPHER, + sizeof(struct crypto_stat), &rcipher)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static int crypto_report_comp(struct sk_buff *skb, struct crypto_alg *alg) +{ + struct crypto_stat rcomp; + u64 v64; + u32 v32; + + strlcpy(rcomp.type, "compression", sizeof(rcomp.type)); + v32 = atomic_read(&alg->compress_cnt); + rcomp.stat_compress_cnt = v32; + v64 = atomic64_read(&alg->compress_tlen); + rcomp.stat_compress_tlen = v64; + v32 = atomic_read(&alg->decompress_cnt); + rcomp.stat_decompress_cnt = v32; + v64 = atomic64_read(&alg->decompress_tlen); + rcomp.stat_decompress_tlen = v64; + v32 = atomic_read(&alg->cipher_err_cnt); + rcomp.stat_compress_err_cnt = v32; + + if (nla_put(skb, CRYPTOCFGA_STAT_COMPRESS, + sizeof(struct crypto_stat), &rcomp)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static int crypto_report_acomp(struct sk_buff *skb, struct crypto_alg *alg) +{ + struct crypto_stat racomp; + u64 v64; + u32 v32; + + strlcpy(racomp.type, "acomp", sizeof(racomp.type)); + v32 = atomic_read(&alg->compress_cnt); + racomp.stat_compress_cnt = v32; + v64 = atomic64_read(&alg->compress_tlen); + racomp.stat_compress_tlen = v64; + v32 = atomic_read(&alg->decompress_cnt); + racomp.stat_decompress_cnt = v32; + v64 = atomic64_read(&alg->decompress_tlen); + racomp.stat_decompress_tlen = v64; + v32 = atomic_read(&alg->cipher_err_cnt); + racomp.stat_compress_err_cnt = v32; + + if (nla_put(skb, CRYPTOCFGA_STAT_ACOMP, + sizeof(struct crypto_stat), &racomp)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static int crypto_report_akcipher(struct sk_buff *skb, struct crypto_alg *alg) +{ + struct crypto_stat rakcipher; + u64 v64; + u32 v32; + + strncpy(rakcipher.type, "akcipher", sizeof(rakcipher.type)); + v32 = atomic_read(&alg->encrypt_cnt); + rakcipher.stat_encrypt_cnt = v32; + v64 = atomic64_read(&alg->encrypt_tlen); + rakcipher.stat_encrypt_tlen = v64; + v32 = atomic_read(&alg->decrypt_cnt); + rakcipher.stat_decrypt_cnt = v32; + v64 = atomic64_read(&alg->decrypt_tlen); + rakcipher.stat_decrypt_tlen = v64; + v32 = atomic_read(&alg->sign_cnt); + rakcipher.stat_sign_cnt = v32; + v32 = atomic_read(&alg->verify_cnt); + rakcipher.stat_verify_cnt = v32; + v32 = atomic_read(&alg->akcipher_err_cnt); + rakcipher.stat_akcipher_err_cnt = v32; + + if (nla_put(skb, CRYPTOCFGA_STAT_AKCIPHER, + sizeof(struct crypto_stat), &rakcipher)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static int crypto_report_kpp(struct sk_buff *skb, struct crypto_alg *alg) +{ + struct crypto_stat rkpp; + u32 v; + + strlcpy(rkpp.type, "kpp", sizeof(rkpp.type)); + + v = atomic_read(&alg->setsecret_cnt); + rkpp.stat_setsecret_cnt = v; + v = atomic_read(&alg->generate_public_key_cnt); + rkpp.stat_generate_public_key_cnt = v; + v = atomic_read(&alg->compute_shared_secret_cnt); + rkpp.stat_compute_shared_secret_cnt = v; + v = atomic_read(&alg->kpp_err_cnt); + rkpp.stat_kpp_err_cnt = v; + + if (nla_put(skb, CRYPTOCFGA_STAT_KPP, + sizeof(struct crypto_stat), &rkpp)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static int crypto_report_ahash(struct sk_buff *skb, struct crypto_alg *alg) +{ + struct crypto_stat rhash; + u64 v64; + u32 v32; + + strncpy(rhash.type, "ahash", sizeof(rhash.type)); + + v32 = atomic_read(&alg->hash_cnt); + rhash.stat_hash_cnt = v32; + v64 = atomic64_read(&alg->hash_tlen); + rhash.stat_hash_tlen = v64; + v32 = atomic_read(&alg->hash_err_cnt); + rhash.stat_hash_err_cnt = v32; + + if (nla_put(skb, CRYPTOCFGA_STAT_HASH, + sizeof(struct crypto_stat), &rhash)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static int crypto_report_shash(struct sk_buff *skb, struct crypto_alg *alg) +{ + struct crypto_stat rhash; + u64 v64; + u32 v32; + + strncpy(rhash.type, "shash", sizeof(rhash.type)); + + v32 = atomic_read(&alg->hash_cnt); + rhash.stat_hash_cnt = v32; + v64 = atomic64_read(&alg->hash_tlen); + rhash.stat_hash_tlen = v64; + v32 = atomic_read(&alg->hash_err_cnt); + rhash.stat_hash_err_cnt = v32; + + if (nla_put(skb, CRYPTOCFGA_STAT_HASH, + sizeof(struct crypto_stat), &rhash)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static int crypto_report_rng(struct sk_buff *skb, struct crypto_alg *alg) +{ + struct crypto_stat rrng; + u64 v64; + u32 v32; + + strncpy(rrng.type, "rng", sizeof(rrng.type)); + + v32 = atomic_read(&alg->generate_cnt); + rrng.stat_generate_cnt = v32; + v64 = atomic64_read(&alg->generate_tlen); + rrng.stat_generate_tlen = v64; + v32 = atomic_read(&alg->seed_cnt); + rrng.stat_seed_cnt = v32; + v32 = atomic_read(&alg->hash_err_cnt); + rrng.stat_rng_err_cnt = v32; + + if (nla_put(skb, CRYPTOCFGA_STAT_RNG, + sizeof(struct crypto_stat), &rrng)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static int crypto_reportstat_one(struct crypto_alg *alg, + struct crypto_user_alg *ualg, + struct sk_buff *skb) +{ + strlcpy(ualg->cru_name, alg->cra_name, sizeof(ualg->cru_name)); + strlcpy(ualg->cru_driver_name, alg->cra_driver_name, + sizeof(ualg->cru_driver_name)); + strlcpy(ualg->cru_module_name, module_name(alg->cra_module), + sizeof(ualg->cru_module_name)); + + ualg->cru_type = 0; + ualg->cru_mask = 0; + ualg->cru_flags = alg->cra_flags; + ualg->cru_refcnt = refcount_read(&alg->cra_refcnt); + + if (nla_put_u32(skb, CRYPTOCFGA_PRIORITY_VAL, alg->cra_priority)) + goto nla_put_failure; + if (alg->cra_flags & CRYPTO_ALG_LARVAL) { + struct crypto_stat rl; + + strlcpy(rl.type, "larval", sizeof(rl.type)); + if (nla_put(skb, CRYPTOCFGA_STAT_LARVAL, + sizeof(struct crypto_stat), &rl)) + goto nla_put_failure; + goto out; + } + + switch (alg->cra_flags & (CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_LARVAL)) { + case CRYPTO_ALG_TYPE_AEAD: + if (crypto_report_aead(skb, alg)) + goto nla_put_failure; + break; + case CRYPTO_ALG_TYPE_SKCIPHER: + if (crypto_report_cipher(skb, alg)) + goto nla_put_failure; + break; + case CRYPTO_ALG_TYPE_BLKCIPHER: + if (crypto_report_cipher(skb, alg)) + goto nla_put_failure; + break; + case CRYPTO_ALG_TYPE_CIPHER: + if (crypto_report_cipher(skb, alg)) + goto nla_put_failure; + break; + case CRYPTO_ALG_TYPE_COMPRESS: + if (crypto_report_comp(skb, alg)) + goto nla_put_failure; + break; + case CRYPTO_ALG_TYPE_ACOMPRESS: + if (crypto_report_acomp(skb, alg)) + goto nla_put_failure; + break; + case CRYPTO_ALG_TYPE_SCOMPRESS: + if (crypto_report_acomp(skb, alg)) + goto nla_put_failure; + break; + case CRYPTO_ALG_TYPE_AKCIPHER: + if (crypto_report_akcipher(skb, alg)) + goto nla_put_failure; + break; + case CRYPTO_ALG_TYPE_KPP: + if (crypto_report_kpp(skb, alg)) + goto nla_put_failure; + break; + case CRYPTO_ALG_TYPE_AHASH: + if (crypto_report_ahash(skb, alg)) + goto nla_put_failure; + break; + case CRYPTO_ALG_TYPE_HASH: + if (crypto_report_shash(skb, alg)) + goto nla_put_failure; + break; + case CRYPTO_ALG_TYPE_RNG: + if (crypto_report_rng(skb, alg)) + goto nla_put_failure; + break; + default: + pr_err("ERROR: Unhandled alg %d in %s\n", + alg->cra_flags & (CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_LARVAL), + __func__); + } + +out: + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static int crypto_reportstat_alg(struct crypto_alg *alg, + struct crypto_dump_info *info) +{ + struct sk_buff *in_skb = info->in_skb; + struct sk_buff *skb = info->out_skb; + struct nlmsghdr *nlh; + struct crypto_user_alg *ualg; + int err = 0; + + nlh = nlmsg_put(skb, NETLINK_CB(in_skb).portid, info->nlmsg_seq, + CRYPTO_MSG_GETSTAT, sizeof(*ualg), info->nlmsg_flags); + if (!nlh) { + err = -EMSGSIZE; + goto out; + } + + ualg = nlmsg_data(nlh); + + err = crypto_reportstat_one(alg, ualg, skb); + if (err) { + nlmsg_cancel(skb, nlh); + goto out; + } + + nlmsg_end(skb, nlh); + +out: + return err; +} + +int crypto_reportstat(struct sk_buff *in_skb, struct nlmsghdr *in_nlh, + struct nlattr **attrs) +{ + struct crypto_user_alg *p = nlmsg_data(in_nlh); + struct crypto_alg *alg; + struct sk_buff *skb; + struct crypto_dump_info info; + int err; + + if (!null_terminated(p->cru_name) || !null_terminated(p->cru_driver_name)) + return -EINVAL; + + alg = crypto_alg_match(p, 0); + if (!alg) + return -ENOENT; + + err = -ENOMEM; + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); + if (!skb) + goto drop_alg; + + info.in_skb = in_skb; + info.out_skb = skb; + info.nlmsg_seq = in_nlh->nlmsg_seq; + info.nlmsg_flags = 0; + + err = crypto_reportstat_alg(alg, &info); + +drop_alg: + crypto_mod_put(alg); + + if (err) + return err; + + return nlmsg_unicast(crypto_nlsk, skb, NETLINK_CB(in_skb).portid); +} + +int crypto_dump_reportstat(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct crypto_alg *alg; + struct crypto_dump_info info; + int err; + + if (cb->args[0]) + goto out; + + cb->args[0] = 1; + + info.in_skb = cb->skb; + info.out_skb = skb; + info.nlmsg_seq = cb->nlh->nlmsg_seq; + info.nlmsg_flags = NLM_F_MULTI; + + list_for_each_entry(alg, &crypto_alg_list, cra_list) { + err = crypto_reportstat_alg(alg, &info); + if (err) + goto out_err; + } + +out: + return skb->len; +out_err: + return err; +} + +int crypto_dump_reportstat_done(struct netlink_callback *cb) +{ + return 0; +} + +MODULE_LICENSE("GPL"); diff --git a/crypto/rng.c b/crypto/rng.c index b4a618668161..547f16ecbfb0 100644 --- a/crypto/rng.c +++ b/crypto/rng.c @@ -50,6 +50,7 @@ int crypto_rng_reset(struct crypto_rng *tfm, const u8 *seed, unsigned int slen) } err = crypto_rng_alg(tfm)->seed(tfm, seed, slen); + crypto_stat_rng_seed(tfm, err); out: kzfree(buf); return err; diff --git a/include/crypto/acompress.h b/include/crypto/acompress.h index e328b52425a8..22e6f412c595 100644 --- a/include/crypto/acompress.h +++ b/include/crypto/acompress.h @@ -234,6 +234,34 @@ static inline void acomp_request_set_params(struct acomp_req *req, req->flags |= CRYPTO_ACOMP_ALLOC_OUTPUT; } +static inline void crypto_stat_compress(struct acomp_req *req, int ret) +{ +#ifdef CONFIG_CRYPTO_STATS + struct crypto_acomp *tfm = crypto_acomp_reqtfm(req); + + if (ret && ret != -EINPROGRESS && ret != -EBUSY) { + atomic_inc(&tfm->base.__crt_alg->compress_err_cnt); + } else { + atomic_inc(&tfm->base.__crt_alg->compress_cnt); + atomic64_add(req->slen, &tfm->base.__crt_alg->compress_tlen); + } +#endif +} + +static inline void crypto_stat_decompress(struct acomp_req *req, int ret) +{ +#ifdef CONFIG_CRYPTO_STATS + struct crypto_acomp *tfm = crypto_acomp_reqtfm(req); + + if (ret && ret != -EINPROGRESS && ret != -EBUSY) { + atomic_inc(&tfm->base.__crt_alg->compress_err_cnt); + } else { + atomic_inc(&tfm->base.__crt_alg->decompress_cnt); + atomic64_add(req->slen, &tfm->base.__crt_alg->decompress_tlen); + } +#endif +} + /** * crypto_acomp_compress() -- Invoke asynchronous compress operation * @@ -246,8 +274,11 @@ static inline void acomp_request_set_params(struct acomp_req *req, static inline int crypto_acomp_compress(struct acomp_req *req) { struct crypto_acomp *tfm = crypto_acomp_reqtfm(req); + int ret; - return tfm->compress(req); + ret = tfm->compress(req); + crypto_stat_compress(req, ret); + return ret; } /** @@ -262,8 +293,11 @@ static inline int crypto_acomp_compress(struct acomp_req *req) static inline int crypto_acomp_decompress(struct acomp_req *req) { struct crypto_acomp *tfm = crypto_acomp_reqtfm(req); + int ret; - return tfm->decompress(req); + ret = tfm->decompress(req); + crypto_stat_decompress(req, ret); + return ret; } #endif diff --git a/include/crypto/aead.h b/include/crypto/aead.h index 1e26f790b03f..0d765d7bfb82 100644 --- a/include/crypto/aead.h +++ b/include/crypto/aead.h @@ -306,6 +306,34 @@ static inline struct crypto_aead *crypto_aead_reqtfm(struct aead_request *req) return __crypto_aead_cast(req->base.tfm); } +static inline void crypto_stat_aead_encrypt(struct aead_request *req, int ret) +{ +#ifdef CONFIG_CRYPTO_STATS + struct crypto_aead *tfm = crypto_aead_reqtfm(req); + + if (ret && ret != -EINPROGRESS && ret != -EBUSY) { + atomic_inc(&tfm->base.__crt_alg->aead_err_cnt); + } else { + atomic_inc(&tfm->base.__crt_alg->encrypt_cnt); + atomic64_add(req->cryptlen, &tfm->base.__crt_alg->encrypt_tlen); + } +#endif +} + +static inline void crypto_stat_aead_decrypt(struct aead_request *req, int ret) +{ +#ifdef CONFIG_CRYPTO_STATS + struct crypto_aead *tfm = crypto_aead_reqtfm(req); + + if (ret && ret != -EINPROGRESS && ret != -EBUSY) { + atomic_inc(&tfm->base.__crt_alg->aead_err_cnt); + } else { + atomic_inc(&tfm->base.__crt_alg->decrypt_cnt); + atomic64_add(req->cryptlen, &tfm->base.__crt_alg->decrypt_tlen); + } +#endif +} + /** * crypto_aead_encrypt() - encrypt plaintext * @req: reference to the aead_request handle that holds all information @@ -328,11 +356,14 @@ static inline struct crypto_aead *crypto_aead_reqtfm(struct aead_request *req) static inline int crypto_aead_encrypt(struct aead_request *req) { struct crypto_aead *aead = crypto_aead_reqtfm(req); + int ret; if (crypto_aead_get_flags(aead) & CRYPTO_TFM_NEED_KEY) - return -ENOKEY; - - return crypto_aead_alg(aead)->encrypt(req); + ret = -ENOKEY; + else + ret = crypto_aead_alg(aead)->encrypt(req); + crypto_stat_aead_encrypt(req, ret); + return ret; } /** @@ -360,14 +391,16 @@ static inline int crypto_aead_encrypt(struct aead_request *req) static inline int crypto_aead_decrypt(struct aead_request *req) { struct crypto_aead *aead = crypto_aead_reqtfm(req); + int ret; if (crypto_aead_get_flags(aead) & CRYPTO_TFM_NEED_KEY) - return -ENOKEY; - - if (req->cryptlen < crypto_aead_authsize(aead)) - return -EINVAL; - - return crypto_aead_alg(aead)->decrypt(req); + ret = -ENOKEY; + else if (req->cryptlen < crypto_aead_authsize(aead)) + ret = -EINVAL; + else + ret = crypto_aead_alg(aead)->decrypt(req); + crypto_stat_aead_decrypt(req, ret); + return ret; } /** diff --git a/include/crypto/akcipher.h b/include/crypto/akcipher.h index b5e11de4d497..afac71119396 100644 --- a/include/crypto/akcipher.h +++ b/include/crypto/akcipher.h @@ -271,6 +271,62 @@ static inline unsigned int crypto_akcipher_maxsize(struct crypto_akcipher *tfm) return alg->max_size(tfm); } +static inline void crypto_stat_akcipher_encrypt(struct akcipher_request *req, + int ret) +{ +#ifdef CONFIG_CRYPTO_STATS + struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req); + + if (ret && ret != -EINPROGRESS && ret != -EBUSY) { + atomic_inc(&tfm->base.__crt_alg->akcipher_err_cnt); + } else { + atomic_inc(&tfm->base.__crt_alg->encrypt_cnt); + atomic64_add(req->src_len, &tfm->base.__crt_alg->encrypt_tlen); + } +#endif +} + +static inline void crypto_stat_akcipher_decrypt(struct akcipher_request *req, + int ret) +{ +#ifdef CONFIG_CRYPTO_STATS + struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req); + + if (ret && ret != -EINPROGRESS && ret != -EBUSY) { + atomic_inc(&tfm->base.__crt_alg->akcipher_err_cnt); + } else { + atomic_inc(&tfm->base.__crt_alg->decrypt_cnt); + atomic64_add(req->src_len, &tfm->base.__crt_alg->decrypt_tlen); + } +#endif +} + +static inline void crypto_stat_akcipher_sign(struct akcipher_request *req, + int ret) +{ +#ifdef CONFIG_CRYPTO_STATS + struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req); + + if (ret && ret != -EINPROGRESS && ret != -EBUSY) + atomic_inc(&tfm->base.__crt_alg->akcipher_err_cnt); + else + atomic_inc(&tfm->base.__crt_alg->sign_cnt); +#endif +} + +static inline void crypto_stat_akcipher_verify(struct akcipher_request *req, + int ret) +{ +#ifdef CONFIG_CRYPTO_STATS + struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req); + + if (ret && ret != -EINPROGRESS && ret != -EBUSY) + atomic_inc(&tfm->base.__crt_alg->akcipher_err_cnt); + else + atomic_inc(&tfm->base.__crt_alg->verify_cnt); +#endif +} + /** * crypto_akcipher_encrypt() - Invoke public key encrypt operation * @@ -285,8 +341,11 @@ static inline int crypto_akcipher_encrypt(struct akcipher_request *req) { struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req); struct akcipher_alg *alg = crypto_akcipher_alg(tfm); + int ret; - return alg->encrypt(req); + ret = alg->encrypt(req); + crypto_stat_akcipher_encrypt(req, ret); + return ret; } /** @@ -303,8 +362,11 @@ static inline int crypto_akcipher_decrypt(struct akcipher_request *req) { struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req); struct akcipher_alg *alg = crypto_akcipher_alg(tfm); + int ret; - return alg->decrypt(req); + ret = alg->decrypt(req); + crypto_stat_akcipher_decrypt(req, ret); + return ret; } /** @@ -321,8 +383,11 @@ static inline int crypto_akcipher_sign(struct akcipher_request *req) { struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req); struct akcipher_alg *alg = crypto_akcipher_alg(tfm); + int ret; - return alg->sign(req); + ret = alg->sign(req); + crypto_stat_akcipher_sign(req, ret); + return ret; } /** @@ -339,8 +404,11 @@ static inline int crypto_akcipher_verify(struct akcipher_request *req) { struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req); struct akcipher_alg *alg = crypto_akcipher_alg(tfm); + int ret; - return alg->verify(req); + ret = alg->verify(req); + crypto_stat_akcipher_verify(req, ret); + return ret; } /** diff --git a/include/crypto/hash.h b/include/crypto/hash.h index 21587011ab0f..bc7796600338 100644 --- a/include/crypto/hash.h +++ b/include/crypto/hash.h @@ -412,6 +412,32 @@ static inline void *ahash_request_ctx(struct ahash_request *req) int crypto_ahash_setkey(struct crypto_ahash *tfm, const u8 *key, unsigned int keylen); +static inline void crypto_stat_ahash_update(struct ahash_request *req, int ret) +{ +#ifdef CONFIG_CRYPTO_STATS + struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); + + if (ret && ret != -EINPROGRESS && ret != -EBUSY) + atomic_inc(&tfm->base.__crt_alg->hash_err_cnt); + else + atomic64_add(req->nbytes, &tfm->base.__crt_alg->hash_tlen); +#endif +} + +static inline void crypto_stat_ahash_final(struct ahash_request *req, int ret) +{ +#ifdef CONFIG_CRYPTO_STATS + struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); + + if (ret && ret != -EINPROGRESS && ret != -EBUSY) { + atomic_inc(&tfm->base.__crt_alg->hash_err_cnt); + } else { + atomic_inc(&tfm->base.__crt_alg->hash_cnt); + atomic64_add(req->nbytes, &tfm->base.__crt_alg->hash_tlen); + } +#endif +} + /** * crypto_ahash_finup() - update and finalize message digest * @req: reference to the ahash_request handle that holds all information @@ -526,7 +552,11 @@ static inline int crypto_ahash_init(struct ahash_request *req) */ static inline int crypto_ahash_update(struct ahash_request *req) { - return crypto_ahash_reqtfm(req)->update(req); + int ret; + + ret = crypto_ahash_reqtfm(req)->update(req); + crypto_stat_ahash_update(req, ret); + return ret; } /** diff --git a/include/crypto/internal/cryptouser.h b/include/crypto/internal/cryptouser.h new file mode 100644 index 000000000000..8db299c25566 --- /dev/null +++ b/include/crypto/internal/cryptouser.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include + +struct crypto_alg *crypto_alg_match(struct crypto_user_alg *p, int exact); + +int crypto_dump_reportstat(struct sk_buff *skb, struct netlink_callback *cb); +int crypto_reportstat(struct sk_buff *in_skb, struct nlmsghdr *in_nlh, struct nlattr **attrs); +int crypto_dump_reportstat_done(struct netlink_callback *cb); diff --git a/include/crypto/kpp.h b/include/crypto/kpp.h index 1bde0a6514fa..f517ba6d3a27 100644 --- a/include/crypto/kpp.h +++ b/include/crypto/kpp.h @@ -268,6 +268,42 @@ struct kpp_secret { unsigned short len; }; +static inline void crypto_stat_kpp_set_secret(struct crypto_kpp *tfm, int ret) +{ +#ifdef CONFIG_CRYPTO_STATS + if (ret) + atomic_inc(&tfm->base.__crt_alg->kpp_err_cnt); + else + atomic_inc(&tfm->base.__crt_alg->setsecret_cnt); +#endif +} + +static inline void crypto_stat_kpp_generate_public_key(struct kpp_request *req, + int ret) +{ +#ifdef CONFIG_CRYPTO_STATS + struct crypto_kpp *tfm = crypto_kpp_reqtfm(req); + + if (ret) + atomic_inc(&tfm->base.__crt_alg->kpp_err_cnt); + else + atomic_inc(&tfm->base.__crt_alg->generate_public_key_cnt); +#endif +} + +static inline void crypto_stat_kpp_compute_shared_secret(struct kpp_request *req, + int ret) +{ +#ifdef CONFIG_CRYPTO_STATS + struct crypto_kpp *tfm = crypto_kpp_reqtfm(req); + + if (ret) + atomic_inc(&tfm->base.__crt_alg->kpp_err_cnt); + else + atomic_inc(&tfm->base.__crt_alg->compute_shared_secret_cnt); +#endif +} + /** * crypto_kpp_set_secret() - Invoke kpp operation * @@ -287,8 +323,11 @@ static inline int crypto_kpp_set_secret(struct crypto_kpp *tfm, const void *buffer, unsigned int len) { struct kpp_alg *alg = crypto_kpp_alg(tfm); + int ret; - return alg->set_secret(tfm, buffer, len); + ret = alg->set_secret(tfm, buffer, len); + crypto_stat_kpp_set_secret(tfm, ret); + return ret; } /** @@ -308,8 +347,11 @@ static inline int crypto_kpp_generate_public_key(struct kpp_request *req) { struct crypto_kpp *tfm = crypto_kpp_reqtfm(req); struct kpp_alg *alg = crypto_kpp_alg(tfm); + int ret; - return alg->generate_public_key(req); + ret = alg->generate_public_key(req); + crypto_stat_kpp_generate_public_key(req, ret); + return ret; } /** @@ -326,8 +368,11 @@ static inline int crypto_kpp_compute_shared_secret(struct kpp_request *req) { struct crypto_kpp *tfm = crypto_kpp_reqtfm(req); struct kpp_alg *alg = crypto_kpp_alg(tfm); + int ret; - return alg->compute_shared_secret(req); + ret = alg->compute_shared_secret(req); + crypto_stat_kpp_compute_shared_secret(req, ret); + return ret; } /** diff --git a/include/crypto/rng.h b/include/crypto/rng.h index b95ede354a66..6d258f5b68f1 100644 --- a/include/crypto/rng.h +++ b/include/crypto/rng.h @@ -122,6 +122,29 @@ static inline void crypto_free_rng(struct crypto_rng *tfm) crypto_destroy_tfm(tfm, crypto_rng_tfm(tfm)); } +static inline void crypto_stat_rng_seed(struct crypto_rng *tfm, int ret) +{ +#ifdef CONFIG_CRYPTO_STATS + if (ret && ret != -EINPROGRESS && ret != -EBUSY) + atomic_inc(&tfm->base.__crt_alg->rng_err_cnt); + else + atomic_inc(&tfm->base.__crt_alg->seed_cnt); +#endif +} + +static inline void crypto_stat_rng_generate(struct crypto_rng *tfm, + unsigned int dlen, int ret) +{ +#ifdef CONFIG_CRYPTO_STATS + if (ret && ret != -EINPROGRESS && ret != -EBUSY) { + atomic_inc(&tfm->base.__crt_alg->rng_err_cnt); + } else { + atomic_inc(&tfm->base.__crt_alg->generate_cnt); + atomic64_add(dlen, &tfm->base.__crt_alg->generate_tlen); + } +#endif +} + /** * crypto_rng_generate() - get random number * @tfm: cipher handle @@ -140,7 +163,11 @@ static inline int crypto_rng_generate(struct crypto_rng *tfm, const u8 *src, unsigned int slen, u8 *dst, unsigned int dlen) { - return crypto_rng_alg(tfm)->generate(tfm, src, slen, dst, dlen); + int ret; + + ret = crypto_rng_alg(tfm)->generate(tfm, src, slen, dst, dlen); + crypto_stat_rng_generate(tfm, dlen, ret); + return ret; } /** diff --git a/include/crypto/skcipher.h b/include/crypto/skcipher.h index 45ae894fda32..925f547cdcfa 100644 --- a/include/crypto/skcipher.h +++ b/include/crypto/skcipher.h @@ -486,6 +486,32 @@ static inline struct crypto_sync_skcipher *crypto_sync_skcipher_reqtfm( return container_of(tfm, struct crypto_sync_skcipher, base); } +static inline void crypto_stat_skcipher_encrypt(struct skcipher_request *req, + int ret, struct crypto_alg *alg) +{ +#ifdef CONFIG_CRYPTO_STATS + if (ret && ret != -EINPROGRESS && ret != -EBUSY) { + atomic_inc(&alg->cipher_err_cnt); + } else { + atomic_inc(&alg->encrypt_cnt); + atomic64_add(req->cryptlen, &alg->encrypt_tlen); + } +#endif +} + +static inline void crypto_stat_skcipher_decrypt(struct skcipher_request *req, + int ret, struct crypto_alg *alg) +{ +#ifdef CONFIG_CRYPTO_STATS + if (ret && ret != -EINPROGRESS && ret != -EBUSY) { + atomic_inc(&alg->cipher_err_cnt); + } else { + atomic_inc(&alg->decrypt_cnt); + atomic64_add(req->cryptlen, &alg->decrypt_tlen); + } +#endif +} + /** * crypto_skcipher_encrypt() - encrypt plaintext * @req: reference to the skcipher_request handle that holds all information @@ -500,11 +526,14 @@ static inline struct crypto_sync_skcipher *crypto_sync_skcipher_reqtfm( static inline int crypto_skcipher_encrypt(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + int ret; if (crypto_skcipher_get_flags(tfm) & CRYPTO_TFM_NEED_KEY) - return -ENOKEY; - - return tfm->encrypt(req); + ret = -ENOKEY; + else + ret = tfm->encrypt(req); + crypto_stat_skcipher_encrypt(req, ret, tfm->base.__crt_alg); + return ret; } /** @@ -521,11 +550,14 @@ static inline int crypto_skcipher_encrypt(struct skcipher_request *req) static inline int crypto_skcipher_decrypt(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + int ret; if (crypto_skcipher_get_flags(tfm) & CRYPTO_TFM_NEED_KEY) - return -ENOKEY; - - return tfm->decrypt(req); + ret = -ENOKEY; + else + ret = tfm->decrypt(req); + crypto_stat_skcipher_decrypt(req, ret, tfm->base.__crt_alg); + return ret; } /** diff --git a/include/linux/crypto.h b/include/linux/crypto.h index e8839d3a7559..3634ad6fe202 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -454,6 +454,33 @@ struct compress_alg { * @cra_refcnt: internally used * @cra_destroy: internally used * + * All following statistics are for this crypto_alg + * @encrypt_cnt: number of encrypt requests + * @decrypt_cnt: number of decrypt requests + * @compress_cnt: number of compress requests + * @decompress_cnt: number of decompress requests + * @generate_cnt: number of RNG generate requests + * @seed_cnt: number of times the rng was seeded + * @hash_cnt: number of hash requests + * @sign_cnt: number of sign requests + * @setsecret_cnt: number of setsecrey operation + * @generate_public_key_cnt: number of generate_public_key operation + * @verify_cnt: number of verify operation + * @compute_shared_secret_cnt: number of compute_shared_secret operation + * @encrypt_tlen: total data size handled by encrypt requests + * @decrypt_tlen: total data size handled by decrypt requests + * @compress_tlen: total data size handled by compress requests + * @decompress_tlen: total data size handled by decompress requests + * @generate_tlen: total data size of generated data by the RNG + * @hash_tlen: total data size hashed + * @akcipher_err_cnt: number of error for akcipher requests + * @cipher_err_cnt: number of error for akcipher requests + * @compress_err_cnt: number of error for akcipher requests + * @aead_err_cnt: number of error for akcipher requests + * @hash_err_cnt: number of error for akcipher requests + * @rng_err_cnt: number of error for akcipher requests + * @kpp_err_cnt: number of error for akcipher requests + * * The struct crypto_alg describes a generic Crypto API algorithm and is common * for all of the transformations. Any variable not documented here shall not * be used by a cipher implementation as it is internal to the Crypto API. @@ -487,6 +514,45 @@ struct crypto_alg { void (*cra_destroy)(struct crypto_alg *alg); struct module *cra_module; + + union { + atomic_t encrypt_cnt; + atomic_t compress_cnt; + atomic_t generate_cnt; + atomic_t hash_cnt; + atomic_t setsecret_cnt; + }; + union { + atomic64_t encrypt_tlen; + atomic64_t compress_tlen; + atomic64_t generate_tlen; + atomic64_t hash_tlen; + }; + union { + atomic_t akcipher_err_cnt; + atomic_t cipher_err_cnt; + atomic_t compress_err_cnt; + atomic_t aead_err_cnt; + atomic_t hash_err_cnt; + atomic_t rng_err_cnt; + atomic_t kpp_err_cnt; + }; + union { + atomic_t decrypt_cnt; + atomic_t decompress_cnt; + atomic_t seed_cnt; + atomic_t generate_public_key_cnt; + }; + union { + atomic64_t decrypt_tlen; + atomic64_t decompress_tlen; + }; + union { + atomic_t verify_cnt; + atomic_t compute_shared_secret_cnt; + }; + atomic_t sign_cnt; + } CRYPTO_MINALIGN_ATTR; /* @@ -907,6 +973,38 @@ static inline struct crypto_ablkcipher *crypto_ablkcipher_reqtfm( return __crypto_ablkcipher_cast(req->base.tfm); } +static inline void crypto_stat_ablkcipher_encrypt(struct ablkcipher_request *req, + int ret) +{ +#ifdef CONFIG_CRYPTO_STATS + struct ablkcipher_tfm *crt = + crypto_ablkcipher_crt(crypto_ablkcipher_reqtfm(req)); + + if (ret && ret != -EINPROGRESS && ret != -EBUSY) { + atomic_inc(&crt->base->base.__crt_alg->cipher_err_cnt); + } else { + atomic_inc(&crt->base->base.__crt_alg->encrypt_cnt); + atomic64_add(req->nbytes, &crt->base->base.__crt_alg->encrypt_tlen); + } +#endif +} + +static inline void crypto_stat_ablkcipher_decrypt(struct ablkcipher_request *req, + int ret) +{ +#ifdef CONFIG_CRYPTO_STATS + struct ablkcipher_tfm *crt = + crypto_ablkcipher_crt(crypto_ablkcipher_reqtfm(req)); + + if (ret && ret != -EINPROGRESS && ret != -EBUSY) { + atomic_inc(&crt->base->base.__crt_alg->cipher_err_cnt); + } else { + atomic_inc(&crt->base->base.__crt_alg->decrypt_cnt); + atomic64_add(req->nbytes, &crt->base->base.__crt_alg->decrypt_tlen); + } +#endif +} + /** * crypto_ablkcipher_encrypt() - encrypt plaintext * @req: reference to the ablkcipher_request handle that holds all information @@ -922,7 +1020,11 @@ static inline int crypto_ablkcipher_encrypt(struct ablkcipher_request *req) { struct ablkcipher_tfm *crt = crypto_ablkcipher_crt(crypto_ablkcipher_reqtfm(req)); - return crt->encrypt(req); + int ret; + + ret = crt->encrypt(req); + crypto_stat_ablkcipher_encrypt(req, ret); + return ret; } /** @@ -940,7 +1042,11 @@ static inline int crypto_ablkcipher_decrypt(struct ablkcipher_request *req) { struct ablkcipher_tfm *crt = crypto_ablkcipher_crt(crypto_ablkcipher_reqtfm(req)); - return crt->decrypt(req); + int ret; + + ret = crt->decrypt(req); + crypto_stat_ablkcipher_decrypt(req, ret); + return ret; } /** diff --git a/include/uapi/linux/cryptouser.h b/include/uapi/linux/cryptouser.h index 19bf0ca6d635..6dafbc3e4414 100644 --- a/include/uapi/linux/cryptouser.h +++ b/include/uapi/linux/cryptouser.h @@ -29,6 +29,7 @@ enum { CRYPTO_MSG_UPDATEALG, CRYPTO_MSG_GETALG, CRYPTO_MSG_DELRNG, + CRYPTO_MSG_GETSTAT, __CRYPTO_MSG_MAX }; #define CRYPTO_MSG_MAX (__CRYPTO_MSG_MAX - 1) @@ -50,6 +51,16 @@ enum crypto_attr_type_t { CRYPTOCFGA_REPORT_AKCIPHER, /* struct crypto_report_akcipher */ CRYPTOCFGA_REPORT_KPP, /* struct crypto_report_kpp */ CRYPTOCFGA_REPORT_ACOMP, /* struct crypto_report_acomp */ + CRYPTOCFGA_STAT_LARVAL, /* struct crypto_stat */ + CRYPTOCFGA_STAT_HASH, /* struct crypto_stat */ + CRYPTOCFGA_STAT_BLKCIPHER, /* struct crypto_stat */ + CRYPTOCFGA_STAT_AEAD, /* struct crypto_stat */ + CRYPTOCFGA_STAT_COMPRESS, /* struct crypto_stat */ + CRYPTOCFGA_STAT_RNG, /* struct crypto_stat */ + CRYPTOCFGA_STAT_CIPHER, /* struct crypto_stat */ + CRYPTOCFGA_STAT_AKCIPHER, /* struct crypto_stat */ + CRYPTOCFGA_STAT_KPP, /* struct crypto_stat */ + CRYPTOCFGA_STAT_ACOMP, /* struct crypto_stat */ __CRYPTOCFGA_MAX #define CRYPTOCFGA_MAX (__CRYPTOCFGA_MAX - 1) @@ -65,6 +76,47 @@ struct crypto_user_alg { __u32 cru_flags; }; +struct crypto_stat { + char type[CRYPTO_MAX_NAME]; + union { + __u32 stat_encrypt_cnt; + __u32 stat_compress_cnt; + __u32 stat_generate_cnt; + __u32 stat_hash_cnt; + __u32 stat_setsecret_cnt; + }; + union { + __u64 stat_encrypt_tlen; + __u64 stat_compress_tlen; + __u64 stat_generate_tlen; + __u64 stat_hash_tlen; + }; + union { + __u32 stat_akcipher_err_cnt; + __u32 stat_cipher_err_cnt; + __u32 stat_compress_err_cnt; + __u32 stat_aead_err_cnt; + __u32 stat_hash_err_cnt; + __u32 stat_rng_err_cnt; + __u32 stat_kpp_err_cnt; + }; + union { + __u32 stat_decrypt_cnt; + __u32 stat_decompress_cnt; + __u32 stat_seed_cnt; + __u32 stat_generate_public_key_cnt; + }; + union { + __u64 stat_decrypt_tlen; + __u64 stat_decompress_tlen; + }; + union { + __u32 stat_verify_cnt; + __u32 stat_compute_shared_secret_cnt; + }; + __u32 stat_sign_cnt; +}; + struct crypto_report_larval { char type[CRYPTO_MAX_NAME]; }; -- cgit v1.2.3 From d7b9fd1669d4a4f38281c4e29f1408e1bdce09b3 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 21 Sep 2018 06:40:03 -0700 Subject: nvmem: provide nvmem_dev_name() Kernel users don't have any means of checking the names of nvmem devices. Add a routine that returns the name of the nvmem provider. This will be useful for future nvmem notifier subscribers - otherwise they can't check what device is being added/removed. Signed-off-by: Bartosz Golaszewski Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/core.c | 13 +++++++++++++ include/linux/nvmem-consumer.h | 8 ++++++++ 2 files changed, 21 insertions(+) (limited to 'include/linux') diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 6f064002f439..11afa3b6d551 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -1343,6 +1343,19 @@ int nvmem_device_write(struct nvmem_device *nvmem, } EXPORT_SYMBOL_GPL(nvmem_device_write); +/** + * nvmem_dev_name() - Get the name of a given nvmem device. + * + * @nvmem: nvmem device. + * + * Return: name of the nvmem device. + */ +const char *nvmem_dev_name(struct nvmem_device *nvmem) +{ + return dev_name(&nvmem->dev); +} +EXPORT_SYMBOL_GPL(nvmem_dev_name); + static int __init nvmem_init(void) { return bus_register(&nvmem_bus_type); diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index 4e85447f7860..0389fe00b177 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -55,6 +55,8 @@ ssize_t nvmem_device_cell_read(struct nvmem_device *nvmem, int nvmem_device_cell_write(struct nvmem_device *nvmem, struct nvmem_cell_info *info, void *buf); +const char *nvmem_dev_name(struct nvmem_device *nvmem); + #else static inline struct nvmem_cell *nvmem_cell_get(struct device *dev, @@ -143,6 +145,12 @@ static inline int nvmem_device_write(struct nvmem_device *nvmem, { return -ENOSYS; } + +static inline const char *nvmem_dev_name(struct nvmem_device *nvmem) +{ + return NULL; +} + #endif /* CONFIG_NVMEM */ #if IS_ENABLED(CONFIG_NVMEM) && IS_ENABLED(CONFIG_OF) -- cgit v1.2.3 From bf58e8820c48805394ec9e76339f0c4646050432 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 21 Sep 2018 06:40:13 -0700 Subject: nvmem: change the signature of nvmem_unregister() We switched the nvmem framework to using kref instead of manually checking the current number of users in nvmem_unregister() so this function can no longer fail. We also converted all remaining users that still checked the return value of nvmem_unregister() to using devm_nvmem_register(). Make the routine return void. Signed-off-by: Bartosz Golaszewski Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/core.c | 8 ++------ include/linux/nvmem-provider.h | 9 +++------ 2 files changed, 5 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 920b56e500cc..bd14d04782cd 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -553,20 +553,16 @@ static void nvmem_device_release(struct kref *kref) * nvmem_unregister() - Unregister previously registered nvmem device * * @nvmem: Pointer to previously registered nvmem device. - * - * Return: Will be an negative on error or a zero on success. */ -int nvmem_unregister(struct nvmem_device *nvmem) +void nvmem_unregister(struct nvmem_device *nvmem) { kref_put(&nvmem->refcnt, nvmem_device_release); - - return 0; } EXPORT_SYMBOL_GPL(nvmem_unregister); static void devm_nvmem_release(struct device *dev, void *res) { - WARN_ON(nvmem_unregister(*(struct nvmem_device **)res)); + nvmem_unregister(*(struct nvmem_device **)res); } /** diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 24def6ad09bb..0f357d0c1e75 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -70,7 +70,7 @@ struct nvmem_config { #if IS_ENABLED(CONFIG_NVMEM) struct nvmem_device *nvmem_register(const struct nvmem_config *cfg); -int nvmem_unregister(struct nvmem_device *nvmem); +void nvmem_unregister(struct nvmem_device *nvmem); struct nvmem_device *devm_nvmem_register(struct device *dev, const struct nvmem_config *cfg); @@ -87,10 +87,7 @@ static inline struct nvmem_device *nvmem_register(const struct nvmem_config *c) return ERR_PTR(-ENOSYS); } -static inline int nvmem_unregister(struct nvmem_device *nvmem) -{ - return -ENOSYS; -} +static inline void nvmem_unregister(struct nvmem_device *nvmem) {} static inline struct nvmem_device * devm_nvmem_register(struct device *dev, const struct nvmem_config *c) @@ -101,7 +98,7 @@ devm_nvmem_register(struct device *dev, const struct nvmem_config *c) static inline int devm_nvmem_unregister(struct device *dev, struct nvmem_device *nvmem) { - return nvmem_unregister(nvmem); + return -ENOSYS; } -- cgit v1.2.3 From b985f4cba6dbb3b60ad119c6f7e5cbad6f0d7e45 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 21 Sep 2018 06:40:15 -0700 Subject: nvmem: add support for cell info Add new structs and routines allowing users to define nvmem cells from machine code. This global list of entries is parsed when a provider is registered and cells are associated with the relevant nvmem_device struct. A possible improvement for the future is to allow users to register cell tables after the nvmem provider has been registered by updating the cell list at each call to nvmem_(add|del)_cell_table(). Signed-off-by: Bartosz Golaszewski Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/core.c | 72 ++++++++++++++++++++++++++++++++++++++++++ include/linux/nvmem-provider.h | 33 +++++++++++++------ 2 files changed, 96 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index ee794613024c..8e0108806e65 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -59,6 +59,9 @@ struct nvmem_cell { static DEFINE_MUTEX(nvmem_mutex); static DEFINE_IDA(nvmem_ida); +static DEFINE_MUTEX(nvmem_cell_mutex); +static LIST_HEAD(nvmem_cell_tables); + #ifdef CONFIG_DEBUG_LOCK_ALLOC static struct lock_class_key eeprom_lock_key; #endif @@ -416,6 +419,43 @@ static int nvmem_setup_compat(struct nvmem_device *nvmem, return 0; } +static int nvmem_add_cells_from_table(struct nvmem_device *nvmem) +{ + const struct nvmem_cell_info *info; + struct nvmem_cell_table *table; + struct nvmem_cell *cell; + int rval = 0, i; + + mutex_lock(&nvmem_cell_mutex); + list_for_each_entry(table, &nvmem_cell_tables, node) { + if (strcmp(nvmem_dev_name(nvmem), table->nvmem_name) == 0) { + for (i = 0; i < table->ncells; i++) { + info = &table->cells[i]; + + cell = kzalloc(sizeof(*cell), GFP_KERNEL); + if (!cell) { + rval = -ENOMEM; + goto out; + } + + rval = nvmem_cell_info_to_nvmem_cell(nvmem, + info, + cell); + if (rval) { + kfree(cell); + goto out; + } + + nvmem_cell_add(cell); + } + } + } + +out: + mutex_unlock(&nvmem_cell_mutex); + return rval; +} + /** * nvmem_register() - Register a nvmem device for given nvmem_config. * Also creates an binary entry in /sys/bus/nvmem/devices/dev-name/nvmem @@ -502,8 +542,14 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) goto err_teardown_compat; } + rval = nvmem_add_cells_from_table(nvmem); + if (rval) + goto err_remove_cells; + return nvmem; +err_remove_cells: + nvmem_device_remove_all_cells(nvmem); err_teardown_compat: if (config->compat) device_remove_bin_file(nvmem->base_dev, &nvmem->eeprom); @@ -1306,6 +1352,32 @@ int nvmem_device_write(struct nvmem_device *nvmem, } EXPORT_SYMBOL_GPL(nvmem_device_write); +/** + * nvmem_add_cell_table() - register a table of cell info entries + * + * @table: table of cell info entries + */ +void nvmem_add_cell_table(struct nvmem_cell_table *table) +{ + mutex_lock(&nvmem_cell_mutex); + list_add_tail(&table->node, &nvmem_cell_tables); + mutex_unlock(&nvmem_cell_mutex); +} +EXPORT_SYMBOL_GPL(nvmem_add_cell_table); + +/** + * nvmem_del_cell_table() - remove a previously registered cell info table + * + * @table: table of cell info entries + */ +void nvmem_del_cell_table(struct nvmem_cell_table *table) +{ + mutex_lock(&nvmem_cell_mutex); + list_del(&table->node); + mutex_unlock(&nvmem_cell_mutex); +} +EXPORT_SYMBOL_GPL(nvmem_del_cell_table); + /** * nvmem_dev_name() - Get the name of a given nvmem device. * diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 0f357d0c1e75..5c9f205cac8f 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -67,6 +67,25 @@ struct nvmem_config { struct device *base_dev; }; +/** + * struct nvmem_cell_table - NVMEM cell definitions for given provider + * + * @nvmem_name: Provider name. + * @cells: Array of cell definitions. + * @ncells: Number of cell definitions in the array. + * @node: List node. + * + * This structure together with related helper functions is provided for users + * that don't can't access the nvmem provided structure but wish to register + * cell definitions for it e.g. board files registering an EEPROM device. + */ +struct nvmem_cell_table { + const char *nvmem_name; + const struct nvmem_cell_info *cells; + size_t ncells; + struct list_head node; +}; + #if IS_ENABLED(CONFIG_NVMEM) struct nvmem_device *nvmem_register(const struct nvmem_config *cfg); @@ -77,9 +96,9 @@ struct nvmem_device *devm_nvmem_register(struct device *dev, int devm_nvmem_unregister(struct device *dev, struct nvmem_device *nvmem); -int nvmem_add_cells(struct nvmem_device *nvmem, - const struct nvmem_cell_info *info, - int ncells); +void nvmem_add_cell_table(struct nvmem_cell_table *table); +void nvmem_del_cell_table(struct nvmem_cell_table *table); + #else static inline struct nvmem_device *nvmem_register(const struct nvmem_config *c) @@ -102,12 +121,8 @@ devm_nvmem_unregister(struct device *dev, struct nvmem_device *nvmem) } -static inline int nvmem_add_cells(struct nvmem_device *nvmem, - const struct nvmem_cell_info *info, - int ncells) -{ - return -ENOSYS; -} +static inline void nvmem_add_cell_table(struct nvmem_cell_table *table) {} +static inline void nvmem_del_cell_table(struct nvmem_cell_table *table) {} #endif /* CONFIG_NVMEM */ #endif /* ifndef _LINUX_NVMEM_PROVIDER_H */ -- cgit v1.2.3 From 506157be06ba28137b18b7419a4dccfa244f4983 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 21 Sep 2018 06:40:17 -0700 Subject: nvmem: add support for cell lookups from machine code Add a way for machine code users to associate devices with nvmem cells. This restores the support for non-DT systems but following a different approach. Cells must now be associated with devices using provided routines and data structures before they can be retrieved using nvmem_cell_get(). It's still possible to define cells statically in nvmem_config but cells created this way still need to be associated with consumers using lookup entries. Note that nvmem_find() must be moved higher in the source file as we want to call it from __nvmem_device_get() for devices that don't have a device node. The signature of __nvmem_device_get() is also changed as it's no longer used to retrieve cells. Signed-off-by: Bartosz Golaszewski Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/core.c | 129 ++++++++++++++++++++++++++++++++--------- include/linux/nvmem-consumer.h | 28 +++++++++ 2 files changed, 131 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 74b6b97680d5..9cc86d131e1e 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -62,6 +62,9 @@ static DEFINE_IDA(nvmem_ida); static DEFINE_MUTEX(nvmem_cell_mutex); static LIST_HEAD(nvmem_cell_tables); +static DEFINE_MUTEX(nvmem_lookup_mutex); +static LIST_HEAD(nvmem_lookup_list); + #ifdef CONFIG_DEBUG_LOCK_ALLOC static struct lock_class_key eeprom_lock_key; #endif @@ -283,6 +286,18 @@ static struct nvmem_device *of_nvmem_find(struct device_node *nvmem_np) return to_nvmem_device(d); } +static struct nvmem_device *nvmem_find(const char *name) +{ + struct device *d; + + d = bus_find_device_by_name(&nvmem_bus_type, NULL, name); + + if (!d) + return NULL; + + return to_nvmem_device(d); +} + static void nvmem_cell_drop(struct nvmem_cell *cell) { mutex_lock(&nvmem_mutex); @@ -472,6 +487,21 @@ nvmem_find_cell_by_index(struct nvmem_device *nvmem, int index) return cell; } +static struct nvmem_cell * +nvmem_find_cell_by_name(struct nvmem_device *nvmem, const char *cell_id) +{ + struct nvmem_cell *cell = NULL; + + mutex_lock(&nvmem_mutex); + list_for_each_entry(cell, &nvmem->cells, node) { + if (strcmp(cell_id, cell->name) == 0) + break; + } + mutex_unlock(&nvmem_mutex); + + return cell; +} + static int nvmem_add_cells_from_of(struct nvmem_device *nvmem) { struct device_node *parent, *child; @@ -719,16 +749,12 @@ int devm_nvmem_unregister(struct device *dev, struct nvmem_device *nvmem) EXPORT_SYMBOL(devm_nvmem_unregister); static struct nvmem_device *__nvmem_device_get(struct device_node *np, - struct nvmem_cell **cellp, - const char *cell_id) + const char *nvmem_name) { struct nvmem_device *nvmem = NULL; - if (!np) - return ERR_PTR(-ENOENT); - mutex_lock(&nvmem_mutex); - nvmem = of_nvmem_find(np); + nvmem = np ? of_nvmem_find(np) : nvmem_find(nvmem_name); mutex_unlock(&nvmem_mutex); if (!nvmem) return ERR_PTR(-EPROBE_DEFER); @@ -752,18 +778,6 @@ static void __nvmem_device_put(struct nvmem_device *nvmem) kref_put(&nvmem->refcnt, nvmem_device_release); } -static struct nvmem_device *nvmem_find(const char *name) -{ - struct device *d; - - d = bus_find_device_by_name(&nvmem_bus_type, NULL, name); - - if (!d) - return ERR_PTR(-ENOENT); - - return to_nvmem_device(d); -} - #if IS_ENABLED(CONFIG_OF) /** * of_nvmem_device_get() - Get nvmem device from a given id @@ -786,7 +800,7 @@ struct nvmem_device *of_nvmem_device_get(struct device_node *np, const char *id) if (!nvmem_np) return ERR_PTR(-EINVAL); - return __nvmem_device_get(nvmem_np, NULL, NULL); + return __nvmem_device_get(nvmem_np, NULL); } EXPORT_SYMBOL_GPL(of_nvmem_device_get); #endif @@ -890,15 +904,43 @@ struct nvmem_device *devm_nvmem_device_get(struct device *dev, const char *id) } EXPORT_SYMBOL_GPL(devm_nvmem_device_get); -static struct nvmem_cell *nvmem_cell_get_from_list(const char *cell_id) +static struct nvmem_cell * +nvmem_cell_get_from_lookup(struct device *dev, const char *con_id) { - struct nvmem_cell *cell = NULL; + struct nvmem_cell *cell = ERR_PTR(-ENOENT); + struct nvmem_cell_lookup *lookup; struct nvmem_device *nvmem; + const char *dev_id; - nvmem = __nvmem_device_get(NULL, &cell, cell_id); - if (IS_ERR(nvmem)) - return ERR_CAST(nvmem); + if (!dev) + return ERR_PTR(-EINVAL); + + dev_id = dev_name(dev); + + mutex_lock(&nvmem_lookup_mutex); + + list_for_each_entry(lookup, &nvmem_lookup_list, node) { + if ((strcmp(lookup->dev_id, dev_id) == 0) && + (strcmp(lookup->con_id, con_id) == 0)) { + /* This is the right entry. */ + nvmem = __nvmem_device_get(NULL, lookup->nvmem_name); + if (!nvmem) { + /* Provider may not be registered yet. */ + cell = ERR_PTR(-EPROBE_DEFER); + goto out; + } + + cell = nvmem_find_cell_by_name(nvmem, + lookup->cell_name); + if (!cell) { + __nvmem_device_put(nvmem); + goto out; + } + } + } +out: + mutex_unlock(&nvmem_lookup_mutex); return cell; } @@ -935,7 +977,7 @@ struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, if (!nvmem_np) return ERR_PTR(-EINVAL); - nvmem = __nvmem_device_get(nvmem_np, NULL, NULL); + nvmem = __nvmem_device_get(nvmem_np, NULL); of_node_put(nvmem_np); if (IS_ERR(nvmem)) return ERR_CAST(nvmem); @@ -975,7 +1017,7 @@ struct nvmem_cell *nvmem_cell_get(struct device *dev, const char *cell_id) if (!cell_id) return ERR_PTR(-EINVAL); - return nvmem_cell_get_from_list(cell_id); + return nvmem_cell_get_from_lookup(dev, cell_id); } EXPORT_SYMBOL_GPL(nvmem_cell_get); @@ -1405,6 +1447,41 @@ void nvmem_del_cell_table(struct nvmem_cell_table *table) } EXPORT_SYMBOL_GPL(nvmem_del_cell_table); +/** + * nvmem_add_cell_lookups() - register a list of cell lookup entries + * + * @entries: array of cell lookup entries + * @nentries: number of cell lookup entries in the array + */ +void nvmem_add_cell_lookups(struct nvmem_cell_lookup *entries, size_t nentries) +{ + int i; + + mutex_lock(&nvmem_lookup_mutex); + for (i = 0; i < nentries; i++) + list_add_tail(&entries[i].node, &nvmem_lookup_list); + mutex_unlock(&nvmem_lookup_mutex); +} +EXPORT_SYMBOL_GPL(nvmem_add_cell_lookups); + +/** + * nvmem_del_cell_lookups() - remove a list of previously added cell lookup + * entries + * + * @entries: array of cell lookup entries + * @nentries: number of cell lookup entries in the array + */ +void nvmem_del_cell_lookups(struct nvmem_cell_lookup *entries, size_t nentries) +{ + int i; + + mutex_lock(&nvmem_lookup_mutex); + for (i = 0; i < nentries; i++) + list_del(&entries[i].node); + mutex_unlock(&nvmem_lookup_mutex); +} +EXPORT_SYMBOL_GPL(nvmem_del_cell_lookups); + /** * nvmem_dev_name() - Get the name of a given nvmem device. * diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index 0389fe00b177..27eee3945405 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -29,6 +29,24 @@ struct nvmem_cell_info { unsigned int nbits; }; +/** + * struct nvmem_cell_lookup - cell lookup entry + * + * @nvmem_name: Name of the provider. + * @cell_name: Name of the nvmem cell as defined in the name field of + * struct nvmem_cell_info. + * @dev_id: Name of the consumer device that will be associated with + * this cell. + * @con_id: Connector id for this cell lookup. + */ +struct nvmem_cell_lookup { + const char *nvmem_name; + const char *cell_name; + const char *dev_id; + const char *con_id; + struct list_head node; +}; + #if IS_ENABLED(CONFIG_NVMEM) /* Cell based interface */ @@ -57,6 +75,11 @@ int nvmem_device_cell_write(struct nvmem_device *nvmem, const char *nvmem_dev_name(struct nvmem_device *nvmem); +void nvmem_add_cell_lookups(struct nvmem_cell_lookup *entries, + size_t nentries); +void nvmem_del_cell_lookups(struct nvmem_cell_lookup *entries, + size_t nentries); + #else static inline struct nvmem_cell *nvmem_cell_get(struct device *dev, @@ -151,6 +174,11 @@ static inline const char *nvmem_dev_name(struct nvmem_device *nvmem) return NULL; } +static inline void +nvmem_add_cell_lookups(struct nvmem_cell_lookup *entries, size_t nentries) {} +static inline void +nvmem_del_cell_lookups(struct nvmem_cell_lookup *entries, size_t nentries) {} + #endif /* CONFIG_NVMEM */ #if IS_ENABLED(CONFIG_NVMEM) && IS_ENABLED(CONFIG_OF) -- cgit v1.2.3 From bee1138bea15a640aaa9e9bb909af5b2762520e0 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 21 Sep 2018 06:40:19 -0700 Subject: nvmem: add a notifier chain Add a blocking notifier chain with four events (add and remove for both devices and cells) so that users can get notified about the addition of nvmem resources they're waiting for. We'll use this instead of the at24 setup callback in the mityomapl138 board file. Signed-off-by: Bartosz Golaszewski Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/core.c | 36 ++++++++++++++++++++++++++++++++++++ include/linux/nvmem-consumer.h | 21 +++++++++++++++++++++ 2 files changed, 57 insertions(+) (limited to 'include/linux') diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 9cc86d131e1e..da441019b609 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -65,6 +65,8 @@ static LIST_HEAD(nvmem_cell_tables); static DEFINE_MUTEX(nvmem_lookup_mutex); static LIST_HEAD(nvmem_lookup_list); +static BLOCKING_NOTIFIER_HEAD(nvmem_notifier); + #ifdef CONFIG_DEBUG_LOCK_ALLOC static struct lock_class_key eeprom_lock_key; #endif @@ -300,6 +302,7 @@ static struct nvmem_device *nvmem_find(const char *name) static void nvmem_cell_drop(struct nvmem_cell *cell) { + blocking_notifier_call_chain(&nvmem_notifier, NVMEM_CELL_REMOVE, cell); mutex_lock(&nvmem_mutex); list_del(&cell->node); mutex_unlock(&nvmem_mutex); @@ -319,6 +322,7 @@ static void nvmem_cell_add(struct nvmem_cell *cell) mutex_lock(&nvmem_mutex); list_add_tail(&cell->node, &cell->nvmem->cells); mutex_unlock(&nvmem_mutex); + blocking_notifier_call_chain(&nvmem_notifier, NVMEM_CELL_ADD, cell); } static int nvmem_cell_info_to_nvmem_cell(struct nvmem_device *nvmem, @@ -434,6 +438,32 @@ static int nvmem_setup_compat(struct nvmem_device *nvmem, return 0; } +/** + * nvmem_register_notifier() - Register a notifier block for nvmem events. + * + * @nb: notifier block to be called on nvmem events. + * + * Return: 0 on success, negative error number on failure. + */ +int nvmem_register_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&nvmem_notifier, nb); +} +EXPORT_SYMBOL_GPL(nvmem_register_notifier); + +/** + * nvmem_unregister_notifier() - Unregister a notifier block for nvmem events. + * + * @nb: notifier block to be unregistered. + * + * Return: 0 on success, negative error number on failure. + */ +int nvmem_unregister_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&nvmem_notifier, nb); +} +EXPORT_SYMBOL_GPL(nvmem_unregister_notifier); + static int nvmem_add_cells_from_table(struct nvmem_device *nvmem) { const struct nvmem_cell_info *info; @@ -647,6 +677,10 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) if (rval) goto err_remove_cells; + rval = blocking_notifier_call_chain(&nvmem_notifier, NVMEM_ADD, nvmem); + if (rval) + goto err_remove_cells; + return nvmem; err_remove_cells: @@ -669,6 +703,8 @@ static void nvmem_device_release(struct kref *kref) nvmem = container_of(kref, struct nvmem_device, refcnt); + blocking_notifier_call_chain(&nvmem_notifier, NVMEM_REMOVE, nvmem); + if (nvmem->flags & FLAG_COMPAT) device_remove_bin_file(nvmem->base_dev, &nvmem->eeprom); diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index 27eee3945405..0326b52e906b 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -14,6 +14,7 @@ #include #include +#include struct device; struct device_node; @@ -47,6 +48,13 @@ struct nvmem_cell_lookup { struct list_head node; }; +enum { + NVMEM_ADD = 1, + NVMEM_REMOVE, + NVMEM_CELL_ADD, + NVMEM_CELL_REMOVE, +}; + #if IS_ENABLED(CONFIG_NVMEM) /* Cell based interface */ @@ -80,6 +88,9 @@ void nvmem_add_cell_lookups(struct nvmem_cell_lookup *entries, void nvmem_del_cell_lookups(struct nvmem_cell_lookup *entries, size_t nentries); +int nvmem_register_notifier(struct notifier_block *nb); +int nvmem_unregister_notifier(struct notifier_block *nb); + #else static inline struct nvmem_cell *nvmem_cell_get(struct device *dev, @@ -179,6 +190,16 @@ nvmem_add_cell_lookups(struct nvmem_cell_lookup *entries, size_t nentries) {} static inline void nvmem_del_cell_lookups(struct nvmem_cell_lookup *entries, size_t nentries) {} +static inline int nvmem_register_notifier(struct notifier_block *nb) +{ + return -ENOSYS; +} + +static inline int nvmem_unregister_notifier(struct notifier_block *nb) +{ + return -ENOSYS; +} + #endif /* CONFIG_NVMEM */ #if IS_ENABLED(CONFIG_NVMEM) && IS_ENABLED(CONFIG_OF) -- cgit v1.2.3 From b1c1db9883c276fe41a04e9ce8f89576a64b1ac0 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 21 Sep 2018 06:40:20 -0700 Subject: nvmem: use SPDX license identifiers Use SPDX license identiefiers to core nvmem files and remove GPL 2.0 license boilerplate. Signed-off-by: Bartosz Golaszewski Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/core.c | 10 +--------- include/linux/nvmem-consumer.h | 5 +---- include/linux/nvmem-provider.h | 5 +---- 3 files changed, 3 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index da441019b609..ea05219e60b4 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -1,17 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * nvmem framework core. * * Copyright (C) 2015 Srinivas Kandagatla * Copyright (C) 2013 Maxime Ripard - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 and - * only version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #include diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index 0326b52e906b..d18caae2f7ac 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -1,12 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * nvmem framework consumer. * * Copyright (C) 2015 Srinivas Kandagatla * Copyright (C) 2013 Maxime Ripard - * - * This file is licensed under the terms of the GNU General Public - * License version 2. This program is licensed "as is" without any - * warranty of any kind, whether express or implied. */ #ifndef _LINUX_NVMEM_CONSUMER_H diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 5c9f205cac8f..8ae012f6545a 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -1,12 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * nvmem framework provider. * * Copyright (C) 2015 Srinivas Kandagatla * Copyright (C) 2013 Maxime Ripard - * - * This file is licensed under the terms of the GNU General Public - * License version 2. This program is licensed "as is" without any - * warranty of any kind, whether express or implied. */ #ifndef _LINUX_NVMEM_PROVIDER_H -- cgit v1.2.3 From 165589f0cb52b34db12e15676a034b8f83dfa756 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 21 Sep 2018 06:40:21 -0700 Subject: nvmem: make the naming of arguments in nvmem_cell_get() consistent The argument representing the cell name in the nvmem_cell_get() family of functions is not consistend between function prototypes and definitions. Name it 'id' in all those routines. This is in line with other frameworks and can represent both the DT cell name from the nvmem-cell-names property as well as the con_id field from cell lookup entries. Signed-off-by: Bartosz Golaszewski Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/core.c | 27 ++++++++++++++------------- include/linux/nvmem-consumer.h | 12 ++++++------ 2 files changed, 20 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index ea05219e60b4..ff21402fbd7d 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -977,16 +977,15 @@ out: * of_nvmem_cell_get() - Get a nvmem cell from given device node and cell id * * @np: Device tree node that uses the nvmem cell. - * @name: nvmem cell name from nvmem-cell-names property, or NULL - * for the cell at index 0 (the lone cell with no accompanying - * nvmem-cell-names property). + * @id: nvmem cell name from nvmem-cell-names property, or NULL + * for the cell at index 0 (the lone cell with no accompanying + * nvmem-cell-names property). * * Return: Will be an ERR_PTR() on error or a valid pointer * to a struct nvmem_cell. The nvmem_cell will be freed by the * nvmem_cell_put(). */ -struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, - const char *name) +struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, const char *id) { struct device_node *cell_np, *nvmem_np; struct nvmem_device *nvmem; @@ -994,8 +993,8 @@ struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, int index = 0; /* if cell name exists, find index to the name */ - if (name) - index = of_property_match_string(np, "nvmem-cell-names", name); + if (id) + index = of_property_match_string(np, "nvmem-cell-names", id); cell_np = of_parse_phandle(np, "nvmem-cells", index); if (!cell_np) @@ -1025,27 +1024,29 @@ EXPORT_SYMBOL_GPL(of_nvmem_cell_get); * nvmem_cell_get() - Get nvmem cell of device form a given cell name * * @dev: Device that requests the nvmem cell. - * @cell_id: nvmem cell name to get. + * @id: nvmem cell name to get (this corresponds with the name from the + * nvmem-cell-names property for DT systems and with the con_id from + * the lookup entry for non-DT systems). * * Return: Will be an ERR_PTR() on error or a valid pointer * to a struct nvmem_cell. The nvmem_cell will be freed by the * nvmem_cell_put(). */ -struct nvmem_cell *nvmem_cell_get(struct device *dev, const char *cell_id) +struct nvmem_cell *nvmem_cell_get(struct device *dev, const char *id) { struct nvmem_cell *cell; if (dev->of_node) { /* try dt first */ - cell = of_nvmem_cell_get(dev->of_node, cell_id); + cell = of_nvmem_cell_get(dev->of_node, id); if (!IS_ERR(cell) || PTR_ERR(cell) == -EPROBE_DEFER) return cell; } - /* NULL cell_id only allowed for device tree; invalid otherwise */ - if (!cell_id) + /* NULL cell id only allowed for device tree; invalid otherwise */ + if (!id) return ERR_PTR(-EINVAL); - return nvmem_cell_get_from_lookup(dev, cell_id); + return nvmem_cell_get_from_lookup(dev, id); } EXPORT_SYMBOL_GPL(nvmem_cell_get); diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index d18caae2f7ac..e17617fa034f 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -55,8 +55,8 @@ enum { #if IS_ENABLED(CONFIG_NVMEM) /* Cell based interface */ -struct nvmem_cell *nvmem_cell_get(struct device *dev, const char *name); -struct nvmem_cell *devm_nvmem_cell_get(struct device *dev, const char *name); +struct nvmem_cell *nvmem_cell_get(struct device *dev, const char *id); +struct nvmem_cell *devm_nvmem_cell_get(struct device *dev, const char *id); void nvmem_cell_put(struct nvmem_cell *cell); void devm_nvmem_cell_put(struct device *dev, struct nvmem_cell *cell); void *nvmem_cell_read(struct nvmem_cell *cell, size_t *len); @@ -91,13 +91,13 @@ int nvmem_unregister_notifier(struct notifier_block *nb); #else static inline struct nvmem_cell *nvmem_cell_get(struct device *dev, - const char *name) + const char *id) { return ERR_PTR(-ENOSYS); } static inline struct nvmem_cell *devm_nvmem_cell_get(struct device *dev, - const char *name) + const char *id) { return ERR_PTR(-ENOSYS); } @@ -201,12 +201,12 @@ static inline int nvmem_unregister_notifier(struct notifier_block *nb) #if IS_ENABLED(CONFIG_NVMEM) && IS_ENABLED(CONFIG_OF) struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, - const char *name); + const char *id); struct nvmem_device *of_nvmem_device_get(struct device_node *np, const char *name); #else static inline struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, - const char *name) + const char *id) { return ERR_PTR(-ENOSYS); } -- cgit v1.2.3 From 20167b70c894f20cd01e2579fad206de440816ef Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Fri, 21 Sep 2018 06:40:22 -0700 Subject: nvmem: use EOPNOTSUPP instead of ENOSYS Checkpatch emits warnings when using ENOSYS. Some of the frameworks started using EOPNOTSUPP as return values for API functions when given subsystem is disabled in Kconfig. Signed-off-by: Bartosz Golaszewski Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-consumer.h | 30 +++++++++++++++--------------- include/linux/nvmem-provider.h | 5 ++--- 2 files changed, 17 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index e17617fa034f..312bfa5efd80 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -93,13 +93,13 @@ int nvmem_unregister_notifier(struct notifier_block *nb); static inline struct nvmem_cell *nvmem_cell_get(struct device *dev, const char *id) { - return ERR_PTR(-ENOSYS); + return ERR_PTR(-EOPNOTSUPP); } static inline struct nvmem_cell *devm_nvmem_cell_get(struct device *dev, const char *id) { - return ERR_PTR(-ENOSYS); + return ERR_PTR(-EOPNOTSUPP); } static inline void devm_nvmem_cell_put(struct device *dev, @@ -113,31 +113,31 @@ static inline void nvmem_cell_put(struct nvmem_cell *cell) static inline void *nvmem_cell_read(struct nvmem_cell *cell, size_t *len) { - return ERR_PTR(-ENOSYS); + return ERR_PTR(-EOPNOTSUPP); } static inline int nvmem_cell_write(struct nvmem_cell *cell, const char *buf, size_t len) { - return -ENOSYS; + return -EOPNOTSUPP; } static inline int nvmem_cell_read_u32(struct device *dev, const char *cell_id, u32 *val) { - return -ENOSYS; + return -EOPNOTSUPP; } static inline struct nvmem_device *nvmem_device_get(struct device *dev, const char *name) { - return ERR_PTR(-ENOSYS); + return ERR_PTR(-EOPNOTSUPP); } static inline struct nvmem_device *devm_nvmem_device_get(struct device *dev, const char *name) { - return ERR_PTR(-ENOSYS); + return ERR_PTR(-EOPNOTSUPP); } static inline void nvmem_device_put(struct nvmem_device *nvmem) @@ -153,28 +153,28 @@ static inline ssize_t nvmem_device_cell_read(struct nvmem_device *nvmem, struct nvmem_cell_info *info, void *buf) { - return -ENOSYS; + return -EOPNOTSUPP; } static inline int nvmem_device_cell_write(struct nvmem_device *nvmem, struct nvmem_cell_info *info, void *buf) { - return -ENOSYS; + return -EOPNOTSUPP; } static inline int nvmem_device_read(struct nvmem_device *nvmem, unsigned int offset, size_t bytes, void *buf) { - return -ENOSYS; + return -EOPNOTSUPP; } static inline int nvmem_device_write(struct nvmem_device *nvmem, unsigned int offset, size_t bytes, void *buf) { - return -ENOSYS; + return -EOPNOTSUPP; } static inline const char *nvmem_dev_name(struct nvmem_device *nvmem) @@ -189,12 +189,12 @@ nvmem_del_cell_lookups(struct nvmem_cell_lookup *entries, size_t nentries) {} static inline int nvmem_register_notifier(struct notifier_block *nb) { - return -ENOSYS; + return -EOPNOTSUPP; } static inline int nvmem_unregister_notifier(struct notifier_block *nb) { - return -ENOSYS; + return -EOPNOTSUPP; } #endif /* CONFIG_NVMEM */ @@ -208,13 +208,13 @@ struct nvmem_device *of_nvmem_device_get(struct device_node *np, static inline struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, const char *id) { - return ERR_PTR(-ENOSYS); + return ERR_PTR(-EOPNOTSUPP); } static inline struct nvmem_device *of_nvmem_device_get(struct device_node *np, const char *name) { - return ERR_PTR(-ENOSYS); + return ERR_PTR(-EOPNOTSUPP); } #endif /* CONFIG_NVMEM && CONFIG_OF */ diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 8ae012f6545a..1e3283c2af77 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -100,7 +100,7 @@ void nvmem_del_cell_table(struct nvmem_cell_table *table); static inline struct nvmem_device *nvmem_register(const struct nvmem_config *c) { - return ERR_PTR(-ENOSYS); + return ERR_PTR(-EOPNOTSUPP); } static inline void nvmem_unregister(struct nvmem_device *nvmem) {} @@ -114,8 +114,7 @@ devm_nvmem_register(struct device *dev, const struct nvmem_config *c) static inline int devm_nvmem_unregister(struct device *dev, struct nvmem_device *nvmem) { - return -ENOSYS; - + return -EOPNOTSUPP; } static inline void nvmem_add_cell_table(struct nvmem_cell_table *table) {} -- cgit v1.2.3 From d6112f8def514e019658bcc9b57d53acdb71ca3f Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Fri, 7 Sep 2018 09:16:51 +0300 Subject: PCI: Add support for Immediate Readiness MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit PCIe r4.0, sec 7.5.1.1.4 defines a new bit in the Status Register: Immediate Readiness – This optional bit, when Set, indicates the Function is guaranteed to be ready to successfully complete valid configuration accesses at any time following any reset that the host is capable of issuing Configuration Requests to this Function. When this bit is Set, for accesses to this Function, software is exempt from all requirements to delay configuration accesses following any type of reset, including but not limited to the timing requirements defined in Section 6.6. This means that all delays after a Conventional or Function Reset can be skipped. This patch reads such bit and caches its value in a flag inside struct pci_dev to be checked later if we should delay or can skip delays after a reset. While at that, also move the explicit msleep(100) call from pcie_flr() and pci_af_flr() to pci_dev_wait(). Signed-off-by: Felipe Balbi [bhelgaas: rename PCI_STATUS_IMMEDIATE to PCI_STATUS_IMM_READY] Signed-off-by: Bjorn Helgaas --- drivers/pci/pci.c | 13 ++++++++++++- include/linux/pci.h | 1 + include/uapi/linux/pci_regs.h | 1 + 3 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 1835f3a7aa8d..ee7c2f4eef9b 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -999,7 +999,7 @@ static void __pci_start_power_transition(struct pci_dev *dev, pci_power_t state) * because have already delayed for the bridge. */ if (dev->runtime_d3cold) { - if (dev->d3cold_delay) + if (dev->d3cold_delay && !dev->imm_ready) msleep(dev->d3cold_delay); /* * When powering on a bridge from D3cold, the @@ -2644,6 +2644,7 @@ EXPORT_SYMBOL_GPL(pci_d3cold_disable); void pci_pm_init(struct pci_dev *dev) { int pm; + u16 status; u16 pmc; pm_runtime_forbid(&dev->dev); @@ -2706,6 +2707,10 @@ void pci_pm_init(struct pci_dev *dev) /* Disable the PME# generation functionality */ pci_pme_active(dev, false); } + + pci_read_config_word(dev, PCI_STATUS, &status); + if (status & PCI_STATUS_IMM_READY) + dev->imm_ready = 1; } static unsigned long pci_ea_flags(struct pci_dev *dev, u8 prop) @@ -4376,6 +4381,9 @@ int pcie_flr(struct pci_dev *dev) pcie_capability_set_word(dev, PCI_EXP_DEVCTL, PCI_EXP_DEVCTL_BCR_FLR); + if (dev->imm_ready) + return 0; + /* * Per PCIe r4.0, sec 6.6.2, a device must complete an FLR within * 100ms, but may silently discard requests while the FLR is in @@ -4417,6 +4425,9 @@ static int pci_af_flr(struct pci_dev *dev, int probe) pci_write_config_byte(dev, pos + PCI_AF_CTRL, PCI_AF_CTRL_FLR); + if (dev->imm_ready) + return 0; + /* * Per Advanced Capabilities for Conventional PCI ECN, 13 April 2006, * updated 27 July 2006; a device must complete an FLR within diff --git a/include/linux/pci.h b/include/linux/pci.h index 6925828f9f25..60da5d7d4310 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -325,6 +325,7 @@ struct pci_dev { pci_power_t current_state; /* Current operating state. In ACPI, this is D0-D3, D0 being fully functional, and D3 being off. */ + unsigned int imm_ready:1; /* Supports Immediate Readiness */ u8 pm_cap; /* PM capability offset */ unsigned int pme_support:5; /* Bitmask of states from which PME# can be generated */ diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index ee556ccc93f4..e1e9888c85e6 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -52,6 +52,7 @@ #define PCI_COMMAND_INTX_DISABLE 0x400 /* INTx Emulation Disable */ #define PCI_STATUS 0x06 /* 16 bits */ +#define PCI_STATUS_IMM_READY 0x01 /* Immediate Readiness */ #define PCI_STATUS_INTERRUPT 0x08 /* Interrupt status */ #define PCI_STATUS_CAP_LIST 0x10 /* Support Capability List */ #define PCI_STATUS_66MHZ 0x20 /* Support 66 MHz PCI 2.1 bus */ -- cgit v1.2.3 From f1f207e43b8a49ac2ee3c36a64de1f84651c6079 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 22 Aug 2018 15:04:40 -0500 Subject: of: Add cpu node iterator for_each_of_cpu_node() Iterating thru cpu nodes is a common pattern. Create a common iterator which can find child nodes either by node name or device_type == cpu. Using the former will allow for eventually dropping device_type properties which are deprecated for FDT. Cc: Frank Rowand Reviewed-by: Geert Uytterhoeven Signed-off-by: Rob Herring --- drivers/of/base.c | 39 +++++++++++++++++++++++++++++++++++++++ include/linux/of.h | 11 +++++++++++ 2 files changed, 50 insertions(+) (limited to 'include/linux') diff --git a/drivers/of/base.c b/drivers/of/base.c index a055cd1ef96d..4807db0a35b3 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -741,6 +741,45 @@ struct device_node *of_get_next_available_child(const struct device_node *node, } EXPORT_SYMBOL(of_get_next_available_child); +/** + * of_get_next_cpu_node - Iterate on cpu nodes + * @prev: previous child of the /cpus node, or NULL to get first + * + * Returns a cpu node pointer with refcount incremented, use of_node_put() + * on it when done. Returns NULL when prev is the last child. Decrements + * the refcount of prev. + */ +struct device_node *of_get_next_cpu_node(struct device_node *prev) +{ + struct device_node *next = NULL; + unsigned long flags; + struct device_node *node; + + if (!prev) + node = of_find_node_by_path("/cpus"); + + raw_spin_lock_irqsave(&devtree_lock, flags); + if (prev) + next = prev->sibling; + else if (node) { + next = node->child; + of_node_put(node); + } + for (; next; next = next->sibling) { + if (!(of_node_name_eq(next, "cpu") || + (next->type && !of_node_cmp(next->type, "cpu")))) + continue; + if (!__of_device_is_available(next)) + continue; + if (of_node_get(next)) + break; + } + of_node_put(prev); + raw_spin_unlock_irqrestore(&devtree_lock, flags); + return next; +} +EXPORT_SYMBOL(of_get_next_cpu_node); + /** * of_get_compatible_child - Find compatible child node * @parent: parent node diff --git a/include/linux/of.h b/include/linux/of.h index 99b0ebf49632..1aca0dbd35df 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -353,6 +353,8 @@ extern const void *of_get_property(const struct device_node *node, const char *name, int *lenp); extern struct device_node *of_get_cpu_node(int cpu, unsigned int *thread); +extern struct device_node *of_get_next_cpu_node(struct device_node *prev); + #define for_each_property_of_node(dn, pp) \ for (pp = dn->properties; pp != NULL; pp = pp->next) @@ -754,6 +756,11 @@ static inline struct device_node *of_get_cpu_node(int cpu, return NULL; } +static inline struct device_node *of_get_next_cpu_node(struct device_node *prev) +{ + return NULL; +} + static inline int of_n_addr_cells(struct device_node *np) { return 0; @@ -1217,6 +1224,10 @@ static inline int of_property_read_s32(const struct device_node *np, for (child = of_get_next_available_child(parent, NULL); child != NULL; \ child = of_get_next_available_child(parent, child)) +#define for_each_of_cpu_node(cpu) \ + for (cpu = of_get_next_cpu_node(NULL); cpu != NULL; \ + cpu = of_get_next_cpu_node(cpu)) + #define for_each_node_with_property(dn, prop_name) \ for (dn = of_find_node_with_property(NULL, prop_name); dn; \ dn = of_find_node_with_property(dn, prop_name)) -- cgit v1.2.3 From 9dc6edcf676fe188430e8b119f91280bbf285163 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 22 Aug 2018 14:24:16 -0400 Subject: SUNRPC: Clean up initialisation of the struct rpc_rqst Move the initialisation back into xprt.c. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 - net/sunrpc/clnt.c | 1 - net/sunrpc/xprt.c | 91 +++++++++++++++++++++++++-------------------- 3 files changed, 51 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 336fd1a19cca..3d80524e92d6 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -325,7 +325,6 @@ struct xprt_class { struct rpc_xprt *xprt_create_transport(struct xprt_create *args); void xprt_connect(struct rpc_task *task); void xprt_reserve(struct rpc_task *task); -void xprt_request_init(struct rpc_task *task); void xprt_retry_reserve(struct rpc_task *task); int xprt_reserve_xprt(struct rpc_xprt *xprt, struct rpc_task *task); int xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 8ea2f5fadd96..bc9d020bf71f 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1558,7 +1558,6 @@ call_reserveresult(struct rpc_task *task) task->tk_status = 0; if (status >= 0) { if (task->tk_rqstp) { - xprt_request_init(task); task->tk_action = call_refresh; return; } diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index a8db2e3f8904..6aa09edc9567 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1250,6 +1250,55 @@ void xprt_free(struct rpc_xprt *xprt) } EXPORT_SYMBOL_GPL(xprt_free); +static __be32 +xprt_alloc_xid(struct rpc_xprt *xprt) +{ + __be32 xid; + + spin_lock(&xprt->reserve_lock); + xid = (__force __be32)xprt->xid++; + spin_unlock(&xprt->reserve_lock); + return xid; +} + +static void +xprt_init_xid(struct rpc_xprt *xprt) +{ + xprt->xid = prandom_u32(); +} + +static void +xprt_request_init(struct rpc_task *task) +{ + struct rpc_xprt *xprt = task->tk_xprt; + struct rpc_rqst *req = task->tk_rqstp; + + INIT_LIST_HEAD(&req->rq_list); + req->rq_timeout = task->tk_client->cl_timeout->to_initval; + req->rq_task = task; + req->rq_xprt = xprt; + req->rq_buffer = NULL; + req->rq_xid = xprt_alloc_xid(xprt); + req->rq_connect_cookie = xprt->connect_cookie - 1; + req->rq_bytes_sent = 0; + req->rq_snd_buf.len = 0; + req->rq_snd_buf.buflen = 0; + req->rq_rcv_buf.len = 0; + req->rq_rcv_buf.buflen = 0; + req->rq_release_snd_buf = NULL; + xprt_reset_majortimeo(req); + dprintk("RPC: %5u reserved req %p xid %08x\n", task->tk_pid, + req, ntohl(req->rq_xid)); +} + +static void +xprt_do_reserve(struct rpc_xprt *xprt, struct rpc_task *task) +{ + xprt->ops->alloc_slot(xprt, task); + if (task->tk_rqstp != NULL) + xprt_request_init(task); +} + /** * xprt_reserve - allocate an RPC request slot * @task: RPC task requesting a slot allocation @@ -1269,7 +1318,7 @@ void xprt_reserve(struct rpc_task *task) task->tk_timeout = 0; task->tk_status = -EAGAIN; if (!xprt_throttle_congested(xprt, task)) - xprt->ops->alloc_slot(xprt, task); + xprt_do_reserve(xprt, task); } /** @@ -1291,45 +1340,7 @@ void xprt_retry_reserve(struct rpc_task *task) task->tk_timeout = 0; task->tk_status = -EAGAIN; - xprt->ops->alloc_slot(xprt, task); -} - -static inline __be32 xprt_alloc_xid(struct rpc_xprt *xprt) -{ - __be32 xid; - - spin_lock(&xprt->reserve_lock); - xid = (__force __be32)xprt->xid++; - spin_unlock(&xprt->reserve_lock); - return xid; -} - -static inline void xprt_init_xid(struct rpc_xprt *xprt) -{ - xprt->xid = prandom_u32(); -} - -void xprt_request_init(struct rpc_task *task) -{ - struct rpc_xprt *xprt = task->tk_xprt; - struct rpc_rqst *req = task->tk_rqstp; - - INIT_LIST_HEAD(&req->rq_list); - req->rq_timeout = task->tk_client->cl_timeout->to_initval; - req->rq_task = task; - req->rq_xprt = xprt; - req->rq_buffer = NULL; - req->rq_xid = xprt_alloc_xid(xprt); - req->rq_connect_cookie = xprt->connect_cookie - 1; - req->rq_bytes_sent = 0; - req->rq_snd_buf.len = 0; - req->rq_snd_buf.buflen = 0; - req->rq_rcv_buf.len = 0; - req->rq_rcv_buf.buflen = 0; - req->rq_release_snd_buf = NULL; - xprt_reset_majortimeo(req); - dprintk("RPC: %5u reserved req %p xid %08x\n", task->tk_pid, - req, ntohl(req->rq_xid)); + xprt_do_reserve(xprt, task); } /** -- cgit v1.2.3 From 3021a5bbbf0aa0252f2993b84ee903a0eca0b690 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 14 Aug 2018 13:50:21 -0400 Subject: SUNRPC: The transmitted message must lie in the RPCSEC window of validity If a message has been encoded using RPCSEC_GSS, the server is maintaining a window of sequence numbers that it considers valid. The client should normally be tracking that window, and needs to verify that the sequence number used by the message being transmitted still lies inside the window of validity. So far, we've been able to assume this condition would be realised automatically, since the client has been encoding the message only after taking the socket lock. Once we change that condition, we will need the explicit check. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/auth.h | 2 ++ include/linux/sunrpc/auth_gss.h | 1 + net/sunrpc/auth.c | 10 ++++++++++ net/sunrpc/auth_gss/auth_gss.c | 41 +++++++++++++++++++++++++++++++++++++++++ net/sunrpc/clnt.c | 3 +++ net/sunrpc/xprt.c | 7 +++++++ 6 files changed, 64 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index 58a6765c1c5e..2c97a3933ef9 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -157,6 +157,7 @@ struct rpc_credops { int (*crkey_timeout)(struct rpc_cred *); bool (*crkey_to_expire)(struct rpc_cred *); char * (*crstringify_acceptor)(struct rpc_cred *); + bool (*crneed_reencode)(struct rpc_task *); }; extern const struct rpc_authops authunix_ops; @@ -192,6 +193,7 @@ __be32 * rpcauth_marshcred(struct rpc_task *, __be32 *); __be32 * rpcauth_checkverf(struct rpc_task *, __be32 *); int rpcauth_wrap_req(struct rpc_task *task, kxdreproc_t encode, void *rqstp, __be32 *data, void *obj); int rpcauth_unwrap_resp(struct rpc_task *task, kxdrdproc_t decode, void *rqstp, __be32 *data, void *obj); +bool rpcauth_xmit_need_reencode(struct rpc_task *task); int rpcauth_refreshcred(struct rpc_task *); void rpcauth_invalcred(struct rpc_task *); int rpcauth_uptodatecred(struct rpc_task *); diff --git a/include/linux/sunrpc/auth_gss.h b/include/linux/sunrpc/auth_gss.h index 0c9eac351aab..30427b729070 100644 --- a/include/linux/sunrpc/auth_gss.h +++ b/include/linux/sunrpc/auth_gss.h @@ -70,6 +70,7 @@ struct gss_cl_ctx { refcount_t count; enum rpc_gss_proc gc_proc; u32 gc_seq; + u32 gc_seq_xmit; spinlock_t gc_seq_lock; struct gss_ctx *gc_gss_ctx; struct xdr_netobj gc_wire_ctx; diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index 305ecea92170..59df5cdba0ac 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -817,6 +817,16 @@ rpcauth_unwrap_resp(struct rpc_task *task, kxdrdproc_t decode, void *rqstp, return rpcauth_unwrap_req_decode(decode, rqstp, data, obj); } +bool +rpcauth_xmit_need_reencode(struct rpc_task *task) +{ + struct rpc_cred *cred = task->tk_rqstp->rq_cred; + + if (!cred || !cred->cr_ops->crneed_reencode) + return false; + return cred->cr_ops->crneed_reencode(task); +} + int rpcauth_refreshcred(struct rpc_task *task) { diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 21c0aa0a0d1d..c898a7c75e84 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -1984,6 +1984,46 @@ gss_unwrap_req_decode(kxdrdproc_t decode, struct rpc_rqst *rqstp, return decode(rqstp, &xdr, obj); } +static bool +gss_seq_is_newer(u32 new, u32 old) +{ + return (s32)(new - old) > 0; +} + +static bool +gss_xmit_need_reencode(struct rpc_task *task) +{ + struct rpc_rqst *req = task->tk_rqstp; + struct rpc_cred *cred = req->rq_cred; + struct gss_cl_ctx *ctx = gss_cred_get_ctx(cred); + u32 win, seq_xmit; + bool ret = true; + + if (!ctx) + return true; + + if (gss_seq_is_newer(req->rq_seqno, READ_ONCE(ctx->gc_seq))) + goto out; + + seq_xmit = READ_ONCE(ctx->gc_seq_xmit); + while (gss_seq_is_newer(req->rq_seqno, seq_xmit)) { + u32 tmp = seq_xmit; + + seq_xmit = cmpxchg(&ctx->gc_seq_xmit, tmp, req->rq_seqno); + if (seq_xmit == tmp) { + ret = false; + goto out; + } + } + + win = ctx->gc_win; + if (win > 0) + ret = !gss_seq_is_newer(req->rq_seqno, seq_xmit - win); +out: + gss_put_ctx(ctx); + return ret; +} + static int gss_unwrap_resp(struct rpc_task *task, kxdrdproc_t decode, void *rqstp, __be32 *p, void *obj) @@ -2052,6 +2092,7 @@ static const struct rpc_credops gss_credops = { .crunwrap_resp = gss_unwrap_resp, .crkey_timeout = gss_key_timeout, .crstringify_acceptor = gss_stringify_acceptor, + .crneed_reencode = gss_xmit_need_reencode, }; static const struct rpc_credops gss_nullops = { diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 4f1ec8013332..d41b5ac1d4e8 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -2184,6 +2184,9 @@ call_status(struct rpc_task *task) /* shutdown or soft timeout */ rpc_exit(task, status); break; + case -EBADMSG: + task->tk_action = call_transmit; + break; default: if (clnt->cl_chatty) printk("%s: RPC call returned error %d\n", diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 6aa09edc9567..3973e10ea2bd 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1014,6 +1014,13 @@ void xprt_transmit(struct rpc_task *task) dprintk("RPC: %5u xprt_transmit(%u)\n", task->tk_pid, req->rq_slen); if (!req->rq_reply_bytes_recvd) { + + /* Verify that our message lies in the RPCSEC_GSS window */ + if (!req->rq_bytes_sent && rpcauth_xmit_need_reencode(task)) { + task->tk_status = -EBADMSG; + return; + } + if (list_empty(&req->rq_list) && rpc_reply_expected(task)) { /* * Add to the list only if we're expecting a reply -- cgit v1.2.3 From 7ebbbc6e7bd023903daa5bd95726edf2d60b559c Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 28 Aug 2018 09:00:27 -0400 Subject: SUNRPC: Simplify identification of when the message send/receive is complete Add states to indicate that the message send and receive are not yet complete. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/sched.h | 6 ++++-- net/sunrpc/clnt.c | 19 +++++++------------ net/sunrpc/xprt.c | 17 ++++++++++++++--- 3 files changed, 25 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 592653becd91..9e655df70131 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -140,8 +140,10 @@ struct rpc_task_setup { #define RPC_TASK_RUNNING 0 #define RPC_TASK_QUEUED 1 #define RPC_TASK_ACTIVE 2 -#define RPC_TASK_MSG_RECV 3 -#define RPC_TASK_MSG_RECV_WAIT 4 +#define RPC_TASK_NEED_XMIT 3 +#define RPC_TASK_NEED_RECV 4 +#define RPC_TASK_MSG_RECV 5 +#define RPC_TASK_MSG_RECV_WAIT 6 #define RPC_IS_RUNNING(t) test_bit(RPC_TASK_RUNNING, &(t)->tk_runstate) #define rpc_set_running(t) set_bit(RPC_TASK_RUNNING, &(t)->tk_runstate) diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index d41b5ac1d4e8..e5ac35e803ad 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1156,6 +1156,7 @@ struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req) */ xbufp->len = xbufp->head[0].iov_len + xbufp->page_len + xbufp->tail[0].iov_len; + set_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate); task->tk_action = call_bc_transmit; atomic_inc(&task->tk_count); @@ -1720,17 +1721,10 @@ call_allocate(struct rpc_task *task) rpc_exit(task, -ERESTARTSYS); } -static inline int +static int rpc_task_need_encode(struct rpc_task *task) { - return task->tk_rqstp->rq_snd_buf.len == 0; -} - -static inline void -rpc_task_force_reencode(struct rpc_task *task) -{ - task->tk_rqstp->rq_snd_buf.len = 0; - task->tk_rqstp->rq_bytes_sent = 0; + return test_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate) == 0; } /* @@ -1765,6 +1759,8 @@ rpc_xdr_encode(struct rpc_task *task) task->tk_status = rpcauth_wrap_req(task, encode, req, p, task->tk_msg.rpc_argp); + if (task->tk_status == 0) + set_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate); } /* @@ -1999,7 +1995,6 @@ call_transmit_status(struct rpc_task *task) */ if (task->tk_status == 0) { xprt_end_transmit(task); - rpc_task_force_reencode(task); return; } @@ -2010,7 +2005,6 @@ call_transmit_status(struct rpc_task *task) default: dprint_status(task); xprt_end_transmit(task); - rpc_task_force_reencode(task); break; /* * Special cases: if we've been waiting on the @@ -2038,7 +2032,7 @@ call_transmit_status(struct rpc_task *task) case -EADDRINUSE: case -ENOTCONN: case -EPIPE: - rpc_task_force_reencode(task); + break; } } @@ -2185,6 +2179,7 @@ call_status(struct rpc_task *task) rpc_exit(task, status); break; case -EBADMSG: + clear_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate); task->tk_action = call_transmit; break; default: diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 3973e10ea2bd..45d580cd93ac 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -936,10 +936,18 @@ void xprt_complete_rqst(struct rpc_task *task, int copied) /* req->rq_reply_bytes_recvd */ smp_wmb(); req->rq_reply_bytes_recvd = copied; + clear_bit(RPC_TASK_NEED_RECV, &task->tk_runstate); rpc_wake_up_queued_task(&xprt->pending, task); } EXPORT_SYMBOL_GPL(xprt_complete_rqst); +static bool +xprt_request_data_received(struct rpc_task *task) +{ + return !test_bit(RPC_TASK_NEED_RECV, &task->tk_runstate) && + task->tk_rqstp->rq_reply_bytes_recvd != 0; +} + static void xprt_timer(struct rpc_task *task) { struct rpc_rqst *req = task->tk_rqstp; @@ -1031,12 +1039,13 @@ void xprt_transmit(struct rpc_task *task) /* Add request to the receive list */ spin_lock(&xprt->recv_lock); list_add_tail(&req->rq_list, &xprt->recv); + set_bit(RPC_TASK_NEED_RECV, &task->tk_runstate); spin_unlock(&xprt->recv_lock); xprt_reset_majortimeo(req); /* Turn off autodisconnect */ del_singleshot_timer_sync(&xprt->timer); } - } else if (!req->rq_bytes_sent) + } else if (xprt_request_data_received(task) && !req->rq_bytes_sent) return; connect_cookie = xprt->connect_cookie; @@ -1046,9 +1055,11 @@ void xprt_transmit(struct rpc_task *task) task->tk_status = status; return; } + xprt_inject_disconnect(xprt); dprintk("RPC: %5u xmit complete\n", task->tk_pid); + clear_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate); task->tk_flags |= RPC_TASK_SENT; spin_lock_bh(&xprt->transport_lock); @@ -1062,14 +1073,14 @@ void xprt_transmit(struct rpc_task *task) spin_unlock_bh(&xprt->transport_lock); req->rq_connect_cookie = connect_cookie; - if (rpc_reply_expected(task) && !READ_ONCE(req->rq_reply_bytes_recvd)) { + if (test_bit(RPC_TASK_NEED_RECV, &task->tk_runstate)) { /* * Sleep on the pending queue if we're expecting a reply. * The spinlock ensures atomicity between the test of * req->rq_reply_bytes_recvd, and the call to rpc_sleep_on(). */ spin_lock(&xprt->recv_lock); - if (!req->rq_reply_bytes_recvd) { + if (test_bit(RPC_TASK_NEED_RECV, &task->tk_runstate)) { rpc_sleep_on(&xprt->pending, task, xprt_timer); /* * Send an extra queue wakeup call if the -- cgit v1.2.3 From d1109aa56c71e19fc117e75bff11384fc7279a3b Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 13 Aug 2018 15:48:42 -0400 Subject: SUNRPC: Rename TCP receive-specific state variables Since we will want to introduce similar TCP state variables for the transmission of requests, let's rename the existing ones to label that they are for the receive side. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprtsock.h | 16 ++-- include/trace/events/sunrpc.h | 10 +-- net/sunrpc/xprtsock.c | 178 ++++++++++++++++++++-------------------- 3 files changed, 103 insertions(+), 101 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h index ae0f99b9b965..90d5ca8e65f4 100644 --- a/include/linux/sunrpc/xprtsock.h +++ b/include/linux/sunrpc/xprtsock.h @@ -30,15 +30,17 @@ struct sock_xprt { /* * State of TCP reply receive */ - __be32 tcp_fraghdr, - tcp_xid, - tcp_calldir; + struct { + __be32 fraghdr, + xid, + calldir; - u32 tcp_offset, - tcp_reclen; + u32 offset, + len; - unsigned long tcp_copied, - tcp_flags; + unsigned long copied, + flags; + } recv; /* * Connection of transports diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index bbb08a3ef5cc..0aa347194e0f 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -525,11 +525,11 @@ TRACE_EVENT(xs_tcp_data_recv, TP_fast_assign( __assign_str(addr, xs->xprt.address_strings[RPC_DISPLAY_ADDR]); __assign_str(port, xs->xprt.address_strings[RPC_DISPLAY_PORT]); - __entry->xid = be32_to_cpu(xs->tcp_xid); - __entry->flags = xs->tcp_flags; - __entry->copied = xs->tcp_copied; - __entry->reclen = xs->tcp_reclen; - __entry->offset = xs->tcp_offset; + __entry->xid = be32_to_cpu(xs->recv.xid); + __entry->flags = xs->recv.flags; + __entry->copied = xs->recv.copied; + __entry->reclen = xs->recv.len; + __entry->offset = xs->recv.offset; ), TP_printk("peer=[%s]:%s xid=0x%08x flags=%s copied=%lu reclen=%u offset=%lu", diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 6b7539c0466e..cd7d093721ae 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1169,42 +1169,42 @@ static inline void xs_tcp_read_fraghdr(struct rpc_xprt *xprt, struct xdr_skb_rea size_t len, used; char *p; - p = ((char *) &transport->tcp_fraghdr) + transport->tcp_offset; - len = sizeof(transport->tcp_fraghdr) - transport->tcp_offset; + p = ((char *) &transport->recv.fraghdr) + transport->recv.offset; + len = sizeof(transport->recv.fraghdr) - transport->recv.offset; used = xdr_skb_read_bits(desc, p, len); - transport->tcp_offset += used; + transport->recv.offset += used; if (used != len) return; - transport->tcp_reclen = ntohl(transport->tcp_fraghdr); - if (transport->tcp_reclen & RPC_LAST_STREAM_FRAGMENT) - transport->tcp_flags |= TCP_RCV_LAST_FRAG; + transport->recv.len = ntohl(transport->recv.fraghdr); + if (transport->recv.len & RPC_LAST_STREAM_FRAGMENT) + transport->recv.flags |= TCP_RCV_LAST_FRAG; else - transport->tcp_flags &= ~TCP_RCV_LAST_FRAG; - transport->tcp_reclen &= RPC_FRAGMENT_SIZE_MASK; + transport->recv.flags &= ~TCP_RCV_LAST_FRAG; + transport->recv.len &= RPC_FRAGMENT_SIZE_MASK; - transport->tcp_flags &= ~TCP_RCV_COPY_FRAGHDR; - transport->tcp_offset = 0; + transport->recv.flags &= ~TCP_RCV_COPY_FRAGHDR; + transport->recv.offset = 0; /* Sanity check of the record length */ - if (unlikely(transport->tcp_reclen < 8)) { + if (unlikely(transport->recv.len < 8)) { dprintk("RPC: invalid TCP record fragment length\n"); xs_tcp_force_close(xprt); return; } dprintk("RPC: reading TCP record fragment of length %d\n", - transport->tcp_reclen); + transport->recv.len); } static void xs_tcp_check_fraghdr(struct sock_xprt *transport) { - if (transport->tcp_offset == transport->tcp_reclen) { - transport->tcp_flags |= TCP_RCV_COPY_FRAGHDR; - transport->tcp_offset = 0; - if (transport->tcp_flags & TCP_RCV_LAST_FRAG) { - transport->tcp_flags &= ~TCP_RCV_COPY_DATA; - transport->tcp_flags |= TCP_RCV_COPY_XID; - transport->tcp_copied = 0; + if (transport->recv.offset == transport->recv.len) { + transport->recv.flags |= TCP_RCV_COPY_FRAGHDR; + transport->recv.offset = 0; + if (transport->recv.flags & TCP_RCV_LAST_FRAG) { + transport->recv.flags &= ~TCP_RCV_COPY_DATA; + transport->recv.flags |= TCP_RCV_COPY_XID; + transport->recv.copied = 0; } } } @@ -1214,20 +1214,20 @@ static inline void xs_tcp_read_xid(struct sock_xprt *transport, struct xdr_skb_r size_t len, used; char *p; - len = sizeof(transport->tcp_xid) - transport->tcp_offset; + len = sizeof(transport->recv.xid) - transport->recv.offset; dprintk("RPC: reading XID (%zu bytes)\n", len); - p = ((char *) &transport->tcp_xid) + transport->tcp_offset; + p = ((char *) &transport->recv.xid) + transport->recv.offset; used = xdr_skb_read_bits(desc, p, len); - transport->tcp_offset += used; + transport->recv.offset += used; if (used != len) return; - transport->tcp_flags &= ~TCP_RCV_COPY_XID; - transport->tcp_flags |= TCP_RCV_READ_CALLDIR; - transport->tcp_copied = 4; + transport->recv.flags &= ~TCP_RCV_COPY_XID; + transport->recv.flags |= TCP_RCV_READ_CALLDIR; + transport->recv.copied = 4; dprintk("RPC: reading %s XID %08x\n", - (transport->tcp_flags & TCP_RPC_REPLY) ? "reply for" + (transport->recv.flags & TCP_RPC_REPLY) ? "reply for" : "request with", - ntohl(transport->tcp_xid)); + ntohl(transport->recv.xid)); xs_tcp_check_fraghdr(transport); } @@ -1239,34 +1239,34 @@ static inline void xs_tcp_read_calldir(struct sock_xprt *transport, char *p; /* - * We want transport->tcp_offset to be 8 at the end of this routine + * We want transport->recv.offset to be 8 at the end of this routine * (4 bytes for the xid and 4 bytes for the call/reply flag). * When this function is called for the first time, - * transport->tcp_offset is 4 (after having already read the xid). + * transport->recv.offset is 4 (after having already read the xid). */ - offset = transport->tcp_offset - sizeof(transport->tcp_xid); - len = sizeof(transport->tcp_calldir) - offset; + offset = transport->recv.offset - sizeof(transport->recv.xid); + len = sizeof(transport->recv.calldir) - offset; dprintk("RPC: reading CALL/REPLY flag (%zu bytes)\n", len); - p = ((char *) &transport->tcp_calldir) + offset; + p = ((char *) &transport->recv.calldir) + offset; used = xdr_skb_read_bits(desc, p, len); - transport->tcp_offset += used; + transport->recv.offset += used; if (used != len) return; - transport->tcp_flags &= ~TCP_RCV_READ_CALLDIR; + transport->recv.flags &= ~TCP_RCV_READ_CALLDIR; /* * We don't yet have the XDR buffer, so we will write the calldir * out after we get the buffer from the 'struct rpc_rqst' */ - switch (ntohl(transport->tcp_calldir)) { + switch (ntohl(transport->recv.calldir)) { case RPC_REPLY: - transport->tcp_flags |= TCP_RCV_COPY_CALLDIR; - transport->tcp_flags |= TCP_RCV_COPY_DATA; - transport->tcp_flags |= TCP_RPC_REPLY; + transport->recv.flags |= TCP_RCV_COPY_CALLDIR; + transport->recv.flags |= TCP_RCV_COPY_DATA; + transport->recv.flags |= TCP_RPC_REPLY; break; case RPC_CALL: - transport->tcp_flags |= TCP_RCV_COPY_CALLDIR; - transport->tcp_flags |= TCP_RCV_COPY_DATA; - transport->tcp_flags &= ~TCP_RPC_REPLY; + transport->recv.flags |= TCP_RCV_COPY_CALLDIR; + transport->recv.flags |= TCP_RCV_COPY_DATA; + transport->recv.flags &= ~TCP_RPC_REPLY; break; default: dprintk("RPC: invalid request message type\n"); @@ -1287,21 +1287,21 @@ static inline void xs_tcp_read_common(struct rpc_xprt *xprt, rcvbuf = &req->rq_private_buf; - if (transport->tcp_flags & TCP_RCV_COPY_CALLDIR) { + if (transport->recv.flags & TCP_RCV_COPY_CALLDIR) { /* * Save the RPC direction in the XDR buffer */ - memcpy(rcvbuf->head[0].iov_base + transport->tcp_copied, - &transport->tcp_calldir, - sizeof(transport->tcp_calldir)); - transport->tcp_copied += sizeof(transport->tcp_calldir); - transport->tcp_flags &= ~TCP_RCV_COPY_CALLDIR; + memcpy(rcvbuf->head[0].iov_base + transport->recv.copied, + &transport->recv.calldir, + sizeof(transport->recv.calldir)); + transport->recv.copied += sizeof(transport->recv.calldir); + transport->recv.flags &= ~TCP_RCV_COPY_CALLDIR; } len = desc->count; - if (len > transport->tcp_reclen - transport->tcp_offset) - desc->count = transport->tcp_reclen - transport->tcp_offset; - r = xdr_partial_copy_from_skb(rcvbuf, transport->tcp_copied, + if (len > transport->recv.len - transport->recv.offset) + desc->count = transport->recv.len - transport->recv.offset; + r = xdr_partial_copy_from_skb(rcvbuf, transport->recv.copied, desc, xdr_skb_read_bits); if (desc->count) { @@ -1314,31 +1314,31 @@ static inline void xs_tcp_read_common(struct rpc_xprt *xprt, * Any remaining data from this record will * be discarded. */ - transport->tcp_flags &= ~TCP_RCV_COPY_DATA; + transport->recv.flags &= ~TCP_RCV_COPY_DATA; dprintk("RPC: XID %08x truncated request\n", - ntohl(transport->tcp_xid)); - dprintk("RPC: xprt = %p, tcp_copied = %lu, " - "tcp_offset = %u, tcp_reclen = %u\n", - xprt, transport->tcp_copied, - transport->tcp_offset, transport->tcp_reclen); + ntohl(transport->recv.xid)); + dprintk("RPC: xprt = %p, recv.copied = %lu, " + "recv.offset = %u, recv.len = %u\n", + xprt, transport->recv.copied, + transport->recv.offset, transport->recv.len); return; } - transport->tcp_copied += r; - transport->tcp_offset += r; + transport->recv.copied += r; + transport->recv.offset += r; desc->count = len - r; dprintk("RPC: XID %08x read %zd bytes\n", - ntohl(transport->tcp_xid), r); - dprintk("RPC: xprt = %p, tcp_copied = %lu, tcp_offset = %u, " - "tcp_reclen = %u\n", xprt, transport->tcp_copied, - transport->tcp_offset, transport->tcp_reclen); - - if (transport->tcp_copied == req->rq_private_buf.buflen) - transport->tcp_flags &= ~TCP_RCV_COPY_DATA; - else if (transport->tcp_offset == transport->tcp_reclen) { - if (transport->tcp_flags & TCP_RCV_LAST_FRAG) - transport->tcp_flags &= ~TCP_RCV_COPY_DATA; + ntohl(transport->recv.xid), r); + dprintk("RPC: xprt = %p, recv.copied = %lu, recv.offset = %u, " + "recv.len = %u\n", xprt, transport->recv.copied, + transport->recv.offset, transport->recv.len); + + if (transport->recv.copied == req->rq_private_buf.buflen) + transport->recv.flags &= ~TCP_RCV_COPY_DATA; + else if (transport->recv.offset == transport->recv.len) { + if (transport->recv.flags & TCP_RCV_LAST_FRAG) + transport->recv.flags &= ~TCP_RCV_COPY_DATA; } } @@ -1353,14 +1353,14 @@ static inline int xs_tcp_read_reply(struct rpc_xprt *xprt, container_of(xprt, struct sock_xprt, xprt); struct rpc_rqst *req; - dprintk("RPC: read reply XID %08x\n", ntohl(transport->tcp_xid)); + dprintk("RPC: read reply XID %08x\n", ntohl(transport->recv.xid)); /* Find and lock the request corresponding to this xid */ spin_lock(&xprt->recv_lock); - req = xprt_lookup_rqst(xprt, transport->tcp_xid); + req = xprt_lookup_rqst(xprt, transport->recv.xid); if (!req) { dprintk("RPC: XID %08x request not found!\n", - ntohl(transport->tcp_xid)); + ntohl(transport->recv.xid)); spin_unlock(&xprt->recv_lock); return -1; } @@ -1370,8 +1370,8 @@ static inline int xs_tcp_read_reply(struct rpc_xprt *xprt, xs_tcp_read_common(xprt, desc, req); spin_lock(&xprt->recv_lock); - if (!(transport->tcp_flags & TCP_RCV_COPY_DATA)) - xprt_complete_rqst(req->rq_task, transport->tcp_copied); + if (!(transport->recv.flags & TCP_RCV_COPY_DATA)) + xprt_complete_rqst(req->rq_task, transport->recv.copied); xprt_unpin_rqst(req); spin_unlock(&xprt->recv_lock); return 0; @@ -1393,7 +1393,7 @@ static int xs_tcp_read_callback(struct rpc_xprt *xprt, struct rpc_rqst *req; /* Look up the request corresponding to the given XID */ - req = xprt_lookup_bc_request(xprt, transport->tcp_xid); + req = xprt_lookup_bc_request(xprt, transport->recv.xid); if (req == NULL) { printk(KERN_WARNING "Callback slot table overflowed\n"); xprt_force_disconnect(xprt); @@ -1403,8 +1403,8 @@ static int xs_tcp_read_callback(struct rpc_xprt *xprt, dprintk("RPC: read callback XID %08x\n", ntohl(req->rq_xid)); xs_tcp_read_common(xprt, desc, req); - if (!(transport->tcp_flags & TCP_RCV_COPY_DATA)) - xprt_complete_bc_request(req, transport->tcp_copied); + if (!(transport->recv.flags & TCP_RCV_COPY_DATA)) + xprt_complete_bc_request(req, transport->recv.copied); return 0; } @@ -1415,7 +1415,7 @@ static inline int _xs_tcp_read_data(struct rpc_xprt *xprt, struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); - return (transport->tcp_flags & TCP_RPC_REPLY) ? + return (transport->recv.flags & TCP_RPC_REPLY) ? xs_tcp_read_reply(xprt, desc) : xs_tcp_read_callback(xprt, desc); } @@ -1458,9 +1458,9 @@ static void xs_tcp_read_data(struct rpc_xprt *xprt, else { /* * The transport_lock protects the request handling. - * There's no need to hold it to update the tcp_flags. + * There's no need to hold it to update the recv.flags. */ - transport->tcp_flags &= ~TCP_RCV_COPY_DATA; + transport->recv.flags &= ~TCP_RCV_COPY_DATA; } } @@ -1468,12 +1468,12 @@ static inline void xs_tcp_read_discard(struct sock_xprt *transport, struct xdr_s { size_t len; - len = transport->tcp_reclen - transport->tcp_offset; + len = transport->recv.len - transport->recv.offset; if (len > desc->count) len = desc->count; desc->count -= len; desc->offset += len; - transport->tcp_offset += len; + transport->recv.offset += len; dprintk("RPC: discarded %zu bytes\n", len); xs_tcp_check_fraghdr(transport); } @@ -1494,22 +1494,22 @@ static int xs_tcp_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, uns trace_xs_tcp_data_recv(transport); /* Read in a new fragment marker if necessary */ /* Can we ever really expect to get completely empty fragments? */ - if (transport->tcp_flags & TCP_RCV_COPY_FRAGHDR) { + if (transport->recv.flags & TCP_RCV_COPY_FRAGHDR) { xs_tcp_read_fraghdr(xprt, &desc); continue; } /* Read in the xid if necessary */ - if (transport->tcp_flags & TCP_RCV_COPY_XID) { + if (transport->recv.flags & TCP_RCV_COPY_XID) { xs_tcp_read_xid(transport, &desc); continue; } /* Read in the call/reply flag */ - if (transport->tcp_flags & TCP_RCV_READ_CALLDIR) { + if (transport->recv.flags & TCP_RCV_READ_CALLDIR) { xs_tcp_read_calldir(transport, &desc); continue; } /* Read in the request data */ - if (transport->tcp_flags & TCP_RCV_COPY_DATA) { + if (transport->recv.flags & TCP_RCV_COPY_DATA) { xs_tcp_read_data(xprt, &desc); continue; } @@ -1602,10 +1602,10 @@ static void xs_tcp_state_change(struct sock *sk) if (!xprt_test_and_set_connected(xprt)) { /* Reset TCP record info */ - transport->tcp_offset = 0; - transport->tcp_reclen = 0; - transport->tcp_copied = 0; - transport->tcp_flags = + transport->recv.offset = 0; + transport->recv.len = 0; + transport->recv.copied = 0; + transport->recv.flags = TCP_RCV_COPY_FRAGHDR | TCP_RCV_COPY_XID; xprt->connect_cookie++; clear_bit(XPRT_SOCK_CONNECTING, &transport->sock_state); -- cgit v1.2.3 From 6c7a64e5a44dbc6d073b83a56a48d0a4099f1dd2 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 13 Aug 2018 16:54:57 -0400 Subject: SUNRPC: Add socket transmit queue offset tracking Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprtsock.h | 7 +++++++ net/sunrpc/xprtsock.c | 40 ++++++++++++++++++++++------------------ 2 files changed, 29 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h index 90d5ca8e65f4..005cfb6e7238 100644 --- a/include/linux/sunrpc/xprtsock.h +++ b/include/linux/sunrpc/xprtsock.h @@ -42,6 +42,13 @@ struct sock_xprt { flags; } recv; + /* + * State of TCP transmit queue + */ + struct { + u32 offset; + } xmit; + /* * Connection of transports */ diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index ec1e3f93e707..629cc45e1e6c 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -461,7 +461,7 @@ static int xs_nospace(struct rpc_task *task) int ret = -EAGAIN; dprintk("RPC: %5u xmit incomplete (%u left of %u)\n", - task->tk_pid, req->rq_slen - req->rq_bytes_sent, + task->tk_pid, req->rq_slen - transport->xmit.offset, req->rq_slen); /* Protect against races with write_space */ @@ -528,19 +528,22 @@ static int xs_local_send_request(struct rpc_task *task) req->rq_svec->iov_base, req->rq_svec->iov_len); req->rq_xtime = ktime_get(); - status = xs_sendpages(transport->sock, NULL, 0, xdr, req->rq_bytes_sent, + status = xs_sendpages(transport->sock, NULL, 0, xdr, + transport->xmit.offset, true, &sent); dprintk("RPC: %s(%u) = %d\n", - __func__, xdr->len - req->rq_bytes_sent, status); + __func__, xdr->len - transport->xmit.offset, status); if (status == -EAGAIN && sock_writeable(transport->inet)) status = -ENOBUFS; if (likely(sent > 0) || status == 0) { - req->rq_bytes_sent += sent; - req->rq_xmit_bytes_sent += sent; + transport->xmit.offset += sent; + req->rq_bytes_sent = transport->xmit.offset; if (likely(req->rq_bytes_sent >= req->rq_slen)) { + req->rq_xmit_bytes_sent += transport->xmit.offset; req->rq_bytes_sent = 0; + transport->xmit.offset = 0; return 0; } status = -EAGAIN; @@ -592,10 +595,10 @@ static int xs_udp_send_request(struct rpc_task *task) return -ENOTCONN; req->rq_xtime = ktime_get(); status = xs_sendpages(transport->sock, xs_addr(xprt), xprt->addrlen, - xdr, req->rq_bytes_sent, true, &sent); + xdr, 0, true, &sent); dprintk("RPC: xs_udp_send_request(%u) = %d\n", - xdr->len - req->rq_bytes_sent, status); + xdr->len, status); /* firewall is blocking us, don't return -EAGAIN or we end up looping */ if (status == -EPERM) @@ -684,17 +687,20 @@ static int xs_tcp_send_request(struct rpc_task *task) while (1) { sent = 0; status = xs_sendpages(transport->sock, NULL, 0, xdr, - req->rq_bytes_sent, zerocopy, &sent); + transport->xmit.offset, + zerocopy, &sent); dprintk("RPC: xs_tcp_send_request(%u) = %d\n", - xdr->len - req->rq_bytes_sent, status); + xdr->len - transport->xmit.offset, status); /* If we've sent the entire packet, immediately * reset the count of bytes sent. */ - req->rq_bytes_sent += sent; - req->rq_xmit_bytes_sent += sent; + transport->xmit.offset += sent; + req->rq_bytes_sent = transport->xmit.offset; if (likely(req->rq_bytes_sent >= req->rq_slen)) { + req->rq_xmit_bytes_sent += transport->xmit.offset; req->rq_bytes_sent = 0; + transport->xmit.offset = 0; return 0; } @@ -760,18 +766,13 @@ static int xs_tcp_send_request(struct rpc_task *task) */ static void xs_tcp_release_xprt(struct rpc_xprt *xprt, struct rpc_task *task) { - struct rpc_rqst *req; + struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); if (task != xprt->snd_task) return; if (task == NULL) goto out_release; - req = task->tk_rqstp; - if (req == NULL) - goto out_release; - if (req->rq_bytes_sent == 0) - goto out_release; - if (req->rq_bytes_sent == req->rq_snd_buf.len) + if (transport->xmit.offset == 0 || !xprt_connected(xprt)) goto out_release; set_bit(XPRT_CLOSE_WAIT, &xprt->state); out_release: @@ -2021,6 +2022,8 @@ static int xs_local_finish_connecting(struct rpc_xprt *xprt, write_unlock_bh(&sk->sk_callback_lock); } + transport->xmit.offset = 0; + /* Tell the socket layer to start connecting... */ xprt->stat.connect_count++; xprt->stat.connect_start = jiffies; @@ -2384,6 +2387,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) transport->recv.len = 0; transport->recv.copied = 0; transport->recv.flags = TCP_RCV_COPY_FRAGHDR | TCP_RCV_COPY_XID; + transport->xmit.offset = 0; /* Tell the socket layer to start connecting... */ xprt->stat.connect_count++; -- cgit v1.2.3 From cf9946cd6144410ced00d52586ff5a2cb4868fc5 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 6 Aug 2018 12:55:34 -0400 Subject: SUNRPC: Refactor the transport request pinning We are going to need to pin for both send and receive. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/sched.h | 3 +-- include/linux/sunrpc/xprt.h | 1 + net/sunrpc/xprt.c | 43 +++++++++++++++++++++++-------------------- 3 files changed, 25 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 9e655df70131..8062ce6b18e5 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -142,8 +142,7 @@ struct rpc_task_setup { #define RPC_TASK_ACTIVE 2 #define RPC_TASK_NEED_XMIT 3 #define RPC_TASK_NEED_RECV 4 -#define RPC_TASK_MSG_RECV 5 -#define RPC_TASK_MSG_RECV_WAIT 6 +#define RPC_TASK_MSG_PIN_WAIT 5 #define RPC_IS_RUNNING(t) test_bit(RPC_TASK_RUNNING, &(t)->tk_runstate) #define rpc_set_running(t) set_bit(RPC_TASK_RUNNING, &(t)->tk_runstate) diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 3d80524e92d6..bd743c51a865 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -103,6 +103,7 @@ struct rpc_rqst { /* A cookie used to track the state of the transport connection */ + atomic_t rq_pin; /* * Partial send handling diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 45d580cd93ac..649a40cfae6d 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -847,16 +847,22 @@ struct rpc_rqst *xprt_lookup_rqst(struct rpc_xprt *xprt, __be32 xid) } EXPORT_SYMBOL_GPL(xprt_lookup_rqst); +static bool +xprt_is_pinned_rqst(struct rpc_rqst *req) +{ + return atomic_read(&req->rq_pin) != 0; +} + /** * xprt_pin_rqst - Pin a request on the transport receive list * @req: Request to pin * * Caller must ensure this is atomic with the call to xprt_lookup_rqst() - * so should be holding the xprt transport lock. + * so should be holding the xprt receive lock. */ void xprt_pin_rqst(struct rpc_rqst *req) { - set_bit(RPC_TASK_MSG_RECV, &req->rq_task->tk_runstate); + atomic_inc(&req->rq_pin); } EXPORT_SYMBOL_GPL(xprt_pin_rqst); @@ -864,31 +870,22 @@ EXPORT_SYMBOL_GPL(xprt_pin_rqst); * xprt_unpin_rqst - Unpin a request on the transport receive list * @req: Request to pin * - * Caller should be holding the xprt transport lock. + * Caller should be holding the xprt receive lock. */ void xprt_unpin_rqst(struct rpc_rqst *req) { - struct rpc_task *task = req->rq_task; - - clear_bit(RPC_TASK_MSG_RECV, &task->tk_runstate); - if (test_bit(RPC_TASK_MSG_RECV_WAIT, &task->tk_runstate)) - wake_up_bit(&task->tk_runstate, RPC_TASK_MSG_RECV); + if (!test_bit(RPC_TASK_MSG_PIN_WAIT, &req->rq_task->tk_runstate)) { + atomic_dec(&req->rq_pin); + return; + } + if (atomic_dec_and_test(&req->rq_pin)) + wake_up_var(&req->rq_pin); } EXPORT_SYMBOL_GPL(xprt_unpin_rqst); static void xprt_wait_on_pinned_rqst(struct rpc_rqst *req) -__must_hold(&req->rq_xprt->recv_lock) { - struct rpc_task *task = req->rq_task; - - if (task && test_bit(RPC_TASK_MSG_RECV, &task->tk_runstate)) { - spin_unlock(&req->rq_xprt->recv_lock); - set_bit(RPC_TASK_MSG_RECV_WAIT, &task->tk_runstate); - wait_on_bit(&task->tk_runstate, RPC_TASK_MSG_RECV, - TASK_UNINTERRUPTIBLE); - clear_bit(RPC_TASK_MSG_RECV_WAIT, &task->tk_runstate); - spin_lock(&req->rq_xprt->recv_lock); - } + wait_var_event(&req->rq_pin, !xprt_is_pinned_rqst(req)); } /** @@ -1388,7 +1385,13 @@ void xprt_release(struct rpc_task *task) spin_lock(&xprt->recv_lock); if (!list_empty(&req->rq_list)) { list_del_init(&req->rq_list); - xprt_wait_on_pinned_rqst(req); + if (xprt_is_pinned_rqst(req)) { + set_bit(RPC_TASK_MSG_PIN_WAIT, &req->rq_task->tk_runstate); + spin_unlock(&xprt->recv_lock); + xprt_wait_on_pinned_rqst(req); + spin_lock(&xprt->recv_lock); + clear_bit(RPC_TASK_MSG_PIN_WAIT, &req->rq_task->tk_runstate); + } } spin_unlock(&xprt->recv_lock); spin_lock_bh(&xprt->transport_lock); -- cgit v1.2.3 From 359c48c04af25397ecefec1ccf200ddd199617ce Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 29 Aug 2018 09:22:28 -0400 Subject: SUNRPC: Add a helper to wake up a sleeping rpc_task and set its status Add a helper that will wake up a task that is sleeping on a specific queue, and will set the value of task->tk_status. This is mainly intended for use by the transport layer to notify the task of an error condition. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/sched.h | 3 ++ net/sunrpc/sched.c | 65 +++++++++++++++++++++++++++++++++++++------- 2 files changed, 58 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 8062ce6b18e5..8840a420cf4c 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -235,6 +235,9 @@ void rpc_wake_up_queued_task_on_wq(struct workqueue_struct *wq, struct rpc_task *task); void rpc_wake_up_queued_task(struct rpc_wait_queue *, struct rpc_task *); +void rpc_wake_up_queued_task_set_status(struct rpc_wait_queue *, + struct rpc_task *, + int); void rpc_wake_up(struct rpc_wait_queue *); struct rpc_task *rpc_wake_up_next(struct rpc_wait_queue *); struct rpc_task *rpc_wake_up_first_on_wq(struct workqueue_struct *wq, diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 3fe5d60ab0e2..dec01bd1b71c 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -440,14 +440,28 @@ static void __rpc_do_wake_up_task_on_wq(struct workqueue_struct *wq, /* * Wake up a queued task while the queue lock is being held */ -static void rpc_wake_up_task_on_wq_queue_locked(struct workqueue_struct *wq, - struct rpc_wait_queue *queue, struct rpc_task *task) +static struct rpc_task * +rpc_wake_up_task_on_wq_queue_action_locked(struct workqueue_struct *wq, + struct rpc_wait_queue *queue, struct rpc_task *task, + bool (*action)(struct rpc_task *, void *), void *data) { if (RPC_IS_QUEUED(task)) { smp_rmb(); - if (task->tk_waitqueue == queue) - __rpc_do_wake_up_task_on_wq(wq, queue, task); + if (task->tk_waitqueue == queue) { + if (action == NULL || action(task, data)) { + __rpc_do_wake_up_task_on_wq(wq, queue, task); + return task; + } + } } + return NULL; +} + +static void +rpc_wake_up_task_on_wq_queue_locked(struct workqueue_struct *wq, + struct rpc_wait_queue *queue, struct rpc_task *task) +{ + rpc_wake_up_task_on_wq_queue_action_locked(wq, queue, task, NULL, NULL); } /* @@ -481,6 +495,40 @@ void rpc_wake_up_queued_task(struct rpc_wait_queue *queue, struct rpc_task *task } EXPORT_SYMBOL_GPL(rpc_wake_up_queued_task); +static bool rpc_task_action_set_status(struct rpc_task *task, void *status) +{ + task->tk_status = *(int *)status; + return true; +} + +static void +rpc_wake_up_task_queue_set_status_locked(struct rpc_wait_queue *queue, + struct rpc_task *task, int status) +{ + rpc_wake_up_task_on_wq_queue_action_locked(rpciod_workqueue, queue, + task, rpc_task_action_set_status, &status); +} + +/** + * rpc_wake_up_queued_task_set_status - wake up a task and set task->tk_status + * @queue: pointer to rpc_wait_queue + * @task: pointer to rpc_task + * @status: integer error value + * + * If @task is queued on @queue, then it is woken up, and @task->tk_status is + * set to the value of @status. + */ +void +rpc_wake_up_queued_task_set_status(struct rpc_wait_queue *queue, + struct rpc_task *task, int status) +{ + if (!RPC_IS_QUEUED(task)) + return; + spin_lock_bh(&queue->lock); + rpc_wake_up_task_queue_set_status_locked(queue, task, status); + spin_unlock_bh(&queue->lock); +} + /* * Wake up the next task on a priority queue. */ @@ -553,12 +601,9 @@ struct rpc_task *rpc_wake_up_first_on_wq(struct workqueue_struct *wq, queue, rpc_qname(queue)); spin_lock_bh(&queue->lock); task = __rpc_find_next_queued(queue); - if (task != NULL) { - if (func(task, data)) - rpc_wake_up_task_on_wq_queue_locked(wq, queue, task); - else - task = NULL; - } + if (task != NULL) + task = rpc_wake_up_task_on_wq_queue_action_locked(wq, queue, + task, func, data); spin_unlock_bh(&queue->lock); return task; -- cgit v1.2.3 From 75c84151a9dc7a755c607e6761d8f14a1690dbf0 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 31 Aug 2018 10:21:00 -0400 Subject: SUNRPC: Rename xprt->recv_lock to xprt->queue_lock We will use the same lock to protect both the transmit and receive queues. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 2 +- net/sunrpc/svcsock.c | 6 +++--- net/sunrpc/xprt.c | 24 ++++++++++++------------ net/sunrpc/xprtrdma/rpc_rdma.c | 10 +++++----- net/sunrpc/xprtrdma/svc_rdma_backchannel.c | 4 ++-- net/sunrpc/xprtsock.c | 30 +++++++++++++++--------------- 6 files changed, 38 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index bd743c51a865..c25d0a5fda69 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -235,7 +235,7 @@ struct rpc_xprt { */ spinlock_t transport_lock; /* lock transport info */ spinlock_t reserve_lock; /* lock slot table */ - spinlock_t recv_lock; /* lock receive list */ + spinlock_t queue_lock; /* send/receive queue lock */ u32 xid; /* Next XID value to use */ struct rpc_task * snd_task; /* Task blocked in send */ struct svc_xprt *bc_xprt; /* NFSv4.1 backchannel */ diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 5445145e639c..db8bb6b3a2b0 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1004,7 +1004,7 @@ static int receive_cb_reply(struct svc_sock *svsk, struct svc_rqst *rqstp) if (!bc_xprt) return -EAGAIN; - spin_lock(&bc_xprt->recv_lock); + spin_lock(&bc_xprt->queue_lock); req = xprt_lookup_rqst(bc_xprt, xid); if (!req) goto unlock_notfound; @@ -1022,7 +1022,7 @@ static int receive_cb_reply(struct svc_sock *svsk, struct svc_rqst *rqstp) memcpy(dst->iov_base, src->iov_base, src->iov_len); xprt_complete_rqst(req->rq_task, rqstp->rq_arg.len); rqstp->rq_arg.len = 0; - spin_unlock(&bc_xprt->recv_lock); + spin_unlock(&bc_xprt->queue_lock); return 0; unlock_notfound: printk(KERN_NOTICE @@ -1031,7 +1031,7 @@ unlock_notfound: __func__, ntohl(calldir), bc_xprt, ntohl(xid)); unlock_eagain: - spin_unlock(&bc_xprt->recv_lock); + spin_unlock(&bc_xprt->queue_lock); return -EAGAIN; } diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 3a3b3445a7c0..6e3d4b4ee79e 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -826,7 +826,7 @@ static void xprt_connect_status(struct rpc_task *task) * @xprt: transport on which the original request was transmitted * @xid: RPC XID of incoming reply * - * Caller holds xprt->recv_lock. + * Caller holds xprt->queue_lock. */ struct rpc_rqst *xprt_lookup_rqst(struct rpc_xprt *xprt, __be32 xid) { @@ -892,7 +892,7 @@ static void xprt_wait_on_pinned_rqst(struct rpc_rqst *req) * xprt_update_rtt - Update RPC RTT statistics * @task: RPC request that recently completed * - * Caller holds xprt->recv_lock. + * Caller holds xprt->queue_lock. */ void xprt_update_rtt(struct rpc_task *task) { @@ -914,7 +914,7 @@ EXPORT_SYMBOL_GPL(xprt_update_rtt); * @task: RPC request that recently completed * @copied: actual number of bytes received from the transport * - * Caller holds xprt->recv_lock. + * Caller holds xprt->queue_lock. */ void xprt_complete_rqst(struct rpc_task *task, int copied) { @@ -1034,10 +1034,10 @@ void xprt_transmit(struct rpc_task *task) memcpy(&req->rq_private_buf, &req->rq_rcv_buf, sizeof(req->rq_private_buf)); /* Add request to the receive list */ - spin_lock(&xprt->recv_lock); + spin_lock(&xprt->queue_lock); list_add_tail(&req->rq_list, &xprt->recv); set_bit(RPC_TASK_NEED_RECV, &task->tk_runstate); - spin_unlock(&xprt->recv_lock); + spin_unlock(&xprt->queue_lock); xprt_reset_majortimeo(req); /* Turn off autodisconnect */ del_singleshot_timer_sync(&xprt->timer); @@ -1076,7 +1076,7 @@ void xprt_transmit(struct rpc_task *task) * The spinlock ensures atomicity between the test of * req->rq_reply_bytes_recvd, and the call to rpc_sleep_on(). */ - spin_lock(&xprt->recv_lock); + spin_lock(&xprt->queue_lock); if (test_bit(RPC_TASK_NEED_RECV, &task->tk_runstate)) { rpc_sleep_on(&xprt->pending, task, xprt_timer); /* Wake up immediately if the connection was dropped */ @@ -1084,7 +1084,7 @@ void xprt_transmit(struct rpc_task *task) rpc_wake_up_queued_task_set_status(&xprt->pending, task, -ENOTCONN); } - spin_unlock(&xprt->recv_lock); + spin_unlock(&xprt->queue_lock); } } @@ -1379,18 +1379,18 @@ void xprt_release(struct rpc_task *task) task->tk_ops->rpc_count_stats(task, task->tk_calldata); else if (task->tk_client) rpc_count_iostats(task, task->tk_client->cl_metrics); - spin_lock(&xprt->recv_lock); + spin_lock(&xprt->queue_lock); if (!list_empty(&req->rq_list)) { list_del_init(&req->rq_list); if (xprt_is_pinned_rqst(req)) { set_bit(RPC_TASK_MSG_PIN_WAIT, &req->rq_task->tk_runstate); - spin_unlock(&xprt->recv_lock); + spin_unlock(&xprt->queue_lock); xprt_wait_on_pinned_rqst(req); - spin_lock(&xprt->recv_lock); + spin_lock(&xprt->queue_lock); clear_bit(RPC_TASK_MSG_PIN_WAIT, &req->rq_task->tk_runstate); } } - spin_unlock(&xprt->recv_lock); + spin_unlock(&xprt->queue_lock); spin_lock_bh(&xprt->transport_lock); xprt->ops->release_xprt(xprt, task); if (xprt->ops->release_request) @@ -1420,7 +1420,7 @@ static void xprt_init(struct rpc_xprt *xprt, struct net *net) spin_lock_init(&xprt->transport_lock); spin_lock_init(&xprt->reserve_lock); - spin_lock_init(&xprt->recv_lock); + spin_lock_init(&xprt->queue_lock); INIT_LIST_HEAD(&xprt->free); INIT_LIST_HEAD(&xprt->recv); diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index c8ae983c6cc0..0020dc401215 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -1238,7 +1238,7 @@ void rpcrdma_complete_rqst(struct rpcrdma_rep *rep) goto out_badheader; out: - spin_lock(&xprt->recv_lock); + spin_lock(&xprt->queue_lock); cwnd = xprt->cwnd; xprt->cwnd = r_xprt->rx_buf.rb_credits << RPC_CWNDSHIFT; if (xprt->cwnd > cwnd) @@ -1246,7 +1246,7 @@ out: xprt_complete_rqst(rqst->rq_task, status); xprt_unpin_rqst(rqst); - spin_unlock(&xprt->recv_lock); + spin_unlock(&xprt->queue_lock); return; /* If the incoming reply terminated a pending RPC, the next @@ -1345,7 +1345,7 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *rep) /* Match incoming rpcrdma_rep to an rpcrdma_req to * get context for handling any incoming chunks. */ - spin_lock(&xprt->recv_lock); + spin_lock(&xprt->queue_lock); rqst = xprt_lookup_rqst(xprt, rep->rr_xid); if (!rqst) goto out_norqst; @@ -1357,7 +1357,7 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *rep) credits = buf->rb_max_requests; buf->rb_credits = credits; - spin_unlock(&xprt->recv_lock); + spin_unlock(&xprt->queue_lock); req = rpcr_to_rdmar(rqst); req->rl_reply = rep; @@ -1378,7 +1378,7 @@ out_badversion: * is corrupt. */ out_norqst: - spin_unlock(&xprt->recv_lock); + spin_unlock(&xprt->queue_lock); trace_xprtrdma_reply_rqst(rep); goto repost; diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c index a68180090554..09b12b7568fe 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c +++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c @@ -56,7 +56,7 @@ int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, __be32 *rdma_resp, if (src->iov_len < 24) goto out_shortreply; - spin_lock(&xprt->recv_lock); + spin_lock(&xprt->queue_lock); req = xprt_lookup_rqst(xprt, xid); if (!req) goto out_notfound; @@ -86,7 +86,7 @@ int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, __be32 *rdma_resp, rcvbuf->len = 0; out_unlock: - spin_unlock(&xprt->recv_lock); + spin_unlock(&xprt->queue_lock); out: return ret; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 3fbccebd0b10..8d6404259ff9 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -966,12 +966,12 @@ static void xs_local_data_read_skb(struct rpc_xprt *xprt, return; /* Look up and lock the request corresponding to the given XID */ - spin_lock(&xprt->recv_lock); + spin_lock(&xprt->queue_lock); rovr = xprt_lookup_rqst(xprt, *xp); if (!rovr) goto out_unlock; xprt_pin_rqst(rovr); - spin_unlock(&xprt->recv_lock); + spin_unlock(&xprt->queue_lock); task = rovr->rq_task; copied = rovr->rq_private_buf.buflen; @@ -980,16 +980,16 @@ static void xs_local_data_read_skb(struct rpc_xprt *xprt, if (xs_local_copy_to_xdr(&rovr->rq_private_buf, skb)) { dprintk("RPC: sk_buff copy failed\n"); - spin_lock(&xprt->recv_lock); + spin_lock(&xprt->queue_lock); goto out_unpin; } - spin_lock(&xprt->recv_lock); + spin_lock(&xprt->queue_lock); xprt_complete_rqst(task, copied); out_unpin: xprt_unpin_rqst(rovr); out_unlock: - spin_unlock(&xprt->recv_lock); + spin_unlock(&xprt->queue_lock); } static void xs_local_data_receive(struct sock_xprt *transport) @@ -1058,13 +1058,13 @@ static void xs_udp_data_read_skb(struct rpc_xprt *xprt, return; /* Look up and lock the request corresponding to the given XID */ - spin_lock(&xprt->recv_lock); + spin_lock(&xprt->queue_lock); rovr = xprt_lookup_rqst(xprt, *xp); if (!rovr) goto out_unlock; xprt_pin_rqst(rovr); xprt_update_rtt(rovr->rq_task); - spin_unlock(&xprt->recv_lock); + spin_unlock(&xprt->queue_lock); task = rovr->rq_task; if ((copied = rovr->rq_private_buf.buflen) > repsize) @@ -1072,7 +1072,7 @@ static void xs_udp_data_read_skb(struct rpc_xprt *xprt, /* Suck it into the iovec, verify checksum if not done by hw. */ if (csum_partial_copy_to_xdr(&rovr->rq_private_buf, skb)) { - spin_lock(&xprt->recv_lock); + spin_lock(&xprt->queue_lock); __UDPX_INC_STATS(sk, UDP_MIB_INERRORS); goto out_unpin; } @@ -1081,13 +1081,13 @@ static void xs_udp_data_read_skb(struct rpc_xprt *xprt, spin_lock_bh(&xprt->transport_lock); xprt_adjust_cwnd(xprt, task, copied); spin_unlock_bh(&xprt->transport_lock); - spin_lock(&xprt->recv_lock); + spin_lock(&xprt->queue_lock); xprt_complete_rqst(task, copied); __UDPX_INC_STATS(sk, UDP_MIB_INDATAGRAMS); out_unpin: xprt_unpin_rqst(rovr); out_unlock: - spin_unlock(&xprt->recv_lock); + spin_unlock(&xprt->queue_lock); } static void xs_udp_data_receive(struct sock_xprt *transport) @@ -1356,24 +1356,24 @@ static inline int xs_tcp_read_reply(struct rpc_xprt *xprt, dprintk("RPC: read reply XID %08x\n", ntohl(transport->recv.xid)); /* Find and lock the request corresponding to this xid */ - spin_lock(&xprt->recv_lock); + spin_lock(&xprt->queue_lock); req = xprt_lookup_rqst(xprt, transport->recv.xid); if (!req) { dprintk("RPC: XID %08x request not found!\n", ntohl(transport->recv.xid)); - spin_unlock(&xprt->recv_lock); + spin_unlock(&xprt->queue_lock); return -1; } xprt_pin_rqst(req); - spin_unlock(&xprt->recv_lock); + spin_unlock(&xprt->queue_lock); xs_tcp_read_common(xprt, desc, req); - spin_lock(&xprt->recv_lock); + spin_lock(&xprt->queue_lock); if (!(transport->recv.flags & TCP_RCV_COPY_DATA)) xprt_complete_rqst(req->rq_task, transport->recv.copied); xprt_unpin_rqst(req); - spin_unlock(&xprt->recv_lock); + spin_unlock(&xprt->queue_lock); return 0; } -- cgit v1.2.3 From edc81dcd5b7f699c4049042b35c904396642032e Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 22 Aug 2018 17:55:46 -0400 Subject: SUNRPC: Refactor xprt_transmit() to remove the reply queue code Separate out the action of adding a request to the reply queue so that the backchannel code can simply skip calling it altogether. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 + net/sunrpc/backchannel_rqst.c | 1 - net/sunrpc/clnt.c | 5 ++ net/sunrpc/xprt.c | 127 +++++++++++++++++++++++++------------- net/sunrpc/xprtrdma/backchannel.c | 1 - 5 files changed, 89 insertions(+), 46 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index c25d0a5fda69..0250294c904a 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -334,6 +334,7 @@ void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req); void xprt_lock_and_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task); bool xprt_prepare_transmit(struct rpc_task *task); +void xprt_request_enqueue_receive(struct rpc_task *task); void xprt_transmit(struct rpc_task *task); void xprt_end_transmit(struct rpc_task *task); int xprt_adjust_timeout(struct rpc_rqst *req); diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c index 3c15a99b9700..fa5ba6ed3197 100644 --- a/net/sunrpc/backchannel_rqst.c +++ b/net/sunrpc/backchannel_rqst.c @@ -91,7 +91,6 @@ struct rpc_rqst *xprt_alloc_bc_req(struct rpc_xprt *xprt, gfp_t gfp_flags) return NULL; req->rq_xprt = xprt; - INIT_LIST_HEAD(&req->rq_list); INIT_LIST_HEAD(&req->rq_bc_list); /* Preallocate one XDR receive buffer */ diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index a858366cd15d..414966273a3f 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1962,6 +1962,11 @@ call_transmit(struct rpc_task *task) return; } } + + /* Add task to reply queue before transmission to avoid races */ + if (rpc_reply_expected(task)) + xprt_request_enqueue_receive(task); + if (!xprt_prepare_transmit(task)) return; task->tk_action = call_transmit_status; diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 6e3d4b4ee79e..2ae0a4c47d59 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -888,6 +888,62 @@ static void xprt_wait_on_pinned_rqst(struct rpc_rqst *req) wait_var_event(&req->rq_pin, !xprt_is_pinned_rqst(req)); } +static bool +xprt_request_data_received(struct rpc_task *task) +{ + return !test_bit(RPC_TASK_NEED_RECV, &task->tk_runstate) && + READ_ONCE(task->tk_rqstp->rq_reply_bytes_recvd) != 0; +} + +static bool +xprt_request_need_enqueue_receive(struct rpc_task *task, struct rpc_rqst *req) +{ + return !test_bit(RPC_TASK_NEED_RECV, &task->tk_runstate) && + READ_ONCE(task->tk_rqstp->rq_reply_bytes_recvd) == 0; +} + +/** + * xprt_request_enqueue_receive - Add an request to the receive queue + * @task: RPC task + * + */ +void +xprt_request_enqueue_receive(struct rpc_task *task) +{ + struct rpc_rqst *req = task->tk_rqstp; + struct rpc_xprt *xprt = req->rq_xprt; + + if (!xprt_request_need_enqueue_receive(task, req)) + return; + spin_lock(&xprt->queue_lock); + + /* Update the softirq receive buffer */ + memcpy(&req->rq_private_buf, &req->rq_rcv_buf, + sizeof(req->rq_private_buf)); + + /* Add request to the receive list */ + list_add_tail(&req->rq_list, &xprt->recv); + set_bit(RPC_TASK_NEED_RECV, &task->tk_runstate); + spin_unlock(&xprt->queue_lock); + + xprt_reset_majortimeo(req); + /* Turn off autodisconnect */ + del_singleshot_timer_sync(&xprt->timer); +} + +/** + * xprt_request_dequeue_receive_locked - Remove a request from the receive queue + * @task: RPC task + * + * Caller must hold xprt->queue_lock. + */ +static void +xprt_request_dequeue_receive_locked(struct rpc_task *task) +{ + if (test_and_clear_bit(RPC_TASK_NEED_RECV, &task->tk_runstate)) + list_del(&task->tk_rqstp->rq_list); +} + /** * xprt_update_rtt - Update RPC RTT statistics * @task: RPC request that recently completed @@ -927,24 +983,16 @@ void xprt_complete_rqst(struct rpc_task *task, int copied) xprt->stat.recvs++; - list_del_init(&req->rq_list); req->rq_private_buf.len = copied; /* Ensure all writes are done before we update */ /* req->rq_reply_bytes_recvd */ smp_wmb(); req->rq_reply_bytes_recvd = copied; - clear_bit(RPC_TASK_NEED_RECV, &task->tk_runstate); + xprt_request_dequeue_receive_locked(task); rpc_wake_up_queued_task(&xprt->pending, task); } EXPORT_SYMBOL_GPL(xprt_complete_rqst); -static bool -xprt_request_data_received(struct rpc_task *task) -{ - return !test_bit(RPC_TASK_NEED_RECV, &task->tk_runstate) && - task->tk_rqstp->rq_reply_bytes_recvd != 0; -} - static void xprt_timer(struct rpc_task *task) { struct rpc_rqst *req = task->tk_rqstp; @@ -1018,32 +1066,15 @@ void xprt_transmit(struct rpc_task *task) dprintk("RPC: %5u xprt_transmit(%u)\n", task->tk_pid, req->rq_slen); - if (!req->rq_reply_bytes_recvd) { - + if (!req->rq_bytes_sent) { + if (xprt_request_data_received(task)) + return; /* Verify that our message lies in the RPCSEC_GSS window */ - if (!req->rq_bytes_sent && rpcauth_xmit_need_reencode(task)) { + if (rpcauth_xmit_need_reencode(task)) { task->tk_status = -EBADMSG; return; } - - if (list_empty(&req->rq_list) && rpc_reply_expected(task)) { - /* - * Add to the list only if we're expecting a reply - */ - /* Update the softirq receive buffer */ - memcpy(&req->rq_private_buf, &req->rq_rcv_buf, - sizeof(req->rq_private_buf)); - /* Add request to the receive list */ - spin_lock(&xprt->queue_lock); - list_add_tail(&req->rq_list, &xprt->recv); - set_bit(RPC_TASK_NEED_RECV, &task->tk_runstate); - spin_unlock(&xprt->queue_lock); - xprt_reset_majortimeo(req); - /* Turn off autodisconnect */ - del_singleshot_timer_sync(&xprt->timer); - } - } else if (xprt_request_data_received(task) && !req->rq_bytes_sent) - return; + } connect_cookie = xprt->connect_cookie; status = xprt->ops->send_request(task); @@ -1285,7 +1316,6 @@ xprt_request_init(struct rpc_task *task) struct rpc_xprt *xprt = task->tk_xprt; struct rpc_rqst *req = task->tk_rqstp; - INIT_LIST_HEAD(&req->rq_list); req->rq_timeout = task->tk_client->cl_timeout->to_initval; req->rq_task = task; req->rq_xprt = xprt; @@ -1355,6 +1385,26 @@ void xprt_retry_reserve(struct rpc_task *task) xprt_do_reserve(xprt, task); } +static void +xprt_request_dequeue_all(struct rpc_task *task, struct rpc_rqst *req) +{ + struct rpc_xprt *xprt = req->rq_xprt; + + if (test_bit(RPC_TASK_NEED_RECV, &task->tk_runstate) || + xprt_is_pinned_rqst(req)) { + spin_lock(&xprt->queue_lock); + xprt_request_dequeue_receive_locked(task); + while (xprt_is_pinned_rqst(req)) { + set_bit(RPC_TASK_MSG_PIN_WAIT, &task->tk_runstate); + spin_unlock(&xprt->queue_lock); + xprt_wait_on_pinned_rqst(req); + spin_lock(&xprt->queue_lock); + clear_bit(RPC_TASK_MSG_PIN_WAIT, &task->tk_runstate); + } + spin_unlock(&xprt->queue_lock); + } +} + /** * xprt_release - release an RPC request slot * @task: task which is finished with the slot @@ -1379,18 +1429,7 @@ void xprt_release(struct rpc_task *task) task->tk_ops->rpc_count_stats(task, task->tk_calldata); else if (task->tk_client) rpc_count_iostats(task, task->tk_client->cl_metrics); - spin_lock(&xprt->queue_lock); - if (!list_empty(&req->rq_list)) { - list_del_init(&req->rq_list); - if (xprt_is_pinned_rqst(req)) { - set_bit(RPC_TASK_MSG_PIN_WAIT, &req->rq_task->tk_runstate); - spin_unlock(&xprt->queue_lock); - xprt_wait_on_pinned_rqst(req); - spin_lock(&xprt->queue_lock); - clear_bit(RPC_TASK_MSG_PIN_WAIT, &req->rq_task->tk_runstate); - } - } - spin_unlock(&xprt->queue_lock); + xprt_request_dequeue_all(task, req); spin_lock_bh(&xprt->transport_lock); xprt->ops->release_xprt(xprt, task); if (xprt->ops->release_request) diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c index 90adeff4c06b..ed58761e6b23 100644 --- a/net/sunrpc/xprtrdma/backchannel.c +++ b/net/sunrpc/xprtrdma/backchannel.c @@ -51,7 +51,6 @@ static int rpcrdma_bc_setup_reqs(struct rpcrdma_xprt *r_xprt, rqst = &req->rl_slot; rqst->rq_xprt = xprt; - INIT_LIST_HEAD(&rqst->rq_list); INIT_LIST_HEAD(&rqst->rq_bc_list); __set_bit(RPC_BC_PA_IN_USE, &rqst->rq_bc_pa_state); spin_lock_bh(&xprt->bc_pa_lock); -- cgit v1.2.3 From 7f3a1d1e1806a0eb9b200e3aed2a04431f2bcc6a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 23 Aug 2018 00:03:43 -0400 Subject: SUNRPC: Refactor xprt_transmit() to remove wait for reply code Allow the caller in clnt.c to call into the code to wait for a reply after calling xprt_transmit(). Again, the reason is that the backchannel code does not need this functionality. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 + net/sunrpc/clnt.c | 10 +----- net/sunrpc/xprt.c | 74 +++++++++++++++++++++++++++++++-------------- 3 files changed, 54 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 0250294c904a..4fa2af087cff 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -335,6 +335,7 @@ void xprt_free_slot(struct rpc_xprt *xprt, void xprt_lock_and_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task); bool xprt_prepare_transmit(struct rpc_task *task); void xprt_request_enqueue_receive(struct rpc_task *task); +void xprt_request_wait_receive(struct rpc_task *task); void xprt_transmit(struct rpc_task *task); void xprt_end_transmit(struct rpc_task *task); int xprt_adjust_timeout(struct rpc_rqst *req); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 414966273a3f..775d6e80b6e8 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1975,15 +1975,6 @@ call_transmit(struct rpc_task *task) return; if (is_retrans) task->tk_client->cl_stats->rpcretrans++; - /* - * On success, ensure that we call xprt_end_transmit() before sleeping - * in order to allow access to the socket to other RPC requests. - */ - call_transmit_status(task); - if (rpc_reply_expected(task)) - return; - task->tk_action = rpc_exit_task; - rpc_wake_up_queued_task(&task->tk_rqstp->rq_xprt->pending, task); } /* @@ -2000,6 +1991,7 @@ call_transmit_status(struct rpc_task *task) */ if (task->tk_status == 0) { xprt_end_transmit(task); + xprt_request_wait_receive(task); return; } diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 2ae0a4c47d59..a6a33c178870 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -654,6 +654,22 @@ void xprt_force_disconnect(struct rpc_xprt *xprt) } EXPORT_SYMBOL_GPL(xprt_force_disconnect); +static unsigned int +xprt_connect_cookie(struct rpc_xprt *xprt) +{ + return READ_ONCE(xprt->connect_cookie); +} + +static bool +xprt_request_retransmit_after_disconnect(struct rpc_task *task) +{ + struct rpc_rqst *req = task->tk_rqstp; + struct rpc_xprt *xprt = req->rq_xprt; + + return req->rq_connect_cookie != xprt_connect_cookie(xprt) || + !xprt_connected(xprt); +} + /** * xprt_conditional_disconnect - force a transport to disconnect * @xprt: transport to disconnect @@ -1009,6 +1025,39 @@ static void xprt_timer(struct rpc_task *task) task->tk_status = 0; } +/** + * xprt_request_wait_receive - wait for the reply to an RPC request + * @task: RPC task about to send a request + * + */ +void xprt_request_wait_receive(struct rpc_task *task) +{ + struct rpc_rqst *req = task->tk_rqstp; + struct rpc_xprt *xprt = req->rq_xprt; + + if (!test_bit(RPC_TASK_NEED_RECV, &task->tk_runstate)) + return; + /* + * Sleep on the pending queue if we're expecting a reply. + * The spinlock ensures atomicity between the test of + * req->rq_reply_bytes_recvd, and the call to rpc_sleep_on(). + */ + spin_lock(&xprt->queue_lock); + if (test_bit(RPC_TASK_NEED_RECV, &task->tk_runstate)) { + xprt->ops->set_retrans_timeout(task); + rpc_sleep_on(&xprt->pending, task, xprt_timer); + /* + * Send an extra queue wakeup call if the + * connection was dropped in case the call to + * rpc_sleep_on() raced. + */ + if (xprt_request_retransmit_after_disconnect(task)) + rpc_wake_up_queued_task_set_status(&xprt->pending, + task, -ENOTCONN); + } + spin_unlock(&xprt->queue_lock); +} + /** * xprt_prepare_transmit - reserve the transport before sending a request * @task: RPC task about to send a request @@ -1028,9 +1077,8 @@ bool xprt_prepare_transmit(struct rpc_task *task) task->tk_status = req->rq_reply_bytes_recvd; goto out_unlock; } - if ((task->tk_flags & RPC_TASK_NO_RETRANS_TIMEOUT) - && xprt_connected(xprt) - && req->rq_connect_cookie == xprt->connect_cookie) { + if ((task->tk_flags & RPC_TASK_NO_RETRANS_TIMEOUT) && + !xprt_request_retransmit_after_disconnect(task)) { xprt->ops->set_retrans_timeout(task); rpc_sleep_on(&xprt->pending, task, xprt_timer); goto out_unlock; @@ -1091,8 +1139,6 @@ void xprt_transmit(struct rpc_task *task) task->tk_flags |= RPC_TASK_SENT; spin_lock_bh(&xprt->transport_lock); - xprt->ops->set_retrans_timeout(task); - xprt->stat.sends++; xprt->stat.req_u += xprt->stat.sends - xprt->stat.recvs; xprt->stat.bklog_u += xprt->backlog.qlen; @@ -1101,22 +1147,6 @@ void xprt_transmit(struct rpc_task *task) spin_unlock_bh(&xprt->transport_lock); req->rq_connect_cookie = connect_cookie; - if (test_bit(RPC_TASK_NEED_RECV, &task->tk_runstate)) { - /* - * Sleep on the pending queue if we're expecting a reply. - * The spinlock ensures atomicity between the test of - * req->rq_reply_bytes_recvd, and the call to rpc_sleep_on(). - */ - spin_lock(&xprt->queue_lock); - if (test_bit(RPC_TASK_NEED_RECV, &task->tk_runstate)) { - rpc_sleep_on(&xprt->pending, task, xprt_timer); - /* Wake up immediately if the connection was dropped */ - if (!xprt_connected(xprt)) - rpc_wake_up_queued_task_set_status(&xprt->pending, - task, -ENOTCONN); - } - spin_unlock(&xprt->queue_lock); - } } static void xprt_add_backlog(struct rpc_xprt *xprt, struct rpc_task *task) @@ -1321,7 +1351,7 @@ xprt_request_init(struct rpc_task *task) req->rq_xprt = xprt; req->rq_buffer = NULL; req->rq_xid = xprt_alloc_xid(xprt); - req->rq_connect_cookie = xprt->connect_cookie - 1; + req->rq_connect_cookie = xprt_connect_cookie(xprt) - 1; req->rq_bytes_sent = 0; req->rq_snd_buf.len = 0; req->rq_snd_buf.buflen = 0; -- cgit v1.2.3 From ef3f54347f690d06649c0d7a1f63d3410b3d08d3 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 8 Aug 2018 09:23:32 -0400 Subject: SUNRPC: Distinguish between the slot allocation list and receive queue When storing a struct rpc_rqst on the slot allocation list, we currently use the same field 'rq_list' as we use to store the request on the receive queue. Since the structure is never on both lists at the same time, this is OK. However, for clarity, let's make that a union with different names for the different lists so that we can more easily distinguish between the two states. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 9 +++++++-- net/sunrpc/xprt.c | 12 ++++++------ 2 files changed, 13 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 4fa2af087cff..9cec2d0811f2 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -82,7 +82,11 @@ struct rpc_rqst { struct page **rq_enc_pages; /* scratch pages for use by gss privacy code */ void (*rq_release_snd_buf)(struct rpc_rqst *); /* release rq_enc_pages */ - struct list_head rq_list; + + union { + struct list_head rq_list; /* Slot allocation list */ + struct list_head rq_recv; /* Receive queue */ + }; void *rq_buffer; /* Call XDR encode buffer */ size_t rq_callsize; @@ -249,7 +253,8 @@ struct rpc_xprt { struct list_head bc_pa_list; /* List of preallocated * backchannel rpc_rqst's */ #endif /* CONFIG_SUNRPC_BACKCHANNEL */ - struct list_head recv; + + struct list_head recv_queue; /* Receive queue */ struct { unsigned long bind_count, /* total number of binds */ diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index a6a33c178870..d527dc08540e 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -708,7 +708,7 @@ static void xprt_schedule_autodisconnect(struct rpc_xprt *xprt) __must_hold(&xprt->transport_lock) { - if (list_empty(&xprt->recv) && xprt_has_timer(xprt)) + if (list_empty(&xprt->recv_queue) && xprt_has_timer(xprt)) mod_timer(&xprt->timer, xprt->last_used + xprt->idle_timeout); } @@ -718,7 +718,7 @@ xprt_init_autodisconnect(struct timer_list *t) struct rpc_xprt *xprt = from_timer(xprt, t, timer); spin_lock(&xprt->transport_lock); - if (!list_empty(&xprt->recv)) + if (!list_empty(&xprt->recv_queue)) goto out_abort; /* Reset xprt->last_used to avoid connect/autodisconnect cycling */ xprt->last_used = jiffies; @@ -848,7 +848,7 @@ struct rpc_rqst *xprt_lookup_rqst(struct rpc_xprt *xprt, __be32 xid) { struct rpc_rqst *entry; - list_for_each_entry(entry, &xprt->recv, rq_list) + list_for_each_entry(entry, &xprt->recv_queue, rq_recv) if (entry->rq_xid == xid) { trace_xprt_lookup_rqst(xprt, xid, 0); entry->rq_rtt = ktime_sub(ktime_get(), entry->rq_xtime); @@ -938,7 +938,7 @@ xprt_request_enqueue_receive(struct rpc_task *task) sizeof(req->rq_private_buf)); /* Add request to the receive list */ - list_add_tail(&req->rq_list, &xprt->recv); + list_add_tail(&req->rq_recv, &xprt->recv_queue); set_bit(RPC_TASK_NEED_RECV, &task->tk_runstate); spin_unlock(&xprt->queue_lock); @@ -957,7 +957,7 @@ static void xprt_request_dequeue_receive_locked(struct rpc_task *task) { if (test_and_clear_bit(RPC_TASK_NEED_RECV, &task->tk_runstate)) - list_del(&task->tk_rqstp->rq_list); + list_del(&task->tk_rqstp->rq_recv); } /** @@ -1492,7 +1492,7 @@ static void xprt_init(struct rpc_xprt *xprt, struct net *net) spin_lock_init(&xprt->queue_lock); INIT_LIST_HEAD(&xprt->free); - INIT_LIST_HEAD(&xprt->recv); + INIT_LIST_HEAD(&xprt->recv_queue); #if defined(CONFIG_SUNRPC_BACKCHANNEL) spin_lock_init(&xprt->bc_pa_lock); INIT_LIST_HEAD(&xprt->bc_pa_list); -- cgit v1.2.3 From 944b042921a17d1a4e51bb05f8edf2b93d26e36f Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 9 Aug 2018 23:33:21 -0400 Subject: SUNRPC: Add a transmission queue for RPC requests Add the queue that will enforce the ordering of RPC task transmission. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 6 ++++ net/sunrpc/clnt.c | 6 ++-- net/sunrpc/xprt.c | 84 ++++++++++++++++++++++++++++++++++++++++----- 3 files changed, 83 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 9cec2d0811f2..81a6c2c8dfc7 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -88,6 +88,8 @@ struct rpc_rqst { struct list_head rq_recv; /* Receive queue */ }; + struct list_head rq_xmit; /* Send queue */ + void *rq_buffer; /* Call XDR encode buffer */ size_t rq_callsize; void *rq_rbuffer; /* Reply XDR decode buffer */ @@ -242,6 +244,9 @@ struct rpc_xprt { spinlock_t queue_lock; /* send/receive queue lock */ u32 xid; /* Next XID value to use */ struct rpc_task * snd_task; /* Task blocked in send */ + + struct list_head xmit_queue; /* Send queue */ + struct svc_xprt *bc_xprt; /* NFSv4.1 backchannel */ #if defined(CONFIG_SUNRPC_BACKCHANNEL) struct svc_serv *bc_serv; /* The RPC service which will */ @@ -339,6 +344,7 @@ void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req); void xprt_lock_and_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task); bool xprt_prepare_transmit(struct rpc_task *task); +void xprt_request_enqueue_transmit(struct rpc_task *task); void xprt_request_enqueue_receive(struct rpc_task *task); void xprt_request_wait_receive(struct rpc_task *task); void xprt_transmit(struct rpc_task *task); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index be0f06a8156b..c1a19a3e1356 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1156,11 +1156,11 @@ struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req) */ xbufp->len = xbufp->head[0].iov_len + xbufp->page_len + xbufp->tail[0].iov_len; - set_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate); task->tk_action = call_bc_transmit; atomic_inc(&task->tk_count); WARN_ON_ONCE(atomic_read(&task->tk_count) != 2); + xprt_request_enqueue_transmit(task); rpc_execute(task); dprintk("RPC: rpc_run_bc_task: task= %p\n", task); @@ -1759,8 +1759,6 @@ rpc_xdr_encode(struct rpc_task *task) task->tk_status = rpcauth_wrap_req(task, encode, req, p, task->tk_msg.rpc_argp); - if (task->tk_status == 0) - set_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate); } /* @@ -1964,6 +1962,7 @@ call_transmit(struct rpc_task *task) /* Add task to reply queue before transmission to avoid races */ if (rpc_reply_expected(task)) xprt_request_enqueue_receive(task); + xprt_request_enqueue_transmit(task); if (!xprt_prepare_transmit(task)) return; @@ -1998,7 +1997,6 @@ call_transmit_status(struct rpc_task *task) xprt_end_transmit(task); break; case -EBADMSG: - clear_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate); task->tk_action = call_transmit; task->tk_status = 0; xprt_end_transmit(task); diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index d527dc08540e..1f69d9f219af 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1058,6 +1058,72 @@ void xprt_request_wait_receive(struct rpc_task *task) spin_unlock(&xprt->queue_lock); } +static bool +xprt_request_need_transmit(struct rpc_task *task) +{ + return !(task->tk_flags & RPC_TASK_NO_RETRANS_TIMEOUT) || + xprt_request_retransmit_after_disconnect(task); +} + +static bool +xprt_request_need_enqueue_transmit(struct rpc_task *task, struct rpc_rqst *req) +{ + return xprt_request_need_transmit(task) && + !test_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate); +} + +/** + * xprt_request_enqueue_transmit - queue a task for transmission + * @task: pointer to rpc_task + * + * Add a task to the transmission queue. + */ +void +xprt_request_enqueue_transmit(struct rpc_task *task) +{ + struct rpc_rqst *req = task->tk_rqstp; + struct rpc_xprt *xprt = req->rq_xprt; + + if (xprt_request_need_enqueue_transmit(task, req)) { + spin_lock(&xprt->queue_lock); + list_add_tail(&req->rq_xmit, &xprt->xmit_queue); + set_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate); + spin_unlock(&xprt->queue_lock); + } +} + +/** + * xprt_request_dequeue_transmit_locked - remove a task from the transmission queue + * @task: pointer to rpc_task + * + * Remove a task from the transmission queue + * Caller must hold xprt->queue_lock + */ +static void +xprt_request_dequeue_transmit_locked(struct rpc_task *task) +{ + xprt_task_clear_bytes_sent(task); + if (test_and_clear_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate)) + list_del(&task->tk_rqstp->rq_xmit); +} + +/** + * xprt_request_dequeue_transmit - remove a task from the transmission queue + * @task: pointer to rpc_task + * + * Remove a task from the transmission queue + */ +static void +xprt_request_dequeue_transmit(struct rpc_task *task) +{ + struct rpc_rqst *req = task->tk_rqstp; + struct rpc_xprt *xprt = req->rq_xprt; + + spin_lock(&xprt->queue_lock); + xprt_request_dequeue_transmit_locked(task); + spin_unlock(&xprt->queue_lock); +} + /** * xprt_prepare_transmit - reserve the transport before sending a request * @task: RPC task about to send a request @@ -1077,12 +1143,8 @@ bool xprt_prepare_transmit(struct rpc_task *task) task->tk_status = req->rq_reply_bytes_recvd; goto out_unlock; } - if ((task->tk_flags & RPC_TASK_NO_RETRANS_TIMEOUT) && - !xprt_request_retransmit_after_disconnect(task)) { - xprt->ops->set_retrans_timeout(task); - rpc_sleep_on(&xprt->pending, task, xprt_timer); + if (!test_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate)) goto out_unlock; - } } if (!xprt->ops->reserve_xprt(xprt, task)) { task->tk_status = -EAGAIN; @@ -1116,11 +1178,11 @@ void xprt_transmit(struct rpc_task *task) if (!req->rq_bytes_sent) { if (xprt_request_data_received(task)) - return; + goto out_dequeue; /* Verify that our message lies in the RPCSEC_GSS window */ if (rpcauth_xmit_need_reencode(task)) { task->tk_status = -EBADMSG; - return; + goto out_dequeue; } } @@ -1135,7 +1197,6 @@ void xprt_transmit(struct rpc_task *task) xprt_inject_disconnect(xprt); dprintk("RPC: %5u xmit complete\n", task->tk_pid); - clear_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate); task->tk_flags |= RPC_TASK_SENT; spin_lock_bh(&xprt->transport_lock); @@ -1147,6 +1208,8 @@ void xprt_transmit(struct rpc_task *task) spin_unlock_bh(&xprt->transport_lock); req->rq_connect_cookie = connect_cookie; +out_dequeue: + xprt_request_dequeue_transmit(task); } static void xprt_add_backlog(struct rpc_xprt *xprt, struct rpc_task *task) @@ -1420,9 +1483,11 @@ xprt_request_dequeue_all(struct rpc_task *task, struct rpc_rqst *req) { struct rpc_xprt *xprt = req->rq_xprt; - if (test_bit(RPC_TASK_NEED_RECV, &task->tk_runstate) || + if (test_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate) || + test_bit(RPC_TASK_NEED_RECV, &task->tk_runstate) || xprt_is_pinned_rqst(req)) { spin_lock(&xprt->queue_lock); + xprt_request_dequeue_transmit_locked(task); xprt_request_dequeue_receive_locked(task); while (xprt_is_pinned_rqst(req)) { set_bit(RPC_TASK_MSG_PIN_WAIT, &task->tk_runstate); @@ -1493,6 +1558,7 @@ static void xprt_init(struct rpc_xprt *xprt, struct net *net) INIT_LIST_HEAD(&xprt->free); INIT_LIST_HEAD(&xprt->recv_queue); + INIT_LIST_HEAD(&xprt->xmit_queue); #if defined(CONFIG_SUNRPC_BACKCHANNEL) spin_lock_init(&xprt->bc_pa_lock); INIT_LIST_HEAD(&xprt->bc_pa_list); -- cgit v1.2.3 From 762e4e67b356ab7b8fbfc39bc07dc6110121505e Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 24 Aug 2018 16:28:28 -0400 Subject: SUNRPC: Refactor RPC call encoding Move the call encoding so that it occurs before the transport connection etc. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 + net/sunrpc/clnt.c | 81 +++++++++++++++++++++++++++------------------ net/sunrpc/xprt.c | 22 +++++++----- 3 files changed, 63 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 81a6c2c8dfc7..b8a7de161f67 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -347,6 +347,7 @@ bool xprt_prepare_transmit(struct rpc_task *task); void xprt_request_enqueue_transmit(struct rpc_task *task); void xprt_request_enqueue_receive(struct rpc_task *task); void xprt_request_wait_receive(struct rpc_task *task); +bool xprt_request_need_retransmit(struct rpc_task *task); void xprt_transmit(struct rpc_task *task); void xprt_end_transmit(struct rpc_task *task); int xprt_adjust_timeout(struct rpc_rqst *req); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index c1a19a3e1356..64159716be30 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -61,6 +61,7 @@ static void call_start(struct rpc_task *task); static void call_reserve(struct rpc_task *task); static void call_reserveresult(struct rpc_task *task); static void call_allocate(struct rpc_task *task); +static void call_encode(struct rpc_task *task); static void call_decode(struct rpc_task *task); static void call_bind(struct rpc_task *task); static void call_bind_status(struct rpc_task *task); @@ -1140,7 +1141,8 @@ struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req) struct xdr_buf *xbufp = &req->rq_snd_buf; struct rpc_task_setup task_setup_data = { .callback_ops = &rpc_default_ops, - .flags = RPC_TASK_SOFTCONN, + .flags = RPC_TASK_SOFTCONN | + RPC_TASK_NO_RETRANS_TIMEOUT, }; dprintk("RPC: rpc_run_bc_task req= %p\n", req); @@ -1160,7 +1162,6 @@ struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req) task->tk_action = call_bc_transmit; atomic_inc(&task->tk_count); WARN_ON_ONCE(atomic_read(&task->tk_count) != 2); - xprt_request_enqueue_transmit(task); rpc_execute(task); dprintk("RPC: rpc_run_bc_task: task= %p\n", task); @@ -1680,7 +1681,7 @@ call_allocate(struct rpc_task *task) dprint_status(task); task->tk_status = 0; - task->tk_action = call_bind; + task->tk_action = call_encode; if (req->rq_buffer) return; @@ -1724,12 +1725,12 @@ call_allocate(struct rpc_task *task) static int rpc_task_need_encode(struct rpc_task *task) { - return test_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate) == 0; + return test_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate) == 0 && + (!(task->tk_flags & RPC_TASK_SENT) || + !(task->tk_flags & RPC_TASK_NO_RETRANS_TIMEOUT) || + xprt_request_need_retransmit(task)); } -/* - * 3. Encode arguments of an RPC call - */ static void rpc_xdr_encode(struct rpc_task *task) { @@ -1745,6 +1746,7 @@ rpc_xdr_encode(struct rpc_task *task) xdr_buf_init(&req->rq_rcv_buf, req->rq_rbuffer, req->rq_rcvsize); + req->rq_bytes_sent = 0; p = rpc_encode_header(task); if (p == NULL) { @@ -1761,6 +1763,34 @@ rpc_xdr_encode(struct rpc_task *task) task->tk_msg.rpc_argp); } +/* + * 3. Encode arguments of an RPC call + */ +static void +call_encode(struct rpc_task *task) +{ + if (!rpc_task_need_encode(task)) + goto out; + /* Encode here so that rpcsec_gss can use correct sequence number. */ + rpc_xdr_encode(task); + /* Did the encode result in an error condition? */ + if (task->tk_status != 0) { + /* Was the error nonfatal? */ + if (task->tk_status == -EAGAIN) + rpc_delay(task, HZ >> 4); + else + rpc_exit(task, task->tk_status); + return; + } + + /* Add task to reply queue before transmission to avoid races */ + if (rpc_reply_expected(task)) + xprt_request_enqueue_receive(task); + xprt_request_enqueue_transmit(task); +out: + task->tk_action = call_bind; +} + /* * 4. Get the server port number if not yet set */ @@ -1945,24 +1975,8 @@ call_transmit(struct rpc_task *task) dprint_status(task); task->tk_action = call_transmit_status; - /* Encode here so that rpcsec_gss can use correct sequence number. */ - if (rpc_task_need_encode(task)) { - rpc_xdr_encode(task); - /* Did the encode result in an error condition? */ - if (task->tk_status != 0) { - /* Was the error nonfatal? */ - if (task->tk_status == -EAGAIN) - rpc_delay(task, HZ >> 4); - else - rpc_exit(task, task->tk_status); - return; - } - } - - /* Add task to reply queue before transmission to avoid races */ - if (rpc_reply_expected(task)) - xprt_request_enqueue_receive(task); - xprt_request_enqueue_transmit(task); + if (!test_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate)) + return; if (!xprt_prepare_transmit(task)) return; @@ -1997,9 +2011,9 @@ call_transmit_status(struct rpc_task *task) xprt_end_transmit(task); break; case -EBADMSG: - task->tk_action = call_transmit; - task->tk_status = 0; xprt_end_transmit(task); + task->tk_status = 0; + task->tk_action = call_encode; break; /* * Special cases: if we've been waiting on the @@ -2048,6 +2062,9 @@ call_bc_transmit(struct rpc_task *task) { struct rpc_rqst *req = task->tk_rqstp; + if (rpc_task_need_encode(task)) + xprt_request_enqueue_transmit(task); + if (!xprt_prepare_transmit(task)) goto out_retry; @@ -2169,7 +2186,7 @@ call_status(struct rpc_task *task) case -EPIPE: case -ENOTCONN: case -EAGAIN: - task->tk_action = call_bind; + task->tk_action = call_encode; break; case -EIO: /* shutdown or soft timeout */ @@ -2234,7 +2251,7 @@ call_timeout(struct rpc_task *task) rpcauth_invalcred(task); retry: - task->tk_action = call_bind; + task->tk_action = call_encode; task->tk_status = 0; } @@ -2278,7 +2295,7 @@ call_decode(struct rpc_task *task) if (req->rq_rcv_buf.len < 12) { if (!RPC_IS_SOFT(task)) { - task->tk_action = call_bind; + task->tk_action = call_encode; goto out_retry; } dprintk("RPC: %s: too small RPC reply size (%d bytes)\n", @@ -2409,7 +2426,7 @@ rpc_verify_header(struct rpc_task *task) task->tk_garb_retry--; dprintk("RPC: %5u %s: retry garbled creds\n", task->tk_pid, __func__); - task->tk_action = call_bind; + task->tk_action = call_encode; goto out_retry; case RPC_AUTH_TOOWEAK: printk(KERN_NOTICE "RPC: server %s requires stronger " @@ -2478,7 +2495,7 @@ out_garbage: task->tk_garb_retry--; dprintk("RPC: %5u %s: retrying\n", task->tk_pid, __func__); - task->tk_action = call_bind; + task->tk_action = call_encode; out_retry: return ERR_PTR(-EAGAIN); } diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 1f69d9f219af..613f558a3791 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1058,18 +1058,10 @@ void xprt_request_wait_receive(struct rpc_task *task) spin_unlock(&xprt->queue_lock); } -static bool -xprt_request_need_transmit(struct rpc_task *task) -{ - return !(task->tk_flags & RPC_TASK_NO_RETRANS_TIMEOUT) || - xprt_request_retransmit_after_disconnect(task); -} - static bool xprt_request_need_enqueue_transmit(struct rpc_task *task, struct rpc_rqst *req) { - return xprt_request_need_transmit(task) && - !test_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate); + return !test_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate); } /** @@ -1124,6 +1116,18 @@ xprt_request_dequeue_transmit(struct rpc_task *task) spin_unlock(&xprt->queue_lock); } +/** + * xprt_request_need_retransmit - Test if a task needs retransmission + * @task: pointer to rpc_task + * + * Test for whether a connection breakage requires the task to retransmit + */ +bool +xprt_request_need_retransmit(struct rpc_task *task) +{ + return xprt_request_retransmit_after_disconnect(task); +} + /** * xprt_prepare_transmit - reserve the transport before sending a request * @task: RPC task about to send a request -- cgit v1.2.3 From 902c58872e1e9a2c146a55b0701c0b26cc5a4b24 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 1 Sep 2018 17:21:01 -0400 Subject: SUNRPC: Fix up the back channel transmit Fix up the back channel code to recognise that it has already been transmitted, so does not need to be called again. Also ensure that we set req->rq_task. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/bc_xprt.h | 1 + net/sunrpc/clnt.c | 19 +++++-------------- net/sunrpc/xprt.c | 27 ++++++++++++++++++++++++++- 3 files changed, 32 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/bc_xprt.h b/include/linux/sunrpc/bc_xprt.h index 4397a4824c81..28721cf73ec3 100644 --- a/include/linux/sunrpc/bc_xprt.h +++ b/include/linux/sunrpc/bc_xprt.h @@ -34,6 +34,7 @@ SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. #ifdef CONFIG_SUNRPC_BACKCHANNEL struct rpc_rqst *xprt_lookup_bc_request(struct rpc_xprt *xprt, __be32 xid); void xprt_complete_bc_request(struct rpc_rqst *req, uint32_t copied); +void xprt_init_bc_request(struct rpc_rqst *req, struct rpc_task *task); void xprt_free_bc_request(struct rpc_rqst *req); int xprt_setup_backchannel(struct rpc_xprt *, unsigned int min_reqs); void xprt_destroy_backchannel(struct rpc_xprt *, unsigned int max_reqs); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 64159716be30..dcefbf406482 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1138,7 +1138,6 @@ EXPORT_SYMBOL_GPL(rpc_call_async); struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req) { struct rpc_task *task; - struct xdr_buf *xbufp = &req->rq_snd_buf; struct rpc_task_setup task_setup_data = { .callback_ops = &rpc_default_ops, .flags = RPC_TASK_SOFTCONN | @@ -1150,14 +1149,7 @@ struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req) * Create an rpc_task to send the data */ task = rpc_new_task(&task_setup_data); - task->tk_rqstp = req; - - /* - * Set up the xdr_buf length. - * This also indicates that the buffer is XDR encoded already. - */ - xbufp->len = xbufp->head[0].iov_len + xbufp->page_len + - xbufp->tail[0].iov_len; + xprt_init_bc_request(req, task); task->tk_action = call_bc_transmit; atomic_inc(&task->tk_count); @@ -2064,6 +2056,8 @@ call_bc_transmit(struct rpc_task *task) if (rpc_task_need_encode(task)) xprt_request_enqueue_transmit(task); + if (!test_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate)) + goto out_wakeup; if (!xprt_prepare_transmit(task)) goto out_retry; @@ -2073,13 +2067,11 @@ call_bc_transmit(struct rpc_task *task) "error: %d\n", task->tk_status); goto out_done; } - if (req->rq_connect_cookie != req->rq_xprt->connect_cookie) - req->rq_bytes_sent = 0; xprt_transmit(task); if (task->tk_status == -EAGAIN) - goto out_nospace; + goto out_retry; xprt_end_transmit(task); dprint_status(task); @@ -2119,12 +2111,11 @@ call_bc_transmit(struct rpc_task *task) "error: %d\n", task->tk_status); break; } +out_wakeup: rpc_wake_up_queued_task(&req->rq_xprt->pending, task); out_done: task->tk_action = rpc_exit_task; return; -out_nospace: - req->rq_connect_cookie = req->rq_xprt->connect_cookie; out_retry: task->tk_status = 0; } diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 613f558a3791..f5be739492d4 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1390,6 +1390,12 @@ void xprt_free(struct rpc_xprt *xprt) } EXPORT_SYMBOL_GPL(xprt_free); +static void +xprt_init_connect_cookie(struct rpc_rqst *req, struct rpc_xprt *xprt) +{ + req->rq_connect_cookie = xprt_connect_cookie(xprt) - 1; +} + static __be32 xprt_alloc_xid(struct rpc_xprt *xprt) { @@ -1418,7 +1424,7 @@ xprt_request_init(struct rpc_task *task) req->rq_xprt = xprt; req->rq_buffer = NULL; req->rq_xid = xprt_alloc_xid(xprt); - req->rq_connect_cookie = xprt_connect_cookie(xprt) - 1; + xprt_init_connect_cookie(req, xprt); req->rq_bytes_sent = 0; req->rq_snd_buf.len = 0; req->rq_snd_buf.buflen = 0; @@ -1552,6 +1558,25 @@ void xprt_release(struct rpc_task *task) xprt_free_bc_request(req); } +#ifdef CONFIG_SUNRPC_BACKCHANNEL +void +xprt_init_bc_request(struct rpc_rqst *req, struct rpc_task *task) +{ + struct xdr_buf *xbufp = &req->rq_snd_buf; + + task->tk_rqstp = req; + req->rq_task = task; + xprt_init_connect_cookie(req, req->rq_xprt); + /* + * Set up the xdr_buf length. + * This also indicates that the buffer is XDR encoded already. + */ + xbufp->len = xbufp->head[0].iov_len + xbufp->page_len + + xbufp->tail[0].iov_len; + req->rq_bytes_sent = 0; +} +#endif + static void xprt_init(struct rpc_xprt *xprt, struct net *net) { kref_init(&xprt->kref); -- cgit v1.2.3 From 50f484e298218b7271fad8a23bd44c82fb3110e1 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 30 Aug 2018 13:27:29 -0400 Subject: SUNRPC: Treat the task and request as separate in the xprt_ops->send_request() When we shift to using the transmit queue, then the task that holds the write lock will not necessarily be the same as the one being transmitted. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 2 +- net/sunrpc/xprt.c | 2 +- net/sunrpc/xprtrdma/svc_rdma_backchannel.c | 3 +-- net/sunrpc/xprtrdma/transport.c | 5 ++--- net/sunrpc/xprtsock.c | 27 +++++++++++++-------------- 5 files changed, 18 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index b8a7de161f67..8c2bb078f00c 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -140,7 +140,7 @@ struct rpc_xprt_ops { void (*connect)(struct rpc_xprt *xprt, struct rpc_task *task); int (*buf_alloc)(struct rpc_task *task); void (*buf_free)(struct rpc_task *task); - int (*send_request)(struct rpc_task *task); + int (*send_request)(struct rpc_rqst *req, struct rpc_task *task); void (*set_retrans_timeout)(struct rpc_task *task); void (*timer)(struct rpc_xprt *xprt, struct rpc_task *task); void (*release_request)(struct rpc_task *task); diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index f5be739492d4..6e735dd1fde0 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1191,7 +1191,7 @@ void xprt_transmit(struct rpc_task *task) } connect_cookie = xprt->connect_cookie; - status = xprt->ops->send_request(task); + status = xprt->ops->send_request(req, task); trace_xprt_transmit(xprt, req->rq_xid, status); if (status != 0) { task->tk_status = status; diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c index 09b12b7568fe..d1618c70edb4 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c +++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c @@ -215,9 +215,8 @@ drop_connection: * connection. */ static int -xprt_rdma_bc_send_request(struct rpc_task *task) +xprt_rdma_bc_send_request(struct rpc_rqst *rqst, struct rpc_task *task) { - struct rpc_rqst *rqst = task->tk_rqstp; struct svc_xprt *sxprt = rqst->rq_xprt->bc_xprt; struct svcxprt_rdma *rdma; int ret; diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 143ce2579ba9..fa684bf4d090 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -706,9 +706,8 @@ xprt_rdma_free(struct rpc_task *task) * sent. Do not try to send this message again. */ static int -xprt_rdma_send_request(struct rpc_task *task) +xprt_rdma_send_request(struct rpc_rqst *rqst, struct rpc_task *task) { - struct rpc_rqst *rqst = task->tk_rqstp; struct rpc_xprt *xprt = rqst->rq_xprt; struct rpcrdma_req *req = rpcr_to_rdmar(rqst); struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt); @@ -741,7 +740,7 @@ xprt_rdma_send_request(struct rpc_task *task) /* An RPC with no reply will throw off credit accounting, * so drop the connection to reset the credit grant. */ - if (!rpc_reply_expected(task)) + if (!rpc_reply_expected(rqst->rq_task)) goto drop_connection; return 0; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 8d6404259ff9..b8143eded4af 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -449,12 +449,12 @@ static void xs_nospace_callback(struct rpc_task *task) /** * xs_nospace - place task on wait queue if transmit was incomplete + * @req: pointer to RPC request * @task: task to put to sleep * */ -static int xs_nospace(struct rpc_task *task) +static int xs_nospace(struct rpc_rqst *req, struct rpc_task *task) { - struct rpc_rqst *req = task->tk_rqstp; struct rpc_xprt *xprt = req->rq_xprt; struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); struct sock *sk = transport->inet; @@ -513,6 +513,7 @@ static inline void xs_encode_stream_record_marker(struct xdr_buf *buf) /** * xs_local_send_request - write an RPC request to an AF_LOCAL socket + * @req: pointer to RPC request * @task: RPC task that manages the state of an RPC request * * Return values: @@ -522,9 +523,8 @@ static inline void xs_encode_stream_record_marker(struct xdr_buf *buf) * ENOTCONN: Caller needs to invoke connect logic then call again * other: Some other error occured, the request was not sent */ -static int xs_local_send_request(struct rpc_task *task) +static int xs_local_send_request(struct rpc_rqst *req, struct rpc_task *task) { - struct rpc_rqst *req = task->tk_rqstp; struct rpc_xprt *xprt = req->rq_xprt; struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); @@ -569,7 +569,7 @@ static int xs_local_send_request(struct rpc_task *task) case -ENOBUFS: break; case -EAGAIN: - status = xs_nospace(task); + status = xs_nospace(req, task); break; default: dprintk("RPC: sendmsg returned unrecognized error %d\n", @@ -585,6 +585,7 @@ static int xs_local_send_request(struct rpc_task *task) /** * xs_udp_send_request - write an RPC request to a UDP socket + * @req: pointer to RPC request * @task: address of RPC task that manages the state of an RPC request * * Return values: @@ -594,9 +595,8 @@ static int xs_local_send_request(struct rpc_task *task) * ENOTCONN: Caller needs to invoke connect logic then call again * other: Some other error occurred, the request was not sent */ -static int xs_udp_send_request(struct rpc_task *task) +static int xs_udp_send_request(struct rpc_rqst *req, struct rpc_task *task) { - struct rpc_rqst *req = task->tk_rqstp; struct rpc_xprt *xprt = req->rq_xprt; struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); struct xdr_buf *xdr = &req->rq_snd_buf; @@ -638,7 +638,7 @@ process_status: /* Should we call xs_close() here? */ break; case -EAGAIN: - status = xs_nospace(task); + status = xs_nospace(req, task); break; case -ENETUNREACH: case -ENOBUFS: @@ -658,6 +658,7 @@ process_status: /** * xs_tcp_send_request - write an RPC request to a TCP socket + * @req: pointer to RPC request * @task: address of RPC task that manages the state of an RPC request * * Return values: @@ -670,9 +671,8 @@ process_status: * XXX: In the case of soft timeouts, should we eventually give up * if sendmsg is not able to make progress? */ -static int xs_tcp_send_request(struct rpc_task *task) +static int xs_tcp_send_request(struct rpc_rqst *req, struct rpc_task *task) { - struct rpc_rqst *req = task->tk_rqstp; struct rpc_xprt *xprt = req->rq_xprt; struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); struct xdr_buf *xdr = &req->rq_snd_buf; @@ -697,7 +697,7 @@ static int xs_tcp_send_request(struct rpc_task *task) * completes while the socket holds a reference to the pages, * then we may end up resending corrupted data. */ - if (task->tk_flags & RPC_TASK_SENT) + if (req->rq_task->tk_flags & RPC_TASK_SENT) zerocopy = false; if (test_bit(XPRT_SOCK_UPD_TIMEOUT, &transport->sock_state)) @@ -761,7 +761,7 @@ static int xs_tcp_send_request(struct rpc_task *task) /* Should we call xs_close() here? */ break; case -EAGAIN: - status = xs_nospace(task); + status = xs_nospace(req, task); break; case -ECONNRESET: case -ECONNREFUSED: @@ -2706,9 +2706,8 @@ static int bc_sendto(struct rpc_rqst *req) /* * The send routine. Borrows from svc_send */ -static int bc_send_request(struct rpc_task *task) +static int bc_send_request(struct rpc_rqst *req, struct rpc_task *task) { - struct rpc_rqst *req = task->tk_rqstp; struct svc_xprt *xprt; int len; -- cgit v1.2.3 From 918f3c1fe83c5baa4892b943d3f5ac7191d8fb74 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 9 Sep 2018 11:37:22 -0400 Subject: SUNRPC: Improve latency for interactive tasks One of the intentions with the priority queues was to ensure that no single process can hog the transport. The field task->tk_owner therefore identifies the RPC call's origin, and is intended to allow the RPC layer to organise queues for fairness. This commit therefore modifies the transmit queue to group requests by task->tk_owner, and ensures that we round robin among those groups. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 + net/sunrpc/xprt.c | 27 ++++++++++++++++++++++++--- 2 files changed, 25 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 8c2bb078f00c..e377620b9744 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -89,6 +89,7 @@ struct rpc_rqst { }; struct list_head rq_xmit; /* Send queue */ + struct list_head rq_xmit2; /* Send queue */ void *rq_buffer; /* Call XDR encode buffer */ size_t rq_callsize; diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 9c5a8514d264..44d0eeaddaac 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1053,12 +1053,21 @@ xprt_request_need_enqueue_transmit(struct rpc_task *task, struct rpc_rqst *req) void xprt_request_enqueue_transmit(struct rpc_task *task) { - struct rpc_rqst *req = task->tk_rqstp; + struct rpc_rqst *pos, *req = task->tk_rqstp; struct rpc_xprt *xprt = req->rq_xprt; if (xprt_request_need_enqueue_transmit(task, req)) { spin_lock(&xprt->queue_lock); + list_for_each_entry(pos, &xprt->xmit_queue, rq_xmit) { + if (pos->rq_task->tk_owner != task->tk_owner) + continue; + list_add_tail(&req->rq_xmit2, &pos->rq_xmit2); + INIT_LIST_HEAD(&req->rq_xmit); + goto out; + } list_add_tail(&req->rq_xmit, &xprt->xmit_queue); + INIT_LIST_HEAD(&req->rq_xmit2); +out: set_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate); spin_unlock(&xprt->queue_lock); } @@ -1074,8 +1083,20 @@ xprt_request_enqueue_transmit(struct rpc_task *task) static void xprt_request_dequeue_transmit_locked(struct rpc_task *task) { - if (test_and_clear_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate)) - list_del(&task->tk_rqstp->rq_xmit); + struct rpc_rqst *req = task->tk_rqstp; + + if (!test_and_clear_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate)) + return; + if (!list_empty(&req->rq_xmit)) { + list_del(&req->rq_xmit); + if (!list_empty(&req->rq_xmit2)) { + struct rpc_rqst *next = list_first_entry(&req->rq_xmit2, + struct rpc_rqst, rq_xmit2); + list_del(&req->rq_xmit2); + list_add_tail(&next->rq_xmit, &next->rq_xprt->xmit_queue); + } + } else + list_del(&req->rq_xmit2); } /** -- cgit v1.2.3 From 75891f502f5fc70f52a01af5b924384ed4866907 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 3 Sep 2018 17:37:36 -0400 Subject: SUNRPC: Support for congestion control when queuing is enabled Both RDMA and UDP transports require the request to get a "congestion control" credit before they can be transmitted. Right now, this is done when the request locks the socket. We'd like it to happen when a request attempts to be transmitted for the first time. In order to support retransmission of requests that already hold such credits, we also want to ensure that they get queued first, so that we don't deadlock with requests that have yet to obtain a credit. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 2 + net/sunrpc/clnt.c | 5 ++ net/sunrpc/xprt.c | 128 +++++++++++++++++++++++++++----------- net/sunrpc/xprtrdma/backchannel.c | 3 + net/sunrpc/xprtrdma/transport.c | 3 + net/sunrpc/xprtsock.c | 4 ++ 6 files changed, 109 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index e377620b9744..0d0cc127615e 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -397,6 +397,7 @@ void xprt_complete_rqst(struct rpc_task *task, int copied); void xprt_pin_rqst(struct rpc_rqst *req); void xprt_unpin_rqst(struct rpc_rqst *req); void xprt_release_rqst_cong(struct rpc_task *task); +bool xprt_request_get_cong(struct rpc_xprt *xprt, struct rpc_rqst *req); void xprt_disconnect_done(struct rpc_xprt *xprt); void xprt_force_disconnect(struct rpc_xprt *xprt); void xprt_conditional_disconnect(struct rpc_xprt *xprt, unsigned int cookie); @@ -415,6 +416,7 @@ void xprt_unlock_connect(struct rpc_xprt *, void *); #define XPRT_BINDING (5) #define XPRT_CLOSING (6) #define XPRT_CONGESTED (9) +#define XPRT_CWND_WAIT (10) static inline void xprt_set_connected(struct rpc_xprt *xprt) { diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 8dc3d33827c4..f03911f84953 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1996,6 +1996,11 @@ call_transmit_status(struct rpc_task *task) dprint_status(task); xprt_end_transmit(task); break; + case -EBADSLT: + xprt_end_transmit(task); + task->tk_action = call_transmit; + task->tk_status = 0; + break; case -EBADMSG: xprt_end_transmit(task); task->tk_status = 0; diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 44d0eeaddaac..b03355ae7b16 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -68,8 +68,6 @@ static void xprt_init(struct rpc_xprt *xprt, struct net *net); static __be32 xprt_alloc_xid(struct rpc_xprt *xprt); static void xprt_connect_status(struct rpc_task *task); -static int __xprt_get_cong(struct rpc_xprt *, struct rpc_task *); -static void __xprt_put_cong(struct rpc_xprt *, struct rpc_rqst *); static void xprt_destroy(struct rpc_xprt *xprt); static DEFINE_SPINLOCK(xprt_list_lock); @@ -221,6 +219,31 @@ static void xprt_clear_locked(struct rpc_xprt *xprt) queue_work(xprtiod_workqueue, &xprt->task_cleanup); } +static bool +xprt_need_congestion_window_wait(struct rpc_xprt *xprt) +{ + return test_bit(XPRT_CWND_WAIT, &xprt->state); +} + +static void +xprt_set_congestion_window_wait(struct rpc_xprt *xprt) +{ + if (!list_empty(&xprt->xmit_queue)) { + /* Peek at head of queue to see if it can make progress */ + if (list_first_entry(&xprt->xmit_queue, struct rpc_rqst, + rq_xmit)->rq_cong) + return; + } + set_bit(XPRT_CWND_WAIT, &xprt->state); +} + +static void +xprt_test_and_clear_congestion_window_wait(struct rpc_xprt *xprt) +{ + if (!RPCXPRT_CONGESTED(xprt)) + clear_bit(XPRT_CWND_WAIT, &xprt->state); +} + /* * xprt_reserve_xprt_cong - serialize write access to transports * @task: task that is requesting access to the transport @@ -228,6 +251,7 @@ static void xprt_clear_locked(struct rpc_xprt *xprt) * Same as xprt_reserve_xprt, but Van Jacobson congestion control is * integrated into the decision of whether a request is allowed to be * woken up and given access to the transport. + * Note that the lock is only granted if we know there are free slots. */ int xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task) { @@ -243,14 +267,12 @@ int xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task) xprt->snd_task = task; return 1; } - if (__xprt_get_cong(xprt, task)) { + if (!xprt_need_congestion_window_wait(xprt)) { xprt->snd_task = task; return 1; } xprt_clear_locked(xprt); out_sleep: - if (req) - __xprt_put_cong(xprt, req); dprintk("RPC: %5u failed to lock transport %p\n", task->tk_pid, xprt); task->tk_timeout = 0; task->tk_status = -EAGAIN; @@ -294,32 +316,14 @@ static void __xprt_lock_write_next(struct rpc_xprt *xprt) xprt_clear_locked(xprt); } -static bool __xprt_lock_write_cong_func(struct rpc_task *task, void *data) -{ - struct rpc_xprt *xprt = data; - struct rpc_rqst *req; - - req = task->tk_rqstp; - if (req == NULL) { - xprt->snd_task = task; - return true; - } - if (__xprt_get_cong(xprt, task)) { - xprt->snd_task = task; - req->rq_ntrans++; - return true; - } - return false; -} - static void __xprt_lock_write_next_cong(struct rpc_xprt *xprt) { if (test_and_set_bit(XPRT_LOCKED, &xprt->state)) return; - if (RPCXPRT_CONGESTED(xprt)) + if (xprt_need_congestion_window_wait(xprt)) goto out_unlock; if (rpc_wake_up_first_on_wq(xprtiod_workqueue, &xprt->sending, - __xprt_lock_write_cong_func, xprt)) + __xprt_lock_write_func, xprt)) return; out_unlock: xprt_clear_locked(xprt); @@ -370,16 +374,16 @@ static inline void xprt_release_write(struct rpc_xprt *xprt, struct rpc_task *ta * overflowed. Put the task to sleep if this is the case. */ static int -__xprt_get_cong(struct rpc_xprt *xprt, struct rpc_task *task) +__xprt_get_cong(struct rpc_xprt *xprt, struct rpc_rqst *req) { - struct rpc_rqst *req = task->tk_rqstp; - if (req->rq_cong) return 1; dprintk("RPC: %5u xprt_cwnd_limited cong = %lu cwnd = %lu\n", - task->tk_pid, xprt->cong, xprt->cwnd); - if (RPCXPRT_CONGESTED(xprt)) + req->rq_task->tk_pid, xprt->cong, xprt->cwnd); + if (RPCXPRT_CONGESTED(xprt)) { + xprt_set_congestion_window_wait(xprt); return 0; + } req->rq_cong = 1; xprt->cong += RPC_CWNDSCALE; return 1; @@ -396,9 +400,31 @@ __xprt_put_cong(struct rpc_xprt *xprt, struct rpc_rqst *req) return; req->rq_cong = 0; xprt->cong -= RPC_CWNDSCALE; + xprt_test_and_clear_congestion_window_wait(xprt); __xprt_lock_write_next_cong(xprt); } +/** + * xprt_request_get_cong - Request congestion control credits + * @xprt: pointer to transport + * @req: pointer to RPC request + * + * Useful for transports that require congestion control. + */ +bool +xprt_request_get_cong(struct rpc_xprt *xprt, struct rpc_rqst *req) +{ + bool ret = false; + + if (req->rq_cong) + return true; + spin_lock_bh(&xprt->transport_lock); + ret = __xprt_get_cong(xprt, req) != 0; + spin_unlock_bh(&xprt->transport_lock); + return ret; +} +EXPORT_SYMBOL_GPL(xprt_request_get_cong); + /** * xprt_release_rqst_cong - housekeeping when request is complete * @task: RPC request that recently completed @@ -413,6 +439,20 @@ void xprt_release_rqst_cong(struct rpc_task *task) } EXPORT_SYMBOL_GPL(xprt_release_rqst_cong); +/* + * Clear the congestion window wait flag and wake up the next + * entry on xprt->sending + */ +static void +xprt_clear_congestion_window_wait(struct rpc_xprt *xprt) +{ + if (test_and_clear_bit(XPRT_CWND_WAIT, &xprt->state)) { + spin_lock_bh(&xprt->transport_lock); + __xprt_lock_write_next_cong(xprt); + spin_unlock_bh(&xprt->transport_lock); + } +} + /** * xprt_adjust_cwnd - adjust transport congestion window * @xprt: pointer to xprt @@ -1058,12 +1098,28 @@ xprt_request_enqueue_transmit(struct rpc_task *task) if (xprt_request_need_enqueue_transmit(task, req)) { spin_lock(&xprt->queue_lock); - list_for_each_entry(pos, &xprt->xmit_queue, rq_xmit) { - if (pos->rq_task->tk_owner != task->tk_owner) - continue; - list_add_tail(&req->rq_xmit2, &pos->rq_xmit2); - INIT_LIST_HEAD(&req->rq_xmit); - goto out; + /* + * Requests that carry congestion control credits are added + * to the head of the list to avoid starvation issues. + */ + if (req->rq_cong) { + xprt_clear_congestion_window_wait(xprt); + list_for_each_entry(pos, &xprt->xmit_queue, rq_xmit) { + if (pos->rq_cong) + continue; + /* Note: req is added _before_ pos */ + list_add_tail(&req->rq_xmit, &pos->rq_xmit); + INIT_LIST_HEAD(&req->rq_xmit2); + goto out; + } + } else { + list_for_each_entry(pos, &xprt->xmit_queue, rq_xmit) { + if (pos->rq_task->tk_owner != task->tk_owner) + continue; + list_add_tail(&req->rq_xmit2, &pos->rq_xmit2); + INIT_LIST_HEAD(&req->rq_xmit); + goto out; + } } list_add_tail(&req->rq_xmit, &xprt->xmit_queue); INIT_LIST_HEAD(&req->rq_xmit2); diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c index ed58761e6b23..e7c445cee16f 100644 --- a/net/sunrpc/xprtrdma/backchannel.c +++ b/net/sunrpc/xprtrdma/backchannel.c @@ -200,6 +200,9 @@ int xprt_rdma_bc_send_reply(struct rpc_rqst *rqst) if (!xprt_connected(rqst->rq_xprt)) goto drop_connection; + if (!xprt_request_get_cong(rqst->rq_xprt, rqst)) + return -EBADSLT; + rc = rpcrdma_bc_marshal_reply(rqst); if (rc < 0) goto failed_marshal; diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index fa684bf4d090..9ff322e53f37 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -721,6 +721,9 @@ xprt_rdma_send_request(struct rpc_rqst *rqst, struct rpc_task *task) if (!xprt_connected(xprt)) goto drop_connection; + if (!xprt_request_get_cong(xprt, rqst)) + return -EBADSLT; + rc = rpcrdma_marshal_req(r_xprt, rqst); if (rc < 0) goto failed_marshal; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index b8143eded4af..8831e84a058a 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -609,6 +609,10 @@ static int xs_udp_send_request(struct rpc_rqst *req, struct rpc_task *task) if (!xprt_bound(xprt)) return -ENOTCONN; + + if (!xprt_request_get_cong(xprt, req)) + return -EBADSLT; + req->rq_xtime = ktime_get(); status = xs_sendpages(transport->sock, xs_addr(xprt), xprt->addrlen, xdr, 0, true, &sent); -- cgit v1.2.3 From 36bd7de949f41d586ef7794169af75462b67acbc Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 3 Sep 2018 18:41:32 -0400 Subject: SUNRPC: Turn off throttling of RPC slots for TCP sockets The theory was that we would need to grab the socket lock anyway, so we might as well use it to gate the allocation of RPC slots for a TCP socket. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 - net/sunrpc/xprt.c | 14 -------------- net/sunrpc/xprtsock.c | 2 +- 3 files changed, 1 insertion(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 0d0cc127615e..14c9b4d49fb4 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -343,7 +343,6 @@ int xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req); -void xprt_lock_and_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task); bool xprt_prepare_transmit(struct rpc_task *task); void xprt_request_enqueue_transmit(struct rpc_task *task); void xprt_request_enqueue_receive(struct rpc_task *task); diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 533df198a0e9..849e102e3c5a 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1429,20 +1429,6 @@ out_init_req: } EXPORT_SYMBOL_GPL(xprt_alloc_slot); -void xprt_lock_and_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task) -{ - /* Note: grabbing the xprt_lock_write() ensures that we throttle - * new slot allocation if the transport is congested (i.e. when - * reconnecting a stream transport or when out of socket write - * buffer space). - */ - if (xprt_lock_write(xprt, task)) { - xprt_alloc_slot(xprt, task); - xprt_release_write(xprt, task); - } -} -EXPORT_SYMBOL_GPL(xprt_lock_and_alloc_slot); - void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req) { spin_lock(&xprt->reserve_lock); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 8831e84a058a..f54e8110f4c6 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2809,7 +2809,7 @@ static const struct rpc_xprt_ops xs_udp_ops = { static const struct rpc_xprt_ops xs_tcp_ops = { .reserve_xprt = xprt_reserve_xprt, .release_xprt = xprt_release_xprt, - .alloc_slot = xprt_lock_and_alloc_slot, + .alloc_slot = xprt_alloc_slot, .free_slot = xprt_free_slot, .rpcbind = rpcb_getport_async, .set_port = xs_set_port, -- cgit v1.2.3 From c544577daddb618c7dd5fa7fb98d6a41782f020e Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 3 Sep 2018 23:39:27 -0400 Subject: SUNRPC: Clean up transport write space handling Treat socket write space handling in the same way we now treat transport congestion: by denying the XPRT_LOCK until the transport signals that it has free buffer space. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/svc_xprt.h | 1 - include/linux/sunrpc/xprt.h | 5 +- net/sunrpc/clnt.c | 28 ++++------- net/sunrpc/svc_xprt.c | 2 - net/sunrpc/xprt.c | 77 ++++++++++++++++++------------ net/sunrpc/xprtrdma/rpc_rdma.c | 2 +- net/sunrpc/xprtrdma/svc_rdma_backchannel.c | 7 +-- net/sunrpc/xprtsock.c | 33 +++++-------- 8 files changed, 73 insertions(+), 82 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index c3d72066d4b1..6b7a86c4d6e6 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -84,7 +84,6 @@ struct svc_xprt { struct sockaddr_storage xpt_remote; /* remote peer's address */ size_t xpt_remotelen; /* length of address */ char xpt_remotebuf[INET6_ADDRSTRLEN + 10]; - struct rpc_wait_queue xpt_bc_pending; /* backchannel wait queue */ struct list_head xpt_users; /* callbacks on free */ struct net *xpt_net; diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 14c9b4d49fb4..5600242ccbf9 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -387,8 +387,8 @@ int xprt_load_transport(const char *); void xprt_set_retrans_timeout_def(struct rpc_task *task); void xprt_set_retrans_timeout_rtt(struct rpc_task *task); void xprt_wake_pending_tasks(struct rpc_xprt *xprt, int status); -void xprt_wait_for_buffer_space(struct rpc_task *task, rpc_action action); -void xprt_write_space(struct rpc_xprt *xprt); +void xprt_wait_for_buffer_space(struct rpc_xprt *xprt); +bool xprt_write_space(struct rpc_xprt *xprt); void xprt_adjust_cwnd(struct rpc_xprt *xprt, struct rpc_task *task, int result); struct rpc_rqst * xprt_lookup_rqst(struct rpc_xprt *xprt, __be32 xid); void xprt_update_rtt(struct rpc_task *task); @@ -416,6 +416,7 @@ void xprt_unlock_connect(struct rpc_xprt *, void *); #define XPRT_CLOSING (6) #define XPRT_CONGESTED (9) #define XPRT_CWND_WAIT (10) +#define XPRT_WRITE_SPACE (11) static inline void xprt_set_connected(struct rpc_xprt *xprt) { diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index f03911f84953..0c4b2e7d791f 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1964,13 +1964,14 @@ call_transmit(struct rpc_task *task) { dprint_status(task); + task->tk_status = 0; + if (test_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate)) { + if (!xprt_prepare_transmit(task)) + return; + xprt_transmit(task); + } task->tk_action = call_transmit_status; - if (!test_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate)) - return; - - if (!xprt_prepare_transmit(task)) - return; - xprt_transmit(task); + xprt_end_transmit(task); } /* @@ -1986,7 +1987,6 @@ call_transmit_status(struct rpc_task *task) * test first. */ if (task->tk_status == 0) { - xprt_end_transmit(task); xprt_request_wait_receive(task); return; } @@ -1994,15 +1994,8 @@ call_transmit_status(struct rpc_task *task) switch (task->tk_status) { default: dprint_status(task); - xprt_end_transmit(task); - break; - case -EBADSLT: - xprt_end_transmit(task); - task->tk_action = call_transmit; - task->tk_status = 0; break; case -EBADMSG: - xprt_end_transmit(task); task->tk_status = 0; task->tk_action = call_encode; break; @@ -2015,6 +2008,7 @@ call_transmit_status(struct rpc_task *task) case -ENOBUFS: rpc_delay(task, HZ>>2); /* fall through */ + case -EBADSLT: case -EAGAIN: task->tk_action = call_transmit; task->tk_status = 0; @@ -2026,7 +2020,6 @@ call_transmit_status(struct rpc_task *task) case -ENETUNREACH: case -EPERM: if (RPC_IS_SOFTCONN(task)) { - xprt_end_transmit(task); if (!task->tk_msg.rpc_proc->p_proc) trace_xprt_ping(task->tk_xprt, task->tk_status); @@ -2069,9 +2062,6 @@ call_bc_transmit(struct rpc_task *task) xprt_transmit(task); - if (task->tk_status == -EAGAIN) - goto out_retry; - xprt_end_transmit(task); dprint_status(task); switch (task->tk_status) { @@ -2087,6 +2077,8 @@ call_bc_transmit(struct rpc_task *task) case -ENOTCONN: case -EPIPE: break; + case -EAGAIN: + goto out_retry; case -ETIMEDOUT: /* * Problem reaching the server. Disconnect and let the diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 5185efb9027b..87533fbb96cf 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -171,7 +171,6 @@ void svc_xprt_init(struct net *net, struct svc_xprt_class *xcl, mutex_init(&xprt->xpt_mutex); spin_lock_init(&xprt->xpt_lock); set_bit(XPT_BUSY, &xprt->xpt_flags); - rpc_init_wait_queue(&xprt->xpt_bc_pending, "xpt_bc_pending"); xprt->xpt_net = get_net(net); strcpy(xprt->xpt_remotebuf, "uninitialized"); } @@ -895,7 +894,6 @@ int svc_send(struct svc_rqst *rqstp) else len = xprt->xpt_ops->xpo_sendto(rqstp); mutex_unlock(&xprt->xpt_mutex); - rpc_wake_up(&xprt->xpt_bc_pending); trace_svc_send(rqstp, len); svc_xprt_release(rqstp); diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 849e102e3c5a..55dc5c7069b9 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -169,6 +169,17 @@ out: } EXPORT_SYMBOL_GPL(xprt_load_transport); +static void xprt_clear_locked(struct rpc_xprt *xprt) +{ + xprt->snd_task = NULL; + if (!test_bit(XPRT_CLOSE_WAIT, &xprt->state)) { + smp_mb__before_atomic(); + clear_bit(XPRT_LOCKED, &xprt->state); + smp_mb__after_atomic(); + } else + queue_work(xprtiod_workqueue, &xprt->task_cleanup); +} + /** * xprt_reserve_xprt - serialize write access to transports * @task: task that is requesting access to the transport @@ -188,10 +199,14 @@ int xprt_reserve_xprt(struct rpc_xprt *xprt, struct rpc_task *task) return 1; goto out_sleep; } + if (test_bit(XPRT_WRITE_SPACE, &xprt->state)) + goto out_unlock; xprt->snd_task = task; return 1; +out_unlock: + xprt_clear_locked(xprt); out_sleep: dprintk("RPC: %5u failed to lock transport %p\n", task->tk_pid, xprt); @@ -208,17 +223,6 @@ out_sleep: } EXPORT_SYMBOL_GPL(xprt_reserve_xprt); -static void xprt_clear_locked(struct rpc_xprt *xprt) -{ - xprt->snd_task = NULL; - if (!test_bit(XPRT_CLOSE_WAIT, &xprt->state)) { - smp_mb__before_atomic(); - clear_bit(XPRT_LOCKED, &xprt->state); - smp_mb__after_atomic(); - } else - queue_work(xprtiod_workqueue, &xprt->task_cleanup); -} - static bool xprt_need_congestion_window_wait(struct rpc_xprt *xprt) { @@ -267,10 +271,13 @@ int xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task) xprt->snd_task = task; return 1; } + if (test_bit(XPRT_WRITE_SPACE, &xprt->state)) + goto out_unlock; if (!xprt_need_congestion_window_wait(xprt)) { xprt->snd_task = task; return 1; } +out_unlock: xprt_clear_locked(xprt); out_sleep: dprintk("RPC: %5u failed to lock transport %p\n", task->tk_pid, xprt); @@ -309,10 +316,12 @@ static void __xprt_lock_write_next(struct rpc_xprt *xprt) { if (test_and_set_bit(XPRT_LOCKED, &xprt->state)) return; - + if (test_bit(XPRT_WRITE_SPACE, &xprt->state)) + goto out_unlock; if (rpc_wake_up_first_on_wq(xprtiod_workqueue, &xprt->sending, __xprt_lock_write_func, xprt)) return; +out_unlock: xprt_clear_locked(xprt); } @@ -320,6 +329,8 @@ static void __xprt_lock_write_next_cong(struct rpc_xprt *xprt) { if (test_and_set_bit(XPRT_LOCKED, &xprt->state)) return; + if (test_bit(XPRT_WRITE_SPACE, &xprt->state)) + goto out_unlock; if (xprt_need_congestion_window_wait(xprt)) goto out_unlock; if (rpc_wake_up_first_on_wq(xprtiod_workqueue, &xprt->sending, @@ -510,39 +521,46 @@ EXPORT_SYMBOL_GPL(xprt_wake_pending_tasks); /** * xprt_wait_for_buffer_space - wait for transport output buffer to clear - * @task: task to be put to sleep - * @action: function pointer to be executed after wait + * @xprt: transport * * Note that we only set the timer for the case of RPC_IS_SOFT(), since * we don't in general want to force a socket disconnection due to * an incomplete RPC call transmission. */ -void xprt_wait_for_buffer_space(struct rpc_task *task, rpc_action action) +void xprt_wait_for_buffer_space(struct rpc_xprt *xprt) { - struct rpc_rqst *req = task->tk_rqstp; - struct rpc_xprt *xprt = req->rq_xprt; - - task->tk_timeout = RPC_IS_SOFT(task) ? req->rq_timeout : 0; - rpc_sleep_on(&xprt->pending, task, action); + set_bit(XPRT_WRITE_SPACE, &xprt->state); } EXPORT_SYMBOL_GPL(xprt_wait_for_buffer_space); +static bool +xprt_clear_write_space_locked(struct rpc_xprt *xprt) +{ + if (test_and_clear_bit(XPRT_WRITE_SPACE, &xprt->state)) { + __xprt_lock_write_next(xprt); + dprintk("RPC: write space: waking waiting task on " + "xprt %p\n", xprt); + return true; + } + return false; +} + /** * xprt_write_space - wake the task waiting for transport output buffer space * @xprt: transport with waiting tasks * * Can be called in a soft IRQ context, so xprt_write_space never sleeps. */ -void xprt_write_space(struct rpc_xprt *xprt) +bool xprt_write_space(struct rpc_xprt *xprt) { + bool ret; + + if (!test_bit(XPRT_WRITE_SPACE, &xprt->state)) + return false; spin_lock_bh(&xprt->transport_lock); - if (xprt->snd_task) { - dprintk("RPC: write space: waking waiting task on " - "xprt %p\n", xprt); - rpc_wake_up_queued_task_on_wq(xprtiod_workqueue, - &xprt->pending, xprt->snd_task); - } + ret = xprt_clear_write_space_locked(xprt); spin_unlock_bh(&xprt->transport_lock); + return ret; } EXPORT_SYMBOL_GPL(xprt_write_space); @@ -653,6 +671,7 @@ void xprt_disconnect_done(struct rpc_xprt *xprt) dprintk("RPC: disconnected transport %p\n", xprt); spin_lock_bh(&xprt->transport_lock); xprt_clear_connected(xprt); + xprt_clear_write_space_locked(xprt); xprt_wake_pending_tasks(xprt, -EAGAIN); spin_unlock_bh(&xprt->transport_lock); } @@ -1326,9 +1345,7 @@ xprt_transmit(struct rpc_task *task) if (!xprt_request_data_received(task) || test_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate)) continue; - } else if (!test_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate)) - rpc_wake_up_queued_task(&xprt->pending, task); - else + } else if (test_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate)) task->tk_status = status; break; } diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 0020dc401215..53fa95d60015 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -866,7 +866,7 @@ rpcrdma_marshal_req(struct rpcrdma_xprt *r_xprt, struct rpc_rqst *rqst) out_err: switch (ret) { case -EAGAIN: - xprt_wait_for_buffer_space(rqst->rq_task, NULL); + xprt_wait_for_buffer_space(rqst->rq_xprt); break; case -ENOBUFS: break; diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c index d1618c70edb4..35a8c3aab302 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c +++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c @@ -224,12 +224,7 @@ xprt_rdma_bc_send_request(struct rpc_rqst *rqst, struct rpc_task *task) dprintk("svcrdma: sending bc call with xid: %08x\n", be32_to_cpu(rqst->rq_xid)); - if (!mutex_trylock(&sxprt->xpt_mutex)) { - rpc_sleep_on(&sxprt->xpt_bc_pending, task, NULL); - if (!mutex_trylock(&sxprt->xpt_mutex)) - return -EAGAIN; - rpc_wake_up_queued_task(&sxprt->xpt_bc_pending, task); - } + mutex_lock(&sxprt->xpt_mutex); ret = -ENOTCONN; rdma = container_of(sxprt, struct svcxprt_rdma, sc_xprt); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index f54e8110f4c6..ef8d0e81cbda 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -440,20 +440,12 @@ out: return err; } -static void xs_nospace_callback(struct rpc_task *task) -{ - struct sock_xprt *transport = container_of(task->tk_rqstp->rq_xprt, struct sock_xprt, xprt); - - transport->inet->sk_write_pending--; -} - /** - * xs_nospace - place task on wait queue if transmit was incomplete + * xs_nospace - handle transmit was incomplete * @req: pointer to RPC request - * @task: task to put to sleep * */ -static int xs_nospace(struct rpc_rqst *req, struct rpc_task *task) +static int xs_nospace(struct rpc_rqst *req) { struct rpc_xprt *xprt = req->rq_xprt; struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); @@ -461,7 +453,8 @@ static int xs_nospace(struct rpc_rqst *req, struct rpc_task *task) int ret = -EAGAIN; dprintk("RPC: %5u xmit incomplete (%u left of %u)\n", - task->tk_pid, req->rq_slen - transport->xmit.offset, + req->rq_task->tk_pid, + req->rq_slen - transport->xmit.offset, req->rq_slen); /* Protect against races with write_space */ @@ -471,7 +464,7 @@ static int xs_nospace(struct rpc_rqst *req, struct rpc_task *task) if (xprt_connected(xprt)) { /* wait for more buffer space */ sk->sk_write_pending++; - xprt_wait_for_buffer_space(task, xs_nospace_callback); + xprt_wait_for_buffer_space(xprt); } else ret = -ENOTCONN; @@ -569,7 +562,7 @@ static int xs_local_send_request(struct rpc_rqst *req, struct rpc_task *task) case -ENOBUFS: break; case -EAGAIN: - status = xs_nospace(req, task); + status = xs_nospace(req); break; default: dprintk("RPC: sendmsg returned unrecognized error %d\n", @@ -642,7 +635,7 @@ process_status: /* Should we call xs_close() here? */ break; case -EAGAIN: - status = xs_nospace(req, task); + status = xs_nospace(req); break; case -ENETUNREACH: case -ENOBUFS: @@ -765,7 +758,7 @@ static int xs_tcp_send_request(struct rpc_rqst *req, struct rpc_task *task) /* Should we call xs_close() here? */ break; case -EAGAIN: - status = xs_nospace(req, task); + status = xs_nospace(req); break; case -ECONNRESET: case -ECONNREFUSED: @@ -1672,7 +1665,8 @@ static void xs_write_space(struct sock *sk) if (!wq || test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &wq->flags) == 0) goto out; - xprt_write_space(xprt); + if (xprt_write_space(xprt)) + sk->sk_write_pending--; out: rcu_read_unlock(); } @@ -2725,12 +2719,7 @@ static int bc_send_request(struct rpc_rqst *req, struct rpc_task *task) * Grab the mutex to serialize data as the connection is shared * with the fore channel */ - if (!mutex_trylock(&xprt->xpt_mutex)) { - rpc_sleep_on(&xprt->xpt_bc_pending, task, NULL); - if (!mutex_trylock(&xprt->xpt_mutex)) - return -EAGAIN; - rpc_wake_up_queued_task(&xprt->xpt_bc_pending, task); - } + mutex_lock(&xprt->xpt_mutex); if (test_bit(XPT_DEAD, &xprt->xpt_flags)) len = -ENOTCONN; else -- cgit v1.2.3 From adfa71446dd0943ba376eff3e05c7c89582f8038 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 3 Sep 2018 23:58:59 -0400 Subject: SUNRPC: Cleanup: remove the unused 'task' argument from the request_send() Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 2 +- net/sunrpc/xprt.c | 2 +- net/sunrpc/xprtrdma/svc_rdma_backchannel.c | 2 +- net/sunrpc/xprtrdma/transport.c | 4 ++-- net/sunrpc/xprtsock.c | 11 ++++------- 5 files changed, 9 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 5600242ccbf9..823860cce0bc 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -141,7 +141,7 @@ struct rpc_xprt_ops { void (*connect)(struct rpc_xprt *xprt, struct rpc_task *task); int (*buf_alloc)(struct rpc_task *task); void (*buf_free)(struct rpc_task *task); - int (*send_request)(struct rpc_rqst *req, struct rpc_task *task); + int (*send_request)(struct rpc_rqst *req); void (*set_retrans_timeout)(struct rpc_task *task); void (*timer)(struct rpc_xprt *xprt, struct rpc_task *task); void (*release_request)(struct rpc_task *task); diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 55dc5c7069b9..c86a5df6c338 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1283,7 +1283,7 @@ xprt_request_transmit(struct rpc_rqst *req, struct rpc_task *snd_task) req->rq_ntrans++; connect_cookie = xprt->connect_cookie; - status = xprt->ops->send_request(req, snd_task); + status = xprt->ops->send_request(req); trace_xprt_transmit(xprt, req->rq_xid, status); if (status != 0) { req->rq_ntrans--; diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c index 35a8c3aab302..992312504cfd 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c +++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c @@ -215,7 +215,7 @@ drop_connection: * connection. */ static int -xprt_rdma_bc_send_request(struct rpc_rqst *rqst, struct rpc_task *task) +xprt_rdma_bc_send_request(struct rpc_rqst *rqst) { struct svc_xprt *sxprt = rqst->rq_xprt->bc_xprt; struct svcxprt_rdma *rdma; diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 9ff322e53f37..a5a6a4a353f2 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -693,7 +693,7 @@ xprt_rdma_free(struct rpc_task *task) /** * xprt_rdma_send_request - marshal and send an RPC request - * @task: RPC task with an RPC message in rq_snd_buf + * @rqst: RPC message in rq_snd_buf * * Caller holds the transport's write lock. * @@ -706,7 +706,7 @@ xprt_rdma_free(struct rpc_task *task) * sent. Do not try to send this message again. */ static int -xprt_rdma_send_request(struct rpc_rqst *rqst, struct rpc_task *task) +xprt_rdma_send_request(struct rpc_rqst *rqst) { struct rpc_xprt *xprt = rqst->rq_xprt; struct rpcrdma_req *req = rpcr_to_rdmar(rqst); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index ef8d0e81cbda..f16406228ead 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -507,7 +507,6 @@ static inline void xs_encode_stream_record_marker(struct xdr_buf *buf) /** * xs_local_send_request - write an RPC request to an AF_LOCAL socket * @req: pointer to RPC request - * @task: RPC task that manages the state of an RPC request * * Return values: * 0: The request has been sent @@ -516,7 +515,7 @@ static inline void xs_encode_stream_record_marker(struct xdr_buf *buf) * ENOTCONN: Caller needs to invoke connect logic then call again * other: Some other error occured, the request was not sent */ -static int xs_local_send_request(struct rpc_rqst *req, struct rpc_task *task) +static int xs_local_send_request(struct rpc_rqst *req) { struct rpc_xprt *xprt = req->rq_xprt; struct sock_xprt *transport = @@ -579,7 +578,6 @@ static int xs_local_send_request(struct rpc_rqst *req, struct rpc_task *task) /** * xs_udp_send_request - write an RPC request to a UDP socket * @req: pointer to RPC request - * @task: address of RPC task that manages the state of an RPC request * * Return values: * 0: The request has been sent @@ -588,7 +586,7 @@ static int xs_local_send_request(struct rpc_rqst *req, struct rpc_task *task) * ENOTCONN: Caller needs to invoke connect logic then call again * other: Some other error occurred, the request was not sent */ -static int xs_udp_send_request(struct rpc_rqst *req, struct rpc_task *task) +static int xs_udp_send_request(struct rpc_rqst *req) { struct rpc_xprt *xprt = req->rq_xprt; struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); @@ -656,7 +654,6 @@ process_status: /** * xs_tcp_send_request - write an RPC request to a TCP socket * @req: pointer to RPC request - * @task: address of RPC task that manages the state of an RPC request * * Return values: * 0: The request has been sent @@ -668,7 +665,7 @@ process_status: * XXX: In the case of soft timeouts, should we eventually give up * if sendmsg is not able to make progress? */ -static int xs_tcp_send_request(struct rpc_rqst *req, struct rpc_task *task) +static int xs_tcp_send_request(struct rpc_rqst *req) { struct rpc_xprt *xprt = req->rq_xprt; struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); @@ -2704,7 +2701,7 @@ static int bc_sendto(struct rpc_rqst *req) /* * The send routine. Borrows from svc_send */ -static int bc_send_request(struct rpc_rqst *req, struct rpc_task *task) +static int bc_send_request(struct rpc_rqst *req) { struct svc_xprt *xprt; int len; -- cgit v1.2.3 From 95f7691daa57bbd68caac2bdad79e0b08f4d46c1 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 7 Sep 2018 08:35:22 -0400 Subject: SUNRPC: Convert xprt receive queue to use an rbtree If the server is slow, we can find ourselves with quite a lot of entries on the receive queue. Converting the search from an O(n) to O(log(n)) can make a significant difference, particularly since we have to hold a number of locks while searching. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 4 +- net/sunrpc/xprt.c | 93 +++++++++++++++++++++++++++++++++++++++------ 2 files changed, 84 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 823860cce0bc..9be399020dab 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -85,7 +85,7 @@ struct rpc_rqst { union { struct list_head rq_list; /* Slot allocation list */ - struct list_head rq_recv; /* Receive queue */ + struct rb_node rq_recv; /* Receive queue */ }; struct list_head rq_xmit; /* Send queue */ @@ -260,7 +260,7 @@ struct rpc_xprt { * backchannel rpc_rqst's */ #endif /* CONFIG_SUNRPC_BACKCHANNEL */ - struct list_head recv_queue; /* Receive queue */ + struct rb_root recv_queue; /* Receive queue */ struct { unsigned long bind_count, /* total number of binds */ diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 11133ba716b9..480461ad0c86 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -753,7 +753,7 @@ static void xprt_schedule_autodisconnect(struct rpc_xprt *xprt) __must_hold(&xprt->transport_lock) { - if (list_empty(&xprt->recv_queue) && xprt_has_timer(xprt)) + if (RB_EMPTY_ROOT(&xprt->recv_queue) && xprt_has_timer(xprt)) mod_timer(&xprt->timer, xprt->last_used + xprt->idle_timeout); } @@ -763,7 +763,7 @@ xprt_init_autodisconnect(struct timer_list *t) struct rpc_xprt *xprt = from_timer(xprt, t, timer); spin_lock(&xprt->transport_lock); - if (!list_empty(&xprt->recv_queue)) + if (!RB_EMPTY_ROOT(&xprt->recv_queue)) goto out_abort; /* Reset xprt->last_used to avoid connect/autodisconnect cycling */ xprt->last_used = jiffies; @@ -880,6 +880,75 @@ static void xprt_connect_status(struct rpc_task *task) } } +enum xprt_xid_rb_cmp { + XID_RB_EQUAL, + XID_RB_LEFT, + XID_RB_RIGHT, +}; +static enum xprt_xid_rb_cmp +xprt_xid_cmp(__be32 xid1, __be32 xid2) +{ + if (xid1 == xid2) + return XID_RB_EQUAL; + if ((__force u32)xid1 < (__force u32)xid2) + return XID_RB_LEFT; + return XID_RB_RIGHT; +} + +static struct rpc_rqst * +xprt_request_rb_find(struct rpc_xprt *xprt, __be32 xid) +{ + struct rb_node *n = xprt->recv_queue.rb_node; + struct rpc_rqst *req; + + while (n != NULL) { + req = rb_entry(n, struct rpc_rqst, rq_recv); + switch (xprt_xid_cmp(xid, req->rq_xid)) { + case XID_RB_LEFT: + n = n->rb_left; + break; + case XID_RB_RIGHT: + n = n->rb_right; + break; + case XID_RB_EQUAL: + return req; + } + } + return NULL; +} + +static void +xprt_request_rb_insert(struct rpc_xprt *xprt, struct rpc_rqst *new) +{ + struct rb_node **p = &xprt->recv_queue.rb_node; + struct rb_node *n = NULL; + struct rpc_rqst *req; + + while (*p != NULL) { + n = *p; + req = rb_entry(n, struct rpc_rqst, rq_recv); + switch(xprt_xid_cmp(new->rq_xid, req->rq_xid)) { + case XID_RB_LEFT: + p = &n->rb_left; + break; + case XID_RB_RIGHT: + p = &n->rb_right; + break; + case XID_RB_EQUAL: + WARN_ON_ONCE(new != req); + return; + } + } + rb_link_node(&new->rq_recv, n, p); + rb_insert_color(&new->rq_recv, &xprt->recv_queue); +} + +static void +xprt_request_rb_remove(struct rpc_xprt *xprt, struct rpc_rqst *req) +{ + rb_erase(&req->rq_recv, &xprt->recv_queue); +} + /** * xprt_lookup_rqst - find an RPC request corresponding to an XID * @xprt: transport on which the original request was transmitted @@ -891,12 +960,12 @@ struct rpc_rqst *xprt_lookup_rqst(struct rpc_xprt *xprt, __be32 xid) { struct rpc_rqst *entry; - list_for_each_entry(entry, &xprt->recv_queue, rq_recv) - if (entry->rq_xid == xid) { - trace_xprt_lookup_rqst(xprt, xid, 0); - entry->rq_rtt = ktime_sub(ktime_get(), entry->rq_xtime); - return entry; - } + entry = xprt_request_rb_find(xprt, xid); + if (entry != NULL) { + trace_xprt_lookup_rqst(xprt, xid, 0); + entry->rq_rtt = ktime_sub(ktime_get(), entry->rq_xtime); + return entry; + } dprintk("RPC: xprt_lookup_rqst did not find xid %08x\n", ntohl(xid)); @@ -981,7 +1050,7 @@ xprt_request_enqueue_receive(struct rpc_task *task) sizeof(req->rq_private_buf)); /* Add request to the receive list */ - list_add_tail(&req->rq_recv, &xprt->recv_queue); + xprt_request_rb_insert(xprt, req); set_bit(RPC_TASK_NEED_RECV, &task->tk_runstate); spin_unlock(&xprt->queue_lock); @@ -999,8 +1068,10 @@ xprt_request_enqueue_receive(struct rpc_task *task) static void xprt_request_dequeue_receive_locked(struct rpc_task *task) { + struct rpc_rqst *req = task->tk_rqstp; + if (test_and_clear_bit(RPC_TASK_NEED_RECV, &task->tk_runstate)) - list_del(&task->tk_rqstp->rq_recv); + xprt_request_rb_remove(req->rq_xprt, req); } /** @@ -1711,7 +1782,7 @@ static void xprt_init(struct rpc_xprt *xprt, struct net *net) spin_lock_init(&xprt->queue_lock); INIT_LIST_HEAD(&xprt->free); - INIT_LIST_HEAD(&xprt->recv_queue); + xprt->recv_queue = RB_ROOT; INIT_LIST_HEAD(&xprt->xmit_queue); #if defined(CONFIG_SUNRPC_BACKCHANNEL) spin_lock_init(&xprt->bc_pa_lock); -- cgit v1.2.3 From f42f7c283078ce3c1e8368b140e270755b1ae313 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 8 Sep 2018 22:09:48 -0400 Subject: SUNRPC: Fix priority queue fairness Fix up the priority queue to not batch by owner, but by queue, so that we allow '1 << priority' elements to be dequeued before switching to the next priority queue. The owner field is still used to wake up requests in round robin order by owner to avoid single processes hogging the RPC layer by loading the queues. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/sched.h | 2 - net/sunrpc/sched.c | 109 +++++++++++++++++++++---------------------- 2 files changed, 54 insertions(+), 57 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 8840a420cf4c..7b540c066594 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -189,7 +189,6 @@ struct rpc_timer { struct rpc_wait_queue { spinlock_t lock; struct list_head tasks[RPC_NR_PRIORITY]; /* task queue for each priority level */ - pid_t owner; /* process id of last task serviced */ unsigned char maxpriority; /* maximum priority (0 if queue is not a priority queue) */ unsigned char priority; /* current priority */ unsigned char nr; /* # tasks remaining for cookie */ @@ -205,7 +204,6 @@ struct rpc_wait_queue { * from a single cookie. The aim is to improve * performance of NFS operations such as read/write. */ -#define RPC_BATCH_COUNT 16 #define RPC_IS_PRIORITY(q) ((q)->maxpriority > 0) /* diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 9a8ec012b449..57ca5bead1cb 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -99,64 +99,78 @@ __rpc_add_timer(struct rpc_wait_queue *queue, struct rpc_task *task) list_add(&task->u.tk_wait.timer_list, &queue->timer_list.list); } -static void rpc_rotate_queue_owner(struct rpc_wait_queue *queue) -{ - struct list_head *q = &queue->tasks[queue->priority]; - struct rpc_task *task; - - if (!list_empty(q)) { - task = list_first_entry(q, struct rpc_task, u.tk_wait.list); - if (task->tk_owner == queue->owner) - list_move_tail(&task->u.tk_wait.list, q); - } -} - static void rpc_set_waitqueue_priority(struct rpc_wait_queue *queue, int priority) { if (queue->priority != priority) { - /* Fairness: rotate the list when changing priority */ - rpc_rotate_queue_owner(queue); queue->priority = priority; + queue->nr = 1U << priority; } } -static void rpc_set_waitqueue_owner(struct rpc_wait_queue *queue, pid_t pid) -{ - queue->owner = pid; - queue->nr = RPC_BATCH_COUNT; -} - static void rpc_reset_waitqueue_priority(struct rpc_wait_queue *queue) { rpc_set_waitqueue_priority(queue, queue->maxpriority); - rpc_set_waitqueue_owner(queue, 0); } /* - * Add new request to a priority queue. + * Add a request to a queue list */ -static void __rpc_add_wait_queue_priority(struct rpc_wait_queue *queue, - struct rpc_task *task, - unsigned char queue_priority) +static void +__rpc_list_enqueue_task(struct list_head *q, struct rpc_task *task) { - struct list_head *q; struct rpc_task *t; - INIT_LIST_HEAD(&task->u.tk_wait.links); - if (unlikely(queue_priority > queue->maxpriority)) - queue_priority = queue->maxpriority; - if (queue_priority > queue->priority) - rpc_set_waitqueue_priority(queue, queue_priority); - q = &queue->tasks[queue_priority]; list_for_each_entry(t, q, u.tk_wait.list) { if (t->tk_owner == task->tk_owner) { - list_add_tail(&task->u.tk_wait.list, &t->u.tk_wait.links); + list_add_tail(&task->u.tk_wait.links, + &t->u.tk_wait.links); + /* Cache the queue head in task->u.tk_wait.list */ + task->u.tk_wait.list.next = q; + task->u.tk_wait.list.prev = NULL; return; } } + INIT_LIST_HEAD(&task->u.tk_wait.links); list_add_tail(&task->u.tk_wait.list, q); } +/* + * Remove request from a queue list + */ +static void +__rpc_list_dequeue_task(struct rpc_task *task) +{ + struct list_head *q; + struct rpc_task *t; + + if (task->u.tk_wait.list.prev == NULL) { + list_del(&task->u.tk_wait.links); + return; + } + if (!list_empty(&task->u.tk_wait.links)) { + t = list_first_entry(&task->u.tk_wait.links, + struct rpc_task, + u.tk_wait.links); + /* Assume __rpc_list_enqueue_task() cached the queue head */ + q = t->u.tk_wait.list.next; + list_add_tail(&t->u.tk_wait.list, q); + list_del(&task->u.tk_wait.links); + } + list_del(&task->u.tk_wait.list); +} + +/* + * Add new request to a priority queue. + */ +static void __rpc_add_wait_queue_priority(struct rpc_wait_queue *queue, + struct rpc_task *task, + unsigned char queue_priority) +{ + if (unlikely(queue_priority > queue->maxpriority)) + queue_priority = queue->maxpriority; + __rpc_list_enqueue_task(&queue->tasks[queue_priority], task); +} + /* * Add new request to wait queue. * @@ -194,13 +208,7 @@ static void __rpc_add_wait_queue(struct rpc_wait_queue *queue, */ static void __rpc_remove_wait_queue_priority(struct rpc_task *task) { - struct rpc_task *t; - - if (!list_empty(&task->u.tk_wait.links)) { - t = list_entry(task->u.tk_wait.links.next, struct rpc_task, u.tk_wait.list); - list_move(&t->u.tk_wait.list, &task->u.tk_wait.list); - list_splice_init(&task->u.tk_wait.links, &t->u.tk_wait.links); - } + __rpc_list_dequeue_task(task); } /* @@ -212,7 +220,8 @@ static void __rpc_remove_wait_queue(struct rpc_wait_queue *queue, struct rpc_tas __rpc_disable_timer(queue, task); if (RPC_IS_PRIORITY(queue)) __rpc_remove_wait_queue_priority(task); - list_del(&task->u.tk_wait.list); + else + list_del(&task->u.tk_wait.list); queue->qlen--; dprintk("RPC: %5u removed from queue %p \"%s\"\n", task->tk_pid, queue, rpc_qname(queue)); @@ -545,17 +554,9 @@ static struct rpc_task *__rpc_find_next_queued_priority(struct rpc_wait_queue *q * Service a batch of tasks from a single owner. */ q = &queue->tasks[queue->priority]; - if (!list_empty(q)) { - task = list_entry(q->next, struct rpc_task, u.tk_wait.list); - if (queue->owner == task->tk_owner) { - if (--queue->nr) - goto out; - list_move_tail(&task->u.tk_wait.list, q); - } - /* - * Check if we need to switch queues. - */ - goto new_owner; + if (!list_empty(q) && --queue->nr) { + task = list_first_entry(q, struct rpc_task, u.tk_wait.list); + goto out; } /* @@ -567,7 +568,7 @@ static struct rpc_task *__rpc_find_next_queued_priority(struct rpc_wait_queue *q else q = q - 1; if (!list_empty(q)) { - task = list_entry(q->next, struct rpc_task, u.tk_wait.list); + task = list_first_entry(q, struct rpc_task, u.tk_wait.list); goto new_queue; } } while (q != &queue->tasks[queue->priority]); @@ -577,8 +578,6 @@ static struct rpc_task *__rpc_find_next_queued_priority(struct rpc_wait_queue *q new_queue: rpc_set_waitqueue_priority(queue, (unsigned int)(q - &queue->tasks[0])); -new_owner: - rpc_set_waitqueue_owner(queue, task->tk_owner); out: return task; } -- cgit v1.2.3 From 431f6eb3570f286036bc8718a908a283f5d99473 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 16 Sep 2018 00:08:20 -0400 Subject: SUNRPC: Add a label for RPC calls that require allocation on receive If the RPC call relies on the receive call allocating pages as buffers, then let's label it so that we a) Don't leak memory by allocating pages for requests that do not expect this behaviour b) Can optimise for the common case where calls do not require allocation. Signed-off-by: Trond Myklebust --- fs/nfs/nfs3xdr.c | 4 +++- include/linux/sunrpc/xdr.h | 1 + net/sunrpc/auth_gss/gss_rpc_xdr.c | 1 + net/sunrpc/socklib.c | 2 +- 4 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 64e4fa33d89f..d8c4c10b15f7 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -1364,10 +1364,12 @@ static void nfs3_xdr_enc_getacl3args(struct rpc_rqst *req, encode_nfs_fh3(xdr, args->fh); encode_uint32(xdr, args->mask); - if (args->mask & (NFS_ACL | NFS_DFACL)) + if (args->mask & (NFS_ACL | NFS_DFACL)) { prepare_reply_buffer(req, args->pages, 0, NFSACL_MAXPAGES << PAGE_SHIFT, ACL3_getaclres_sz); + req->rq_rcv_buf.flags |= XDRBUF_SPARSE_PAGES; + } } static void nfs3_xdr_enc_setacl3args(struct rpc_rqst *req, diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 2bd68177a442..431829233392 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -58,6 +58,7 @@ struct xdr_buf { flags; /* Flags for data disposition */ #define XDRBUF_READ 0x01 /* target of file read */ #define XDRBUF_WRITE 0x02 /* source of file write */ +#define XDRBUF_SPARSE_PAGES 0x04 /* Page array is sparse */ unsigned int buflen, /* Total length of storage buffer */ len; /* Length of XDR encoded message */ diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.c b/net/sunrpc/auth_gss/gss_rpc_xdr.c index 444380f968f1..006062ad5f58 100644 --- a/net/sunrpc/auth_gss/gss_rpc_xdr.c +++ b/net/sunrpc/auth_gss/gss_rpc_xdr.c @@ -784,6 +784,7 @@ void gssx_enc_accept_sec_context(struct rpc_rqst *req, xdr_inline_pages(&req->rq_rcv_buf, PAGE_SIZE/2 /* pretty arbitrary */, arg->pages, 0 /* page base */, arg->npages * PAGE_SIZE); + req->rq_rcv_buf.flags |= XDRBUF_SPARSE_PAGES; done: if (err) dprintk("RPC: gssx_enc_accept_sec_context: %d\n", err); diff --git a/net/sunrpc/socklib.c b/net/sunrpc/socklib.c index f217c348b341..08f00a98151f 100644 --- a/net/sunrpc/socklib.c +++ b/net/sunrpc/socklib.c @@ -104,7 +104,7 @@ ssize_t xdr_partial_copy_from_skb(struct xdr_buf *xdr, unsigned int base, struct /* ACL likes to be lazy in allocating pages - ACLs * are small by default but can get huge. */ - if (unlikely(*ppage == NULL)) { + if ((xdr->flags & XDRBUF_SPARSE_PAGES) && *ppage == NULL) { *ppage = alloc_page(GFP_ATOMIC); if (unlikely(*ppage == NULL)) { if (copied == 0) -- cgit v1.2.3 From 9d96acbc7f376dc1ffcedca0c349dd3389187a38 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 13 Sep 2018 12:22:04 -0400 Subject: SUNRPC: Add a bvec array to struct xdr_buf for use with iovec_iter() Add a bvec array to struct xdr_buf, and have the client allocate it when we need to receive data into pages. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xdr.h | 7 +++++++ include/linux/sunrpc/xprt.h | 2 ++ net/sunrpc/clnt.c | 4 +++- net/sunrpc/xdr.c | 34 ++++++++++++++++++++++++++++++++++ net/sunrpc/xprt.c | 17 +++++++++++++++++ 5 files changed, 63 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 431829233392..745587132a87 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -18,6 +18,7 @@ #include #include +struct bio_vec; struct rpc_rqst; /* @@ -52,6 +53,7 @@ struct xdr_buf { struct kvec head[1], /* RPC header + non-page data */ tail[1]; /* Appended after page data */ + struct bio_vec *bvec; struct page ** pages; /* Array of pages */ unsigned int page_base, /* Start of page data */ page_len, /* Length of page data */ @@ -70,6 +72,8 @@ xdr_buf_init(struct xdr_buf *buf, void *start, size_t len) buf->head[0].iov_base = start; buf->head[0].iov_len = len; buf->tail[0].iov_len = 0; + buf->bvec = NULL; + buf->pages = NULL; buf->page_len = 0; buf->flags = 0; buf->len = 0; @@ -116,6 +120,9 @@ __be32 *xdr_decode_netobj(__be32 *p, struct xdr_netobj *); void xdr_inline_pages(struct xdr_buf *, unsigned int, struct page **, unsigned int, unsigned int); void xdr_terminate_string(struct xdr_buf *, const u32); +size_t xdr_buf_pagecount(struct xdr_buf *buf); +int xdr_alloc_bvec(struct xdr_buf *buf, gfp_t gfp); +void xdr_free_bvec(struct xdr_buf *buf); static inline __be32 *xdr_encode_array(__be32 *p, const void *s, unsigned int len) { diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 9be399020dab..a4ab4f8d9140 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -141,6 +141,7 @@ struct rpc_xprt_ops { void (*connect)(struct rpc_xprt *xprt, struct rpc_task *task); int (*buf_alloc)(struct rpc_task *task); void (*buf_free)(struct rpc_task *task); + void (*prepare_request)(struct rpc_rqst *req); int (*send_request)(struct rpc_rqst *req); void (*set_retrans_timeout)(struct rpc_task *task); void (*timer)(struct rpc_xprt *xprt, struct rpc_task *task); @@ -343,6 +344,7 @@ int xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req); +void xprt_request_prepare(struct rpc_rqst *req); bool xprt_prepare_transmit(struct rpc_task *task); void xprt_request_enqueue_transmit(struct rpc_task *task); void xprt_request_enqueue_receive(struct rpc_task *task); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 0c4b2e7d791f..ae3b8145da35 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1753,6 +1753,8 @@ rpc_xdr_encode(struct rpc_task *task) task->tk_status = rpcauth_wrap_req(task, encode, req, p, task->tk_msg.rpc_argp); + if (task->tk_status == 0) + xprt_request_prepare(req); } /* @@ -1768,7 +1770,7 @@ call_encode(struct rpc_task *task) /* Did the encode result in an error condition? */ if (task->tk_status != 0) { /* Was the error nonfatal? */ - if (task->tk_status == -EAGAIN) + if (task->tk_status == -EAGAIN || task->tk_status == -ENOMEM) rpc_delay(task, HZ >> 4); else rpc_exit(task, task->tk_status); diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 30afbd236656..2bbb8d38d2bf 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -15,6 +15,7 @@ #include #include #include +#include /* * XDR functions for basic NFS types @@ -128,6 +129,39 @@ xdr_terminate_string(struct xdr_buf *buf, const u32 len) } EXPORT_SYMBOL_GPL(xdr_terminate_string); +size_t +xdr_buf_pagecount(struct xdr_buf *buf) +{ + if (!buf->page_len) + return 0; + return (buf->page_base + buf->page_len + PAGE_SIZE - 1) >> PAGE_SHIFT; +} + +int +xdr_alloc_bvec(struct xdr_buf *buf, gfp_t gfp) +{ + size_t i, n = xdr_buf_pagecount(buf); + + if (n != 0 && buf->bvec == NULL) { + buf->bvec = kmalloc_array(n, sizeof(buf->bvec[0]), gfp); + if (!buf->bvec) + return -ENOMEM; + for (i = 0; i < n; i++) { + buf->bvec[i].bv_page = buf->pages[i]; + buf->bvec[i].bv_len = PAGE_SIZE; + buf->bvec[i].bv_offset = 0; + } + } + return 0; +} + +void +xdr_free_bvec(struct xdr_buf *buf) +{ + kfree(buf->bvec); + buf->bvec = NULL; +} + void xdr_inline_pages(struct xdr_buf *xdr, unsigned int offset, struct page **pages, unsigned int base, unsigned int len) diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 7333874c6595..7ee9f1e996db 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1263,6 +1263,22 @@ xprt_request_dequeue_transmit(struct rpc_task *task) spin_unlock(&xprt->queue_lock); } +/** + * xprt_request_prepare - prepare an encoded request for transport + * @req: pointer to rpc_rqst + * + * Calls into the transport layer to do whatever is needed to prepare + * the request for transmission or receive. + */ +void +xprt_request_prepare(struct rpc_rqst *req) +{ + struct rpc_xprt *xprt = req->rq_xprt; + + if (xprt->ops->prepare_request) + xprt->ops->prepare_request(req); +} + /** * xprt_request_need_retransmit - Test if a task needs retransmission * @task: pointer to rpc_task @@ -1727,6 +1743,7 @@ void xprt_release(struct rpc_task *task) if (req->rq_buffer) xprt->ops->buf_free(task); xprt_inject_disconnect(xprt); + xdr_free_bvec(&req->rq_rcv_buf); if (req->rq_cred != NULL) put_rpccred(req->rq_cred); task->tk_rqstp = NULL; -- cgit v1.2.3 From 277e4ab7d530bf287e02b65cfcd3ea8f489784f6 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 14 Sep 2018 09:49:06 -0400 Subject: SUNRPC: Simplify TCP receive code by switching to using iterators Most of this code should also be reusable with other socket types. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprtsock.h | 19 +- include/trace/events/sunrpc.h | 15 +- net/sunrpc/xprtsock.c | 697 +++++++++++++++++++--------------------- 3 files changed, 338 insertions(+), 393 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h index 005cfb6e7238..458bfe0137f5 100644 --- a/include/linux/sunrpc/xprtsock.h +++ b/include/linux/sunrpc/xprtsock.h @@ -31,15 +31,16 @@ struct sock_xprt { * State of TCP reply receive */ struct { - __be32 fraghdr, + struct { + __be32 fraghdr, xid, calldir; + } __attribute__((packed)); u32 offset, len; - unsigned long copied, - flags; + unsigned long copied; } recv; /* @@ -76,21 +77,9 @@ struct sock_xprt { void (*old_error_report)(struct sock *); }; -/* - * TCP receive state flags - */ -#define TCP_RCV_LAST_FRAG (1UL << 0) -#define TCP_RCV_COPY_FRAGHDR (1UL << 1) -#define TCP_RCV_COPY_XID (1UL << 2) -#define TCP_RCV_COPY_DATA (1UL << 3) -#define TCP_RCV_READ_CALLDIR (1UL << 4) -#define TCP_RCV_COPY_CALLDIR (1UL << 5) - /* * TCP RPC flags */ -#define TCP_RPC_REPLY (1UL << 6) - #define XPRT_SOCK_CONNECTING 1U #define XPRT_SOCK_DATA_READY (2) #define XPRT_SOCK_UPD_TIMEOUT (3) diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 0aa347194e0f..19e08d12696c 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -497,16 +497,6 @@ TRACE_EVENT(xs_tcp_data_ready, __get_str(port), __entry->err, __entry->total) ); -#define rpc_show_sock_xprt_flags(flags) \ - __print_flags(flags, "|", \ - { TCP_RCV_LAST_FRAG, "TCP_RCV_LAST_FRAG" }, \ - { TCP_RCV_COPY_FRAGHDR, "TCP_RCV_COPY_FRAGHDR" }, \ - { TCP_RCV_COPY_XID, "TCP_RCV_COPY_XID" }, \ - { TCP_RCV_COPY_DATA, "TCP_RCV_COPY_DATA" }, \ - { TCP_RCV_READ_CALLDIR, "TCP_RCV_READ_CALLDIR" }, \ - { TCP_RCV_COPY_CALLDIR, "TCP_RCV_COPY_CALLDIR" }, \ - { TCP_RPC_REPLY, "TCP_RPC_REPLY" }) - TRACE_EVENT(xs_tcp_data_recv, TP_PROTO(struct sock_xprt *xs), @@ -516,7 +506,6 @@ TRACE_EVENT(xs_tcp_data_recv, __string(addr, xs->xprt.address_strings[RPC_DISPLAY_ADDR]) __string(port, xs->xprt.address_strings[RPC_DISPLAY_PORT]) __field(u32, xid) - __field(unsigned long, flags) __field(unsigned long, copied) __field(unsigned int, reclen) __field(unsigned long, offset) @@ -526,15 +515,13 @@ TRACE_EVENT(xs_tcp_data_recv, __assign_str(addr, xs->xprt.address_strings[RPC_DISPLAY_ADDR]); __assign_str(port, xs->xprt.address_strings[RPC_DISPLAY_PORT]); __entry->xid = be32_to_cpu(xs->recv.xid); - __entry->flags = xs->recv.flags; __entry->copied = xs->recv.copied; __entry->reclen = xs->recv.len; __entry->offset = xs->recv.offset; ), - TP_printk("peer=[%s]:%s xid=0x%08x flags=%s copied=%lu reclen=%u offset=%lu", + TP_printk("peer=[%s]:%s xid=0x%08x copied=%lu reclen=%u offset=%lu", __get_str(addr), __get_str(port), __entry->xid, - rpc_show_sock_xprt_flags(__entry->flags), __entry->copied, __entry->reclen, __entry->offset) ); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index f16406228ead..06aa75008708 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -47,13 +47,13 @@ #include #include #include +#include +#include #include #include "sunrpc.h" -#define RPC_TCP_READ_CHUNK_SZ (3*512*1024) - static void xs_close(struct rpc_xprt *xprt); static void xs_tcp_set_socket_timeouts(struct rpc_xprt *xprt, struct socket *sock); @@ -325,6 +325,323 @@ static void xs_free_peer_addresses(struct rpc_xprt *xprt) } } +static size_t +xs_alloc_sparse_pages(struct xdr_buf *buf, size_t want, gfp_t gfp) +{ + size_t i,n; + + if (!(buf->flags & XDRBUF_SPARSE_PAGES)) + return want; + if (want > buf->page_len) + want = buf->page_len; + n = (buf->page_base + want + PAGE_SIZE - 1) >> PAGE_SHIFT; + for (i = 0; i < n; i++) { + if (buf->pages[i]) + continue; + buf->bvec[i].bv_page = buf->pages[i] = alloc_page(gfp); + if (!buf->pages[i]) { + buf->page_len = (i * PAGE_SIZE) - buf->page_base; + return buf->page_len; + } + } + return want; +} + +static ssize_t +xs_sock_recvmsg(struct socket *sock, struct msghdr *msg, int flags, size_t seek) +{ + ssize_t ret; + if (seek != 0) + iov_iter_advance(&msg->msg_iter, seek); + ret = sock_recvmsg(sock, msg, flags); + return ret > 0 ? ret + seek : ret; +} + +static ssize_t +xs_read_kvec(struct socket *sock, struct msghdr *msg, int flags, + struct kvec *kvec, size_t count, size_t seek) +{ + iov_iter_kvec(&msg->msg_iter, READ | ITER_KVEC, kvec, 1, count); + return xs_sock_recvmsg(sock, msg, flags, seek); +} + +static ssize_t +xs_read_bvec(struct socket *sock, struct msghdr *msg, int flags, + struct bio_vec *bvec, unsigned long nr, size_t count, + size_t seek) +{ + iov_iter_bvec(&msg->msg_iter, READ | ITER_BVEC, bvec, nr, count); + return xs_sock_recvmsg(sock, msg, flags, seek); +} + +static ssize_t +xs_read_discard(struct socket *sock, struct msghdr *msg, int flags, + size_t count) +{ + struct kvec kvec = { 0 }; + return xs_read_kvec(sock, msg, flags | MSG_TRUNC, &kvec, count, 0); +} + +static ssize_t +xs_read_xdr_buf(struct socket *sock, struct msghdr *msg, int flags, + struct xdr_buf *buf, size_t count, size_t seek, size_t *read) +{ + size_t want, seek_init = seek, offset = 0; + ssize_t ret; + + if (seek < buf->head[0].iov_len) { + want = min_t(size_t, count, buf->head[0].iov_len); + ret = xs_read_kvec(sock, msg, flags, &buf->head[0], want, seek); + if (ret <= 0) + goto sock_err; + offset += ret; + if (offset == count || msg->msg_flags & (MSG_EOR|MSG_TRUNC)) + goto out; + if (ret != want) + goto eagain; + seek = 0; + } else { + seek -= buf->head[0].iov_len; + offset += buf->head[0].iov_len; + } + if (seek < buf->page_len) { + want = xs_alloc_sparse_pages(buf, + min_t(size_t, count - offset, buf->page_len), + GFP_NOWAIT); + ret = xs_read_bvec(sock, msg, flags, buf->bvec, + xdr_buf_pagecount(buf), + want + buf->page_base, + seek + buf->page_base); + if (ret <= 0) + goto sock_err; + offset += ret - buf->page_base; + if (offset == count || msg->msg_flags & (MSG_EOR|MSG_TRUNC)) + goto out; + if (ret != want) + goto eagain; + seek = 0; + } else { + seek -= buf->page_len; + offset += buf->page_len; + } + if (seek < buf->tail[0].iov_len) { + want = min_t(size_t, count - offset, buf->tail[0].iov_len); + ret = xs_read_kvec(sock, msg, flags, &buf->tail[0], want, seek); + if (ret <= 0) + goto sock_err; + offset += ret; + if (offset == count || msg->msg_flags & (MSG_EOR|MSG_TRUNC)) + goto out; + if (ret != want) + goto eagain; + } else + offset += buf->tail[0].iov_len; + ret = -EMSGSIZE; + msg->msg_flags |= MSG_TRUNC; +out: + *read = offset - seek_init; + return ret; +eagain: + ret = -EAGAIN; + goto out; +sock_err: + offset += seek; + goto out; +} + +static void +xs_read_header(struct sock_xprt *transport, struct xdr_buf *buf) +{ + if (!transport->recv.copied) { + if (buf->head[0].iov_len >= transport->recv.offset) + memcpy(buf->head[0].iov_base, + &transport->recv.xid, + transport->recv.offset); + transport->recv.copied = transport->recv.offset; + } +} + +static bool +xs_read_stream_request_done(struct sock_xprt *transport) +{ + return transport->recv.fraghdr & cpu_to_be32(RPC_LAST_STREAM_FRAGMENT); +} + +static ssize_t +xs_read_stream_request(struct sock_xprt *transport, struct msghdr *msg, + int flags, struct rpc_rqst *req) +{ + struct xdr_buf *buf = &req->rq_private_buf; + size_t want, read; + ssize_t ret; + + xs_read_header(transport, buf); + + want = transport->recv.len - transport->recv.offset; + ret = xs_read_xdr_buf(transport->sock, msg, flags, buf, + transport->recv.copied + want, transport->recv.copied, + &read); + transport->recv.offset += read; + transport->recv.copied += read; + if (transport->recv.offset == transport->recv.len) { + if (xs_read_stream_request_done(transport)) + msg->msg_flags |= MSG_EOR; + return transport->recv.copied; + } + + switch (ret) { + case -EMSGSIZE: + return transport->recv.copied; + case 0: + return -ESHUTDOWN; + default: + if (ret < 0) + return ret; + } + return -EAGAIN; +} + +static size_t +xs_read_stream_headersize(bool isfrag) +{ + if (isfrag) + return sizeof(__be32); + return 3 * sizeof(__be32); +} + +static ssize_t +xs_read_stream_header(struct sock_xprt *transport, struct msghdr *msg, + int flags, size_t want, size_t seek) +{ + struct kvec kvec = { + .iov_base = &transport->recv.fraghdr, + .iov_len = want, + }; + return xs_read_kvec(transport->sock, msg, flags, &kvec, want, seek); +} + +#if defined(CONFIG_SUNRPC_BACKCHANNEL) +static ssize_t +xs_read_stream_call(struct sock_xprt *transport, struct msghdr *msg, int flags) +{ + struct rpc_xprt *xprt = &transport->xprt; + struct rpc_rqst *req; + ssize_t ret; + + /* Look up and lock the request corresponding to the given XID */ + req = xprt_lookup_bc_request(xprt, transport->recv.xid); + if (!req) { + printk(KERN_WARNING "Callback slot table overflowed\n"); + return -ESHUTDOWN; + } + + ret = xs_read_stream_request(transport, msg, flags, req); + if (msg->msg_flags & (MSG_EOR|MSG_TRUNC)) + xprt_complete_bc_request(req, ret); + + return ret; +} +#else /* CONFIG_SUNRPC_BACKCHANNEL */ +static ssize_t +xs_read_stream_call(struct sock_xprt *transport, struct msghdr *msg, int flags) +{ + return -ESHUTDOWN; +} +#endif /* CONFIG_SUNRPC_BACKCHANNEL */ + +static ssize_t +xs_read_stream_reply(struct sock_xprt *transport, struct msghdr *msg, int flags) +{ + struct rpc_xprt *xprt = &transport->xprt; + struct rpc_rqst *req; + ssize_t ret = 0; + + /* Look up and lock the request corresponding to the given XID */ + spin_lock(&xprt->queue_lock); + req = xprt_lookup_rqst(xprt, transport->recv.xid); + if (!req) { + msg->msg_flags |= MSG_TRUNC; + goto out; + } + xprt_pin_rqst(req); + spin_unlock(&xprt->queue_lock); + + ret = xs_read_stream_request(transport, msg, flags, req); + + spin_lock(&xprt->queue_lock); + if (msg->msg_flags & (MSG_EOR|MSG_TRUNC)) + xprt_complete_rqst(req->rq_task, ret); + xprt_unpin_rqst(req); +out: + spin_unlock(&xprt->queue_lock); + return ret; +} + +static ssize_t +xs_read_stream(struct sock_xprt *transport, int flags) +{ + struct msghdr msg = { 0 }; + size_t want, read = 0; + ssize_t ret = 0; + + if (transport->recv.len == 0) { + want = xs_read_stream_headersize(transport->recv.copied != 0); + ret = xs_read_stream_header(transport, &msg, flags, want, + transport->recv.offset); + if (ret <= 0) + goto out_err; + transport->recv.offset = ret; + if (ret != want) { + ret = -EAGAIN; + goto out_err; + } + transport->recv.len = be32_to_cpu(transport->recv.fraghdr) & + RPC_FRAGMENT_SIZE_MASK; + transport->recv.offset -= sizeof(transport->recv.fraghdr); + read = ret; + } + + switch (be32_to_cpu(transport->recv.calldir)) { + case RPC_CALL: + ret = xs_read_stream_call(transport, &msg, flags); + break; + case RPC_REPLY: + ret = xs_read_stream_reply(transport, &msg, flags); + } + if (msg.msg_flags & MSG_TRUNC) { + transport->recv.calldir = cpu_to_be32(-1); + transport->recv.copied = -1; + } + if (ret < 0) + goto out_err; + read += ret; + if (transport->recv.offset < transport->recv.len) { + ret = xs_read_discard(transport->sock, &msg, flags, + transport->recv.len - transport->recv.offset); + if (ret <= 0) + goto out_err; + transport->recv.offset += ret; + read += ret; + if (transport->recv.offset != transport->recv.len) + return -EAGAIN; + } + if (xs_read_stream_request_done(transport)) { + trace_xs_tcp_data_recv(transport); + transport->recv.copied = 0; + } + transport->recv.offset = 0; + transport->recv.len = 0; + return read; +out_err: + switch (ret) { + case 0: + case -ESHUTDOWN: + xprt_force_disconnect(&transport->xprt); + return -ESHUTDOWN; + } + return ret; +} + #define XS_SENDMSG_FLAGS (MSG_DONTWAIT | MSG_NOSIGNAL) static int xs_send_kvec(struct socket *sock, struct sockaddr *addr, int addrlen, struct kvec *vec, unsigned int base, int more) @@ -484,6 +801,12 @@ static int xs_nospace(struct rpc_rqst *req) return ret; } +static void +xs_stream_prepare_request(struct rpc_rqst *req) +{ + req->rq_task->tk_status = xdr_alloc_bvec(&req->rq_rcv_buf, GFP_NOIO); +} + /* * Determine if the previous message in the stream was aborted before it * could complete transmission. @@ -1157,263 +1480,7 @@ static void xs_tcp_force_close(struct rpc_xprt *xprt) xprt_force_disconnect(xprt); } -static inline void xs_tcp_read_fraghdr(struct rpc_xprt *xprt, struct xdr_skb_reader *desc) -{ - struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); - size_t len, used; - char *p; - - p = ((char *) &transport->recv.fraghdr) + transport->recv.offset; - len = sizeof(transport->recv.fraghdr) - transport->recv.offset; - used = xdr_skb_read_bits(desc, p, len); - transport->recv.offset += used; - if (used != len) - return; - - transport->recv.len = ntohl(transport->recv.fraghdr); - if (transport->recv.len & RPC_LAST_STREAM_FRAGMENT) - transport->recv.flags |= TCP_RCV_LAST_FRAG; - else - transport->recv.flags &= ~TCP_RCV_LAST_FRAG; - transport->recv.len &= RPC_FRAGMENT_SIZE_MASK; - - transport->recv.flags &= ~TCP_RCV_COPY_FRAGHDR; - transport->recv.offset = 0; - - /* Sanity check of the record length */ - if (unlikely(transport->recv.len < 8)) { - dprintk("RPC: invalid TCP record fragment length\n"); - xs_tcp_force_close(xprt); - return; - } - dprintk("RPC: reading TCP record fragment of length %d\n", - transport->recv.len); -} - -static void xs_tcp_check_fraghdr(struct sock_xprt *transport) -{ - if (transport->recv.offset == transport->recv.len) { - transport->recv.flags |= TCP_RCV_COPY_FRAGHDR; - transport->recv.offset = 0; - if (transport->recv.flags & TCP_RCV_LAST_FRAG) { - transport->recv.flags &= ~TCP_RCV_COPY_DATA; - transport->recv.flags |= TCP_RCV_COPY_XID; - transport->recv.copied = 0; - } - } -} - -static inline void xs_tcp_read_xid(struct sock_xprt *transport, struct xdr_skb_reader *desc) -{ - size_t len, used; - char *p; - - len = sizeof(transport->recv.xid) - transport->recv.offset; - dprintk("RPC: reading XID (%zu bytes)\n", len); - p = ((char *) &transport->recv.xid) + transport->recv.offset; - used = xdr_skb_read_bits(desc, p, len); - transport->recv.offset += used; - if (used != len) - return; - transport->recv.flags &= ~TCP_RCV_COPY_XID; - transport->recv.flags |= TCP_RCV_READ_CALLDIR; - transport->recv.copied = 4; - dprintk("RPC: reading %s XID %08x\n", - (transport->recv.flags & TCP_RPC_REPLY) ? "reply for" - : "request with", - ntohl(transport->recv.xid)); - xs_tcp_check_fraghdr(transport); -} - -static inline void xs_tcp_read_calldir(struct sock_xprt *transport, - struct xdr_skb_reader *desc) -{ - size_t len, used; - u32 offset; - char *p; - - /* - * We want transport->recv.offset to be 8 at the end of this routine - * (4 bytes for the xid and 4 bytes for the call/reply flag). - * When this function is called for the first time, - * transport->recv.offset is 4 (after having already read the xid). - */ - offset = transport->recv.offset - sizeof(transport->recv.xid); - len = sizeof(transport->recv.calldir) - offset; - dprintk("RPC: reading CALL/REPLY flag (%zu bytes)\n", len); - p = ((char *) &transport->recv.calldir) + offset; - used = xdr_skb_read_bits(desc, p, len); - transport->recv.offset += used; - if (used != len) - return; - transport->recv.flags &= ~TCP_RCV_READ_CALLDIR; - /* - * We don't yet have the XDR buffer, so we will write the calldir - * out after we get the buffer from the 'struct rpc_rqst' - */ - switch (ntohl(transport->recv.calldir)) { - case RPC_REPLY: - transport->recv.flags |= TCP_RCV_COPY_CALLDIR; - transport->recv.flags |= TCP_RCV_COPY_DATA; - transport->recv.flags |= TCP_RPC_REPLY; - break; - case RPC_CALL: - transport->recv.flags |= TCP_RCV_COPY_CALLDIR; - transport->recv.flags |= TCP_RCV_COPY_DATA; - transport->recv.flags &= ~TCP_RPC_REPLY; - break; - default: - dprintk("RPC: invalid request message type\n"); - xs_tcp_force_close(&transport->xprt); - } - xs_tcp_check_fraghdr(transport); -} - -static inline void xs_tcp_read_common(struct rpc_xprt *xprt, - struct xdr_skb_reader *desc, - struct rpc_rqst *req) -{ - struct sock_xprt *transport = - container_of(xprt, struct sock_xprt, xprt); - struct xdr_buf *rcvbuf; - size_t len; - ssize_t r; - - rcvbuf = &req->rq_private_buf; - - if (transport->recv.flags & TCP_RCV_COPY_CALLDIR) { - /* - * Save the RPC direction in the XDR buffer - */ - memcpy(rcvbuf->head[0].iov_base + transport->recv.copied, - &transport->recv.calldir, - sizeof(transport->recv.calldir)); - transport->recv.copied += sizeof(transport->recv.calldir); - transport->recv.flags &= ~TCP_RCV_COPY_CALLDIR; - } - - len = desc->count; - if (len > transport->recv.len - transport->recv.offset) - desc->count = transport->recv.len - transport->recv.offset; - r = xdr_partial_copy_from_skb(rcvbuf, transport->recv.copied, - desc, xdr_skb_read_bits); - - if (desc->count) { - /* Error when copying to the receive buffer, - * usually because we weren't able to allocate - * additional buffer pages. All we can do now - * is turn off TCP_RCV_COPY_DATA, so the request - * will not receive any additional updates, - * and time out. - * Any remaining data from this record will - * be discarded. - */ - transport->recv.flags &= ~TCP_RCV_COPY_DATA; - dprintk("RPC: XID %08x truncated request\n", - ntohl(transport->recv.xid)); - dprintk("RPC: xprt = %p, recv.copied = %lu, " - "recv.offset = %u, recv.len = %u\n", - xprt, transport->recv.copied, - transport->recv.offset, transport->recv.len); - return; - } - - transport->recv.copied += r; - transport->recv.offset += r; - desc->count = len - r; - - dprintk("RPC: XID %08x read %zd bytes\n", - ntohl(transport->recv.xid), r); - dprintk("RPC: xprt = %p, recv.copied = %lu, recv.offset = %u, " - "recv.len = %u\n", xprt, transport->recv.copied, - transport->recv.offset, transport->recv.len); - - if (transport->recv.copied == req->rq_private_buf.buflen) - transport->recv.flags &= ~TCP_RCV_COPY_DATA; - else if (transport->recv.offset == transport->recv.len) { - if (transport->recv.flags & TCP_RCV_LAST_FRAG) - transport->recv.flags &= ~TCP_RCV_COPY_DATA; - } -} - -/* - * Finds the request corresponding to the RPC xid and invokes the common - * tcp read code to read the data. - */ -static inline int xs_tcp_read_reply(struct rpc_xprt *xprt, - struct xdr_skb_reader *desc) -{ - struct sock_xprt *transport = - container_of(xprt, struct sock_xprt, xprt); - struct rpc_rqst *req; - - dprintk("RPC: read reply XID %08x\n", ntohl(transport->recv.xid)); - - /* Find and lock the request corresponding to this xid */ - spin_lock(&xprt->queue_lock); - req = xprt_lookup_rqst(xprt, transport->recv.xid); - if (!req) { - dprintk("RPC: XID %08x request not found!\n", - ntohl(transport->recv.xid)); - spin_unlock(&xprt->queue_lock); - return -1; - } - xprt_pin_rqst(req); - spin_unlock(&xprt->queue_lock); - - xs_tcp_read_common(xprt, desc, req); - - spin_lock(&xprt->queue_lock); - if (!(transport->recv.flags & TCP_RCV_COPY_DATA)) - xprt_complete_rqst(req->rq_task, transport->recv.copied); - xprt_unpin_rqst(req); - spin_unlock(&xprt->queue_lock); - return 0; -} - #if defined(CONFIG_SUNRPC_BACKCHANNEL) -/* - * Obtains an rpc_rqst previously allocated and invokes the common - * tcp read code to read the data. The result is placed in the callback - * queue. - * If we're unable to obtain the rpc_rqst we schedule the closing of the - * connection and return -1. - */ -static int xs_tcp_read_callback(struct rpc_xprt *xprt, - struct xdr_skb_reader *desc) -{ - struct sock_xprt *transport = - container_of(xprt, struct sock_xprt, xprt); - struct rpc_rqst *req; - - /* Look up the request corresponding to the given XID */ - req = xprt_lookup_bc_request(xprt, transport->recv.xid); - if (req == NULL) { - printk(KERN_WARNING "Callback slot table overflowed\n"); - xprt_force_disconnect(xprt); - return -1; - } - - dprintk("RPC: read callback XID %08x\n", ntohl(req->rq_xid)); - xs_tcp_read_common(xprt, desc, req); - - if (!(transport->recv.flags & TCP_RCV_COPY_DATA)) - xprt_complete_bc_request(req, transport->recv.copied); - - return 0; -} - -static inline int _xs_tcp_read_data(struct rpc_xprt *xprt, - struct xdr_skb_reader *desc) -{ - struct sock_xprt *transport = - container_of(xprt, struct sock_xprt, xprt); - - return (transport->recv.flags & TCP_RPC_REPLY) ? - xs_tcp_read_reply(xprt, desc) : - xs_tcp_read_callback(xprt, desc); -} - static int xs_tcp_bc_up(struct svc_serv *serv, struct net *net) { int ret; @@ -1429,106 +1496,14 @@ static size_t xs_tcp_bc_maxpayload(struct rpc_xprt *xprt) { return PAGE_SIZE; } -#else -static inline int _xs_tcp_read_data(struct rpc_xprt *xprt, - struct xdr_skb_reader *desc) -{ - return xs_tcp_read_reply(xprt, desc); -} #endif /* CONFIG_SUNRPC_BACKCHANNEL */ -/* - * Read data off the transport. This can be either an RPC_CALL or an - * RPC_REPLY. Relay the processing to helper functions. - */ -static void xs_tcp_read_data(struct rpc_xprt *xprt, - struct xdr_skb_reader *desc) -{ - struct sock_xprt *transport = - container_of(xprt, struct sock_xprt, xprt); - - if (_xs_tcp_read_data(xprt, desc) == 0) - xs_tcp_check_fraghdr(transport); - else { - /* - * The transport_lock protects the request handling. - * There's no need to hold it to update the recv.flags. - */ - transport->recv.flags &= ~TCP_RCV_COPY_DATA; - } -} - -static inline void xs_tcp_read_discard(struct sock_xprt *transport, struct xdr_skb_reader *desc) -{ - size_t len; - - len = transport->recv.len - transport->recv.offset; - if (len > desc->count) - len = desc->count; - desc->count -= len; - desc->offset += len; - transport->recv.offset += len; - dprintk("RPC: discarded %zu bytes\n", len); - xs_tcp_check_fraghdr(transport); -} - -static int xs_tcp_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, unsigned int offset, size_t len) -{ - struct rpc_xprt *xprt = rd_desc->arg.data; - struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); - struct xdr_skb_reader desc = { - .skb = skb, - .offset = offset, - .count = len, - }; - size_t ret; - - dprintk("RPC: xs_tcp_data_recv started\n"); - do { - trace_xs_tcp_data_recv(transport); - /* Read in a new fragment marker if necessary */ - /* Can we ever really expect to get completely empty fragments? */ - if (transport->recv.flags & TCP_RCV_COPY_FRAGHDR) { - xs_tcp_read_fraghdr(xprt, &desc); - continue; - } - /* Read in the xid if necessary */ - if (transport->recv.flags & TCP_RCV_COPY_XID) { - xs_tcp_read_xid(transport, &desc); - continue; - } - /* Read in the call/reply flag */ - if (transport->recv.flags & TCP_RCV_READ_CALLDIR) { - xs_tcp_read_calldir(transport, &desc); - continue; - } - /* Read in the request data */ - if (transport->recv.flags & TCP_RCV_COPY_DATA) { - xs_tcp_read_data(xprt, &desc); - continue; - } - /* Skip over any trailing bytes on short reads */ - xs_tcp_read_discard(transport, &desc); - } while (desc.count); - ret = len - desc.count; - if (ret < rd_desc->count) - rd_desc->count -= ret; - else - rd_desc->count = 0; - trace_xs_tcp_data_recv(transport); - dprintk("RPC: xs_tcp_data_recv done\n"); - return ret; -} - static void xs_tcp_data_receive(struct sock_xprt *transport) { struct rpc_xprt *xprt = &transport->xprt; struct sock *sk; - read_descriptor_t rd_desc = { - .arg.data = xprt, - }; - unsigned long total = 0; - int read = 0; + size_t read = 0; + ssize_t ret = 0; restart: mutex_lock(&transport->recv_mutex); @@ -1536,18 +1511,12 @@ restart: if (sk == NULL) goto out; - /* We use rd_desc to pass struct xprt to xs_tcp_data_recv */ for (;;) { - rd_desc.count = RPC_TCP_READ_CHUNK_SZ; - lock_sock(sk); - read = tcp_read_sock(sk, &rd_desc, xs_tcp_data_recv); - if (rd_desc.count != 0 || read < 0) { - clear_bit(XPRT_SOCK_DATA_READY, &transport->sock_state); - release_sock(sk); + clear_bit(XPRT_SOCK_DATA_READY, &transport->sock_state); + ret = xs_read_stream(transport, MSG_DONTWAIT | MSG_NOSIGNAL); + if (ret < 0) break; - } - release_sock(sk); - total += read; + read += ret; if (need_resched()) { mutex_unlock(&transport->recv_mutex); cond_resched(); @@ -1558,7 +1527,7 @@ restart: queue_work(xprtiod_workqueue, &transport->recv_worker); out: mutex_unlock(&transport->recv_mutex); - trace_xs_tcp_data_ready(xprt, read, total); + trace_xs_tcp_data_ready(xprt, ret, read); } static void xs_tcp_data_receive_workfn(struct work_struct *work) @@ -2380,7 +2349,6 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) transport->recv.offset = 0; transport->recv.len = 0; transport->recv.copied = 0; - transport->recv.flags = TCP_RCV_COPY_FRAGHDR | TCP_RCV_COPY_XID; transport->xmit.offset = 0; /* Tell the socket layer to start connecting... */ @@ -2802,6 +2770,7 @@ static const struct rpc_xprt_ops xs_tcp_ops = { .connect = xs_connect, .buf_alloc = rpc_malloc, .buf_free = rpc_free, + .prepare_request = xs_stream_prepare_request, .send_request = xs_tcp_send_request, .set_retrans_timeout = xprt_set_retrans_timeout_def, .close = xs_tcp_shutdown, -- cgit v1.2.3 From 550aebfe1c573518c35ae85d6ffbdc2d44c92703 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 14 Sep 2018 14:32:45 -0400 Subject: SUNRPC: Allow AF_LOCAL sockets to use the generic stream receive Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xdr.h | 1 - net/sunrpc/socklib.c | 4 +- net/sunrpc/xprtsock.c | 137 ++++++--------------------------------------- 3 files changed, 18 insertions(+), 124 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 745587132a87..8815be7cae72 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -185,7 +185,6 @@ struct xdr_skb_reader { typedef size_t (*xdr_skb_read_actor)(struct xdr_skb_reader *desc, void *to, size_t len); -size_t xdr_skb_read_bits(struct xdr_skb_reader *desc, void *to, size_t len); extern int csum_partial_copy_to_xdr(struct xdr_buf *, struct sk_buff *); extern ssize_t xdr_partial_copy_from_skb(struct xdr_buf *, unsigned int, struct xdr_skb_reader *, xdr_skb_read_actor); diff --git a/net/sunrpc/socklib.c b/net/sunrpc/socklib.c index 08f00a98151f..0e7c0dee7578 100644 --- a/net/sunrpc/socklib.c +++ b/net/sunrpc/socklib.c @@ -26,7 +26,8 @@ * Possibly called several times to iterate over an sk_buff and copy * data out of it. */ -size_t xdr_skb_read_bits(struct xdr_skb_reader *desc, void *to, size_t len) +static size_t +xdr_skb_read_bits(struct xdr_skb_reader *desc, void *to, size_t len) { if (len > desc->count) len = desc->count; @@ -36,7 +37,6 @@ size_t xdr_skb_read_bits(struct xdr_skb_reader *desc, void *to, size_t len) desc->offset += len; return len; } -EXPORT_SYMBOL_GPL(xdr_skb_read_bits); /** * xdr_skb_read_and_csum_bits - copy and checksum from skb to buffer diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 55df1fadab27..90d4c92177b7 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -670,6 +670,17 @@ static void xs_stream_data_receive_workfn(struct work_struct *work) xs_stream_data_receive(transport); } +static void +xs_stream_reset_connect(struct sock_xprt *transport) +{ + transport->recv.offset = 0; + transport->recv.len = 0; + transport->recv.copied = 0; + transport->xmit.offset = 0; + transport->xprt.stat.connect_count++; + transport->xprt.stat.connect_start = jiffies; +} + #define XS_SENDMSG_FLAGS (MSG_DONTWAIT | MSG_NOSIGNAL) static int xs_send_kvec(struct socket *sock, struct sockaddr *addr, int addrlen, struct kvec *vec, unsigned int base, int more) @@ -1266,114 +1277,6 @@ static void xs_destroy(struct rpc_xprt *xprt) module_put(THIS_MODULE); } -static int xs_local_copy_to_xdr(struct xdr_buf *xdr, struct sk_buff *skb) -{ - struct xdr_skb_reader desc = { - .skb = skb, - .offset = sizeof(rpc_fraghdr), - .count = skb->len - sizeof(rpc_fraghdr), - }; - - if (xdr_partial_copy_from_skb(xdr, 0, &desc, xdr_skb_read_bits) < 0) - return -1; - if (desc.count) - return -1; - return 0; -} - -/** - * xs_local_data_read_skb - * @xprt: transport - * @sk: socket - * @skb: skbuff - * - * Currently this assumes we can read the whole reply in a single gulp. - */ -static void xs_local_data_read_skb(struct rpc_xprt *xprt, - struct sock *sk, - struct sk_buff *skb) -{ - struct rpc_task *task; - struct rpc_rqst *rovr; - int repsize, copied; - u32 _xid; - __be32 *xp; - - repsize = skb->len - sizeof(rpc_fraghdr); - if (repsize < 4) { - dprintk("RPC: impossible RPC reply size %d\n", repsize); - return; - } - - /* Copy the XID from the skb... */ - xp = skb_header_pointer(skb, sizeof(rpc_fraghdr), sizeof(_xid), &_xid); - if (xp == NULL) - return; - - /* Look up and lock the request corresponding to the given XID */ - spin_lock(&xprt->queue_lock); - rovr = xprt_lookup_rqst(xprt, *xp); - if (!rovr) - goto out_unlock; - xprt_pin_rqst(rovr); - spin_unlock(&xprt->queue_lock); - task = rovr->rq_task; - - copied = rovr->rq_private_buf.buflen; - if (copied > repsize) - copied = repsize; - - if (xs_local_copy_to_xdr(&rovr->rq_private_buf, skb)) { - dprintk("RPC: sk_buff copy failed\n"); - spin_lock(&xprt->queue_lock); - goto out_unpin; - } - - spin_lock(&xprt->queue_lock); - xprt_complete_rqst(task, copied); -out_unpin: - xprt_unpin_rqst(rovr); - out_unlock: - spin_unlock(&xprt->queue_lock); -} - -static void xs_local_data_receive(struct sock_xprt *transport) -{ - struct sk_buff *skb; - struct sock *sk; - int err; - -restart: - mutex_lock(&transport->recv_mutex); - sk = transport->inet; - if (sk == NULL) - goto out; - for (;;) { - skb = skb_recv_datagram(sk, 0, 1, &err); - if (skb != NULL) { - xs_local_data_read_skb(&transport->xprt, sk, skb); - skb_free_datagram(sk, skb); - continue; - } - if (!test_and_clear_bit(XPRT_SOCK_DATA_READY, &transport->sock_state)) - break; - if (need_resched()) { - mutex_unlock(&transport->recv_mutex); - cond_resched(); - goto restart; - } - } -out: - mutex_unlock(&transport->recv_mutex); -} - -static void xs_local_data_receive_workfn(struct work_struct *work) -{ - struct sock_xprt *transport = - container_of(work, struct sock_xprt, recv_worker); - xs_local_data_receive(transport); -} - /** * xs_udp_data_read_skb - receive callback for UDP sockets * @xprt: transport @@ -1974,11 +1877,8 @@ static int xs_local_finish_connecting(struct rpc_xprt *xprt, write_unlock_bh(&sk->sk_callback_lock); } - transport->xmit.offset = 0; + xs_stream_reset_connect(transport); - /* Tell the socket layer to start connecting... */ - xprt->stat.connect_count++; - xprt->stat.connect_start = jiffies; return kernel_connect(sock, xs_addr(xprt), xprt->addrlen, 0); } @@ -2335,14 +2235,9 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) xs_set_memalloc(xprt); /* Reset TCP record info */ - transport->recv.offset = 0; - transport->recv.len = 0; - transport->recv.copied = 0; - transport->xmit.offset = 0; + xs_stream_reset_connect(transport); /* Tell the socket layer to start connecting... */ - xprt->stat.connect_count++; - xprt->stat.connect_start = jiffies; set_bit(XPRT_SOCK_CONNECTING, &transport->sock_state); ret = kernel_connect(sock, xs_addr(xprt), xprt->addrlen, O_NONBLOCK); switch (ret) { @@ -2717,6 +2612,7 @@ static const struct rpc_xprt_ops xs_local_ops = { .connect = xs_local_connect, .buf_alloc = rpc_malloc, .buf_free = rpc_free, + .prepare_request = xs_stream_prepare_request, .send_request = xs_local_send_request, .set_retrans_timeout = xprt_set_retrans_timeout_def, .close = xs_close, @@ -2901,9 +2797,8 @@ static struct rpc_xprt *xs_setup_local(struct xprt_create *args) xprt->ops = &xs_local_ops; xprt->timeout = &xs_local_default_timeout; - INIT_WORK(&transport->recv_worker, xs_local_data_receive_workfn); - INIT_DELAYED_WORK(&transport->connect_worker, - xs_dummy_setup_socket); + INIT_WORK(&transport->recv_worker, xs_stream_data_receive_workfn); + INIT_DELAYED_WORK(&transport->connect_worker, xs_dummy_setup_socket); switch (sun->sun_family) { case AF_LOCAL: -- cgit v1.2.3 From ec846469ba7bdb81e42c04e4e15d8fbf19e426e2 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 14 Sep 2018 14:38:05 -0400 Subject: SUNRPC: Unexport xdr_partial_copy_from_skb() It is no longer used outside of net/sunrpc/socklib.c Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xdr.h | 2 -- net/sunrpc/socklib.c | 4 ++-- 2 files changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 8815be7cae72..43106ffa6788 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -186,8 +186,6 @@ struct xdr_skb_reader { typedef size_t (*xdr_skb_read_actor)(struct xdr_skb_reader *desc, void *to, size_t len); extern int csum_partial_copy_to_xdr(struct xdr_buf *, struct sk_buff *); -extern ssize_t xdr_partial_copy_from_skb(struct xdr_buf *, unsigned int, - struct xdr_skb_reader *, xdr_skb_read_actor); extern int xdr_encode_word(struct xdr_buf *, unsigned int, u32); extern int xdr_decode_word(struct xdr_buf *, unsigned int, u32 *); diff --git a/net/sunrpc/socklib.c b/net/sunrpc/socklib.c index 0e7c0dee7578..9062967575c4 100644 --- a/net/sunrpc/socklib.c +++ b/net/sunrpc/socklib.c @@ -69,7 +69,8 @@ static size_t xdr_skb_read_and_csum_bits(struct xdr_skb_reader *desc, void *to, * @copy_actor: virtual method for copying data * */ -ssize_t xdr_partial_copy_from_skb(struct xdr_buf *xdr, unsigned int base, struct xdr_skb_reader *desc, xdr_skb_read_actor copy_actor) +static ssize_t +xdr_partial_copy_from_skb(struct xdr_buf *xdr, unsigned int base, struct xdr_skb_reader *desc, xdr_skb_read_actor copy_actor) { struct page **ppage = xdr->pages; unsigned int len, pglen = xdr->page_len; @@ -140,7 +141,6 @@ copy_tail: out: return copied; } -EXPORT_SYMBOL_GPL(xdr_partial_copy_from_skb); /** * csum_partial_copy_to_xdr - checksum and copy data -- cgit v1.2.3 From 1db97eaa0b482a738c715da6edb023d6f99e50b0 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 2 Sep 2018 15:11:57 -0400 Subject: NFS: Convert lookups of the lock context to RCU Speed up lookups of an existing lock context by avoiding the inode->i_lock, and using RCU instead. Signed-off-by: Trond Myklebust --- fs/nfs/inode.c | 25 ++++++++++++------------- include/linux/nfs_fs.h | 1 + 2 files changed, 13 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index b65aee481d13..09b3b7146ff4 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -857,15 +857,14 @@ static void nfs_init_lock_context(struct nfs_lock_context *l_ctx) static struct nfs_lock_context *__nfs_find_lock_context(struct nfs_open_context *ctx) { - struct nfs_lock_context *head = &ctx->lock_context; - struct nfs_lock_context *pos = head; + struct nfs_lock_context *pos; - do { + list_for_each_entry_rcu(pos, &ctx->lock_context.list, list) { if (pos->lockowner != current->files) continue; - refcount_inc(&pos->count); - return pos; - } while ((pos = list_entry(pos->list.next, typeof(*pos), list)) != head); + if (refcount_inc_not_zero(&pos->count)) + return pos; + } return NULL; } @@ -874,10 +873,10 @@ struct nfs_lock_context *nfs_get_lock_context(struct nfs_open_context *ctx) struct nfs_lock_context *res, *new = NULL; struct inode *inode = d_inode(ctx->dentry); - spin_lock(&inode->i_lock); + rcu_read_lock(); res = __nfs_find_lock_context(ctx); + rcu_read_unlock(); if (res == NULL) { - spin_unlock(&inode->i_lock); new = kmalloc(sizeof(*new), GFP_KERNEL); if (new == NULL) return ERR_PTR(-ENOMEM); @@ -885,14 +884,14 @@ struct nfs_lock_context *nfs_get_lock_context(struct nfs_open_context *ctx) spin_lock(&inode->i_lock); res = __nfs_find_lock_context(ctx); if (res == NULL) { - list_add_tail(&new->list, &ctx->lock_context.list); + list_add_tail_rcu(&new->list, &ctx->lock_context.list); new->open_context = ctx; res = new; new = NULL; } + spin_unlock(&inode->i_lock); + kfree(new); } - spin_unlock(&inode->i_lock); - kfree(new); return res; } EXPORT_SYMBOL_GPL(nfs_get_lock_context); @@ -904,9 +903,9 @@ void nfs_put_lock_context(struct nfs_lock_context *l_ctx) if (!refcount_dec_and_lock(&l_ctx->count, &inode->i_lock)) return; - list_del(&l_ctx->list); + list_del_rcu(&l_ctx->list); spin_unlock(&inode->i_lock); - kfree(l_ctx); + kfree_rcu(l_ctx, rcu_head); } EXPORT_SYMBOL_GPL(nfs_put_lock_context); diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index a0831e9d19c9..d2f4f88a0e66 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -62,6 +62,7 @@ struct nfs_lock_context { struct nfs_open_context *open_context; fl_owner_t lockowner; atomic_t io_count; + struct rcu_head rcu_head; }; struct nfs4_state; -- cgit v1.2.3 From 0de43976fbe716379084f954b1e370c35aa87bf0 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 2 Sep 2018 15:57:01 -0400 Subject: NFS: Convert lookups of the open context to RCU Reduce contention on the inode->i_lock by ensuring that we use RCU when looking up the NFS open context. Signed-off-by: Trond Myklebust --- fs/nfs/delegation.c | 11 ++++++----- fs/nfs/inode.c | 35 +++++++++++++++-------------------- fs/nfs/nfs4proc.c | 30 ++++++++++++++++++++++++------ fs/nfs/nfs4state.c | 12 ++++++------ fs/nfs/pnfs.c | 5 ++++- include/linux/nfs_fs.h | 1 + 6 files changed, 56 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index f033f3a69a3b..76d205d1c7bc 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -136,8 +136,8 @@ static int nfs_delegation_claim_opens(struct inode *inode, int err; again: - spin_lock(&inode->i_lock); - list_for_each_entry(ctx, &nfsi->open_files, list) { + rcu_read_lock(); + list_for_each_entry_rcu(ctx, &nfsi->open_files, list) { state = ctx->state; if (state == NULL) continue; @@ -147,8 +147,9 @@ again: continue; if (!nfs4_stateid_match(&state->stateid, stateid)) continue; - get_nfs_open_context(ctx); - spin_unlock(&inode->i_lock); + if (!get_nfs_open_context(ctx)) + continue; + rcu_read_unlock(); sp = state->owner; /* Block nfs4_proc_unlck */ mutex_lock(&sp->so_delegreturn_mutex); @@ -164,7 +165,7 @@ again: return err; goto again; } - spin_unlock(&inode->i_lock); + rcu_read_unlock(); return 0; } diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 052db41a7f80..5b1eee4952b7 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -977,9 +977,9 @@ EXPORT_SYMBOL_GPL(alloc_nfs_open_context); struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx) { - if (ctx != NULL) - refcount_inc(&ctx->lock_context.count); - return ctx; + if (ctx != NULL && refcount_inc_not_zero(&ctx->lock_context.count)) + return ctx; + return NULL; } EXPORT_SYMBOL_GPL(get_nfs_open_context); @@ -988,13 +988,13 @@ static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync) struct inode *inode = d_inode(ctx->dentry); struct super_block *sb = ctx->dentry->d_sb; + if (!refcount_dec_and_test(&ctx->lock_context.count)) + return; if (!list_empty(&ctx->list)) { - if (!refcount_dec_and_lock(&ctx->lock_context.count, &inode->i_lock)) - return; - list_del(&ctx->list); + spin_lock(&inode->i_lock); + list_del_rcu(&ctx->list); spin_unlock(&inode->i_lock); - } else if (!refcount_dec_and_test(&ctx->lock_context.count)) - return; + } if (inode != NULL) NFS_PROTO(inode)->close_context(ctx, is_sync); if (ctx->cred != NULL) @@ -1002,7 +1002,7 @@ static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync) dput(ctx->dentry); nfs_sb_deactive(sb); kfree(ctx->mdsthreshold); - kfree(ctx); + kfree_rcu(ctx, rcu_head); } void put_nfs_open_context(struct nfs_open_context *ctx) @@ -1026,10 +1026,7 @@ void nfs_inode_attach_open_context(struct nfs_open_context *ctx) struct nfs_inode *nfsi = NFS_I(inode); spin_lock(&inode->i_lock); - if (ctx->mode & FMODE_WRITE) - list_add(&ctx->list, &nfsi->open_files); - else - list_add_tail(&ctx->list, &nfsi->open_files); + list_add_tail_rcu(&ctx->list, &nfsi->open_files); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL_GPL(nfs_inode_attach_open_context); @@ -1050,16 +1047,17 @@ struct nfs_open_context *nfs_find_open_context(struct inode *inode, struct rpc_c struct nfs_inode *nfsi = NFS_I(inode); struct nfs_open_context *pos, *ctx = NULL; - spin_lock(&inode->i_lock); - list_for_each_entry(pos, &nfsi->open_files, list) { + rcu_read_lock(); + list_for_each_entry_rcu(pos, &nfsi->open_files, list) { if (cred != NULL && pos->cred != cred) continue; if ((pos->mode & (FMODE_READ|FMODE_WRITE)) != mode) continue; ctx = get_nfs_open_context(pos); - break; + if (ctx) + break; } - spin_unlock(&inode->i_lock); + rcu_read_unlock(); return ctx; } @@ -1077,9 +1075,6 @@ void nfs_file_clear_open_context(struct file *filp) if (ctx->error < 0) invalidate_inode_pages2(inode->i_mapping); filp->private_data = NULL; - spin_lock(&inode->i_lock); - list_move_tail(&ctx->list, &NFS_I(inode)->open_files); - spin_unlock(&inode->i_lock); put_nfs_open_context_sync(ctx); } } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 8220a168282e..10c20a5b075d 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1933,23 +1933,41 @@ nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data) return ret; } -static struct nfs_open_context *nfs4_state_find_open_context(struct nfs4_state *state) +static struct nfs_open_context * +nfs4_state_find_open_context_mode(struct nfs4_state *state, fmode_t mode) { struct nfs_inode *nfsi = NFS_I(state->inode); struct nfs_open_context *ctx; - spin_lock(&state->inode->i_lock); - list_for_each_entry(ctx, &nfsi->open_files, list) { + rcu_read_lock(); + list_for_each_entry_rcu(ctx, &nfsi->open_files, list) { if (ctx->state != state) continue; - get_nfs_open_context(ctx); - spin_unlock(&state->inode->i_lock); + if ((ctx->mode & mode) != mode) + continue; + if (!get_nfs_open_context(ctx)) + continue; + rcu_read_unlock(); return ctx; } - spin_unlock(&state->inode->i_lock); + rcu_read_unlock(); return ERR_PTR(-ENOENT); } +static struct nfs_open_context * +nfs4_state_find_open_context(struct nfs4_state *state) +{ + struct nfs_open_context *ctx; + + ctx = nfs4_state_find_open_context_mode(state, FMODE_READ|FMODE_WRITE); + if (!IS_ERR(ctx)) + return ctx; + ctx = nfs4_state_find_open_context_mode(state, FMODE_WRITE); + if (!IS_ERR(ctx)) + return ctx; + return nfs4_state_find_open_context_mode(state, FMODE_READ); +} + static struct nfs4_opendata *nfs4_open_recoverdata_alloc(struct nfs_open_context *ctx, struct nfs4_state *state, enum open_claim_type4 claim) { diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 40a08cd483f0..be92ce4259e9 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1437,8 +1437,8 @@ void nfs_inode_find_state_and_recover(struct inode *inode, struct nfs4_state *state; bool found = false; - spin_lock(&inode->i_lock); - list_for_each_entry(ctx, &nfsi->open_files, list) { + rcu_read_lock(); + list_for_each_entry_rcu(ctx, &nfsi->open_files, list) { state = ctx->state; if (state == NULL) continue; @@ -1456,7 +1456,7 @@ void nfs_inode_find_state_and_recover(struct inode *inode, nfs4_state_mark_reclaim_nograce(clp, state)) found = true; } - spin_unlock(&inode->i_lock); + rcu_read_unlock(); nfs_inode_find_delegation_state_and_recover(inode, stateid); if (found) @@ -1469,13 +1469,13 @@ static void nfs4_state_mark_open_context_bad(struct nfs4_state *state) struct nfs_inode *nfsi = NFS_I(inode); struct nfs_open_context *ctx; - spin_lock(&inode->i_lock); - list_for_each_entry(ctx, &nfsi->open_files, list) { + rcu_read_lock(); + list_for_each_entry_rcu(ctx, &nfsi->open_files, list) { if (ctx->state != state) continue; set_bit(NFS_CONTEXT_BAD, &ctx->flags); } - spin_unlock(&inode->i_lock); + rcu_read_unlock(); } static void nfs4_state_mark_recovery_failed(struct nfs4_state *state, int error) diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index c5672c02afd6..06cb90e9bc6e 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1339,6 +1339,7 @@ bool pnfs_roc(struct inode *ino, if (!nfs_have_layout(ino)) return false; retry: + rcu_read_lock(); spin_lock(&ino->i_lock); lo = nfsi->layout; if (!lo || !pnfs_layout_is_valid(lo) || @@ -1349,6 +1350,7 @@ retry: pnfs_get_layout_hdr(lo); if (test_bit(NFS_LAYOUT_RETURN_LOCK, &lo->plh_flags)) { spin_unlock(&ino->i_lock); + rcu_read_unlock(); wait_on_bit(&lo->plh_flags, NFS_LAYOUT_RETURN, TASK_UNINTERRUPTIBLE); pnfs_put_layout_hdr(lo); @@ -1362,7 +1364,7 @@ retry: skip_read = true; } - list_for_each_entry(ctx, &nfsi->open_files, list) { + list_for_each_entry_rcu(ctx, &nfsi->open_files, list) { state = ctx->state; if (state == NULL) continue; @@ -1410,6 +1412,7 @@ retry: out_noroc: spin_unlock(&ino->i_lock); + rcu_read_unlock(); pnfs_layoutcommit_inode(ino, true); if (roc) { struct pnfs_layoutdriver_type *ld = NFS_SERVER(ino)->pnfs_curr_ld; diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index d2f4f88a0e66..6e0417c02279 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -83,6 +83,7 @@ struct nfs_open_context { struct list_head list; struct nfs4_threshold *mdsthreshold; + struct rcu_head rcu_head; }; struct nfs_open_dir_context { -- cgit v1.2.3 From 8d8928d87960d71f898767185b8c0e4ce3de3cbe Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 5 Mar 2018 12:03:00 -0500 Subject: NFSv3: Improve NFSv3 performance when server returns no post-op attributes When the server fails to return post-op attributes, the client's attempt to place read data directly in the page cache fails, and so we have to do an extra copy in order to realign the data with page borders. This patch attempts to detect servers that don't return post-op attributes on read (e.g. for pNFS) and adjusts the placement calculation accordingly. Signed-off-by: Trond Myklebust --- fs/nfs/nfs3proc.c | 5 +++++ fs/nfs/nfs3xdr.c | 6 +++++- include/linux/nfs_fs_sb.h | 3 +++ include/linux/nfs_xdr.h | 3 ++- 4 files changed, 15 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index ec8a9efa268f..71bc16225b98 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -786,6 +786,7 @@ nfs3_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle, static int nfs3_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr) { struct inode *inode = hdr->inode; + struct nfs_server *server = NFS_SERVER(inode); if (hdr->pgio_done_cb != NULL) return hdr->pgio_done_cb(task, hdr); @@ -793,6 +794,9 @@ static int nfs3_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr) if (nfs3_async_handle_jukebox(task, inode)) return -EAGAIN; + if (task->tk_status >= 0 && !server->read_hdrsize) + cmpxchg(&server->read_hdrsize, 0, hdr->res.replen); + nfs_invalidate_atime(inode); nfs_refresh_inode(inode, &hdr->fattr); return 0; @@ -802,6 +806,7 @@ static void nfs3_proc_read_setup(struct nfs_pgio_header *hdr, struct rpc_message *msg) { msg->rpc_proc = &nfs3_procedures[NFS3PROC_READ]; + hdr->args.replen = NFS_SERVER(hdr->inode)->read_hdrsize; } static int nfs3_proc_pgio_rpc_prepare(struct rpc_task *task, diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index d8c4c10b15f7..78df4eb60f85 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -983,10 +983,11 @@ static void nfs3_xdr_enc_read3args(struct rpc_rqst *req, const void *data) { const struct nfs_pgio_args *args = data; + unsigned int replen = args->replen ? args->replen : NFS3_readres_sz; encode_read3args(xdr, args); prepare_reply_buffer(req, args->pages, args->pgbase, - args->count, NFS3_readres_sz); + args->count, replen); req->rq_rcv_buf.flags |= XDRBUF_READ; } @@ -1675,9 +1676,11 @@ static int nfs3_xdr_dec_read3res(struct rpc_rqst *req, struct xdr_stream *xdr, void *data) { struct nfs_pgio_res *result = data; + unsigned int pos; enum nfs_stat status; int error; + pos = xdr_stream_pos(xdr); error = decode_nfsstat3(xdr, &status); if (unlikely(error)) goto out; @@ -1687,6 +1690,7 @@ static int nfs3_xdr_dec_read3res(struct rpc_rqst *req, struct xdr_stream *xdr, result->op_status = status; if (status != NFS3_OK) goto out_status; + result->replen = 3 + ((xdr_stream_pos(xdr) - pos) >> 2); error = decode_read3resok(xdr, result); out: return error; diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index bf39d9c92201..0fc0b9135d46 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -228,6 +228,9 @@ struct nfs_server { unsigned short mountd_port; unsigned short mountd_protocol; struct rpc_wait_queue uoc_rpcwaitq; + + /* XDR related information */ + unsigned int read_hdrsize; }; /* Server capabilities */ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index bd1c889a9ed9..7f5535e5e852 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -608,6 +608,7 @@ struct nfs_pgio_args { __u32 count; unsigned int pgbase; struct page ** pages; + unsigned int replen; /* used by read */ const u32 * bitmask; /* used by write */ enum nfs3_stable_how stable; /* used by write */ }; @@ -618,9 +619,9 @@ struct nfs_pgio_res { __u32 count; __u32 op_status; int eof; /* used by read */ + unsigned int replen; /* used by read */ struct nfs_writeverf * verf; /* used by write */ const struct nfs_server *server; /* used by write */ - }; /* -- cgit v1.2.3 From 28d52235ee25ba7d843242b4cb3c3f27a8828b5a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 24 Sep 2018 13:15:37 -0400 Subject: NFSv4: Save a few bytes in the nfs_pgio_args/res Save a few bytes by allowing the read/write specific fields of the structures to share storage. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 24 +++++++++++++++++------- 1 file changed, 17 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 7f5535e5e852..343e44166346 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -608,9 +608,13 @@ struct nfs_pgio_args { __u32 count; unsigned int pgbase; struct page ** pages; - unsigned int replen; /* used by read */ - const u32 * bitmask; /* used by write */ - enum nfs3_stable_how stable; /* used by write */ + union { + unsigned int replen; /* used by read */ + struct { + const u32 * bitmask; /* used by write */ + enum nfs3_stable_how stable; /* used by write */ + }; + }; }; struct nfs_pgio_res { @@ -618,10 +622,16 @@ struct nfs_pgio_res { struct nfs_fattr * fattr; __u32 count; __u32 op_status; - int eof; /* used by read */ - unsigned int replen; /* used by read */ - struct nfs_writeverf * verf; /* used by write */ - const struct nfs_server *server; /* used by write */ + union { + struct { + unsigned int replen; /* used by read */ + int eof; /* used by read */ + }; + struct { + struct nfs_writeverf * verf; /* used by write */ + const struct nfs_server *server; /* used by write */ + }; + }; }; /* -- cgit v1.2.3 From 1c6c4b740df12f2162ae5c3fac337137e2776236 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 25 Sep 2018 12:34:43 -0400 Subject: NFS: Remove private spinlock in struct nfs_pgio_header Now that each struct nfs_pgio_header corresponds to one RPC call, we only have one writer to the struct nfs_pgio_header. Signed-off-by: Trond Myklebust --- fs/nfs/pagelist.c | 13 ++++++------- fs/nfs/read.c | 10 ++++------ include/linux/nfs_xdr.h | 5 ++--- 3 files changed, 12 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index bb5476a6d264..f97c455f5734 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -63,14 +63,14 @@ EXPORT_SYMBOL_GPL(nfs_pgheader_init); void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos) { - spin_lock(&hdr->lock); - if (!test_and_set_bit(NFS_IOHDR_ERROR, &hdr->flags) - || pos < hdr->io_start + hdr->good_bytes) { + unsigned int new = pos - hdr->io_start; + + if (hdr->good_bytes > new) { + hdr->good_bytes = new; clear_bit(NFS_IOHDR_EOF, &hdr->flags); - hdr->good_bytes = pos - hdr->io_start; - hdr->error = error; + if (!test_and_set_bit(NFS_IOHDR_ERROR, &hdr->flags)) + hdr->error = error; } - spin_unlock(&hdr->lock); } static inline struct nfs_page * @@ -494,7 +494,6 @@ struct nfs_pgio_header *nfs_pgio_header_alloc(const struct nfs_rw_ops *ops) if (hdr) { INIT_LIST_HEAD(&hdr->pages); - spin_lock_init(&hdr->lock); hdr->rw_ops = ops; } return hdr; diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 48d7277c60a9..f9f19784db82 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -276,16 +276,14 @@ static void nfs_readpage_result(struct rpc_task *task, struct nfs_pgio_header *hdr) { if (hdr->res.eof) { - loff_t bound; + loff_t pos = hdr->args.offset + hdr->res.count; + unsigned int new = pos - hdr->io_start; - bound = hdr->args.offset + hdr->res.count; - spin_lock(&hdr->lock); - if (bound < hdr->io_start + hdr->good_bytes) { + if (hdr->good_bytes > new) { + hdr->good_bytes = new; set_bit(NFS_IOHDR_EOF, &hdr->flags); clear_bit(NFS_IOHDR_ERROR, &hdr->flags); - hdr->good_bytes = bound - hdr->io_start; } - spin_unlock(&hdr->lock); } else if (hdr->res.count < hdr->args.count) nfs_readpage_retry(task, hdr); } diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 343e44166346..0e016252cfc6 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1482,11 +1482,10 @@ struct nfs_pgio_header { const struct nfs_rw_ops *rw_ops; struct nfs_io_completion *io_completion; struct nfs_direct_req *dreq; - spinlock_t lock; - /* fields protected by lock */ + int pnfs_error; int error; /* merge with pnfs_error */ - unsigned long good_bytes; /* boundary of good data */ + unsigned int good_bytes; /* boundary of good data */ unsigned long flags; /* -- cgit v1.2.3 From 571ed1fd2390f74e4c1f46994f753fb0d29285e4 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 29 Sep 2018 16:00:43 -0400 Subject: SUNRPC: Replace krb5_seq_lock with a lockless scheme Signed-off-by: Trond Myklebust --- include/linux/sunrpc/gss_krb5.h | 3 ++- net/sunrpc/auth_gss/gss_krb5_seal.c | 37 ++++++++++++++++++++++++++----------- net/sunrpc/auth_gss/gss_krb5_wrap.c | 8 ++------ 3 files changed, 30 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index 7df625d41e35..69f749afa617 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -118,7 +118,8 @@ struct krb5_ctx { u8 acceptor_integ[GSS_KRB5_MAX_KEYLEN]; }; -extern spinlock_t krb5_seq_lock; +extern u32 gss_seq_send_fetch_and_inc(struct krb5_ctx *ctx); +extern u64 gss_seq_send64_fetch_and_inc(struct krb5_ctx *ctx); /* The length of the Kerberos GSS token header */ #define GSS_KRB5_TOK_HDR_LEN (16) diff --git a/net/sunrpc/auth_gss/gss_krb5_seal.c b/net/sunrpc/auth_gss/gss_krb5_seal.c index eaad9bc7a0bd..0ffb797b92e5 100644 --- a/net/sunrpc/auth_gss/gss_krb5_seal.c +++ b/net/sunrpc/auth_gss/gss_krb5_seal.c @@ -68,8 +68,6 @@ # define RPCDBG_FACILITY RPCDBG_AUTH #endif -DEFINE_SPINLOCK(krb5_seq_lock); - static void * setup_token(struct krb5_ctx *ctx, struct xdr_netobj *token) { @@ -124,6 +122,30 @@ setup_token_v2(struct krb5_ctx *ctx, struct xdr_netobj *token) return krb5_hdr; } +u32 +gss_seq_send_fetch_and_inc(struct krb5_ctx *ctx) +{ + u32 old, seq_send = READ_ONCE(ctx->seq_send); + + do { + old = seq_send; + seq_send = cmpxchg(&ctx->seq_send, old, old + 1); + } while (old != seq_send); + return seq_send; +} + +u64 +gss_seq_send64_fetch_and_inc(struct krb5_ctx *ctx) +{ + u64 old, seq_send = READ_ONCE(ctx->seq_send); + + do { + old = seq_send; + seq_send = cmpxchg(&ctx->seq_send64, old, old + 1); + } while (old != seq_send); + return seq_send; +} + static u32 gss_get_mic_v1(struct krb5_ctx *ctx, struct xdr_buf *text, struct xdr_netobj *token) @@ -154,9 +176,7 @@ gss_get_mic_v1(struct krb5_ctx *ctx, struct xdr_buf *text, memcpy(ptr + GSS_KRB5_TOK_HDR_LEN, md5cksum.data, md5cksum.len); - spin_lock(&krb5_seq_lock); - seq_send = ctx->seq_send++; - spin_unlock(&krb5_seq_lock); + seq_send = gss_seq_send_fetch_and_inc(ctx); if (krb5_make_seq_num(ctx, ctx->seq, ctx->initiate ? 0 : 0xff, seq_send, ptr + GSS_KRB5_TOK_HDR_LEN, ptr + 8)) @@ -174,7 +194,6 @@ gss_get_mic_v2(struct krb5_ctx *ctx, struct xdr_buf *text, .data = cksumdata}; void *krb5_hdr; s32 now; - u64 seq_send; u8 *cksumkey; unsigned int cksum_usage; __be64 seq_send_be64; @@ -185,11 +204,7 @@ gss_get_mic_v2(struct krb5_ctx *ctx, struct xdr_buf *text, /* Set up the sequence number. Now 64-bits in clear * text and w/o direction indicator */ - spin_lock(&krb5_seq_lock); - seq_send = ctx->seq_send64++; - spin_unlock(&krb5_seq_lock); - - seq_send_be64 = cpu_to_be64(seq_send); + seq_send_be64 = cpu_to_be64(gss_seq_send64_fetch_and_inc(ctx)); memcpy(krb5_hdr + 8, (char *) &seq_send_be64, 8); if (ctx->initiate) { diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c index 39a2e672900b..41cb294cd071 100644 --- a/net/sunrpc/auth_gss/gss_krb5_wrap.c +++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c @@ -228,9 +228,7 @@ gss_wrap_kerberos_v1(struct krb5_ctx *kctx, int offset, memcpy(ptr + GSS_KRB5_TOK_HDR_LEN, md5cksum.data, md5cksum.len); - spin_lock(&krb5_seq_lock); - seq_send = kctx->seq_send++; - spin_unlock(&krb5_seq_lock); + seq_send = gss_seq_send_fetch_and_inc(kctx); /* XXX would probably be more efficient to compute checksum * and encrypt at the same time: */ @@ -477,9 +475,7 @@ gss_wrap_kerberos_v2(struct krb5_ctx *kctx, u32 offset, *be16ptr++ = 0; be64ptr = (__be64 *)be16ptr; - spin_lock(&krb5_seq_lock); - *be64ptr = cpu_to_be64(kctx->seq_send64++); - spin_unlock(&krb5_seq_lock); + *be64ptr = cpu_to_be64(gss_seq_send64_fetch_and_inc(kctx)); err = (*kctx->gk5e->encrypt_v2)(kctx, offset, buf, pages); if (err) -- cgit v1.2.3 From aef716fa5e6da3919cca22ac2097a90d73d8177f Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Thu, 27 Sep 2018 13:55:58 -0700 Subject: RDMA/qedr: Remove enumerated type qed_roce_ll2_tx_dest Clang warns when one enumerated type is explicitly converted to another. drivers/infiniband/hw/qedr/qedr_roce_cm.c:198:28: warning: implicit conversion from enumeration type 'enum qed_roce_ll2_tx_dest' to different enumeration type 'enum qed_ll2_tx_dest' [-Wenum-conversion] ll2_tx_pkt.tx_dest = pkt->tx_dest; ~ ~~~~~^~~~~~~ 1 warning generated. Turns out that QED_ROCE_LL2_TX_DEST_NW and QED_ROCE_LL2_TX_DEST_LB are only used once in the whole tree and QED_ROCE_LL2_TX_DEST_MAX is used nowhere. Remove them and use the equivalent values from qed_ll2_tx_dest in their place. Reported-by: Nick Desaulniers Signed-off-by: Nathan Chancellor Reviewed-by: Nick Desaulniers Acked-by: Michal Kalderon Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/qedr/qedr_roce_cm.c | 4 ++-- include/linux/qed/qed_rdma_if.h | 11 +---------- 2 files changed, 3 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/qedr/qedr_roce_cm.c b/drivers/infiniband/hw/qedr/qedr_roce_cm.c index 85578887421b..e1ac2fd60bb1 100644 --- a/drivers/infiniband/hw/qedr/qedr_roce_cm.c +++ b/drivers/infiniband/hw/qedr/qedr_roce_cm.c @@ -519,9 +519,9 @@ static inline int qedr_gsi_build_packet(struct qedr_dev *dev, } if (ether_addr_equal(udh.eth.smac_h, udh.eth.dmac_h)) - packet->tx_dest = QED_ROCE_LL2_TX_DEST_LB; + packet->tx_dest = QED_LL2_TX_DEST_LB; else - packet->tx_dest = QED_ROCE_LL2_TX_DEST_NW; + packet->tx_dest = QED_LL2_TX_DEST_NW; packet->roce_mode = roce_mode; memcpy(packet->header.vaddr, ud_header_buffer, header_size); diff --git a/include/linux/qed/qed_rdma_if.h b/include/linux/qed/qed_rdma_if.h index df4d13f7e191..d15f8e4815e3 100644 --- a/include/linux/qed/qed_rdma_if.h +++ b/include/linux/qed/qed_rdma_if.h @@ -39,15 +39,6 @@ #include #include -enum qed_roce_ll2_tx_dest { - /* Light L2 TX Destination to the Network */ - QED_ROCE_LL2_TX_DEST_NW, - - /* Light L2 TX Destination to the Loopback */ - QED_ROCE_LL2_TX_DEST_LB, - QED_ROCE_LL2_TX_DEST_MAX -}; - #define QED_RDMA_MAX_CNQ_SIZE (0xFFFF) /* rdma interface */ @@ -581,7 +572,7 @@ struct qed_roce_ll2_packet { int n_seg; struct qed_roce_ll2_buffer payload[RDMA_MAX_SGE_PER_SQ_WQE]; int roce_mode; - enum qed_roce_ll2_tx_dest tx_dest; + enum qed_ll2_tx_dest tx_dest; }; enum qed_rdma_type { -- cgit v1.2.3 From d440c52d3151a28358f4c2d52d8583a0aa54ab83 Mon Sep 17 00:00:00 2001 From: Junling Zheng Date: Fri, 28 Sep 2018 20:25:56 +0800 Subject: f2fs: support superblock checksum Now we support crc32 checksum for superblock. Reviewed-by: Chao Yu Signed-off-by: Junling Zheng Signed-off-by: Jaegeuk Kim --- fs/f2fs/f2fs.h | 2 ++ fs/f2fs/super.c | 28 ++++++++++++++++++++++++++++ fs/f2fs/sysfs.c | 7 +++++++ include/linux/f2fs_fs.h | 3 ++- 4 files changed, 39 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 19243678d5d9..668836c2d678 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -148,6 +148,7 @@ struct f2fs_mount_info { #define F2FS_FEATURE_INODE_CRTIME 0x0100 #define F2FS_FEATURE_LOST_FOUND 0x0200 #define F2FS_FEATURE_VERITY 0x0400 /* reserved */ +#define F2FS_FEATURE_SB_CHKSUM 0x0800 #define F2FS_HAS_FEATURE(sb, mask) \ ((F2FS_SB(sb)->raw_super->feature & cpu_to_le32(mask)) != 0) @@ -3431,6 +3432,7 @@ F2FS_FEATURE_FUNCS(flexible_inline_xattr, FLEXIBLE_INLINE_XATTR); F2FS_FEATURE_FUNCS(quota_ino, QUOTA_INO); F2FS_FEATURE_FUNCS(inode_crtime, INODE_CRTIME); F2FS_FEATURE_FUNCS(lost_found, LOST_FOUND); +F2FS_FEATURE_FUNCS(sb_chksum, SB_CHKSUM); #ifdef CONFIG_BLK_DEV_ZONED static inline int get_blkz_type(struct f2fs_sb_info *sbi, diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 218695e44bd4..a44913224e3b 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -2178,6 +2178,26 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, (bh->b_data + F2FS_SUPER_OFFSET); struct super_block *sb = sbi->sb; unsigned int blocksize; + size_t crc_offset = 0; + __u32 crc = 0; + + /* Check checksum_offset and crc in superblock */ + if (le32_to_cpu(raw_super->feature) & F2FS_FEATURE_SB_CHKSUM) { + crc_offset = le32_to_cpu(raw_super->checksum_offset); + if (crc_offset != + offsetof(struct f2fs_super_block, crc)) { + f2fs_msg(sb, KERN_INFO, + "Invalid SB checksum offset: %zu", + crc_offset); + return 1; + } + crc = le32_to_cpu(raw_super->crc); + if (!f2fs_crc_valid(sbi, crc, raw_super, crc_offset)) { + f2fs_msg(sb, KERN_INFO, + "Invalid SB checksum value: %u", crc); + return 1; + } + } if (F2FS_SUPER_MAGIC != le32_to_cpu(raw_super->magic)) { f2fs_msg(sb, KERN_INFO, @@ -2635,6 +2655,7 @@ static int read_raw_super_block(struct f2fs_sb_info *sbi, int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover) { struct buffer_head *bh; + __u32 crc = 0; int err; if ((recover && f2fs_readonly(sbi->sb)) || @@ -2643,6 +2664,13 @@ int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover) return -EROFS; } + /* we should update superblock crc here */ + if (!recover && f2fs_sb_has_sb_chksum(sbi->sb)) { + crc = f2fs_crc32(sbi, F2FS_RAW_SUPER(sbi), + offsetof(struct f2fs_super_block, crc)); + F2FS_RAW_SUPER(sbi)->crc = cpu_to_le32(crc); + } + /* write back-up superblock first */ bh = sb_bread(sbi->sb, sbi->valid_super_block ? 0 : 1); if (!bh) diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index f5a545437b81..b777cbdd796b 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -117,6 +117,9 @@ static ssize_t features_show(struct f2fs_attr *a, if (f2fs_sb_has_lost_found(sb)) len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", len ? ", " : "", "lost_found"); + if (f2fs_sb_has_sb_chksum(sb)) + len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", + len ? ", " : "", "sb_checksum"); len += snprintf(buf + len, PAGE_SIZE - len, "\n"); return len; } @@ -334,6 +337,7 @@ enum feat_id { FEAT_QUOTA_INO, FEAT_INODE_CRTIME, FEAT_LOST_FOUND, + FEAT_SB_CHECKSUM, }; static ssize_t f2fs_feature_show(struct f2fs_attr *a, @@ -350,6 +354,7 @@ static ssize_t f2fs_feature_show(struct f2fs_attr *a, case FEAT_QUOTA_INO: case FEAT_INODE_CRTIME: case FEAT_LOST_FOUND: + case FEAT_SB_CHECKSUM: return snprintf(buf, PAGE_SIZE, "supported\n"); } return 0; @@ -434,6 +439,7 @@ F2FS_FEATURE_RO_ATTR(flexible_inline_xattr, FEAT_FLEXIBLE_INLINE_XATTR); F2FS_FEATURE_RO_ATTR(quota_ino, FEAT_QUOTA_INO); F2FS_FEATURE_RO_ATTR(inode_crtime, FEAT_INODE_CRTIME); F2FS_FEATURE_RO_ATTR(lost_found, FEAT_LOST_FOUND); +F2FS_FEATURE_RO_ATTR(sb_checksum, FEAT_SB_CHECKSUM); #define ATTR_LIST(name) (&f2fs_attr_##name.attr) static struct attribute *f2fs_attrs[] = { @@ -493,6 +499,7 @@ static struct attribute *f2fs_feat_attrs[] = { ATTR_LIST(quota_ino), ATTR_LIST(inode_crtime), ATTR_LIST(lost_found), + ATTR_LIST(sb_checksum), NULL, }; diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 1d4b196291d6..1db13ff9a3f4 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -109,7 +109,8 @@ struct f2fs_super_block { struct f2fs_device devs[MAX_DEVICES]; /* device list */ __le32 qf_ino[F2FS_MAX_QUOTAS]; /* quota inode numbers */ __u8 hot_ext_count; /* # of hot file extension */ - __u8 reserved[314]; /* valid reserved region */ + __u8 reserved[310]; /* valid reserved region */ + __le32 crc; /* checksum of superblock */ } __packed; /* -- cgit v1.2.3 From 2da274cdf998a1c12afa6b5975db2df1df01edf1 Mon Sep 17 00:00:00 2001 From: Zhen Lei Date: Thu, 20 Sep 2018 17:10:22 +0100 Subject: iommu/dma: Add support for non-strict mode With the flush queue infrastructure already abstracted into IOVA domains, hooking it up in iommu-dma is pretty simple. Since there is a degree of dependency on the IOMMU driver knowing what to do to play along, we key the whole thing off a domain attribute which will be set on default DMA ops domains to request non-strict invalidation. That way, drivers can indicate the appropriate support by acknowledging the attribute, and we can easily fall back to strict invalidation otherwise. The flush queue callback needs a handle on the iommu_domain which owns our cookie, so we have to add a pointer back to that, but neatly, that's also sufficient to indicate whether we're using a flush queue or not, and thus which way to release IOVAs. The only slight subtlety is switching __iommu_dma_unmap() from calling iommu_unmap() to explicit iommu_unmap_fast()/iommu_tlb_sync() so that we can elide the sync entirely in non-strict mode. Signed-off-by: Zhen Lei [rm: convert to domain attribute, tweak comments and commit message] Signed-off-by: Robin Murphy Signed-off-by: Will Deacon --- drivers/iommu/dma-iommu.c | 32 +++++++++++++++++++++++++++++++- include/linux/iommu.h | 1 + 2 files changed, 32 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 511ff9a1d6d9..cc1bf786cfac 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -55,6 +55,9 @@ struct iommu_dma_cookie { }; struct list_head msi_page_list; spinlock_t msi_lock; + + /* Domain for flush queue callback; NULL if flush queue not in use */ + struct iommu_domain *fq_domain; }; static inline size_t cookie_msi_granule(struct iommu_dma_cookie *cookie) @@ -257,6 +260,20 @@ static int iova_reserve_iommu_regions(struct device *dev, return ret; } +static void iommu_dma_flush_iotlb_all(struct iova_domain *iovad) +{ + struct iommu_dma_cookie *cookie; + struct iommu_domain *domain; + + cookie = container_of(iovad, struct iommu_dma_cookie, iovad); + domain = cookie->fq_domain; + /* + * The IOMMU driver supporting DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE + * implies that ops->flush_iotlb_all must be non-NULL. + */ + domain->ops->flush_iotlb_all(domain); +} + /** * iommu_dma_init_domain - Initialise a DMA mapping domain * @domain: IOMMU domain previously prepared by iommu_get_dma_cookie() @@ -275,6 +292,7 @@ int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base, struct iommu_dma_cookie *cookie = domain->iova_cookie; struct iova_domain *iovad = &cookie->iovad; unsigned long order, base_pfn, end_pfn; + int attr; if (!cookie || cookie->type != IOMMU_DMA_IOVA_COOKIE) return -EINVAL; @@ -308,6 +326,13 @@ int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base, } init_iova_domain(iovad, 1UL << order, base_pfn); + + if (!cookie->fq_domain && !iommu_domain_get_attr(domain, + DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE, &attr) && attr) { + cookie->fq_domain = domain; + init_iova_flush_queue(iovad, iommu_dma_flush_iotlb_all, NULL); + } + if (!dev) return 0; @@ -393,6 +418,9 @@ static void iommu_dma_free_iova(struct iommu_dma_cookie *cookie, /* The MSI case is only ever cleaning up its most recent allocation */ if (cookie->type == IOMMU_DMA_MSI_COOKIE) cookie->msi_iova -= size; + else if (cookie->fq_domain) /* non-strict mode */ + queue_iova(iovad, iova_pfn(iovad, iova), + size >> iova_shift(iovad), 0); else free_iova_fast(iovad, iova_pfn(iovad, iova), size >> iova_shift(iovad)); @@ -408,7 +436,9 @@ static void __iommu_dma_unmap(struct iommu_domain *domain, dma_addr_t dma_addr, dma_addr -= iova_off; size = iova_align(iovad, size + iova_off); - WARN_ON(iommu_unmap(domain, dma_addr, size) != size); + WARN_ON(iommu_unmap_fast(domain, dma_addr, size) != size); + if (!cookie->fq_domain) + iommu_tlb_sync(domain); iommu_dma_free_iova(cookie, dma_addr, size); } diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 87994c265bf5..decabe8e8dbe 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -124,6 +124,7 @@ enum iommu_attr { DOMAIN_ATTR_FSL_PAMU_ENABLE, DOMAIN_ATTR_FSL_PAMUV1, DOMAIN_ATTR_NESTING, /* two stages of translation */ + DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE, DOMAIN_ATTR_MAX, }; -- cgit v1.2.3 From 8ad50c8985d805923f52a80698010a0a5123c07d Mon Sep 17 00:00:00 2001 From: Kristina Martsenko Date: Wed, 26 Sep 2018 17:32:50 +0100 Subject: vgic: Add support for 52bit guest physical address Add support for handling 52bit guest physical address to the VGIC layer. So far we have limited the guest physical address to 48bits, by explicitly masking the upper bits. This patch removes the restriction. We do not have to check if the host supports 52bit as the gpa is always validated during an access. (e.g, kvm_{read/write}_guest, kvm_is_visible_gfn()). Also, the ITS table save-restore is also not affected with the enhancement. The DTE entries already store the bits[51:8] of the ITT_addr (with a 256byte alignment). Cc: Marc Zyngier Cc: Christoffer Dall Reviewed-by: Eric Auger Signed-off-by: Kristina Martsenko [ Macro clean ups, fix PROPBASER and PENDBASER accesses ] Signed-off-by: Suzuki K Poulose Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v3.h | 5 +++++ virt/kvm/arm/vgic/vgic-its.c | 36 ++++++++++-------------------------- virt/kvm/arm/vgic/vgic-mmio-v3.c | 2 -- 3 files changed, 15 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 8bdbb5f29494..74b0aa9c7499 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -357,6 +357,8 @@ #define GITS_CBASER_RaWaWt GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, RaWaWt) #define GITS_CBASER_RaWaWb GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, RaWaWb) +#define GITS_CBASER_ADDRESS(cbaser) ((cbaser) & GENMASK_ULL(51, 12)) + #define GITS_BASER_NR_REGS 8 #define GITS_BASER_VALID (1ULL << 63) @@ -388,6 +390,9 @@ #define GITS_BASER_ENTRY_SIZE_MASK GENMASK_ULL(52, 48) #define GITS_BASER_PHYS_52_to_48(phys) \ (((phys) & GENMASK_ULL(47, 16)) | (((phys) >> 48) & 0xf) << 12) +#define GITS_BASER_ADDR_48_to_52(baser) \ + (((baser) & GENMASK_ULL(47, 16)) | (((baser) >> 12) & 0xf) << 48) + #define GITS_BASER_SHAREABILITY_SHIFT (10) #define GITS_BASER_InnerShareable \ GIC_BASER_SHAREABILITY(GITS_BASER, InnerShareable) diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c index 12502251727e..eb2a390a6c86 100644 --- a/virt/kvm/arm/vgic/vgic-its.c +++ b/virt/kvm/arm/vgic/vgic-its.c @@ -241,13 +241,6 @@ static struct its_ite *find_ite(struct vgic_its *its, u32 device_id, list_for_each_entry(dev, &(its)->device_list, dev_list) \ list_for_each_entry(ite, &(dev)->itt_head, ite_list) -/* - * We only implement 48 bits of PA at the moment, although the ITS - * supports more. Let's be restrictive here. - */ -#define BASER_ADDRESS(x) ((x) & GENMASK_ULL(47, 16)) -#define CBASER_ADDRESS(x) ((x) & GENMASK_ULL(47, 12)) - #define GIC_LPI_OFFSET 8192 #define VITS_TYPER_IDBITS 16 @@ -759,6 +752,7 @@ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, u32 id, { int l1_tbl_size = GITS_BASER_NR_PAGES(baser) * SZ_64K; u64 indirect_ptr, type = GITS_BASER_TYPE(baser); + phys_addr_t base = GITS_BASER_ADDR_48_to_52(baser); int esz = GITS_BASER_ENTRY_SIZE(baser); int index; gfn_t gfn; @@ -783,7 +777,7 @@ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, u32 id, if (id >= (l1_tbl_size / esz)) return false; - addr = BASER_ADDRESS(baser) + id * esz; + addr = base + id * esz; gfn = addr >> PAGE_SHIFT; if (eaddr) @@ -798,7 +792,7 @@ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, u32 id, /* Each 1st level entry is represented by a 64-bit value. */ if (kvm_read_guest_lock(its->dev->kvm, - BASER_ADDRESS(baser) + index * sizeof(indirect_ptr), + base + index * sizeof(indirect_ptr), &indirect_ptr, sizeof(indirect_ptr))) return false; @@ -808,11 +802,7 @@ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, u32 id, if (!(indirect_ptr & BIT_ULL(63))) return false; - /* - * Mask the guest physical address and calculate the frame number. - * Any address beyond our supported 48 bits of PA will be caught - * by the actual check in the final step. - */ + /* Mask the guest physical address and calculate the frame number. */ indirect_ptr &= GENMASK_ULL(51, 16); /* Find the address of the actual entry */ @@ -1304,9 +1294,6 @@ static u64 vgic_sanitise_its_baser(u64 reg) GITS_BASER_OUTER_CACHEABILITY_SHIFT, vgic_sanitise_outer_cacheability); - /* Bits 15:12 contain bits 51:48 of the PA, which we don't support. */ - reg &= ~GENMASK_ULL(15, 12); - /* We support only one (ITS) page size: 64K */ reg = (reg & ~GITS_BASER_PAGE_SIZE_MASK) | GITS_BASER_PAGE_SIZE_64K; @@ -1325,11 +1312,8 @@ static u64 vgic_sanitise_its_cbaser(u64 reg) GITS_CBASER_OUTER_CACHEABILITY_SHIFT, vgic_sanitise_outer_cacheability); - /* - * Sanitise the physical address to be 64k aligned. - * Also limit the physical addresses to 48 bits. - */ - reg &= ~(GENMASK_ULL(51, 48) | GENMASK_ULL(15, 12)); + /* Sanitise the physical address to be 64k aligned. */ + reg &= ~GENMASK_ULL(15, 12); return reg; } @@ -1375,7 +1359,7 @@ static void vgic_its_process_commands(struct kvm *kvm, struct vgic_its *its) if (!its->enabled) return; - cbaser = CBASER_ADDRESS(its->cbaser); + cbaser = GITS_CBASER_ADDRESS(its->cbaser); while (its->cwriter != its->creadr) { int ret = kvm_read_guest_lock(kvm, cbaser + its->creadr, @@ -2233,7 +2217,7 @@ static int vgic_its_restore_device_tables(struct vgic_its *its) if (!(baser & GITS_BASER_VALID)) return 0; - l1_gpa = BASER_ADDRESS(baser); + l1_gpa = GITS_BASER_ADDR_48_to_52(baser); if (baser & GITS_BASER_INDIRECT) { l1_esz = GITS_LVL1_ENTRY_SIZE; @@ -2305,7 +2289,7 @@ static int vgic_its_save_collection_table(struct vgic_its *its) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); u64 baser = its->baser_coll_table; - gpa_t gpa = BASER_ADDRESS(baser); + gpa_t gpa = GITS_BASER_ADDR_48_to_52(baser); struct its_collection *collection; u64 val; size_t max_size, filled = 0; @@ -2354,7 +2338,7 @@ static int vgic_its_restore_collection_table(struct vgic_its *its) if (!(baser & GITS_BASER_VALID)) return 0; - gpa = BASER_ADDRESS(baser); + gpa = GITS_BASER_ADDR_48_to_52(baser); max_size = GITS_BASER_NR_PAGES(baser) * SZ_64K; diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c index a2a175b08b17..b3d1f0985117 100644 --- a/virt/kvm/arm/vgic/vgic-mmio-v3.c +++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c @@ -364,7 +364,6 @@ static u64 vgic_sanitise_pendbaser(u64 reg) vgic_sanitise_outer_cacheability); reg &= ~PENDBASER_RES0_MASK; - reg &= ~GENMASK_ULL(51, 48); return reg; } @@ -382,7 +381,6 @@ static u64 vgic_sanitise_propbaser(u64 reg) vgic_sanitise_outer_cacheability); reg &= ~PROPBASER_RES0_MASK; - reg &= ~GENMASK_ULL(51, 48); return reg; } -- cgit v1.2.3 From 8bad74f9840f87661f20ced3dc80c84ab4fd55a1 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 28 Sep 2018 14:45:36 +0000 Subject: bpf: extend cgroup bpf core to allow multiple cgroup storage types In order to introduce per-cpu cgroup storage, let's generalize bpf cgroup core to support multiple cgroup storage types. Potentially, per-node cgroup storage can be added later. This commit is mostly a formal change that replaces cgroup_storage pointer with a array of cgroup_storage pointers. It doesn't actually introduce a new storage type, it will be done later. Each bpf program is now able to have one cgroup storage of each type. Signed-off-by: Roman Gushchin Acked-by: Song Liu Cc: Daniel Borkmann Cc: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/bpf-cgroup.h | 38 +++++++++++++++++------- include/linux/bpf.h | 11 +++++-- kernel/bpf/cgroup.c | 74 ++++++++++++++++++++++++++++++++-------------- kernel/bpf/helpers.c | 15 ++++++---- kernel/bpf/local_storage.c | 18 ++++++----- kernel/bpf/syscall.c | 9 ++++-- kernel/bpf/verifier.c | 8 +++-- net/bpf/test_run.c | 20 +++++++++---- 8 files changed, 136 insertions(+), 57 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index f91b0f8ff3a9..e9871b012dac 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -2,6 +2,7 @@ #ifndef _BPF_CGROUP_H #define _BPF_CGROUP_H +#include #include #include #include @@ -22,7 +23,10 @@ struct bpf_cgroup_storage; extern struct static_key_false cgroup_bpf_enabled_key; #define cgroup_bpf_enabled static_branch_unlikely(&cgroup_bpf_enabled_key) -DECLARE_PER_CPU(void*, bpf_cgroup_storage); +DECLARE_PER_CPU(void*, bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); + +#define for_each_cgroup_storage_type(stype) \ + for (stype = 0; stype < MAX_BPF_CGROUP_STORAGE_TYPE; stype++) struct bpf_cgroup_storage_map; @@ -43,7 +47,7 @@ struct bpf_cgroup_storage { struct bpf_prog_list { struct list_head node; struct bpf_prog *prog; - struct bpf_cgroup_storage *storage; + struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]; }; struct bpf_prog_array; @@ -101,18 +105,29 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, short access, enum bpf_attach_type type); -static inline void bpf_cgroup_storage_set(struct bpf_cgroup_storage *storage) +static inline enum bpf_cgroup_storage_type cgroup_storage_type( + struct bpf_map *map) { + return BPF_CGROUP_STORAGE_SHARED; +} + +static inline void bpf_cgroup_storage_set(struct bpf_cgroup_storage + *storage[MAX_BPF_CGROUP_STORAGE_TYPE]) +{ + enum bpf_cgroup_storage_type stype; struct bpf_storage_buffer *buf; - if (!storage) - return; + for_each_cgroup_storage_type(stype) { + if (!storage[stype]) + continue; - buf = READ_ONCE(storage->buf); - this_cpu_write(bpf_cgroup_storage, &buf->data[0]); + buf = READ_ONCE(storage[stype]->buf); + this_cpu_write(bpf_cgroup_storage[stype], &buf->data[0]); + } } -struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog); +struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog, + enum bpf_cgroup_storage_type stype); void bpf_cgroup_storage_free(struct bpf_cgroup_storage *storage); void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage, struct cgroup *cgroup, @@ -265,13 +280,14 @@ static inline int cgroup_bpf_prog_query(const union bpf_attr *attr, return -EINVAL; } -static inline void bpf_cgroup_storage_set(struct bpf_cgroup_storage *storage) {} +static inline void bpf_cgroup_storage_set( + struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]) {} static inline int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *map) { return 0; } static inline void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *map) {} static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc( - struct bpf_prog *prog) { return 0; } + struct bpf_prog *prog, enum bpf_cgroup_storage_type stype) { return 0; } static inline void bpf_cgroup_storage_free( struct bpf_cgroup_storage *storage) {} @@ -293,6 +309,8 @@ static inline void bpf_cgroup_storage_free( #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; }) +#define for_each_cgroup_storage_type(stype) for (; false; ) + #endif /* CONFIG_CGROUP_BPF */ #endif /* _BPF_CGROUP_H */ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 988a00797bcd..b457fbe7b70b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -272,6 +272,13 @@ struct bpf_prog_offload { u32 jited_len; }; +enum bpf_cgroup_storage_type { + BPF_CGROUP_STORAGE_SHARED, + __BPF_CGROUP_STORAGE_MAX +}; + +#define MAX_BPF_CGROUP_STORAGE_TYPE __BPF_CGROUP_STORAGE_MAX + struct bpf_prog_aux { atomic_t refcnt; u32 used_map_cnt; @@ -289,7 +296,7 @@ struct bpf_prog_aux { struct bpf_prog *prog; struct user_struct *user; u64 load_time; /* ns since boottime */ - struct bpf_map *cgroup_storage; + struct bpf_map *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]; char name[BPF_OBJ_NAME_LEN]; #ifdef CONFIG_SECURITY void *security; @@ -358,7 +365,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, */ struct bpf_prog_array_item { struct bpf_prog *prog; - struct bpf_cgroup_storage *cgroup_storage; + struct bpf_cgroup_storage *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]; }; struct bpf_prog_array { diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 549f6fbcc461..00f6ed2e4f9a 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -25,6 +25,7 @@ EXPORT_SYMBOL(cgroup_bpf_enabled_key); */ void cgroup_bpf_put(struct cgroup *cgrp) { + enum bpf_cgroup_storage_type stype; unsigned int type; for (type = 0; type < ARRAY_SIZE(cgrp->bpf.progs); type++) { @@ -34,8 +35,10 @@ void cgroup_bpf_put(struct cgroup *cgrp) list_for_each_entry_safe(pl, tmp, progs, node) { list_del(&pl->node); bpf_prog_put(pl->prog); - bpf_cgroup_storage_unlink(pl->storage); - bpf_cgroup_storage_free(pl->storage); + for_each_cgroup_storage_type(stype) { + bpf_cgroup_storage_unlink(pl->storage[stype]); + bpf_cgroup_storage_free(pl->storage[stype]); + } kfree(pl); static_branch_dec(&cgroup_bpf_enabled_key); } @@ -97,6 +100,7 @@ static int compute_effective_progs(struct cgroup *cgrp, enum bpf_attach_type type, struct bpf_prog_array __rcu **array) { + enum bpf_cgroup_storage_type stype; struct bpf_prog_array *progs; struct bpf_prog_list *pl; struct cgroup *p = cgrp; @@ -125,7 +129,9 @@ static int compute_effective_progs(struct cgroup *cgrp, continue; progs->items[cnt].prog = pl->prog; - progs->items[cnt].cgroup_storage = pl->storage; + for_each_cgroup_storage_type(stype) + progs->items[cnt].cgroup_storage[stype] = + pl->storage[stype]; cnt++; } } while ((p = cgroup_parent(p))); @@ -232,7 +238,9 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, { struct list_head *progs = &cgrp->bpf.progs[type]; struct bpf_prog *old_prog = NULL; - struct bpf_cgroup_storage *storage, *old_storage = NULL; + struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE], + *old_storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {NULL}; + enum bpf_cgroup_storage_type stype; struct bpf_prog_list *pl; bool pl_was_allocated; int err; @@ -254,34 +262,44 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, if (prog_list_length(progs) >= BPF_CGROUP_MAX_PROGS) return -E2BIG; - storage = bpf_cgroup_storage_alloc(prog); - if (IS_ERR(storage)) - return -ENOMEM; + for_each_cgroup_storage_type(stype) { + storage[stype] = bpf_cgroup_storage_alloc(prog, stype); + if (IS_ERR(storage[stype])) { + storage[stype] = NULL; + for_each_cgroup_storage_type(stype) + bpf_cgroup_storage_free(storage[stype]); + return -ENOMEM; + } + } if (flags & BPF_F_ALLOW_MULTI) { list_for_each_entry(pl, progs, node) { if (pl->prog == prog) { /* disallow attaching the same prog twice */ - bpf_cgroup_storage_free(storage); + for_each_cgroup_storage_type(stype) + bpf_cgroup_storage_free(storage[stype]); return -EINVAL; } } pl = kmalloc(sizeof(*pl), GFP_KERNEL); if (!pl) { - bpf_cgroup_storage_free(storage); + for_each_cgroup_storage_type(stype) + bpf_cgroup_storage_free(storage[stype]); return -ENOMEM; } pl_was_allocated = true; pl->prog = prog; - pl->storage = storage; + for_each_cgroup_storage_type(stype) + pl->storage[stype] = storage[stype]; list_add_tail(&pl->node, progs); } else { if (list_empty(progs)) { pl = kmalloc(sizeof(*pl), GFP_KERNEL); if (!pl) { - bpf_cgroup_storage_free(storage); + for_each_cgroup_storage_type(stype) + bpf_cgroup_storage_free(storage[stype]); return -ENOMEM; } pl_was_allocated = true; @@ -289,12 +307,15 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, } else { pl = list_first_entry(progs, typeof(*pl), node); old_prog = pl->prog; - old_storage = pl->storage; - bpf_cgroup_storage_unlink(old_storage); + for_each_cgroup_storage_type(stype) { + old_storage[stype] = pl->storage[stype]; + bpf_cgroup_storage_unlink(old_storage[stype]); + } pl_was_allocated = false; } pl->prog = prog; - pl->storage = storage; + for_each_cgroup_storage_type(stype) + pl->storage[stype] = storage[stype]; } cgrp->bpf.flags[type] = flags; @@ -304,21 +325,27 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, goto cleanup; static_branch_inc(&cgroup_bpf_enabled_key); - if (old_storage) - bpf_cgroup_storage_free(old_storage); + for_each_cgroup_storage_type(stype) { + if (!old_storage[stype]) + continue; + bpf_cgroup_storage_free(old_storage[stype]); + } if (old_prog) { bpf_prog_put(old_prog); static_branch_dec(&cgroup_bpf_enabled_key); } - bpf_cgroup_storage_link(storage, cgrp, type); + for_each_cgroup_storage_type(stype) + bpf_cgroup_storage_link(storage[stype], cgrp, type); return 0; cleanup: /* and cleanup the prog list */ pl->prog = old_prog; - bpf_cgroup_storage_free(pl->storage); - pl->storage = old_storage; - bpf_cgroup_storage_link(old_storage, cgrp, type); + for_each_cgroup_storage_type(stype) { + bpf_cgroup_storage_free(pl->storage[stype]); + pl->storage[stype] = old_storage[stype]; + bpf_cgroup_storage_link(old_storage[stype], cgrp, type); + } if (pl_was_allocated) { list_del(&pl->node); kfree(pl); @@ -339,6 +366,7 @@ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, enum bpf_attach_type type, u32 unused_flags) { struct list_head *progs = &cgrp->bpf.progs[type]; + enum bpf_cgroup_storage_type stype; u32 flags = cgrp->bpf.flags[type]; struct bpf_prog *old_prog = NULL; struct bpf_prog_list *pl; @@ -385,8 +413,10 @@ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, /* now can actually delete it from this cgroup list */ list_del(&pl->node); - bpf_cgroup_storage_unlink(pl->storage); - bpf_cgroup_storage_free(pl->storage); + for_each_cgroup_storage_type(stype) { + bpf_cgroup_storage_unlink(pl->storage[stype]); + bpf_cgroup_storage_free(pl->storage[stype]); + } kfree(pl); if (list_empty(progs)) /* last program was detached, reset flags to zero */ diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 1991466b8327..9070b2ace6aa 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -194,16 +194,18 @@ const struct bpf_func_proto bpf_get_current_cgroup_id_proto = { .ret_type = RET_INTEGER, }; -DECLARE_PER_CPU(void*, bpf_cgroup_storage); +#ifdef CONFIG_CGROUP_BPF +DECLARE_PER_CPU(void*, bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags) { - /* map and flags arguments are not used now, - * but provide an ability to extend the API - * for other types of local storages. - * verifier checks that their values are correct. + /* flags argument is not used now, + * but provides an ability to extend the API. + * verifier checks that its value is correct. */ - return (unsigned long) this_cpu_read(bpf_cgroup_storage); + enum bpf_cgroup_storage_type stype = cgroup_storage_type(map); + + return (unsigned long) this_cpu_read(bpf_cgroup_storage[stype]); } const struct bpf_func_proto bpf_get_local_storage_proto = { @@ -214,3 +216,4 @@ const struct bpf_func_proto bpf_get_local_storage_proto = { .arg2_type = ARG_ANYTHING, }; #endif +#endif diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index 22ad967d1e5f..0bd9f19fc557 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -7,7 +7,7 @@ #include #include -DEFINE_PER_CPU(void*, bpf_cgroup_storage); +DEFINE_PER_CPU(void*, bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); #ifdef CONFIG_CGROUP_BPF @@ -251,6 +251,7 @@ const struct bpf_map_ops cgroup_storage_map_ops = { int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *_map) { + enum bpf_cgroup_storage_type stype = cgroup_storage_type(_map); struct bpf_cgroup_storage_map *map = map_to_storage(_map); int ret = -EBUSY; @@ -258,11 +259,12 @@ int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *_map) if (map->prog && map->prog != prog) goto unlock; - if (prog->aux->cgroup_storage && prog->aux->cgroup_storage != _map) + if (prog->aux->cgroup_storage[stype] && + prog->aux->cgroup_storage[stype] != _map) goto unlock; map->prog = prog; - prog->aux->cgroup_storage = _map; + prog->aux->cgroup_storage[stype] = _map; ret = 0; unlock: spin_unlock_bh(&map->lock); @@ -272,24 +274,26 @@ unlock: void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *_map) { + enum bpf_cgroup_storage_type stype = cgroup_storage_type(_map); struct bpf_cgroup_storage_map *map = map_to_storage(_map); spin_lock_bh(&map->lock); if (map->prog == prog) { - WARN_ON(prog->aux->cgroup_storage != _map); + WARN_ON(prog->aux->cgroup_storage[stype] != _map); map->prog = NULL; - prog->aux->cgroup_storage = NULL; + prog->aux->cgroup_storage[stype] = NULL; } spin_unlock_bh(&map->lock); } -struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog) +struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog, + enum bpf_cgroup_storage_type stype) { struct bpf_cgroup_storage *storage; struct bpf_map *map; u32 pages; - map = prog->aux->cgroup_storage; + map = prog->aux->cgroup_storage[stype]; if (!map) return NULL; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index b3c2d09bcf7a..8c91d2b41b1e 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -988,10 +988,15 @@ static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog) /* drop refcnt on maps used by eBPF program and free auxilary data */ static void free_used_maps(struct bpf_prog_aux *aux) { + enum bpf_cgroup_storage_type stype; int i; - if (aux->cgroup_storage) - bpf_cgroup_storage_release(aux->prog, aux->cgroup_storage); + for_each_cgroup_storage_type(stype) { + if (!aux->cgroup_storage[stype]) + continue; + bpf_cgroup_storage_release(aux->prog, + aux->cgroup_storage[stype]); + } for (i = 0; i < aux->used_map_cnt; i++) bpf_map_put(aux->used_maps[i]); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e986518d7bc3..e90899df585d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5171,11 +5171,15 @@ next_insn: /* drop refcnt of maps used by the rejected program */ static void release_maps(struct bpf_verifier_env *env) { + enum bpf_cgroup_storage_type stype; int i; - if (env->prog->aux->cgroup_storage) + for_each_cgroup_storage_type(stype) { + if (!env->prog->aux->cgroup_storage[stype]) + continue; bpf_cgroup_storage_release(env->prog, - env->prog->aux->cgroup_storage); + env->prog->aux->cgroup_storage[stype]); + } for (i = 0; i < env->used_map_cnt; i++) bpf_map_put(env->used_maps[i]); diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index f4078830ea50..0c423b8cd75c 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -12,7 +12,7 @@ #include static __always_inline u32 bpf_test_run_one(struct bpf_prog *prog, void *ctx, - struct bpf_cgroup_storage *storage) + struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]) { u32 ret; @@ -28,13 +28,20 @@ static __always_inline u32 bpf_test_run_one(struct bpf_prog *prog, void *ctx, static u32 bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *time) { - struct bpf_cgroup_storage *storage = NULL; + struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE] = { 0 }; + enum bpf_cgroup_storage_type stype; u64 time_start, time_spent = 0; u32 ret = 0, i; - storage = bpf_cgroup_storage_alloc(prog); - if (IS_ERR(storage)) - return PTR_ERR(storage); + for_each_cgroup_storage_type(stype) { + storage[stype] = bpf_cgroup_storage_alloc(prog, stype); + if (IS_ERR(storage[stype])) { + storage[stype] = NULL; + for_each_cgroup_storage_type(stype) + bpf_cgroup_storage_free(storage[stype]); + return -ENOMEM; + } + } if (!repeat) repeat = 1; @@ -53,7 +60,8 @@ static u32 bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *time) do_div(time_spent, repeat); *time = time_spent > U32_MAX ? U32_MAX : (u32)time_spent; - bpf_cgroup_storage_free(storage); + for_each_cgroup_storage_type(stype) + bpf_cgroup_storage_free(storage[stype]); return ret; } -- cgit v1.2.3 From f294b37ec7b24a574884cd157497a3748081c0f0 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 28 Sep 2018 14:45:40 +0000 Subject: bpf: rework cgroup storage pointer passing To simplify the following introduction of per-cpu cgroup storage, let's rework a bit a mechanism of passing a pointer to a cgroup storage into the bpf_get_local_storage(). Let's save a pointer to the corresponding bpf_cgroup_storage structure, instead of a pointer to the actual buffer. It will help us to handle per-cpu storage later, which has a different way of accessing to the actual data. Signed-off-by: Roman Gushchin Acked-by: Song Liu Cc: Daniel Borkmann Cc: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/bpf-cgroup.h | 13 ++++--------- kernel/bpf/helpers.c | 8 ++++++-- kernel/bpf/local_storage.c | 3 ++- 3 files changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index e9871b012dac..7e0c9a1d48b7 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -23,7 +23,8 @@ struct bpf_cgroup_storage; extern struct static_key_false cgroup_bpf_enabled_key; #define cgroup_bpf_enabled static_branch_unlikely(&cgroup_bpf_enabled_key) -DECLARE_PER_CPU(void*, bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); +DECLARE_PER_CPU(struct bpf_cgroup_storage*, + bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); #define for_each_cgroup_storage_type(stype) \ for (stype = 0; stype < MAX_BPF_CGROUP_STORAGE_TYPE; stype++) @@ -115,15 +116,9 @@ static inline void bpf_cgroup_storage_set(struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]) { enum bpf_cgroup_storage_type stype; - struct bpf_storage_buffer *buf; - - for_each_cgroup_storage_type(stype) { - if (!storage[stype]) - continue; - buf = READ_ONCE(storage[stype]->buf); - this_cpu_write(bpf_cgroup_storage[stype], &buf->data[0]); - } + for_each_cgroup_storage_type(stype) + this_cpu_write(bpf_cgroup_storage[stype], storage[stype]); } struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog, diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 9070b2ace6aa..e42f8789b7ea 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -195,7 +195,8 @@ const struct bpf_func_proto bpf_get_current_cgroup_id_proto = { }; #ifdef CONFIG_CGROUP_BPF -DECLARE_PER_CPU(void*, bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); +DECLARE_PER_CPU(struct bpf_cgroup_storage*, + bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags) { @@ -204,8 +205,11 @@ BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags) * verifier checks that its value is correct. */ enum bpf_cgroup_storage_type stype = cgroup_storage_type(map); + struct bpf_cgroup_storage *storage; - return (unsigned long) this_cpu_read(bpf_cgroup_storage[stype]); + storage = this_cpu_read(bpf_cgroup_storage[stype]); + + return (unsigned long)&READ_ONCE(storage->buf)->data[0]; } const struct bpf_func_proto bpf_get_local_storage_proto = { diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index 0bd9f19fc557..6742292fb39e 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -7,7 +7,8 @@ #include #include -DEFINE_PER_CPU(void*, bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); +DEFINE_PER_CPU(struct bpf_cgroup_storage*, + bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); #ifdef CONFIG_CGROUP_BPF -- cgit v1.2.3 From b741f1630346defcbc8cc60f1a2bdae8b3b0036f Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 28 Sep 2018 14:45:43 +0000 Subject: bpf: introduce per-cpu cgroup local storage This commit introduced per-cpu cgroup local storage. Per-cpu cgroup local storage is very similar to simple cgroup storage (let's call it shared), except all the data is per-cpu. The main goal of per-cpu variant is to implement super fast counters (e.g. packet counters), which don't require neither lookups, neither atomic operations. >From userspace's point of view, accessing a per-cpu cgroup storage is similar to other per-cpu map types (e.g. per-cpu hashmaps and arrays). Writing to a per-cpu cgroup storage is not atomic, but is performed by copying longs, so some minimal atomicity is here, exactly as with other per-cpu maps. Signed-off-by: Roman Gushchin Cc: Daniel Borkmann Cc: Alexei Starovoitov Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- include/linux/bpf-cgroup.h | 20 +++++- include/linux/bpf.h | 1 + include/linux/bpf_types.h | 1 + include/uapi/linux/bpf.h | 1 + kernel/bpf/helpers.c | 8 ++- kernel/bpf/local_storage.c | 150 +++++++++++++++++++++++++++++++++++++++------ kernel/bpf/syscall.c | 11 +++- kernel/bpf/verifier.c | 15 +++-- 8 files changed, 179 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 7e0c9a1d48b7..588dd5f0bd85 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -37,7 +37,10 @@ struct bpf_storage_buffer { }; struct bpf_cgroup_storage { - struct bpf_storage_buffer *buf; + union { + struct bpf_storage_buffer *buf; + void __percpu *percpu_buf; + }; struct bpf_cgroup_storage_map *map; struct bpf_cgroup_storage_key key; struct list_head list; @@ -109,6 +112,9 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, static inline enum bpf_cgroup_storage_type cgroup_storage_type( struct bpf_map *map) { + if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) + return BPF_CGROUP_STORAGE_PERCPU; + return BPF_CGROUP_STORAGE_SHARED; } @@ -131,6 +137,10 @@ void bpf_cgroup_storage_unlink(struct bpf_cgroup_storage *storage); int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *map); void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *map); +int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key, void *value); +int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, + void *value, u64 flags); + /* Wrappers for __cgroup_bpf_run_filter_skb() guarded by cgroup_bpf_enabled. */ #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb) \ ({ \ @@ -285,6 +295,14 @@ static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc( struct bpf_prog *prog, enum bpf_cgroup_storage_type stype) { return 0; } static inline void bpf_cgroup_storage_free( struct bpf_cgroup_storage *storage) {} +static inline int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key, + void *value) { + return 0; +} +static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, + void *key, void *value, u64 flags) { + return 0; +} #define cgroup_bpf_enabled (0) #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b457fbe7b70b..018299a595c8 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -274,6 +274,7 @@ struct bpf_prog_offload { enum bpf_cgroup_storage_type { BPF_CGROUP_STORAGE_SHARED, + BPF_CGROUP_STORAGE_PERCPU, __BPF_CGROUP_STORAGE_MAX }; diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index c9bd6fb765b0..5432f4c9f50e 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -43,6 +43,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_CGROUP_ARRAY, cgroup_array_map_ops) #endif #ifdef CONFIG_CGROUP_BPF BPF_MAP_TYPE(BPF_MAP_TYPE_CGROUP_STORAGE, cgroup_storage_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, cgroup_storage_map_ops) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_HASH, htab_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_HASH, htab_percpu_map_ops) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index aa5ccd2385ed..e2070d819e04 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -127,6 +127,7 @@ enum bpf_map_type { BPF_MAP_TYPE_SOCKHASH, BPF_MAP_TYPE_CGROUP_STORAGE, BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, + BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, }; enum bpf_prog_type { diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index e42f8789b7ea..6502115e8f55 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -206,10 +206,16 @@ BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags) */ enum bpf_cgroup_storage_type stype = cgroup_storage_type(map); struct bpf_cgroup_storage *storage; + void *ptr; storage = this_cpu_read(bpf_cgroup_storage[stype]); - return (unsigned long)&READ_ONCE(storage->buf)->data[0]; + if (stype == BPF_CGROUP_STORAGE_SHARED) + ptr = &READ_ONCE(storage->buf)->data[0]; + else + ptr = this_cpu_ptr(storage->percpu_buf); + + return (unsigned long)ptr; } const struct bpf_func_proto bpf_get_local_storage_proto = { diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index 6742292fb39e..944eb297465f 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -152,6 +152,71 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *_key, return 0; } +int bpf_percpu_cgroup_storage_copy(struct bpf_map *_map, void *_key, + void *value) +{ + struct bpf_cgroup_storage_map *map = map_to_storage(_map); + struct bpf_cgroup_storage_key *key = _key; + struct bpf_cgroup_storage *storage; + int cpu, off = 0; + u32 size; + + rcu_read_lock(); + storage = cgroup_storage_lookup(map, key, false); + if (!storage) { + rcu_read_unlock(); + return -ENOENT; + } + + /* per_cpu areas are zero-filled and bpf programs can only + * access 'value_size' of them, so copying rounded areas + * will not leak any kernel data + */ + size = round_up(_map->value_size, 8); + for_each_possible_cpu(cpu) { + bpf_long_memcpy(value + off, + per_cpu_ptr(storage->percpu_buf, cpu), size); + off += size; + } + rcu_read_unlock(); + return 0; +} + +int bpf_percpu_cgroup_storage_update(struct bpf_map *_map, void *_key, + void *value, u64 map_flags) +{ + struct bpf_cgroup_storage_map *map = map_to_storage(_map); + struct bpf_cgroup_storage_key *key = _key; + struct bpf_cgroup_storage *storage; + int cpu, off = 0; + u32 size; + + if (map_flags != BPF_ANY && map_flags != BPF_EXIST) + return -EINVAL; + + rcu_read_lock(); + storage = cgroup_storage_lookup(map, key, false); + if (!storage) { + rcu_read_unlock(); + return -ENOENT; + } + + /* the user space will provide round_up(value_size, 8) bytes that + * will be copied into per-cpu area. bpf programs can only access + * value_size of it. During lookup the same extra bytes will be + * returned or zeros which were zero-filled by percpu_alloc, + * so no kernel data leaks possible + */ + size = round_up(_map->value_size, 8); + for_each_possible_cpu(cpu) { + bpf_long_memcpy(per_cpu_ptr(storage->percpu_buf, cpu), + value + off, size); + off += size; + } + rcu_read_unlock(); + return 0; +} + static int cgroup_storage_get_next_key(struct bpf_map *_map, void *_key, void *_next_key) { @@ -287,60 +352,105 @@ void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *_map) spin_unlock_bh(&map->lock); } +static size_t bpf_cgroup_storage_calculate_size(struct bpf_map *map, u32 *pages) +{ + size_t size; + + if (cgroup_storage_type(map) == BPF_CGROUP_STORAGE_SHARED) { + size = sizeof(struct bpf_storage_buffer) + map->value_size; + *pages = round_up(sizeof(struct bpf_cgroup_storage) + size, + PAGE_SIZE) >> PAGE_SHIFT; + } else { + size = map->value_size; + *pages = round_up(round_up(size, 8) * num_possible_cpus(), + PAGE_SIZE) >> PAGE_SHIFT; + } + + return size; +} + struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog, enum bpf_cgroup_storage_type stype) { struct bpf_cgroup_storage *storage; struct bpf_map *map; + gfp_t flags; + size_t size; u32 pages; map = prog->aux->cgroup_storage[stype]; if (!map) return NULL; - pages = round_up(sizeof(struct bpf_cgroup_storage) + - sizeof(struct bpf_storage_buffer) + - map->value_size, PAGE_SIZE) >> PAGE_SHIFT; + size = bpf_cgroup_storage_calculate_size(map, &pages); + if (bpf_map_charge_memlock(map, pages)) return ERR_PTR(-EPERM); storage = kmalloc_node(sizeof(struct bpf_cgroup_storage), __GFP_ZERO | GFP_USER, map->numa_node); - if (!storage) { - bpf_map_uncharge_memlock(map, pages); - return ERR_PTR(-ENOMEM); - } + if (!storage) + goto enomem; - storage->buf = kmalloc_node(sizeof(struct bpf_storage_buffer) + - map->value_size, __GFP_ZERO | GFP_USER, - map->numa_node); - if (!storage->buf) { - bpf_map_uncharge_memlock(map, pages); - kfree(storage); - return ERR_PTR(-ENOMEM); + flags = __GFP_ZERO | GFP_USER; + + if (stype == BPF_CGROUP_STORAGE_SHARED) { + storage->buf = kmalloc_node(size, flags, map->numa_node); + if (!storage->buf) + goto enomem; + } else { + storage->percpu_buf = __alloc_percpu_gfp(size, 8, flags); + if (!storage->percpu_buf) + goto enomem; } storage->map = (struct bpf_cgroup_storage_map *)map; return storage; + +enomem: + bpf_map_uncharge_memlock(map, pages); + kfree(storage); + return ERR_PTR(-ENOMEM); +} + +static void free_shared_cgroup_storage_rcu(struct rcu_head *rcu) +{ + struct bpf_cgroup_storage *storage = + container_of(rcu, struct bpf_cgroup_storage, rcu); + + kfree(storage->buf); + kfree(storage); +} + +static void free_percpu_cgroup_storage_rcu(struct rcu_head *rcu) +{ + struct bpf_cgroup_storage *storage = + container_of(rcu, struct bpf_cgroup_storage, rcu); + + free_percpu(storage->percpu_buf); + kfree(storage); } void bpf_cgroup_storage_free(struct bpf_cgroup_storage *storage) { - u32 pages; + enum bpf_cgroup_storage_type stype; struct bpf_map *map; + u32 pages; if (!storage) return; map = &storage->map->map; - pages = round_up(sizeof(struct bpf_cgroup_storage) + - sizeof(struct bpf_storage_buffer) + - map->value_size, PAGE_SIZE) >> PAGE_SHIFT; + + bpf_cgroup_storage_calculate_size(map, &pages); bpf_map_uncharge_memlock(map, pages); - kfree_rcu(storage->buf, rcu); - kfree_rcu(storage, rcu); + stype = cgroup_storage_type(map); + if (stype == BPF_CGROUP_STORAGE_SHARED) + call_rcu(&storage->rcu, free_shared_cgroup_storage_rcu); + else + call_rcu(&storage->rcu, free_percpu_cgroup_storage_rcu); } void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage, diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 8c91d2b41b1e..5742df21598c 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -686,7 +686,8 @@ static int map_lookup_elem(union bpf_attr *attr) if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || - map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) + map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY || + map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) value_size = round_up(map->value_size, 8) * num_possible_cpus(); else if (IS_FD_MAP(map)) value_size = sizeof(u32); @@ -705,6 +706,8 @@ static int map_lookup_elem(union bpf_attr *attr) err = bpf_percpu_hash_copy(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_copy(map, key, value); + } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) { + err = bpf_percpu_cgroup_storage_copy(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) { err = bpf_stackmap_copy(map, key, value); } else if (IS_FD_ARRAY(map)) { @@ -774,7 +777,8 @@ static int map_update_elem(union bpf_attr *attr) if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || - map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) + map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY || + map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) value_size = round_up(map->value_size, 8) * num_possible_cpus(); else value_size = map->value_size; @@ -809,6 +813,9 @@ static int map_update_elem(union bpf_attr *attr) err = bpf_percpu_hash_update(map, key, value, attr->flags); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_update(map, key, value, attr->flags); + } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) { + err = bpf_percpu_cgroup_storage_update(map, key, value, + attr->flags); } else if (IS_FD_ARRAY(map)) { rcu_read_lock(); err = bpf_fd_array_map_update_elem(map, f.file, key, value, diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e90899df585d..a8cc83a970d1 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2074,6 +2074,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, goto error; break; case BPF_MAP_TYPE_CGROUP_STORAGE: + case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE: if (func_id != BPF_FUNC_get_local_storage) goto error; break; @@ -2164,7 +2165,8 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, goto error; break; case BPF_FUNC_get_local_storage: - if (map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE) + if (map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE && + map->map_type != BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) goto error; break; case BPF_FUNC_sk_select_reuseport: @@ -5049,6 +5051,12 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, return 0; } +static bool bpf_map_is_cgroup_storage(struct bpf_map *map) +{ + return (map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE || + map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE); +} + /* look for pseudo eBPF instructions that access map FDs and * replace them with actual map pointers */ @@ -5139,10 +5147,9 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) } env->used_maps[env->used_map_cnt++] = map; - if (map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE && + if (bpf_map_is_cgroup_storage(map) && bpf_cgroup_storage_assign(env->prog, map)) { - verbose(env, - "only one cgroup storage is allowed\n"); + verbose(env, "only one cgroup storage of each type is allowed\n"); fdput(f); return -EBUSY; } -- cgit v1.2.3 From 59c9d35ea9cd73c3a55642ec9a0097770baccb93 Mon Sep 17 00:00:00 2001 From: Alaa Hleihel Date: Wed, 5 Sep 2018 17:06:37 +0300 Subject: net/mlx5: Cache the system image guid The system image guid is a read-only field which is used by the TC offloads code to determine if two mlx5 devices belong to the same ASIC while adding flows. Read this once and save it on the core device rather than querying each time an offloaded flow is added. Signed-off-by: Alaa Hleihel Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/vport.c | 9 +++++++++ include/linux/mlx5/driver.h | 1 + include/linux/mlx5/vport.h | 2 ++ 4 files changed, 14 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 9fed54017659..82723a0e509a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -2040,8 +2040,8 @@ static bool same_hw_devs(struct mlx5e_priv *priv, struct mlx5e_priv *peer_priv) fmdev = priv->mdev; pmdev = peer_priv->mdev; - mlx5_query_nic_vport_system_image_guid(fmdev, &fsystem_guid); - mlx5_query_nic_vport_system_image_guid(pmdev, &psystem_guid); + fsystem_guid = mlx5_query_nic_system_image_guid(fmdev); + psystem_guid = mlx5_query_nic_system_image_guid(pmdev); return (fsystem_guid == psystem_guid); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index b02af317c125..cfbea66b4879 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -1201,3 +1201,12 @@ int mlx5_nic_vport_unaffiliate_multiport(struct mlx5_core_dev *port_mdev) return err; } EXPORT_SYMBOL_GPL(mlx5_nic_vport_unaffiliate_multiport); + +u64 mlx5_query_nic_system_image_guid(struct mlx5_core_dev *mdev) +{ + if (!mdev->sys_image_guid) + mlx5_query_nic_vport_system_image_guid(mdev, &mdev->sys_image_guid); + + return mdev->sys_image_guid; +} +EXPORT_SYMBOL_GPL(mlx5_query_nic_system_image_guid); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index ed73b51f6697..26a92462f4ce 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -838,6 +838,7 @@ struct mlx5_core_dev { u32 fpga[MLX5_ST_SZ_DW(fpga_cap)]; u32 qcam[MLX5_ST_SZ_DW(qcam_reg)]; } caps; + u64 sys_image_guid; phys_addr_t iseg_base; struct mlx5_init_seg __iomem *iseg; enum mlx5_device_state state; diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index 7e7c6dfcfb09..9c694808c212 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -121,4 +121,6 @@ int mlx5_nic_vport_query_local_lb(struct mlx5_core_dev *mdev, bool *status); int mlx5_nic_vport_affiliate_multiport(struct mlx5_core_dev *master_mdev, struct mlx5_core_dev *port_mdev); int mlx5_nic_vport_unaffiliate_multiport(struct mlx5_core_dev *port_mdev); + +u64 mlx5_query_nic_system_image_guid(struct mlx5_core_dev *mdev); #endif /* __MLX5_VPORT_H__ */ -- cgit v1.2.3 From b31cdffa2329fe330cd304ca26c250dd1520fb0a Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 29 Sep 2018 23:04:09 +0200 Subject: net: phy: Move linkmode helpers to somewhere public phylink has some useful helpers to working with linkmode bitmaps. Move them to there own header so other code can use them. Signed-off-by: Andrew Lunn Acked-by: Florian Fainelli Reviewed-by: Maxime Chevallier Signed-off-by: David S. Miller --- drivers/net/phy/phylink.c | 27 ------------------- include/linux/linkmode.h | 67 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/mii.h | 1 + include/linux/phy.h | 1 + 4 files changed, 69 insertions(+), 27 deletions(-) create mode 100644 include/linux/linkmode.h (limited to 'include/linux') diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 1d01e0c625a5..b6993af5c9e4 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -68,33 +68,6 @@ struct phylink { struct sfp_bus *sfp_bus; }; -static inline void linkmode_zero(unsigned long *dst) -{ - bitmap_zero(dst, __ETHTOOL_LINK_MODE_MASK_NBITS); -} - -static inline void linkmode_copy(unsigned long *dst, const unsigned long *src) -{ - bitmap_copy(dst, src, __ETHTOOL_LINK_MODE_MASK_NBITS); -} - -static inline void linkmode_and(unsigned long *dst, const unsigned long *a, - const unsigned long *b) -{ - bitmap_and(dst, a, b, __ETHTOOL_LINK_MODE_MASK_NBITS); -} - -static inline void linkmode_or(unsigned long *dst, const unsigned long *a, - const unsigned long *b) -{ - bitmap_or(dst, a, b, __ETHTOOL_LINK_MODE_MASK_NBITS); -} - -static inline bool linkmode_empty(const unsigned long *src) -{ - return bitmap_empty(src, __ETHTOOL_LINK_MODE_MASK_NBITS); -} - /** * phylink_set_port_modes() - set the port type modes in the ethtool mask * @mask: ethtool link mode mask diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h new file mode 100644 index 000000000000..014fb86c7114 --- /dev/null +++ b/include/linux/linkmode.h @@ -0,0 +1,67 @@ +#ifndef __LINKMODE_H +#define __LINKMODE_H + +#include +#include +#include + +static inline void linkmode_zero(unsigned long *dst) +{ + bitmap_zero(dst, __ETHTOOL_LINK_MODE_MASK_NBITS); +} + +static inline void linkmode_copy(unsigned long *dst, const unsigned long *src) +{ + bitmap_copy(dst, src, __ETHTOOL_LINK_MODE_MASK_NBITS); +} + +static inline void linkmode_and(unsigned long *dst, const unsigned long *a, + const unsigned long *b) +{ + bitmap_and(dst, a, b, __ETHTOOL_LINK_MODE_MASK_NBITS); +} + +static inline void linkmode_or(unsigned long *dst, const unsigned long *a, + const unsigned long *b) +{ + bitmap_or(dst, a, b, __ETHTOOL_LINK_MODE_MASK_NBITS); +} + +static inline bool linkmode_empty(const unsigned long *src) +{ + return bitmap_empty(src, __ETHTOOL_LINK_MODE_MASK_NBITS); +} + +static inline int linkmode_andnot(unsigned long *dst, const unsigned long *src1, + const unsigned long *src2) +{ + return bitmap_andnot(dst, src1, src2, __ETHTOOL_LINK_MODE_MASK_NBITS); +} + +static inline void linkmode_set_bit(int nr, volatile unsigned long *addr) +{ + __set_bit(nr, addr); +} + +static inline void linkmode_clear_bit(int nr, volatile unsigned long *addr) +{ + __clear_bit(nr, addr); +} + +static inline void linkmode_change_bit(int nr, volatile unsigned long *addr) +{ + __change_bit(nr, addr); +} + +static inline int linkmode_test_bit(int nr, volatile unsigned long *addr) +{ + return test_bit(nr, addr); +} + +static inline int linkmode_equal(const unsigned long *src1, + const unsigned long *src2) +{ + return bitmap_equal(src1, src2, __ETHTOOL_LINK_MODE_MASK_NBITS); +} + +#endif /* __LINKMODE_H */ diff --git a/include/linux/mii.h b/include/linux/mii.h index 55000ee5c6ad..567047ef0309 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -10,6 +10,7 @@ #include +#include #include struct ethtool_cmd; diff --git a/include/linux/phy.h b/include/linux/phy.h index 192a1fa0c73b..d24cc46748e2 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include -- cgit v1.2.3 From ab2a605fa621ecf4ec26603a237822f7772cfa28 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 29 Sep 2018 23:04:10 +0200 Subject: net: phy: Add phydev_warn() Not all new style LINK_MODE bits can be converted into old style SUPPORTED bits. We need to warn when such a conversion is attempted. Add a helper for this. Convert all pr_warn() calls to phydev_warn() where possible. Signed-off-by: Andrew Lunn Reviewed-by: Maxime Chevallier Signed-off-by: David S. Miller --- drivers/net/phy/at803x.c | 2 +- drivers/net/phy/dp83640.c | 7 ++++--- drivers/net/phy/marvell.c | 2 +- drivers/net/phy/marvell10g.c | 6 +++--- drivers/net/phy/microchip.c | 33 +++++++++++++++++---------------- include/linux/phy.h | 3 +++ 6 files changed, 29 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index 411cf1072bae..e74a047a846e 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -357,7 +357,7 @@ static int at803x_aneg_done(struct phy_device *phydev) /* check if the SGMII link is OK. */ if (!(phy_read(phydev, AT803X_PSSR) & AT803X_PSSR_MR_AN_COMPLETE)) { - pr_warn("803x_aneg_done: SGMII link is not ok\n"); + phydev_warn(phydev, "803x_aneg_done: SGMII link is not ok\n"); aneg_done = 0; } /* switch back to copper page */ diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index 29aa8d772b0c..74cf356d8171 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -553,16 +553,17 @@ static void enable_status_frames(struct phy_device *phydev, bool on) mutex_unlock(&clock->extreg_lock); if (!phydev->attached_dev) { - pr_warn("expected to find an attached netdevice\n"); + phydev_warn(phydev, + "expected to find an attached netdevice\n"); return; } if (on) { if (dev_mc_add(phydev->attached_dev, status_frame_dst)) - pr_warn("failed to add mc address\n"); + phydev_warn(phydev, "failed to add mc address\n"); } else { if (dev_mc_del(phydev->attached_dev, status_frame_dst)) - pr_warn("failed to delete mc address\n"); + phydev_warn(phydev, "failed to delete mc address\n"); } } diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 24fc4a73c300..8872a430d74a 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -638,7 +638,7 @@ static void marvell_config_led(struct phy_device *phydev) err = phy_write_paged(phydev, MII_MARVELL_LED_PAGE, MII_PHY_LED_CTRL, def_config); if (err < 0) - pr_warn("Fail to config marvell phy LED.\n"); + phydev_warn(phydev, "Fail to config marvell phy LED.\n"); } static int marvell_config_init(struct phy_device *phydev) diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c index f77a2d9e7f9d..f214834819dd 100644 --- a/drivers/net/phy/marvell10g.c +++ b/drivers/net/phy/marvell10g.c @@ -337,9 +337,9 @@ static int mv3310_config_init(struct phy_device *phydev) } if (!ethtool_convert_link_mode_to_legacy_u32(&mask, supported)) - dev_warn(&phydev->mdio.dev, - "PHY supports (%*pb) more modes than phylib supports, some modes not supported.\n", - __ETHTOOL_LINK_MODE_MASK_NBITS, supported); + phydev_warn(phydev, + "PHY supports (%*pb) more modes than phylib supports, some modes not supported.\n", + __ETHTOOL_LINK_MODE_MASK_NBITS, supported); phydev->supported &= mask; phydev->advertising &= phydev->supported; diff --git a/drivers/net/phy/microchip.c b/drivers/net/phy/microchip.c index 2d67937866a3..04b12e34da58 100644 --- a/drivers/net/phy/microchip.c +++ b/drivers/net/phy/microchip.c @@ -88,7 +88,7 @@ static int lan88xx_TR_reg_set(struct phy_device *phydev, u16 regaddr, /* Save current page */ save_page = phy_save_page(phydev); if (save_page < 0) { - pr_warn("Failed to get current page\n"); + phydev_warn(phydev, "Failed to get current page\n"); goto err; } @@ -98,14 +98,14 @@ static int lan88xx_TR_reg_set(struct phy_device *phydev, u16 regaddr, ret = __phy_write(phydev, LAN88XX_EXT_PAGE_TR_LOW_DATA, (data & 0xFFFF)); if (ret < 0) { - pr_warn("Failed to write TR low data\n"); + phydev_warn(phydev, "Failed to write TR low data\n"); goto err; } ret = __phy_write(phydev, LAN88XX_EXT_PAGE_TR_HIGH_DATA, (data & 0x00FF0000) >> 16); if (ret < 0) { - pr_warn("Failed to write TR high data\n"); + phydev_warn(phydev, "Failed to write TR high data\n"); goto err; } @@ -115,14 +115,15 @@ static int lan88xx_TR_reg_set(struct phy_device *phydev, u16 regaddr, ret = __phy_write(phydev, LAN88XX_EXT_PAGE_TR_CR, buf); if (ret < 0) { - pr_warn("Failed to write data in reg\n"); + phydev_warn(phydev, "Failed to write data in reg\n"); goto err; } usleep_range(1000, 2000);/* Wait for Data to be written */ val = __phy_read(phydev, LAN88XX_EXT_PAGE_TR_CR); if (!(val & 0x8000)) - pr_warn("TR Register[0x%X] configuration failed\n", regaddr); + phydev_warn(phydev, "TR Register[0x%X] configuration failed\n", + regaddr); err: return phy_restore_page(phydev, save_page, ret); } @@ -137,7 +138,7 @@ static void lan88xx_config_TR_regs(struct phy_device *phydev) */ err = lan88xx_TR_reg_set(phydev, 0x0F82, 0x12B00A); if (err < 0) - pr_warn("Failed to Set Register[0x0F82]\n"); + phydev_warn(phydev, "Failed to Set Register[0x0F82]\n"); /* Get access to Channel b'10, Node b'1101, Register 0x06. * Write 24-bit value 0xD2C46F to register. Setting SSTrKf1000Slv, @@ -145,7 +146,7 @@ static void lan88xx_config_TR_regs(struct phy_device *phydev) */ err = lan88xx_TR_reg_set(phydev, 0x168C, 0xD2C46F); if (err < 0) - pr_warn("Failed to Set Register[0x168C]\n"); + phydev_warn(phydev, "Failed to Set Register[0x168C]\n"); /* Get access to Channel b'10, Node b'1111, Register 0x11. * Write 24-bit value 0x620 to register. Setting rem_upd_done_thresh @@ -153,7 +154,7 @@ static void lan88xx_config_TR_regs(struct phy_device *phydev) */ err = lan88xx_TR_reg_set(phydev, 0x17A2, 0x620); if (err < 0) - pr_warn("Failed to Set Register[0x17A2]\n"); + phydev_warn(phydev, "Failed to Set Register[0x17A2]\n"); /* Get access to Channel b'10, Node b'1101, Register 0x10. * Write 24-bit value 0xEEFFDD to register. Setting @@ -162,7 +163,7 @@ static void lan88xx_config_TR_regs(struct phy_device *phydev) */ err = lan88xx_TR_reg_set(phydev, 0x16A0, 0xEEFFDD); if (err < 0) - pr_warn("Failed to Set Register[0x16A0]\n"); + phydev_warn(phydev, "Failed to Set Register[0x16A0]\n"); /* Get access to Channel b'10, Node b'1101, Register 0x13. * Write 24-bit value 0x071448 to register. Setting @@ -170,7 +171,7 @@ static void lan88xx_config_TR_regs(struct phy_device *phydev) */ err = lan88xx_TR_reg_set(phydev, 0x16A6, 0x071448); if (err < 0) - pr_warn("Failed to Set Register[0x16A6]\n"); + phydev_warn(phydev, "Failed to Set Register[0x16A6]\n"); /* Get access to Channel b'10, Node b'1101, Register 0x12. * Write 24-bit value 0x13132F to register. Setting @@ -178,7 +179,7 @@ static void lan88xx_config_TR_regs(struct phy_device *phydev) */ err = lan88xx_TR_reg_set(phydev, 0x16A4, 0x13132F); if (err < 0) - pr_warn("Failed to Set Register[0x16A4]\n"); + phydev_warn(phydev, "Failed to Set Register[0x16A4]\n"); /* Get access to Channel b'10, Node b'1101, Register 0x14. * Write 24-bit value 0x0 to register. Setting eee_3level_delay, @@ -186,7 +187,7 @@ static void lan88xx_config_TR_regs(struct phy_device *phydev) */ err = lan88xx_TR_reg_set(phydev, 0x16A8, 0x0); if (err < 0) - pr_warn("Failed to Set Register[0x16A8]\n"); + phydev_warn(phydev, "Failed to Set Register[0x16A8]\n"); /* Get access to Channel b'01, Node b'1111, Register 0x34. * Write 24-bit value 0x91B06C to register. Setting @@ -195,7 +196,7 @@ static void lan88xx_config_TR_regs(struct phy_device *phydev) */ err = lan88xx_TR_reg_set(phydev, 0x0FE8, 0x91B06C); if (err < 0) - pr_warn("Failed to Set Register[0x0FE8]\n"); + phydev_warn(phydev, "Failed to Set Register[0x0FE8]\n"); /* Get access to Channel b'01, Node b'1111, Register 0x3E. * Write 24-bit value 0xC0A028 to register. Setting @@ -204,7 +205,7 @@ static void lan88xx_config_TR_regs(struct phy_device *phydev) */ err = lan88xx_TR_reg_set(phydev, 0x0FFC, 0xC0A028); if (err < 0) - pr_warn("Failed to Set Register[0x0FFC]\n"); + phydev_warn(phydev, "Failed to Set Register[0x0FFC]\n"); /* Get access to Channel b'01, Node b'1111, Register 0x35. * Write 24-bit value 0x041600 to register. Setting @@ -213,14 +214,14 @@ static void lan88xx_config_TR_regs(struct phy_device *phydev) */ err = lan88xx_TR_reg_set(phydev, 0x0FEA, 0x041600); if (err < 0) - pr_warn("Failed to Set Register[0x0FEA]\n"); + phydev_warn(phydev, "Failed to Set Register[0x0FEA]\n"); /* Get access to Channel b'10, Node b'1101, Register 0x03. * Write 24-bit value 0x000004 to register. Setting TrFreeze bits. */ err = lan88xx_TR_reg_set(phydev, 0x1686, 0x000004); if (err < 0) - pr_warn("Failed to Set Register[0x1686]\n"); + phydev_warn(phydev, "Failed to Set Register[0x1686]\n"); } static int lan88xx_probe(struct phy_device *phydev) diff --git a/include/linux/phy.h b/include/linux/phy.h index d24cc46748e2..0ab9f89773fd 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -968,6 +968,9 @@ static inline void phy_device_reset(struct phy_device *phydev, int value) #define phydev_err(_phydev, format, args...) \ dev_err(&_phydev->mdio.dev, format, ##args) +#define phydev_warn(_phydev, format, args...) \ + dev_warn(&_phydev->mdio.dev, format, ##args) + #define phydev_dbg(_phydev, format, args...) \ dev_dbg(&_phydev->mdio.dev, format, ##args) -- cgit v1.2.3 From c4fabb8b3c0d724eb93dabaf346b0dd8a8be7118 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 29 Sep 2018 23:04:11 +0200 Subject: net: phy: Add phydev_info() Add phydev_info() and make use of it within the phy drivers and core code. Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/phy/dp83640.c | 11 ++++++----- drivers/net/phy/phy_device.c | 4 ++-- include/linux/phy.h | 3 +++ 3 files changed, 11 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index 74cf356d8171..edd4d44a386d 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -687,9 +687,9 @@ static void recalibrate(struct dp83640_clock *clock) * read out and correct offsets */ val = ext_read(master, PAGE4, PTP_STS); - pr_info("master PTP_STS 0x%04hx\n", val); + phydev_info(master, "master PTP_STS 0x%04hx\n", val); val = ext_read(master, PAGE4, PTP_ESTS); - pr_info("master PTP_ESTS 0x%04hx\n", val); + phydev_info(master, "master PTP_ESTS 0x%04hx\n", val); event_ts.ns_lo = ext_read(master, PAGE4, PTP_EDATA); event_ts.ns_hi = ext_read(master, PAGE4, PTP_EDATA); event_ts.sec_lo = ext_read(master, PAGE4, PTP_EDATA); @@ -699,15 +699,16 @@ static void recalibrate(struct dp83640_clock *clock) list_for_each(this, &clock->phylist) { tmp = list_entry(this, struct dp83640_private, list); val = ext_read(tmp->phydev, PAGE4, PTP_STS); - pr_info("slave PTP_STS 0x%04hx\n", val); + phydev_info(tmp->phydev, "slave PTP_STS 0x%04hx\n", val); val = ext_read(tmp->phydev, PAGE4, PTP_ESTS); - pr_info("slave PTP_ESTS 0x%04hx\n", val); + phydev_info(tmp->phydev, "slave PTP_ESTS 0x%04hx\n", val); event_ts.ns_lo = ext_read(tmp->phydev, PAGE4, PTP_EDATA); event_ts.ns_hi = ext_read(tmp->phydev, PAGE4, PTP_EDATA); event_ts.sec_lo = ext_read(tmp->phydev, PAGE4, PTP_EDATA); event_ts.sec_hi = ext_read(tmp->phydev, PAGE4, PTP_EDATA); diff = now - (s64) phy2txts(&event_ts); - pr_info("slave offset %lld nanoseconds\n", diff); + phydev_info(tmp->phydev, "slave offset %lld nanoseconds\n", + diff); diff += ADJTIME_FIX; ts = ns_to_timespec64(diff); tdr_write(0, tmp->phydev, &ts, PTP_STEP_CLK); diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index ee676d75fe02..35102e17bbeb 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -920,13 +920,13 @@ void phy_attached_print(struct phy_device *phydev, const char *fmt, ...) if (!fmt) { - dev_info(&phydev->mdio.dev, ATTACHED_FMT "\n", + phydev_info(phydev, ATTACHED_FMT "\n", drv_name, phydev_name(phydev), irq_str); } else { va_list ap; - dev_info(&phydev->mdio.dev, ATTACHED_FMT, + phydev_info(phydev, ATTACHED_FMT, drv_name, phydev_name(phydev), irq_str); diff --git a/include/linux/phy.h b/include/linux/phy.h index 0ab9f89773fd..0f6e7bf5e9c5 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -968,6 +968,9 @@ static inline void phy_device_reset(struct phy_device *phydev, int value) #define phydev_err(_phydev, format, args...) \ dev_err(&_phydev->mdio.dev, format, ##args) +#define phydev_info(_phydev, format, args...) \ + dev_info(&_phydev->mdio.dev, format, ##args) + #define phydev_warn(_phydev, format, args...) \ dev_warn(&_phydev->mdio.dev, format, ##args) -- cgit v1.2.3 From edc7ccbbcf32b97c7d26cd556f364eb4f22c4285 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 29 Sep 2018 23:04:12 +0200 Subject: net: phy: Add helper to convert MII ADV register to a linkmode The phy_mii_ioctl can be used to write a value into the MII_ADVERTISE register in the PHY. Since this changes the state of the PHY, we need to make the same change to phydev->advertising. Add a helper which can convert the register value to a linkmode. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Reviewed-by: Maxime Chevallier Signed-off-by: David S. Miller --- include/linux/mii.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mii.h b/include/linux/mii.h index 567047ef0309..8c7da9473ad9 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -303,6 +303,37 @@ static inline u32 mii_lpa_to_ethtool_lpa_x(u32 lpa) return result | mii_adv_to_ethtool_adv_x(lpa); } +/** + * mii_adv_to_linkmode_adv_t + * @advertising:pointer to destination link mode. + * @adv: value of the MII_ADVERTISE register + * + * A small helper function that translates MII_ADVERTISE bits + * to linkmode advertisement settings. + */ +static inline void mii_adv_to_linkmode_adv_t(unsigned long *advertising, + u32 adv) +{ + linkmode_zero(advertising); + + if (adv & ADVERTISE_10HALF) + linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, + advertising); + if (adv & ADVERTISE_10FULL) + linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, + advertising); + if (adv & ADVERTISE_100HALF) + linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, + advertising); + if (adv & ADVERTISE_100FULL) + linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, + advertising); + if (adv & ADVERTISE_PAUSE_CAP) + linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, advertising); + if (adv & ADVERTISE_PAUSE_ASYM) + linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, advertising); +} + /** * mii_advertise_flowctrl - get flow control advertisement flags * @cap: Flow control capabilities (FLOW_CTRL_RX, FLOW_CTRL_TX or both) -- cgit v1.2.3 From 5f991f7bddc991ecc3c8a009ffd76fccff4661c7 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 29 Sep 2018 23:04:13 +0200 Subject: net: phy: Add helper for advertise to lcl value Add a helper to convert the local advertising to an LCL capabilities, which is then used to resolve pause flow control settings. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Reviewed-by: Maxime Chevallier Signed-off-by: David S. Miller --- drivers/net/dsa/mt7530.c | 6 +----- drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c | 5 +---- drivers/net/ethernet/freescale/fman/mac.c | 6 +----- drivers/net/ethernet/freescale/gianfar.c | 7 +------ .../net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 6 +----- drivers/net/ethernet/mediatek/mtk_eth_soc.c | 6 +----- drivers/net/ethernet/socionext/sni_ave.c | 5 +---- include/linux/mii.h | 19 +++++++++++++++++++ 8 files changed, 26 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 62e486652e62..a5de9bffe5be 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -658,11 +658,7 @@ static void mt7530_adjust_link(struct dsa_switch *ds, int port, if (phydev->asym_pause) rmt_adv |= LPA_PAUSE_ASYM; - if (phydev->advertising & ADVERTISED_Pause) - lcl_adv |= ADVERTISE_PAUSE_CAP; - if (phydev->advertising & ADVERTISED_Asym_Pause) - lcl_adv |= ADVERTISE_PAUSE_ASYM; - + lcl_adv = ethtool_adv_to_lcl_adv_t(phydev->advertising); flowctrl = mii_resolve_flowctrl_fdx(lcl_adv, rmt_adv); if (flowctrl & FLOW_CTRL_TX) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c index 289129011b9f..a7e03e3ecc93 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c @@ -1495,10 +1495,7 @@ static void xgbe_phy_phydev_flowctrl(struct xgbe_prv_data *pdata) if (!phy_data->phydev) return; - if (phy_data->phydev->advertising & ADVERTISED_Pause) - lcl_adv |= ADVERTISE_PAUSE_CAP; - if (phy_data->phydev->advertising & ADVERTISED_Asym_Pause) - lcl_adv |= ADVERTISE_PAUSE_ASYM; + lcl_adv = ethtool_adv_to_lcl_adv_t(phy_data->phydev->advertising); if (phy_data->phydev->pause) { XGBE_SET_LP_ADV(lks, Pause); diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c index a847b9c3b31a..d79e4e009d63 100644 --- a/drivers/net/ethernet/freescale/fman/mac.c +++ b/drivers/net/ethernet/freescale/fman/mac.c @@ -393,11 +393,7 @@ void fman_get_pause_cfg(struct mac_device *mac_dev, bool *rx_pause, */ /* get local capabilities */ - lcl_adv = 0; - if (phy_dev->advertising & ADVERTISED_Pause) - lcl_adv |= ADVERTISE_PAUSE_CAP; - if (phy_dev->advertising & ADVERTISED_Asym_Pause) - lcl_adv |= ADVERTISE_PAUSE_ASYM; + lcl_adv = ethtool_adv_to_lcl_adv_t(phy_dev->advertising); /* get link partner capabilities */ rmt_adv = 0; diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index 0bd21a493016..3c8da1a18ba0 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -3656,12 +3656,7 @@ static u32 gfar_get_flowctrl_cfg(struct gfar_private *priv) if (phydev->asym_pause) rmt_adv |= LPA_PAUSE_ASYM; - lcl_adv = 0; - if (phydev->advertising & ADVERTISED_Pause) - lcl_adv |= ADVERTISE_PAUSE_CAP; - if (phydev->advertising & ADVERTISED_Asym_Pause) - lcl_adv |= ADVERTISE_PAUSE_ASYM; - + lcl_adv = ethtool_adv_to_lcl_adv_t(phydev->advertising); flowctrl = mii_resolve_flowctrl_fdx(lcl_adv, rmt_adv); if (flowctrl & FLOW_CTRL_TX) val |= MACCFG1_TX_FLOW; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 7c8b686b1ce1..c17ceeefa453 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -5006,11 +5006,7 @@ int hclge_cfg_flowctrl(struct hclge_dev *hdev) if (!phydev->link || !phydev->autoneg) return 0; - if (phydev->advertising & ADVERTISED_Pause) - local_advertising = ADVERTISE_PAUSE_CAP; - - if (phydev->advertising & ADVERTISED_Asym_Pause) - local_advertising |= ADVERTISE_PAUSE_ASYM; + local_advertising = ethtool_adv_to_lcl_adv_t(phydev->advertising); if (phydev->pause) remote_advertising = LPA_PAUSE_CAP; diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index cc1e9a96a43b..7dbfdac4067a 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -243,11 +243,7 @@ static void mtk_phy_link_adjust(struct net_device *dev) if (dev->phydev->asym_pause) rmt_adv |= LPA_PAUSE_ASYM; - if (dev->phydev->advertising & ADVERTISED_Pause) - lcl_adv |= ADVERTISE_PAUSE_CAP; - if (dev->phydev->advertising & ADVERTISED_Asym_Pause) - lcl_adv |= ADVERTISE_PAUSE_ASYM; - + lcl_adv = ethtool_adv_to_lcl_adv_t(dev->phydev->advertising); flowctrl = mii_resolve_flowctrl_fdx(lcl_adv, rmt_adv); if (flowctrl & FLOW_CTRL_TX) diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c index 2a156dcd4534..6732f5cbde08 100644 --- a/drivers/net/ethernet/socionext/sni_ave.c +++ b/drivers/net/ethernet/socionext/sni_ave.c @@ -1116,11 +1116,8 @@ static void ave_phy_adjust_link(struct net_device *ndev) rmt_adv |= LPA_PAUSE_CAP; if (phydev->asym_pause) rmt_adv |= LPA_PAUSE_ASYM; - if (phydev->advertising & ADVERTISED_Pause) - lcl_adv |= ADVERTISE_PAUSE_CAP; - if (phydev->advertising & ADVERTISED_Asym_Pause) - lcl_adv |= ADVERTISE_PAUSE_ASYM; + lcl_adv = ethtool_adv_to_lcl_adv_t(phydev->advertising); cap = mii_resolve_flowctrl_fdx(lcl_adv, rmt_adv); if (cap & FLOW_CTRL_TX) txcr |= AVE_TXCR_FLOCTR; diff --git a/include/linux/mii.h b/include/linux/mii.h index 8c7da9473ad9..9ed49c8261d0 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -334,6 +334,25 @@ static inline void mii_adv_to_linkmode_adv_t(unsigned long *advertising, linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, advertising); } +/** + * ethtool_adv_to_lcl_adv_t + * @advertising:pointer to ethtool advertising + * + * A small helper function that translates ethtool advertising to LVL + * pause capabilities. + */ +static inline u32 ethtool_adv_to_lcl_adv_t(u32 advertising) +{ + u32 lcl_adv = 0; + + if (advertising & ADVERTISED_Pause) + lcl_adv |= ADVERTISE_PAUSE_CAP; + if (advertising & ADVERTISED_Asym_Pause) + lcl_adv |= ADVERTISE_PAUSE_ASYM; + + return lcl_adv; +} + /** * mii_advertise_flowctrl - get flow control advertisement flags * @cap: Flow control capabilities (FLOW_CTRL_RX, FLOW_CTRL_TX or both) -- cgit v1.2.3 From f954a04ea18ebfcba1cd2756eaee59eb4978a20e Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 29 Sep 2018 23:04:14 +0200 Subject: net: phy: Add limkmode equivalents to some of the MII ethtool helpers Add helpers which take a linkmode rather than a u32 ethtool for advertising settings. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Reviewed-by: Maxime Chevallier Signed-off-by: David S. Miller --- include/linux/mii.h | 50 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 50 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mii.h b/include/linux/mii.h index 9ed49c8261d0..2da85b02e1c0 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -132,6 +132,34 @@ static inline u32 ethtool_adv_to_mii_adv_t(u32 ethadv) return result; } +/** + * linkmode_adv_to_mii_adv_t + * @advertising: the linkmode advertisement settings + * + * A small helper function that translates linkmode advertisement + * settings to phy autonegotiation advertisements for the + * MII_ADVERTISE register. + */ +static inline u32 linkmode_adv_to_mii_adv_t(unsigned long *advertising) +{ + u32 result = 0; + + if (linkmode_test_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, advertising)) + result |= ADVERTISE_10HALF; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, advertising)) + result |= ADVERTISE_10FULL; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, advertising)) + result |= ADVERTISE_100HALF; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, advertising)) + result |= ADVERTISE_100FULL; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, advertising)) + result |= ADVERTISE_PAUSE_CAP; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, advertising)) + result |= ADVERTISE_PAUSE_ASYM; + + return result; +} + /** * mii_adv_to_ethtool_adv_t * @adv: value of the MII_ADVERTISE register @@ -179,6 +207,28 @@ static inline u32 ethtool_adv_to_mii_ctrl1000_t(u32 ethadv) return result; } +/** + * linkmode_adv_to_mii_ctrl1000_t + * advertising: the linkmode advertisement settings + * + * A small helper function that translates linkmode advertisement + * settings to phy autonegotiation advertisements for the + * MII_CTRL1000 register when in 1000T mode. + */ +static inline u32 linkmode_adv_to_mii_ctrl1000_t(unsigned long *advertising) +{ + u32 result = 0; + + if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, + advertising)) + result |= ADVERTISE_1000HALF; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, + advertising)) + result |= ADVERTISE_1000FULL; + + return result; +} + /** * mii_ctrl1000_to_ethtool_adv_t * @adv: value of the MII_CTRL1000 register -- cgit v1.2.3 From 719655a149715f26fc4de904fe0aa83068bd5b9e Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 29 Sep 2018 23:04:16 +0200 Subject: net: phy: Replace phy driver features u32 with link_mode bitmap This is one step in allowing phylib to make use of link_mode bitmaps, instead of u32 for supported and advertised features. Convert the phy drivers to use bitmaps to indicates the features they support. Build bitmap equivalents of the u32 values at runtime, and have the drivers point to the appropriate bitmap. These bitmaps are shared, and we don't want a driver to modify them. So mark them __ro_after_init. Within phylib, the features bitmap is currently turned back into a u32. This will be removed once the whole of phylib, and the drivers are converted to use bitmaps. Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/pxa168_eth.c | 4 +- drivers/net/phy/aquantia.c | 12 +-- drivers/net/phy/bcm63xx.c | 9 +- drivers/net/phy/marvell.c | 2 +- drivers/net/phy/marvell10g.c | 11 +- drivers/net/phy/microchip_t1.c | 2 +- drivers/net/phy/phy_device.c | 164 ++++++++++++++++++++++++++++-- include/linux/linkmode.h | 9 ++ include/linux/phy.h | 24 +++-- 9 files changed, 198 insertions(+), 39 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c index ff2fea0f8b75..0bd4351b2a49 100644 --- a/drivers/net/ethernet/marvell/pxa168_eth.c +++ b/drivers/net/ethernet/marvell/pxa168_eth.c @@ -988,8 +988,8 @@ static int pxa168_init_phy(struct net_device *dev) cmd.base.phy_address = pep->phy_addr; cmd.base.speed = pep->phy_speed; cmd.base.duplex = pep->phy_duplex; - ethtool_convert_legacy_u32_to_link_mode(cmd.link_modes.advertising, - PHY_BASIC_FEATURES); + bitmap_copy(cmd.link_modes.advertising, PHY_BASIC_FEATURES, + __ETHTOOL_LINK_MODE_MASK_NBITS); cmd.base.autoneg = AUTONEG_ENABLE; if (cmd.base.speed != 0) diff --git a/drivers/net/phy/aquantia.c b/drivers/net/phy/aquantia.c index 319edc9c8ec7..632472cab3bb 100644 --- a/drivers/net/phy/aquantia.c +++ b/drivers/net/phy/aquantia.c @@ -115,7 +115,7 @@ static struct phy_driver aquantia_driver[] = { .phy_id = PHY_ID_AQ1202, .phy_id_mask = 0xfffffff0, .name = "Aquantia AQ1202", - .features = PHY_AQUANTIA_FEATURES, + .features = PHY_10GBIT_FULL_FEATURES, .flags = PHY_HAS_INTERRUPT, .aneg_done = genphy_c45_aneg_done, .config_aneg = aquantia_config_aneg, @@ -127,7 +127,7 @@ static struct phy_driver aquantia_driver[] = { .phy_id = PHY_ID_AQ2104, .phy_id_mask = 0xfffffff0, .name = "Aquantia AQ2104", - .features = PHY_AQUANTIA_FEATURES, + .features = PHY_10GBIT_FULL_FEATURES, .flags = PHY_HAS_INTERRUPT, .aneg_done = genphy_c45_aneg_done, .config_aneg = aquantia_config_aneg, @@ -139,7 +139,7 @@ static struct phy_driver aquantia_driver[] = { .phy_id = PHY_ID_AQR105, .phy_id_mask = 0xfffffff0, .name = "Aquantia AQR105", - .features = PHY_AQUANTIA_FEATURES, + .features = PHY_10GBIT_FULL_FEATURES, .flags = PHY_HAS_INTERRUPT, .aneg_done = genphy_c45_aneg_done, .config_aneg = aquantia_config_aneg, @@ -151,7 +151,7 @@ static struct phy_driver aquantia_driver[] = { .phy_id = PHY_ID_AQR106, .phy_id_mask = 0xfffffff0, .name = "Aquantia AQR106", - .features = PHY_AQUANTIA_FEATURES, + .features = PHY_10GBIT_FULL_FEATURES, .flags = PHY_HAS_INTERRUPT, .aneg_done = genphy_c45_aneg_done, .config_aneg = aquantia_config_aneg, @@ -163,7 +163,7 @@ static struct phy_driver aquantia_driver[] = { .phy_id = PHY_ID_AQR107, .phy_id_mask = 0xfffffff0, .name = "Aquantia AQR107", - .features = PHY_AQUANTIA_FEATURES, + .features = PHY_10GBIT_FULL_FEATURES, .flags = PHY_HAS_INTERRUPT, .aneg_done = genphy_c45_aneg_done, .config_aneg = aquantia_config_aneg, @@ -175,7 +175,7 @@ static struct phy_driver aquantia_driver[] = { .phy_id = PHY_ID_AQR405, .phy_id_mask = 0xfffffff0, .name = "Aquantia AQR405", - .features = PHY_AQUANTIA_FEATURES, + .features = PHY_10GBIT_FULL_FEATURES, .flags = PHY_HAS_INTERRUPT, .aneg_done = genphy_c45_aneg_done, .config_aneg = aquantia_config_aneg, diff --git a/drivers/net/phy/bcm63xx.c b/drivers/net/phy/bcm63xx.c index cf14613745c9..d95bffdec4c1 100644 --- a/drivers/net/phy/bcm63xx.c +++ b/drivers/net/phy/bcm63xx.c @@ -42,6 +42,9 @@ static int bcm63xx_config_init(struct phy_device *phydev) { int reg, err; + /* ASYM_PAUSE bit is marked RO in datasheet, so don't cheat */ + phydev->supported |= SUPPORTED_Pause; + reg = phy_read(phydev, MII_BCM63XX_IR); if (reg < 0) return reg; @@ -65,8 +68,7 @@ static struct phy_driver bcm63xx_driver[] = { .phy_id = 0x00406000, .phy_id_mask = 0xfffffc00, .name = "Broadcom BCM63XX (1)", - /* ASYM_PAUSE bit is marked RO in datasheet, so don't cheat */ - .features = (PHY_BASIC_FEATURES | SUPPORTED_Pause), + .features = PHY_BASIC_FEATURES, .flags = PHY_HAS_INTERRUPT | PHY_IS_INTERNAL, .config_init = bcm63xx_config_init, .ack_interrupt = bcm_phy_ack_intr, @@ -75,8 +77,7 @@ static struct phy_driver bcm63xx_driver[] = { /* same phy as above, with just a different OUI */ .phy_id = 0x002bdc00, .phy_id_mask = 0xfffffc00, - .name = "Broadcom BCM63XX (2)", - .features = (PHY_BASIC_FEATURES | SUPPORTED_Pause), + .features = PHY_BASIC_FEATURES, .flags = PHY_HAS_INTERRUPT | PHY_IS_INTERNAL, .config_init = bcm63xx_config_init, .ack_interrupt = bcm_phy_ack_intr, diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 8872a430d74a..cbec296107bd 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -2201,7 +2201,7 @@ static struct phy_driver marvell_drivers[] = { .phy_id = MARVELL_PHY_ID_88E1510, .phy_id_mask = MARVELL_PHY_ID_MASK, .name = "Marvell 88E1510", - .features = PHY_GBIT_FEATURES | SUPPORTED_FIBRE, + .features = PHY_GBIT_FIBRE_FEATURES, .flags = PHY_HAS_INTERRUPT, .probe = &m88e1510_probe, .config_init = &m88e1510_config_init, diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c index f214834819dd..1c9d039eec63 100644 --- a/drivers/net/phy/marvell10g.c +++ b/drivers/net/phy/marvell10g.c @@ -535,16 +535,7 @@ static struct phy_driver mv3310_drivers[] = { .phy_id = 0x002b09aa, .phy_id_mask = MARVELL_PHY_ID_MASK, .name = "mv88x3310", - .features = SUPPORTED_10baseT_Full | - SUPPORTED_10baseT_Half | - SUPPORTED_100baseT_Full | - SUPPORTED_100baseT_Half | - SUPPORTED_1000baseT_Full | - SUPPORTED_Autoneg | - SUPPORTED_TP | - SUPPORTED_FIBRE | - SUPPORTED_10000baseT_Full | - SUPPORTED_Backplane, + .features = PHY_10GBIT_FEATURES, .soft_reset = gen10g_no_soft_reset, .config_init = mv3310_config_init, .probe = mv3310_probe, diff --git a/drivers/net/phy/microchip_t1.c b/drivers/net/phy/microchip_t1.c index b1917dd1978a..c600a8509d60 100644 --- a/drivers/net/phy/microchip_t1.c +++ b/drivers/net/phy/microchip_t1.c @@ -46,7 +46,7 @@ static struct phy_driver microchip_t1_phy_driver[] = { .phy_id_mask = 0xfffffff0, .name = "Microchip LAN87xx T1", - .features = SUPPORTED_100baseT_Full, + .features = PHY_BASIC_T1_FEATURES, .flags = PHY_HAS_INTERRUPT, .config_init = genphy_config_init, diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 35102e17bbeb..f53ce65f45c5 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include #include @@ -42,6 +43,149 @@ MODULE_DESCRIPTION("PHY library"); MODULE_AUTHOR("Andy Fleming"); MODULE_LICENSE("GPL"); +__ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_features) __ro_after_init; +EXPORT_SYMBOL_GPL(phy_basic_features); + +__ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_t1_features) __ro_after_init; +EXPORT_SYMBOL_GPL(phy_basic_t1_features); + +__ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_features) __ro_after_init; +EXPORT_SYMBOL_GPL(phy_gbit_features); + +__ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_fibre_features) __ro_after_init; +EXPORT_SYMBOL_GPL(phy_gbit_fibre_features); + +__ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_all_ports_features) __ro_after_init; +EXPORT_SYMBOL_GPL(phy_gbit_all_ports_features); + +__ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_features) __ro_after_init; +EXPORT_SYMBOL_GPL(phy_10gbit_features); + +static const int phy_basic_ports_array[] = { + ETHTOOL_LINK_MODE_Autoneg_BIT, + ETHTOOL_LINK_MODE_TP_BIT, + ETHTOOL_LINK_MODE_MII_BIT, +}; + +static const int phy_fibre_port_array[] = { + ETHTOOL_LINK_MODE_FIBRE_BIT, +}; + +static const int phy_all_ports_features_array[] = { + ETHTOOL_LINK_MODE_Autoneg_BIT, + ETHTOOL_LINK_MODE_TP_BIT, + ETHTOOL_LINK_MODE_MII_BIT, + ETHTOOL_LINK_MODE_FIBRE_BIT, + ETHTOOL_LINK_MODE_AUI_BIT, + ETHTOOL_LINK_MODE_BNC_BIT, + ETHTOOL_LINK_MODE_Backplane_BIT, +}; + +static const int phy_10_100_features_array[] = { + ETHTOOL_LINK_MODE_10baseT_Half_BIT, + ETHTOOL_LINK_MODE_10baseT_Full_BIT, + ETHTOOL_LINK_MODE_100baseT_Half_BIT, + ETHTOOL_LINK_MODE_100baseT_Full_BIT, +}; + +static const int phy_basic_t1_features_array[] = { + ETHTOOL_LINK_MODE_TP_BIT, + ETHTOOL_LINK_MODE_100baseT_Full_BIT, +}; + +static const int phy_gbit_features_array[] = { + ETHTOOL_LINK_MODE_1000baseT_Half_BIT, + ETHTOOL_LINK_MODE_1000baseT_Full_BIT, +}; + +static const int phy_10gbit_features_array[] = { + ETHTOOL_LINK_MODE_10000baseT_Full_BIT, +}; + +__ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_init; +EXPORT_SYMBOL_GPL(phy_10gbit_full_features); + +static const int phy_10gbit_full_features_array[] = { + ETHTOOL_LINK_MODE_10baseT_Full_BIT, + ETHTOOL_LINK_MODE_100baseT_Full_BIT, + ETHTOOL_LINK_MODE_1000baseT_Full_BIT, + ETHTOOL_LINK_MODE_10000baseT_Full_BIT, +}; + +static void features_init(void) +{ + /* 10/100 half/full*/ + linkmode_set_bit_array(phy_basic_ports_array, + ARRAY_SIZE(phy_basic_ports_array), + phy_basic_features); + linkmode_set_bit_array(phy_10_100_features_array, + ARRAY_SIZE(phy_10_100_features_array), + phy_basic_features); + + /* 100 full, TP */ + linkmode_set_bit_array(phy_basic_t1_features_array, + ARRAY_SIZE(phy_basic_t1_features_array), + phy_basic_t1_features); + + /* 10/100 half/full + 1000 half/full */ + linkmode_set_bit_array(phy_basic_ports_array, + ARRAY_SIZE(phy_basic_ports_array), + phy_gbit_features); + linkmode_set_bit_array(phy_10_100_features_array, + ARRAY_SIZE(phy_10_100_features_array), + phy_gbit_features); + linkmode_set_bit_array(phy_gbit_features_array, + ARRAY_SIZE(phy_gbit_features_array), + phy_gbit_features); + + /* 10/100 half/full + 1000 half/full + fibre*/ + linkmode_set_bit_array(phy_basic_ports_array, + ARRAY_SIZE(phy_basic_ports_array), + phy_gbit_fibre_features); + linkmode_set_bit_array(phy_10_100_features_array, + ARRAY_SIZE(phy_10_100_features_array), + phy_gbit_fibre_features); + linkmode_set_bit_array(phy_gbit_features_array, + ARRAY_SIZE(phy_gbit_features_array), + phy_gbit_fibre_features); + linkmode_set_bit_array(phy_fibre_port_array, + ARRAY_SIZE(phy_fibre_port_array), + phy_gbit_fibre_features); + + /* 10/100 half/full + 1000 half/full + TP/MII/FIBRE/AUI/BNC/Backplane*/ + linkmode_set_bit_array(phy_all_ports_features_array, + ARRAY_SIZE(phy_all_ports_features_array), + phy_gbit_all_ports_features); + linkmode_set_bit_array(phy_10_100_features_array, + ARRAY_SIZE(phy_10_100_features_array), + phy_gbit_all_ports_features); + linkmode_set_bit_array(phy_gbit_features_array, + ARRAY_SIZE(phy_gbit_features_array), + phy_gbit_all_ports_features); + + /* 10/100 half/full + 1000 half/full + 10G full*/ + linkmode_set_bit_array(phy_all_ports_features_array, + ARRAY_SIZE(phy_all_ports_features_array), + phy_10gbit_features); + linkmode_set_bit_array(phy_10_100_features_array, + ARRAY_SIZE(phy_10_100_features_array), + phy_10gbit_features); + linkmode_set_bit_array(phy_gbit_features_array, + ARRAY_SIZE(phy_gbit_features_array), + phy_10gbit_features); + linkmode_set_bit_array(phy_10gbit_features_array, + ARRAY_SIZE(phy_10gbit_features_array), + phy_10gbit_features); + + /* 10/100/1000/10G full */ + linkmode_set_bit_array(phy_all_ports_features_array, + ARRAY_SIZE(phy_all_ports_features_array), + phy_10gbit_full_features); + linkmode_set_bit_array(phy_10gbit_full_features_array, + ARRAY_SIZE(phy_10gbit_full_features_array), + phy_10gbit_full_features); +} + void phy_device_free(struct phy_device *phydev) { put_device(&phydev->mdio.dev); @@ -1936,6 +2080,7 @@ static int phy_probe(struct device *dev) struct phy_device *phydev = to_phy_device(dev); struct device_driver *drv = phydev->mdio.dev.driver; struct phy_driver *phydrv = to_phy_driver(drv); + u32 features; int err = 0; phydev->drv = phydrv; @@ -1956,7 +2101,8 @@ static int phy_probe(struct device *dev) * a controller will attach, and may modify one * or both of these values */ - phydev->supported = phydrv->features; + ethtool_convert_link_mode_to_legacy_u32(&features, phydrv->features); + phydev->supported = features; of_set_phy_supported(phydev); phydev->advertising = phydev->supported; @@ -1976,10 +2122,14 @@ static int phy_probe(struct device *dev) * (e.g. hardware erratum) where the driver wants to set only one * of these bits. */ - if (phydrv->features & (SUPPORTED_Pause | SUPPORTED_Asym_Pause)) { + if (test_bit(ETHTOOL_LINK_MODE_Pause_BIT, phydrv->features) || + test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, phydrv->features)) { phydev->supported &= ~(SUPPORTED_Pause | SUPPORTED_Asym_Pause); - phydev->supported |= phydrv->features & - (SUPPORTED_Pause | SUPPORTED_Asym_Pause); + if (test_bit(ETHTOOL_LINK_MODE_Pause_BIT, phydrv->features)) + phydev->supported |= SUPPORTED_Pause; + if (test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, + phydrv->features)) + phydev->supported |= SUPPORTED_Asym_Pause; } else { phydev->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; } @@ -2092,9 +2242,7 @@ static struct phy_driver genphy_driver = { .name = "Generic PHY", .soft_reset = genphy_no_soft_reset, .config_init = genphy_config_init, - .features = PHY_GBIT_FEATURES | SUPPORTED_MII | - SUPPORTED_AUI | SUPPORTED_FIBRE | - SUPPORTED_BNC, + .features = PHY_GBIT_ALL_PORTS_FEATURES, .aneg_done = genphy_aneg_done, .suspend = genphy_suspend, .resume = genphy_resume, @@ -2109,6 +2257,8 @@ static int __init phy_init(void) if (rc) return rc; + features_init(); + rc = phy_driver_register(&genphy_10g_driver, THIS_MODULE); if (rc) goto err_10g; diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h index 014fb86c7114..22443d7fb5cd 100644 --- a/include/linux/linkmode.h +++ b/include/linux/linkmode.h @@ -43,6 +43,15 @@ static inline void linkmode_set_bit(int nr, volatile unsigned long *addr) __set_bit(nr, addr); } +static inline void linkmode_set_bit_array(const int *array, int array_size, + unsigned long *addr) +{ + int i; + + for (i = 0; i < array_size; i++) + linkmode_set_bit(array[i], addr); +} + static inline void linkmode_clear_bit(int nr, volatile unsigned long *addr) { __clear_bit(nr, addr); diff --git a/include/linux/phy.h b/include/linux/phy.h index 0f6e7bf5e9c5..dff51dd36e52 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -42,13 +42,21 @@ #define PHY_1000BT_FEATURES (SUPPORTED_1000baseT_Half | \ SUPPORTED_1000baseT_Full) -#define PHY_BASIC_FEATURES (PHY_10BT_FEATURES | \ - PHY_100BT_FEATURES | \ - PHY_DEFAULT_FEATURES) - -#define PHY_GBIT_FEATURES (PHY_BASIC_FEATURES | \ - PHY_1000BT_FEATURES) - +extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_features) __ro_after_init; +extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_t1_features) __ro_after_init; +extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_features) __ro_after_init; +extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_fibre_features) __ro_after_init; +extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_all_ports_features) __ro_after_init; +extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_features) __ro_after_init; +extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_init; + +#define PHY_BASIC_FEATURES ((unsigned long *)&phy_basic_features) +#define PHY_BASIC_T1_FEATURES ((unsigned long *)&phy_basic_t1_features) +#define PHY_GBIT_FEATURES ((unsigned long *)&phy_gbit_features) +#define PHY_GBIT_FIBRE_FEATURES ((unsigned long *)&phy_gbit_fibre_features) +#define PHY_GBIT_ALL_PORTS_FEATURES ((unsigned long *)&phy_gbit_all_ports_features) +#define PHY_10GBIT_FEATURES ((unsigned long *)&phy_10gbit_features) +#define PHY_10GBIT_FULL_FEATURES ((unsigned long *)&phy_10gbit_full_features) /* * Set phydev->irq to PHY_POLL if interrupts are not supported, @@ -510,7 +518,7 @@ struct phy_driver { u32 phy_id; char *name; u32 phy_id_mask; - u32 features; + const unsigned long * const features; u32 flags; const void *driver_data; -- cgit v1.2.3 From 9f2959b6b52d43326b2f6a0e0d7ffe6f4fc3b5ca Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Fri, 28 Sep 2018 08:51:09 +0200 Subject: net: phy: improve handling delayed work Using mod_delayed_work() allows to simplify handling delayed work and removes the need for the sync parameter in phy_trigger_machine(). Also introduce a helper phy_queue_state_machine() to encapsulate the low-level delayed work calls. No functional change intended. Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- drivers/net/phy/phy.c | 29 +++++++++++++++-------------- include/linux/phy.h | 2 +- 2 files changed, 16 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index a1f8e4816f72..14509a8903c6 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -537,7 +537,7 @@ out_unlock: mutex_unlock(&phydev->lock); if (trigger) - phy_trigger_machine(phydev, sync); + phy_trigger_machine(phydev); return err; } @@ -635,6 +635,13 @@ int phy_speed_up(struct phy_device *phydev) } EXPORT_SYMBOL_GPL(phy_speed_up); +static void phy_queue_state_machine(struct phy_device *phydev, + unsigned int secs) +{ + mod_delayed_work(system_power_efficient_wq, &phydev->state_queue, + secs * HZ); +} + /** * phy_start_machine - start PHY state machine tracking * @phydev: the phy_device struct @@ -647,7 +654,7 @@ EXPORT_SYMBOL_GPL(phy_speed_up); */ void phy_start_machine(struct phy_device *phydev) { - queue_delayed_work(system_power_efficient_wq, &phydev->state_queue, HZ); + phy_queue_state_machine(phydev, 1); } EXPORT_SYMBOL_GPL(phy_start_machine); @@ -655,19 +662,14 @@ EXPORT_SYMBOL_GPL(phy_start_machine); * phy_trigger_machine - trigger the state machine to run * * @phydev: the phy_device struct - * @sync: indicate whether we should wait for the workqueue cancelation * * Description: There has been a change in state which requires that the * state machine runs. */ -void phy_trigger_machine(struct phy_device *phydev, bool sync) +void phy_trigger_machine(struct phy_device *phydev) { - if (sync) - cancel_delayed_work_sync(&phydev->state_queue); - else - cancel_delayed_work(&phydev->state_queue); - queue_delayed_work(system_power_efficient_wq, &phydev->state_queue, 0); + phy_queue_state_machine(phydev, 0); } /** @@ -703,7 +705,7 @@ static void phy_error(struct phy_device *phydev) phydev->state = PHY_HALTED; mutex_unlock(&phydev->lock); - phy_trigger_machine(phydev, false); + phy_trigger_machine(phydev); } /** @@ -745,7 +747,7 @@ static irqreturn_t phy_change(struct phy_device *phydev) mutex_unlock(&phydev->lock); /* reschedule state queue work to run as soon as possible */ - phy_trigger_machine(phydev, true); + phy_trigger_machine(phydev); if (phy_interrupt_is_valid(phydev) && phy_clear_interrupt(phydev)) goto phy_err; @@ -911,7 +913,7 @@ void phy_start(struct phy_device *phydev) } mutex_unlock(&phydev->lock); - phy_trigger_machine(phydev, true); + phy_trigger_machine(phydev); } EXPORT_SYMBOL(phy_start); @@ -1130,8 +1132,7 @@ void phy_state_machine(struct work_struct *work) * called from phy_disconnect() synchronously. */ if (phy_polling_mode(phydev) && old_state != PHY_HALTED) - queue_delayed_work(system_power_efficient_wq, &phydev->state_queue, - PHY_STATE_TIME * HZ); + phy_queue_state_machine(phydev, PHY_STATE_TIME); } /** diff --git a/include/linux/phy.h b/include/linux/phy.h index dff51dd36e52..3ea87f774a76 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1054,7 +1054,7 @@ void phy_change_work(struct work_struct *work); void phy_mac_interrupt(struct phy_device *phydev); void phy_start_machine(struct phy_device *phydev); void phy_stop_machine(struct phy_device *phydev); -void phy_trigger_machine(struct phy_device *phydev, bool sync); +void phy_trigger_machine(struct phy_device *phydev); int phy_ethtool_sset(struct phy_device *phydev, struct ethtool_cmd *cmd); void phy_ethtool_ksettings_get(struct phy_device *phydev, struct ethtool_link_ksettings *cmd); -- cgit v1.2.3 From 11e37d357f6ba7a9af850a872396082cc0a0001f Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 27 Jul 2018 13:38:54 +0100 Subject: irqchip/gic-v3-its: Move pending table allocation to init time Pending tables for the redistributors are currently allocated one at a time as each CPU boots. This is causing some grief for Linux/RT (allocation from within a CPU hotplug notifier is frown upon). Let's move this allocation to take place at init time, when we only have a single CPU. It means we're allocating memory for CPUs that are not online yet, but most system will boot all of their CPUs anyway, so that's not completely wasted. Tested-by: Jeremy Linton Tested-by: Bhupesh Sharma Tested-by: Lei Zhang Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-gic-v3-its.c | 80 +++++++++++++++++++++++++------------- include/linux/irqchip/arm-gic-v3.h | 1 + 2 files changed, 53 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index cb59a4d513c9..02196682821b 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -173,6 +173,7 @@ static DEFINE_RAW_SPINLOCK(vmovp_lock); static DEFINE_IDA(its_vpeid_ida); #define gic_data_rdist() (raw_cpu_ptr(gic_rdists->rdist)) +#define gic_data_rdist_cpu(cpu) (per_cpu_ptr(gic_rdists->rdist, cpu)) #define gic_data_rdist_rd_base() (gic_data_rdist()->rd_base) #define gic_data_rdist_vlpi_base() (gic_data_rdist_rd_base() + SZ_128K) @@ -1625,7 +1626,7 @@ static void its_free_prop_table(struct page *prop_page) get_order(LPI_PROPBASE_SZ)); } -static int __init its_alloc_lpi_tables(void) +static int __init its_setup_lpi_prop_table(void) { phys_addr_t paddr; @@ -1944,30 +1945,47 @@ static void its_free_pending_table(struct page *pt) free_pages((unsigned long)page_address(pt), get_order(LPI_PENDBASE_SZ)); } -static void its_cpu_init_lpis(void) +static int __init allocate_lpi_tables(void) { - void __iomem *rbase = gic_data_rdist_rd_base(); - struct page *pend_page; - u64 val, tmp; + int err, cpu; - /* If we didn't allocate the pending table yet, do it now */ - pend_page = gic_data_rdist()->pend_page; - if (!pend_page) { - phys_addr_t paddr; + err = its_setup_lpi_prop_table(); + if (err) + return err; + + /* + * We allocate all the pending tables anyway, as we may have a + * mix of RDs that have had LPIs enabled, and some that + * don't. We'll free the unused ones as each CPU comes online. + */ + for_each_possible_cpu(cpu) { + struct page *pend_page; pend_page = its_allocate_pending_table(GFP_NOWAIT); if (!pend_page) { - pr_err("Failed to allocate PENDBASE for CPU%d\n", - smp_processor_id()); - return; + pr_err("Failed to allocate PENDBASE for CPU%d\n", cpu); + return -ENOMEM; } - paddr = page_to_phys(pend_page); - pr_info("CPU%d: using LPI pending table @%pa\n", - smp_processor_id(), &paddr); - gic_data_rdist()->pend_page = pend_page; + gic_data_rdist_cpu(cpu)->pend_page = pend_page; } + return 0; +} + +static void its_cpu_init_lpis(void) +{ + void __iomem *rbase = gic_data_rdist_rd_base(); + struct page *pend_page; + phys_addr_t paddr; + u64 val, tmp; + + if (gic_data_rdist()->lpi_enabled) + return; + + pend_page = gic_data_rdist()->pend_page; + paddr = page_to_phys(pend_page); + /* set PROPBASE */ val = (page_to_phys(gic_rdists->prop_page) | GICR_PROPBASER_InnerShareable | @@ -2019,6 +2037,10 @@ static void its_cpu_init_lpis(void) /* Make sure the GIC has seen the above */ dsb(sy); + gic_data_rdist()->lpi_enabled = true; + pr_info("GICv3: CPU%d: using LPI pending table @%pa\n", + smp_processor_id(), + &paddr); } static void its_cpu_init_collection(struct its_node *its) @@ -3497,16 +3519,6 @@ static int redist_disable_lpis(void) u64 timeout = USEC_PER_SEC; u64 val; - /* - * If coming via a CPU hotplug event, we don't need to disable - * LPIs before trying to re-enable them. They are already - * configured and all is well in the world. Detect this case - * by checking the allocation of the pending table for the - * current CPU. - */ - if (gic_data_rdist()->pend_page) - return 0; - if (!gic_rdists_supports_plpis()) { pr_info("CPU%d: LPIs not supported\n", smp_processor_id()); return -ENXIO; @@ -3516,7 +3528,18 @@ static int redist_disable_lpis(void) if (!(val & GICR_CTLR_ENABLE_LPIS)) return 0; - pr_warn("CPU%d: Booted with LPIs enabled, memory probably corrupted\n", + /* + * If coming via a CPU hotplug event, we don't need to disable + * LPIs before trying to re-enable them. They are already + * configured and all is well in the world. + */ + if (gic_data_rdist()->lpi_enabled) + return 0; + + /* + * From that point on, we only try to do some damage control. + */ + pr_warn("GICv3: CPU%d: Booted with LPIs enabled, memory probably corrupted\n", smp_processor_id()); add_taint(TAINT_CRAP, LOCKDEP_STILL_OK); @@ -3772,7 +3795,8 @@ int __init its_init(struct fwnode_handle *handle, struct rdists *rdists, } gic_rdists = rdists; - err = its_alloc_lpi_tables(); + + err = allocate_lpi_tables(); if (err) return err; diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 8bdbb5f29494..266093e845bb 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -585,6 +585,7 @@ struct rdists { void __iomem *rd_base; struct page *pend_page; phys_addr_t phys_base; + bool lpi_enabled; } __percpu *rdist; struct page *prop_page; u64 flags; -- cgit v1.2.3 From e1a2e2010ba9d3c765b2e37a7ae8b332564716f1 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 27 Jul 2018 14:36:00 +0100 Subject: irqchip/gic-v3-its: Keep track of property table's PA and VA We're currently only tracking the page allocated to contain the property table by its struct page. In the future, it is going to be convenient to track both PA and VA for that page instead. Let's do that. Tested-by: Jeremy Linton Tested-by: Bhupesh Sharma Tested-by: Lei Zhang Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-gic-v3-its.c | 23 +++++++++++++---------- include/linux/irqchip/arm-gic-v3.h | 3 ++- 2 files changed, 15 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 02196682821b..9f26445eee4a 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -1029,7 +1029,7 @@ static inline u32 its_get_event_id(struct irq_data *d) static void lpi_write_config(struct irq_data *d, u8 clr, u8 set) { irq_hw_number_t hwirq; - struct page *prop_page; + void *va; u8 *cfg; if (irqd_is_forwarded_to_vcpu(d)) { @@ -1037,7 +1037,7 @@ static void lpi_write_config(struct irq_data *d, u8 clr, u8 set) u32 event = its_get_event_id(d); struct its_vlpi_map *map; - prop_page = its_dev->event_map.vm->vprop_page; + va = page_address(its_dev->event_map.vm->vprop_page); map = &its_dev->event_map.vlpi_maps[event]; hwirq = map->vintid; @@ -1045,11 +1045,11 @@ static void lpi_write_config(struct irq_data *d, u8 clr, u8 set) map->properties &= ~clr; map->properties |= set | LPI_PROP_GROUP1; } else { - prop_page = gic_rdists->prop_page; + va = gic_rdists->prop_table_va; hwirq = d->hwirq; } - cfg = page_address(prop_page) + hwirq - 8192; + cfg = va + hwirq - 8192; *cfg &= ~clr; *cfg |= set | LPI_PROP_GROUP1; @@ -1628,18 +1628,21 @@ static void its_free_prop_table(struct page *prop_page) static int __init its_setup_lpi_prop_table(void) { - phys_addr_t paddr; + struct page *page; lpi_id_bits = min_t(u32, GICD_TYPER_ID_BITS(gic_rdists->gicd_typer), ITS_MAX_LPI_NRBITS); - gic_rdists->prop_page = its_allocate_prop_table(GFP_NOWAIT); - if (!gic_rdists->prop_page) { + page = its_allocate_prop_table(GFP_NOWAIT); + if (!page) { pr_err("Failed to allocate PROPBASE\n"); return -ENOMEM; } - paddr = page_to_phys(gic_rdists->prop_page); - pr_info("GIC: using LPI property table @%pa\n", &paddr); + gic_rdists->prop_table_pa = page_to_phys(page); + gic_rdists->prop_table_va = page_address(page); + + pr_info("GICv3: using LPI property table @%pa\n", + &gic_rdists->prop_table_pa); return its_lpi_init(lpi_id_bits); } @@ -1987,7 +1990,7 @@ static void its_cpu_init_lpis(void) paddr = page_to_phys(pend_page); /* set PROPBASE */ - val = (page_to_phys(gic_rdists->prop_page) | + val = (gic_rdists->prop_table_pa | GICR_PROPBASER_InnerShareable | GICR_PROPBASER_RaWaWb | ((LPI_NRBITS - 1) & GICR_PROPBASER_IDBITS_MASK)); diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 266093e845bb..c2a7b863fc2e 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -587,7 +587,8 @@ struct rdists { phys_addr_t phys_base; bool lpi_enabled; } __percpu *rdist; - struct page *prop_page; + phys_addr_t prop_table_pa; + void *prop_table_va; u64 flags; u32 gicd_typer; bool has_vlpis; -- cgit v1.2.3 From 1f83515bebc236d2acda59976a8e852f1a6d50b7 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 1 Oct 2018 16:13:45 +0200 Subject: genirq/msi: Allow creation of a tree-based irqdomain for platform-msi platform_msi_create_device_domain() always creates a revmap-based irqdomain, which has the drawback of requiring the number of MSIs that can be allocated ahead of time. This is not always possible, and we sometimes need to use a tree-based irqdomain instead. Add a new platform_msi_create_device_tree_domain() helper to that effect. Reported-by: Miquel Raynal Signed-off-by: Marc Zyngier Signed-off-by: Miquel Raynal Signed-off-by: Marc Zyngier --- drivers/base/platform-msi.c | 14 ++++++++------ include/linux/msi.h | 17 ++++++++++++----- 2 files changed, 20 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/platform-msi.c b/drivers/base/platform-msi.c index 60d6cc618f1c..f39a920496fb 100644 --- a/drivers/base/platform-msi.c +++ b/drivers/base/platform-msi.c @@ -321,11 +321,12 @@ void *platform_msi_get_host_data(struct irq_domain *domain) * Returns an irqdomain for @nvec interrupts */ struct irq_domain * -platform_msi_create_device_domain(struct device *dev, - unsigned int nvec, - irq_write_msi_msg_t write_msi_msg, - const struct irq_domain_ops *ops, - void *host_data) +__platform_msi_create_device_domain(struct device *dev, + unsigned int nvec, + bool is_tree, + irq_write_msi_msg_t write_msi_msg, + const struct irq_domain_ops *ops, + void *host_data) { struct platform_msi_priv_data *data; struct irq_domain *domain; @@ -336,7 +337,8 @@ platform_msi_create_device_domain(struct device *dev, return NULL; data->host_data = host_data; - domain = irq_domain_create_hierarchy(dev->msi_domain, 0, nvec, + domain = irq_domain_create_hierarchy(dev->msi_domain, 0, + is_tree ? 0 : nvec, dev->fwnode, ops, data); if (!domain) goto free_priv; diff --git a/include/linux/msi.h b/include/linux/msi.h index 5839d8062dfc..0e9c50052ff3 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -317,11 +317,18 @@ int msi_domain_prepare_irqs(struct irq_domain *domain, struct device *dev, int msi_domain_populate_irqs(struct irq_domain *domain, struct device *dev, int virq, int nvec, msi_alloc_info_t *args); struct irq_domain * -platform_msi_create_device_domain(struct device *dev, - unsigned int nvec, - irq_write_msi_msg_t write_msi_msg, - const struct irq_domain_ops *ops, - void *host_data); +__platform_msi_create_device_domain(struct device *dev, + unsigned int nvec, + bool is_tree, + irq_write_msi_msg_t write_msi_msg, + const struct irq_domain_ops *ops, + void *host_data); + +#define platform_msi_create_device_domain(dev, nvec, write, ops, data) \ + __platform_msi_create_device_domain(dev, nvec, false, write, ops, data) +#define platform_msi_create_device_tree_domain(dev, nvec, write, ops, data) \ + __platform_msi_create_device_domain(dev, nvec, true, write, ops, data) + int platform_msi_domain_alloc(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs); void platform_msi_domain_free(struct irq_domain *domain, unsigned int virq, -- cgit v1.2.3 From 61ce8d8d8a8168a714de80fc31b3d6ac160fc5b0 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Mon, 1 Oct 2018 16:13:51 +0200 Subject: irqchip/irq-mvebu-sei: Add new driver for Marvell SEI This is a cascaded interrupt controller in the AP806 GIC that collapses SEIs (System Error Interrupt) coming from the AP and the CPs (through the ICU). The SEI handles up to 64 interrupts. The first 21 interrupts are wired from the AP. The next 43 interrupts are from the CPs and are triggered through MSI messages. To handle this complexity, the driver has to declare to the upper layer: one IRQ domain for the wired interrupts, one IRQ domain for the MSIs; and acts as a MSI controller ('parent') by declaring an MSI domain. Suggested-by: Haim Boot Suggested-by: Marc Zyngier Signed-off-by: Miquel Raynal Signed-off-by: Marc Zyngier --- drivers/irqchip/Kconfig | 3 + drivers/irqchip/Makefile | 1 + drivers/irqchip/irq-mvebu-sei.c | 507 ++++++++++++++++++++++++++++++++++++++++ include/linux/irqdomain.h | 1 + 4 files changed, 512 insertions(+) create mode 100644 drivers/irqchip/irq-mvebu-sei.c (limited to 'include/linux') diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index 383e7b70221d..96451b581452 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -310,6 +310,9 @@ config MVEBU_ODMI config MVEBU_PIC bool +config MVEBU_SEI + bool + config LS_SCFG_MSI def_bool y if SOC_LS1021A || ARCH_LAYERSCAPE depends on PCI && PCI_MSI diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile index fbd1ec8070ef..b822199445ff 100644 --- a/drivers/irqchip/Makefile +++ b/drivers/irqchip/Makefile @@ -76,6 +76,7 @@ obj-$(CONFIG_MVEBU_GICP) += irq-mvebu-gicp.o obj-$(CONFIG_MVEBU_ICU) += irq-mvebu-icu.o obj-$(CONFIG_MVEBU_ODMI) += irq-mvebu-odmi.o obj-$(CONFIG_MVEBU_PIC) += irq-mvebu-pic.o +obj-$(CONFIG_MVEBU_SEI) += irq-mvebu-sei.o obj-$(CONFIG_LS_SCFG_MSI) += irq-ls-scfg-msi.o obj-$(CONFIG_EZNPS_GIC) += irq-eznps.o obj-$(CONFIG_ARCH_ASPEED) += irq-aspeed-vic.o irq-aspeed-i2c-ic.o diff --git a/drivers/irqchip/irq-mvebu-sei.c b/drivers/irqchip/irq-mvebu-sei.c new file mode 100644 index 000000000000..566d69a2edbc --- /dev/null +++ b/drivers/irqchip/irq-mvebu-sei.c @@ -0,0 +1,507 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define pr_fmt(fmt) "mvebu-sei: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* Cause register */ +#define GICP_SECR(idx) (0x0 + ((idx) * 0x4)) +/* Mask register */ +#define GICP_SEMR(idx) (0x20 + ((idx) * 0x4)) +#define GICP_SET_SEI_OFFSET 0x30 + +#define SEI_IRQ_COUNT_PER_REG 32 +#define SEI_IRQ_REG_COUNT 2 +#define SEI_IRQ_COUNT (SEI_IRQ_COUNT_PER_REG * SEI_IRQ_REG_COUNT) +#define SEI_IRQ_REG_IDX(irq_id) ((irq_id) / SEI_IRQ_COUNT_PER_REG) +#define SEI_IRQ_REG_BIT(irq_id) ((irq_id) % SEI_IRQ_COUNT_PER_REG) + +struct mvebu_sei_interrupt_range { + u32 first; + u32 size; +}; + +struct mvebu_sei_caps { + struct mvebu_sei_interrupt_range ap_range; + struct mvebu_sei_interrupt_range cp_range; +}; + +struct mvebu_sei { + struct device *dev; + void __iomem *base; + struct resource *res; + struct irq_domain *sei_domain; + struct irq_domain *ap_domain; + struct irq_domain *cp_domain; + const struct mvebu_sei_caps *caps; + + /* Lock on MSI allocations/releases */ + struct mutex cp_msi_lock; + DECLARE_BITMAP(cp_msi_bitmap, SEI_IRQ_COUNT); + + /* Lock on IRQ masking register */ + raw_spinlock_t mask_lock; +}; + +static void mvebu_sei_ack_irq(struct irq_data *d) +{ + struct mvebu_sei *sei = irq_data_get_irq_chip_data(d); + u32 reg_idx = SEI_IRQ_REG_IDX(d->hwirq); + + writel_relaxed(BIT(SEI_IRQ_REG_BIT(d->hwirq)), + sei->base + GICP_SECR(reg_idx)); +} + +static void mvebu_sei_mask_irq(struct irq_data *d) +{ + struct mvebu_sei *sei = irq_data_get_irq_chip_data(d); + u32 reg, reg_idx = SEI_IRQ_REG_IDX(d->hwirq); + unsigned long flags; + + /* 1 disables the interrupt */ + raw_spin_lock_irqsave(&sei->mask_lock, flags); + reg = readl_relaxed(sei->base + GICP_SEMR(reg_idx)); + reg |= BIT(SEI_IRQ_REG_BIT(d->hwirq)); + writel_relaxed(reg, sei->base + GICP_SEMR(reg_idx)); + raw_spin_unlock_irqrestore(&sei->mask_lock, flags); +} + +static void mvebu_sei_unmask_irq(struct irq_data *d) +{ + struct mvebu_sei *sei = irq_data_get_irq_chip_data(d); + u32 reg, reg_idx = SEI_IRQ_REG_IDX(d->hwirq); + unsigned long flags; + + /* 0 enables the interrupt */ + raw_spin_lock_irqsave(&sei->mask_lock, flags); + reg = readl_relaxed(sei->base + GICP_SEMR(reg_idx)); + reg &= ~BIT(SEI_IRQ_REG_BIT(d->hwirq)); + writel_relaxed(reg, sei->base + GICP_SEMR(reg_idx)); + raw_spin_unlock_irqrestore(&sei->mask_lock, flags); +} + +static int mvebu_sei_set_affinity(struct irq_data *d, + const struct cpumask *mask_val, + bool force) +{ + return -EINVAL; +} + +static int mvebu_sei_set_irqchip_state(struct irq_data *d, + enum irqchip_irq_state which, + bool state) +{ + /* We can only clear the pending state by acking the interrupt */ + if (which != IRQCHIP_STATE_PENDING || state) + return -EINVAL; + + mvebu_sei_ack_irq(d); + return 0; +} + +static struct irq_chip mvebu_sei_irq_chip = { + .name = "SEI", + .irq_ack = mvebu_sei_ack_irq, + .irq_mask = mvebu_sei_mask_irq, + .irq_unmask = mvebu_sei_unmask_irq, + .irq_set_affinity = mvebu_sei_set_affinity, + .irq_set_irqchip_state = mvebu_sei_set_irqchip_state, +}; + +static int mvebu_sei_ap_set_type(struct irq_data *data, unsigned int type) +{ + if ((type & IRQ_TYPE_SENSE_MASK) != IRQ_TYPE_LEVEL_HIGH) + return -EINVAL; + + return 0; +} + +static struct irq_chip mvebu_sei_ap_irq_chip = { + .name = "AP SEI", + .irq_ack = irq_chip_ack_parent, + .irq_mask = irq_chip_mask_parent, + .irq_unmask = irq_chip_unmask_parent, + .irq_set_affinity = irq_chip_set_affinity_parent, + .irq_set_type = mvebu_sei_ap_set_type, +}; + +static void mvebu_sei_cp_compose_msi_msg(struct irq_data *data, + struct msi_msg *msg) +{ + struct mvebu_sei *sei = data->chip_data; + phys_addr_t set = sei->res->start + GICP_SET_SEI_OFFSET; + + msg->data = data->hwirq + sei->caps->cp_range.first; + msg->address_lo = lower_32_bits(set); + msg->address_hi = upper_32_bits(set); +} + +static int mvebu_sei_cp_set_type(struct irq_data *data, unsigned int type) +{ + if ((type & IRQ_TYPE_SENSE_MASK) != IRQ_TYPE_EDGE_RISING) + return -EINVAL; + + return 0; +} + +static struct irq_chip mvebu_sei_cp_irq_chip = { + .name = "CP SEI", + .irq_ack = irq_chip_ack_parent, + .irq_mask = irq_chip_mask_parent, + .irq_unmask = irq_chip_unmask_parent, + .irq_set_affinity = irq_chip_set_affinity_parent, + .irq_set_type = mvebu_sei_cp_set_type, + .irq_compose_msi_msg = mvebu_sei_cp_compose_msi_msg, +}; + +static int mvebu_sei_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *arg) +{ + struct mvebu_sei *sei = domain->host_data; + struct irq_fwspec *fwspec = arg; + + /* Not much to do, just setup the irqdata */ + irq_domain_set_hwirq_and_chip(domain, virq, fwspec->param[0], + &mvebu_sei_irq_chip, sei); + + return 0; +} + +static void mvebu_sei_domain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) +{ + int i; + + for (i = 0; i < nr_irqs; i++) { + struct irq_data *d = irq_domain_get_irq_data(domain, virq + i); + irq_set_handler(virq + i, NULL); + irq_domain_reset_irq_data(d); + } +} + +static const struct irq_domain_ops mvebu_sei_domain_ops = { + .alloc = mvebu_sei_domain_alloc, + .free = mvebu_sei_domain_free, +}; + +static int mvebu_sei_ap_translate(struct irq_domain *domain, + struct irq_fwspec *fwspec, + unsigned long *hwirq, + unsigned int *type) +{ + *hwirq = fwspec->param[0]; + *type = IRQ_TYPE_LEVEL_HIGH; + + return 0; +} + +static int mvebu_sei_ap_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *arg) +{ + struct mvebu_sei *sei = domain->host_data; + struct irq_fwspec fwspec; + unsigned long hwirq; + unsigned int type; + int err; + + mvebu_sei_ap_translate(domain, arg, &hwirq, &type); + + fwspec.fwnode = domain->parent->fwnode; + fwspec.param_count = 1; + fwspec.param[0] = hwirq + sei->caps->ap_range.first; + + err = irq_domain_alloc_irqs_parent(domain, virq, 1, &fwspec); + if (err) + return err; + + irq_domain_set_info(domain, virq, hwirq, + &mvebu_sei_ap_irq_chip, sei, + handle_level_irq, NULL, NULL); + irq_set_probe(virq); + + return 0; +} + +static const struct irq_domain_ops mvebu_sei_ap_domain_ops = { + .translate = mvebu_sei_ap_translate, + .alloc = mvebu_sei_ap_alloc, + .free = irq_domain_free_irqs_parent, +}; + +static void mvebu_sei_cp_release_irq(struct mvebu_sei *sei, unsigned long hwirq) +{ + mutex_lock(&sei->cp_msi_lock); + clear_bit(hwirq, sei->cp_msi_bitmap); + mutex_unlock(&sei->cp_msi_lock); +} + +static int mvebu_sei_cp_domain_alloc(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs, + void *args) +{ + struct mvebu_sei *sei = domain->host_data; + struct irq_fwspec fwspec; + unsigned long hwirq; + int ret; + + /* The software only supports single allocations for now */ + if (nr_irqs != 1) + return -ENOTSUPP; + + mutex_lock(&sei->cp_msi_lock); + hwirq = find_first_zero_bit(sei->cp_msi_bitmap, + sei->caps->cp_range.size); + if (hwirq < sei->caps->cp_range.size) + set_bit(hwirq, sei->cp_msi_bitmap); + mutex_unlock(&sei->cp_msi_lock); + + if (hwirq == sei->caps->cp_range.size) + return -ENOSPC; + + fwspec.fwnode = domain->parent->fwnode; + fwspec.param_count = 1; + fwspec.param[0] = hwirq + sei->caps->cp_range.first; + + ret = irq_domain_alloc_irqs_parent(domain, virq, 1, &fwspec); + if (ret) + goto free_irq; + + irq_domain_set_info(domain, virq, hwirq, + &mvebu_sei_cp_irq_chip, sei, + handle_edge_irq, NULL, NULL); + + return 0; + +free_irq: + mvebu_sei_cp_release_irq(sei, hwirq); + return ret; +} + +static void mvebu_sei_cp_domain_free(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs) +{ + struct mvebu_sei *sei = domain->host_data; + struct irq_data *d = irq_domain_get_irq_data(domain, virq); + + if (nr_irqs != 1 || d->hwirq >= sei->caps->cp_range.size) { + dev_err(sei->dev, "Invalid hwirq %lu\n", d->hwirq); + return; + } + + mvebu_sei_cp_release_irq(sei, d->hwirq); + irq_domain_free_irqs_parent(domain, virq, 1); +} + +static const struct irq_domain_ops mvebu_sei_cp_domain_ops = { + .alloc = mvebu_sei_cp_domain_alloc, + .free = mvebu_sei_cp_domain_free, +}; + +static struct irq_chip mvebu_sei_msi_irq_chip = { + .name = "SEI pMSI", + .irq_ack = irq_chip_ack_parent, + .irq_set_type = irq_chip_set_type_parent, +}; + +static struct msi_domain_ops mvebu_sei_msi_ops = { +}; + +static struct msi_domain_info mvebu_sei_msi_domain_info = { + .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS, + .ops = &mvebu_sei_msi_ops, + .chip = &mvebu_sei_msi_irq_chip, +}; + +static void mvebu_sei_handle_cascade_irq(struct irq_desc *desc) +{ + struct mvebu_sei *sei = irq_desc_get_handler_data(desc); + struct irq_chip *chip = irq_desc_get_chip(desc); + u32 idx; + + chained_irq_enter(chip, desc); + + for (idx = 0; idx < SEI_IRQ_REG_COUNT; idx++) { + unsigned long irqmap; + int bit; + + irqmap = readl_relaxed(sei->base + GICP_SECR(idx)); + for_each_set_bit(bit, &irqmap, SEI_IRQ_COUNT_PER_REG) { + unsigned long hwirq; + unsigned int virq; + + hwirq = idx * SEI_IRQ_COUNT_PER_REG + bit; + virq = irq_find_mapping(sei->sei_domain, hwirq); + if (likely(virq)) { + generic_handle_irq(virq); + continue; + } + + dev_warn(sei->dev, + "Spurious IRQ detected (hwirq %lu)\n", hwirq); + } + } + + chained_irq_exit(chip, desc); +} + +static void mvebu_sei_reset(struct mvebu_sei *sei) +{ + u32 reg_idx; + + /* Clear IRQ cause registers, mask all interrupts */ + for (reg_idx = 0; reg_idx < SEI_IRQ_REG_COUNT; reg_idx++) { + writel_relaxed(0xFFFFFFFF, sei->base + GICP_SECR(reg_idx)); + writel_relaxed(0xFFFFFFFF, sei->base + GICP_SEMR(reg_idx)); + } +} + +static int mvebu_sei_probe(struct platform_device *pdev) +{ + struct device_node *node = pdev->dev.of_node; + struct irq_domain *plat_domain; + struct mvebu_sei *sei; + u32 parent_irq; + int ret; + + sei = devm_kzalloc(&pdev->dev, sizeof(*sei), GFP_KERNEL); + if (!sei) + return -ENOMEM; + + sei->dev = &pdev->dev; + + mutex_init(&sei->cp_msi_lock); + raw_spin_lock_init(&sei->mask_lock); + + sei->res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + sei->base = devm_ioremap_resource(sei->dev, sei->res); + if (!sei->base) { + dev_err(sei->dev, "Failed to remap SEI resource\n"); + return -ENODEV; + } + + /* Retrieve the SEI capabilities with the interrupt ranges */ + sei->caps = of_device_get_match_data(&pdev->dev); + if (!sei->caps) { + dev_err(sei->dev, + "Could not retrieve controller capabilities\n"); + return -EINVAL; + } + + /* + * Reserve the single (top-level) parent SPI IRQ from which all the + * interrupts handled by this driver will be signaled. + */ + parent_irq = irq_of_parse_and_map(node, 0); + if (parent_irq <= 0) { + dev_err(sei->dev, "Failed to retrieve top-level SPI IRQ\n"); + return -ENODEV; + } + + /* Create the root SEI domain */ + sei->sei_domain = irq_domain_create_linear(of_node_to_fwnode(node), + (sei->caps->ap_range.size + + sei->caps->cp_range.size), + &mvebu_sei_domain_ops, + sei); + if (!sei->sei_domain) { + dev_err(sei->dev, "Failed to create SEI IRQ domain\n"); + ret = -ENOMEM; + goto dispose_irq; + } + + irq_domain_update_bus_token(sei->sei_domain, DOMAIN_BUS_NEXUS); + + /* Create the 'wired' domain */ + sei->ap_domain = irq_domain_create_hierarchy(sei->sei_domain, 0, + sei->caps->ap_range.size, + of_node_to_fwnode(node), + &mvebu_sei_ap_domain_ops, + sei); + if (!sei->ap_domain) { + dev_err(sei->dev, "Failed to create AP IRQ domain\n"); + ret = -ENOMEM; + goto remove_sei_domain; + } + + irq_domain_update_bus_token(sei->ap_domain, DOMAIN_BUS_WIRED); + + /* Create the 'MSI' domain */ + sei->cp_domain = irq_domain_create_hierarchy(sei->sei_domain, 0, + sei->caps->cp_range.size, + of_node_to_fwnode(node), + &mvebu_sei_cp_domain_ops, + sei); + if (!sei->cp_domain) { + pr_err("Failed to create CPs IRQ domain\n"); + ret = -ENOMEM; + goto remove_ap_domain; + } + + irq_domain_update_bus_token(sei->cp_domain, DOMAIN_BUS_GENERIC_MSI); + + plat_domain = platform_msi_create_irq_domain(of_node_to_fwnode(node), + &mvebu_sei_msi_domain_info, + sei->cp_domain); + if (!plat_domain) { + pr_err("Failed to create CPs MSI domain\n"); + ret = -ENOMEM; + goto remove_cp_domain; + } + + mvebu_sei_reset(sei); + + irq_set_chained_handler_and_data(parent_irq, + mvebu_sei_handle_cascade_irq, + sei); + + return 0; + +remove_cp_domain: + irq_domain_remove(sei->cp_domain); +remove_ap_domain: + irq_domain_remove(sei->ap_domain); +remove_sei_domain: + irq_domain_remove(sei->sei_domain); +dispose_irq: + irq_dispose_mapping(parent_irq); + + return ret; +} + +struct mvebu_sei_caps mvebu_sei_ap806_caps = { + .ap_range = { + .first = 0, + .size = 21, + }, + .cp_range = { + .first = 21, + .size = 43, + }, +}; + +static const struct of_device_id mvebu_sei_of_match[] = { + { + .compatible = "marvell,ap806-sei", + .data = &mvebu_sei_ap806_caps, + }, + {}, +}; + +static struct platform_driver mvebu_sei_driver = { + .probe = mvebu_sei_probe, + .driver = { + .name = "mvebu-sei", + .of_match_table = mvebu_sei_of_match, + }, +}; +builtin_platform_driver(mvebu_sei_driver); diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index dccfa65aee96..068aa46f0d55 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -75,6 +75,7 @@ struct irq_fwspec { enum irq_domain_bus_token { DOMAIN_BUS_ANY = 0, DOMAIN_BUS_WIRED, + DOMAIN_BUS_GENERIC_MSI, DOMAIN_BUS_PCI_MSI, DOMAIN_BUS_PLATFORM_MSI, DOMAIN_BUS_NEXUS, -- cgit v1.2.3 From 9524d6b265f9b2b9a61fceb2ee2ce1c2a83e39ca Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Tue, 11 Sep 2018 16:40:20 -0700 Subject: dmaengine: ep93xx: Return proper enum in ep93xx_dma_chan_direction Clang warns when implicitly converting from one enumerated type to another. Avoid this by using the equivalent value from the expected type. In file included from drivers/dma/ep93xx_dma.c:30: ./include/linux/platform_data/dma-ep93xx.h:88:10: warning: implicit conversion from enumeration type 'enum dma_data_direction' to different enumeration type 'enum dma_transfer_direction' [-Wenum-conversion] return DMA_NONE; ~~~~~~ ^~~~~~~~ 1 warning generated. Reported-by: Nick Desaulniers Signed-off-by: Nathan Chancellor Reviewed-by: Nick Desaulniers Signed-off-by: Vinod Koul --- include/linux/platform_data/dma-ep93xx.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/dma-ep93xx.h b/include/linux/platform_data/dma-ep93xx.h index f8f1f6b952a6..eb9805bb3fe8 100644 --- a/include/linux/platform_data/dma-ep93xx.h +++ b/include/linux/platform_data/dma-ep93xx.h @@ -85,7 +85,7 @@ static inline enum dma_transfer_direction ep93xx_dma_chan_direction(struct dma_chan *chan) { if (!ep93xx_dma_chan_is_m2p(chan)) - return DMA_NONE; + return DMA_TRANS_NONE; /* even channels are for TX, odd for RX */ return (chan->chan_id % 2 == 0) ? DMA_MEM_TO_DEV : DMA_DEV_TO_MEM; -- cgit v1.2.3 From cc16567e5a8a7bb9439ef61ab80069acdd33f76f Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 2 Oct 2018 11:03:40 +0200 Subject: net: drop unused skb_append_datato_frags() This helper is unused since commit 988cf74deb45 ("inet: Stop generating UFO packets.") Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- include/linux/skbuff.h | 5 ----- net/core/skbuff.c | 58 -------------------------------------------------- 2 files changed, 63 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 87e29710373f..119d092c6b13 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1082,11 +1082,6 @@ static inline int skb_pad(struct sk_buff *skb, int pad) } #define dev_kfree_skb(a) consume_skb(a) -int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb, - int getfrag(void *from, char *to, int offset, - int len, int odd, struct sk_buff *skb), - void *from, int length); - int skb_append_pagefrags(struct sk_buff *skb, struct page *page, int offset, size_t size); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index b2c807f67aba..0e937d3d85b5 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3381,64 +3381,6 @@ unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, } EXPORT_SYMBOL(skb_find_text); -/** - * skb_append_datato_frags - append the user data to a skb - * @sk: sock structure - * @skb: skb structure to be appended with user data. - * @getfrag: call back function to be used for getting the user data - * @from: pointer to user message iov - * @length: length of the iov message - * - * Description: This procedure append the user data in the fragment part - * of the skb if any page alloc fails user this procedure returns -ENOMEM - */ -int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb, - int (*getfrag)(void *from, char *to, int offset, - int len, int odd, struct sk_buff *skb), - void *from, int length) -{ - int frg_cnt = skb_shinfo(skb)->nr_frags; - int copy; - int offset = 0; - int ret; - struct page_frag *pfrag = ¤t->task_frag; - - do { - /* Return error if we don't have space for new frag */ - if (frg_cnt >= MAX_SKB_FRAGS) - return -EMSGSIZE; - - if (!sk_page_frag_refill(sk, pfrag)) - return -ENOMEM; - - /* copy the user data to page */ - copy = min_t(int, length, pfrag->size - pfrag->offset); - - ret = getfrag(from, page_address(pfrag->page) + pfrag->offset, - offset, copy, 0, skb); - if (ret < 0) - return -EFAULT; - - /* copy was successful so update the size parameters */ - skb_fill_page_desc(skb, frg_cnt, pfrag->page, pfrag->offset, - copy); - frg_cnt++; - pfrag->offset += copy; - get_page(pfrag->page); - - skb->truesize += copy; - refcount_add(copy, &sk->sk_wmem_alloc); - skb->len += copy; - skb->data_len += copy; - offset += copy; - length -= copy; - - } while (length > 0); - - return 0; -} -EXPORT_SYMBOL(skb_append_datato_frags); - int skb_append_pagefrags(struct sk_buff *skb, struct page *page, int offset, size_t size) { -- cgit v1.2.3 From 5bf0961cc6a180c077793f2615a8fd842c655876 Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Tue, 2 Oct 2018 06:16:11 -0700 Subject: qed: Add driver support for 20G link speed. Add driver support for configuring/reading the 20G link speed. Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_dev.c | 3 +++ drivers/net/ethernet/qlogic/qed/qed_hsi.h | 2 ++ drivers/net/ethernet/qlogic/qed/qed_main.c | 11 +++++++++++ include/linux/qed/qed_if.h | 9 +++++---- 4 files changed, 21 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index 0fbeafeef7a0..7ceb2b97538d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -2679,6 +2679,9 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) case NVM_CFG1_PORT_DRV_LINK_SPEED_10G: link->speed.forced_speed = 10000; break; + case NVM_CFG1_PORT_DRV_LINK_SPEED_20G: + link->speed.forced_speed = 20000; + break; case NVM_CFG1_PORT_DRV_LINK_SPEED_25G: link->speed.forced_speed = 25000; break; diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h index d4d08383c753..56578f888b70 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h @@ -13154,6 +13154,7 @@ struct nvm_cfg1_port { #define NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_OFFSET 0 #define NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_1G 0x1 #define NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_10G 0x2 +#define NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_20G 0x4 #define NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_25G 0x8 #define NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_40G 0x10 #define NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_50G 0x20 @@ -13164,6 +13165,7 @@ struct nvm_cfg1_port { #define NVM_CFG1_PORT_DRV_LINK_SPEED_AUTONEG 0x0 #define NVM_CFG1_PORT_DRV_LINK_SPEED_1G 0x1 #define NVM_CFG1_PORT_DRV_LINK_SPEED_10G 0x2 +#define NVM_CFG1_PORT_DRV_LINK_SPEED_20G 0x3 #define NVM_CFG1_PORT_DRV_LINK_SPEED_25G 0x4 #define NVM_CFG1_PORT_DRV_LINK_SPEED_40G 0x5 #define NVM_CFG1_PORT_DRV_LINK_SPEED_50G 0x6 diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index 2094d86a7a08..75d217aaf8ce 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -1337,6 +1337,9 @@ static int qed_set_link(struct qed_dev *cdev, struct qed_link_params *params) if (params->adv_speeds & QED_LM_10000baseKR_Full_BIT) link_params->speed.advertised_speeds |= NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_10G; + if (params->adv_speeds & QED_LM_20000baseKR2_Full_BIT) + link_params->speed.advertised_speeds |= + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_20G; if (params->adv_speeds & QED_LM_25000baseKR_Full_BIT) link_params->speed.advertised_speeds |= NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_25G; @@ -1502,6 +1505,9 @@ static void qed_fill_link(struct qed_hwfn *hwfn, if (params.speed.advertised_speeds & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_10G) if_link->advertised_caps |= QED_LM_10000baseKR_Full_BIT; + if (params.speed.advertised_speeds & + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_20G) + if_link->advertised_caps |= QED_LM_20000baseKR2_Full_BIT; if (params.speed.advertised_speeds & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_25G) if_link->advertised_caps |= QED_LM_25000baseKR_Full_BIT; @@ -1522,6 +1528,9 @@ static void qed_fill_link(struct qed_hwfn *hwfn, if (link_caps.speed_capabilities & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_10G) if_link->supported_caps |= QED_LM_10000baseKR_Full_BIT; + if (link_caps.speed_capabilities & + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_20G) + if_link->supported_caps |= QED_LM_20000baseKR2_Full_BIT; if (link_caps.speed_capabilities & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_25G) if_link->supported_caps |= QED_LM_25000baseKR_Full_BIT; @@ -1559,6 +1568,8 @@ static void qed_fill_link(struct qed_hwfn *hwfn, if_link->lp_caps |= QED_LM_1000baseT_Full_BIT; if (link.partner_adv_speed & QED_LINK_PARTNER_SPEED_10G) if_link->lp_caps |= QED_LM_10000baseKR_Full_BIT; + if (link.partner_adv_speed & QED_LINK_PARTNER_SPEED_20G) + if_link->lp_caps |= QED_LM_20000baseKR2_Full_BIT; if (link.partner_adv_speed & QED_LINK_PARTNER_SPEED_25G) if_link->lp_caps |= QED_LM_25000baseKR_Full_BIT; if (link.partner_adv_speed & QED_LINK_PARTNER_SPEED_40G) diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 8cd34645e892..dee3c9c744f7 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -670,10 +670,11 @@ enum qed_link_mode_bits { QED_LM_1000baseT_Half_BIT = BIT(4), QED_LM_1000baseT_Full_BIT = BIT(5), QED_LM_10000baseKR_Full_BIT = BIT(6), - QED_LM_25000baseKR_Full_BIT = BIT(7), - QED_LM_40000baseLR4_Full_BIT = BIT(8), - QED_LM_50000baseKR2_Full_BIT = BIT(9), - QED_LM_100000baseKR4_Full_BIT = BIT(10), + QED_LM_20000baseKR2_Full_BIT = BIT(7), + QED_LM_25000baseKR_Full_BIT = BIT(8), + QED_LM_40000baseLR4_Full_BIT = BIT(9), + QED_LM_50000baseKR2_Full_BIT = BIT(10), + QED_LM_100000baseKR4_Full_BIT = BIT(11), QED_LM_COUNT = 11 }; -- cgit v1.2.3 From f0157160b359b1d263ee9d4e0a435a7ad85bbcea Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 20 Sep 2018 10:27:17 -0600 Subject: PCI: Make link active reporting detection generic The spec has timing requirements when waiting for a link to become active after a conventional reset. Implement those hard delays when waiting for an active link so pciehp and dpc drivers don't need to duplicate this. For devices that don't support data link layer active reporting, wait the fixed time recommended by the PCIe spec. Signed-off-by: Keith Busch [bhelgaas: changelog] Signed-off-by: Bjorn Helgaas Reviewed-by: Sinan Kaya --- drivers/pci/hotplug/pciehp.h | 6 ------ drivers/pci/hotplug/pciehp_hpc.c | 22 ++-------------------- drivers/pci/pci.c | 33 +++++++++++++++++++++++++++------ drivers/pci/pcie/dpc.c | 4 +++- drivers/pci/probe.c | 1 + include/linux/pci.h | 1 + 6 files changed, 34 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h index 3740f1a759c5..75fd52571107 100644 --- a/drivers/pci/hotplug/pciehp.h +++ b/drivers/pci/hotplug/pciehp.h @@ -62,11 +62,6 @@ do { \ * struct controller - PCIe hotplug controller * @pcie: pointer to the controller's PCIe port service device * @slot_cap: cached copy of the Slot Capabilities register - * @link_active_reporting: cached copy of Data Link Layer Link Active Reporting - * Capable bit in Link Capabilities register; if this bit is zero, the - * Data Link Layer Link Active bit in the Link Status register will never - * be set and the driver is thus confined to wait 1 second before assuming - * the link to a hotplugged device is up and accessing it * @slot_ctrl: cached copy of the Slot Control register * @ctrl_lock: serializes writes to the Slot Control register * @cmd_started: jiffies when the Slot Control register was last written; @@ -103,7 +98,6 @@ struct controller { struct pcie_device *pcie; u32 slot_cap; /* capabilities and quirks */ - unsigned int link_active_reporting:1; u16 slot_ctrl; /* control register access */ struct mutex ctrl_lock; diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c index 7b5f9db60d9a..f0f3f4a3dac4 100644 --- a/drivers/pci/hotplug/pciehp_hpc.c +++ b/drivers/pci/hotplug/pciehp_hpc.c @@ -214,13 +214,6 @@ bool pciehp_check_link_active(struct controller *ctrl) return ret; } -static void pcie_wait_link_active(struct controller *ctrl) -{ - struct pci_dev *pdev = ctrl_dev(ctrl); - - pcie_wait_for_link(pdev, true); -} - static bool pci_bus_check_dev(struct pci_bus *bus, int devfn) { u32 l; @@ -253,18 +246,9 @@ int pciehp_check_link_status(struct controller *ctrl) bool found; u16 lnk_status; - /* - * Data Link Layer Link Active Reporting must be capable for - * hot-plug capable downstream port. But old controller might - * not implement it. In this case, we wait for 1000 ms. - */ - if (ctrl->link_active_reporting) - pcie_wait_link_active(ctrl); - else - msleep(1000); + if (!pcie_wait_for_link(pdev, true)) + return -1; - /* wait 100ms before read pci conf, and try in 1s */ - msleep(100); found = pci_bus_check_dev(ctrl->pcie->port->subordinate, PCI_DEVFN(0, 0)); @@ -865,8 +849,6 @@ struct controller *pcie_init(struct pcie_device *dev) /* Check if Data Link Layer Link Active Reporting is implemented */ pcie_capability_read_dword(pdev, PCI_EXP_LNKCAP, &link_cap); - if (link_cap & PCI_EXP_LNKCAP_DLLLARC) - ctrl->link_active_reporting = 1; /* Clear all remaining event bits in Slot Status register. */ pcie_capability_write_word(pdev, PCI_EXP_SLTSTA, diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 6916af269b19..4b0b1d0548f0 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -4489,21 +4489,42 @@ bool pcie_wait_for_link(struct pci_dev *pdev, bool active) bool ret; u16 lnk_status; + /* + * Some controllers might not implement link active reporting. In this + * case, we wait for 1000 + 100 ms. + */ + if (!pdev->link_active_reporting) { + msleep(1100); + return true; + } + + /* + * PCIe r4.0 sec 6.6.1, a component must enter LTSSM Detect within 20ms, + * after which we should expect an link active if the reset was + * successful. If so, software must wait a minimum 100ms before sending + * configuration requests to devices downstream this port. + * + * If the link fails to activate, either the device was physically + * removed or the link is permanently failed. + */ + if (active) + msleep(20); for (;;) { pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnk_status); ret = !!(lnk_status & PCI_EXP_LNKSTA_DLLLA); if (ret == active) - return true; + break; if (timeout <= 0) break; msleep(10); timeout -= 10; } - - pci_info(pdev, "Data Link Layer Link Active not %s in 1000 msec\n", - active ? "set" : "cleared"); - - return false; + if (active && ret) + msleep(100); + else if (ret != active) + pci_info(pdev, "Data Link Layer Link Active not %s in 1000 msec\n", + active ? "set" : "cleared"); + return ret == active; } void pci_reset_secondary_bus(struct pci_dev *dev) diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c index 23e063aefddf..e435d12e61a0 100644 --- a/drivers/pci/pcie/dpc.c +++ b/drivers/pci/pcie/dpc.c @@ -140,10 +140,12 @@ static pci_ers_result_t dpc_reset_link(struct pci_dev *pdev) pci_write_config_word(pdev, cap + PCI_EXP_DPC_STATUS, PCI_EXP_DPC_STATUS_TRIGGER); + if (!pcie_wait_for_link(pdev, true)) + return PCI_ERS_RESULT_DISCONNECT; + return PCI_ERS_RESULT_RECOVERED; } - static void dpc_process_rp_pio_error(struct dpc_dev *dpc) { struct device *dev = &dpc->dev->device; diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 201f9e5ff55c..bb2999d1b199 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -713,6 +713,7 @@ static void pci_set_bus_speed(struct pci_bus *bus) pcie_capability_read_dword(bridge, PCI_EXP_LNKCAP, &linkcap); bus->max_bus_speed = pcie_link_speed[linkcap & PCI_EXP_LNKCAP_SLS]; + bridge->link_active_reporting = !!(linkcap & PCI_EXP_LNKCAP_DLLLARC); pcie_capability_read_word(bridge, PCI_EXP_LNKSTA, &linksta); pcie_update_link_speed(bus, linksta); diff --git a/include/linux/pci.h b/include/linux/pci.h index 6925828f9f25..896b42032ec5 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -402,6 +402,7 @@ struct pci_dev { unsigned int has_secondary_link:1; unsigned int non_compliant_bars:1; /* Broken BARs; ignore them */ unsigned int is_probed:1; /* Device probing in progress */ + unsigned int link_active_reporting:1;/* Device capable of reporting link active */ pci_dev_flags_t dev_flags; atomic_t enable_cnt; /* pci_enable_device has been called */ -- cgit v1.2.3 From 5f5e4890d57a8af5da72c9d73a4efa9bad43a7a3 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Thu, 27 Sep 2018 16:57:05 -0500 Subject: ACPI / property: Allow multiple property compatible _DSD entries It is possible to have _DSD entries where the data is compatible with device properties format but are using different GUID for various reasons. In addition to that there can be many such _DSD entries for a single device such as for PCIe root port used to host a Thunderbolt hierarchy: Scope (\_SB.PCI0.RP21) { Name (_DSD, Package () { ToUUID ("6211e2c0-58a3-4af3-90e1-927a4e0c55a4"), Package () { Package () {"HotPlugSupportInD3", 1} }, ToUUID ("efcc06cc-73ac-4bc3-bff0-76143807c389"), Package () { Package () {"ExternalFacingPort", 1}, Package () {"UID", 0 } } }) } More information about these new _DSD entries can be found in: https://docs.microsoft.com/en-us/windows-hardware/drivers/pci/dsd-for-pcie-root-ports To make these available for drivers via unified device property APIs, modify ACPI property core so that it supports multiple _DSD entries organized in a linked list. We also store GUID of each _DSD entry in struct acpi_device_properties in case there is need to differentiate between entries. The supported GUIDs are then listed in prp_guids array. Signed-off-by: Mika Westerberg Signed-off-by: Bjorn Helgaas Reviewed-by: Rafael J. Wysocki Acked-by: Sakari Ailus --- drivers/acpi/property.c | 94 ++++++++++++++++++++++++++++++++------------- drivers/acpi/x86/apple.c | 2 +- drivers/gpio/gpiolib-acpi.c | 2 +- include/acpi/acpi_bus.h | 8 +++- include/linux/acpi.h | 9 +++++ 5 files changed, 86 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c index 693cf05b0cc4..90ba9371bae6 100644 --- a/drivers/acpi/property.c +++ b/drivers/acpi/property.c @@ -24,11 +24,12 @@ static int acpi_data_get_property_array(const struct acpi_device_data *data, acpi_object_type type, const union acpi_object **obj); -/* ACPI _DSD device properties GUID: daffd814-6eba-4d8c-8a91-bc9bbf4aa301 */ -static const guid_t prp_guid = +static const guid_t prp_guids[] = { + /* ACPI _DSD device properties GUID: daffd814-6eba-4d8c-8a91-bc9bbf4aa301 */ GUID_INIT(0xdaffd814, 0x6eba, 0x4d8c, - 0x8a, 0x91, 0xbc, 0x9b, 0xbf, 0x4a, 0xa3, 0x01); -/* ACPI _DSD data subnodes GUID: dbb8e3e6-5886-4ba6-8795-1319f52a966b */ + 0x8a, 0x91, 0xbc, 0x9b, 0xbf, 0x4a, 0xa3, 0x01), +}; + static const guid_t ads_guid = GUID_INIT(0xdbb8e3e6, 0x5886, 0x4ba6, 0x87, 0x95, 0x13, 0x19, 0xf5, 0x2a, 0x96, 0x6b); @@ -56,6 +57,7 @@ static bool acpi_nondev_subnode_extract(const union acpi_object *desc, dn->name = link->package.elements[0].string.pointer; dn->fwnode.ops = &acpi_data_fwnode_ops; dn->parent = parent; + INIT_LIST_HEAD(&dn->data.properties); INIT_LIST_HEAD(&dn->data.subnodes); result = acpi_extract_properties(desc, &dn->data); @@ -288,6 +290,35 @@ static void acpi_init_of_compatible(struct acpi_device *adev) adev->flags.of_compatible_ok = 1; } +static bool acpi_is_property_guid(const guid_t *guid) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(prp_guids); i++) { + if (guid_equal(guid, &prp_guids[i])) + return true; + } + + return false; +} + +struct acpi_device_properties * +acpi_data_add_props(struct acpi_device_data *data, const guid_t *guid, + const union acpi_object *properties) +{ + struct acpi_device_properties *props; + + props = kzalloc(sizeof(*props), GFP_KERNEL); + if (props) { + INIT_LIST_HEAD(&props->list); + props->guid = guid; + props->properties = properties; + list_add_tail(&props->list, &data->properties); + } + + return props; +} + static bool acpi_extract_properties(const union acpi_object *desc, struct acpi_device_data *data) { @@ -312,7 +343,7 @@ static bool acpi_extract_properties(const union acpi_object *desc, properties->type != ACPI_TYPE_PACKAGE) break; - if (!guid_equal((guid_t *)guid->buffer.pointer, &prp_guid)) + if (!acpi_is_property_guid((guid_t *)guid->buffer.pointer)) continue; /* @@ -320,13 +351,13 @@ static bool acpi_extract_properties(const union acpi_object *desc, * package immediately following it. */ if (!acpi_properties_format_valid(properties)) - break; + continue; - data->properties = properties; - return true; + acpi_data_add_props(data, (const guid_t *)guid->buffer.pointer, + properties); } - return false; + return !list_empty(&data->properties); } void acpi_init_properties(struct acpi_device *adev) @@ -336,6 +367,7 @@ void acpi_init_properties(struct acpi_device *adev) acpi_status status; bool acpi_of = false; + INIT_LIST_HEAD(&adev->data.properties); INIT_LIST_HEAD(&adev->data.subnodes); if (!adev->handle) @@ -398,11 +430,16 @@ static void acpi_destroy_nondev_subnodes(struct list_head *list) void acpi_free_properties(struct acpi_device *adev) { + struct acpi_device_properties *props, *tmp; + acpi_destroy_nondev_subnodes(&adev->data.subnodes); ACPI_FREE((void *)adev->data.pointer); adev->data.of_compatible = NULL; adev->data.pointer = NULL; - adev->data.properties = NULL; + list_for_each_entry_safe(props, tmp, &adev->data.properties, list) { + list_del(&props->list); + kfree(props); + } } /** @@ -427,32 +464,37 @@ static int acpi_data_get_property(const struct acpi_device_data *data, const char *name, acpi_object_type type, const union acpi_object **obj) { - const union acpi_object *properties; - int i; + const struct acpi_device_properties *props; if (!data || !name) return -EINVAL; - if (!data->pointer || !data->properties) + if (!data->pointer || list_empty(&data->properties)) return -EINVAL; - properties = data->properties; - for (i = 0; i < properties->package.count; i++) { - const union acpi_object *propname, *propvalue; - const union acpi_object *property; + list_for_each_entry(props, &data->properties, list) { + const union acpi_object *properties; + unsigned int i; - property = &properties->package.elements[i]; + properties = props->properties; + for (i = 0; i < properties->package.count; i++) { + const union acpi_object *propname, *propvalue; + const union acpi_object *property; - propname = &property->package.elements[0]; - propvalue = &property->package.elements[1]; + property = &properties->package.elements[i]; - if (!strcmp(name, propname->string.pointer)) { - if (type != ACPI_TYPE_ANY && propvalue->type != type) - return -EPROTO; - if (obj) - *obj = propvalue; + propname = &property->package.elements[0]; + propvalue = &property->package.elements[1]; - return 0; + if (!strcmp(name, propname->string.pointer)) { + if (type != ACPI_TYPE_ANY && + propvalue->type != type) + return -EPROTO; + if (obj) + *obj = propvalue; + + return 0; + } } } return -EINVAL; diff --git a/drivers/acpi/x86/apple.c b/drivers/acpi/x86/apple.c index 51b4cf9f25da..130df1c8ed7d 100644 --- a/drivers/acpi/x86/apple.c +++ b/drivers/acpi/x86/apple.c @@ -132,8 +132,8 @@ void acpi_extract_apple_properties(struct acpi_device *adev) } WARN_ON(free_space != (void *)newprops + newsize); - adev->data.properties = newprops; adev->data.pointer = newprops; + acpi_data_add_props(&adev->data, &apple_prp_guid, newprops); out_free: ACPI_FREE(props); diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index 8b9d7e42c600..f74aa0e60300 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -1198,7 +1198,7 @@ int acpi_gpio_count(struct device *dev, const char *con_id) bool acpi_can_fallback_to_crs(struct acpi_device *adev, const char *con_id) { /* Never allow fallback if the device has properties */ - if (adev->data.properties || adev->driver_gpios) + if (acpi_dev_has_props(adev) || adev->driver_gpios) return false; return con_id == NULL; diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index ba4dd54f2c82..cd35e3ce9a8b 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -346,10 +346,16 @@ struct acpi_device_physical_node { bool put_online:1; }; +struct acpi_device_properties { + const guid_t *guid; + const union acpi_object *properties; + struct list_head list; +}; + /* ACPI Device Specific Data (_DSD) */ struct acpi_device_data { const union acpi_object *pointer; - const union acpi_object *properties; + struct list_head properties; const union acpi_object *of_compatible; struct list_head subnodes; }; diff --git a/include/linux/acpi.h b/include/linux/acpi.h index de8d3d3fa651..51e3c29663fe 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1074,6 +1074,15 @@ static inline int acpi_node_get_property_reference( NR_FWNODE_REFERENCE_ARGS, args); } +static inline bool acpi_dev_has_props(const struct acpi_device *adev) +{ + return !list_empty(&adev->data.properties); +} + +struct acpi_device_properties * +acpi_data_add_props(struct acpi_device_data *data, const guid_t *guid, + const union acpi_object *properties); + int acpi_node_prop_get(const struct fwnode_handle *fwnode, const char *propname, void **valptr); int acpi_dev_prop_read_single(struct acpi_device *adev, -- cgit v1.2.3 From fd3b339cbb6047dacfa7ccc81c846efcb61032a9 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Mon, 1 Oct 2018 12:31:21 +0300 Subject: thunderbolt: Convert rest of the driver files to use SPDX identifier This gets rid of the licence boilerplate duplicated in each file. While there fix doubled space in domain.c author line. No functional changes intended. Signed-off-by: Mika Westerberg Acked-by: Yehezkel Bernat Signed-off-by: Greg Kroah-Hartman --- drivers/thunderbolt/dma_port.c | 5 +---- drivers/thunderbolt/dma_port.h | 5 +---- drivers/thunderbolt/domain.c | 7 ++----- drivers/thunderbolt/icm.c | 5 +---- drivers/thunderbolt/property.c | 5 +---- drivers/thunderbolt/tb_msgs.h | 5 +---- drivers/thunderbolt/xdomain.c | 5 +---- include/linux/thunderbolt.h | 5 +---- 8 files changed, 9 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/drivers/thunderbolt/dma_port.c b/drivers/thunderbolt/dma_port.c index f2701194f810..847dd07a7b17 100644 --- a/drivers/thunderbolt/dma_port.c +++ b/drivers/thunderbolt/dma_port.c @@ -1,13 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Thunderbolt DMA configuration based mailbox support * * Copyright (C) 2017, Intel Corporation * Authors: Michael Jamet * Mika Westerberg - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include diff --git a/drivers/thunderbolt/dma_port.h b/drivers/thunderbolt/dma_port.h index c4a69e0fbff7..7deadd97ce31 100644 --- a/drivers/thunderbolt/dma_port.h +++ b/drivers/thunderbolt/dma_port.h @@ -1,13 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Thunderbolt DMA configuration based mailbox support * * Copyright (C) 2017, Intel Corporation * Authors: Michael Jamet * Mika Westerberg - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef DMA_PORT_H_ diff --git a/drivers/thunderbolt/domain.c b/drivers/thunderbolt/domain.c index 092381e2accf..93e562f18d40 100644 --- a/drivers/thunderbolt/domain.c +++ b/drivers/thunderbolt/domain.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Thunderbolt bus support * * Copyright (C) 2017, Intel Corporation - * Author: Mika Westerberg - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. + * Author: Mika Westerberg */ #include diff --git a/drivers/thunderbolt/icm.c b/drivers/thunderbolt/icm.c index e1e264a9a4c7..533068651f90 100644 --- a/drivers/thunderbolt/icm.c +++ b/drivers/thunderbolt/icm.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Internal Thunderbolt Connection Manager. This is a firmware running on * the Thunderbolt host controller performing most of the low-level @@ -6,10 +7,6 @@ * Copyright (C) 2017, Intel Corporation * Authors: Michael Jamet * Mika Westerberg - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include diff --git a/drivers/thunderbolt/property.c b/drivers/thunderbolt/property.c index 8fe913a95b4a..b2f0d6386cee 100644 --- a/drivers/thunderbolt/property.c +++ b/drivers/thunderbolt/property.c @@ -1,13 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Thunderbolt XDomain property support * * Copyright (C) 2017, Intel Corporation * Authors: Michael Jamet * Mika Westerberg - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include diff --git a/drivers/thunderbolt/tb_msgs.h b/drivers/thunderbolt/tb_msgs.h index 2487e162c885..02c84aa3d018 100644 --- a/drivers/thunderbolt/tb_msgs.h +++ b/drivers/thunderbolt/tb_msgs.h @@ -1,12 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Thunderbolt control channel messages * * Copyright (C) 2014 Andreas Noever * Copyright (C) 2017, Intel Corporation - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef _TB_MSGS diff --git a/drivers/thunderbolt/xdomain.c b/drivers/thunderbolt/xdomain.c index db8bece63327..e27dd8beb94b 100644 --- a/drivers/thunderbolt/xdomain.c +++ b/drivers/thunderbolt/xdomain.c @@ -1,13 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Thunderbolt XDomain discovery protocol support * * Copyright (C) 2017, Intel Corporation * Authors: Michael Jamet * Mika Westerberg - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h index a3ed26082bc1..bf6ec83e60ee 100644 --- a/include/linux/thunderbolt.h +++ b/include/linux/thunderbolt.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Thunderbolt service API * @@ -5,10 +6,6 @@ * Copyright (C) 2017, Intel Corporation * Authors: Michael Jamet * Mika Westerberg - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef THUNDERBOLT_H_ -- cgit v1.2.3 From f3709f69b7c5cba6323cc03c29b64293b93be817 Mon Sep 17 00:00:00 2001 From: Joe Stringer Date: Tue, 2 Oct 2018 13:35:29 -0700 Subject: bpf: Add iterator for spilled registers Add this iterator for spilled registers, it concentrates the details of how to get the current frame's spilled registers into a single macro while clarifying the intention of the code which is calling the macro. Signed-off-by: Joe Stringer Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/bpf_verifier.h | 11 +++++++++++ kernel/bpf/verifier.c | 16 +++++++--------- 2 files changed, 18 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index b42b60a83e19..d0e7f97e8b60 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -131,6 +131,17 @@ struct bpf_verifier_state { u32 curframe; }; +#define bpf_get_spilled_reg(slot, frame) \ + (((slot < frame->allocated_stack / BPF_REG_SIZE) && \ + (frame->stack[slot].slot_type[0] == STACK_SPILL)) \ + ? &frame->stack[slot].spilled_ptr : NULL) + +/* Iterate over 'frame', setting 'reg' to either NULL or a spilled register. */ +#define bpf_for_each_spilled_reg(iter, frame, reg) \ + for (iter = 0, reg = bpf_get_spilled_reg(iter, frame); \ + iter < frame->allocated_stack / BPF_REG_SIZE; \ + iter++, reg = bpf_get_spilled_reg(iter, frame)) + /* linked list of verifier states used to prune search */ struct bpf_verifier_state_list { struct bpf_verifier_state state; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index a8cc83a970d1..9c82d8f58085 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2252,10 +2252,9 @@ static void __clear_all_pkt_pointers(struct bpf_verifier_env *env, if (reg_is_pkt_pointer_any(®s[i])) mark_reg_unknown(env, regs, i); - for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { - if (state->stack[i].slot_type[0] != STACK_SPILL) + bpf_for_each_spilled_reg(i, state, reg) { + if (!reg) continue; - reg = &state->stack[i].spilled_ptr; if (reg_is_pkt_pointer_any(reg)) __mark_reg_unknown(reg); } @@ -3395,10 +3394,9 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, for (j = 0; j <= vstate->curframe; j++) { state = vstate->frame[j]; - for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { - if (state->stack[i].slot_type[0] != STACK_SPILL) + bpf_for_each_spilled_reg(i, state, reg) { + if (!reg) continue; - reg = &state->stack[i].spilled_ptr; if (reg->type == type && reg->id == dst_reg->id) reg->range = max(reg->range, new_range); } @@ -3643,7 +3641,7 @@ static void mark_map_regs(struct bpf_verifier_state *vstate, u32 regno, bool is_null) { struct bpf_func_state *state = vstate->frame[vstate->curframe]; - struct bpf_reg_state *regs = state->regs; + struct bpf_reg_state *reg, *regs = state->regs; u32 id = regs[regno].id; int i, j; @@ -3652,8 +3650,8 @@ static void mark_map_regs(struct bpf_verifier_state *vstate, u32 regno, for (j = 0; j <= vstate->curframe; j++) { state = vstate->frame[j]; - for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { - if (state->stack[i].slot_type[0] != STACK_SPILL) + bpf_for_each_spilled_reg(i, state, reg) { + if (!reg) continue; mark_map_reg(&state->stack[i].spilled_ptr, 0, id, is_null); } -- cgit v1.2.3 From c64b7983288e636356f7f5f652de4813e1cfedac Mon Sep 17 00:00:00 2001 From: Joe Stringer Date: Tue, 2 Oct 2018 13:35:33 -0700 Subject: bpf: Add PTR_TO_SOCKET verifier type Teach the verifier a little bit about a new type of pointer, a PTR_TO_SOCKET. This pointer type is accessed from BPF through the 'struct bpf_sock' structure. Signed-off-by: Joe Stringer Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 34 ++++++++++++ include/linux/bpf_verifier.h | 2 + kernel/bpf/verifier.c | 120 ++++++++++++++++++++++++++++++++++++++----- net/core/filter.c | 30 ++++++----- 4 files changed, 160 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 018299a595c8..027697b6a22f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -154,6 +154,7 @@ enum bpf_arg_type { ARG_PTR_TO_CTX, /* pointer to context */ ARG_ANYTHING, /* any (initialized) argument is ok */ + ARG_PTR_TO_SOCKET, /* pointer to bpf_sock */ }; /* type of values returned from helper functions */ @@ -162,6 +163,7 @@ enum bpf_return_type { RET_VOID, /* function doesn't return anything */ RET_PTR_TO_MAP_VALUE, /* returns a pointer to map elem value */ RET_PTR_TO_MAP_VALUE_OR_NULL, /* returns a pointer to map elem value or NULL */ + RET_PTR_TO_SOCKET_OR_NULL, /* returns a pointer to a socket or NULL */ }; /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs @@ -213,6 +215,8 @@ enum bpf_reg_type { PTR_TO_PACKET, /* reg points to skb->data */ PTR_TO_PACKET_END, /* skb->data + headlen */ PTR_TO_FLOW_KEYS, /* reg points to bpf_flow_keys */ + PTR_TO_SOCKET, /* reg points to struct bpf_sock */ + PTR_TO_SOCKET_OR_NULL, /* reg points to struct bpf_sock or NULL */ }; /* The information passed from prog-specific *_is_valid_access @@ -343,6 +347,11 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void); typedef unsigned long (*bpf_ctx_copy_t)(void *dst, const void *src, unsigned long off, unsigned long len); +typedef u32 (*bpf_convert_ctx_access_t)(enum bpf_access_type type, + const struct bpf_insn *src, + struct bpf_insn *dst, + struct bpf_prog *prog, + u32 *target_size); u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy); @@ -836,4 +845,29 @@ extern const struct bpf_func_proto bpf_get_local_storage_proto; void bpf_user_rnd_init_once(void); u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); +#if defined(CONFIG_NET) +bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, + struct bpf_insn_access_aux *info); +u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog, + u32 *target_size); +#else +static inline bool bpf_sock_is_valid_access(int off, int size, + enum bpf_access_type type, + struct bpf_insn_access_aux *info) +{ + return false; +} +static inline u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog, + u32 *target_size) +{ + return 0; +} +#endif + #endif /* _LINUX_BPF_H */ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index d0e7f97e8b60..a411363098a5 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -58,6 +58,8 @@ struct bpf_reg_state { * offset, so they can share range knowledge. * For PTR_TO_MAP_VALUE_OR_NULL this is used to share which map value we * came from, when one is tested for != NULL. + * For PTR_TO_SOCKET this is used to share which pointers retain the + * same reference to the socket, to determine proper reference freeing. */ u32 id; /* For scalar types (SCALAR_VALUE), this represents our knowledge of diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 98b218bd46e8..f86386c9affd 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -80,8 +80,8 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = { * (like pointer plus pointer becomes SCALAR_VALUE type) * * When verifier sees load or store instructions the type of base register - * can be: PTR_TO_MAP_VALUE, PTR_TO_CTX, PTR_TO_STACK. These are three pointer - * types recognized by check_mem_access() function. + * can be: PTR_TO_MAP_VALUE, PTR_TO_CTX, PTR_TO_STACK, PTR_TO_SOCKET. These are + * four pointer types recognized by check_mem_access() function. * * PTR_TO_MAP_VALUE means that this register is pointing to 'map element value' * and the range of [ptr, ptr + map's value_size) is accessible. @@ -267,6 +267,8 @@ static const char * const reg_type_str[] = { [PTR_TO_PACKET_META] = "pkt_meta", [PTR_TO_PACKET_END] = "pkt_end", [PTR_TO_FLOW_KEYS] = "flow_keys", + [PTR_TO_SOCKET] = "sock", + [PTR_TO_SOCKET_OR_NULL] = "sock_or_null", }; static char slot_type_char[] = { @@ -973,6 +975,8 @@ static bool is_spillable_regtype(enum bpf_reg_type type) case PTR_TO_PACKET_END: case PTR_TO_FLOW_KEYS: case CONST_PTR_TO_MAP: + case PTR_TO_SOCKET: + case PTR_TO_SOCKET_OR_NULL: return true; default: return false; @@ -1341,6 +1345,28 @@ static int check_flow_keys_access(struct bpf_verifier_env *env, int off, return 0; } +static int check_sock_access(struct bpf_verifier_env *env, u32 regno, int off, + int size, enum bpf_access_type t) +{ + struct bpf_reg_state *regs = cur_regs(env); + struct bpf_reg_state *reg = ®s[regno]; + struct bpf_insn_access_aux info; + + if (reg->smin_value < 0) { + verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", + regno); + return -EACCES; + } + + if (!bpf_sock_is_valid_access(off, size, t, &info)) { + verbose(env, "invalid bpf_sock access off=%d size=%d\n", + off, size); + return -EACCES; + } + + return 0; +} + static bool __is_pointer_value(bool allow_ptr_leaks, const struct bpf_reg_state *reg) { @@ -1459,6 +1485,9 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, */ strict = true; break; + case PTR_TO_SOCKET: + pointer_desc = "sock "; + break; default: break; } @@ -1726,6 +1755,14 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn err = check_flow_keys_access(env, off, size); if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); + } else if (reg->type == PTR_TO_SOCKET) { + if (t == BPF_WRITE) { + verbose(env, "cannot write into socket\n"); + return -EACCES; + } + err = check_sock_access(env, regno, off, size, t); + if (!err && value_regno >= 0) + mark_reg_unknown(env, regs, value_regno); } else { verbose(env, "R%d invalid mem access '%s'\n", regno, reg_type_str[reg->type]); @@ -1948,6 +1985,10 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, err = check_ctx_reg(env, reg, regno); if (err < 0) return err; + } else if (arg_type == ARG_PTR_TO_SOCKET) { + expected_type = PTR_TO_SOCKET; + if (type != expected_type) + goto err_type; } else if (arg_type_is_mem_ptr(arg_type)) { expected_type = PTR_TO_STACK; /* One exception here. In case function allows for NULL to be @@ -2543,6 +2584,10 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn } regs[BPF_REG_0].map_ptr = meta.map_ptr; regs[BPF_REG_0].id = ++env->id_gen; + } else if (fn->ret_type == RET_PTR_TO_SOCKET_OR_NULL) { + mark_reg_known_zero(env, regs, BPF_REG_0); + regs[BPF_REG_0].type = PTR_TO_SOCKET_OR_NULL; + regs[BPF_REG_0].id = ++env->id_gen; } else { verbose(env, "unknown return type %d of func %s#%d\n", fn->ret_type, func_id_name(func_id), func_id); @@ -2680,6 +2725,8 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, return -EACCES; case CONST_PTR_TO_MAP: case PTR_TO_PACKET_END: + case PTR_TO_SOCKET: + case PTR_TO_SOCKET_OR_NULL: verbose(env, "R%d pointer arithmetic on %s prohibited\n", dst, reg_type_str[ptr_reg->type]); return -EACCES; @@ -3627,6 +3674,8 @@ static void mark_ptr_or_null_reg(struct bpf_reg_state *reg, u32 id, } else { reg->type = PTR_TO_MAP_VALUE; } + } else if (reg->type == PTR_TO_SOCKET_OR_NULL) { + reg->type = PTR_TO_SOCKET; } /* We don't need id from this point onwards anymore, thus we * should better reset it, so that state pruning has chances @@ -4402,6 +4451,8 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, case CONST_PTR_TO_MAP: case PTR_TO_PACKET_END: case PTR_TO_FLOW_KEYS: + case PTR_TO_SOCKET: + case PTR_TO_SOCKET_OR_NULL: /* Only valid matches are exact, which memcmp() above * would have accepted */ @@ -4679,6 +4730,37 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) return 0; } +/* Return true if it's OK to have the same insn return a different type. */ +static bool reg_type_mismatch_ok(enum bpf_reg_type type) +{ + switch (type) { + case PTR_TO_CTX: + case PTR_TO_SOCKET: + case PTR_TO_SOCKET_OR_NULL: + return false; + default: + return true; + } +} + +/* If an instruction was previously used with particular pointer types, then we + * need to be careful to avoid cases such as the below, where it may be ok + * for one branch accessing the pointer, but not ok for the other branch: + * + * R1 = sock_ptr + * goto X; + * ... + * R1 = some_other_valid_ptr; + * goto X; + * ... + * R2 = *(u32 *)(R1 + 0); + */ +static bool reg_type_mismatch(enum bpf_reg_type src, enum bpf_reg_type prev) +{ + return src != prev && (!reg_type_mismatch_ok(src) || + !reg_type_mismatch_ok(prev)); +} + static int do_check(struct bpf_verifier_env *env) { struct bpf_verifier_state *state; @@ -4811,9 +4893,7 @@ static int do_check(struct bpf_verifier_env *env) */ *prev_src_type = src_reg_type; - } else if (src_reg_type != *prev_src_type && - (src_reg_type == PTR_TO_CTX || - *prev_src_type == PTR_TO_CTX)) { + } else if (reg_type_mismatch(src_reg_type, *prev_src_type)) { /* ABuser program is trying to use the same insn * dst_reg = *(u32*) (src_reg + off) * with different pointer types: @@ -4858,9 +4938,7 @@ static int do_check(struct bpf_verifier_env *env) if (*prev_dst_type == NOT_INIT) { *prev_dst_type = dst_reg_type; - } else if (dst_reg_type != *prev_dst_type && - (dst_reg_type == PTR_TO_CTX || - *prev_dst_type == PTR_TO_CTX)) { + } else if (reg_type_mismatch(dst_reg_type, *prev_dst_type)) { verbose(env, "same insn cannot be used with different pointers\n"); return -EINVAL; } @@ -5286,8 +5364,10 @@ static void sanitize_dead_code(struct bpf_verifier_env *env) } } -/* convert load instructions that access fields of 'struct __sk_buff' - * into sequence of instructions that access fields of 'struct sk_buff' +/* convert load instructions that access fields of a context type into a + * sequence of instructions that access fields of the underlying structure: + * struct __sk_buff -> struct sk_buff + * struct bpf_sock_ops -> struct sock */ static int convert_ctx_accesses(struct bpf_verifier_env *env) { @@ -5316,12 +5396,14 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) } } - if (!ops->convert_ctx_access || bpf_prog_is_dev_bound(env->prog->aux)) + if (bpf_prog_is_dev_bound(env->prog->aux)) return 0; insn = env->prog->insnsi + delta; for (i = 0; i < insn_cnt; i++, insn++) { + bpf_convert_ctx_access_t convert_ctx_access; + if (insn->code == (BPF_LDX | BPF_MEM | BPF_B) || insn->code == (BPF_LDX | BPF_MEM | BPF_H) || insn->code == (BPF_LDX | BPF_MEM | BPF_W) || @@ -5363,8 +5445,18 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) continue; } - if (env->insn_aux_data[i + delta].ptr_type != PTR_TO_CTX) + switch (env->insn_aux_data[i + delta].ptr_type) { + case PTR_TO_CTX: + if (!ops->convert_ctx_access) + continue; + convert_ctx_access = ops->convert_ctx_access; + break; + case PTR_TO_SOCKET: + convert_ctx_access = bpf_sock_convert_ctx_access; + break; + default: continue; + } ctx_field_size = env->insn_aux_data[i + delta].ctx_field_size; size = BPF_LDST_BYTES(insn); @@ -5396,8 +5488,8 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) } target_size = 0; - cnt = ops->convert_ctx_access(type, insn, insn_buf, env->prog, - &target_size); + cnt = convert_ctx_access(type, insn, insn_buf, env->prog, + &target_size); if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf) || (ctx_field_size && !target_size)) { verbose(env, "bpf verifier is misconfigured\n"); diff --git a/net/core/filter.c b/net/core/filter.c index 72db8afb7cb6..b2cb186252e4 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5394,23 +5394,29 @@ static bool __sock_filter_check_size(int off, int size, return size == size_default; } -static bool sock_filter_is_valid_access(int off, int size, - enum bpf_access_type type, - const struct bpf_prog *prog, - struct bpf_insn_access_aux *info) +bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, + struct bpf_insn_access_aux *info) { if (off < 0 || off >= sizeof(struct bpf_sock)) return false; if (off % size != 0) return false; - if (!__sock_filter_check_attach_type(off, type, - prog->expected_attach_type)) - return false; if (!__sock_filter_check_size(off, size, info)) return false; return true; } +static bool sock_filter_is_valid_access(int off, int size, + enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + if (!bpf_sock_is_valid_access(off, size, type, info)) + return false; + return __sock_filter_check_attach_type(off, type, + prog->expected_attach_type); +} + static int bpf_unclone_prologue(struct bpf_insn *insn_buf, bool direct_write, const struct bpf_prog *prog, int drop_verdict) { @@ -6122,10 +6128,10 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, return insn - insn_buf; } -static u32 sock_filter_convert_ctx_access(enum bpf_access_type type, - const struct bpf_insn *si, - struct bpf_insn *insn_buf, - struct bpf_prog *prog, u32 *target_size) +u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; int off; @@ -7037,7 +7043,7 @@ const struct bpf_prog_ops lwt_seg6local_prog_ops = { const struct bpf_verifier_ops cg_sock_verifier_ops = { .get_func_proto = sock_filter_func_proto, .is_valid_access = sock_filter_is_valid_access, - .convert_ctx_access = sock_filter_convert_ctx_access, + .convert_ctx_access = bpf_sock_convert_ctx_access, }; const struct bpf_prog_ops cg_sock_prog_ops = { -- cgit v1.2.3 From fd978bf7fd312581a7ca454a991f0ffb34c4204b Mon Sep 17 00:00:00 2001 From: Joe Stringer Date: Tue, 2 Oct 2018 13:35:35 -0700 Subject: bpf: Add reference tracking to verifier Allow helper functions to acquire a reference and return it into a register. Specific pointer types such as the PTR_TO_SOCKET will implicitly represent such a reference. The verifier must ensure that these references are released exactly once in each path through the program. To achieve this, this commit assigns an id to the pointer and tracks it in the 'bpf_func_state', then when the function or program exits, verifies that all of the acquired references have been freed. When the pointer is passed to a function that frees the reference, it is removed from the 'bpf_func_state` and all existing copies of the pointer in registers are marked invalid. Signed-off-by: Joe Stringer Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/bpf_verifier.h | 24 +++- kernel/bpf/verifier.c | 306 ++++++++++++++++++++++++++++++++++++++++--- 2 files changed, 308 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index a411363098a5..7b6fd2ab3263 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -104,6 +104,17 @@ struct bpf_stack_state { u8 slot_type[BPF_REG_SIZE]; }; +struct bpf_reference_state { + /* Track each reference created with a unique id, even if the same + * instruction creates the reference multiple times (eg, via CALL). + */ + int id; + /* Instruction where the allocation of this reference occurred. This + * is used purely to inform the user of a reference leak. + */ + int insn_idx; +}; + /* state of the program: * type of all registers and stack info */ @@ -121,7 +132,9 @@ struct bpf_func_state { */ u32 subprogno; - /* should be second to last. See copy_func_state() */ + /* The following fields should be last. See copy_func_state() */ + int acquired_refs; + struct bpf_reference_state *refs; int allocated_stack; struct bpf_stack_state *stack; }; @@ -217,11 +230,16 @@ __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log, __printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env, const char *fmt, ...); -static inline struct bpf_reg_state *cur_regs(struct bpf_verifier_env *env) +static inline struct bpf_func_state *cur_func(struct bpf_verifier_env *env) { struct bpf_verifier_state *cur = env->cur_state; - return cur->frame[cur->curframe]->regs; + return cur->frame[cur->curframe]; +} + +static inline struct bpf_reg_state *cur_regs(struct bpf_verifier_env *env) +{ + return cur_func(env)->regs; } int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 11e982381061..cd0d8bc00bd1 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1,5 +1,6 @@ /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com * Copyright (c) 2016 Facebook + * Copyright (c) 2018 Covalent IO, Inc. http://covalent.io * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public @@ -140,6 +141,18 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = { * * After the call R0 is set to return type of the function and registers R1-R5 * are set to NOT_INIT to indicate that they are no longer readable. + * + * The following reference types represent a potential reference to a kernel + * resource which, after first being allocated, must be checked and freed by + * the BPF program: + * - PTR_TO_SOCKET_OR_NULL, PTR_TO_SOCKET + * + * When the verifier sees a helper call return a reference type, it allocates a + * pointer id for the reference and stores it in the current function state. + * Similar to the way that PTR_TO_MAP_VALUE_OR_NULL is converted into + * PTR_TO_MAP_VALUE, PTR_TO_SOCKET_OR_NULL becomes PTR_TO_SOCKET when the type + * passes through a NULL-check conditional. For the branch wherein the state is + * changed to CONST_IMM, the verifier releases the reference. */ /* verifier_state + insn_idx are pushed to stack when branch is encountered */ @@ -189,6 +202,7 @@ struct bpf_call_arg_meta { int access_size; s64 msize_smax_value; u64 msize_umax_value; + int ptr_id; }; static DEFINE_MUTEX(bpf_verifier_lock); @@ -251,7 +265,42 @@ static bool type_is_pkt_pointer(enum bpf_reg_type type) static bool reg_type_may_be_null(enum bpf_reg_type type) { - return type == PTR_TO_MAP_VALUE_OR_NULL; + return type == PTR_TO_MAP_VALUE_OR_NULL || + type == PTR_TO_SOCKET_OR_NULL; +} + +static bool type_is_refcounted(enum bpf_reg_type type) +{ + return type == PTR_TO_SOCKET; +} + +static bool type_is_refcounted_or_null(enum bpf_reg_type type) +{ + return type == PTR_TO_SOCKET || type == PTR_TO_SOCKET_OR_NULL; +} + +static bool reg_is_refcounted(const struct bpf_reg_state *reg) +{ + return type_is_refcounted(reg->type); +} + +static bool reg_is_refcounted_or_null(const struct bpf_reg_state *reg) +{ + return type_is_refcounted_or_null(reg->type); +} + +static bool arg_type_is_refcounted(enum bpf_arg_type type) +{ + return type == ARG_PTR_TO_SOCKET; +} + +/* Determine whether the function releases some resources allocated by another + * function call. The first reference type argument will be assumed to be + * released by release_reference(). + */ +static bool is_release_function(enum bpf_func_id func_id) +{ + return false; } /* string representation of 'enum bpf_reg_type' */ @@ -385,6 +434,12 @@ static void print_verifier_state(struct bpf_verifier_env *env, else verbose(env, "=%s", types_buf); } + if (state->acquired_refs && state->refs[0].id) { + verbose(env, " refs=%d", state->refs[0].id); + for (i = 1; i < state->acquired_refs; i++) + if (state->refs[i].id) + verbose(env, ",%d", state->refs[i].id); + } verbose(env, "\n"); } @@ -403,6 +458,8 @@ static int copy_##NAME##_state(struct bpf_func_state *dst, \ sizeof(*src->FIELD) * (src->COUNT / SIZE)); \ return 0; \ } +/* copy_reference_state() */ +COPY_STATE_FN(reference, acquired_refs, refs, 1) /* copy_stack_state() */ COPY_STATE_FN(stack, allocated_stack, stack, BPF_REG_SIZE) #undef COPY_STATE_FN @@ -441,6 +498,8 @@ static int realloc_##NAME##_state(struct bpf_func_state *state, int size, \ state->FIELD = new_##FIELD; \ return 0; \ } +/* realloc_reference_state() */ +REALLOC_STATE_FN(reference, acquired_refs, refs, 1) /* realloc_stack_state() */ REALLOC_STATE_FN(stack, allocated_stack, stack, BPF_REG_SIZE) #undef REALLOC_STATE_FN @@ -452,16 +511,89 @@ REALLOC_STATE_FN(stack, allocated_stack, stack, BPF_REG_SIZE) * which realloc_stack_state() copies over. It points to previous * bpf_verifier_state which is never reallocated. */ -static int realloc_func_state(struct bpf_func_state *state, int size, - bool copy_old) +static int realloc_func_state(struct bpf_func_state *state, int stack_size, + int refs_size, bool copy_old) { - return realloc_stack_state(state, size, copy_old); + int err = realloc_reference_state(state, refs_size, copy_old); + if (err) + return err; + return realloc_stack_state(state, stack_size, copy_old); +} + +/* Acquire a pointer id from the env and update the state->refs to include + * this new pointer reference. + * On success, returns a valid pointer id to associate with the register + * On failure, returns a negative errno. + */ +static int acquire_reference_state(struct bpf_verifier_env *env, int insn_idx) +{ + struct bpf_func_state *state = cur_func(env); + int new_ofs = state->acquired_refs; + int id, err; + + err = realloc_reference_state(state, state->acquired_refs + 1, true); + if (err) + return err; + id = ++env->id_gen; + state->refs[new_ofs].id = id; + state->refs[new_ofs].insn_idx = insn_idx; + + return id; +} + +/* release function corresponding to acquire_reference_state(). Idempotent. */ +static int __release_reference_state(struct bpf_func_state *state, int ptr_id) +{ + int i, last_idx; + + if (!ptr_id) + return -EFAULT; + + last_idx = state->acquired_refs - 1; + for (i = 0; i < state->acquired_refs; i++) { + if (state->refs[i].id == ptr_id) { + if (last_idx && i != last_idx) + memcpy(&state->refs[i], &state->refs[last_idx], + sizeof(*state->refs)); + memset(&state->refs[last_idx], 0, sizeof(*state->refs)); + state->acquired_refs--; + return 0; + } + } + return -EFAULT; +} + +/* variation on the above for cases where we expect that there must be an + * outstanding reference for the specified ptr_id. + */ +static int release_reference_state(struct bpf_verifier_env *env, int ptr_id) +{ + struct bpf_func_state *state = cur_func(env); + int err; + + err = __release_reference_state(state, ptr_id); + if (WARN_ON_ONCE(err != 0)) + verbose(env, "verifier internal error: can't release reference\n"); + return err; +} + +static int transfer_reference_state(struct bpf_func_state *dst, + struct bpf_func_state *src) +{ + int err = realloc_reference_state(dst, src->acquired_refs, false); + if (err) + return err; + err = copy_reference_state(dst, src); + if (err) + return err; + return 0; } static void free_func_state(struct bpf_func_state *state) { if (!state) return; + kfree(state->refs); kfree(state->stack); kfree(state); } @@ -487,10 +619,14 @@ static int copy_func_state(struct bpf_func_state *dst, { int err; - err = realloc_func_state(dst, src->allocated_stack, false); + err = realloc_func_state(dst, src->allocated_stack, src->acquired_refs, + false); + if (err) + return err; + memcpy(dst, src, offsetof(struct bpf_func_state, acquired_refs)); + err = copy_reference_state(dst, src); if (err) return err; - memcpy(dst, src, offsetof(struct bpf_func_state, allocated_stack)); return copy_stack_state(dst, src); } @@ -1015,7 +1151,7 @@ static int check_stack_write(struct bpf_verifier_env *env, enum bpf_reg_type type; err = realloc_func_state(state, round_up(slot + 1, BPF_REG_SIZE), - true); + state->acquired_refs, true); if (err) return err; /* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0, @@ -1399,7 +1535,8 @@ static bool is_ctx_reg(struct bpf_verifier_env *env, int regno) { const struct bpf_reg_state *reg = cur_regs(env) + regno; - return reg->type == PTR_TO_CTX; + return reg->type == PTR_TO_CTX || + reg->type == PTR_TO_SOCKET; } static bool is_pkt_reg(struct bpf_verifier_env *env, int regno) @@ -2003,6 +2140,12 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, expected_type = PTR_TO_SOCKET; if (type != expected_type) goto err_type; + if (meta->ptr_id || !reg->id) { + verbose(env, "verifier internal error: mismatched references meta=%d, reg=%d\n", + meta->ptr_id, reg->id); + return -EFAULT; + } + meta->ptr_id = reg->id; } else if (arg_type_is_mem_ptr(arg_type)) { expected_type = PTR_TO_STACK; /* One exception here. In case function allows for NULL to be @@ -2292,10 +2435,32 @@ static bool check_arg_pair_ok(const struct bpf_func_proto *fn) return true; } +static bool check_refcount_ok(const struct bpf_func_proto *fn) +{ + int count = 0; + + if (arg_type_is_refcounted(fn->arg1_type)) + count++; + if (arg_type_is_refcounted(fn->arg2_type)) + count++; + if (arg_type_is_refcounted(fn->arg3_type)) + count++; + if (arg_type_is_refcounted(fn->arg4_type)) + count++; + if (arg_type_is_refcounted(fn->arg5_type)) + count++; + + /* We only support one arg being unreferenced at the moment, + * which is sufficient for the helper functions we have right now. + */ + return count <= 1; +} + static int check_func_proto(const struct bpf_func_proto *fn) { return check_raw_mode_ok(fn) && - check_arg_pair_ok(fn) ? 0 : -EINVAL; + check_arg_pair_ok(fn) && + check_refcount_ok(fn) ? 0 : -EINVAL; } /* Packet data might have moved, any old PTR_TO_PACKET[_META,_END] @@ -2328,12 +2493,45 @@ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) __clear_all_pkt_pointers(env, vstate->frame[i]); } +static void release_reg_references(struct bpf_verifier_env *env, + struct bpf_func_state *state, int id) +{ + struct bpf_reg_state *regs = state->regs, *reg; + int i; + + for (i = 0; i < MAX_BPF_REG; i++) + if (regs[i].id == id) + mark_reg_unknown(env, regs, i); + + bpf_for_each_spilled_reg(i, state, reg) { + if (!reg) + continue; + if (reg_is_refcounted(reg) && reg->id == id) + __mark_reg_unknown(reg); + } +} + +/* The pointer with the specified id has released its reference to kernel + * resources. Identify all copies of the same pointer and clear the reference. + */ +static int release_reference(struct bpf_verifier_env *env, + struct bpf_call_arg_meta *meta) +{ + struct bpf_verifier_state *vstate = env->cur_state; + int i; + + for (i = 0; i <= vstate->curframe; i++) + release_reg_references(env, vstate->frame[i], meta->ptr_id); + + return release_reference_state(env, meta->ptr_id); +} + static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx) { struct bpf_verifier_state *state = env->cur_state; struct bpf_func_state *caller, *callee; - int i, subprog, target_insn; + int i, err, subprog, target_insn; if (state->curframe + 1 >= MAX_CALL_FRAMES) { verbose(env, "the call stack of %d frames is too deep\n", @@ -2371,6 +2569,11 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, state->curframe + 1 /* frameno within this callchain */, subprog /* subprog number within this prog */); + /* Transfer references to the callee */ + err = transfer_reference_state(callee, caller); + if (err) + return err; + /* copy r1 - r5 args that callee can access. The copy includes parent * pointers, which connects us up to the liveness chain */ @@ -2403,6 +2606,7 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) struct bpf_verifier_state *state = env->cur_state; struct bpf_func_state *caller, *callee; struct bpf_reg_state *r0; + int err; callee = state->frame[state->curframe]; r0 = &callee->regs[BPF_REG_0]; @@ -2422,6 +2626,11 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) /* return to the caller whatever r0 had in the callee */ caller->regs[BPF_REG_0] = *r0; + /* Transfer references to the caller */ + err = transfer_reference_state(caller, callee); + if (err) + return err; + *insn_idx = callee->callsite + 1; if (env->log.level) { verbose(env, "returning from callee:\n"); @@ -2478,6 +2687,18 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, return 0; } +static int check_reference_leak(struct bpf_verifier_env *env) +{ + struct bpf_func_state *state = cur_func(env); + int i; + + for (i = 0; i < state->acquired_refs; i++) { + verbose(env, "Unreleased reference id=%d alloc_insn=%d\n", + state->refs[i].id, state->refs[i].insn_idx); + } + return state->acquired_refs ? -EINVAL : 0; +} + static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn_idx) { const struct bpf_func_proto *fn = NULL; @@ -2556,6 +2777,18 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn return err; } + if (func_id == BPF_FUNC_tail_call) { + err = check_reference_leak(env); + if (err) { + verbose(env, "tail_call would lead to reference leak\n"); + return err; + } + } else if (is_release_function(func_id)) { + err = release_reference(env, &meta); + if (err) + return err; + } + regs = cur_regs(env); /* check that flags argument in get_local_storage(map, flags) is 0, @@ -2599,9 +2832,12 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn regs[BPF_REG_0].map_ptr = meta.map_ptr; regs[BPF_REG_0].id = ++env->id_gen; } else if (fn->ret_type == RET_PTR_TO_SOCKET_OR_NULL) { + int id = acquire_reference_state(env, insn_idx); + if (id < 0) + return id; mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_SOCKET_OR_NULL; - regs[BPF_REG_0].id = ++env->id_gen; + regs[BPF_REG_0].id = id; } else { verbose(env, "unknown return type %d of func %s#%d\n", fn->ret_type, func_id_name(func_id), func_id); @@ -3665,7 +3901,8 @@ static void reg_combine_min_max(struct bpf_reg_state *true_src, } } -static void mark_ptr_or_null_reg(struct bpf_reg_state *reg, u32 id, +static void mark_ptr_or_null_reg(struct bpf_func_state *state, + struct bpf_reg_state *reg, u32 id, bool is_null) { if (reg_type_may_be_null(reg->type) && reg->id == id) { @@ -3691,11 +3928,13 @@ static void mark_ptr_or_null_reg(struct bpf_reg_state *reg, u32 id, } else if (reg->type == PTR_TO_SOCKET_OR_NULL) { reg->type = PTR_TO_SOCKET; } - /* We don't need id from this point onwards anymore, thus we - * should better reset it, so that state pruning has chances - * to take effect. - */ - reg->id = 0; + if (is_null || !reg_is_refcounted(reg)) { + /* We don't need id from this point onwards anymore, + * thus we should better reset it, so that state + * pruning has chances to take effect. + */ + reg->id = 0; + } } } @@ -3710,15 +3949,18 @@ static void mark_ptr_or_null_regs(struct bpf_verifier_state *vstate, u32 regno, u32 id = regs[regno].id; int i, j; + if (reg_is_refcounted_or_null(®s[regno]) && is_null) + __release_reference_state(state, id); + for (i = 0; i < MAX_BPF_REG; i++) - mark_ptr_or_null_reg(®s[i], id, is_null); + mark_ptr_or_null_reg(state, ®s[i], id, is_null); for (j = 0; j <= vstate->curframe; j++) { state = vstate->frame[j]; bpf_for_each_spilled_reg(i, state, reg) { if (!reg) continue; - mark_ptr_or_null_reg(reg, id, is_null); + mark_ptr_or_null_reg(state, reg, id, is_null); } } } @@ -4050,6 +4292,16 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) if (err) return err; + /* Disallow usage of BPF_LD_[ABS|IND] with reference tracking, as + * gen_ld_abs() may terminate the program at runtime, leading to + * reference leak. + */ + err = check_reference_leak(env); + if (err) { + verbose(env, "BPF_LD_[ABS|IND] cannot be mixed with socket references\n"); + return err; + } + if (regs[BPF_REG_6].type != PTR_TO_CTX) { verbose(env, "at the time of BPF_LD_ABS|IND R6 != pointer to skb\n"); @@ -4542,6 +4794,14 @@ static bool stacksafe(struct bpf_func_state *old, return true; } +static bool refsafe(struct bpf_func_state *old, struct bpf_func_state *cur) +{ + if (old->acquired_refs != cur->acquired_refs) + return false; + return !memcmp(old->refs, cur->refs, + sizeof(*old->refs) * old->acquired_refs); +} + /* compare two verifier states * * all states stored in state_list are known to be valid, since @@ -4587,6 +4847,9 @@ static bool func_states_equal(struct bpf_func_state *old, if (!stacksafe(old, cur, idmap)) goto out_free; + + if (!refsafe(old, cur)) + goto out_free; ret = true; out_free: kfree(idmap); @@ -4868,6 +5131,7 @@ static int do_check(struct bpf_verifier_env *env) regs = cur_regs(env); env->insn_aux_data[insn_idx].seen = true; + if (class == BPF_ALU || class == BPF_ALU64) { err = check_alu_op(env, insn); if (err) @@ -5032,6 +5296,10 @@ static int do_check(struct bpf_verifier_env *env) continue; } + err = check_reference_leak(env); + if (err) + return err; + /* eBPF calling convetion is such that R0 is used * to return the value from eBPF program. * Make sure that it's readable at this time -- cgit v1.2.3 From 401b25aa1a75e7fe4e3202a6336604269697d705 Mon Sep 17 00:00:00 2001 From: Souptick Joarder Date: Tue, 2 Oct 2018 22:20:50 -0400 Subject: ext4: convert fault handler to use vm_fault_t type Return type of ext4_page_mkwrite and ext4_filemap_fault are changed to use vm_fault_t type. With this patch all the callers of block_page_mkwrite_return() are changed to handle vm_fault_t. So converting the return type of block_page_mkwrite_return() to vm_fault_t. Signed-off-by: Souptick Joarder Signed-off-by: Theodore Ts'o Reviewed-by: Matthew Wilcox --- fs/ext4/ext4.h | 4 ++-- fs/ext4/inode.c | 29 +++++++++++++++-------------- include/linux/buffer_head.h | 2 +- 3 files changed, 18 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 57cbc98d730f..86e1bacac757 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2487,8 +2487,8 @@ extern int ext4_writepage_trans_blocks(struct inode *); extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks); extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode, loff_t lstart, loff_t lend); -extern int ext4_page_mkwrite(struct vm_fault *vmf); -extern int ext4_filemap_fault(struct vm_fault *vmf); +extern vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf); +extern vm_fault_t ext4_filemap_fault(struct vm_fault *vmf); extern qsize_t *ext4_get_reserved_space(struct inode *inode); extern int ext4_get_projid(struct inode *inode, kprojid_t *projid); extern void ext4_da_release_space(struct inode *inode, int to_free); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 9b69f88bdacc..c3d9a42c561e 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -6184,13 +6184,14 @@ static int ext4_bh_unmapped(handle_t *handle, struct buffer_head *bh) return !buffer_mapped(bh); } -int ext4_page_mkwrite(struct vm_fault *vmf) +vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct page *page = vmf->page; loff_t size; unsigned long len; - int ret; + int err; + vm_fault_t ret; struct file *file = vma->vm_file; struct inode *inode = file_inode(file); struct address_space *mapping = inode->i_mapping; @@ -6203,8 +6204,8 @@ int ext4_page_mkwrite(struct vm_fault *vmf) down_read(&EXT4_I(inode)->i_mmap_sem); - ret = ext4_convert_inline_data(inode); - if (ret) + err = ext4_convert_inline_data(inode); + if (err) goto out_ret; /* Delalloc case is easy... */ @@ -6212,9 +6213,9 @@ int ext4_page_mkwrite(struct vm_fault *vmf) !ext4_should_journal_data(inode) && !ext4_nonda_switch(inode->i_sb)) { do { - ret = block_page_mkwrite(vma, vmf, + err = block_page_mkwrite(vma, vmf, ext4_da_get_block_prep); - } while (ret == -ENOSPC && + } while (err == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)); goto out_ret; } @@ -6259,8 +6260,8 @@ retry_alloc: ret = VM_FAULT_SIGBUS; goto out; } - ret = block_page_mkwrite(vma, vmf, get_block); - if (!ret && ext4_should_journal_data(inode)) { + err = block_page_mkwrite(vma, vmf, get_block); + if (!err && ext4_should_journal_data(inode)) { if (ext4_walk_page_buffers(handle, page_buffers(page), 0, PAGE_SIZE, NULL, do_journal_get_write_access)) { unlock_page(page); @@ -6271,24 +6272,24 @@ retry_alloc: ext4_set_inode_state(inode, EXT4_STATE_JDATA); } ext4_journal_stop(handle); - if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) + if (err == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry_alloc; out_ret: - ret = block_page_mkwrite_return(ret); + ret = block_page_mkwrite_return(err); out: up_read(&EXT4_I(inode)->i_mmap_sem); sb_end_pagefault(inode->i_sb); return ret; } -int ext4_filemap_fault(struct vm_fault *vmf) +vm_fault_t ext4_filemap_fault(struct vm_fault *vmf) { struct inode *inode = file_inode(vmf->vma->vm_file); - int err; + vm_fault_t ret; down_read(&EXT4_I(inode)->i_mmap_sem); - err = filemap_fault(vmf); + ret = filemap_fault(vmf); up_read(&EXT4_I(inode)->i_mmap_sem); - return err; + return ret; } diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 96225a77c112..7b73ef7f902d 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -242,7 +242,7 @@ int block_commit_write(struct page *page, unsigned from, unsigned to); int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, get_block_t get_block); /* Convert errno to return value from ->page_mkwrite() call */ -static inline int block_page_mkwrite_return(int err) +static inline vm_fault_t block_page_mkwrite_return(int err) { if (err == 0) return VM_FAULT_LOCKED; -- cgit v1.2.3 From f3edc2dbe0ad0bbbd8450cd37328f99acf215fd8 Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Mon, 1 Oct 2018 17:02:43 +0100 Subject: net: usbnet: make driver_info const The driver_info field that is used for describing each of the usb-net drivers using the usbnet.c core all declare their information as const and the usbnet.c itself does not try and modify the struct. It is therefore a good idea to make this const in the usbnet.c structure in case anyone tries to modify it. Signed-off-by: Ben Dooks Signed-off-by: Ben Dooks Signed-off-by: David S. Miller --- drivers/net/usb/usbnet.c | 12 ++++++------ include/linux/usb/usbnet.h | 2 +- 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 73aa33364d80..504282af27e5 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -802,7 +802,7 @@ static void usbnet_terminate_urbs(struct usbnet *dev) int usbnet_stop (struct net_device *net) { struct usbnet *dev = netdev_priv(net); - struct driver_info *info = dev->driver_info; + const struct driver_info *info = dev->driver_info; int retval, pm, mpn; clear_bit(EVENT_DEV_OPEN, &dev->flags); @@ -865,7 +865,7 @@ int usbnet_open (struct net_device *net) { struct usbnet *dev = netdev_priv(net); int retval; - struct driver_info *info = dev->driver_info; + const struct driver_info *info = dev->driver_info; if ((retval = usb_autopm_get_interface(dev->intf)) < 0) { netif_info(dev, ifup, dev->net, @@ -1205,7 +1205,7 @@ fail_lowmem: } if (test_bit (EVENT_LINK_RESET, &dev->flags)) { - struct driver_info *info = dev->driver_info; + const struct driver_info *info = dev->driver_info; int retval = 0; clear_bit (EVENT_LINK_RESET, &dev->flags); @@ -1353,7 +1353,7 @@ netdev_tx_t usbnet_start_xmit (struct sk_buff *skb, unsigned int length; struct urb *urb = NULL; struct skb_data *entry; - struct driver_info *info = dev->driver_info; + const struct driver_info *info = dev->driver_info; unsigned long flags; int retval; @@ -1647,7 +1647,7 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) struct usbnet *dev; struct net_device *net; struct usb_host_interface *interface; - struct driver_info *info; + const struct driver_info *info; struct usb_device *xdev; int status; const char *name; @@ -1663,7 +1663,7 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) } name = udev->dev.driver->name; - info = (struct driver_info *) prod->driver_info; + info = (const struct driver_info *) prod->driver_info; if (!info) { dev_dbg (&udev->dev, "blacklisted by %s\n", name); return -ENODEV; diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index e2ec3582e549..d8860f2d0976 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -28,7 +28,7 @@ struct usbnet { /* housekeeping */ struct usb_device *udev; struct usb_interface *intf; - struct driver_info *driver_info; + const struct driver_info *driver_info; const char *driver_name; void *driver_priv; wait_queue_head_t wait; -- cgit v1.2.3 From 2130b789b3ef6a518b9c9c6f245642620e2b0c0c Mon Sep 17 00:00:00 2001 From: Julien Thierry Date: Tue, 28 Aug 2018 16:51:18 +0100 Subject: irqchip/gic: Unify GIC priority definitions LPIs use the same priority value as other GIC interrupts. Make the GIC default priority definition visible to ITS implementation and use this same definition for LPI priorities. Tested-by: Daniel Thompson Signed-off-by: Julien Thierry Cc: Thomas Gleixner Cc: Jason Cooper Cc: Marc Zyngier Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-gic-v3-its.c | 2 +- include/linux/irqchip/arm-gic-common.h | 6 ++++++ include/linux/irqchip/arm-gic.h | 5 ----- 3 files changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 4251d2d8e6e7..db20e992a40f 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -68,7 +68,7 @@ static u32 lpi_id_bits; #define LPI_PROPBASE_SZ ALIGN(BIT(LPI_NRBITS), SZ_64K) #define LPI_PENDBASE_SZ ALIGN(BIT(LPI_NRBITS) / 8, SZ_64K) -#define LPI_PROP_DEFAULT_PRIO 0xa0 +#define LPI_PROP_DEFAULT_PRIO GICD_INT_DEF_PRI /* * Collection structure - just an ID, and a redistributor address to diff --git a/include/linux/irqchip/arm-gic-common.h b/include/linux/irqchip/arm-gic-common.h index 0a83b4379f34..9a1a479a2bf4 100644 --- a/include/linux/irqchip/arm-gic-common.h +++ b/include/linux/irqchip/arm-gic-common.h @@ -13,6 +13,12 @@ #include #include +#define GICD_INT_DEF_PRI 0xa0 +#define GICD_INT_DEF_PRI_X4 ((GICD_INT_DEF_PRI << 24) |\ + (GICD_INT_DEF_PRI << 16) |\ + (GICD_INT_DEF_PRI << 8) |\ + GICD_INT_DEF_PRI) + enum gic_type { GIC_V2, GIC_V3, diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h index 6c4aaf04046c..626179077bb0 100644 --- a/include/linux/irqchip/arm-gic.h +++ b/include/linux/irqchip/arm-gic.h @@ -65,11 +65,6 @@ #define GICD_INT_EN_CLR_X32 0xffffffff #define GICD_INT_EN_SET_SGI 0x0000ffff #define GICD_INT_EN_CLR_PPI 0xffff0000 -#define GICD_INT_DEF_PRI 0xa0 -#define GICD_INT_DEF_PRI_X4 ((GICD_INT_DEF_PRI << 24) |\ - (GICD_INT_DEF_PRI << 16) |\ - (GICD_INT_DEF_PRI << 8) |\ - GICD_INT_DEF_PRI) #define GICD_IIDR_IMPLEMENTER_SHIFT 0 #define GICD_IIDR_IMPLEMENTER_MASK (0xfff << GICD_IIDR_IMPLEMENTER_SHIFT) -- cgit v1.2.3 From 9414229c9c53d3604032aa80f3d2e9ba5770cd4a Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Mon, 24 Sep 2018 06:08:07 +0200 Subject: clocksource: Remove obsolete CLOCKSOURCE_OF_DECLARE The macro CLOCKSOURCE_OF_DECLARE was renamed more TIMER_OF_DECLARE, and we kept an alias CLOCKSOURCE_OF_DECLARE in order to smooth the transition for drivers. This change was done 1.5 year ago, we can reasonably remove this backward compatible macro as it is no longer used anywhere. Signed-off-by: Daniel Lezcano --- include/linux/clocksource.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 308918928767..4c58c1e64080 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -257,9 +257,6 @@ extern int clocksource_i8253_init(void); #define TIMER_OF_DECLARE(name, compat, fn) \ OF_DECLARE_1_RET(timer, name, compat, fn) -#define CLOCKSOURCE_OF_DECLARE(name, compat, fn) \ - TIMER_OF_DECLARE(name, compat, fn) - #ifdef CONFIG_TIMER_PROBE extern void timer_probe(void); #else -- cgit v1.2.3 From 16fc087b9cb22c9a97307cc24a5413d0df68fe11 Mon Sep 17 00:00:00 2001 From: Yashaswini Raghuram Prathivadi Bhayankaram Date: Fri, 10 Aug 2018 00:17:44 -0700 Subject: virtchnl: Added support to exchange additional speed values Introduced a new virtchnl capability flag and a struct to support exchange of additional supported speeds. Signed-off-by: Yashaswini Raghuram Prathivadi Bhayankaram Signed-off-by: Anirudh Venkataramanan Signed-off-by: Jeff Kirsher --- include/linux/avf/virtchnl.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index b41f7bc958ef..2c9756bd9c4c 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -252,6 +252,8 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource); #define VIRTCHNL_VF_OFFLOAD_RX_ENCAP_CSUM 0X00400000 #define VIRTCHNL_VF_OFFLOAD_ADQ 0X00800000 +/* Define below the capability flags that are not offloads */ +#define VIRTCHNL_VF_CAP_ADV_LINK_SPEED 0x00000080 #define VF_BASE_MODE_OFFLOADS (VIRTCHNL_VF_OFFLOAD_L2 | \ VIRTCHNL_VF_OFFLOAD_VLAN | \ VIRTCHNL_VF_OFFLOAD_RSS_PF) @@ -596,10 +598,23 @@ enum virtchnl_event_codes { struct virtchnl_pf_event { enum virtchnl_event_codes event; union { + /* If the PF driver does not support the new speed reporting + * capabilities then use link_event else use link_event_adv to + * get the speed and link information. The ability to understand + * new speeds is indicated by setting the capability flag + * VIRTCHNL_VF_CAP_ADV_LINK_SPEED in vf_cap_flags parameter + * in virtchnl_vf_resource struct and can be used to determine + * which link event struct to use below. + */ struct { enum virtchnl_link_speed link_speed; bool link_status; } link_event; + struct { + /* link_speed provided in Mbps */ + u32 link_speed; + u8 link_status; + } link_event_adv; } event_data; int severity; -- cgit v1.2.3 From 4cd2e0e70af6897ca2247fa1ffb1553ca16b4903 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 18 Apr 2018 17:30:19 -0500 Subject: signal: Introduce copy_siginfo_from_user and use it's return value In preparation for using a smaller version of siginfo in the kernel introduce copy_siginfo_from_user and use it when siginfo is copied from userspace. Make the pattern for using copy_siginfo_from_user and copy_siginfo_from_user32 to capture the return value and return that value on error. This is a necessary prerequisite for using a smaller siginfo in the kernel than the kernel exports to userspace. Signed-off-by: "Eric W. Biederman" --- include/linux/signal.h | 1 + kernel/ptrace.c | 12 +++++------- kernel/signal.c | 25 ++++++++++++++++--------- 3 files changed, 22 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index 3d4cd5db30a9..de94c159bfb0 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -22,6 +22,7 @@ static inline void clear_siginfo(struct siginfo *info) } int copy_siginfo_to_user(struct siginfo __user *to, const struct siginfo *from); +int copy_siginfo_from_user(struct siginfo *to, const struct siginfo __user *from); enum siginfo_layout { SIL_KILL, diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 45f77a1b9c97..a807ff5cc1a9 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -919,9 +919,8 @@ int ptrace_request(struct task_struct *child, long request, break; case PTRACE_SETSIGINFO: - if (copy_from_user(&siginfo, datavp, sizeof siginfo)) - ret = -EFAULT; - else + ret = copy_siginfo_from_user(&siginfo, datavp); + if (!ret) ret = ptrace_setsiginfo(child, &siginfo); break; @@ -1215,10 +1214,9 @@ int compat_ptrace_request(struct task_struct *child, compat_long_t request, break; case PTRACE_SETSIGINFO: - if (copy_siginfo_from_user32( - &siginfo, (struct compat_siginfo __user *) datap)) - ret = -EFAULT; - else + ret = copy_siginfo_from_user32( + &siginfo, (struct compat_siginfo __user *) datap); + if (!ret) ret = ptrace_setsiginfo(child, &siginfo); break; #ifdef CONFIG_HAVE_ARCH_TRACEHOOK diff --git a/kernel/signal.c b/kernel/signal.c index debb485a76db..c0e289e62d77 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2896,6 +2896,13 @@ int copy_siginfo_to_user(siginfo_t __user *to, const siginfo_t *from) return 0; } +int copy_siginfo_from_user(siginfo_t *to, const siginfo_t __user *from) +{ + if (copy_from_user(to, from, sizeof(struct siginfo))) + return -EFAULT; + return 0; +} + #ifdef CONFIG_COMPAT int copy_siginfo_to_user32(struct compat_siginfo __user *to, const struct siginfo *from) @@ -3323,8 +3330,9 @@ SYSCALL_DEFINE3(rt_sigqueueinfo, pid_t, pid, int, sig, siginfo_t __user *, uinfo) { siginfo_t info; - if (copy_from_user(&info, uinfo, sizeof(siginfo_t))) - return -EFAULT; + int ret = copy_siginfo_from_user(&info, uinfo); + if (unlikely(ret)) + return ret; return do_rt_sigqueueinfo(pid, sig, &info); } @@ -3365,10 +3373,9 @@ SYSCALL_DEFINE4(rt_tgsigqueueinfo, pid_t, tgid, pid_t, pid, int, sig, siginfo_t __user *, uinfo) { siginfo_t info; - - if (copy_from_user(&info, uinfo, sizeof(siginfo_t))) - return -EFAULT; - + int ret = copy_siginfo_from_user(&info, uinfo); + if (unlikely(ret)) + return ret; return do_rt_tgsigqueueinfo(tgid, pid, sig, &info); } @@ -3380,9 +3387,9 @@ COMPAT_SYSCALL_DEFINE4(rt_tgsigqueueinfo, struct compat_siginfo __user *, uinfo) { siginfo_t info; - - if (copy_siginfo_from_user32(&info, uinfo)) - return -EFAULT; + int ret = copy_siginfo_from_user32(&info, uinfo); + if (unlikely(ret)) + return ret; return do_rt_tgsigqueueinfo(tgid, pid, sig, &info); } #endif -- cgit v1.2.3 From ae7795bc6187a15ec51cf258abae656a625f9980 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 25 Sep 2018 11:27:20 +0200 Subject: signal: Distinguish between kernel_siginfo and siginfo Linus recently observed that if we did not worry about the padding member in struct siginfo it is only about 48 bytes, and 48 bytes is much nicer than 128 bytes for allocating on the stack and copying around in the kernel. The obvious thing of only adding the padding when userspace is including siginfo.h won't work as there are sigframe definitions in the kernel that embed struct siginfo. So split siginfo in two; kernel_siginfo and siginfo. Keeping the traditional name for the userspace definition. While the version that is used internally to the kernel and ultimately will not be padded to 128 bytes is called kernel_siginfo. The definition of struct kernel_siginfo I have put in include/signal_types.h A set of buildtime checks has been added to verify the two structures have the same field offsets. To make it easy to verify the change kernel_siginfo retains the same size as siginfo. The reduction in size comes in a following change. Signed-off-by: "Eric W. Biederman" --- arch/x86/include/asm/compat.h | 2 +- drivers/usb/core/devio.c | 4 +- fs/binfmt_elf.c | 6 +- fs/coredump.c | 2 +- fs/fcntl.c | 2 +- fs/signalfd.c | 6 +- include/linux/binfmts.h | 2 +- include/linux/compat.h | 4 +- include/linux/coredump.h | 4 +- include/linux/lsm_hooks.h | 4 +- include/linux/posix-timers.h | 2 +- include/linux/ptrace.h | 2 +- include/linux/sched.h | 2 +- include/linux/sched/signal.h | 18 ++--- include/linux/security.h | 6 +- include/linux/signal.h | 15 +++-- include/linux/signal_types.h | 11 ++- include/trace/events/signal.h | 4 +- ipc/mqueue.c | 2 +- kernel/ptrace.c | 10 +-- kernel/seccomp.c | 6 +- kernel/signal.c | 151 +++++++++++++++++++++++++++--------------- kernel/time/posix-timers.c | 2 +- security/apparmor/lsm.c | 2 +- security/security.c | 2 +- security/selinux/hooks.c | 2 +- security/smack/smack_lsm.c | 2 +- 27 files changed, 165 insertions(+), 110 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h index fb97cf7c4137..a0f46bdd9f24 100644 --- a/arch/x86/include/asm/compat.h +++ b/arch/x86/include/asm/compat.h @@ -240,6 +240,6 @@ static inline bool in_compat_syscall(void) struct compat_siginfo; int __copy_siginfo_to_user32(struct compat_siginfo __user *to, - const siginfo_t *from, bool x32_ABI); + const kernel_siginfo_t *from, bool x32_ABI); #endif /* _ASM_X86_COMPAT_H */ diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index 6ce77b33da61..c260ea8808b0 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -582,7 +582,7 @@ static void async_completed(struct urb *urb) { struct async *as = urb->context; struct usb_dev_state *ps = as->ps; - struct siginfo sinfo; + struct kernel_siginfo sinfo; struct pid *pid = NULL; const struct cred *cred = NULL; unsigned long flags; @@ -2599,7 +2599,7 @@ const struct file_operations usbdev_file_operations = { static void usbdev_remove(struct usb_device *udev) { struct usb_dev_state *ps; - struct siginfo sinfo; + struct kernel_siginfo sinfo; while (!list_empty(&udev->filelist)) { ps = list_entry(udev->filelist.next, struct usb_dev_state, list); diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index efae2fb0930a..54207327f98f 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1580,7 +1580,7 @@ static void fill_auxv_note(struct memelfnote *note, struct mm_struct *mm) } static void fill_siginfo_note(struct memelfnote *note, user_siginfo_t *csigdata, - const siginfo_t *siginfo) + const kernel_siginfo_t *siginfo) { mm_segment_t old_fs = get_fs(); set_fs(KERNEL_DS); @@ -1782,7 +1782,7 @@ static int fill_thread_core_info(struct elf_thread_core_info *t, static int fill_note_info(struct elfhdr *elf, int phdrs, struct elf_note_info *info, - const siginfo_t *siginfo, struct pt_regs *regs) + const kernel_siginfo_t *siginfo, struct pt_regs *regs) { struct task_struct *dump_task = current; const struct user_regset_view *view = task_user_regset_view(dump_task); @@ -2031,7 +2031,7 @@ static int elf_note_info_init(struct elf_note_info *info) static int fill_note_info(struct elfhdr *elf, int phdrs, struct elf_note_info *info, - const siginfo_t *siginfo, struct pt_regs *regs) + const kernel_siginfo_t *siginfo, struct pt_regs *regs) { struct list_head *t; struct core_thread *ct; diff --git a/fs/coredump.c b/fs/coredump.c index 1e2c87acac9b..e42e17e55bfd 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -536,7 +536,7 @@ static int umh_pipe_setup(struct subprocess_info *info, struct cred *new) return err; } -void do_coredump(const siginfo_t *siginfo) +void do_coredump(const kernel_siginfo_t *siginfo) { struct core_state core_state; struct core_name cn; diff --git a/fs/fcntl.c b/fs/fcntl.c index 4137d96534a6..083185174c6d 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -735,7 +735,7 @@ static void send_sigio_to_task(struct task_struct *p, return; switch (signum) { - siginfo_t si; + kernel_siginfo_t si; default: /* Queue a rt signal with the appropriate fd as its value. We use SI_SIGIO as the source, not diff --git a/fs/signalfd.c b/fs/signalfd.c index 4fcd1498acf5..757afc7c5895 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -79,7 +79,7 @@ static __poll_t signalfd_poll(struct file *file, poll_table *wait) * Copied from copy_siginfo_to_user() in kernel/signal.c */ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo, - siginfo_t const *kinfo) + kernel_siginfo_t const *kinfo) { struct signalfd_siginfo new; @@ -163,7 +163,7 @@ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo, return sizeof(*uinfo); } -static ssize_t signalfd_dequeue(struct signalfd_ctx *ctx, siginfo_t *info, +static ssize_t signalfd_dequeue(struct signalfd_ctx *ctx, kernel_siginfo_t *info, int nonblock) { ssize_t ret; @@ -215,7 +215,7 @@ static ssize_t signalfd_read(struct file *file, char __user *buf, size_t count, struct signalfd_siginfo __user *siginfo; int nonblock = file->f_flags & O_NONBLOCK; ssize_t ret, total = 0; - siginfo_t info; + kernel_siginfo_t info; count /= sizeof(struct signalfd_siginfo); if (!count) diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index c05f24fac4f6..e9f5fe69df31 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -78,7 +78,7 @@ struct linux_binprm { /* Function parameter for binfmt->coredump */ struct coredump_params { - const siginfo_t *siginfo; + const kernel_siginfo_t *siginfo; struct pt_regs *regs; struct file *file; unsigned long limit; diff --git a/include/linux/compat.h b/include/linux/compat.h index 1a3c4f37e908..4565d65b1776 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -452,8 +452,8 @@ long compat_get_bitmap(unsigned long *mask, const compat_ulong_t __user *umask, unsigned long bitmap_size); long compat_put_bitmap(compat_ulong_t __user *umask, unsigned long *mask, unsigned long bitmap_size); -int copy_siginfo_from_user32(siginfo_t *to, const struct compat_siginfo __user *from); -int copy_siginfo_to_user32(struct compat_siginfo __user *to, const siginfo_t *from); +int copy_siginfo_from_user32(kernel_siginfo_t *to, const struct compat_siginfo __user *from); +int copy_siginfo_to_user32(struct compat_siginfo __user *to, const kernel_siginfo_t *from); int get_compat_sigevent(struct sigevent *event, const struct compat_sigevent __user *u_event); diff --git a/include/linux/coredump.h b/include/linux/coredump.h index 207aed96a5b7..abf4b4e65dbb 100644 --- a/include/linux/coredump.h +++ b/include/linux/coredump.h @@ -17,9 +17,9 @@ extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr); extern int dump_align(struct coredump_params *cprm, int align); extern void dump_truncate(struct coredump_params *cprm); #ifdef CONFIG_COREDUMP -extern void do_coredump(const siginfo_t *siginfo); +extern void do_coredump(const kernel_siginfo_t *siginfo); #else -static inline void do_coredump(const siginfo_t *siginfo) {} +static inline void do_coredump(const kernel_siginfo_t *siginfo) {} #endif #endif /* _LINUX_COREDUMP_H */ diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 97a020c616ad..bb40f6d34163 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -672,7 +672,7 @@ * Return 0 if permission is granted. * @task_kill: * Check permission before sending signal @sig to @p. @info can be NULL, - * the constant 1, or a pointer to a siginfo structure. If @info is 1 or + * the constant 1, or a pointer to a kernel_siginfo structure. If @info is 1 or * SI_FROMKERNEL(info) is true, then the signal should be viewed as coming * from the kernel and should typically be permitted. * SIGIO signals are handled separately by the send_sigiotask hook in @@ -1606,7 +1606,7 @@ union security_list_options { int (*task_setscheduler)(struct task_struct *p); int (*task_getscheduler)(struct task_struct *p); int (*task_movememory)(struct task_struct *p); - int (*task_kill)(struct task_struct *p, struct siginfo *info, + int (*task_kill)(struct task_struct *p, struct kernel_siginfo *info, int sig, const struct cred *cred); int (*task_prctl)(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5); diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index ee7e987ea1b4..e96581ca7c9d 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -126,5 +126,5 @@ void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx, void update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new); -void posixtimer_rearm(struct siginfo *info); +void posixtimer_rearm(struct kernel_siginfo *info); #endif diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 1de2235511c8..d19a795100da 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -341,7 +341,7 @@ extern void user_single_step_report(struct pt_regs *regs); #else static inline void user_single_step_report(struct pt_regs *regs) { - siginfo_t info; + kernel_siginfo_t info; clear_siginfo(&info); info.si_signo = SIGTRAP; info.si_errno = 0; diff --git a/include/linux/sched.h b/include/linux/sched.h index 977cb57d7bc9..2ba88082e1ef 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -960,7 +960,7 @@ struct task_struct { /* Ptrace state: */ unsigned long ptrace_message; - siginfo_t *last_siginfo; + kernel_siginfo_t *last_siginfo; struct task_io_accounting ioac; #ifdef CONFIG_TASK_XACCT diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 9e07f3521549..13789d10a50e 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -270,12 +270,12 @@ static inline int signal_group_exit(const struct signal_struct *sig) extern void flush_signals(struct task_struct *); extern void ignore_signals(struct task_struct *); extern void flush_signal_handlers(struct task_struct *, int force_default); -extern int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info); +extern int dequeue_signal(struct task_struct *tsk, sigset_t *mask, kernel_siginfo_t *info); static inline int kernel_dequeue_signal(void) { struct task_struct *tsk = current; - siginfo_t __info; + kernel_siginfo_t __info; int ret; spin_lock_irq(&tsk->sighand->siglock); @@ -322,12 +322,12 @@ int force_sig_pkuerr(void __user *addr, u32 pkey); int force_sig_ptrace_errno_trap(int errno, void __user *addr); -extern int send_sig_info(int, struct siginfo *, struct task_struct *); +extern int send_sig_info(int, struct kernel_siginfo *, struct task_struct *); extern void force_sigsegv(int sig, struct task_struct *p); -extern int force_sig_info(int, struct siginfo *, struct task_struct *); -extern int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp); -extern int kill_pid_info(int sig, struct siginfo *info, struct pid *pid); -extern int kill_pid_info_as_cred(int, struct siginfo *, struct pid *, +extern int force_sig_info(int, struct kernel_siginfo *, struct task_struct *); +extern int __kill_pgrp_info(int sig, struct kernel_siginfo *info, struct pid *pgrp); +extern int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid); +extern int kill_pid_info_as_cred(int, struct kernel_siginfo *, struct pid *, const struct cred *); extern int kill_pgrp(struct pid *pid, int sig, int priv); extern int kill_pid(struct pid *pid, int sig, int priv); @@ -475,8 +475,8 @@ static inline int kill_cad_pid(int sig, int priv) } /* These can be the second arg to send_sig_info/send_group_sig_info. */ -#define SEND_SIG_NOINFO ((struct siginfo *) 0) -#define SEND_SIG_PRIV ((struct siginfo *) 1) +#define SEND_SIG_NOINFO ((struct kernel_siginfo *) 0) +#define SEND_SIG_PRIV ((struct kernel_siginfo *) 1) /* * True if we are on the alternate signal stack. diff --git a/include/linux/security.h b/include/linux/security.h index 75f4156c84d7..d170a5b031f3 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -35,7 +35,7 @@ struct linux_binprm; struct cred; struct rlimit; -struct siginfo; +struct kernel_siginfo; struct sembuf; struct kern_ipc_perm; struct audit_context; @@ -361,7 +361,7 @@ int security_task_setrlimit(struct task_struct *p, unsigned int resource, int security_task_setscheduler(struct task_struct *p); int security_task_getscheduler(struct task_struct *p); int security_task_movememory(struct task_struct *p); -int security_task_kill(struct task_struct *p, struct siginfo *info, +int security_task_kill(struct task_struct *p, struct kernel_siginfo *info, int sig, const struct cred *cred); int security_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5); @@ -1020,7 +1020,7 @@ static inline int security_task_movememory(struct task_struct *p) } static inline int security_task_kill(struct task_struct *p, - struct siginfo *info, int sig, + struct kernel_siginfo *info, int sig, const struct cred *cred) { return 0; diff --git a/include/linux/signal.h b/include/linux/signal.h index de94c159bfb0..70031b10b918 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -11,18 +11,19 @@ struct task_struct; /* for sysctl */ extern int print_fatal_signals; -static inline void copy_siginfo(struct siginfo *to, const struct siginfo *from) +static inline void copy_siginfo(kernel_siginfo_t *to, + const kernel_siginfo_t *from) { memcpy(to, from, sizeof(*to)); } -static inline void clear_siginfo(struct siginfo *info) +static inline void clear_siginfo(kernel_siginfo_t *info) { memset(info, 0, sizeof(*info)); } -int copy_siginfo_to_user(struct siginfo __user *to, const struct siginfo *from); -int copy_siginfo_from_user(struct siginfo *to, const struct siginfo __user *from); +int copy_siginfo_to_user(siginfo_t __user *to, const kernel_siginfo_t *from); +int copy_siginfo_from_user(kernel_siginfo_t *to, const siginfo_t __user *from); enum siginfo_layout { SIL_KILL, @@ -258,11 +259,11 @@ struct pt_regs; enum pid_type; extern int next_signal(struct sigpending *pending, sigset_t *mask); -extern int do_send_sig_info(int sig, struct siginfo *info, +extern int do_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p, enum pid_type type); -extern int group_send_sig_info(int sig, struct siginfo *info, +extern int group_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p, enum pid_type type); -extern int __group_send_sig_info(int, struct siginfo *, struct task_struct *); +extern int __group_send_sig_info(int, struct kernel_siginfo *, struct task_struct *); extern int sigprocmask(int, sigset_t *, sigset_t *); extern void set_current_blocked(sigset_t *); extern void __set_current_blocked(const sigset_t *); diff --git a/include/linux/signal_types.h b/include/linux/signal_types.h index 222ae696000b..2a40a9c5e4ad 100644 --- a/include/linux/signal_types.h +++ b/include/linux/signal_types.h @@ -9,6 +9,13 @@ #include #include +typedef struct kernel_siginfo { + union { + __SIGINFO; + int _si_pad[SI_MAX_SIZE/sizeof(int)]; + }; +} kernel_siginfo_t; + /* * Real Time signals may be queued. */ @@ -16,7 +23,7 @@ struct sigqueue { struct list_head list; int flags; - siginfo_t info; + kernel_siginfo_t info; struct user_struct *user; }; @@ -60,7 +67,7 @@ struct old_sigaction { struct ksignal { struct k_sigaction ka; - siginfo_t info; + kernel_siginfo_t info; int sig; }; diff --git a/include/trace/events/signal.h b/include/trace/events/signal.h index 3deeed50ffd0..1db7e4b07c01 100644 --- a/include/trace/events/signal.h +++ b/include/trace/events/signal.h @@ -49,7 +49,7 @@ enum { */ TRACE_EVENT(signal_generate, - TP_PROTO(int sig, struct siginfo *info, struct task_struct *task, + TP_PROTO(int sig, struct kernel_siginfo *info, struct task_struct *task, int group, int result), TP_ARGS(sig, info, task, group, result), @@ -95,7 +95,7 @@ TRACE_EVENT(signal_generate, */ TRACE_EVENT(signal_deliver, - TP_PROTO(int sig, struct siginfo *info, struct k_sigaction *ka), + TP_PROTO(int sig, struct kernel_siginfo *info, struct k_sigaction *ka), TP_ARGS(sig, info, ka), diff --git a/ipc/mqueue.c b/ipc/mqueue.c index c0d58f390c3b..cc41de3b8deb 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -655,7 +655,7 @@ static void __do_notify(struct mqueue_inode_info *info) * synchronously. */ if (info->notify_owner && info->attr.mq_curmsgs == 1) { - struct siginfo sig_i; + struct kernel_siginfo sig_i; switch (info->notify.sigev_notify) { case SIGEV_NONE: break; diff --git a/kernel/ptrace.c b/kernel/ptrace.c index a807ff5cc1a9..c2cee9db5204 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -651,7 +651,7 @@ static int ptrace_setoptions(struct task_struct *child, unsigned long data) return 0; } -static int ptrace_getsiginfo(struct task_struct *child, siginfo_t *info) +static int ptrace_getsiginfo(struct task_struct *child, kernel_siginfo_t *info) { unsigned long flags; int error = -ESRCH; @@ -667,7 +667,7 @@ static int ptrace_getsiginfo(struct task_struct *child, siginfo_t *info) return error; } -static int ptrace_setsiginfo(struct task_struct *child, const siginfo_t *info) +static int ptrace_setsiginfo(struct task_struct *child, const kernel_siginfo_t *info) { unsigned long flags; int error = -ESRCH; @@ -709,7 +709,7 @@ static int ptrace_peek_siginfo(struct task_struct *child, pending = &child->pending; for (i = 0; i < arg.nr; ) { - siginfo_t info; + kernel_siginfo_t info; s32 off = arg.off + i; spin_lock_irq(&child->sighand->siglock); @@ -885,7 +885,7 @@ int ptrace_request(struct task_struct *child, long request, { bool seized = child->ptrace & PT_SEIZED; int ret = -EIO; - siginfo_t siginfo, *si; + kernel_siginfo_t siginfo, *si; void __user *datavp = (void __user *) data; unsigned long __user *datalp = datavp; unsigned long flags; @@ -1180,7 +1180,7 @@ int compat_ptrace_request(struct task_struct *child, compat_long_t request, { compat_ulong_t __user *datap = compat_ptr(data); compat_ulong_t word; - siginfo_t siginfo; + kernel_siginfo_t siginfo; int ret; switch (request) { diff --git a/kernel/seccomp.c b/kernel/seccomp.c index fd023ac24e10..4d7809cdd27d 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -522,7 +522,7 @@ void put_seccomp_filter(struct task_struct *tsk) __put_seccomp_filter(tsk->seccomp.filter); } -static void seccomp_init_siginfo(siginfo_t *info, int syscall, int reason) +static void seccomp_init_siginfo(kernel_siginfo_t *info, int syscall, int reason) { clear_siginfo(info); info->si_signo = SIGSYS; @@ -542,7 +542,7 @@ static void seccomp_init_siginfo(siginfo_t *info, int syscall, int reason) */ static void seccomp_send_sigsys(int syscall, int reason) { - struct siginfo info; + struct kernel_siginfo info; seccomp_init_siginfo(&info, syscall, reason); force_sig_info(SIGSYS, &info, current); } @@ -747,7 +747,7 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, /* Dump core only if this is the last remaining thread. */ if (action == SECCOMP_RET_KILL_PROCESS || get_nr_threads(current) == 1) { - siginfo_t info; + kernel_siginfo_t info; /* Show the original registers in the dump. */ syscall_rollback(current, task_pt_regs(current)); diff --git a/kernel/signal.c b/kernel/signal.c index c0e289e62d77..161cad4e448c 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -549,7 +549,7 @@ bool unhandled_signal(struct task_struct *tsk, int sig) return !tsk->ptrace; } -static void collect_signal(int sig, struct sigpending *list, siginfo_t *info, +static void collect_signal(int sig, struct sigpending *list, kernel_siginfo_t *info, bool *resched_timer) { struct sigqueue *q, *first = NULL; @@ -595,7 +595,7 @@ still_pending: } static int __dequeue_signal(struct sigpending *pending, sigset_t *mask, - siginfo_t *info, bool *resched_timer) + kernel_siginfo_t *info, bool *resched_timer) { int sig = next_signal(pending, mask); @@ -610,7 +610,7 @@ static int __dequeue_signal(struct sigpending *pending, sigset_t *mask, * * All callers have to hold the siglock. */ -int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info) +int dequeue_signal(struct task_struct *tsk, sigset_t *mask, kernel_siginfo_t *info) { bool resched_timer = false; int signr; @@ -737,12 +737,12 @@ static void flush_sigqueue_mask(sigset_t *mask, struct sigpending *s) } } -static inline int is_si_special(const struct siginfo *info) +static inline int is_si_special(const struct kernel_siginfo *info) { return info <= SEND_SIG_PRIV; } -static inline bool si_fromuser(const struct siginfo *info) +static inline bool si_fromuser(const struct kernel_siginfo *info) { return info == SEND_SIG_NOINFO || (!is_si_special(info) && SI_FROMUSER(info)); @@ -767,7 +767,7 @@ static bool kill_ok_by_cred(struct task_struct *t) * Bad permissions for sending the signal * - the caller must hold the RCU read lock */ -static int check_kill_permission(int sig, struct siginfo *info, +static int check_kill_permission(int sig, struct kernel_siginfo *info, struct task_struct *t) { struct pid *sid; @@ -1010,7 +1010,7 @@ static inline bool legacy_queue(struct sigpending *signals, int sig) } #ifdef CONFIG_USER_NS -static inline void userns_fixup_signal_uid(struct siginfo *info, struct task_struct *t) +static inline void userns_fixup_signal_uid(struct kernel_siginfo *info, struct task_struct *t) { if (current_user_ns() == task_cred_xxx(t, user_ns)) return; @@ -1024,13 +1024,13 @@ static inline void userns_fixup_signal_uid(struct siginfo *info, struct task_str rcu_read_unlock(); } #else -static inline void userns_fixup_signal_uid(struct siginfo *info, struct task_struct *t) +static inline void userns_fixup_signal_uid(struct kernel_siginfo *info, struct task_struct *t) { return; } #endif -static int __send_signal(int sig, struct siginfo *info, struct task_struct *t, +static int __send_signal(int sig, struct kernel_siginfo *info, struct task_struct *t, enum pid_type type, int from_ancestor_ns) { struct sigpending *pending; @@ -1150,7 +1150,7 @@ ret: return ret; } -static int send_signal(int sig, struct siginfo *info, struct task_struct *t, +static int send_signal(int sig, struct kernel_siginfo *info, struct task_struct *t, enum pid_type type) { int from_ancestor_ns = 0; @@ -1197,12 +1197,12 @@ static int __init setup_print_fatal_signals(char *str) __setup("print-fatal-signals=", setup_print_fatal_signals); int -__group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p) +__group_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p) { return send_signal(sig, info, p, PIDTYPE_TGID); } -int do_send_sig_info(int sig, struct siginfo *info, struct task_struct *p, +int do_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p, enum pid_type type) { unsigned long flags; @@ -1228,7 +1228,7 @@ int do_send_sig_info(int sig, struct siginfo *info, struct task_struct *p, * that is why we also clear SIGNAL_UNKILLABLE. */ int -force_sig_info(int sig, struct siginfo *info, struct task_struct *t) +force_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *t) { unsigned long int flags; int ret, blocked, ignored; @@ -1316,8 +1316,8 @@ struct sighand_struct *__lock_task_sighand(struct task_struct *tsk, /* * send signal info to all the members of a group */ -int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p, - enum pid_type type) +int group_send_sig_info(int sig, struct kernel_siginfo *info, + struct task_struct *p, enum pid_type type) { int ret; @@ -1336,7 +1336,7 @@ int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p, * control characters do (^C, ^Z etc) * - the caller must hold at least a readlock on tasklist_lock */ -int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp) +int __kill_pgrp_info(int sig, struct kernel_siginfo *info, struct pid *pgrp) { struct task_struct *p = NULL; int retval, success; @@ -1351,7 +1351,7 @@ int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp) return success ? 0 : retval; } -int kill_pid_info(int sig, struct siginfo *info, struct pid *pid) +int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid) { int error = -ESRCH; struct task_struct *p; @@ -1373,7 +1373,7 @@ int kill_pid_info(int sig, struct siginfo *info, struct pid *pid) } } -static int kill_proc_info(int sig, struct siginfo *info, pid_t pid) +static int kill_proc_info(int sig, struct kernel_siginfo *info, pid_t pid) { int error; rcu_read_lock(); @@ -1394,7 +1394,7 @@ static inline bool kill_as_cred_perm(const struct cred *cred, } /* like kill_pid_info(), but doesn't use uid/euid of "current" */ -int kill_pid_info_as_cred(int sig, struct siginfo *info, struct pid *pid, +int kill_pid_info_as_cred(int sig, struct kernel_siginfo *info, struct pid *pid, const struct cred *cred) { int ret = -EINVAL; @@ -1438,7 +1438,7 @@ EXPORT_SYMBOL_GPL(kill_pid_info_as_cred); * is probably wrong. Should make it like BSD or SYSV. */ -static int kill_something_info(int sig, struct siginfo *info, pid_t pid) +static int kill_something_info(int sig, struct kernel_siginfo *info, pid_t pid) { int ret; @@ -1482,7 +1482,7 @@ static int kill_something_info(int sig, struct siginfo *info, pid_t pid) * These are for backward compatibility with the rest of the kernel source. */ -int send_sig_info(int sig, struct siginfo *info, struct task_struct *p) +int send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p) { /* * Make sure legacy kernel users don't send in bad values @@ -1533,7 +1533,7 @@ int force_sig_fault(int sig, int code, void __user *addr ___ARCH_SI_IA64(int imm, unsigned int flags, unsigned long isr) , struct task_struct *t) { - struct siginfo info; + struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = sig; @@ -1556,7 +1556,7 @@ int send_sig_fault(int sig, int code, void __user *addr ___ARCH_SI_IA64(int imm, unsigned int flags, unsigned long isr) , struct task_struct *t) { - struct siginfo info; + struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = sig; @@ -1576,7 +1576,7 @@ int send_sig_fault(int sig, int code, void __user *addr int force_sig_mceerr(int code, void __user *addr, short lsb, struct task_struct *t) { - struct siginfo info; + struct kernel_siginfo info; WARN_ON((code != BUS_MCEERR_AO) && (code != BUS_MCEERR_AR)); clear_siginfo(&info); @@ -1590,7 +1590,7 @@ int force_sig_mceerr(int code, void __user *addr, short lsb, struct task_struct int send_sig_mceerr(int code, void __user *addr, short lsb, struct task_struct *t) { - struct siginfo info; + struct kernel_siginfo info; WARN_ON((code != BUS_MCEERR_AO) && (code != BUS_MCEERR_AR)); clear_siginfo(&info); @@ -1605,7 +1605,7 @@ EXPORT_SYMBOL(send_sig_mceerr); int force_sig_bnderr(void __user *addr, void __user *lower, void __user *upper) { - struct siginfo info; + struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = SIGSEGV; @@ -1620,7 +1620,7 @@ int force_sig_bnderr(void __user *addr, void __user *lower, void __user *upper) #ifdef SEGV_PKUERR int force_sig_pkuerr(void __user *addr, u32 pkey) { - struct siginfo info; + struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = SIGSEGV; @@ -1637,7 +1637,7 @@ int force_sig_pkuerr(void __user *addr, u32 pkey) */ int force_sig_ptrace_errno_trap(int errno, void __user *addr) { - struct siginfo info; + struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = SIGTRAP; @@ -1766,7 +1766,7 @@ ret: */ bool do_notify_parent(struct task_struct *tsk, int sig) { - struct siginfo info; + struct kernel_siginfo info; unsigned long flags; struct sighand_struct *psig; bool autoreap = false; @@ -1871,7 +1871,7 @@ bool do_notify_parent(struct task_struct *tsk, int sig) static void do_notify_parent_cldstop(struct task_struct *tsk, bool for_ptracer, int why) { - struct siginfo info; + struct kernel_siginfo info; unsigned long flags; struct task_struct *parent; struct sighand_struct *sighand; @@ -1971,7 +1971,7 @@ static bool sigkill_pending(struct task_struct *tsk) * If we actually decide not to stop at all because the tracer * is gone, we keep current->exit_code unless clear_code. */ -static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info) +static void ptrace_stop(int exit_code, int why, int clear_code, kernel_siginfo_t *info) __releases(¤t->sighand->siglock) __acquires(¤t->sighand->siglock) { @@ -2108,7 +2108,7 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info) static void ptrace_do_notify(int signr, int exit_code, int why) { - siginfo_t info; + kernel_siginfo_t info; clear_siginfo(&info); info.si_signo = signr; @@ -2289,7 +2289,7 @@ static void do_jobctl_trap(void) } } -static int ptrace_signal(int signr, siginfo_t *info) +static int ptrace_signal(int signr, kernel_siginfo_t *info) { /* * We do not check sig_kernel_stop(signr) but set this marker @@ -2889,14 +2889,14 @@ enum siginfo_layout siginfo_layout(int sig, int si_code) return layout; } -int copy_siginfo_to_user(siginfo_t __user *to, const siginfo_t *from) +int copy_siginfo_to_user(siginfo_t __user *to, const kernel_siginfo_t *from) { - if (copy_to_user(to, from , sizeof(struct siginfo))) + if (copy_to_user(to, from , sizeof(struct kernel_siginfo))) return -EFAULT; return 0; } -int copy_siginfo_from_user(siginfo_t *to, const siginfo_t __user *from) +int copy_siginfo_from_user(kernel_siginfo_t *to, const siginfo_t __user *from) { if (copy_from_user(to, from, sizeof(struct siginfo))) return -EFAULT; @@ -2905,13 +2905,13 @@ int copy_siginfo_from_user(siginfo_t *to, const siginfo_t __user *from) #ifdef CONFIG_COMPAT int copy_siginfo_to_user32(struct compat_siginfo __user *to, - const struct siginfo *from) + const struct kernel_siginfo *from) #if defined(CONFIG_X86_X32_ABI) || defined(CONFIG_IA32_EMULATION) { return __copy_siginfo_to_user32(to, from, in_x32_syscall()); } int __copy_siginfo_to_user32(struct compat_siginfo __user *to, - const struct siginfo *from, bool x32_ABI) + const struct kernel_siginfo *from, bool x32_ABI) #endif { struct compat_siginfo new; @@ -2995,7 +2995,7 @@ int __copy_siginfo_to_user32(struct compat_siginfo __user *to, return 0; } -int copy_siginfo_from_user32(struct siginfo *to, +int copy_siginfo_from_user32(struct kernel_siginfo *to, const struct compat_siginfo __user *ufrom) { struct compat_siginfo from; @@ -3085,7 +3085,7 @@ int copy_siginfo_from_user32(struct siginfo *to, * @info: if non-null, the signal's siginfo is returned here * @ts: upper bound on process time suspension */ -static int do_sigtimedwait(const sigset_t *which, siginfo_t *info, +static int do_sigtimedwait(const sigset_t *which, kernel_siginfo_t *info, const struct timespec *ts) { ktime_t *to = NULL, timeout = KTIME_MAX; @@ -3149,7 +3149,7 @@ SYSCALL_DEFINE4(rt_sigtimedwait, const sigset_t __user *, uthese, { sigset_t these; struct timespec ts; - siginfo_t info; + kernel_siginfo_t info; int ret; /* XXX: Don't preclude handling different sized sigset_t's. */ @@ -3181,7 +3181,7 @@ COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait, compat_sigset_t __user *, uthese, { sigset_t s; struct timespec t; - siginfo_t info; + kernel_siginfo_t info; long ret; if (sigsetsize != sizeof(sigset_t)) @@ -3213,7 +3213,7 @@ COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait, compat_sigset_t __user *, uthese, */ SYSCALL_DEFINE2(kill, pid_t, pid, int, sig) { - struct siginfo info; + struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = sig; @@ -3226,7 +3226,7 @@ SYSCALL_DEFINE2(kill, pid_t, pid, int, sig) } static int -do_send_specific(pid_t tgid, pid_t pid, int sig, struct siginfo *info) +do_send_specific(pid_t tgid, pid_t pid, int sig, struct kernel_siginfo *info) { struct task_struct *p; int error = -ESRCH; @@ -3257,7 +3257,7 @@ do_send_specific(pid_t tgid, pid_t pid, int sig, struct siginfo *info) static int do_tkill(pid_t tgid, pid_t pid, int sig) { - struct siginfo info; + struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = sig; @@ -3304,7 +3304,7 @@ SYSCALL_DEFINE2(tkill, pid_t, pid, int, sig) return do_tkill(0, pid, sig); } -static int do_rt_sigqueueinfo(pid_t pid, int sig, siginfo_t *info) +static int do_rt_sigqueueinfo(pid_t pid, int sig, kernel_siginfo_t *info) { /* Not even root can pretend to send signals from the kernel. * Nor can they impersonate a kill()/tgkill(), which adds source info. @@ -3329,7 +3329,7 @@ static int do_rt_sigqueueinfo(pid_t pid, int sig, siginfo_t *info) SYSCALL_DEFINE3(rt_sigqueueinfo, pid_t, pid, int, sig, siginfo_t __user *, uinfo) { - siginfo_t info; + kernel_siginfo_t info; int ret = copy_siginfo_from_user(&info, uinfo); if (unlikely(ret)) return ret; @@ -3342,7 +3342,7 @@ COMPAT_SYSCALL_DEFINE3(rt_sigqueueinfo, int, sig, struct compat_siginfo __user *, uinfo) { - siginfo_t info; + kernel_siginfo_t info; int ret = copy_siginfo_from_user32(&info, uinfo); if (unlikely(ret)) return ret; @@ -3350,7 +3350,7 @@ COMPAT_SYSCALL_DEFINE3(rt_sigqueueinfo, } #endif -static int do_rt_tgsigqueueinfo(pid_t tgid, pid_t pid, int sig, siginfo_t *info) +static int do_rt_tgsigqueueinfo(pid_t tgid, pid_t pid, int sig, kernel_siginfo_t *info) { /* This is only valid for single tasks */ if (pid <= 0 || tgid <= 0) @@ -3372,7 +3372,7 @@ static int do_rt_tgsigqueueinfo(pid_t tgid, pid_t pid, int sig, siginfo_t *info) SYSCALL_DEFINE4(rt_tgsigqueueinfo, pid_t, tgid, pid_t, pid, int, sig, siginfo_t __user *, uinfo) { - siginfo_t info; + kernel_siginfo_t info; int ret = copy_siginfo_from_user(&info, uinfo); if (unlikely(ret)) return ret; @@ -3386,7 +3386,7 @@ COMPAT_SYSCALL_DEFINE4(rt_tgsigqueueinfo, int, sig, struct compat_siginfo __user *, uinfo) { - siginfo_t info; + kernel_siginfo_t info; int ret = copy_siginfo_from_user32(&info, uinfo); if (unlikely(ret)) return ret; @@ -3968,10 +3968,57 @@ __weak const char *arch_vma_name(struct vm_area_struct *vma) return NULL; } -void __init signals_init(void) +static inline void siginfo_buildtime_checks(void) { BUILD_BUG_ON(sizeof(struct siginfo) != SI_MAX_SIZE); + /* Verify the offsets in the two siginfos match */ +#define CHECK_OFFSET(field) \ + BUILD_BUG_ON(offsetof(siginfo_t, field) != offsetof(kernel_siginfo_t, field)) + + /* kill */ + CHECK_OFFSET(si_pid); + CHECK_OFFSET(si_uid); + + /* timer */ + CHECK_OFFSET(si_tid); + CHECK_OFFSET(si_overrun); + CHECK_OFFSET(si_value); + + /* rt */ + CHECK_OFFSET(si_pid); + CHECK_OFFSET(si_uid); + CHECK_OFFSET(si_value); + + /* sigchld */ + CHECK_OFFSET(si_pid); + CHECK_OFFSET(si_uid); + CHECK_OFFSET(si_status); + CHECK_OFFSET(si_utime); + CHECK_OFFSET(si_stime); + + /* sigfault */ + CHECK_OFFSET(si_addr); + CHECK_OFFSET(si_addr_lsb); + CHECK_OFFSET(si_lower); + CHECK_OFFSET(si_upper); + CHECK_OFFSET(si_pkey); + + /* sigpoll */ + CHECK_OFFSET(si_band); + CHECK_OFFSET(si_fd); + + /* sigsys */ + CHECK_OFFSET(si_call_addr); + CHECK_OFFSET(si_syscall); + CHECK_OFFSET(si_arch); +#undef CHECK_OFFSET +} + +void __init signals_init(void) +{ + siginfo_buildtime_checks(); + sigqueue_cachep = KMEM_CACHE(sigqueue, SLAB_PANIC); } diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 4b9127e95430..eabb4c22728d 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -308,7 +308,7 @@ static void common_hrtimer_rearm(struct k_itimer *timr) * To protect against the timer going away while the interrupt is queued, * we require that the it_requeue_pending flag be set. */ -void posixtimer_rearm(struct siginfo *info) +void posixtimer_rearm(struct kernel_siginfo *info) { struct k_itimer *timr; unsigned long flags; diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index 8b8b70620bbe..cbcb8ba51142 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -732,7 +732,7 @@ static int apparmor_task_setrlimit(struct task_struct *task, return error; } -static int apparmor_task_kill(struct task_struct *target, struct siginfo *info, +static int apparmor_task_kill(struct task_struct *target, struct kernel_siginfo *info, int sig, const struct cred *cred) { struct aa_label *cl, *tl; diff --git a/security/security.c b/security/security.c index 736e78da1ab9..0d504fceda8b 100644 --- a/security/security.c +++ b/security/security.c @@ -1147,7 +1147,7 @@ int security_task_movememory(struct task_struct *p) return call_int_hook(task_movememory, 0, p); } -int security_task_kill(struct task_struct *p, struct siginfo *info, +int security_task_kill(struct task_struct *p, struct kernel_siginfo *info, int sig, const struct cred *cred) { return call_int_hook(task_kill, 0, p, info, sig, cred); diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index ad9a9b8e9979..1b500b4c78a7 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -4186,7 +4186,7 @@ static int selinux_task_movememory(struct task_struct *p) PROCESS__SETSCHED, NULL); } -static int selinux_task_kill(struct task_struct *p, struct siginfo *info, +static int selinux_task_kill(struct task_struct *p, struct kernel_siginfo *info, int sig, const struct cred *cred) { u32 secid; diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index 340fc30ad85d..025de76af1db 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -2251,7 +2251,7 @@ static int smack_task_movememory(struct task_struct *p) * Return 0 if write access is permitted * */ -static int smack_task_kill(struct task_struct *p, struct siginfo *info, +static int smack_task_kill(struct task_struct *p, struct kernel_siginfo *info, int sig, const struct cred *cred) { struct smk_audit_info ad; -- cgit v1.2.3 From 4ce5f9c9e7546915c559ffae594e6d73f918db00 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 25 Sep 2018 12:59:31 +0200 Subject: signal: Use a smaller struct siginfo in the kernel We reserve 128 bytes for struct siginfo but only use about 48 bytes on 64bit and 32 bytes on 32bit. Someday we might use more but it is unlikely to be anytime soon. Userspace seems content with just enough bytes of siginfo to implement sigqueue. Or in the case of checkpoint/restart reinjecting signals the kernel has sent. Reducing the stack footprint and the work to copy siginfo around from 2 cachelines to 1 cachelines seems worth doing even if I don't have benchmarks to show a performance difference. Suggested-by: Linus Torvalds Signed-off-by: "Eric W. Biederman" --- include/linux/signal.h | 2 ++ include/linux/signal_types.h | 5 +-- kernel/signal.c | 82 ++++++++++++++++++++++++++++++++++---------- 3 files changed, 67 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index 70031b10b918..706a499d1eb1 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -22,6 +22,8 @@ static inline void clear_siginfo(kernel_siginfo_t *info) memset(info, 0, sizeof(*info)); } +#define SI_EXPANSION_SIZE (sizeof(struct siginfo) - sizeof(struct kernel_siginfo)) + int copy_siginfo_to_user(siginfo_t __user *to, const kernel_siginfo_t *from); int copy_siginfo_from_user(kernel_siginfo_t *to, const siginfo_t __user *from); diff --git a/include/linux/signal_types.h b/include/linux/signal_types.h index 2a40a9c5e4ad..f8a90ae9c6ec 100644 --- a/include/linux/signal_types.h +++ b/include/linux/signal_types.h @@ -10,10 +10,7 @@ #include typedef struct kernel_siginfo { - union { - __SIGINFO; - int _si_pad[SI_MAX_SIZE/sizeof(int)]; - }; + __SIGINFO; } kernel_siginfo_t; /* diff --git a/kernel/signal.c b/kernel/signal.c index 161cad4e448c..1c2dd117fee0 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2844,27 +2844,48 @@ COMPAT_SYSCALL_DEFINE2(rt_sigpending, compat_sigset_t __user *, uset, } #endif +static const struct { + unsigned char limit, layout; +} sig_sicodes[] = { + [SIGILL] = { NSIGILL, SIL_FAULT }, + [SIGFPE] = { NSIGFPE, SIL_FAULT }, + [SIGSEGV] = { NSIGSEGV, SIL_FAULT }, + [SIGBUS] = { NSIGBUS, SIL_FAULT }, + [SIGTRAP] = { NSIGTRAP, SIL_FAULT }, +#if defined(SIGEMT) + [SIGEMT] = { NSIGEMT, SIL_FAULT }, +#endif + [SIGCHLD] = { NSIGCHLD, SIL_CHLD }, + [SIGPOLL] = { NSIGPOLL, SIL_POLL }, + [SIGSYS] = { NSIGSYS, SIL_SYS }, +}; + +static bool known_siginfo_layout(int sig, int si_code) +{ + if (si_code == SI_KERNEL) + return true; + else if ((si_code > SI_USER)) { + if (sig_specific_sicodes(sig)) { + if (si_code <= sig_sicodes[sig].limit) + return true; + } + else if (si_code <= NSIGPOLL) + return true; + } + else if (si_code >= SI_DETHREAD) + return true; + else if (si_code == SI_ASYNCNL) + return true; + return false; +} + enum siginfo_layout siginfo_layout(int sig, int si_code) { enum siginfo_layout layout = SIL_KILL; if ((si_code > SI_USER) && (si_code < SI_KERNEL)) { - static const struct { - unsigned char limit, layout; - } filter[] = { - [SIGILL] = { NSIGILL, SIL_FAULT }, - [SIGFPE] = { NSIGFPE, SIL_FAULT }, - [SIGSEGV] = { NSIGSEGV, SIL_FAULT }, - [SIGBUS] = { NSIGBUS, SIL_FAULT }, - [SIGTRAP] = { NSIGTRAP, SIL_FAULT }, -#if defined(SIGEMT) - [SIGEMT] = { NSIGEMT, SIL_FAULT }, -#endif - [SIGCHLD] = { NSIGCHLD, SIL_CHLD }, - [SIGPOLL] = { NSIGPOLL, SIL_POLL }, - [SIGSYS] = { NSIGSYS, SIL_SYS }, - }; - if ((sig < ARRAY_SIZE(filter)) && (si_code <= filter[sig].limit)) { - layout = filter[sig].layout; + if ((sig < ARRAY_SIZE(sig_sicodes)) && + (si_code <= sig_sicodes[sig].limit)) { + layout = sig_sicodes[sig].layout; /* Handle the exceptions */ if ((sig == SIGBUS) && (si_code >= BUS_MCEERR_AR) && (si_code <= BUS_MCEERR_AO)) @@ -2889,17 +2910,42 @@ enum siginfo_layout siginfo_layout(int sig, int si_code) return layout; } +static inline char __user *si_expansion(const siginfo_t __user *info) +{ + return ((char __user *)info) + sizeof(struct kernel_siginfo); +} + int copy_siginfo_to_user(siginfo_t __user *to, const kernel_siginfo_t *from) { + char __user *expansion = si_expansion(to); if (copy_to_user(to, from , sizeof(struct kernel_siginfo))) return -EFAULT; + if (clear_user(expansion, SI_EXPANSION_SIZE)) + return -EFAULT; return 0; } int copy_siginfo_from_user(kernel_siginfo_t *to, const siginfo_t __user *from) { - if (copy_from_user(to, from, sizeof(struct siginfo))) + if (copy_from_user(to, from, sizeof(struct kernel_siginfo))) return -EFAULT; + if (unlikely(!known_siginfo_layout(to->si_signo, to->si_code))) { + char __user *expansion = si_expansion(from); + char buf[SI_EXPANSION_SIZE]; + int i; + /* + * An unknown si_code might need more than + * sizeof(struct kernel_siginfo) bytes. Verify all of the + * extra bytes are 0. This guarantees copy_siginfo_to_user + * will return this data to userspace exactly. + */ + if (copy_from_user(&buf, expansion, SI_EXPANSION_SIZE)) + return -EFAULT; + for (i = 0; i < SI_EXPANSION_SIZE; i++) { + if (buf[i] != 0) + return -E2BIG; + } + } return 0; } -- cgit v1.2.3 From fcd29ad17c6ff885dfae58f557e9323941e63ba2 Mon Sep 17 00:00:00 2001 From: Feras Daoud Date: Thu, 9 Aug 2018 09:55:21 +0300 Subject: net/mlx5: Add Fast teardown support Today mlx5 devices support two teardown modes: 1- Regular teardown 2- Force teardown This change introduces the enhanced version of the "Force teardown" that allows SW to perform teardown in a faster way without the need to reclaim all the pages. Fast teardown provides the following advantages: 1- Fix a FW race condition that could cause command timeout 2- Avoid moving to polling mode 3- Close the vport to prevent PCI ACK to be sent without been scatter to memory Signed-off-by: Feras Daoud Reviewed-by: Majd Dibbiny Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fw.c | 50 +++++++++++++++++++++- drivers/net/ethernet/mellanox/mlx5/core/health.c | 25 ++++++----- drivers/net/ethernet/mellanox/mlx5/core/main.c | 29 +++++++++---- .../net/ethernet/mellanox/mlx5/core/mlx5_core.h | 12 ++++++ include/linux/mlx5/device.h | 4 ++ include/linux/mlx5/mlx5_ifc.h | 6 ++- 6 files changed, 103 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index 41ad24f0de2c..1ab6f7e3bec6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -250,7 +250,7 @@ int mlx5_cmd_force_teardown_hca(struct mlx5_core_dev *dev) if (ret) return ret; - force_state = MLX5_GET(teardown_hca_out, out, force_state); + force_state = MLX5_GET(teardown_hca_out, out, state); if (force_state == MLX5_TEARDOWN_HCA_OUT_FORCE_STATE_FAIL) { mlx5_core_warn(dev, "teardown with force mode failed, doing normal teardown\n"); return -EIO; @@ -259,6 +259,54 @@ int mlx5_cmd_force_teardown_hca(struct mlx5_core_dev *dev) return 0; } +#define MLX5_FAST_TEARDOWN_WAIT_MS 3000 +int mlx5_cmd_fast_teardown_hca(struct mlx5_core_dev *dev) +{ + unsigned long end, delay_ms = MLX5_FAST_TEARDOWN_WAIT_MS; + u32 out[MLX5_ST_SZ_DW(teardown_hca_out)] = {0}; + u32 in[MLX5_ST_SZ_DW(teardown_hca_in)] = {0}; + int state; + int ret; + + if (!MLX5_CAP_GEN(dev, fast_teardown)) { + mlx5_core_dbg(dev, "fast teardown is not supported in the firmware\n"); + return -EOPNOTSUPP; + } + + MLX5_SET(teardown_hca_in, in, opcode, MLX5_CMD_OP_TEARDOWN_HCA); + MLX5_SET(teardown_hca_in, in, profile, + MLX5_TEARDOWN_HCA_IN_PROFILE_PREPARE_FAST_TEARDOWN); + + ret = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); + if (ret) + return ret; + + state = MLX5_GET(teardown_hca_out, out, state); + if (state == MLX5_TEARDOWN_HCA_OUT_FORCE_STATE_FAIL) { + mlx5_core_warn(dev, "teardown with fast mode failed\n"); + return -EIO; + } + + mlx5_set_nic_state(dev, MLX5_NIC_IFC_DISABLED); + + /* Loop until device state turns to disable */ + end = jiffies + msecs_to_jiffies(delay_ms); + do { + if (mlx5_get_nic_state(dev) == MLX5_NIC_IFC_DISABLED) + break; + + cond_resched(); + } while (!time_after(jiffies, end)); + + if (mlx5_get_nic_state(dev) != MLX5_NIC_IFC_DISABLED) { + dev_err(&dev->pdev->dev, "NIC IFC still %d after %lums.\n", + mlx5_get_nic_state(dev), delay_ms); + return -EIO; + } + + return 0; +} + enum mlxsw_reg_mcc_instruction { MLX5_REG_MCC_INSTRUCTION_LOCK_UPDATE_HANDLE = 0x01, MLX5_REG_MCC_INSTRUCTION_RELEASE_UPDATE_HANDLE = 0x02, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 9f39aeca863f..43118de8ee99 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -58,23 +58,26 @@ enum { MLX5_HEALTH_SYNDR_HIGH_TEMP = 0x10 }; -enum { - MLX5_NIC_IFC_FULL = 0, - MLX5_NIC_IFC_DISABLED = 1, - MLX5_NIC_IFC_NO_DRAM_NIC = 2, - MLX5_NIC_IFC_INVALID = 3 -}; - enum { MLX5_DROP_NEW_HEALTH_WORK, MLX5_DROP_NEW_RECOVERY_WORK, }; -static u8 get_nic_state(struct mlx5_core_dev *dev) +u8 mlx5_get_nic_state(struct mlx5_core_dev *dev) { return (ioread32be(&dev->iseg->cmdq_addr_l_sz) >> 8) & 3; } +void mlx5_set_nic_state(struct mlx5_core_dev *dev, u8 state) +{ + u32 cur_cmdq_addr_l_sz; + + cur_cmdq_addr_l_sz = ioread32be(&dev->iseg->cmdq_addr_l_sz); + iowrite32be((cur_cmdq_addr_l_sz & 0xFFFFF000) | + state << MLX5_NIC_IFC_OFFSET, + &dev->iseg->cmdq_addr_l_sz); +} + static void trigger_cmd_completions(struct mlx5_core_dev *dev) { unsigned long flags; @@ -103,7 +106,7 @@ static int in_fatal(struct mlx5_core_dev *dev) struct mlx5_core_health *health = &dev->priv.health; struct health_buffer __iomem *h = health->health; - if (get_nic_state(dev) == MLX5_NIC_IFC_DISABLED) + if (mlx5_get_nic_state(dev) == MLX5_NIC_IFC_DISABLED) return 1; if (ioread32be(&h->fw_ver) == 0xffffffff) @@ -133,7 +136,7 @@ unlock: static void mlx5_handle_bad_state(struct mlx5_core_dev *dev) { - u8 nic_interface = get_nic_state(dev); + u8 nic_interface = mlx5_get_nic_state(dev); switch (nic_interface) { case MLX5_NIC_IFC_FULL: @@ -168,7 +171,7 @@ static void health_recover(struct work_struct *work) priv = container_of(health, struct mlx5_priv, health); dev = container_of(priv, struct mlx5_core_dev, priv); - nic_state = get_nic_state(dev); + nic_state = mlx5_get_nic_state(dev); if (nic_state == MLX5_NIC_IFC_INVALID) { dev_err(&dev->pdev->dev, "health recovery flow aborted since the nic state is invalid\n"); return; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index b5e9f664fc66..28132c7dc05f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1594,12 +1594,17 @@ static const struct pci_error_handlers mlx5_err_handler = { static int mlx5_try_fast_unload(struct mlx5_core_dev *dev) { - int ret; + bool fast_teardown = false, force_teardown = false; + int ret = 1; + + fast_teardown = MLX5_CAP_GEN(dev, fast_teardown); + force_teardown = MLX5_CAP_GEN(dev, force_teardown); + + mlx5_core_dbg(dev, "force teardown firmware support=%d\n", force_teardown); + mlx5_core_dbg(dev, "fast teardown firmware support=%d\n", fast_teardown); - if (!MLX5_CAP_GEN(dev, force_teardown)) { - mlx5_core_dbg(dev, "force teardown is not supported in the firmware\n"); + if (!fast_teardown && !force_teardown) return -EOPNOTSUPP; - } if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) { mlx5_core_dbg(dev, "Device in internal error state, giving up\n"); @@ -1612,13 +1617,19 @@ static int mlx5_try_fast_unload(struct mlx5_core_dev *dev) mlx5_drain_health_wq(dev); mlx5_stop_health_poll(dev, false); + ret = mlx5_cmd_fast_teardown_hca(dev); + if (!ret) + goto succeed; + ret = mlx5_cmd_force_teardown_hca(dev); - if (ret) { - mlx5_core_dbg(dev, "Firmware couldn't do fast unload error: %d\n", ret); - mlx5_start_health_poll(dev); - return ret; - } + if (!ret) + goto succeed; + + mlx5_core_dbg(dev, "Firmware couldn't do fast unload error: %d\n", ret); + mlx5_start_health_poll(dev); + return ret; +succeed: mlx5_enter_error_state(dev, true); /* Some platforms requiring freeing the IRQ's in the shutdown diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index b4134fa0bba3..cc298527baf1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -95,6 +95,8 @@ int mlx5_query_board_id(struct mlx5_core_dev *dev); int mlx5_cmd_init_hca(struct mlx5_core_dev *dev, uint32_t *sw_owner_id); int mlx5_cmd_teardown_hca(struct mlx5_core_dev *dev); int mlx5_cmd_force_teardown_hca(struct mlx5_core_dev *dev); +int mlx5_cmd_fast_teardown_hca(struct mlx5_core_dev *dev); + void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event, unsigned long param); void mlx5_core_page_fault(struct mlx5_core_dev *dev, @@ -214,4 +216,14 @@ int mlx5_lag_allow(struct mlx5_core_dev *dev); int mlx5_lag_forbid(struct mlx5_core_dev *dev); void mlx5_reload_interface(struct mlx5_core_dev *mdev, int protocol); + +enum { + MLX5_NIC_IFC_FULL = 0, + MLX5_NIC_IFC_DISABLED = 1, + MLX5_NIC_IFC_NO_DRAM_NIC = 2, + MLX5_NIC_IFC_INVALID = 3 +}; + +u8 mlx5_get_nic_state(struct mlx5_core_dev *dev); +void mlx5_set_nic_state(struct mlx5_core_dev *dev, u8 state); #endif /* __MLX5_CORE_H__ */ diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 11fa4e66afc5..e9b502d5bcc1 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -504,6 +504,10 @@ struct health_buffer { __be16 ext_synd; }; +enum mlx5_cmd_addr_l_sz_offset { + MLX5_NIC_IFC_OFFSET = 8, +}; + struct mlx5_init_seg { __be32 fw_rev; __be32 cmdif_rev_fw_sub; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index f043d65b9bac..6e8a882052b1 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -896,7 +896,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_mkey[0x6]; u8 reserved_at_f0[0x8]; u8 dump_fill_mkey[0x1]; - u8 reserved_at_f9[0x3]; + u8 reserved_at_f9[0x2]; + u8 fast_teardown[0x1]; u8 log_max_eq[0x4]; u8 max_indirection[0x8]; @@ -3352,12 +3353,13 @@ struct mlx5_ifc_teardown_hca_out_bits { u8 reserved_at_40[0x3f]; - u8 force_state[0x1]; + u8 state[0x1]; }; enum { MLX5_TEARDOWN_HCA_IN_PROFILE_GRACEFUL_CLOSE = 0x0, MLX5_TEARDOWN_HCA_IN_PROFILE_FORCE_CLOSE = 0x1, + MLX5_TEARDOWN_HCA_IN_PROFILE_PREPARE_FAST_TEARDOWN = 0x2, }; struct mlx5_ifc_teardown_hca_in_bits { -- cgit v1.2.3 From bbb4c4323a4d9cb5ca04db904aa3050a7586839a Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 4 Oct 2018 14:27:55 +0100 Subject: dns: Allow the dns resolver to retrieve a server set Allow the DNS resolver to retrieve a set of servers and their associated addresses, ports, preference and weight ratings. In terms of communication with userspace, "srv=1" is added to the callout string (the '1' indicating the maximum data version supported by the kernel) to ask the userspace side for this. If the userspace side doesn't recognise it, it will ignore the option and return the usual text address list. If the userspace side does recognise it, it will return some binary data that begins with a zero byte that would cause the string parsers to give an error. The second byte contains the version of the data in the blob (this may be between 1 and the version specified in the callout data). The remainder of the payload is version-specific. In version 1, the payload looks like (note that this is packed): u8 Non-string marker (ie. 0) u8 Content (0 => Server list) u8 Version (ie. 1) u8 Source (eg. DNS_RECORD_FROM_DNS_SRV) u8 Status (eg. DNS_LOOKUP_GOOD) u8 Number of servers foreach-server { u16 Name length (LE) u16 Priority (as per SRV record) (LE) u16 Weight (as per SRV record) (LE) u16 Port (LE) u8 Source (eg. DNS_RECORD_FROM_NSS) u8 Status (eg. DNS_LOOKUP_GOT_NOT_FOUND) u8 Protocol (eg. DNS_SERVER_PROTOCOL_UDP) u8 Number of addresses char[] Name (not NUL-terminated) foreach-address { u8 Family (AF_INET{,6}) union { u8[4] ipv4_addr u8[16] ipv6_addr } } } This can then be used to fetch a whole cell's VL-server configuration for AFS, for example. Signed-off-by: David Howells Signed-off-by: David S. Miller --- include/linux/dns_resolver.h | 4 +- include/uapi/linux/dns_resolver.h | 116 ++++++++++++++++++++++++++++++++++++++ net/dns_resolver/dns_key.c | 67 +++++++++++++++++++++- net/dns_resolver/dns_query.c | 5 +- 4 files changed, 182 insertions(+), 10 deletions(-) create mode 100644 include/uapi/linux/dns_resolver.h (limited to 'include/linux') diff --git a/include/linux/dns_resolver.h b/include/linux/dns_resolver.h index 6ac3cad9aef1..34a744a1bafc 100644 --- a/include/linux/dns_resolver.h +++ b/include/linux/dns_resolver.h @@ -24,11 +24,9 @@ #ifndef _LINUX_DNS_RESOLVER_H #define _LINUX_DNS_RESOLVER_H -#ifdef __KERNEL__ +#include extern int dns_query(const char *type, const char *name, size_t namelen, const char *options, char **_result, time64_t *_expiry); -#endif /* KERNEL */ - #endif /* _LINUX_DNS_RESOLVER_H */ diff --git a/include/uapi/linux/dns_resolver.h b/include/uapi/linux/dns_resolver.h new file mode 100644 index 000000000000..129745f9c794 --- /dev/null +++ b/include/uapi/linux/dns_resolver.h @@ -0,0 +1,116 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* DNS resolver interface definitions. + * + * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#ifndef _UAPI_LINUX_DNS_RESOLVER_H +#define _UAPI_LINUX_DNS_RESOLVER_H + +#include + +/* + * Type of payload. + */ +enum dns_payload_content_type { + DNS_PAYLOAD_IS_SERVER_LIST = 0, /* List of servers, requested by srv=1 */ +}; + +/* + * Type of address that might be found in an address record. + */ +enum dns_payload_address_type { + DNS_ADDRESS_IS_IPV4 = 0, /* 4-byte AF_INET address */ + DNS_ADDRESS_IS_IPV6 = 1, /* 16-byte AF_INET6 address */ +}; + +/* + * Type of protocol used to access a server. + */ +enum dns_payload_protocol_type { + DNS_SERVER_PROTOCOL_UNSPECIFIED = 0, + DNS_SERVER_PROTOCOL_UDP = 1, /* Use UDP to talk to the server */ + DNS_SERVER_PROTOCOL_TCP = 2, /* Use TCP to talk to the server */ +}; + +/* + * Source of record included in DNS resolver payload. + */ +enum dns_record_source { + DNS_RECORD_UNAVAILABLE = 0, /* No source available (empty record) */ + DNS_RECORD_FROM_CONFIG = 1, /* From local configuration data */ + DNS_RECORD_FROM_DNS_A = 2, /* From DNS A or AAAA record */ + DNS_RECORD_FROM_DNS_AFSDB = 3, /* From DNS AFSDB record */ + DNS_RECORD_FROM_DNS_SRV = 4, /* From DNS SRV record */ + DNS_RECORD_FROM_NSS = 5, /* From NSS */ + NR__dns_record_source +}; + +/* + * Status of record included in DNS resolver payload. + */ +enum dns_lookup_status { + DNS_LOOKUP_NOT_DONE = 0, /* No lookup has been made */ + DNS_LOOKUP_GOOD = 1, /* Good records obtained */ + DNS_LOOKUP_GOOD_WITH_BAD = 2, /* Good records, some decoding errors */ + DNS_LOOKUP_BAD = 3, /* Couldn't decode results */ + DNS_LOOKUP_GOT_NOT_FOUND = 4, /* Got a "Not Found" result */ + DNS_LOOKUP_GOT_LOCAL_FAILURE = 5, /* Local failure during lookup */ + DNS_LOOKUP_GOT_TEMP_FAILURE = 6, /* Temporary failure during lookup */ + DNS_LOOKUP_GOT_NS_FAILURE = 7, /* Name server failure */ + NR__dns_lookup_status +}; + +/* + * Header at the beginning of binary format payload. + */ +struct dns_payload_header { + __u8 zero; /* Zero byte: marks this as not being text */ + __u8 content; /* enum dns_payload_content_type */ + __u8 version; /* Encoding version */ +} __packed; + +/* + * Header at the beginning of a V1 server list. This is followed directly by + * the server records. Each server records begins with a struct of type + * dns_server_list_v1_server. + */ +struct dns_server_list_v1_header { + struct dns_payload_header hdr; + __u8 source; /* enum dns_record_source */ + __u8 status; /* enum dns_lookup_status */ + __u8 nr_servers; /* Number of server records following this */ +} __packed; + +/* + * Header at the beginning of each V1 server record. This is followed by the + * characters of the name with no NUL-terminator, followed by the address + * records for that server. Each address record begins with a struct of type + * struct dns_server_list_v1_address. + */ +struct dns_server_list_v1_server { + __u16 name_len; /* Length of name (LE) */ + __u16 priority; /* Priority (as SRV record) (LE) */ + __u16 weight; /* Weight (as SRV record) (LE) */ + __u16 port; /* UDP/TCP port number (LE) */ + __u8 source; /* enum dns_record_source */ + __u8 status; /* enum dns_lookup_status */ + __u8 protocol; /* enum dns_payload_protocol_type */ + __u8 nr_addrs; +} __packed; + +/* + * Header at the beginning of each V1 address record. This is followed by the + * bytes of the address, 4 for IPV4 and 16 for IPV6. + */ +struct dns_server_list_v1_address { + __u8 address_type; /* enum dns_payload_address_type */ +} __packed; + +#endif /* _UAPI_LINUX_DNS_RESOLVER_H */ diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c index 7f4534828f6c..a65d553e730d 100644 --- a/net/dns_resolver/dns_key.c +++ b/net/dns_resolver/dns_key.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include #include "internal.h" @@ -48,27 +49,86 @@ const struct cred *dns_resolver_cache; /* * Preparse instantiation data for a dns_resolver key. * - * The data must be a NUL-terminated string, with the NUL char accounted in - * datalen. + * For normal hostname lookups, the data must be a NUL-terminated string, with + * the NUL char accounted in datalen. * * If the data contains a '#' characters, then we take the clause after each * one to be an option of the form 'key=value'. The actual data of interest is * the string leading up to the first '#'. For instance: * * "ip1,ip2,...#foo=bar" + * + * For server list requests, the data must begin with a NUL char and be + * followed by a byte indicating the version of the data format. Version 1 + * looks something like (note this is packed): + * + * u8 Non-string marker (ie. 0) + * u8 Content (DNS_PAYLOAD_IS_*) + * u8 Version (e.g. 1) + * u8 Source of server list + * u8 Lookup status of server list + * u8 Number of servers + * foreach-server { + * __le16 Name length + * __le16 Priority (as per SRV record, low first) + * __le16 Weight (as per SRV record, higher first) + * __le16 Port + * u8 Source of address list + * u8 Lookup status of address list + * u8 Protocol (DNS_SERVER_PROTOCOL_*) + * u8 Number of addresses + * char[] Name (not NUL-terminated) + * foreach-address { + * u8 Family (DNS_ADDRESS_IS_*) + * union { + * u8[4] ipv4_addr + * u8[16] ipv6_addr + * } + * } + * } + * */ static int dns_resolver_preparse(struct key_preparsed_payload *prep) { + const struct dns_payload_header *bin; struct user_key_payload *upayload; unsigned long derrno; int ret; int datalen = prep->datalen, result_len = 0; const char *data = prep->data, *end, *opt; + if (datalen <= 1 || !data) + return -EINVAL; + + if (data[0] == 0) { + /* It may be a server list. */ + if (datalen <= sizeof(*bin)) + return -EINVAL; + + bin = (const struct dns_payload_header *)data; + kenter("[%u,%u],%u", bin->content, bin->version, datalen); + if (bin->content != DNS_PAYLOAD_IS_SERVER_LIST) { + pr_warn_ratelimited( + "dns_resolver: Unsupported content type (%u)\n", + bin->content); + return -EINVAL; + } + + if (bin->version != 1) { + pr_warn_ratelimited( + "dns_resolver: Unsupported server list version (%u)\n", + bin->version); + return -EINVAL; + } + + result_len = datalen; + goto store_result; + } + kenter("'%*.*s',%u", datalen, datalen, data, datalen); - if (datalen <= 1 || !data || data[datalen - 1] != '\0') + if (!data || data[datalen - 1] != '\0') return -EINVAL; datalen--; @@ -144,6 +204,7 @@ dns_resolver_preparse(struct key_preparsed_payload *prep) return 0; } +store_result: kdebug("store result"); prep->quotalen = result_len; diff --git a/net/dns_resolver/dns_query.c b/net/dns_resolver/dns_query.c index 49da67034f29..76338c38738a 100644 --- a/net/dns_resolver/dns_query.c +++ b/net/dns_resolver/dns_query.c @@ -148,12 +148,9 @@ int dns_query(const char *type, const char *name, size_t namelen, if (_result) { ret = -ENOMEM; - *_result = kmalloc(len + 1, GFP_KERNEL); + *_result = kmemdup_nul(upayload->data, len, GFP_KERNEL); if (!*_result) goto put; - - memcpy(*_result, upayload->data, len); - (*_result)[len] = '\0'; } if (_expiry) -- cgit v1.2.3 From 5d5a0ab1a7918fce5ca5c0fb1871a3e2000f85de Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Mon, 1 Oct 2018 10:54:51 -0500 Subject: of: Fix property name in of_node_get_device_type Commit 0413bedabc88 ("of: Add device_type access helper functions") added a new helper not yet used in preparation for some treewide clean up of accesses to 'device_type' properties. Unfortunately, there's an error and 'type' was used for the property name. Fix this. Fixes: 0413bedabc88 ("of: Add device_type access helper functions") Cc: Frank Rowand Signed-off-by: Rob Herring --- include/linux/of.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index f581531d797e..04cef4490efc 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -991,7 +991,7 @@ static inline struct device_node *of_find_matching_node( static inline const char *of_node_get_device_type(const struct device_node *np) { - return of_get_property(np, "type", NULL); + return of_get_property(np, "device_type", NULL); } static inline bool of_node_is_type(const struct device_node *np, const char *type) -- cgit v1.2.3 From fae29f135ef4a86228d3ce13b61babf0d3031118 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Tue, 25 Sep 2018 12:35:18 -0400 Subject: hwrng: core - document the quality field quality field is currently documented as being 'per mill'. In fact the math involved is: add_hwgenerator_randomness((void *)rng_fillbuf, rc, rc * current_quality * 8 >> 10); thus the actual definition is "bits of entropy per 1024 bits of input". The current documentation seems to have confused multiple people in the past, let's fix the documentation to match code. An alternative is to change core to match driver expectations, replacing rc * current_quality * 8 >> 10 with rc * current_quality / 1000 but that has performance costs, so probably isn't a good option. Fixes: 0f734e6e768 ("hwrng: add per-device entropy derating") Reported-by: "Dr. David Alan Gilbert" Signed-off-by: Michael S. Tsirkin Signed-off-by: Herbert Xu --- drivers/char/hw_random/core.c | 4 ++-- include/linux/hw_random.h | 3 ++- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c index aaf9e5afaad4..95be7228f327 100644 --- a/drivers/char/hw_random/core.c +++ b/drivers/char/hw_random/core.c @@ -44,10 +44,10 @@ static unsigned short default_quality; /* = 0; default to "off" */ module_param(current_quality, ushort, 0644); MODULE_PARM_DESC(current_quality, - "current hwrng entropy estimation per mill"); + "current hwrng entropy estimation per 1024 bits of input"); module_param(default_quality, ushort, 0644); MODULE_PARM_DESC(default_quality, - "default entropy content of hwrng per mill"); + "default entropy content of hwrng per 1024 bits of input"); static void drop_current_rng(void); static int hwrng_init(struct hwrng *rng); diff --git a/include/linux/hw_random.h b/include/linux/hw_random.h index bee0827766a3..c0b93e0ff0c0 100644 --- a/include/linux/hw_random.h +++ b/include/linux/hw_random.h @@ -33,7 +33,8 @@ * and max is a multiple of 4 and >= 32 bytes. * @priv: Private data, for use by the RNG driver. * @quality: Estimation of true entropy in RNG's bitstream - * (per mill). + * (in bits of entropy per 1024 bits of input; + * valid values: 1 to 1024, or 0 for unknown). */ struct hwrng { const char *name; -- cgit v1.2.3 From 661b8d1b0e3a745e25f05adef2ebd00d830eeea7 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Mon, 1 Oct 2018 14:51:33 +0200 Subject: net: add umem reference in netdev{_rx}_queue These references to the umem will be used to store information on what kind of AF_XDP umem that is bound to a queue id, if any. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann --- include/linux/netdevice.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1cbbf77a685f..8318f79586c2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -609,6 +609,9 @@ struct netdev_queue { /* Subordinate device that the queue has been assigned to */ struct net_device *sb_dev; +#ifdef CONFIG_XDP_SOCKETS + struct xdp_umem *umem; +#endif /* * write-mostly part */ @@ -738,6 +741,9 @@ struct netdev_rx_queue { struct kobject kobj; struct net_device *dev; struct xdp_rxq_info xdp_rxq; +#ifdef CONFIG_XDP_SOCKETS + struct xdp_umem *umem; +#endif } ____cacheline_aligned_in_smp; /* -- cgit v1.2.3 From c2a90025ad09d830c8d8ae69f485eac6aaaa2472 Mon Sep 17 00:00:00 2001 From: Quentin Schulz Date: Thu, 4 Oct 2018 14:22:03 +0200 Subject: phy: add QSGMII and PCIE modes Prepare for upcoming phys that'll handle QSGMII or PCIe. Reviewed-by: Florian Fainelli Signed-off-by: Quentin Schulz Signed-off-by: David S. Miller --- include/linux/phy/phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h index 9713aebdd348..03b319f89a34 100644 --- a/include/linux/phy/phy.h +++ b/include/linux/phy/phy.h @@ -37,9 +37,11 @@ enum phy_mode { PHY_MODE_USB_OTG, PHY_MODE_SGMII, PHY_MODE_2500SGMII, + PHY_MODE_QSGMII, PHY_MODE_10GKR, PHY_MODE_UFS_HS_A, PHY_MODE_UFS_HS_B, + PHY_MODE_PCIE, }; /** -- cgit v1.2.3 From c941ce9c282cc606e6517356fcc186a9da2b4ab9 Mon Sep 17 00:00:00 2001 From: Quentin Monnet Date: Sun, 7 Oct 2018 12:56:47 +0100 Subject: bpf: add verifier callback to get stack usage info for offloaded progs In preparation for BPF-to-BPF calls in offloaded programs, add a new function attribute to the struct bpf_prog_offload_ops so that drivers supporting eBPF offload can hook at the end of program verification, and potentially extract information collected by the verifier. Implement a minimal callback (returning 0) in the drivers providing the structs, namely netdevsim and nfp. This will be useful in the nfp driver, in later commits, to extract the number of subprograms as well as the stack depth for those subprograms. Signed-off-by: Quentin Monnet Reviewed-by: Jiong Wang Reviewed-by: Jakub Kicinski Signed-off-by: Daniel Borkmann --- drivers/net/ethernet/netronome/nfp/bpf/verifier.c | 8 +++++++- drivers/net/netdevsim/bpf.c | 8 +++++++- include/linux/bpf.h | 1 + include/linux/bpf_verifier.h | 1 + kernel/bpf/offload.c | 18 ++++++++++++++++++ kernel/bpf/verifier.c | 3 +++ 6 files changed, 37 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c index a6e9248669e1..e470489021e3 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c @@ -640,6 +640,12 @@ nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx) return 0; } +static int nfp_bpf_finalize(struct bpf_verifier_env *env) +{ + return 0; +} + const struct bpf_prog_offload_ops nfp_bpf_analyzer_ops = { - .insn_hook = nfp_verify_insn, + .insn_hook = nfp_verify_insn, + .finalize = nfp_bpf_finalize, }; diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c index 81444208b216..cb3518474f0e 100644 --- a/drivers/net/netdevsim/bpf.c +++ b/drivers/net/netdevsim/bpf.c @@ -86,8 +86,14 @@ nsim_bpf_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn) return 0; } +static int nsim_bpf_finalize(struct bpf_verifier_env *env) +{ + return 0; +} + static const struct bpf_prog_offload_ops nsim_bpf_analyzer_ops = { - .insn_hook = nsim_bpf_verify_insn, + .insn_hook = nsim_bpf_verify_insn, + .finalize = nsim_bpf_finalize, }; static bool nsim_xdp_offload_active(struct netdevsim *ns) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 027697b6a22f..9b558713447f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -263,6 +263,7 @@ struct bpf_verifier_ops { struct bpf_prog_offload_ops { int (*insn_hook)(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx); + int (*finalize)(struct bpf_verifier_env *env); }; struct bpf_prog_offload { diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 7b6fd2ab3263..9e8056ec20fa 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -245,5 +245,6 @@ static inline struct bpf_reg_state *cur_regs(struct bpf_verifier_env *env) int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env); int bpf_prog_offload_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx); +int bpf_prog_offload_finalize(struct bpf_verifier_env *env); #endif /* _LINUX_BPF_VERIFIER_H */ diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index 177a52436394..8e93c47f0779 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -172,6 +172,24 @@ int bpf_prog_offload_verify_insn(struct bpf_verifier_env *env, return ret; } +int bpf_prog_offload_finalize(struct bpf_verifier_env *env) +{ + struct bpf_prog_offload *offload; + int ret = -ENODEV; + + down_read(&bpf_devs_lock); + offload = env->prog->aux->offload; + if (offload) { + if (offload->dev_ops->finalize) + ret = offload->dev_ops->finalize(env); + else + ret = 0; + } + up_read(&bpf_devs_lock); + + return ret; +} + static void __bpf_prog_offload_destroy(struct bpf_prog *prog) { struct bpf_prog_offload *offload = prog->aux->offload; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 73c81bef6ae8..a0454cb299ba 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6309,6 +6309,9 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) env->cur_state = NULL; } + if (ret == 0 && bpf_prog_is_dev_bound(env->prog->aux)) + ret = bpf_prog_offload_finalize(env); + skip_full_check: while (!pop_stack(env, NULL, NULL)); free_states(env); -- cgit v1.2.3 From 0792a2c8e0bbda3605b8d42c6b9635be7b19982a Mon Sep 17 00:00:00 2001 From: Finn Thain Date: Tue, 11 Sep 2018 20:18:44 -0400 Subject: macintosh: Use common code to access RTC Now that the 68k Mac port has adopted the via-pmu driver, the same RTC code can be shared between m68k and powerpc. Replace duplicated code in arch/powerpc and arch/m68k with common RTC accessors for Cuda and PMU. Drop the problematic WARN_ON which was introduced in commit 22db552b50fa ("powerpc/powermac: Fix rtc read/write functions"). Tested-by: Stan Johnson Signed-off-by: Finn Thain Cc: Geert Uytterhoeven Cc: Arnd Bergmann Acked-by: Geert Uytterhoeven Signed-off-by: Michael Ellerman --- arch/m68k/mac/misc.c | 75 +++----------------- arch/powerpc/platforms/powermac/time.c | 126 ++++++--------------------------- drivers/macintosh/via-cuda.c | 35 +++++++++ drivers/macintosh/via-pmu.c | 33 +++++++++ include/linux/cuda.h | 4 ++ include/linux/pmu.h | 4 ++ 6 files changed, 106 insertions(+), 171 deletions(-) (limited to 'include/linux') diff --git a/arch/m68k/mac/misc.c b/arch/m68k/mac/misc.c index 1b083c500b9a..ebb3b6d169ea 100644 --- a/arch/m68k/mac/misc.c +++ b/arch/m68k/mac/misc.c @@ -37,35 +37,6 @@ static void (*rom_reset)(void); #ifdef CONFIG_ADB_CUDA -static time64_t cuda_read_time(void) -{ - struct adb_request req; - time64_t time; - - if (cuda_request(&req, NULL, 2, CUDA_PACKET, CUDA_GET_TIME) < 0) - return 0; - while (!req.complete) - cuda_poll(); - - time = (u32)((req.reply[3] << 24) | (req.reply[4] << 16) | - (req.reply[5] << 8) | req.reply[6]); - - return time - RTC_OFFSET; -} - -static void cuda_write_time(time64_t time) -{ - struct adb_request req; - u32 data = lower_32_bits(time + RTC_OFFSET); - - if (cuda_request(&req, NULL, 6, CUDA_PACKET, CUDA_SET_TIME, - (data >> 24) & 0xFF, (data >> 16) & 0xFF, - (data >> 8) & 0xFF, data & 0xFF) < 0) - return; - while (!req.complete) - cuda_poll(); -} - static __u8 cuda_read_pram(int offset) { struct adb_request req; @@ -91,33 +62,6 @@ static void cuda_write_pram(int offset, __u8 data) #endif /* CONFIG_ADB_CUDA */ #ifdef CONFIG_ADB_PMU -static time64_t pmu_read_time(void) -{ - struct adb_request req; - time64_t time; - - if (pmu_request(&req, NULL, 1, PMU_READ_RTC) < 0) - return 0; - pmu_wait_complete(&req); - - time = (u32)((req.reply[0] << 24) | (req.reply[1] << 16) | - (req.reply[2] << 8) | req.reply[3]); - - return time - RTC_OFFSET; -} - -static void pmu_write_time(time64_t time) -{ - struct adb_request req; - u32 data = lower_32_bits(time + RTC_OFFSET); - - if (pmu_request(&req, NULL, 5, PMU_SET_RTC, - (data >> 24) & 0xFF, (data >> 16) & 0xFF, - (data >> 8) & 0xFF, data & 0xFF) < 0) - return; - pmu_wait_complete(&req); -} - static __u8 pmu_read_pram(int offset) { struct adb_request req; @@ -295,13 +239,17 @@ static time64_t via_read_time(void) * is basically any machine with Mac II-style ADB. */ -static void via_write_time(time64_t time) +static void via_set_rtc_time(struct rtc_time *tm) { union { __u8 cdata[4]; __u32 idata; } data; __u8 temp; + time64_t time; + + time = mktime64(tm->tm_year + 1900, tm->tm_mon + 1, tm->tm_mday, + tm->tm_hour, tm->tm_min, tm->tm_sec); /* Clear the write protect bit */ @@ -641,12 +589,12 @@ int mac_hwclk(int op, struct rtc_time *t) #ifdef CONFIG_ADB_CUDA case MAC_ADB_EGRET: case MAC_ADB_CUDA: - now = cuda_read_time(); + now = cuda_get_time(); break; #endif #ifdef CONFIG_ADB_PMU case MAC_ADB_PB2: - now = pmu_read_time(); + now = pmu_get_time(); break; #endif default: @@ -665,24 +613,21 @@ int mac_hwclk(int op, struct rtc_time *t) __func__, t->tm_year + 1900, t->tm_mon + 1, t->tm_mday, t->tm_hour, t->tm_min, t->tm_sec); - now = mktime64(t->tm_year + 1900, t->tm_mon + 1, t->tm_mday, - t->tm_hour, t->tm_min, t->tm_sec); - switch (macintosh_config->adb_type) { case MAC_ADB_IOP: case MAC_ADB_II: case MAC_ADB_PB1: - via_write_time(now); + via_set_rtc_time(t); break; #ifdef CONFIG_ADB_CUDA case MAC_ADB_EGRET: case MAC_ADB_CUDA: - cuda_write_time(now); + cuda_set_rtc_time(t); break; #endif #ifdef CONFIG_ADB_PMU case MAC_ADB_PB2: - pmu_write_time(now); + pmu_set_rtc_time(t); break; #endif default: diff --git a/arch/powerpc/platforms/powermac/time.c b/arch/powerpc/platforms/powermac/time.c index f92c1918fb56..f157e3d071f2 100644 --- a/arch/powerpc/platforms/powermac/time.c +++ b/arch/powerpc/platforms/powermac/time.c @@ -44,13 +44,6 @@ #define DBG(x...) #endif -/* - * Offset between Unix time (1970-based) and Mac time (1904-based). Cuda and PMU - * times wrap in 2040. If we need to handle later times, the read_time functions - * need to be changed to interpret wrapped times as post-2040. - */ -#define RTC_OFFSET 2082844800 - /* * Calibrate the decrementer frequency with the VIA timer 1. */ @@ -90,98 +83,6 @@ long __init pmac_time_init(void) return delta; } -#ifdef CONFIG_ADB_CUDA -static time64_t cuda_get_time(void) -{ - struct adb_request req; - time64_t now; - - if (cuda_request(&req, NULL, 2, CUDA_PACKET, CUDA_GET_TIME) < 0) - return 0; - while (!req.complete) - cuda_poll(); - if (req.reply_len != 7) - printk(KERN_ERR "cuda_get_time: got %d byte reply\n", - req.reply_len); - now = (u32)((req.reply[3] << 24) + (req.reply[4] << 16) + - (req.reply[5] << 8) + req.reply[6]); - /* it's either after year 2040, or the RTC has gone backwards */ - WARN_ON(now < RTC_OFFSET); - - return now - RTC_OFFSET; -} - -#define cuda_get_rtc_time(tm) rtc_time64_to_tm(cuda_get_time(), (tm)) - -static int cuda_set_rtc_time(struct rtc_time *tm) -{ - u32 nowtime; - struct adb_request req; - - nowtime = lower_32_bits(rtc_tm_to_time64(tm) + RTC_OFFSET); - if (cuda_request(&req, NULL, 6, CUDA_PACKET, CUDA_SET_TIME, - nowtime >> 24, nowtime >> 16, nowtime >> 8, - nowtime) < 0) - return -ENXIO; - while (!req.complete) - cuda_poll(); - if ((req.reply_len != 3) && (req.reply_len != 7)) - printk(KERN_ERR "cuda_set_rtc_time: got %d byte reply\n", - req.reply_len); - return 0; -} - -#else -#define cuda_get_time() 0 -#define cuda_get_rtc_time(tm) -#define cuda_set_rtc_time(tm) 0 -#endif - -#ifdef CONFIG_ADB_PMU -static time64_t pmu_get_time(void) -{ - struct adb_request req; - time64_t now; - - if (pmu_request(&req, NULL, 1, PMU_READ_RTC) < 0) - return 0; - pmu_wait_complete(&req); - if (req.reply_len != 4) - printk(KERN_ERR "pmu_get_time: got %d byte reply from PMU\n", - req.reply_len); - now = (u32)((req.reply[0] << 24) + (req.reply[1] << 16) + - (req.reply[2] << 8) + req.reply[3]); - - /* it's either after year 2040, or the RTC has gone backwards */ - WARN_ON(now < RTC_OFFSET); - - return now - RTC_OFFSET; -} - -#define pmu_get_rtc_time(tm) rtc_time64_to_tm(pmu_get_time(), (tm)) - -static int pmu_set_rtc_time(struct rtc_time *tm) -{ - u32 nowtime; - struct adb_request req; - - nowtime = lower_32_bits(rtc_tm_to_time64(tm) + RTC_OFFSET); - if (pmu_request(&req, NULL, 5, PMU_SET_RTC, nowtime >> 24, - nowtime >> 16, nowtime >> 8, nowtime) < 0) - return -ENXIO; - pmu_wait_complete(&req); - if (req.reply_len != 0) - printk(KERN_ERR "pmu_set_rtc_time: %d byte reply from PMU\n", - req.reply_len); - return 0; -} - -#else -#define pmu_get_time() 0 -#define pmu_get_rtc_time(tm) -#define pmu_set_rtc_time(tm) 0 -#endif - #ifdef CONFIG_PMAC_SMU static time64_t smu_get_time(void) { @@ -191,11 +92,6 @@ static time64_t smu_get_time(void) return 0; return rtc_tm_to_time64(&tm); } - -#else -#define smu_get_time() 0 -#define smu_get_rtc_time(tm, spin) -#define smu_set_rtc_time(tm, spin) 0 #endif /* Can't be __init, it's called when suspending and resuming */ @@ -203,12 +99,18 @@ time64_t pmac_get_boot_time(void) { /* Get the time from the RTC, used only at boot time */ switch (sys_ctrler) { +#ifdef CONFIG_ADB_CUDA case SYS_CTRLER_CUDA: return cuda_get_time(); +#endif +#ifdef CONFIG_ADB_PMU case SYS_CTRLER_PMU: return pmu_get_time(); +#endif +#ifdef CONFIG_PMAC_SMU case SYS_CTRLER_SMU: return smu_get_time(); +#endif default: return 0; } @@ -218,15 +120,21 @@ void pmac_get_rtc_time(struct rtc_time *tm) { /* Get the time from the RTC, used only at boot time */ switch (sys_ctrler) { +#ifdef CONFIG_ADB_CUDA case SYS_CTRLER_CUDA: - cuda_get_rtc_time(tm); + rtc_time64_to_tm(cuda_get_time(), tm); break; +#endif +#ifdef CONFIG_ADB_PMU case SYS_CTRLER_PMU: - pmu_get_rtc_time(tm); + rtc_time64_to_tm(pmu_get_time(), tm); break; +#endif +#ifdef CONFIG_PMAC_SMU case SYS_CTRLER_SMU: smu_get_rtc_time(tm, 1); break; +#endif default: ; } @@ -235,12 +143,18 @@ void pmac_get_rtc_time(struct rtc_time *tm) int pmac_set_rtc_time(struct rtc_time *tm) { switch (sys_ctrler) { +#ifdef CONFIG_ADB_CUDA case SYS_CTRLER_CUDA: return cuda_set_rtc_time(tm); +#endif +#ifdef CONFIG_ADB_PMU case SYS_CTRLER_PMU: return pmu_set_rtc_time(tm); +#endif +#ifdef CONFIG_PMAC_SMU case SYS_CTRLER_SMU: return smu_set_rtc_time(tm, 1); +#endif default: return -ENODEV; } diff --git a/drivers/macintosh/via-cuda.c b/drivers/macintosh/via-cuda.c index 98dd702eb867..bbec6ac0a966 100644 --- a/drivers/macintosh/via-cuda.c +++ b/drivers/macintosh/via-cuda.c @@ -766,3 +766,38 @@ cuda_input(unsigned char *buf, int nb) buf, nb, false); } } + +/* Offset between Unix time (1970-based) and Mac time (1904-based) */ +#define RTC_OFFSET 2082844800 + +time64_t cuda_get_time(void) +{ + struct adb_request req; + u32 now; + + if (cuda_request(&req, NULL, 2, CUDA_PACKET, CUDA_GET_TIME) < 0) + return 0; + while (!req.complete) + cuda_poll(); + if (req.reply_len != 7) + pr_err("%s: got %d byte reply\n", __func__, req.reply_len); + now = (req.reply[3] << 24) + (req.reply[4] << 16) + + (req.reply[5] << 8) + req.reply[6]; + return (time64_t)now - RTC_OFFSET; +} + +int cuda_set_rtc_time(struct rtc_time *tm) +{ + u32 now; + struct adb_request req; + + now = lower_32_bits(rtc_tm_to_time64(tm) + RTC_OFFSET); + if (cuda_request(&req, NULL, 6, CUDA_PACKET, CUDA_SET_TIME, + now >> 24, now >> 16, now >> 8, now) < 0) + return -ENXIO; + while (!req.complete) + cuda_poll(); + if ((req.reply_len != 3) && (req.reply_len != 7)) + pr_err("%s: got %d byte reply\n", __func__, req.reply_len); + return 0; +} diff --git a/drivers/macintosh/via-pmu.c b/drivers/macintosh/via-pmu.c index d72c450aebe5..60f57e2abf21 100644 --- a/drivers/macintosh/via-pmu.c +++ b/drivers/macintosh/via-pmu.c @@ -1737,6 +1737,39 @@ pmu_enable_irled(int on) pmu_wait_complete(&req); } +/* Offset between Unix time (1970-based) and Mac time (1904-based) */ +#define RTC_OFFSET 2082844800 + +time64_t pmu_get_time(void) +{ + struct adb_request req; + u32 now; + + if (pmu_request(&req, NULL, 1, PMU_READ_RTC) < 0) + return 0; + pmu_wait_complete(&req); + if (req.reply_len != 4) + pr_err("%s: got %d byte reply\n", __func__, req.reply_len); + now = (req.reply[0] << 24) + (req.reply[1] << 16) + + (req.reply[2] << 8) + req.reply[3]; + return (time64_t)now - RTC_OFFSET; +} + +int pmu_set_rtc_time(struct rtc_time *tm) +{ + u32 now; + struct adb_request req; + + now = lower_32_bits(rtc_tm_to_time64(tm) + RTC_OFFSET); + if (pmu_request(&req, NULL, 5, PMU_SET_RTC, + now >> 24, now >> 16, now >> 8, now) < 0) + return -ENXIO; + pmu_wait_complete(&req); + if (req.reply_len != 0) + pr_err("%s: got %d byte reply\n", __func__, req.reply_len); + return 0; +} + void pmu_restart(void) { diff --git a/include/linux/cuda.h b/include/linux/cuda.h index 056867f09a01..45bfe9d61271 100644 --- a/include/linux/cuda.h +++ b/include/linux/cuda.h @@ -8,6 +8,7 @@ #ifndef _LINUX_CUDA_H #define _LINUX_CUDA_H +#include #include @@ -16,4 +17,7 @@ extern int cuda_request(struct adb_request *req, void (*done)(struct adb_request *), int nbytes, ...); extern void cuda_poll(void); +extern time64_t cuda_get_time(void); +extern int cuda_set_rtc_time(struct rtc_time *tm); + #endif /* _LINUX_CUDA_H */ diff --git a/include/linux/pmu.h b/include/linux/pmu.h index 9ac8fc60ad49..52453a24a24f 100644 --- a/include/linux/pmu.h +++ b/include/linux/pmu.h @@ -9,6 +9,7 @@ #ifndef _LINUX_PMU_H #define _LINUX_PMU_H +#include #include @@ -36,6 +37,9 @@ static inline void pmu_resume(void) extern void pmu_enable_irled(int on); +extern time64_t pmu_get_time(void); +extern int pmu_set_rtc_time(struct rtc_time *tm); + extern void pmu_restart(void); extern void pmu_shutdown(void); extern void pmu_unlock(void); -- cgit v1.2.3 From 4a19edb60d0203cd5bf95a8b46ea8f63fd41194c Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sun, 7 Oct 2018 20:16:22 -0700 Subject: netlink: Pass extack to dump handlers Declare extack in netlink_dump and pass to dump handlers via netlink_callback. Add any extack message after the dump_done_errno allowing error messages to be returned. This will be useful when strict checking is done on dump requests, returning why the dump fails EINVAL. Signed-off-by: David Ahern Acked-by: Christian Brauner Signed-off-by: David S. Miller --- include/linux/netlink.h | 1 + net/netlink/af_netlink.c | 12 +++++++++++- 2 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 71f121b66ca8..88c8a2d83eb3 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -176,6 +176,7 @@ struct netlink_callback { void *data; /* the module that dump function belong to */ struct module *module; + struct netlink_ext_ack *extack; u16 family; u16 min_dump_alloc; unsigned int prev_seq, seq; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index e3a0538ec0be..7ac585f33a9e 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2171,6 +2171,7 @@ EXPORT_SYMBOL(__nlmsg_put); static int netlink_dump(struct sock *sk) { struct netlink_sock *nlk = nlk_sk(sk); + struct netlink_ext_ack extack = {}; struct netlink_callback *cb; struct sk_buff *skb = NULL; struct nlmsghdr *nlh; @@ -2222,8 +2223,11 @@ static int netlink_dump(struct sock *sk) skb_reserve(skb, skb_tailroom(skb) - alloc_size); netlink_skb_set_owner_r(skb, sk); - if (nlk->dump_done_errno > 0) + if (nlk->dump_done_errno > 0) { + cb->extack = &extack; nlk->dump_done_errno = cb->dump(skb, cb); + cb->extack = NULL; + } if (nlk->dump_done_errno > 0 || skb_tailroom(skb) < nlmsg_total_size(sizeof(nlk->dump_done_errno))) { @@ -2246,6 +2250,12 @@ static int netlink_dump(struct sock *sk) memcpy(nlmsg_data(nlh), &nlk->dump_done_errno, sizeof(nlk->dump_done_errno)); + if (extack._msg && nlk->flags & NETLINK_F_EXT_ACK) { + nlh->nlmsg_flags |= NLM_F_ACK_TLVS; + if (!nla_put_string(skb, NLMSGERR_ATTR_MSG, extack._msg)) + nlmsg_end(skb, nlh); + } + if (sk_filter(sk, skb)) kfree_skb(skb); else -- cgit v1.2.3 From 89d35528d17d25819a755a2b52931e911baebc66 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sun, 7 Oct 2018 20:16:27 -0700 Subject: netlink: Add new socket option to enable strict checking on dumps Add a new socket option, NETLINK_DUMP_STRICT_CHK, that userspace can use via setsockopt to request strict checking of headers and attributes on dump requests. To get dump features such as kernel side filtering based on data in the header or attributes appended to the dump request, userspace must call setsockopt() for NETLINK_DUMP_STRICT_CHK and a non-zero value. Since the netlink sock and its flags are private to the af_netlink code, the strict checking flag is passed to dump handlers via a flag in the netlink_callback struct. For old userspace on new kernel there is no impact as all of the data checks in later patches are wrapped in a check on the new strict flag. For new userspace on old kernel, the setsockopt will fail and even if new userspace sets data in the headers and appended attributes the kernel will silently ignore it. Moving forward when the setsockopt succeeds, the new userspace on old kernel means the dump request can pass an attribute the kernel does not understand. The dump will then fail as the older kernel does not understand it. New userspace on new kernel setting the socket option gets the benefit of the improved data dump. Kernel side the NETLINK_DUMP_STRICT_CHK uapi is converted to a generic NETLINK_F_STRICT_CHK flag which can potentially be leveraged for tighter checking on the NEW, DEL, and SET commands. Signed-off-by: David Ahern Acked-by: Christian Brauner Signed-off-by: David S. Miller --- include/linux/netlink.h | 1 + include/uapi/linux/netlink.h | 1 + net/netlink/af_netlink.c | 21 ++++++++++++++++++++- net/netlink/af_netlink.h | 1 + 4 files changed, 23 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 88c8a2d83eb3..72580f1a72a2 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -179,6 +179,7 @@ struct netlink_callback { struct netlink_ext_ack *extack; u16 family; u16 min_dump_alloc; + bool strict_check; unsigned int prev_seq, seq; long args[6]; }; diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h index 776bc92e9118..486ed1f0c0bc 100644 --- a/include/uapi/linux/netlink.h +++ b/include/uapi/linux/netlink.h @@ -155,6 +155,7 @@ enum nlmsgerr_attrs { #define NETLINK_LIST_MEMBERSHIPS 9 #define NETLINK_CAP_ACK 10 #define NETLINK_EXT_ACK 11 +#define NETLINK_DUMP_STRICT_CHK 12 struct nl_pktinfo { __u32 group; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 7ac585f33a9e..e613a9f89600 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1706,6 +1706,13 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname, nlk->flags &= ~NETLINK_F_EXT_ACK; err = 0; break; + case NETLINK_DUMP_STRICT_CHK: + if (val) + nlk->flags |= NETLINK_F_STRICT_CHK; + else + nlk->flags &= ~NETLINK_F_STRICT_CHK; + err = 0; + break; default: err = -ENOPROTOOPT; } @@ -1799,6 +1806,15 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname, return -EFAULT; err = 0; break; + case NETLINK_DUMP_STRICT_CHK: + if (len < sizeof(int)) + return -EINVAL; + len = sizeof(int); + val = nlk->flags & NETLINK_F_STRICT_CHK ? 1 : 0; + if (put_user(len, optlen) || put_user(val, optval)) + return -EFAULT; + err = 0; + break; default: err = -ENOPROTOOPT; } @@ -2282,9 +2298,9 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, const struct nlmsghdr *nlh, struct netlink_dump_control *control) { + struct netlink_sock *nlk, *nlk2; struct netlink_callback *cb; struct sock *sk; - struct netlink_sock *nlk; int ret; refcount_inc(&skb->users); @@ -2318,6 +2334,9 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, cb->min_dump_alloc = control->min_dump_alloc; cb->skb = skb; + nlk2 = nlk_sk(NETLINK_CB(skb).sk); + cb->strict_check = !!(nlk2->flags & NETLINK_F_STRICT_CHK); + if (control->start) { ret = control->start(cb); if (ret) diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h index 962de7b3c023..5f454c8de6a4 100644 --- a/net/netlink/af_netlink.h +++ b/net/netlink/af_netlink.h @@ -15,6 +15,7 @@ #define NETLINK_F_LISTEN_ALL_NSID 0x10 #define NETLINK_F_CAP_ACK 0x20 #define NETLINK_F_EXT_ACK 0x40 +#define NETLINK_F_STRICT_CHK 0x80 #define NLGRPSZ(x) (ALIGN(x, sizeof(unsigned long) * 8) / 8) #define NLGRPLONGS(x) (NLGRPSZ(x)/sizeof(unsigned long)) -- cgit v1.2.3 From b8d62f33b7b225935649ab165d901fe8dd7f95e5 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 8 Oct 2018 13:17:26 +0200 Subject: genirq: Fix grammar s/an /a / Fix a grammar mistake in . [ mingo: While at it also fix another similar error in another comment as well. ] Signed-off-by: Geert Uytterhoeven Cc: Jiri Kosina Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20181008111726.26286-1-geert%2Brenesas@glider.be Signed-off-by: Ingo Molnar --- include/linux/interrupt.h | 2 +- kernel/irq/irqdomain.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index eeceac3376fc..1d6711c28271 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -45,7 +45,7 @@ * IRQF_PERCPU - Interrupt is per cpu * IRQF_NOBALANCING - Flag to exclude this interrupt from irq balancing * IRQF_IRQPOLL - Interrupt is used for polling (only the interrupt that is - * registered first in an shared interrupt is considered for + * registered first in a shared interrupt is considered for * performance reasons) * IRQF_ONESHOT - Interrupt is not reenabled after the hardirq handler finished. * Used by threaded interrupts which need to keep the diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 3b30a4aeb0db..3366d11c3e02 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -867,7 +867,7 @@ void irq_dispose_mapping(unsigned int virq) EXPORT_SYMBOL_GPL(irq_dispose_mapping); /** - * irq_find_mapping() - Find a linux irq from an hw irq number. + * irq_find_mapping() - Find a linux irq from a hw irq number. * @domain: domain owning this hardware interrupt * @hwirq: hardware irq number in that domain space */ -- cgit v1.2.3 From 78d8f8f1a1800cf6068ffcac7a14cda19ae693d8 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Fri, 5 Oct 2018 11:41:13 -0700 Subject: mfd: cros: add "base attached" MKBP switch definition This adds a "base attached" switch definition to the MKBP protocol that is used by Whiskers driver to properly determine device state (clamshell vs tablet mode). Signed-off-by: Dmitry Torokhov Acked-by: Lee Jones Signed-off-by: Jiri Kosina --- include/linux/mfd/cros_ec_commands.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/cros_ec_commands.h b/include/linux/mfd/cros_ec_commands.h index 6e1ab9bead28..7690f0793965 100644 --- a/include/linux/mfd/cros_ec_commands.h +++ b/include/linux/mfd/cros_ec_commands.h @@ -2132,6 +2132,7 @@ struct ec_response_get_next_event_v1 { /* Switches */ #define EC_MKBP_LID_OPEN 0 #define EC_MKBP_TABLET_MODE 1 +#define EC_MKBP_BASE_ATTACHED 2 /*****************************************************************************/ /* Temperature sensor commands */ -- cgit v1.2.3 From 52916982af48d9f9fc01ad825259de1eb3a9b25e Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Thu, 4 Oct 2018 15:27:35 -0600 Subject: PCI/P2PDMA: Support peer-to-peer memory Some PCI devices may have memory mapped in a BAR space that's intended for use in peer-to-peer transactions. To enable such transactions the memory must be registered with ZONE_DEVICE pages so it can be used by DMA interfaces in existing drivers. Add an interface for other subsystems to find and allocate chunks of P2P memory as necessary to facilitate transfers between two PCI peers: struct pci_dev *pci_p2pmem_find[_many](); int pci_p2pdma_distance[_many](); void *pci_alloc_p2pmem(); The new interface requires a driver to collect a list of client devices involved in the transaction then call pci_p2pmem_find() to obtain any suitable P2P memory. Alternatively, if the caller knows a device which provides P2P memory, they can use pci_p2pdma_distance() to determine if it is usable. With a suitable p2pmem device, memory can then be allocated with pci_alloc_p2pmem() for use in DMA transactions. Depending on hardware, using peer-to-peer memory may reduce the bandwidth of the transfer but can significantly reduce pressure on system memory. This may be desirable in many cases: for example a system could be designed with a small CPU connected to a PCIe switch by a small number of lanes which would maximize the number of lanes available to connect to NVMe devices. The code is designed to only utilize the p2pmem device if all the devices involved in a transfer are behind the same PCI bridge. This is because we have no way of knowing whether peer-to-peer routing between PCIe Root Ports is supported (PCIe r4.0, sec 1.3.1). Additionally, the benefits of P2P transfers that go through the RC is limited to only reducing DRAM usage and, in some cases, coding convenience. The PCI-SIG may be exploring adding a new capability bit to advertise whether this is possible for future hardware. This commit includes significant rework and feedback from Christoph Hellwig. Signed-off-by: Christoph Hellwig Signed-off-by: Logan Gunthorpe [bhelgaas: fold in fix from Keith Busch : https://lore.kernel.org/linux-pci/20181012155920.15418-1-keith.busch@intel.com, to address comment from Dan Carpenter , fold in https://lore.kernel.org/linux-pci/20181017160510.17926-1-logang@deltatee.com] Signed-off-by: Bjorn Helgaas --- drivers/pci/Kconfig | 17 ++ drivers/pci/Makefile | 1 + drivers/pci/p2pdma.c | 626 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/memremap.h | 5 + include/linux/mm.h | 18 ++ include/linux/pci-p2pdma.h | 92 +++++++ include/linux/pci.h | 4 + 7 files changed, 763 insertions(+) create mode 100644 drivers/pci/p2pdma.c create mode 100644 include/linux/pci-p2pdma.h (limited to 'include/linux') diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig index 56ff8f6d31fc..deb68be4fdac 100644 --- a/drivers/pci/Kconfig +++ b/drivers/pci/Kconfig @@ -132,6 +132,23 @@ config PCI_PASID If unsure, say N. +config PCI_P2PDMA + bool "PCI peer-to-peer transfer support" + depends on PCI && ZONE_DEVICE + select GENERIC_ALLOCATOR + help + EnableÑ• drivers to do PCI peer-to-peer transactions to and from + BARs that are exposed in other devices that are the part of + the hierarchy where peer-to-peer DMA is guaranteed by the PCI + specification to work (ie. anything below a single PCI bridge). + + Many PCIe root complexes do not support P2P transactions and + it's hard to tell which support it at all, so at this time, + P2P DMA transations must be between devices behind the same root + port. + + If unsure, say N. + config PCI_LABEL def_bool y if (DMI || ACPI) depends on PCI diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile index 1b2cfe51e8d7..85f4a703b2be 100644 --- a/drivers/pci/Makefile +++ b/drivers/pci/Makefile @@ -26,6 +26,7 @@ obj-$(CONFIG_PCI_SYSCALL) += syscall.o obj-$(CONFIG_PCI_STUB) += pci-stub.o obj-$(CONFIG_PCI_PF_STUB) += pci-pf-stub.o obj-$(CONFIG_PCI_ECAM) += ecam.o +obj-$(CONFIG_PCI_P2PDMA) += p2pdma.o obj-$(CONFIG_XEN_PCIDEV_FRONTEND) += xen-pcifront.o # Endpoint library must be initialized before its users diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c new file mode 100644 index 000000000000..24d0dbb36ba6 --- /dev/null +++ b/drivers/pci/p2pdma.c @@ -0,0 +1,626 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCI Peer 2 Peer DMA support. + * + * Copyright (c) 2016-2018, Logan Gunthorpe + * Copyright (c) 2016-2017, Microsemi Corporation + * Copyright (c) 2017, Christoph Hellwig + * Copyright (c) 2018, Eideticom Inc. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +struct pci_p2pdma { + struct percpu_ref devmap_ref; + struct completion devmap_ref_done; + struct gen_pool *pool; + bool p2pmem_published; +}; + +static void pci_p2pdma_percpu_release(struct percpu_ref *ref) +{ + struct pci_p2pdma *p2p = + container_of(ref, struct pci_p2pdma, devmap_ref); + + complete_all(&p2p->devmap_ref_done); +} + +static void pci_p2pdma_percpu_kill(void *data) +{ + struct percpu_ref *ref = data; + + /* + * pci_p2pdma_add_resource() may be called multiple times + * by a driver and may register the percpu_kill devm action multiple + * times. We only want the first action to actually kill the + * percpu_ref. + */ + if (percpu_ref_is_dying(ref)) + return; + + percpu_ref_kill(ref); +} + +static void pci_p2pdma_release(void *data) +{ + struct pci_dev *pdev = data; + + if (!pdev->p2pdma) + return; + + wait_for_completion(&pdev->p2pdma->devmap_ref_done); + percpu_ref_exit(&pdev->p2pdma->devmap_ref); + + gen_pool_destroy(pdev->p2pdma->pool); + pdev->p2pdma = NULL; +} + +static int pci_p2pdma_setup(struct pci_dev *pdev) +{ + int error = -ENOMEM; + struct pci_p2pdma *p2p; + + p2p = devm_kzalloc(&pdev->dev, sizeof(*p2p), GFP_KERNEL); + if (!p2p) + return -ENOMEM; + + p2p->pool = gen_pool_create(PAGE_SHIFT, dev_to_node(&pdev->dev)); + if (!p2p->pool) + goto out; + + init_completion(&p2p->devmap_ref_done); + error = percpu_ref_init(&p2p->devmap_ref, + pci_p2pdma_percpu_release, 0, GFP_KERNEL); + if (error) + goto out_pool_destroy; + + error = devm_add_action_or_reset(&pdev->dev, pci_p2pdma_release, pdev); + if (error) + goto out_pool_destroy; + + pdev->p2pdma = p2p; + + return 0; + +out_pool_destroy: + gen_pool_destroy(p2p->pool); +out: + devm_kfree(&pdev->dev, p2p); + return error; +} + +/** + * pci_p2pdma_add_resource - add memory for use as p2p memory + * @pdev: the device to add the memory to + * @bar: PCI BAR to add + * @size: size of the memory to add, may be zero to use the whole BAR + * @offset: offset into the PCI BAR + * + * The memory will be given ZONE_DEVICE struct pages so that it may + * be used with any DMA request. + */ +int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size, + u64 offset) +{ + struct dev_pagemap *pgmap; + void *addr; + int error; + + if (!(pci_resource_flags(pdev, bar) & IORESOURCE_MEM)) + return -EINVAL; + + if (offset >= pci_resource_len(pdev, bar)) + return -EINVAL; + + if (!size) + size = pci_resource_len(pdev, bar) - offset; + + if (size + offset > pci_resource_len(pdev, bar)) + return -EINVAL; + + if (!pdev->p2pdma) { + error = pci_p2pdma_setup(pdev); + if (error) + return error; + } + + pgmap = devm_kzalloc(&pdev->dev, sizeof(*pgmap), GFP_KERNEL); + if (!pgmap) + return -ENOMEM; + + pgmap->res.start = pci_resource_start(pdev, bar) + offset; + pgmap->res.end = pgmap->res.start + size - 1; + pgmap->res.flags = pci_resource_flags(pdev, bar); + pgmap->ref = &pdev->p2pdma->devmap_ref; + pgmap->type = MEMORY_DEVICE_PCI_P2PDMA; + + addr = devm_memremap_pages(&pdev->dev, pgmap); + if (IS_ERR(addr)) { + error = PTR_ERR(addr); + goto pgmap_free; + } + + error = gen_pool_add_virt(pdev->p2pdma->pool, (unsigned long)addr, + pci_bus_address(pdev, bar) + offset, + resource_size(&pgmap->res), dev_to_node(&pdev->dev)); + if (error) + goto pgmap_free; + + error = devm_add_action_or_reset(&pdev->dev, pci_p2pdma_percpu_kill, + &pdev->p2pdma->devmap_ref); + if (error) + goto pgmap_free; + + pci_info(pdev, "added peer-to-peer DMA memory %pR\n", + &pgmap->res); + + return 0; + +pgmap_free: + devm_kfree(&pdev->dev, pgmap); + return error; +} +EXPORT_SYMBOL_GPL(pci_p2pdma_add_resource); + +/* + * Note this function returns the parent PCI device with a + * reference taken. It is the caller's responsibily to drop + * the reference. + */ +static struct pci_dev *find_parent_pci_dev(struct device *dev) +{ + struct device *parent; + + dev = get_device(dev); + + while (dev) { + if (dev_is_pci(dev)) + return to_pci_dev(dev); + + parent = get_device(dev->parent); + put_device(dev); + dev = parent; + } + + return NULL; +} + +/* + * Check if a PCI bridge has its ACS redirection bits set to redirect P2P + * TLPs upstream via ACS. Returns 1 if the packets will be redirected + * upstream, 0 otherwise. + */ +static int pci_bridge_has_acs_redir(struct pci_dev *pdev) +{ + int pos; + u16 ctrl; + + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ACS); + if (!pos) + return 0; + + pci_read_config_word(pdev, pos + PCI_ACS_CTRL, &ctrl); + + if (ctrl & (PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_EC)) + return 1; + + return 0; +} + +static void seq_buf_print_bus_devfn(struct seq_buf *buf, struct pci_dev *pdev) +{ + if (!buf) + return; + + seq_buf_printf(buf, "%s;", pci_name(pdev)); +} + +/* + * Find the distance through the nearest common upstream bridge between + * two PCI devices. + * + * If the two devices are the same device then 0 will be returned. + * + * If there are two virtual functions of the same device behind the same + * bridge port then 2 will be returned (one step down to the PCIe switch, + * then one step back to the same device). + * + * In the case where two devices are connected to the same PCIe switch, the + * value 4 will be returned. This corresponds to the following PCI tree: + * + * -+ Root Port + * \+ Switch Upstream Port + * +-+ Switch Downstream Port + * + \- Device A + * \-+ Switch Downstream Port + * \- Device B + * + * The distance is 4 because we traverse from Device A through the downstream + * port of the switch, to the common upstream port, back up to the second + * downstream port and then to Device B. + * + * Any two devices that don't have a common upstream bridge will return -1. + * In this way devices on separate PCIe root ports will be rejected, which + * is what we want for peer-to-peer seeing each PCIe root port defines a + * separate hierarchy domain and there's no way to determine whether the root + * complex supports forwarding between them. + * + * In the case where two devices are connected to different PCIe switches, + * this function will still return a positive distance as long as both + * switches eventually have a common upstream bridge. Note this covers + * the case of using multiple PCIe switches to achieve a desired level of + * fan-out from a root port. The exact distance will be a function of the + * number of switches between Device A and Device B. + * + * If a bridge which has any ACS redirection bits set is in the path + * then this functions will return -2. This is so we reject any + * cases where the TLPs are forwarded up into the root complex. + * In this case, a list of all infringing bridge addresses will be + * populated in acs_list (assuming it's non-null) for printk purposes. + */ +static int upstream_bridge_distance(struct pci_dev *a, + struct pci_dev *b, + struct seq_buf *acs_list) +{ + int dist_a = 0; + int dist_b = 0; + struct pci_dev *bb = NULL; + int acs_cnt = 0; + + /* + * Note, we don't need to take references to devices returned by + * pci_upstream_bridge() seeing we hold a reference to a child + * device which will already hold a reference to the upstream bridge. + */ + + while (a) { + dist_b = 0; + + if (pci_bridge_has_acs_redir(a)) { + seq_buf_print_bus_devfn(acs_list, a); + acs_cnt++; + } + + bb = b; + + while (bb) { + if (a == bb) + goto check_b_path_acs; + + bb = pci_upstream_bridge(bb); + dist_b++; + } + + a = pci_upstream_bridge(a); + dist_a++; + } + + return -1; + +check_b_path_acs: + bb = b; + + while (bb) { + if (a == bb) + break; + + if (pci_bridge_has_acs_redir(bb)) { + seq_buf_print_bus_devfn(acs_list, bb); + acs_cnt++; + } + + bb = pci_upstream_bridge(bb); + } + + if (acs_cnt) + return -2; + + return dist_a + dist_b; +} + +static int upstream_bridge_distance_warn(struct pci_dev *provider, + struct pci_dev *client) +{ + struct seq_buf acs_list; + int ret; + + seq_buf_init(&acs_list, kmalloc(PAGE_SIZE, GFP_KERNEL), PAGE_SIZE); + if (!acs_list.buffer) + return -ENOMEM; + + ret = upstream_bridge_distance(provider, client, &acs_list); + if (ret == -2) { + pci_warn(client, "cannot be used for peer-to-peer DMA as ACS redirect is set between the client and provider (%s)\n", + pci_name(provider)); + /* Drop final semicolon */ + acs_list.buffer[acs_list.len-1] = 0; + pci_warn(client, "to disable ACS redirect for this path, add the kernel parameter: pci=disable_acs_redir=%s\n", + acs_list.buffer); + + } else if (ret < 0) { + pci_warn(client, "cannot be used for peer-to-peer DMA as the client and provider (%s) do not share an upstream bridge\n", + pci_name(provider)); + } + + kfree(acs_list.buffer); + + return ret; +} + +/** + * pci_p2pdma_distance_many - Determive the cumulative distance between + * a p2pdma provider and the clients in use. + * @provider: p2pdma provider to check against the client list + * @clients: array of devices to check (NULL-terminated) + * @num_clients: number of clients in the array + * @verbose: if true, print warnings for devices when we return -1 + * + * Returns -1 if any of the clients are not compatible (behind the same + * root port as the provider), otherwise returns a positive number where + * a lower number is the preferrable choice. (If there's one client + * that's the same as the provider it will return 0, which is best choice). + * + * For now, "compatible" means the provider and the clients are all behind + * the same PCI root port. This cuts out cases that may work but is safest + * for the user. Future work can expand this to white-list root complexes that + * can safely forward between each ports. + */ +int pci_p2pdma_distance_many(struct pci_dev *provider, struct device **clients, + int num_clients, bool verbose) +{ + bool not_supported = false; + struct pci_dev *pci_client; + int distance = 0; + int i, ret; + + if (num_clients == 0) + return -1; + + for (i = 0; i < num_clients; i++) { + pci_client = find_parent_pci_dev(clients[i]); + if (!pci_client) { + if (verbose) + dev_warn(clients[i], + "cannot be used for peer-to-peer DMA as it is not a PCI device\n"); + return -1; + } + + if (verbose) + ret = upstream_bridge_distance_warn(provider, + pci_client); + else + ret = upstream_bridge_distance(provider, pci_client, + NULL); + + pci_dev_put(pci_client); + + if (ret < 0) + not_supported = true; + + if (not_supported && !verbose) + break; + + distance += ret; + } + + if (not_supported) + return -1; + + return distance; +} +EXPORT_SYMBOL_GPL(pci_p2pdma_distance_many); + +/** + * pci_has_p2pmem - check if a given PCI device has published any p2pmem + * @pdev: PCI device to check + */ +bool pci_has_p2pmem(struct pci_dev *pdev) +{ + return pdev->p2pdma && pdev->p2pdma->p2pmem_published; +} +EXPORT_SYMBOL_GPL(pci_has_p2pmem); + +/** + * pci_p2pmem_find - find a peer-to-peer DMA memory device compatible with + * the specified list of clients and shortest distance (as determined + * by pci_p2pmem_dma()) + * @clients: array of devices to check (NULL-terminated) + * @num_clients: number of client devices in the list + * + * If multiple devices are behind the same switch, the one "closest" to the + * client devices in use will be chosen first. (So if one of the providers are + * the same as one of the clients, that provider will be used ahead of any + * other providers that are unrelated). If multiple providers are an equal + * distance away, one will be chosen at random. + * + * Returns a pointer to the PCI device with a reference taken (use pci_dev_put + * to return the reference) or NULL if no compatible device is found. The + * found provider will also be assigned to the client list. + */ +struct pci_dev *pci_p2pmem_find_many(struct device **clients, int num_clients) +{ + struct pci_dev *pdev = NULL; + int distance; + int closest_distance = INT_MAX; + struct pci_dev **closest_pdevs; + int dev_cnt = 0; + const int max_devs = PAGE_SIZE / sizeof(*closest_pdevs); + int i; + + closest_pdevs = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!closest_pdevs) + return NULL; + + while ((pdev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, pdev))) { + if (!pci_has_p2pmem(pdev)) + continue; + + distance = pci_p2pdma_distance_many(pdev, clients, + num_clients, false); + if (distance < 0 || distance > closest_distance) + continue; + + if (distance == closest_distance && dev_cnt >= max_devs) + continue; + + if (distance < closest_distance) { + for (i = 0; i < dev_cnt; i++) + pci_dev_put(closest_pdevs[i]); + + dev_cnt = 0; + closest_distance = distance; + } + + closest_pdevs[dev_cnt++] = pci_dev_get(pdev); + } + + if (dev_cnt) + pdev = pci_dev_get(closest_pdevs[prandom_u32_max(dev_cnt)]); + + for (i = 0; i < dev_cnt; i++) + pci_dev_put(closest_pdevs[i]); + + kfree(closest_pdevs); + return pdev; +} +EXPORT_SYMBOL_GPL(pci_p2pmem_find_many); + +/** + * pci_alloc_p2p_mem - allocate peer-to-peer DMA memory + * @pdev: the device to allocate memory from + * @size: number of bytes to allocate + * + * Returns the allocated memory or NULL on error. + */ +void *pci_alloc_p2pmem(struct pci_dev *pdev, size_t size) +{ + void *ret; + + if (unlikely(!pdev->p2pdma)) + return NULL; + + if (unlikely(!percpu_ref_tryget_live(&pdev->p2pdma->devmap_ref))) + return NULL; + + ret = (void *)gen_pool_alloc(pdev->p2pdma->pool, size); + + if (unlikely(!ret)) + percpu_ref_put(&pdev->p2pdma->devmap_ref); + + return ret; +} +EXPORT_SYMBOL_GPL(pci_alloc_p2pmem); + +/** + * pci_free_p2pmem - free peer-to-peer DMA memory + * @pdev: the device the memory was allocated from + * @addr: address of the memory that was allocated + * @size: number of bytes that was allocated + */ +void pci_free_p2pmem(struct pci_dev *pdev, void *addr, size_t size) +{ + gen_pool_free(pdev->p2pdma->pool, (uintptr_t)addr, size); + percpu_ref_put(&pdev->p2pdma->devmap_ref); +} +EXPORT_SYMBOL_GPL(pci_free_p2pmem); + +/** + * pci_virt_to_bus - return the PCI bus address for a given virtual + * address obtained with pci_alloc_p2pmem() + * @pdev: the device the memory was allocated from + * @addr: address of the memory that was allocated + */ +pci_bus_addr_t pci_p2pmem_virt_to_bus(struct pci_dev *pdev, void *addr) +{ + if (!addr) + return 0; + if (!pdev->p2pdma) + return 0; + + /* + * Note: when we added the memory to the pool we used the PCI + * bus address as the physical address. So gen_pool_virt_to_phys() + * actually returns the bus address despite the misleading name. + */ + return gen_pool_virt_to_phys(pdev->p2pdma->pool, (unsigned long)addr); +} +EXPORT_SYMBOL_GPL(pci_p2pmem_virt_to_bus); + +/** + * pci_p2pmem_alloc_sgl - allocate peer-to-peer DMA memory in a scatterlist + * @pdev: the device to allocate memory from + * @nents: the number of SG entries in the list + * @length: number of bytes to allocate + * + * Returns 0 on success + */ +struct scatterlist *pci_p2pmem_alloc_sgl(struct pci_dev *pdev, + unsigned int *nents, u32 length) +{ + struct scatterlist *sg; + void *addr; + + sg = kzalloc(sizeof(*sg), GFP_KERNEL); + if (!sg) + return NULL; + + sg_init_table(sg, 1); + + addr = pci_alloc_p2pmem(pdev, length); + if (!addr) + goto out_free_sg; + + sg_set_buf(sg, addr, length); + *nents = 1; + return sg; + +out_free_sg: + kfree(sg); + return NULL; +} +EXPORT_SYMBOL_GPL(pci_p2pmem_alloc_sgl); + +/** + * pci_p2pmem_free_sgl - free a scatterlist allocated by pci_p2pmem_alloc_sgl() + * @pdev: the device to allocate memory from + * @sgl: the allocated scatterlist + */ +void pci_p2pmem_free_sgl(struct pci_dev *pdev, struct scatterlist *sgl) +{ + struct scatterlist *sg; + int count; + + for_each_sg(sgl, sg, INT_MAX, count) { + if (!sg) + break; + + pci_free_p2pmem(pdev, sg_virt(sg), sg->length); + } + kfree(sgl); +} +EXPORT_SYMBOL_GPL(pci_p2pmem_free_sgl); + +/** + * pci_p2pmem_publish - publish the peer-to-peer DMA memory for use by + * other devices with pci_p2pmem_find() + * @pdev: the device with peer-to-peer DMA memory to publish + * @publish: set to true to publish the memory, false to unpublish it + * + * Published memory can be used by other PCI device drivers for + * peer-2-peer DMA operations. Non-published memory is reserved for + * exlusive use of the device driver that registers the peer-to-peer + * memory. + */ +void pci_p2pmem_publish(struct pci_dev *pdev, bool publish) +{ + if (pdev->p2pdma) + pdev->p2pdma->p2pmem_published = publish; +} +EXPORT_SYMBOL_GPL(pci_p2pmem_publish); diff --git a/include/linux/memremap.h b/include/linux/memremap.h index f91f9e763557..9553370ebdad 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -53,11 +53,16 @@ struct vmem_altmap { * wakeup event whenever a page is unpinned and becomes idle. This * wakeup is used to coordinate physical address space management (ex: * fs truncate/hole punch) vs pinned pages (ex: device dma). + * + * MEMORY_DEVICE_PCI_P2PDMA: + * Device memory residing in a PCI BAR intended for use with Peer-to-Peer + * transactions. */ enum memory_type { MEMORY_DEVICE_PRIVATE = 1, MEMORY_DEVICE_PUBLIC, MEMORY_DEVICE_FS_DAX, + MEMORY_DEVICE_PCI_P2PDMA, }; /* diff --git a/include/linux/mm.h b/include/linux/mm.h index a61ebe8ad4ca..2055df412a77 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -890,6 +890,19 @@ static inline bool is_device_public_page(const struct page *page) page->pgmap->type == MEMORY_DEVICE_PUBLIC; } +#ifdef CONFIG_PCI_P2PDMA +static inline bool is_pci_p2pdma_page(const struct page *page) +{ + return is_zone_device_page(page) && + page->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA; +} +#else /* CONFIG_PCI_P2PDMA */ +static inline bool is_pci_p2pdma_page(const struct page *page) +{ + return false; +} +#endif /* CONFIG_PCI_P2PDMA */ + #else /* CONFIG_DEV_PAGEMAP_OPS */ static inline void dev_pagemap_get_ops(void) { @@ -913,6 +926,11 @@ static inline bool is_device_public_page(const struct page *page) { return false; } + +static inline bool is_pci_p2pdma_page(const struct page *page) +{ + return false; +} #endif /* CONFIG_DEV_PAGEMAP_OPS */ static inline void get_page(struct page *page) diff --git a/include/linux/pci-p2pdma.h b/include/linux/pci-p2pdma.h new file mode 100644 index 000000000000..7bdaacfd5892 --- /dev/null +++ b/include/linux/pci-p2pdma.h @@ -0,0 +1,92 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * PCI Peer 2 Peer DMA support. + * + * Copyright (c) 2016-2018, Logan Gunthorpe + * Copyright (c) 2016-2017, Microsemi Corporation + * Copyright (c) 2017, Christoph Hellwig + * Copyright (c) 2018, Eideticom Inc. + */ + +#ifndef _LINUX_PCI_P2PDMA_H +#define _LINUX_PCI_P2PDMA_H + +#include + +struct block_device; +struct scatterlist; + +#ifdef CONFIG_PCI_P2PDMA +int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size, + u64 offset); +int pci_p2pdma_distance_many(struct pci_dev *provider, struct device **clients, + int num_clients, bool verbose); +bool pci_has_p2pmem(struct pci_dev *pdev); +struct pci_dev *pci_p2pmem_find_many(struct device **clients, int num_clients); +void *pci_alloc_p2pmem(struct pci_dev *pdev, size_t size); +void pci_free_p2pmem(struct pci_dev *pdev, void *addr, size_t size); +pci_bus_addr_t pci_p2pmem_virt_to_bus(struct pci_dev *pdev, void *addr); +struct scatterlist *pci_p2pmem_alloc_sgl(struct pci_dev *pdev, + unsigned int *nents, u32 length); +void pci_p2pmem_free_sgl(struct pci_dev *pdev, struct scatterlist *sgl); +void pci_p2pmem_publish(struct pci_dev *pdev, bool publish); +#else /* CONFIG_PCI_P2PDMA */ +static inline int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, + size_t size, u64 offset) +{ + return -EOPNOTSUPP; +} +static inline int pci_p2pdma_distance_many(struct pci_dev *provider, + struct device **clients, int num_clients, bool verbose) +{ + return -1; +} +static inline bool pci_has_p2pmem(struct pci_dev *pdev) +{ + return false; +} +static inline struct pci_dev *pci_p2pmem_find_many(struct device **clients, + int num_clients) +{ + return NULL; +} +static inline void *pci_alloc_p2pmem(struct pci_dev *pdev, size_t size) +{ + return NULL; +} +static inline void pci_free_p2pmem(struct pci_dev *pdev, void *addr, + size_t size) +{ +} +static inline pci_bus_addr_t pci_p2pmem_virt_to_bus(struct pci_dev *pdev, + void *addr) +{ + return 0; +} +static inline struct scatterlist *pci_p2pmem_alloc_sgl(struct pci_dev *pdev, + unsigned int *nents, u32 length) +{ + return NULL; +} +static inline void pci_p2pmem_free_sgl(struct pci_dev *pdev, + struct scatterlist *sgl) +{ +} +static inline void pci_p2pmem_publish(struct pci_dev *pdev, bool publish) +{ +} +#endif /* CONFIG_PCI_P2PDMA */ + + +static inline int pci_p2pdma_distance(struct pci_dev *provider, + struct device *client, bool verbose) +{ + return pci_p2pdma_distance_many(provider, &client, 1, verbose); +} + +static inline struct pci_dev *pci_p2pmem_find(struct device *client) +{ + return pci_p2pmem_find_many(&client, 1); +} + +#endif /* _LINUX_PCI_P2P_H */ diff --git a/include/linux/pci.h b/include/linux/pci.h index 6925828f9f25..bf5277768f69 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -281,6 +281,7 @@ struct pcie_link_state; struct pci_vpd; struct pci_sriov; struct pci_ats; +struct pci_p2pdma; /* The pci_dev structure describes PCI devices */ struct pci_dev { @@ -438,6 +439,9 @@ struct pci_dev { #endif #ifdef CONFIG_PCI_PASID u16 pasid_features; +#endif +#ifdef CONFIG_PCI_P2PDMA + struct pci_p2pdma *p2pdma; #endif phys_addr_t rom; /* Physical address if not from BAR */ size_t romlen; /* Length if not from BAR */ -- cgit v1.2.3 From 18b01b16e8bae9cd227909f6e6d2783d74855f65 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 9 Oct 2018 16:08:22 +0200 Subject: PCI: Remove pci_unmap_addr() wrappers for DMA API Only some of these were still used by the cxgb4 driver, and that despite the fact that the driver otherwise uses the generic DMA API. Signed-off-by: Christoph Hellwig Signed-off-by: Bjorn Helgaas --- drivers/infiniband/hw/cxgb4/qp.c | 10 +++++----- drivers/infiniband/hw/cxgb4/t4.h | 2 +- include/linux/pci-dma.h | 12 ------------ include/linux/pci.h | 1 - 4 files changed, 6 insertions(+), 19 deletions(-) delete mode 100644 include/linux/pci-dma.h (limited to 'include/linux') diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c index 347fe18b1a41..62d6f197ec0b 100644 --- a/drivers/infiniband/hw/cxgb4/qp.c +++ b/drivers/infiniband/hw/cxgb4/qp.c @@ -99,7 +99,7 @@ static void dealloc_oc_sq(struct c4iw_rdev *rdev, struct t4_sq *sq) static void dealloc_host_sq(struct c4iw_rdev *rdev, struct t4_sq *sq) { dma_free_coherent(&(rdev->lldi.pdev->dev), sq->memsize, sq->queue, - pci_unmap_addr(sq, mapping)); + dma_unmap_addr(sq, mapping)); } static void dealloc_sq(struct c4iw_rdev *rdev, struct t4_sq *sq) @@ -132,7 +132,7 @@ static int alloc_host_sq(struct c4iw_rdev *rdev, struct t4_sq *sq) if (!sq->queue) return -ENOMEM; sq->phys_addr = virt_to_phys(sq->queue); - pci_unmap_addr_set(sq, mapping, sq->dma_addr); + dma_unmap_addr_set(sq, mapping, sq->dma_addr); return 0; } @@ -2521,7 +2521,7 @@ static void free_srq_queue(struct c4iw_srq *srq, struct c4iw_dev_ucontext *uctx, dma_free_coherent(&rdev->lldi.pdev->dev, wq->memsize, wq->queue, - pci_unmap_addr(wq, mapping)); + dma_unmap_addr(wq, mapping)); c4iw_rqtpool_free(rdev, wq->rqt_hwaddr, wq->rqt_size); kfree(wq->sw_rq); c4iw_put_qpid(rdev, wq->qid, uctx); @@ -2570,7 +2570,7 @@ static int alloc_srq_queue(struct c4iw_srq *srq, struct c4iw_dev_ucontext *uctx, goto err_free_rqtpool; memset(wq->queue, 0, wq->memsize); - pci_unmap_addr_set(wq, mapping, wq->dma_addr); + dma_unmap_addr_set(wq, mapping, wq->dma_addr); wq->bar2_va = c4iw_bar2_addrs(rdev, wq->qid, T4_BAR2_QTYPE_EGRESS, &wq->bar2_qid, @@ -2649,7 +2649,7 @@ static int alloc_srq_queue(struct c4iw_srq *srq, struct c4iw_dev_ucontext *uctx, err_free_queue: dma_free_coherent(&rdev->lldi.pdev->dev, wq->memsize, wq->queue, - pci_unmap_addr(wq, mapping)); + dma_unmap_addr(wq, mapping)); err_free_rqtpool: c4iw_rqtpool_free(rdev, wq->rqt_hwaddr, wq->rqt_size); err_free_pending_wrs: diff --git a/drivers/infiniband/hw/cxgb4/t4.h b/drivers/infiniband/hw/cxgb4/t4.h index e42021fd6fd6..fff6d48d262f 100644 --- a/drivers/infiniband/hw/cxgb4/t4.h +++ b/drivers/infiniband/hw/cxgb4/t4.h @@ -397,7 +397,7 @@ struct t4_srq_pending_wr { struct t4_srq { union t4_recv_wr *queue; dma_addr_t dma_addr; - DECLARE_PCI_UNMAP_ADDR(mapping); + DEFINE_DMA_UNMAP_ADDR(mapping); struct t4_swrqe *sw_rq; void __iomem *bar2_va; u64 bar2_pa; diff --git a/include/linux/pci-dma.h b/include/linux/pci-dma.h deleted file mode 100644 index 0f7aa7353ca3..000000000000 --- a/include/linux/pci-dma.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_PCI_DMA_H -#define _LINUX_PCI_DMA_H - -#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) DEFINE_DMA_UNMAP_ADDR(ADDR_NAME); -#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) DEFINE_DMA_UNMAP_LEN(LEN_NAME); -#define pci_unmap_addr dma_unmap_addr -#define pci_unmap_addr_set dma_unmap_addr_set -#define pci_unmap_len dma_unmap_len -#define pci_unmap_len_set dma_unmap_len_set - -#endif diff --git a/include/linux/pci.h b/include/linux/pci.h index 6925828f9f25..e938e80e59c1 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1342,7 +1342,6 @@ int pci_set_vga_state(struct pci_dev *pdev, bool decode, /* kmem_cache style wrapper around pci_alloc_consistent() */ -#include #include #define pci_pool dma_pool -- cgit v1.2.3 From a6f44cf9f5cc60471cf06f3d5391fc6041eb37a5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 9 Oct 2018 16:08:23 +0200 Subject: PCI: Remove pci_set_dma_seg_boundary() The two callers can just use dma_set_seg_boundary() directly. Signed-off-by: Christoph Hellwig Signed-off-by: Bjorn Helgaas --- drivers/pci/probe.c | 2 +- drivers/s390/net/ism_drv.c | 2 +- include/linux/pci-dma-compat.h | 9 --------- 3 files changed, 2 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 7c422ccbf9b4..72dd926680be 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2398,7 +2398,7 @@ void pci_device_add(struct pci_dev *dev, struct pci_bus *bus) dev->dev.coherent_dma_mask = 0xffffffffull; pci_set_dma_max_seg_size(dev, 65536); - pci_set_dma_seg_boundary(dev, 0xffffffff); + dma_set_seg_boundary(&dev->dev, 0xffffffff); /* Fix up broken headers */ pci_fixup_device(pci_fixup_header, dev); diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c index c0631895154e..8688c0fff761 100644 --- a/drivers/s390/net/ism_drv.c +++ b/drivers/s390/net/ism_drv.c @@ -515,7 +515,7 @@ static int ism_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (ret) goto err_unmap; - pci_set_dma_seg_boundary(pdev, SZ_1M - 1); + dma_set_seg_boundary(&pdev->dev, SZ_1M - 1); pci_set_dma_max_seg_size(pdev, SZ_1M); pci_set_master(pdev); diff --git a/include/linux/pci-dma-compat.h b/include/linux/pci-dma-compat.h index c3f1b44ade29..558a109ab497 100644 --- a/include/linux/pci-dma-compat.h +++ b/include/linux/pci-dma-compat.h @@ -125,12 +125,6 @@ static inline int pci_set_dma_max_seg_size(struct pci_dev *dev, { return dma_set_max_seg_size(&dev->dev, size); } - -static inline int pci_set_dma_seg_boundary(struct pci_dev *dev, - unsigned long mask) -{ - return dma_set_seg_boundary(&dev->dev, mask); -} #else static inline int pci_set_dma_mask(struct pci_dev *dev, u64 mask) { return -EIO; } @@ -139,9 +133,6 @@ static inline int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask) static inline int pci_set_dma_max_seg_size(struct pci_dev *dev, unsigned int size) { return -EIO; } -static inline int pci_set_dma_seg_boundary(struct pci_dev *dev, - unsigned long mask) -{ return -EIO; } #endif #endif -- cgit v1.2.3 From b0da3498c587c20e64799c4c7ba65a31314b2182 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 9 Oct 2018 16:08:24 +0200 Subject: PCI: Remove pci_set_dma_max_seg_size() The few callers can just use dma_set_max_seg_size ()directly. Signed-off-by: Christoph Hellwig Signed-off-by: Bjorn Helgaas --- drivers/ata/sata_inic162x.c | 2 +- drivers/block/rsxx/core.c | 2 +- drivers/pci/probe.c | 2 +- drivers/s390/net/ism_drv.c | 2 +- drivers/scsi/aacraid/linit.c | 2 +- include/linux/pci-dma-compat.h | 9 --------- 6 files changed, 5 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/sata_inic162x.c b/drivers/ata/sata_inic162x.c index 9b6d7930d1c7..e0bcf9b2dab0 100644 --- a/drivers/ata/sata_inic162x.c +++ b/drivers/ata/sata_inic162x.c @@ -873,7 +873,7 @@ static int inic_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) * like others but it will lock up the whole machine HARD if * 65536 byte PRD entry is fed. Reduce maximum segment size. */ - rc = pci_set_dma_max_seg_size(pdev, 65536 - 512); + rc = dma_set_max_seg_size(&pdev->dev, 65536 - 512); if (rc) { dev_err(&pdev->dev, "failed to set the maximum segment size\n"); return rc; diff --git a/drivers/block/rsxx/core.c b/drivers/block/rsxx/core.c index f2c631ce793c..37df486c7c3c 100644 --- a/drivers/block/rsxx/core.c +++ b/drivers/block/rsxx/core.c @@ -780,7 +780,7 @@ static int rsxx_pci_probe(struct pci_dev *dev, goto failed_enable; pci_set_master(dev); - pci_set_dma_max_seg_size(dev, RSXX_HW_BLK_SIZE); + dma_set_max_seg_size(&dev->dev, RSXX_HW_BLK_SIZE); st = pci_set_dma_mask(dev, DMA_BIT_MASK(64)); if (st) { diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 72dd926680be..75d896549360 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2397,7 +2397,7 @@ void pci_device_add(struct pci_dev *dev, struct pci_bus *bus) dev->dev.dma_parms = &dev->dma_parms; dev->dev.coherent_dma_mask = 0xffffffffull; - pci_set_dma_max_seg_size(dev, 65536); + dma_set_max_seg_size(&dev->dev, 65536); dma_set_seg_boundary(&dev->dev, 0xffffffff); /* Fix up broken headers */ diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c index 8688c0fff761..f96ec68af2e5 100644 --- a/drivers/s390/net/ism_drv.c +++ b/drivers/s390/net/ism_drv.c @@ -516,7 +516,7 @@ static int ism_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto err_unmap; dma_set_seg_boundary(&pdev->dev, SZ_1M - 1); - pci_set_dma_max_seg_size(pdev, SZ_1M); + dma_set_max_seg_size(&pdev->dev, SZ_1M); pci_set_master(pdev); ism->smcd = smcd_alloc_dev(&pdev->dev, dev_name(&pdev->dev), &ism_ops, diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c index 04443577d48b..53eb2e9569b9 100644 --- a/drivers/scsi/aacraid/linit.c +++ b/drivers/scsi/aacraid/linit.c @@ -1747,7 +1747,7 @@ static int aac_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) shost->max_sectors = (shost->sg_tablesize * 8) + 112; } - error = pci_set_dma_max_seg_size(pdev, + error = dma_set_max_seg_size(&pdev->dev, (aac->adapter_info.options & AAC_OPT_NEW_COMM) ? (shost->max_sectors << 9) : 65536); if (error) diff --git a/include/linux/pci-dma-compat.h b/include/linux/pci-dma-compat.h index 558a109ab497..cb1adf0b78a9 100644 --- a/include/linux/pci-dma-compat.h +++ b/include/linux/pci-dma-compat.h @@ -119,20 +119,11 @@ static inline int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask) { return dma_set_coherent_mask(&dev->dev, mask); } - -static inline int pci_set_dma_max_seg_size(struct pci_dev *dev, - unsigned int size) -{ - return dma_set_max_seg_size(&dev->dev, size); -} #else static inline int pci_set_dma_mask(struct pci_dev *dev, u64 mask) { return -EIO; } static inline int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask) { return -EIO; } -static inline int pci_set_dma_max_seg_size(struct pci_dev *dev, - unsigned int size) -{ return -EIO; } #endif #endif -- cgit v1.2.3 From f6a8a19bb11b46d60250ddc4e3e1ba6aa166f488 Mon Sep 17 00:00:00 2001 From: Denis Drozdov Date: Tue, 14 Aug 2018 14:08:51 +0300 Subject: RDMA/netdev: Hoist alloc_netdev_mqs out of the driver netdev has several interfaces that expect to call alloc_netdev_mqs from the core code, with the driver only providing the arguments. This is incompatible with the rdma_netdev interface that returns the netdev directly. Thus re-organize the API used by ipoib so that the verbs core code calls alloc_netdev_mqs for the driver. This is done by allowing the drivers to provide the allocation parameters via a 'get_params' callback and then initializing an allocated netdev as a second step. Fixes: cd565b4b51e5 ("IB/IPoIB: Support acceleration options callbacks") Signed-off-by: Jason Gunthorpe Signed-off-by: Denis Drozdov Signed-off-by: Saeed Mahameed --- drivers/infiniband/core/verbs.c | 32 ++++++++ drivers/infiniband/hw/mlx5/main.c | 23 ++---- drivers/infiniband/ulp/ipoib/ipoib_main.c | 21 ++---- .../net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 87 ++++++++++++---------- include/linux/mlx5/driver.h | 14 +--- include/rdma/ib_verbs.h | 23 +++++- 6 files changed, 119 insertions(+), 81 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index 6ee03d6089eb..2f34d3412097 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -2621,3 +2621,35 @@ void ib_drain_qp(struct ib_qp *qp) ib_drain_rq(qp); } EXPORT_SYMBOL(ib_drain_qp); + +struct net_device *rdma_alloc_netdev(struct ib_device *device, u8 port_num, + enum rdma_netdev_t type, const char *name, + unsigned char name_assign_type, + void (*setup)(struct net_device *)) +{ + struct rdma_netdev_alloc_params params; + struct net_device *netdev; + int rc; + + if (!device->rdma_netdev_get_params) + return ERR_PTR(-EOPNOTSUPP); + + rc = device->rdma_netdev_get_params(device, port_num, type, ¶ms); + if (rc) + return ERR_PTR(rc); + + netdev = alloc_netdev_mqs(params.sizeof_priv, name, name_assign_type, + setup, params.txqs, params.rxqs); + if (!netdev) + return ERR_PTR(-ENOMEM); + + rc = params.initialize_rdma_netdev(device, port_num, netdev, + params.param); + if (rc) { + free_netdev(netdev); + return ERR_PTR(rc); + } + + return netdev; +} +EXPORT_SYMBOL(rdma_alloc_netdev); diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index c414f3809e5c..5d9b7f62a0ba 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -5163,22 +5163,14 @@ done: return num_counters; } -static struct net_device* -mlx5_ib_alloc_rdma_netdev(struct ib_device *hca, - u8 port_num, - enum rdma_netdev_t type, - const char *name, - unsigned char name_assign_type, - void (*setup)(struct net_device *)) +static int mlx5_ib_rn_get_params(struct ib_device *device, u8 port_num, + enum rdma_netdev_t type, + struct rdma_netdev_alloc_params *params) { - struct net_device *netdev; - if (type != RDMA_NETDEV_IPOIB) - return ERR_PTR(-EOPNOTSUPP); + return -EOPNOTSUPP; - netdev = mlx5_rdma_netdev_alloc(to_mdev(hca)->mdev, hca, - name, setup); - return netdev; + return mlx5_rdma_rn_get_params(to_mdev(device)->mdev, device, params); } static void delay_drop_debugfs_cleanup(struct mlx5_ib_dev *dev) @@ -5824,8 +5816,9 @@ int mlx5_ib_stage_caps_init(struct mlx5_ib_dev *dev) dev->ib_dev.check_mr_status = mlx5_ib_check_mr_status; dev->ib_dev.get_dev_fw_str = get_dev_fw_str; dev->ib_dev.get_vector_affinity = mlx5_ib_get_vector_affinity; - if (MLX5_CAP_GEN(mdev, ipoib_enhanced_offloads)) - dev->ib_dev.alloc_rdma_netdev = mlx5_ib_alloc_rdma_netdev; + if (MLX5_CAP_GEN(mdev, ipoib_enhanced_offloads) && + IS_ENABLED(CONFIG_MLX5_CORE_IPOIB)) + dev->ib_dev.rdma_netdev_get_params = mlx5_ib_rn_get_params; if (mlx5_core_is_pf(mdev)) { dev->ib_dev.get_vf_config = mlx5_ib_get_vf_config; diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index e3d28f9ad9c0..9c816cd41724 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -2146,20 +2146,15 @@ static struct net_device *ipoib_get_netdev(struct ib_device *hca, u8 port, { struct net_device *dev; - if (hca->alloc_rdma_netdev) { - dev = hca->alloc_rdma_netdev(hca, port, - RDMA_NETDEV_IPOIB, name, - NET_NAME_UNKNOWN, - ipoib_setup_common); - if (IS_ERR_OR_NULL(dev) && PTR_ERR(dev) != -EOPNOTSUPP) - return NULL; - } - - if (!hca->alloc_rdma_netdev || PTR_ERR(dev) == -EOPNOTSUPP) - dev = ipoib_create_netdev_default(hca, name, NET_NAME_UNKNOWN, - ipoib_setup_common); + dev = rdma_alloc_netdev(hca, port, RDMA_NETDEV_IPOIB, name, + NET_NAME_UNKNOWN, ipoib_setup_common); + if (!IS_ERR(dev)) + return dev; + if (PTR_ERR(dev) != -EOPNOTSUPP) + return NULL; - return dev; + return ipoib_create_netdev_default(hca, name, NET_NAME_UNKNOWN, + ipoib_setup_common); } struct ipoib_dev_priv *ipoib_intf_alloc(struct ib_device *hca, u8 port, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 299e2a897f7e..af1a95f80404 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -658,53 +658,36 @@ static void mlx5_rdma_netdev_free(struct net_device *netdev) } } -struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, - struct ib_device *ibdev, - const char *name, - void (*setup)(struct net_device *)) +static bool mlx5_is_sub_interface(struct mlx5_core_dev *mdev) { - const struct mlx5e_profile *profile; - struct net_device *netdev; + return mdev->mlx5e_res.pdn != 0; +} + +static const struct mlx5e_profile *mlx5_get_profile(struct mlx5_core_dev *mdev) +{ + if (mlx5_is_sub_interface(mdev)) + return mlx5i_pkey_get_profile(); + return &mlx5i_nic_profile; +} + +static int mlx5_rdma_setup_rn(struct ib_device *ibdev, u8 port_num, + struct net_device *netdev, void *param) +{ + struct mlx5_core_dev *mdev = (struct mlx5_core_dev *)param; + const struct mlx5e_profile *prof = mlx5_get_profile(mdev); struct mlx5i_priv *ipriv; struct mlx5e_priv *epriv; struct rdma_netdev *rn; - bool sub_interface; - int nch; int err; - if (mlx5i_check_required_hca_cap(mdev)) { - mlx5_core_warn(mdev, "Accelerated mode is not supported\n"); - return ERR_PTR(-EOPNOTSUPP); - } - - /* TODO: Need to find a better way to check if child device*/ - sub_interface = (mdev->mlx5e_res.pdn != 0); - - if (sub_interface) - profile = mlx5i_pkey_get_profile(); - else - profile = &mlx5i_nic_profile; - - nch = profile->max_nch(mdev); - - netdev = alloc_netdev_mqs(sizeof(struct mlx5i_priv) + sizeof(struct mlx5e_priv), - name, NET_NAME_UNKNOWN, - setup, - nch * MLX5E_MAX_NUM_TC, - nch); - if (!netdev) { - mlx5_core_warn(mdev, "alloc_netdev_mqs failed\n"); - return NULL; - } - ipriv = netdev_priv(netdev); epriv = mlx5i_epriv(netdev); epriv->wq = create_singlethread_workqueue("mlx5i"); if (!epriv->wq) - goto err_free_netdev; + return -ENOMEM; - ipriv->sub_interface = sub_interface; + ipriv->sub_interface = mlx5_is_sub_interface(mdev); if (!ipriv->sub_interface) { err = mlx5i_pkey_qpn_ht_init(netdev); if (err) { @@ -718,7 +701,7 @@ struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, goto destroy_ht; } - profile->init(mdev, netdev, profile, ipriv); + prof->init(mdev, netdev, prof, ipriv); mlx5e_attach_netdev(epriv); netif_carrier_off(netdev); @@ -734,15 +717,37 @@ struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, netdev->priv_destructor = mlx5_rdma_netdev_free; netdev->needs_free_netdev = 1; - return netdev; + return 0; destroy_ht: mlx5i_pkey_qpn_ht_cleanup(netdev); destroy_wq: destroy_workqueue(epriv->wq); -err_free_netdev: - free_netdev(netdev); + return err; +} + +int mlx5_rdma_rn_get_params(struct mlx5_core_dev *mdev, + struct ib_device *device, + struct rdma_netdev_alloc_params *params) +{ + int nch; + int rc; + + rc = mlx5i_check_required_hca_cap(mdev); + if (rc) + return rc; - return NULL; + nch = mlx5_get_profile(mdev)->max_nch(mdev); + + *params = (struct rdma_netdev_alloc_params){ + .sizeof_priv = sizeof(struct mlx5i_priv) + + sizeof(struct mlx5e_priv), + .txqs = nch * MLX5E_MAX_NUM_TC, + .rxqs = nch, + .param = mdev, + .initialize_rdma_netdev = mlx5_rdma_setup_rn, + }; + + return 0; } -EXPORT_SYMBOL(mlx5_rdma_netdev_alloc); +EXPORT_SYMBOL(mlx5_rdma_rn_get_params); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 26a92462f4ce..4b75796cac23 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1228,21 +1228,15 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev, struct mlx5_uars_page *mlx5_get_uars_page(struct mlx5_core_dev *mdev); void mlx5_put_uars_page(struct mlx5_core_dev *mdev, struct mlx5_uars_page *up); -#ifndef CONFIG_MLX5_CORE_IPOIB -static inline -struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, - struct ib_device *ibdev, - const char *name, - void (*setup)(struct net_device *)) -{ - return ERR_PTR(-EOPNOTSUPP); -} -#else +#ifdef CONFIG_MLX5_CORE_IPOIB struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, struct ib_device *ibdev, const char *name, void (*setup)(struct net_device *)); #endif /* CONFIG_MLX5_CORE_IPOIB */ +int mlx5_rdma_rn_get_params(struct mlx5_core_dev *mdev, + struct ib_device *device, + struct rdma_netdev_alloc_params *params); struct mlx5_profile { u64 mask; diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index e950c2a68f06..020216cee8f1 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2223,6 +2223,16 @@ struct rdma_netdev { union ib_gid *gid, u16 mlid); }; +struct rdma_netdev_alloc_params { + size_t sizeof_priv; + unsigned int txqs; + unsigned int rxqs; + void *param; + + int (*initialize_rdma_netdev)(struct ib_device *device, u8 port_num, + struct net_device *netdev, void *param); +}; + struct ib_port_pkey_list { /* Lock to hold while modifying the list. */ spinlock_t list_lock; @@ -2523,8 +2533,8 @@ struct ib_device { /** * rdma netdev operation * - * Driver implementing alloc_rdma_netdev must return -EOPNOTSUPP if it - * doesn't support the specified rdma netdev type. + * Driver implementing alloc_rdma_netdev or rdma_netdev_get_params + * must return -EOPNOTSUPP if it doesn't support the specified type. */ struct net_device *(*alloc_rdma_netdev)( struct ib_device *device, @@ -2534,6 +2544,10 @@ struct ib_device { unsigned char name_assign_type, void (*setup)(struct net_device *)); + int (*rdma_netdev_get_params)(struct ib_device *device, u8 port_num, + enum rdma_netdev_t type, + struct rdma_netdev_alloc_params *params); + struct module *owner; struct device dev; struct kobject *ports_parent; @@ -4179,4 +4193,9 @@ struct ib_ucontext *ib_uverbs_get_ucontext(struct ib_uverbs_file *ufile); int uverbs_destroy_def_handler(struct ib_uverbs_file *file, struct uverbs_attr_bundle *attrs); + +struct net_device *rdma_alloc_netdev(struct ib_device *device, u8 port_num, + enum rdma_netdev_t type, const char *name, + unsigned char name_assign_type, + void (*setup)(struct net_device *)); #endif /* IB_VERBS_H */ -- cgit v1.2.3 From a36700589b85443e28170be59fa11c8a104130a5 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 10 Oct 2018 20:29:44 -0500 Subject: signal: Guard against negative signal numbers in copy_siginfo_from_user32 While fixing an out of bounds array access in known_siginfo_layout reported by the kernel test robot it became apparent that the same bug exists in siginfo_layout and affects copy_siginfo_from_user32. The straight forward fix that makes guards against making this mistake in the future and should keep the code size small is to just take an unsigned signal number instead of a signed signal number, as I did to fix known_siginfo_layout. Cc: stable@vger.kernel.org Fixes: cc731525f26a ("signal: Remove kernel interal si_code magic") Signed-off-by: "Eric W. Biederman" --- include/linux/signal.h | 2 +- kernel/signal.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index 706a499d1eb1..200ed96a05af 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -40,7 +40,7 @@ enum siginfo_layout { SIL_SYS, }; -enum siginfo_layout siginfo_layout(int sig, int si_code); +enum siginfo_layout siginfo_layout(unsigned sig, int si_code); /* * Define some primitives to manipulate sigset_t. diff --git a/kernel/signal.c b/kernel/signal.c index 5f5bf374512b..4fd431ce4f91 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2879,7 +2879,7 @@ static bool known_siginfo_layout(unsigned sig, int si_code) return false; } -enum siginfo_layout siginfo_layout(int sig, int si_code) +enum siginfo_layout siginfo_layout(unsigned sig, int si_code) { enum siginfo_layout layout = SIL_KILL; if ((si_code > SI_USER) && (si_code < SI_KERNEL)) { -- cgit v1.2.3 From b048ae6e6c7062809e4398f4d0bfe80870715d3c Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 10 Oct 2018 17:18:19 -0700 Subject: LSM: Rename .security_initcall section to .lsm_info In preparation for switching from initcall to just a regular set of pointers in a section, rename the internal section name. Signed-off-by: Kees Cook Reviewed-by: Casey Schaufler Reviewed-by: James Morris Reviewed-by: John Johansen Signed-off-by: James Morris --- include/asm-generic/vmlinux.lds.h | 10 +++++----- include/linux/init.h | 4 ++-- security/security.c | 4 ++-- 3 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 934a45395547..5079a969e612 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -787,14 +787,14 @@ __con_initcall_end = .; #define SECURITY_INITCALL \ - __security_initcall_start = .; \ - KEEP(*(.security_initcall.init)) \ - __security_initcall_end = .; + __start_lsm_info = .; \ + KEEP(*(.lsm_info.init)) \ + __end_lsm_info = .; /* Older linker script style for security init. */ #define SECURITY_INIT \ - .security_initcall.init : AT(ADDR(.security_initcall.init) - LOAD_OFFSET) { \ - SECURITY_INITCALL \ + .lsm_info.init : AT(ADDR(.lsm_info.init) - LOAD_OFFSET) { \ + LSM_INFO \ } #ifdef CONFIG_BLK_DEV_INITRD diff --git a/include/linux/init.h b/include/linux/init.h index 2538d176dd1f..77636539e77c 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -133,7 +133,7 @@ static inline initcall_t initcall_from_entry(initcall_entry_t *entry) #endif extern initcall_entry_t __con_initcall_start[], __con_initcall_end[]; -extern initcall_entry_t __security_initcall_start[], __security_initcall_end[]; +extern initcall_entry_t __start_lsm_info[], __end_lsm_info[]; /* Used for contructor calls. */ typedef void (*ctor_fn_t)(void); @@ -236,7 +236,7 @@ extern bool initcall_debug; static exitcall_t __exitcall_##fn __exit_call = fn #define console_initcall(fn) ___define_initcall(fn,, .con_initcall) -#define security_initcall(fn) ___define_initcall(fn,, .security_initcall) +#define security_initcall(fn) ___define_initcall(fn,, .lsm_info) struct obs_kernel_param { const char *str; diff --git a/security/security.c b/security/security.c index 4cbcf244a965..892fe6b691cf 100644 --- a/security/security.c +++ b/security/security.c @@ -51,9 +51,9 @@ static void __init do_security_initcalls(void) initcall_t call; initcall_entry_t *ce; - ce = __security_initcall_start; + ce = __start_lsm_info; trace_initcall_level("security"); - while (ce < __security_initcall_end) { + while (ce < __end_lsm_info) { call = initcall_from_entry(ce); trace_initcall_start(call); ret = call(); -- cgit v1.2.3 From 5b89c1bd4c7e5c5ca8c5374fde35ecee6e16496c Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 10 Oct 2018 17:18:21 -0700 Subject: LSM: Convert from initcall to struct lsm_info In preparation for doing more interesting LSM init probing, this converts the existing initcall system into an explicit call into a function pointer from a section-collected struct lsm_info array. Signed-off-by: Kees Cook Reviewed-by: Casey Schaufler Reviewed-by: James Morris Reviewed-by: John Johansen Signed-off-by: James Morris --- include/linux/init.h | 2 -- include/linux/lsm_hooks.h | 12 ++++++++++++ include/linux/module.h | 1 - security/integrity/iint.c | 1 + security/security.c | 14 +++++--------- 5 files changed, 18 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init.h b/include/linux/init.h index 77636539e77c..9c2aba1dbabf 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -133,7 +133,6 @@ static inline initcall_t initcall_from_entry(initcall_entry_t *entry) #endif extern initcall_entry_t __con_initcall_start[], __con_initcall_end[]; -extern initcall_entry_t __start_lsm_info[], __end_lsm_info[]; /* Used for contructor calls. */ typedef void (*ctor_fn_t)(void); @@ -236,7 +235,6 @@ extern bool initcall_debug; static exitcall_t __exitcall_##fn __exit_call = fn #define console_initcall(fn) ___define_initcall(fn,, .con_initcall) -#define security_initcall(fn) ___define_initcall(fn,, .lsm_info) struct obs_kernel_param { const char *str; diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 97a020c616ad..d13059feca09 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -2039,6 +2039,18 @@ extern char *lsm_names; extern void security_add_hooks(struct security_hook_list *hooks, int count, char *lsm); +struct lsm_info { + int (*init)(void); /* Required. */ +}; + +extern struct lsm_info __start_lsm_info[], __end_lsm_info[]; + +#define security_initcall(lsm) \ + static struct lsm_info __lsm_##lsm \ + __used __section(.lsm_info.init) \ + __aligned(sizeof(unsigned long)) \ + = { .init = lsm, } + #ifdef CONFIG_SECURITY_SELINUX_DISABLE /* * Assuring the safety of deleting a security module is up to diff --git a/include/linux/module.h b/include/linux/module.h index f807f15bebbe..264979283756 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -123,7 +123,6 @@ extern void cleanup_module(void); #define late_initcall_sync(fn) module_init(fn) #define console_initcall(fn) module_init(fn) -#define security_initcall(fn) module_init(fn) /* Each module must use one module_init(). */ #define module_init(initfn) \ diff --git a/security/integrity/iint.c b/security/integrity/iint.c index 5a6810041e5c..70d21b566955 100644 --- a/security/integrity/iint.c +++ b/security/integrity/iint.c @@ -22,6 +22,7 @@ #include #include #include +#include #include "integrity.h" static struct rb_root integrity_iint_tree = RB_ROOT; diff --git a/security/security.c b/security/security.c index 41a5da2c7faf..e74f46fba591 100644 --- a/security/security.c +++ b/security/security.c @@ -43,16 +43,12 @@ char *lsm_names; static __initdata char chosen_lsm[SECURITY_NAME_MAX + 1] = CONFIG_DEFAULT_SECURITY; -static void __init do_security_initcalls(void) +static void __init major_lsm_init(void) { - initcall_t call; - initcall_entry_t *ce; + struct lsm_info *lsm; - ce = __start_lsm_info; - while (ce < __end_lsm_info) { - call = initcall_from_entry(ce); - call(); - ce++; + for (lsm = __start_lsm_info; lsm < __end_lsm_info; lsm++) { + lsm->init(); } } @@ -82,7 +78,7 @@ int __init security_init(void) /* * Load all the remaining security modules. */ - do_security_initcalls(); + major_lsm_init(); return 0; } -- cgit v1.2.3 From 3d6e5f6dcf6561e57b6466e43e14029fb196028d Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 10 Oct 2018 17:18:23 -0700 Subject: LSM: Convert security_initcall() into DEFINE_LSM() Instead of using argument-based initializers, switch to defining the contents of struct lsm_info on a per-LSM basis. This also drops the final use of the now inaccurate "initcall" naming. Signed-off-by: Kees Cook Reviewed-by: Casey Schaufler Reviewed-by: James Morris Signed-off-by: James Morris --- include/linux/lsm_hooks.h | 5 ++--- security/apparmor/lsm.c | 4 +++- security/integrity/iint.c | 4 +++- security/selinux/hooks.c | 4 +++- security/smack/smack_lsm.c | 4 +++- security/tomoyo/tomoyo.c | 4 +++- 6 files changed, 17 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index d13059feca09..9c6b4198ff5a 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -2045,11 +2045,10 @@ struct lsm_info { extern struct lsm_info __start_lsm_info[], __end_lsm_info[]; -#define security_initcall(lsm) \ +#define DEFINE_LSM(lsm) \ static struct lsm_info __lsm_##lsm \ __used __section(.lsm_info.init) \ - __aligned(sizeof(unsigned long)) \ - = { .init = lsm, } + __aligned(sizeof(unsigned long)) #ifdef CONFIG_SECURITY_SELINUX_DISABLE /* diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index 8b8b70620bbe..c4863956c832 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -1606,4 +1606,6 @@ alloc_out: return error; } -security_initcall(apparmor_init); +DEFINE_LSM(apparmor) = { + .init = apparmor_init, +}; diff --git a/security/integrity/iint.c b/security/integrity/iint.c index 70d21b566955..94e8e1820748 100644 --- a/security/integrity/iint.c +++ b/security/integrity/iint.c @@ -175,7 +175,9 @@ static int __init integrity_iintcache_init(void) 0, SLAB_PANIC, init_once); return 0; } -security_initcall(integrity_iintcache_init); +DEFINE_LSM(integrity) = { + .init = integrity_iintcache_init, +}; /* diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index ad9a9b8e9979..6ca2e89ddbd6 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -7202,7 +7202,9 @@ void selinux_complete_init(void) /* SELinux requires early initialization in order to label all processes and objects when they are created. */ -security_initcall(selinux_init); +DEFINE_LSM(selinux) = { + .init = selinux_init, +}; #if defined(CONFIG_NETFILTER) diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index 340fc30ad85d..c62e26939a69 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -4882,4 +4882,6 @@ static __init int smack_init(void) * Smack requires early initialization in order to label * all processes and objects when they are created. */ -security_initcall(smack_init); +DEFINE_LSM(smack) = { + .init = smack_init, +}; diff --git a/security/tomoyo/tomoyo.c b/security/tomoyo/tomoyo.c index 9f932e2d6852..b2d833999910 100644 --- a/security/tomoyo/tomoyo.c +++ b/security/tomoyo/tomoyo.c @@ -550,4 +550,6 @@ static int __init tomoyo_init(void) return 0; } -security_initcall(tomoyo_init); +DEFINE_LSM(tomoyo) = { + .init = tomoyo_init, +}; -- cgit v1.2.3 From 07aed2f2af5a5892ced035dbcf3993f630825fc3 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 10 Oct 2018 17:18:24 -0700 Subject: LSM: Record LSM name in struct lsm_info In preparation for making LSM selections outside of the LSMs, include the name of LSMs in struct lsm_info. Signed-off-by: Kees Cook Reviewed-by: Casey Schaufler Signed-off-by: James Morris --- include/linux/lsm_hooks.h | 1 + security/apparmor/lsm.c | 1 + security/integrity/iint.c | 1 + security/selinux/hooks.c | 1 + security/smack/smack_lsm.c | 1 + security/tomoyo/tomoyo.c | 1 + 6 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 9c6b4198ff5a..ae159b02f3ab 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -2040,6 +2040,7 @@ extern void security_add_hooks(struct security_hook_list *hooks, int count, char *lsm); struct lsm_info { + const char *name; /* Required. */ int (*init)(void); /* Required. */ }; diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index c4863956c832..dca4b7dbf368 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -1607,5 +1607,6 @@ alloc_out: } DEFINE_LSM(apparmor) = { + .name = "apparmor", .init = apparmor_init, }; diff --git a/security/integrity/iint.c b/security/integrity/iint.c index 94e8e1820748..1ea05da2323d 100644 --- a/security/integrity/iint.c +++ b/security/integrity/iint.c @@ -176,6 +176,7 @@ static int __init integrity_iintcache_init(void) return 0; } DEFINE_LSM(integrity) = { + .name = "integrity", .init = integrity_iintcache_init, }; diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 6ca2e89ddbd6..9651bccae270 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -7203,6 +7203,7 @@ void selinux_complete_init(void) /* SELinux requires early initialization in order to label all processes and objects when they are created. */ DEFINE_LSM(selinux) = { + .name = "selinux", .init = selinux_init, }; diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index c62e26939a69..2fb56bcf1316 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -4883,5 +4883,6 @@ static __init int smack_init(void) * all processes and objects when they are created. */ DEFINE_LSM(smack) = { + .name = "smack", .init = smack_init, }; diff --git a/security/tomoyo/tomoyo.c b/security/tomoyo/tomoyo.c index b2d833999910..1b5b5097efd7 100644 --- a/security/tomoyo/tomoyo.c +++ b/security/tomoyo/tomoyo.c @@ -551,5 +551,6 @@ static int __init tomoyo_init(void) } DEFINE_LSM(tomoyo) = { + .name = "tomoyo", .init = tomoyo_init, }; -- cgit v1.2.3 From ce76d938dd98817f998c905e01fbb99b072c0bf6 Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Fri, 5 Oct 2018 15:43:05 +0300 Subject: lib: Add memcat_p(): paste 2 pointer arrays together This adds a helper to paste 2 pointer arrays together, useful for merging various types of attribute arrays. There are a few places in the kernel tree where this is open coded, and I just added one more in the STM class. The naming is inspired by memset_p() and memcat(), and partial credit for it goes to Andy Shevchenko. This patch adds the function wrapped in a type-enforcing macro and a test module. Signed-off-by: Alexander Shishkin Reviewed-by: Andy Shevchenko Tested-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- include/linux/string.h | 7 +++ lib/Kconfig.debug | 8 ++++ lib/Makefile | 1 + lib/string.c | 31 +++++++++++++ lib/test_memcat_p.c | 115 +++++++++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 162 insertions(+) create mode 100644 lib/test_memcat_p.c (limited to 'include/linux') diff --git a/include/linux/string.h b/include/linux/string.h index 4a5a0eb7df51..27d0482e5e05 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -131,6 +131,13 @@ static inline void *memset_p(void **p, void *v, __kernel_size_t n) return memset64((uint64_t *)p, (uintptr_t)v, n); } +extern void **__memcat_p(void **a, void **b); +#define memcat_p(a, b) ({ \ + BUILD_BUG_ON_MSG(!__same_type(*(a), *(b)), \ + "type mismatch in memcat_p()"); \ + (typeof(*a) *)__memcat_p((void **)(a), (void **)(b)); \ +}) + #ifndef __HAVE_ARCH_MEMCPY extern void * memcpy(void *,const void *,__kernel_size_t); #endif diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 4966c4fbe7f7..c0176510262e 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1965,6 +1965,14 @@ config TEST_DEBUG_VIRTUAL If unsure, say N. +config TEST_MEMCAT_P + tristate "Test memcat_p() helper function" + help + Test the memcat_p() helper for correctly merging two + pointer arrays together. + + If unsure, say N. + endif # RUNTIME_TESTING_MENU config MEMTEST diff --git a/lib/Makefile b/lib/Makefile index ca3f7ebb900d..c2588a2d7b1e 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -71,6 +71,7 @@ obj-$(CONFIG_TEST_UUID) += test_uuid.o obj-$(CONFIG_TEST_PARMAN) += test_parman.o obj-$(CONFIG_TEST_KMOD) += test_kmod.o obj-$(CONFIG_TEST_DEBUG_VIRTUAL) += test_debug_virtual.o +obj-$(CONFIG_TEST_MEMCAT_P) += test_memcat_p.o ifeq ($(CONFIG_DEBUG_KOBJECT),y) CFLAGS_kobject.o += -DDEBUG diff --git a/lib/string.c b/lib/string.c index 2c0900a5d51a..453f35994eb6 100644 --- a/lib/string.c +++ b/lib/string.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include @@ -890,6 +891,36 @@ void *memscan(void *addr, int c, size_t size) EXPORT_SYMBOL(memscan); #endif +/* + * Merge two NULL-terminated pointer arrays into a newly allocated + * array, which is also NULL-terminated. Nomenclature is inspired by + * memset_p() and memcat() found elsewhere in the kernel source tree. + */ +void **__memcat_p(void **a, void **b) +{ + void **p = a, **new; + int nr; + + /* count the elements in both arrays */ + for (nr = 0, p = a; *p; nr++, p++) + ; + for (p = b; *p; nr++, p++) + ; + /* one for the NULL-terminator */ + nr++; + + new = kmalloc_array(nr, sizeof(void *), GFP_KERNEL); + if (!new) + return NULL; + + /* nr -> last index; p points to NULL in b[] */ + for (nr--; nr >= 0; nr--, p = p == b ? &a[nr] : p - 1) + new[nr] = *p; + + return new; +} +EXPORT_SYMBOL_GPL(__memcat_p); + #ifndef __HAVE_ARCH_STRSTR /** * strstr - Find the first substring in a %NUL terminated string diff --git a/lib/test_memcat_p.c b/lib/test_memcat_p.c new file mode 100644 index 000000000000..2b163a749ecb --- /dev/null +++ b/lib/test_memcat_p.c @@ -0,0 +1,115 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test cases for memcat_p() in lib/string.c + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include + +struct test_struct { + int num; + unsigned int magic; +}; + +#define MAGIC 0xf00ff00f +/* Size of each of the NULL-terminated input arrays */ +#define INPUT_MAX 128 +/* Expected number of non-NULL elements in the output array */ +#define EXPECT (INPUT_MAX * 2 - 2) + +static int __init test_memcat_p_init(void) +{ + struct test_struct **in0, **in1, **out, **p; + int err = -ENOMEM, i, r, total = 0; + + in0 = kcalloc(INPUT_MAX, sizeof(*in0), GFP_KERNEL); + if (!in0) + return err; + + in1 = kcalloc(INPUT_MAX, sizeof(*in1), GFP_KERNEL); + if (!in1) + goto err_free_in0; + + for (i = 0, r = 1; i < INPUT_MAX - 1; i++) { + in0[i] = kmalloc(sizeof(**in0), GFP_KERNEL); + if (!in0[i]) + goto err_free_elements; + + in1[i] = kmalloc(sizeof(**in1), GFP_KERNEL); + if (!in1[i]) { + kfree(in0[i]); + goto err_free_elements; + } + + /* lifted from test_sort.c */ + r = (r * 725861) % 6599; + in0[i]->num = r; + in1[i]->num = -r; + in0[i]->magic = MAGIC; + in1[i]->magic = MAGIC; + } + + in0[i] = in1[i] = NULL; + + out = memcat_p(in0, in1); + if (!out) + goto err_free_all_elements; + + err = -EINVAL; + for (i = 0, p = out; *p && (i < INPUT_MAX * 2 - 1); p++, i++) { + total += (*p)->num; + + if ((*p)->magic != MAGIC) { + pr_err("test failed: wrong magic at %d: %u\n", i, + (*p)->magic); + goto err_free_out; + } + } + + if (total) { + pr_err("test failed: expected zero total, got %d\n", total); + goto err_free_out; + } + + if (i != EXPECT) { + pr_err("test failed: expected output size %d, got %d\n", + EXPECT, i); + goto err_free_out; + } + + for (i = 0; i < INPUT_MAX - 1; i++) + if (out[i] != in0[i] || out[i + INPUT_MAX - 1] != in1[i]) { + pr_err("test failed: wrong element order at %d\n", i); + goto err_free_out; + } + + err = 0; + pr_info("test passed\n"); + +err_free_out: + kfree(out); +err_free_all_elements: + i = INPUT_MAX; +err_free_elements: + for (i--; i >= 0; i--) { + kfree(in1[i]); + kfree(in0[i]); + } + + kfree(in1); +err_free_in0: + kfree(in0); + + return err; +} + +static void __exit test_memcat_p_exit(void) +{ +} + +module_init(test_memcat_p_init); +module_exit(test_memcat_p_exit); + +MODULE_LICENSE("GPL"); -- cgit v1.2.3 From f458e832ba510f843807fc2c2906a8fb59554c9f Mon Sep 17 00:00:00 2001 From: Chaitanya T K Date: Sat, 6 Oct 2018 19:34:59 +0200 Subject: mac80211: minstrel: Enable STBC and LDPC for VHT Rates If peer support reception of STBC and LDPC, enable them for better performance. Signed-off-by: Chaitanya TK Signed-off-by: Felix Fietkau Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 1 + net/mac80211/rc80211_minstrel_ht.c | 23 +++++++++++++++-------- 2 files changed, 16 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index c4809ad8ab46..0ef67f837ae1 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1670,6 +1670,7 @@ struct ieee80211_mu_edca_param_set { #define IEEE80211_VHT_CAP_RXSTBC_3 0x00000300 #define IEEE80211_VHT_CAP_RXSTBC_4 0x00000400 #define IEEE80211_VHT_CAP_RXSTBC_MASK 0x00000700 +#define IEEE80211_VHT_CAP_RXSTBC_SHIFT 8 #define IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE 0x00000800 #define IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE 0x00001000 #define IEEE80211_VHT_CAP_BEAMFORMEE_STS_SHIFT 13 diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index 67ebdeaffbbc..16d1ac30978d 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -1130,7 +1130,7 @@ minstrel_ht_update_caps(void *priv, struct ieee80211_supported_band *sband, struct minstrel_ht_sta_priv *msp = priv_sta; struct minstrel_ht_sta *mi = &msp->ht; struct ieee80211_mcs_info *mcs = &sta->ht_cap.mcs; - u16 sta_cap = sta->ht_cap.cap; + u16 ht_cap = sta->ht_cap.cap; struct ieee80211_sta_vht_cap *vht_cap = &sta->vht_cap; struct sta_info *sinfo = container_of(sta, struct sta_info, sta); int use_vht; @@ -1138,6 +1138,7 @@ minstrel_ht_update_caps(void *priv, struct ieee80211_supported_band *sband, int ack_dur; int stbc; int i; + bool ldpc; /* fall back to the old minstrel for legacy stations */ if (!sta->ht_cap.ht_supported) @@ -1175,16 +1176,22 @@ minstrel_ht_update_caps(void *priv, struct ieee80211_supported_band *sband, } mi->sample_tries = 4; - /* TODO tx_flags for vht - ATM the RC API is not fine-grained enough */ if (!use_vht) { - stbc = (sta_cap & IEEE80211_HT_CAP_RX_STBC) >> + stbc = (ht_cap & IEEE80211_HT_CAP_RX_STBC) >> IEEE80211_HT_CAP_RX_STBC_SHIFT; - mi->tx_flags |= stbc << IEEE80211_TX_CTL_STBC_SHIFT; - if (sta_cap & IEEE80211_HT_CAP_LDPC_CODING) - mi->tx_flags |= IEEE80211_TX_CTL_LDPC; + ldpc = ht_cap & IEEE80211_HT_CAP_LDPC_CODING; + } else { + stbc = (vht_cap->cap & IEEE80211_VHT_CAP_RXSTBC_MASK) >> + IEEE80211_VHT_CAP_RXSTBC_SHIFT; + + ldpc = vht_cap->cap & IEEE80211_VHT_CAP_RXLDPC; } + mi->tx_flags |= stbc << IEEE80211_TX_CTL_STBC_SHIFT; + if (ldpc) + mi->tx_flags |= IEEE80211_TX_CTL_LDPC; + for (i = 0; i < ARRAY_SIZE(mi->groups); i++) { u32 gflags = minstrel_mcs_groups[i].flags; int bw, nss; @@ -1197,10 +1204,10 @@ minstrel_ht_update_caps(void *priv, struct ieee80211_supported_band *sband, if (gflags & IEEE80211_TX_RC_SHORT_GI) { if (gflags & IEEE80211_TX_RC_40_MHZ_WIDTH) { - if (!(sta_cap & IEEE80211_HT_CAP_SGI_40)) + if (!(ht_cap & IEEE80211_HT_CAP_SGI_40)) continue; } else { - if (!(sta_cap & IEEE80211_HT_CAP_SGI_20)) + if (!(ht_cap & IEEE80211_HT_CAP_SGI_20)) continue; } } -- cgit v1.2.3 From 953923c09fe83255ae11845db1c9eb576ba73df8 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Thu, 11 Oct 2018 11:06:29 -0400 Subject: dm: rename DM_TYPE_MQ_REQUEST_BASED to DM_TYPE_REQUEST_BASED Now that request-based DM is only using blk-mq, there is no need to differentiate between legacy "rq" and new "mq". We're back to a single request-based DM -- and there was much rejoicing! Signed-off-by: Mike Snitzer --- drivers/md/dm-mpath.c | 14 +++++--------- drivers/md/dm-table.c | 7 +------ drivers/md/dm.c | 2 -- include/linux/device-mapper.h | 5 ++--- 4 files changed, 8 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index a24ed3973e7c..d6a66921daf4 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -203,7 +203,7 @@ static struct multipath *alloc_multipath(struct dm_target *ti) static int alloc_multipath_stage2(struct dm_target *ti, struct multipath *m) { if (m->queue_mode == DM_TYPE_NONE) { - m->queue_mode = DM_TYPE_MQ_REQUEST_BASED; + m->queue_mode = DM_TYPE_REQUEST_BASED; } else if (m->queue_mode == DM_TYPE_BIO_BASED) { INIT_WORK(&m->process_queued_bios, process_queued_bios); /* @@ -658,7 +658,7 @@ static int multipath_map_bio(struct dm_target *ti, struct bio *bio) static void process_queued_io_list(struct multipath *m) { - if (m->queue_mode == DM_TYPE_MQ_REQUEST_BASED) + if (m->queue_mode == DM_TYPE_REQUEST_BASED) dm_mq_kick_requeue_list(dm_table_get_md(m->ti->table)); else if (m->queue_mode == DM_TYPE_BIO_BASED) queue_work(kmultipathd, &m->process_queued_bios); @@ -1079,10 +1079,9 @@ static int parse_features(struct dm_arg_set *as, struct multipath *m) if (!strcasecmp(queue_mode_name, "bio")) m->queue_mode = DM_TYPE_BIO_BASED; - else if (!strcasecmp(queue_mode_name, "rq")) + else if (!strcasecmp(queue_mode_name, "rq") || + !strcasecmp(queue_mode_name, "mq")) m->queue_mode = DM_TYPE_REQUEST_BASED; - else if (!strcasecmp(queue_mode_name, "mq")) - m->queue_mode = DM_TYPE_MQ_REQUEST_BASED; else { ti->error = "Unknown 'queue_mode' requested"; r = -EINVAL; @@ -1716,9 +1715,6 @@ static void multipath_status(struct dm_target *ti, status_type_t type, case DM_TYPE_BIO_BASED: DMEMIT("queue_mode bio "); break; - case DM_TYPE_MQ_REQUEST_BASED: - DMEMIT("queue_mode mq "); - break; default: WARN_ON_ONCE(true); break; @@ -1962,7 +1958,7 @@ static int multipath_busy(struct dm_target *ti) /* no paths available, for blk-mq: rely on IO mapping to delay requeue */ if (!atomic_read(&m->nr_valid_paths) && test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) - return (m->queue_mode != DM_TYPE_MQ_REQUEST_BASED); + return (m->queue_mode != DM_TYPE_REQUEST_BASED); /* Guess which priority_group will be used at next mapping time */ pg = READ_ONCE(m->current_pg); diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 96e152c339a6..eeea32bb6a3e 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -871,8 +871,7 @@ static bool __table_type_bio_based(enum dm_queue_mode table_type) static bool __table_type_request_based(enum dm_queue_mode table_type) { - return (table_type == DM_TYPE_REQUEST_BASED || - table_type == DM_TYPE_MQ_REQUEST_BASED); + return table_type == DM_TYPE_REQUEST_BASED; } void dm_table_set_type(struct dm_table *t, enum dm_queue_mode type) @@ -986,10 +985,6 @@ verify_bio_based: BUG_ON(!request_based); /* No targets in this table */ - /* - * The only way to establish DM_TYPE_MQ_REQUEST_BASED is by - * having a compatible target use dm_table_set_type. - */ t->type = DM_TYPE_REQUEST_BASED; verify_rq_based: diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 0ce00c6f5f9a..bf36e2635ea7 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -2213,7 +2213,6 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t) switch (type) { case DM_TYPE_REQUEST_BASED: - case DM_TYPE_MQ_REQUEST_BASED: r = dm_mq_init_request_queue(md, t); if (r) { DMERR("Cannot initialize queue for request-based dm-mq mapped device"); @@ -2946,7 +2945,6 @@ struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, enum dm_qu goto out; break; case DM_TYPE_REQUEST_BASED: - case DM_TYPE_MQ_REQUEST_BASED: pool_size = max(dm_get_reserved_rq_based_ios(), min_pool_size); front_pad = offsetof(struct dm_rq_clone_bio_info, clone); /* per_io_data_size is used for blk-mq pdu at queue allocation */ diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 6fb0808e87c8..8d937754aa0c 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -26,9 +26,8 @@ enum dm_queue_mode { DM_TYPE_NONE = 0, DM_TYPE_BIO_BASED = 1, DM_TYPE_REQUEST_BASED = 2, - DM_TYPE_MQ_REQUEST_BASED = 3, - DM_TYPE_DAX_BIO_BASED = 4, - DM_TYPE_NVME_BIO_BASED = 5, + DM_TYPE_DAX_BIO_BASED = 3, + DM_TYPE_NVME_BIO_BASED = 4, }; typedef enum { STATUSTYPE_INFO, STATUSTYPE_TABLE } status_type_t; -- cgit v1.2.3 From 3f2aa244ee1a0d17ed5b6c86564d2c1b24d1c96b Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Wed, 3 Oct 2018 13:21:07 +0100 Subject: TC: Set DMA masks for devices Fix a TURBOchannel support regression with commit 205e1b7f51e4 ("dma-mapping: warn when there is no coherent_dma_mask") that caused coherent DMA allocations to produce a warning such as: defxx: v1.11 2014/07/01 Lawrence V. Stefani and others tc1: DEFTA at MMIO addr = 0x1e900000, IRQ = 20, Hardware addr = 08-00-2b-a3-a3-29 ------------[ cut here ]------------ WARNING: CPU: 0 PID: 1 at ./include/linux/dma-mapping.h:516 dfx_dev_register+0x670/0x678 Modules linked in: CPU: 0 PID: 1 Comm: swapper Not tainted 4.19.0-rc6 #2 Stack : ffffffff8009ffc0 fffffffffffffec0 0000000000000000 ffffffff80647650 0000000000000000 0000000000000000 ffffffff806f5f80 ffffffffffffffff 0000000000000000 0000000000000000 0000000000000001 ffffffff8065d4e8 98000000031b6300 ffffffff80563478 ffffffff805685b0 ffffffffffffffff 0000000000000000 ffffffff805d6720 0000000000000204 ffffffff80388df8 0000000000000000 0000000000000009 ffffffff8053efd0 ffffffff806657d0 0000000000000000 ffffffff803177f8 0000000000000000 ffffffff806d0000 9800000003078000 980000000307b9e0 000000001e900000 ffffffff80067940 0000000000000000 ffffffff805d6720 0000000000000204 ffffffff80388df8 ffffffff805176c0 ffffffff8004dc78 0000000000000000 ffffffff80067940 ... Call Trace: [] show_stack+0xa0/0x130 [] __warn+0x128/0x170 ---[ end trace b1d1e094f67f3bb2 ]--- This is because the TURBOchannel bus driver fails to set the coherent DMA mask for devices enumerated. Set the regular and coherent DMA masks for TURBOchannel devices then, observing that the bus protocol supports a 34-bit (16GiB) DMA address space, by interpreting the value presented in the address cycle across the 32 `ad' lines as a 32-bit word rather than byte address[1]. The architectural size of the TURBOchannel DMA address space exceeds the maximum amount of RAM any actual TURBOchannel system in existence may have, hence both masks are the same. This removes the warning shown above. References: [1] "TURBOchannel Hardware Specification", EK-369AA-OD-007B, Digital Equipment Corporation, January 1993, Section "DMA", pp. 1-15 -- 1-17 Signed-off-by: Maciej W. Rozycki Signed-off-by: Paul Burton Patchwork: https://patchwork.linux-mips.org/patch/20835/ Fixes: 205e1b7f51e4 ("dma-mapping: warn when there is no coherent_dma_mask") Cc: stable@vger.kernel.org # 4.16+ Cc: Ralf Baechle --- drivers/tc/tc.c | 8 +++++++- include/linux/tc.h | 1 + 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/tc/tc.c b/drivers/tc/tc.c index 3be9519654e5..cf3fad2cb871 100644 --- a/drivers/tc/tc.c +++ b/drivers/tc/tc.c @@ -2,7 +2,7 @@ * TURBOchannel bus services. * * Copyright (c) Harald Koerfgen, 1998 - * Copyright (c) 2001, 2003, 2005, 2006 Maciej W. Rozycki + * Copyright (c) 2001, 2003, 2005, 2006, 2018 Maciej W. Rozycki * Copyright (c) 2005 James Simmons * * This file is subject to the terms and conditions of the GNU @@ -10,6 +10,7 @@ * directory of this archive for more details. */ #include +#include #include #include #include @@ -92,6 +93,11 @@ static void __init tc_bus_add_devices(struct tc_bus *tbus) tdev->dev.bus = &tc_bus_type; tdev->slot = slot; + /* TURBOchannel has 34-bit DMA addressing (16GiB space). */ + tdev->dma_mask = DMA_BIT_MASK(34); + tdev->dev.dma_mask = &tdev->dma_mask; + tdev->dev.coherent_dma_mask = DMA_BIT_MASK(34); + for (i = 0; i < 8; i++) { tdev->firmware[i] = readb(module + offset + TC_FIRM_VER + 4 * i); diff --git a/include/linux/tc.h b/include/linux/tc.h index f92511e57cdb..a60639f37963 100644 --- a/include/linux/tc.h +++ b/include/linux/tc.h @@ -84,6 +84,7 @@ struct tc_dev { device. */ struct device dev; /* Generic device interface. */ struct resource resource; /* Address space of this device. */ + u64 dma_mask; /* DMA addressable range. */ char vendor[9]; char name[9]; char firmware[9]; -- cgit v1.2.3 From 81732b26e05994552f347746eb11762e986079a0 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 11 Sep 2018 23:28:07 -0400 Subject: usb-serial: begin switching to ->[sg]et_serial() add such methods for usb_serial_driver, provide tty_operations ->[sg]et_serial() calling those. For now the lack of methods in driver means ENOIOCTLCMD from usb-serial ->[sg]et_serial(), making tty_ioctl() fall back to calling ->ioctl(). Once all drivers are converted, we'll be returning -ENOTTY instead, completing the switchover. Reviewed-by: Johan Hovold Signed-off-by: Al Viro --- drivers/usb/serial/usb-serial.c | 20 ++++++++++++++++++++ include/linux/usb/serial.h | 2 ++ 2 files changed, 22 insertions(+) (limited to 'include/linux') diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c index f7aaa7f079e1..0f96d82fc575 100644 --- a/drivers/usb/serial/usb-serial.c +++ b/drivers/usb/serial/usb-serial.c @@ -396,6 +396,24 @@ static void serial_unthrottle(struct tty_struct *tty) port->serial->type->unthrottle(tty); } +static int serial_get_serial(struct tty_struct *tty, struct serial_struct *ss) +{ + struct usb_serial_port *port = tty->driver_data; + + if (port->serial->type->get_serial) + return port->serial->type->get_serial(tty, ss); + return -ENOIOCTLCMD; +} + +static int serial_set_serial(struct tty_struct *tty, struct serial_struct *ss) +{ + struct usb_serial_port *port = tty->driver_data; + + if (port->serial->type->set_serial) + return port->serial->type->set_serial(tty, ss); + return -ENOIOCTLCMD; +} + static int serial_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { @@ -1177,6 +1195,8 @@ static const struct tty_operations serial_ops = { .tiocmget = serial_tiocmget, .tiocmset = serial_tiocmset, .get_icount = serial_get_icount, + .set_serial = serial_set_serial, + .get_serial = serial_get_serial, .cleanup = serial_cleanup, .install = serial_install, .proc_show = serial_proc_show, diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index 106551a5616e..1c19f77ed541 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -285,6 +285,8 @@ struct usb_serial_driver { int (*write_room)(struct tty_struct *tty); int (*ioctl)(struct tty_struct *tty, unsigned int cmd, unsigned long arg); + int (*get_serial)(struct tty_struct *tty, struct serial_struct *ss); + int (*set_serial)(struct tty_struct *tty, struct serial_struct *ss); void (*set_termios)(struct tty_struct *tty, struct usb_serial_port *port, struct ktermios *old); void (*break_ctl)(struct tty_struct *tty, int break_state); -- cgit v1.2.3 From f0193d3ea73b966b5dbfa272c8228d743b8856ef Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 13 Sep 2018 22:12:15 -0400 Subject: change semantics of ldisc ->compat_ioctl() First of all, make it return int. Returning long when native method had never allowed that is ridiculous and inconvenient. More importantly, change the caller; if ldisc ->compat_ioctl() is NULL or returns -ENOIOCTLCMD, tty_compat_ioctl() will try to feed cmd and compat_ptr(arg) to ldisc's native ->ioctl(). That simplifies ->compat_ioctl() instances quite a bit - they only need to deal with ioctls that are neither generic tty ones (those would get shunted off to tty_ioctl()) nor simple compat pointer ones. Note that something like TCFLSH won't reach ->compat_ioctl(), even if ldisc ->ioctl() does handle it - it will be recognized earlier and passed to tty_ioctl() (and ultimately - ldisc ->ioctl()). For many ldiscs it means that NULL ->compat_ioctl() does the right thing. Those where it won't serve (see e.g. n_r3964.c) are also easily dealt with - we need to handle the numeric-argument ioctls (calling the native instance) and, if such would exist, the ioctls that need layout conversion, etc. All in-tree ldiscs dealt with. Signed-off-by: Al Viro --- drivers/bluetooth/hci_ldisc.c | 1 + drivers/input/serio/serport.c | 2 +- drivers/net/hamradio/6pack.c | 21 --------------------- drivers/net/hamradio/mkiss.c | 21 --------------------- drivers/net/slip/slip.c | 25 ------------------------- drivers/net/wan/x25_asy.c | 19 ------------------- drivers/tty/n_gsm.c | 11 ----------- drivers/tty/n_r3964.c | 22 ++++++++++++++++++++++ drivers/tty/tty_io.c | 3 +++ include/linux/tty_ldisc.h | 10 ++++++++-- net/nfc/nci/uart.c | 1 + 11 files changed, 36 insertions(+), 100 deletions(-) (limited to 'include/linux') diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c index 963bb0309e25..ae0dd57a8e99 100644 --- a/drivers/bluetooth/hci_ldisc.c +++ b/drivers/bluetooth/hci_ldisc.c @@ -821,6 +821,7 @@ static int __init hci_uart_init(void) hci_uart_ldisc.read = hci_uart_tty_read; hci_uart_ldisc.write = hci_uart_tty_write; hci_uart_ldisc.ioctl = hci_uart_tty_ioctl; + hci_uart_ldisc.compat_ioctl = hci_uart_tty_ioctl; hci_uart_ldisc.poll = hci_uart_tty_poll; hci_uart_ldisc.receive_buf = hci_uart_tty_receive; hci_uart_ldisc.write_wakeup = hci_uart_tty_wakeup; diff --git a/drivers/input/serio/serport.c b/drivers/input/serio/serport.c index f8ead9f9c77e..5977b8a34ebe 100644 --- a/drivers/input/serio/serport.c +++ b/drivers/input/serio/serport.c @@ -226,7 +226,7 @@ static int serport_ldisc_ioctl(struct tty_struct *tty, struct file *file, #ifdef CONFIG_COMPAT #define COMPAT_SPIOCSTYPE _IOW('q', 0x01, compat_ulong_t) -static long serport_ldisc_compat_ioctl(struct tty_struct *tty, +static int serport_ldisc_compat_ioctl(struct tty_struct *tty, struct file *file, unsigned int cmd, unsigned long arg) { diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c index d79a69dd2146..17e6dcd2eb42 100644 --- a/drivers/net/hamradio/6pack.c +++ b/drivers/net/hamradio/6pack.c @@ -34,7 +34,6 @@ #include #include #include -#include #include #define SIXPACK_VERSION "Revision: 0.3.0" @@ -752,23 +751,6 @@ static int sixpack_ioctl(struct tty_struct *tty, struct file *file, return err; } -#ifdef CONFIG_COMPAT -static long sixpack_compat_ioctl(struct tty_struct * tty, struct file * file, - unsigned int cmd, unsigned long arg) -{ - switch (cmd) { - case SIOCGIFNAME: - case SIOCGIFENCAP: - case SIOCSIFENCAP: - case SIOCSIFHWADDR: - return sixpack_ioctl(tty, file, cmd, - (unsigned long)compat_ptr(arg)); - } - - return -ENOIOCTLCMD; -} -#endif - static struct tty_ldisc_ops sp_ldisc = { .owner = THIS_MODULE, .magic = TTY_LDISC_MAGIC, @@ -776,9 +758,6 @@ static struct tty_ldisc_ops sp_ldisc = { .open = sixpack_open, .close = sixpack_close, .ioctl = sixpack_ioctl, -#ifdef CONFIG_COMPAT - .compat_ioctl = sixpack_compat_ioctl, -#endif .receive_buf = sixpack_receive_buf, .write_wakeup = sixpack_write_wakeup, }; diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c index 13e4c1eff353..802233d41b25 100644 --- a/drivers/net/hamradio/mkiss.c +++ b/drivers/net/hamradio/mkiss.c @@ -35,7 +35,6 @@ #include #include #include -#include #include @@ -875,23 +874,6 @@ static int mkiss_ioctl(struct tty_struct *tty, struct file *file, return err; } -#ifdef CONFIG_COMPAT -static long mkiss_compat_ioctl(struct tty_struct *tty, struct file *file, - unsigned int cmd, unsigned long arg) -{ - switch (cmd) { - case SIOCGIFNAME: - case SIOCGIFENCAP: - case SIOCSIFENCAP: - case SIOCSIFHWADDR: - return mkiss_ioctl(tty, file, cmd, - (unsigned long)compat_ptr(arg)); - } - - return -ENOIOCTLCMD; -} -#endif - /* * Handle the 'receiver data ready' interrupt. * This function is called by the 'tty_io' module in the kernel when @@ -966,9 +948,6 @@ static struct tty_ldisc_ops ax_ldisc = { .open = mkiss_open, .close = mkiss_close, .ioctl = mkiss_ioctl, -#ifdef CONFIG_COMPAT - .compat_ioctl = mkiss_compat_ioctl, -#endif .receive_buf = mkiss_receive_buf, .write_wakeup = mkiss_write_wakeup }; diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c index b008266e91ea..9757f1fc104f 100644 --- a/drivers/net/slip/slip.c +++ b/drivers/net/slip/slip.c @@ -79,7 +79,6 @@ #include #include #include -#include #include #include #include @@ -1167,27 +1166,6 @@ static int slip_ioctl(struct tty_struct *tty, struct file *file, } } -#ifdef CONFIG_COMPAT -static long slip_compat_ioctl(struct tty_struct *tty, struct file *file, - unsigned int cmd, unsigned long arg) -{ - switch (cmd) { - case SIOCGIFNAME: - case SIOCGIFENCAP: - case SIOCSIFENCAP: - case SIOCSIFHWADDR: - case SIOCSKEEPALIVE: - case SIOCGKEEPALIVE: - case SIOCSOUTFILL: - case SIOCGOUTFILL: - return slip_ioctl(tty, file, cmd, - (unsigned long)compat_ptr(arg)); - } - - return -ENOIOCTLCMD; -} -#endif - /* VSV changes start here */ #ifdef CONFIG_SLIP_SMART /* function do_ioctl called from net/core/dev.c @@ -1280,9 +1258,6 @@ static struct tty_ldisc_ops sl_ldisc = { .close = slip_close, .hangup = slip_hangup, .ioctl = slip_ioctl, -#ifdef CONFIG_COMPAT - .compat_ioctl = slip_compat_ioctl, -#endif .receive_buf = slip_receive_buf, .write_wakeup = slip_write_wakeup, }; diff --git a/drivers/net/wan/x25_asy.c b/drivers/net/wan/x25_asy.c index 74c06a5f586f..1098263ab862 100644 --- a/drivers/net/wan/x25_asy.c +++ b/drivers/net/wan/x25_asy.c @@ -33,7 +33,6 @@ #include #include #include -#include #include #include #include "x25_asy.h" @@ -703,21 +702,6 @@ static int x25_asy_ioctl(struct tty_struct *tty, struct file *file, } } -#ifdef CONFIG_COMPAT -static long x25_asy_compat_ioctl(struct tty_struct *tty, struct file *file, - unsigned int cmd, unsigned long arg) -{ - switch (cmd) { - case SIOCGIFNAME: - case SIOCSIFHWADDR: - return x25_asy_ioctl(tty, file, cmd, - (unsigned long)compat_ptr(arg)); - } - - return -ENOIOCTLCMD; -} -#endif - static int x25_asy_open_dev(struct net_device *dev) { struct x25_asy *sl = netdev_priv(dev); @@ -769,9 +753,6 @@ static struct tty_ldisc_ops x25_ldisc = { .open = x25_asy_open_tty, .close = x25_asy_close_tty, .ioctl = x25_asy_ioctl, -#ifdef CONFIG_COMPAT - .compat_ioctl = x25_asy_compat_ioctl, -#endif .receive_buf = x25_asy_receive_buf, .write_wakeup = x25_asy_write_wakeup, }; diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index 86b7e20ffd7f..6f7da9a9d76f 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -2614,14 +2614,6 @@ static int gsmld_ioctl(struct tty_struct *tty, struct file *file, } } -#ifdef CONFIG_COMPAT -static long gsmld_compat_ioctl(struct tty_struct *tty, struct file *file, - unsigned int cmd, unsigned long arg) -{ - return gsmld_ioctl(tty, file, cmd, arg); -} -#endif - /* * Network interface * @@ -2833,9 +2825,6 @@ static struct tty_ldisc_ops tty_ldisc_packet = { .flush_buffer = gsmld_flush_buffer, .read = gsmld_read, .write = gsmld_write, -#ifdef CONFIG_COMPAT - .compat_ioctl = gsmld_compat_ioctl, -#endif .ioctl = gsmld_ioctl, .poll = gsmld_poll, .receive_buf = gsmld_receive_buf, diff --git a/drivers/tty/n_r3964.c b/drivers/tty/n_r3964.c index dbf1ab36758e..749a608c40b0 100644 --- a/drivers/tty/n_r3964.c +++ b/drivers/tty/n_r3964.c @@ -134,6 +134,10 @@ static ssize_t r3964_write(struct tty_struct *tty, struct file *file, const unsigned char *buf, size_t nr); static int r3964_ioctl(struct tty_struct *tty, struct file *file, unsigned int cmd, unsigned long arg); +#ifdef CONFIG_COMPAT +static int r3964_compat_ioctl(struct tty_struct *tty, struct file *file, + unsigned int cmd, unsigned long arg); +#endif static void r3964_set_termios(struct tty_struct *tty, struct ktermios *old); static __poll_t r3964_poll(struct tty_struct *tty, struct file *file, struct poll_table_struct *wait); @@ -149,6 +153,9 @@ static struct tty_ldisc_ops tty_ldisc_N_R3964 = { .read = r3964_read, .write = r3964_write, .ioctl = r3964_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = r3964_compat_ioctl, +#endif .set_termios = r3964_set_termios, .poll = r3964_poll, .receive_buf = r3964_receive_buf, @@ -1210,6 +1217,21 @@ static int r3964_ioctl(struct tty_struct *tty, struct file *file, } } +#ifdef CONFIG_COMPAT +static int r3964_compat_ioctl(struct tty_struct *tty, struct file *file, + unsigned int cmd, unsigned long arg) +{ + switch (cmd) { + case R3964_ENABLE_SIGNALS: + case R3964_SETPRIORITY: + case R3964_USE_BCC: + return r3964_ioctl(tty, file, cmd, arg); + default: + return -ENOIOCTLCMD; + } +} +#endif + static void r3964_set_termios(struct tty_struct *tty, struct ktermios *old) { TRACE_L("set_termios"); diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 1a55c3e20299..cd8df45f09d9 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -2824,6 +2824,9 @@ static long tty_compat_ioctl(struct file *file, unsigned int cmd, return hung_up_tty_compat_ioctl(file, cmd, arg); if (ld->ops->compat_ioctl) retval = ld->ops->compat_ioctl(tty, file, cmd, arg); + if (retval == -ENOIOCTLCMD && ld->ops->ioctl) + retval = ld->ops->ioctl(tty, file, + (unsigned long)compat_ptr(cmd), arg); tty_ldisc_deref(ld); return retval; diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h index 840894ca3fc0..b1e6043e9917 100644 --- a/include/linux/tty_ldisc.h +++ b/include/linux/tty_ldisc.h @@ -54,11 +54,17 @@ * low-level driver can "grab" an ioctl request before the line * discpline has a chance to see it. * - * long (*compat_ioctl)(struct tty_struct * tty, struct file * file, + * int (*compat_ioctl)(struct tty_struct * tty, struct file * file, * unsigned int cmd, unsigned long arg); * * Process ioctl calls from 32-bit process on 64-bit system * + * NOTE: only ioctls that are neither "pointer to compatible + * structure" nor tty-generic. Something private that takes + * an integer or a pointer to wordsize-sensitive structure + * belongs here, but most of ldiscs will happily leave + * it NULL. + * * void (*set_termios)(struct tty_struct *tty, struct ktermios * old); * * This function notifies the line discpline that a change has @@ -184,7 +190,7 @@ struct tty_ldisc_ops { const unsigned char *buf, size_t nr); int (*ioctl)(struct tty_struct *tty, struct file *file, unsigned int cmd, unsigned long arg); - long (*compat_ioctl)(struct tty_struct *tty, struct file *file, + int (*compat_ioctl)(struct tty_struct *tty, struct file *file, unsigned int cmd, unsigned long arg); void (*set_termios)(struct tty_struct *tty, struct ktermios *old); __poll_t (*poll)(struct tty_struct *, struct file *, diff --git a/net/nfc/nci/uart.c b/net/nfc/nci/uart.c index a66f102c6c01..d1fa0f22c10c 100644 --- a/net/nfc/nci/uart.c +++ b/net/nfc/nci/uart.c @@ -465,6 +465,7 @@ static struct tty_ldisc_ops nci_uart_ldisc = { .receive_buf = nci_uart_tty_receive, .write_wakeup = nci_uart_tty_wakeup, .ioctl = nci_uart_tty_ioctl, + .compat_ioctl = nci_uart_tty_ioctl, }; static int __init nci_uart_init(void) -- cgit v1.2.3 From cc53aabcc283c36274d3f3ce9adc4b40c21d4838 Mon Sep 17 00:00:00 2001 From: Govind Singh Date: Thu, 11 Oct 2018 13:16:01 +0300 Subject: firmware: qcom: scm: Add WLAN VMID for Qualcomm SCM interface Add WLAN related VMID's to support wlan driver to set up the remote's permissions call via TrustZone. Signed-off-by: Govind Singh Reviewed-by: Bjorn Andersson Acked-by: Niklas Cassel Reviewed-by: Brian Norris Signed-off-by: Kalle Valo --- include/linux/qcom_scm.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h index 5d65521260b3..06996ad4f2bc 100644 --- a/include/linux/qcom_scm.h +++ b/include/linux/qcom_scm.h @@ -1,4 +1,4 @@ -/* Copyright (c) 2010-2015, The Linux Foundation. All rights reserved. +/* Copyright (c) 2010-2015, 2018, The Linux Foundation. All rights reserved. * Copyright (C) 2015 Linaro Ltd. * * This program is free software; you can redistribute it and/or modify @@ -33,6 +33,8 @@ struct qcom_scm_vmperm { #define QCOM_SCM_VMID_HLOS 0x3 #define QCOM_SCM_VMID_MSS_MSA 0xF +#define QCOM_SCM_VMID_WLAN 0x18 +#define QCOM_SCM_VMID_WLAN_CE 0x19 #define QCOM_SCM_PERM_READ 0x4 #define QCOM_SCM_PERM_WRITE 0x2 #define QCOM_SCM_PERM_EXEC 0x1 -- cgit v1.2.3 From 604326b41a6fb9b4a78b6179335decee0365cd8c Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 13 Oct 2018 02:45:58 +0200 Subject: bpf, sockmap: convert to generic sk_msg interface Add a generic sk_msg layer, and convert current sockmap and later kTLS over to make use of it. While sk_buff handles network packet representation from netdevice up to socket, sk_msg handles data representation from application to socket layer. This means that sk_msg framework spans across ULP users in the kernel, and enables features such as introspection or filtering of data with the help of BPF programs that operate on this data structure. Latter becomes in particular useful for kTLS where data encryption is deferred into the kernel, and as such enabling the kernel to perform L7 introspection and policy based on BPF for TLS connections where the record is being encrypted after BPF has run and came to a verdict. In order to get there, first step is to transform open coding of scatter-gather list handling into a common core framework that subsystems can use. The code itself has been split and refactored into three bigger pieces: i) the generic sk_msg API which deals with managing the scatter gather ring, providing helpers for walking and mangling, transferring application data from user space into it, and preparing it for BPF pre/post-processing, ii) the plain sock map itself where sockets can be attached to or detached from; these bits are independent of i) which can now be used also without sock map, and iii) the integration with plain TCP as one protocol to be used for processing L7 application data (later this could e.g. also be extended to other protocols like UDP). The semantics are the same with the old sock map code and therefore no change of user facing behavior or APIs. While pursuing this work it also helped finding a number of bugs in the old sockmap code that we've fixed already in earlier commits. The test_sockmap kselftest suite passes through fine as well. Joint work with John. Signed-off-by: Daniel Borkmann Signed-off-by: John Fastabend Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 33 +- include/linux/bpf_types.h | 2 +- include/linux/filter.h | 21 - include/linux/skmsg.h | 371 +++++++ include/net/tcp.h | 27 + kernel/bpf/Makefile | 5 - kernel/bpf/core.c | 2 - kernel/bpf/sockmap.c | 2610 --------------------------------------------- kernel/bpf/syscall.c | 6 +- net/Kconfig | 11 + net/core/Makefile | 2 + net/core/filter.c | 270 ++--- net/core/skmsg.c | 763 +++++++++++++ net/core/sock_map.c | 1002 +++++++++++++++++ net/ipv4/Makefile | 1 + net/ipv4/tcp_bpf.c | 655 ++++++++++++ net/strparser/Kconfig | 4 +- 17 files changed, 2925 insertions(+), 2860 deletions(-) create mode 100644 include/linux/skmsg.h delete mode 100644 kernel/bpf/sockmap.c create mode 100644 net/core/skmsg.c create mode 100644 net/core/sock_map.c create mode 100644 net/ipv4/tcp_bpf.c (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 9b558713447f..e60fff48288b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -737,33 +737,18 @@ static inline void bpf_map_offload_map_free(struct bpf_map *map) } #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ -#if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_INET) -struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key); -struct sock *__sock_hash_lookup_elem(struct bpf_map *map, void *key); -int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type); -int sockmap_get_from_fd(const union bpf_attr *attr, int type, - struct bpf_prog *prog); +#if defined(CONFIG_BPF_STREAM_PARSER) +int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, u32 which); +int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog); #else -static inline struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key) -{ - return NULL; -} - -static inline struct sock *__sock_hash_lookup_elem(struct bpf_map *map, - void *key) -{ - return NULL; -} - -static inline int sock_map_prog(struct bpf_map *map, - struct bpf_prog *prog, - u32 type) +static inline int sock_map_prog_update(struct bpf_map *map, + struct bpf_prog *prog, u32 which) { return -EOPNOTSUPP; } -static inline int sockmap_get_from_fd(const union bpf_attr *attr, int type, - struct bpf_prog *prog) +static inline int sock_map_get_from_fd(const union bpf_attr *attr, + struct bpf_prog *prog) { return -EINVAL; } @@ -839,6 +824,10 @@ extern const struct bpf_func_proto bpf_get_stack_proto; extern const struct bpf_func_proto bpf_sock_map_update_proto; extern const struct bpf_func_proto bpf_sock_hash_update_proto; extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto; +extern const struct bpf_func_proto bpf_msg_redirect_hash_proto; +extern const struct bpf_func_proto bpf_msg_redirect_map_proto; +extern const struct bpf_func_proto bpf_sk_redirect_hash_proto; +extern const struct bpf_func_proto bpf_sk_redirect_map_proto; extern const struct bpf_func_proto bpf_get_local_storage_proto; diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 5432f4c9f50e..fa48343a5ea1 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -57,7 +57,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops) #ifdef CONFIG_NET BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops) -#if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_INET) +#if defined(CONFIG_BPF_STREAM_PARSER) BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKHASH, sock_hash_ops) #endif diff --git a/include/linux/filter.h b/include/linux/filter.h index 6791a0ac0139..5771874bc01e 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -520,24 +520,6 @@ struct bpf_skb_data_end { void *data_end; }; -struct sk_msg_buff { - void *data; - void *data_end; - __u32 apply_bytes; - __u32 cork_bytes; - int sg_copybreak; - int sg_start; - int sg_curr; - int sg_end; - struct scatterlist sg_data[MAX_SKB_FRAGS]; - bool sg_copy[MAX_SKB_FRAGS]; - __u32 flags; - struct sock *sk_redir; - struct sock *sk; - struct sk_buff *skb; - struct list_head list; -}; - struct bpf_redirect_info { u32 ifindex; u32 flags; @@ -833,9 +815,6 @@ void xdp_do_flush_map(void); void bpf_warn_invalid_xdp_action(u32 act); -struct sock *do_sk_redirect_map(struct sk_buff *skb); -struct sock *do_msg_redirect_map(struct sk_msg_buff *md); - #ifdef CONFIG_INET struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, struct bpf_prog *prog, struct sk_buff *skb, diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h new file mode 100644 index 000000000000..95678103c4a0 --- /dev/null +++ b/include/linux/skmsg.h @@ -0,0 +1,371 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2017 - 2018 Covalent IO, Inc. http://covalent.io */ + +#ifndef _LINUX_SKMSG_H +#define _LINUX_SKMSG_H + +#include +#include +#include +#include + +#include +#include +#include + +#define MAX_MSG_FRAGS MAX_SKB_FRAGS + +enum __sk_action { + __SK_DROP = 0, + __SK_PASS, + __SK_REDIRECT, + __SK_NONE, +}; + +struct sk_msg_sg { + u32 start; + u32 curr; + u32 end; + u32 size; + u32 copybreak; + bool copy[MAX_MSG_FRAGS]; + struct scatterlist data[MAX_MSG_FRAGS]; +}; + +struct sk_msg { + struct sk_msg_sg sg; + void *data; + void *data_end; + u32 apply_bytes; + u32 cork_bytes; + u32 flags; + struct sk_buff *skb; + struct sock *sk_redir; + struct sock *sk; + struct list_head list; +}; + +struct sk_psock_progs { + struct bpf_prog *msg_parser; + struct bpf_prog *skb_parser; + struct bpf_prog *skb_verdict; +}; + +enum sk_psock_state_bits { + SK_PSOCK_TX_ENABLED, +}; + +struct sk_psock_link { + struct list_head list; + struct bpf_map *map; + void *link_raw; +}; + +struct sk_psock_parser { + struct strparser strp; + bool enabled; + void (*saved_data_ready)(struct sock *sk); +}; + +struct sk_psock_work_state { + struct sk_buff *skb; + u32 len; + u32 off; +}; + +struct sk_psock { + struct sock *sk; + struct sock *sk_redir; + u32 apply_bytes; + u32 cork_bytes; + u32 eval; + struct sk_msg *cork; + struct sk_psock_progs progs; + struct sk_psock_parser parser; + struct sk_buff_head ingress_skb; + struct list_head ingress_msg; + unsigned long state; + struct list_head link; + spinlock_t link_lock; + refcount_t refcnt; + void (*saved_unhash)(struct sock *sk); + void (*saved_close)(struct sock *sk, long timeout); + void (*saved_write_space)(struct sock *sk); + struct proto *sk_proto; + struct sk_psock_work_state work_state; + struct work_struct work; + union { + struct rcu_head rcu; + struct work_struct gc; + }; +}; + +int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len, + int elem_first_coalesce); +void sk_msg_trim(struct sock *sk, struct sk_msg *msg, int len); +int sk_msg_free(struct sock *sk, struct sk_msg *msg); +int sk_msg_free_nocharge(struct sock *sk, struct sk_msg *msg); +void sk_msg_free_partial(struct sock *sk, struct sk_msg *msg, u32 bytes); +void sk_msg_free_partial_nocharge(struct sock *sk, struct sk_msg *msg, + u32 bytes); + +void sk_msg_return(struct sock *sk, struct sk_msg *msg, int bytes); + +int sk_msg_zerocopy_from_iter(struct sock *sk, struct iov_iter *from, + struct sk_msg *msg, u32 bytes); +int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from, + struct sk_msg *msg, u32 bytes); + +static inline void sk_msg_check_to_free(struct sk_msg *msg, u32 i, u32 bytes) +{ + WARN_ON(i == msg->sg.end && bytes); +} + +static inline void sk_msg_apply_bytes(struct sk_psock *psock, u32 bytes) +{ + if (psock->apply_bytes) { + if (psock->apply_bytes < bytes) + psock->apply_bytes = 0; + else + psock->apply_bytes -= bytes; + } +} + +#define sk_msg_iter_var_prev(var) \ + do { \ + if (var == 0) \ + var = MAX_MSG_FRAGS - 1; \ + else \ + var--; \ + } while (0) + +#define sk_msg_iter_var_next(var) \ + do { \ + var++; \ + if (var == MAX_MSG_FRAGS) \ + var = 0; \ + } while (0) + +#define sk_msg_iter_prev(msg, which) \ + sk_msg_iter_var_prev(msg->sg.which) + +#define sk_msg_iter_next(msg, which) \ + sk_msg_iter_var_next(msg->sg.which) + +static inline void sk_msg_clear_meta(struct sk_msg *msg) +{ + memset(&msg->sg, 0, offsetofend(struct sk_msg_sg, copy)); +} + +static inline void sk_msg_init(struct sk_msg *msg) +{ + memset(msg, 0, sizeof(*msg)); + sg_init_marker(msg->sg.data, ARRAY_SIZE(msg->sg.data)); +} + +static inline void sk_msg_xfer(struct sk_msg *dst, struct sk_msg *src, + int which, u32 size) +{ + dst->sg.data[which] = src->sg.data[which]; + dst->sg.data[which].length = size; + src->sg.data[which].length -= size; + src->sg.data[which].offset += size; +} + +static inline u32 sk_msg_elem_used(const struct sk_msg *msg) +{ + return msg->sg.end >= msg->sg.start ? + msg->sg.end - msg->sg.start : + msg->sg.end + (MAX_MSG_FRAGS - msg->sg.start); +} + +static inline bool sk_msg_full(const struct sk_msg *msg) +{ + return (msg->sg.end == msg->sg.start) && msg->sg.size; +} + +static inline struct scatterlist *sk_msg_elem(struct sk_msg *msg, int which) +{ + return &msg->sg.data[which]; +} + +static inline struct page *sk_msg_page(struct sk_msg *msg, int which) +{ + return sg_page(sk_msg_elem(msg, which)); +} + +static inline bool sk_msg_to_ingress(const struct sk_msg *msg) +{ + return msg->flags & BPF_F_INGRESS; +} + +static inline void sk_msg_compute_data_pointers(struct sk_msg *msg) +{ + struct scatterlist *sge = sk_msg_elem(msg, msg->sg.start); + + if (msg->sg.copy[msg->sg.start]) { + msg->data = NULL; + msg->data_end = NULL; + } else { + msg->data = sg_virt(sge); + msg->data_end = msg->data + sge->length; + } +} + +static inline void sk_msg_page_add(struct sk_msg *msg, struct page *page, + u32 len, u32 offset) +{ + struct scatterlist *sge; + + get_page(page); + sge = sk_msg_elem(msg, msg->sg.end); + sg_set_page(sge, page, len, offset); + sg_unmark_end(sge); + + msg->sg.copy[msg->sg.end] = true; + msg->sg.size += len; + sk_msg_iter_next(msg, end); +} + +static inline struct sk_psock *sk_psock(const struct sock *sk) +{ + return rcu_dereference_sk_user_data(sk); +} + +static inline bool sk_has_psock(struct sock *sk) +{ + return sk_psock(sk) != NULL && sk->sk_prot->recvmsg == tcp_bpf_recvmsg; +} + +static inline void sk_psock_queue_msg(struct sk_psock *psock, + struct sk_msg *msg) +{ + list_add_tail(&msg->list, &psock->ingress_msg); +} + +static inline void sk_psock_report_error(struct sk_psock *psock, int err) +{ + struct sock *sk = psock->sk; + + sk->sk_err = err; + sk->sk_error_report(sk); +} + +struct sk_psock *sk_psock_init(struct sock *sk, int node); + +int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock); +void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock); +void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock); + +int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock, + struct sk_msg *msg); + +static inline struct sk_psock_link *sk_psock_init_link(void) +{ + return kzalloc(sizeof(struct sk_psock_link), + GFP_ATOMIC | __GFP_NOWARN); +} + +static inline void sk_psock_free_link(struct sk_psock_link *link) +{ + kfree(link); +} + +struct sk_psock_link *sk_psock_link_pop(struct sk_psock *psock); +#if defined(CONFIG_BPF_STREAM_PARSER) +void sk_psock_unlink(struct sock *sk, struct sk_psock_link *link); +#else +static inline void sk_psock_unlink(struct sock *sk, + struct sk_psock_link *link) +{ +} +#endif + +void __sk_psock_purge_ingress_msg(struct sk_psock *psock); + +static inline void sk_psock_cork_free(struct sk_psock *psock) +{ + if (psock->cork) { + sk_msg_free(psock->sk, psock->cork); + kfree(psock->cork); + psock->cork = NULL; + } +} + +static inline void sk_psock_update_proto(struct sock *sk, + struct sk_psock *psock, + struct proto *ops) +{ + psock->saved_unhash = sk->sk_prot->unhash; + psock->saved_close = sk->sk_prot->close; + psock->saved_write_space = sk->sk_write_space; + + psock->sk_proto = sk->sk_prot; + sk->sk_prot = ops; +} + +static inline void sk_psock_restore_proto(struct sock *sk, + struct sk_psock *psock) +{ + if (psock->sk_proto) { + sk->sk_prot = psock->sk_proto; + psock->sk_proto = NULL; + } +} + +static inline void sk_psock_set_state(struct sk_psock *psock, + enum sk_psock_state_bits bit) +{ + set_bit(bit, &psock->state); +} + +static inline void sk_psock_clear_state(struct sk_psock *psock, + enum sk_psock_state_bits bit) +{ + clear_bit(bit, &psock->state); +} + +static inline bool sk_psock_test_state(const struct sk_psock *psock, + enum sk_psock_state_bits bit) +{ + return test_bit(bit, &psock->state); +} + +static inline struct sk_psock *sk_psock_get(struct sock *sk) +{ + struct sk_psock *psock; + + rcu_read_lock(); + psock = sk_psock(sk); + if (psock && !refcount_inc_not_zero(&psock->refcnt)) + psock = NULL; + rcu_read_unlock(); + return psock; +} + +void sk_psock_stop(struct sock *sk, struct sk_psock *psock); +void sk_psock_destroy(struct rcu_head *rcu); +void sk_psock_drop(struct sock *sk, struct sk_psock *psock); + +static inline void sk_psock_put(struct sock *sk, struct sk_psock *psock) +{ + if (refcount_dec_and_test(&psock->refcnt)) + sk_psock_drop(sk, psock); +} + +static inline void psock_set_prog(struct bpf_prog **pprog, + struct bpf_prog *prog) +{ + prog = xchg(pprog, prog); + if (prog) + bpf_prog_put(prog); +} + +static inline void psock_progs_drop(struct sk_psock_progs *progs) +{ + psock_set_prog(&progs->msg_parser, NULL); + psock_set_prog(&progs->skb_parser, NULL); + psock_set_prog(&progs->skb_verdict, NULL); +} + +#endif /* _LINUX_SKMSG_H */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 8f5cef67fd35..3600ae0f25c3 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -858,6 +858,21 @@ static inline void bpf_compute_data_end_sk_skb(struct sk_buff *skb) TCP_SKB_CB(skb)->bpf.data_end = skb->data + skb_headlen(skb); } +static inline bool tcp_skb_bpf_ingress(const struct sk_buff *skb) +{ + return TCP_SKB_CB(skb)->bpf.flags & BPF_F_INGRESS; +} + +static inline struct sock *tcp_skb_bpf_redirect_fetch(struct sk_buff *skb) +{ + return TCP_SKB_CB(skb)->bpf.sk_redir; +} + +static inline void tcp_skb_bpf_redirect_clear(struct sk_buff *skb) +{ + TCP_SKB_CB(skb)->bpf.sk_redir = NULL; +} + #if IS_ENABLED(CONFIG_IPV6) /* This is the variant of inet6_iif() that must be used by TCP, * as TCP moves IP6CB into a different location in skb->cb[] @@ -2064,6 +2079,18 @@ void tcp_cleanup_ulp(struct sock *sk); __MODULE_INFO(alias, alias_userspace, name); \ __MODULE_INFO(alias, alias_tcp_ulp, "tcp-ulp-" name) +struct sk_msg; +struct sk_psock; + +int tcp_bpf_init(struct sock *sk); +void tcp_bpf_reinit(struct sock *sk); +int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg, u32 bytes, + int flags); +int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, + int nonblock, int flags, int *addr_len); +int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, + struct msghdr *msg, int len); + /* Call BPF_SOCK_OPS program that returns an int. If the return value * is < 0, then the BPF op failed (for example if the loaded BPF * program does not support the chosen operation or there is no BPF diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 0488b8258321..ff8262626b8f 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -13,11 +13,6 @@ ifeq ($(CONFIG_XDP_SOCKETS),y) obj-$(CONFIG_BPF_SYSCALL) += xskmap.o endif obj-$(CONFIG_BPF_SYSCALL) += offload.o -ifeq ($(CONFIG_STREAM_PARSER),y) -ifeq ($(CONFIG_INET),y) -obj-$(CONFIG_BPF_SYSCALL) += sockmap.o -endif -endif endif ifeq ($(CONFIG_PERF_EVENTS),y) obj-$(CONFIG_BPF_SYSCALL) += stackmap.o diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 3f5bf1af0826..defcf4df6d91 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1792,8 +1792,6 @@ const struct bpf_func_proto bpf_ktime_get_ns_proto __weak; const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak; const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak; const struct bpf_func_proto bpf_get_current_comm_proto __weak; -const struct bpf_func_proto bpf_sock_map_update_proto __weak; -const struct bpf_func_proto bpf_sock_hash_update_proto __weak; const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak; const struct bpf_func_proto bpf_get_local_storage_proto __weak; diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c deleted file mode 100644 index de6f7a65c72b..000000000000 --- a/kernel/bpf/sockmap.c +++ /dev/null @@ -1,2610 +0,0 @@ -/* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of version 2 of the GNU General Public - * License as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - */ - -/* A BPF sock_map is used to store sock objects. This is primarly used - * for doing socket redirect with BPF helper routines. - * - * A sock map may have BPF programs attached to it, currently a program - * used to parse packets and a program to provide a verdict and redirect - * decision on the packet are supported. Any programs attached to a sock - * map are inherited by sock objects when they are added to the map. If - * no BPF programs are attached the sock object may only be used for sock - * redirect. - * - * A sock object may be in multiple maps, but can only inherit a single - * parse or verdict program. If adding a sock object to a map would result - * in having multiple parsing programs the update will return an EBUSY error. - * - * For reference this program is similar to devmap used in XDP context - * reviewing these together may be useful. For an example please review - * ./samples/bpf/sockmap/. - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#define SOCK_CREATE_FLAG_MASK \ - (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) - -struct bpf_sock_progs { - struct bpf_prog *bpf_tx_msg; - struct bpf_prog *bpf_parse; - struct bpf_prog *bpf_verdict; -}; - -struct bpf_stab { - struct bpf_map map; - struct sock **sock_map; - struct bpf_sock_progs progs; - raw_spinlock_t lock; -}; - -struct bucket { - struct hlist_head head; - raw_spinlock_t lock; -}; - -struct bpf_htab { - struct bpf_map map; - struct bucket *buckets; - atomic_t count; - u32 n_buckets; - u32 elem_size; - struct bpf_sock_progs progs; - struct rcu_head rcu; -}; - -struct htab_elem { - struct rcu_head rcu; - struct hlist_node hash_node; - u32 hash; - struct sock *sk; - char key[0]; -}; - -enum smap_psock_state { - SMAP_TX_RUNNING, -}; - -struct smap_psock_map_entry { - struct list_head list; - struct bpf_map *map; - struct sock **entry; - struct htab_elem __rcu *hash_link; -}; - -struct smap_psock { - struct rcu_head rcu; - refcount_t refcnt; - - /* datapath variables */ - struct sk_buff_head rxqueue; - bool strp_enabled; - - /* datapath error path cache across tx work invocations */ - int save_rem; - int save_off; - struct sk_buff *save_skb; - - /* datapath variables for tx_msg ULP */ - struct sock *sk_redir; - int apply_bytes; - int cork_bytes; - int sg_size; - int eval; - struct sk_msg_buff *cork; - struct list_head ingress; - - struct strparser strp; - struct bpf_prog *bpf_tx_msg; - struct bpf_prog *bpf_parse; - struct bpf_prog *bpf_verdict; - struct list_head maps; - spinlock_t maps_lock; - - /* Back reference used when sock callback trigger sockmap operations */ - struct sock *sock; - unsigned long state; - - struct work_struct tx_work; - struct work_struct gc_work; - - struct proto *sk_proto; - void (*save_unhash)(struct sock *sk); - void (*save_close)(struct sock *sk, long timeout); - void (*save_data_ready)(struct sock *sk); - void (*save_write_space)(struct sock *sk); -}; - -static void smap_release_sock(struct smap_psock *psock, struct sock *sock); -static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, - int nonblock, int flags, int *addr_len); -static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); -static int bpf_tcp_sendpage(struct sock *sk, struct page *page, - int offset, size_t size, int flags); -static void bpf_tcp_unhash(struct sock *sk); -static void bpf_tcp_close(struct sock *sk, long timeout); - -static inline struct smap_psock *smap_psock_sk(const struct sock *sk) -{ - return rcu_dereference_sk_user_data(sk); -} - -static bool bpf_tcp_stream_read(const struct sock *sk) -{ - struct smap_psock *psock; - bool empty = true; - - rcu_read_lock(); - psock = smap_psock_sk(sk); - if (unlikely(!psock)) - goto out; - empty = list_empty(&psock->ingress); -out: - rcu_read_unlock(); - return !empty; -} - -enum { - SOCKMAP_IPV4, - SOCKMAP_IPV6, - SOCKMAP_NUM_PROTS, -}; - -enum { - SOCKMAP_BASE, - SOCKMAP_TX, - SOCKMAP_NUM_CONFIGS, -}; - -static struct proto *saved_tcpv6_prot __read_mostly; -static DEFINE_SPINLOCK(tcpv6_prot_lock); -static struct proto bpf_tcp_prots[SOCKMAP_NUM_PROTS][SOCKMAP_NUM_CONFIGS]; - -static void build_protos(struct proto prot[SOCKMAP_NUM_CONFIGS], - struct proto *base) -{ - prot[SOCKMAP_BASE] = *base; - prot[SOCKMAP_BASE].unhash = bpf_tcp_unhash; - prot[SOCKMAP_BASE].close = bpf_tcp_close; - prot[SOCKMAP_BASE].recvmsg = bpf_tcp_recvmsg; - prot[SOCKMAP_BASE].stream_memory_read = bpf_tcp_stream_read; - - prot[SOCKMAP_TX] = prot[SOCKMAP_BASE]; - prot[SOCKMAP_TX].sendmsg = bpf_tcp_sendmsg; - prot[SOCKMAP_TX].sendpage = bpf_tcp_sendpage; -} - -static void update_sk_prot(struct sock *sk, struct smap_psock *psock) -{ - int family = sk->sk_family == AF_INET6 ? SOCKMAP_IPV6 : SOCKMAP_IPV4; - int conf = psock->bpf_tx_msg ? SOCKMAP_TX : SOCKMAP_BASE; - - sk->sk_prot = &bpf_tcp_prots[family][conf]; -} - -static int bpf_tcp_init(struct sock *sk) -{ - struct smap_psock *psock; - - rcu_read_lock(); - psock = smap_psock_sk(sk); - if (unlikely(!psock)) { - rcu_read_unlock(); - return -EINVAL; - } - - if (unlikely(psock->sk_proto)) { - rcu_read_unlock(); - return -EBUSY; - } - - psock->save_unhash = sk->sk_prot->unhash; - psock->save_close = sk->sk_prot->close; - psock->sk_proto = sk->sk_prot; - - /* Build IPv6 sockmap whenever the address of tcpv6_prot changes */ - if (sk->sk_family == AF_INET6 && - unlikely(sk->sk_prot != smp_load_acquire(&saved_tcpv6_prot))) { - spin_lock_bh(&tcpv6_prot_lock); - if (likely(sk->sk_prot != saved_tcpv6_prot)) { - build_protos(bpf_tcp_prots[SOCKMAP_IPV6], sk->sk_prot); - smp_store_release(&saved_tcpv6_prot, sk->sk_prot); - } - spin_unlock_bh(&tcpv6_prot_lock); - } - update_sk_prot(sk, psock); - rcu_read_unlock(); - return 0; -} - -static int __init bpf_sock_init(void) -{ - build_protos(bpf_tcp_prots[SOCKMAP_IPV4], &tcp_prot); - return 0; -} -core_initcall(bpf_sock_init); - -static void smap_release_sock(struct smap_psock *psock, struct sock *sock); -static int free_start_sg(struct sock *sk, struct sk_msg_buff *md, bool charge); - -static void bpf_tcp_release(struct sock *sk) -{ - struct smap_psock *psock; - - rcu_read_lock(); - psock = smap_psock_sk(sk); - if (unlikely(!psock)) - goto out; - - if (psock->cork) { - free_start_sg(psock->sock, psock->cork, true); - kfree(psock->cork); - psock->cork = NULL; - } - - if (psock->sk_proto) { - sk->sk_prot = psock->sk_proto; - psock->sk_proto = NULL; - } -out: - rcu_read_unlock(); -} - -static struct htab_elem *lookup_elem_raw(struct hlist_head *head, - u32 hash, void *key, u32 key_size) -{ - struct htab_elem *l; - - hlist_for_each_entry_rcu(l, head, hash_node) { - if (l->hash == hash && !memcmp(&l->key, key, key_size)) - return l; - } - - return NULL; -} - -static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash) -{ - return &htab->buckets[hash & (htab->n_buckets - 1)]; -} - -static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash) -{ - return &__select_bucket(htab, hash)->head; -} - -static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) -{ - atomic_dec(&htab->count); - kfree_rcu(l, rcu); -} - -static struct smap_psock_map_entry *psock_map_pop(struct sock *sk, - struct smap_psock *psock) -{ - struct smap_psock_map_entry *e; - - spin_lock_bh(&psock->maps_lock); - e = list_first_entry_or_null(&psock->maps, - struct smap_psock_map_entry, - list); - if (e) - list_del(&e->list); - spin_unlock_bh(&psock->maps_lock); - return e; -} - -static void bpf_tcp_remove(struct sock *sk, struct smap_psock *psock) -{ - struct smap_psock_map_entry *e; - struct sk_msg_buff *md, *mtmp; - struct sock *osk; - - if (psock->cork) { - free_start_sg(psock->sock, psock->cork, true); - kfree(psock->cork); - psock->cork = NULL; - } - - list_for_each_entry_safe(md, mtmp, &psock->ingress, list) { - list_del(&md->list); - free_start_sg(psock->sock, md, true); - kfree(md); - } - - e = psock_map_pop(sk, psock); - while (e) { - if (e->entry) { - struct bpf_stab *stab = container_of(e->map, struct bpf_stab, map); - - raw_spin_lock_bh(&stab->lock); - osk = *e->entry; - if (osk == sk) { - *e->entry = NULL; - smap_release_sock(psock, sk); - } - raw_spin_unlock_bh(&stab->lock); - } else { - struct htab_elem *link = rcu_dereference(e->hash_link); - struct bpf_htab *htab = container_of(e->map, struct bpf_htab, map); - struct hlist_head *head; - struct htab_elem *l; - struct bucket *b; - - b = __select_bucket(htab, link->hash); - head = &b->head; - raw_spin_lock_bh(&b->lock); - l = lookup_elem_raw(head, - link->hash, link->key, - htab->map.key_size); - /* If another thread deleted this object skip deletion. - * The refcnt on psock may or may not be zero. - */ - if (l && l == link) { - hlist_del_rcu(&link->hash_node); - smap_release_sock(psock, link->sk); - free_htab_elem(htab, link); - } - raw_spin_unlock_bh(&b->lock); - } - kfree(e); - e = psock_map_pop(sk, psock); - } -} - -static void bpf_tcp_unhash(struct sock *sk) -{ - void (*unhash_fun)(struct sock *sk); - struct smap_psock *psock; - - rcu_read_lock(); - psock = smap_psock_sk(sk); - if (unlikely(!psock)) { - rcu_read_unlock(); - if (sk->sk_prot->unhash) - sk->sk_prot->unhash(sk); - return; - } - unhash_fun = psock->save_unhash; - bpf_tcp_remove(sk, psock); - rcu_read_unlock(); - unhash_fun(sk); -} - -static void bpf_tcp_close(struct sock *sk, long timeout) -{ - void (*close_fun)(struct sock *sk, long timeout); - struct smap_psock *psock; - - lock_sock(sk); - rcu_read_lock(); - psock = smap_psock_sk(sk); - if (unlikely(!psock)) { - rcu_read_unlock(); - release_sock(sk); - return sk->sk_prot->close(sk, timeout); - } - close_fun = psock->save_close; - bpf_tcp_remove(sk, psock); - rcu_read_unlock(); - release_sock(sk); - close_fun(sk, timeout); -} - -enum __sk_action { - __SK_DROP = 0, - __SK_PASS, - __SK_REDIRECT, - __SK_NONE, -}; - -static int memcopy_from_iter(struct sock *sk, - struct sk_msg_buff *md, - struct iov_iter *from, int bytes) -{ - struct scatterlist *sg = md->sg_data; - int i = md->sg_curr, rc = -ENOSPC; - - do { - int copy; - char *to; - - if (md->sg_copybreak >= sg[i].length) { - md->sg_copybreak = 0; - - if (++i == MAX_SKB_FRAGS) - i = 0; - - if (i == md->sg_end) - break; - } - - copy = sg[i].length - md->sg_copybreak; - to = sg_virt(&sg[i]) + md->sg_copybreak; - md->sg_copybreak += copy; - - if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY) - rc = copy_from_iter_nocache(to, copy, from); - else - rc = copy_from_iter(to, copy, from); - - if (rc != copy) { - rc = -EFAULT; - goto out; - } - - bytes -= copy; - if (!bytes) - break; - - md->sg_copybreak = 0; - if (++i == MAX_SKB_FRAGS) - i = 0; - } while (i != md->sg_end); -out: - md->sg_curr = i; - return rc; -} - -static int bpf_tcp_push(struct sock *sk, int apply_bytes, - struct sk_msg_buff *md, - int flags, bool uncharge) -{ - bool apply = apply_bytes; - struct scatterlist *sg; - int offset, ret = 0; - struct page *p; - size_t size; - - while (1) { - sg = md->sg_data + md->sg_start; - size = (apply && apply_bytes < sg->length) ? - apply_bytes : sg->length; - offset = sg->offset; - - tcp_rate_check_app_limited(sk); - p = sg_page(sg); -retry: - ret = do_tcp_sendpages(sk, p, offset, size, flags); - if (ret != size) { - if (ret > 0) { - if (apply) - apply_bytes -= ret; - - sg->offset += ret; - sg->length -= ret; - size -= ret; - offset += ret; - if (uncharge) - sk_mem_uncharge(sk, ret); - goto retry; - } - - return ret; - } - - if (apply) - apply_bytes -= ret; - sg->offset += ret; - sg->length -= ret; - if (uncharge) - sk_mem_uncharge(sk, ret); - - if (!sg->length) { - put_page(p); - md->sg_start++; - if (md->sg_start == MAX_SKB_FRAGS) - md->sg_start = 0; - sg_init_table(sg, 1); - - if (md->sg_start == md->sg_end) - break; - } - - if (apply && !apply_bytes) - break; - } - return 0; -} - -static inline void bpf_compute_data_pointers_sg(struct sk_msg_buff *md) -{ - struct scatterlist *sg = md->sg_data + md->sg_start; - - if (md->sg_copy[md->sg_start]) { - md->data = md->data_end = 0; - } else { - md->data = sg_virt(sg); - md->data_end = md->data + sg->length; - } -} - -static void return_mem_sg(struct sock *sk, int bytes, struct sk_msg_buff *md) -{ - struct scatterlist *sg = md->sg_data; - int i = md->sg_start; - - do { - int uncharge = (bytes < sg[i].length) ? bytes : sg[i].length; - - sk_mem_uncharge(sk, uncharge); - bytes -= uncharge; - if (!bytes) - break; - i++; - if (i == MAX_SKB_FRAGS) - i = 0; - } while (i != md->sg_end); -} - -static void free_bytes_sg(struct sock *sk, int bytes, - struct sk_msg_buff *md, bool charge) -{ - struct scatterlist *sg = md->sg_data; - int i = md->sg_start, free; - - while (bytes && sg[i].length) { - free = sg[i].length; - if (bytes < free) { - sg[i].length -= bytes; - sg[i].offset += bytes; - if (charge) - sk_mem_uncharge(sk, bytes); - break; - } - - if (charge) - sk_mem_uncharge(sk, sg[i].length); - put_page(sg_page(&sg[i])); - bytes -= sg[i].length; - sg[i].length = 0; - sg[i].page_link = 0; - sg[i].offset = 0; - i++; - - if (i == MAX_SKB_FRAGS) - i = 0; - } - md->sg_start = i; -} - -static int free_sg(struct sock *sk, int start, - struct sk_msg_buff *md, bool charge) -{ - struct scatterlist *sg = md->sg_data; - int i = start, free = 0; - - while (sg[i].length) { - free += sg[i].length; - if (charge) - sk_mem_uncharge(sk, sg[i].length); - if (!md->skb) - put_page(sg_page(&sg[i])); - sg[i].length = 0; - sg[i].page_link = 0; - sg[i].offset = 0; - i++; - - if (i == MAX_SKB_FRAGS) - i = 0; - } - consume_skb(md->skb); - - return free; -} - -static int free_start_sg(struct sock *sk, struct sk_msg_buff *md, bool charge) -{ - int free = free_sg(sk, md->sg_start, md, charge); - - md->sg_start = md->sg_end; - return free; -} - -static int free_curr_sg(struct sock *sk, struct sk_msg_buff *md) -{ - return free_sg(sk, md->sg_curr, md, true); -} - -static int bpf_map_msg_verdict(int _rc, struct sk_msg_buff *md) -{ - return ((_rc == SK_PASS) ? - (md->sk_redir ? __SK_REDIRECT : __SK_PASS) : - __SK_DROP); -} - -static unsigned int smap_do_tx_msg(struct sock *sk, - struct smap_psock *psock, - struct sk_msg_buff *md) -{ - struct bpf_prog *prog; - unsigned int rc, _rc; - - preempt_disable(); - rcu_read_lock(); - - /* If the policy was removed mid-send then default to 'accept' */ - prog = READ_ONCE(psock->bpf_tx_msg); - if (unlikely(!prog)) { - _rc = SK_PASS; - goto verdict; - } - - bpf_compute_data_pointers_sg(md); - md->sk = sk; - rc = (*prog->bpf_func)(md, prog->insnsi); - psock->apply_bytes = md->apply_bytes; - - /* Moving return codes from UAPI namespace into internal namespace */ - _rc = bpf_map_msg_verdict(rc, md); - - /* The psock has a refcount on the sock but not on the map and because - * we need to drop rcu read lock here its possible the map could be - * removed between here and when we need it to execute the sock - * redirect. So do the map lookup now for future use. - */ - if (_rc == __SK_REDIRECT) { - if (psock->sk_redir) - sock_put(psock->sk_redir); - psock->sk_redir = do_msg_redirect_map(md); - if (!psock->sk_redir) { - _rc = __SK_DROP; - goto verdict; - } - sock_hold(psock->sk_redir); - } -verdict: - rcu_read_unlock(); - preempt_enable(); - - return _rc; -} - -static int bpf_tcp_ingress(struct sock *sk, int apply_bytes, - struct smap_psock *psock, - struct sk_msg_buff *md, int flags) -{ - bool apply = apply_bytes; - size_t size, copied = 0; - struct sk_msg_buff *r; - int err = 0, i; - - r = kzalloc(sizeof(struct sk_msg_buff), __GFP_NOWARN | GFP_KERNEL); - if (unlikely(!r)) - return -ENOMEM; - - lock_sock(sk); - r->sg_start = md->sg_start; - i = md->sg_start; - - do { - size = (apply && apply_bytes < md->sg_data[i].length) ? - apply_bytes : md->sg_data[i].length; - - if (!sk_wmem_schedule(sk, size)) { - if (!copied) - err = -ENOMEM; - break; - } - - sk_mem_charge(sk, size); - r->sg_data[i] = md->sg_data[i]; - r->sg_data[i].length = size; - md->sg_data[i].length -= size; - md->sg_data[i].offset += size; - copied += size; - - if (md->sg_data[i].length) { - get_page(sg_page(&r->sg_data[i])); - r->sg_end = (i + 1) == MAX_SKB_FRAGS ? 0 : i + 1; - } else { - i++; - if (i == MAX_SKB_FRAGS) - i = 0; - r->sg_end = i; - } - - if (apply) { - apply_bytes -= size; - if (!apply_bytes) - break; - } - } while (i != md->sg_end); - - md->sg_start = i; - - if (!err) { - list_add_tail(&r->list, &psock->ingress); - sk->sk_data_ready(sk); - } else { - free_start_sg(sk, r, true); - kfree(r); - } - - release_sock(sk); - return err; -} - -static int bpf_tcp_sendmsg_do_redirect(struct sock *sk, int send, - struct sk_msg_buff *md, - int flags) -{ - bool ingress = !!(md->flags & BPF_F_INGRESS); - struct smap_psock *psock; - int err = 0; - - rcu_read_lock(); - psock = smap_psock_sk(sk); - if (unlikely(!psock)) - goto out_rcu; - - if (!refcount_inc_not_zero(&psock->refcnt)) - goto out_rcu; - - rcu_read_unlock(); - - if (ingress) { - err = bpf_tcp_ingress(sk, send, psock, md, flags); - } else { - lock_sock(sk); - err = bpf_tcp_push(sk, send, md, flags, false); - release_sock(sk); - } - smap_release_sock(psock, sk); - return err; -out_rcu: - rcu_read_unlock(); - return 0; -} - -static inline void bpf_md_init(struct smap_psock *psock) -{ - if (!psock->apply_bytes) { - psock->eval = __SK_NONE; - if (psock->sk_redir) { - sock_put(psock->sk_redir); - psock->sk_redir = NULL; - } - } -} - -static void apply_bytes_dec(struct smap_psock *psock, int i) -{ - if (psock->apply_bytes) { - if (psock->apply_bytes < i) - psock->apply_bytes = 0; - else - psock->apply_bytes -= i; - } -} - -static int bpf_exec_tx_verdict(struct smap_psock *psock, - struct sk_msg_buff *m, - struct sock *sk, - int *copied, int flags) -{ - bool cork = false, enospc = (m->sg_start == m->sg_end); - struct sock *redir; - int err = 0; - int send; - -more_data: - if (psock->eval == __SK_NONE) - psock->eval = smap_do_tx_msg(sk, psock, m); - - if (m->cork_bytes && - m->cork_bytes > psock->sg_size && !enospc) { - psock->cork_bytes = m->cork_bytes - psock->sg_size; - if (!psock->cork) { - psock->cork = kcalloc(1, - sizeof(struct sk_msg_buff), - GFP_ATOMIC | __GFP_NOWARN); - - if (!psock->cork) { - err = -ENOMEM; - goto out_err; - } - } - memcpy(psock->cork, m, sizeof(*m)); - goto out_err; - } - - send = psock->sg_size; - if (psock->apply_bytes && psock->apply_bytes < send) - send = psock->apply_bytes; - - switch (psock->eval) { - case __SK_PASS: - err = bpf_tcp_push(sk, send, m, flags, true); - if (unlikely(err)) { - *copied -= free_start_sg(sk, m, true); - break; - } - - apply_bytes_dec(psock, send); - psock->sg_size -= send; - break; - case __SK_REDIRECT: - redir = psock->sk_redir; - apply_bytes_dec(psock, send); - - if (psock->cork) { - cork = true; - psock->cork = NULL; - } - - return_mem_sg(sk, send, m); - release_sock(sk); - - err = bpf_tcp_sendmsg_do_redirect(redir, send, m, flags); - lock_sock(sk); - - if (unlikely(err < 0)) { - int free = free_start_sg(sk, m, false); - - psock->sg_size = 0; - if (!cork) - *copied -= free; - } else { - psock->sg_size -= send; - } - - if (cork) { - free_start_sg(sk, m, true); - psock->sg_size = 0; - kfree(m); - m = NULL; - err = 0; - } - break; - case __SK_DROP: - default: - free_bytes_sg(sk, send, m, true); - apply_bytes_dec(psock, send); - *copied -= send; - psock->sg_size -= send; - err = -EACCES; - break; - } - - if (likely(!err)) { - bpf_md_init(psock); - if (m && - m->sg_data[m->sg_start].page_link && - m->sg_data[m->sg_start].length) - goto more_data; - } - -out_err: - return err; -} - -static int bpf_wait_data(struct sock *sk, - struct smap_psock *psk, int flags, - long timeo, int *err) -{ - int rc; - - DEFINE_WAIT_FUNC(wait, woken_wake_function); - - add_wait_queue(sk_sleep(sk), &wait); - sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); - rc = sk_wait_event(sk, &timeo, - !list_empty(&psk->ingress) || - !skb_queue_empty(&sk->sk_receive_queue), - &wait); - sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); - remove_wait_queue(sk_sleep(sk), &wait); - - return rc; -} - -static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, - int nonblock, int flags, int *addr_len) -{ - struct iov_iter *iter = &msg->msg_iter; - struct smap_psock *psock; - int copied = 0; - - if (unlikely(flags & MSG_ERRQUEUE)) - return inet_recv_error(sk, msg, len, addr_len); - if (!skb_queue_empty(&sk->sk_receive_queue)) - return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); - - rcu_read_lock(); - psock = smap_psock_sk(sk); - if (unlikely(!psock)) - goto out; - - if (unlikely(!refcount_inc_not_zero(&psock->refcnt))) - goto out; - rcu_read_unlock(); - - lock_sock(sk); -bytes_ready: - while (copied != len) { - struct scatterlist *sg; - struct sk_msg_buff *md; - int i; - - md = list_first_entry_or_null(&psock->ingress, - struct sk_msg_buff, list); - if (unlikely(!md)) - break; - i = md->sg_start; - do { - struct page *page; - int n, copy; - - sg = &md->sg_data[i]; - copy = sg->length; - page = sg_page(sg); - - if (copied + copy > len) - copy = len - copied; - - n = copy_page_to_iter(page, sg->offset, copy, iter); - if (n != copy) { - md->sg_start = i; - release_sock(sk); - smap_release_sock(psock, sk); - return -EFAULT; - } - - copied += copy; - sg->offset += copy; - sg->length -= copy; - sk_mem_uncharge(sk, copy); - - if (!sg->length) { - i++; - if (i == MAX_SKB_FRAGS) - i = 0; - if (!md->skb) - put_page(page); - } - if (copied == len) - break; - } while (i != md->sg_end); - md->sg_start = i; - - if (!sg->length && md->sg_start == md->sg_end) { - list_del(&md->list); - consume_skb(md->skb); - kfree(md); - } - } - - if (!copied) { - long timeo; - int data; - int err = 0; - - timeo = sock_rcvtimeo(sk, nonblock); - data = bpf_wait_data(sk, psock, flags, timeo, &err); - - if (data) { - if (!skb_queue_empty(&sk->sk_receive_queue)) { - release_sock(sk); - smap_release_sock(psock, sk); - copied = tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); - return copied; - } - goto bytes_ready; - } - - if (err) - copied = err; - } - - release_sock(sk); - smap_release_sock(psock, sk); - return copied; -out: - rcu_read_unlock(); - return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); -} - - -static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) -{ - int flags = msg->msg_flags | MSG_NO_SHARED_FRAGS; - struct sk_msg_buff md = {0}; - unsigned int sg_copy = 0; - struct smap_psock *psock; - int copied = 0, err = 0; - struct scatterlist *sg; - long timeo; - - /* Its possible a sock event or user removed the psock _but_ the ops - * have not been reprogrammed yet so we get here. In this case fallback - * to tcp_sendmsg. Note this only works because we _only_ ever allow - * a single ULP there is no hierarchy here. - */ - rcu_read_lock(); - psock = smap_psock_sk(sk); - if (unlikely(!psock)) { - rcu_read_unlock(); - return tcp_sendmsg(sk, msg, size); - } - - /* Increment the psock refcnt to ensure its not released while sending a - * message. Required because sk lookup and bpf programs are used in - * separate rcu critical sections. Its OK if we lose the map entry - * but we can't lose the sock reference. - */ - if (!refcount_inc_not_zero(&psock->refcnt)) { - rcu_read_unlock(); - return tcp_sendmsg(sk, msg, size); - } - - sg = md.sg_data; - sg_init_marker(sg, MAX_SKB_FRAGS); - rcu_read_unlock(); - - lock_sock(sk); - timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); - - while (msg_data_left(msg)) { - struct sk_msg_buff *m = NULL; - bool enospc = false; - int copy; - - if (sk->sk_err) { - err = -sk->sk_err; - goto out_err; - } - - copy = msg_data_left(msg); - if (!sk_stream_memory_free(sk)) - goto wait_for_sndbuf; - - m = psock->cork_bytes ? psock->cork : &md; - m->sg_curr = m->sg_copybreak ? m->sg_curr : m->sg_end; - err = sk_alloc_sg(sk, copy, m->sg_data, - m->sg_start, &m->sg_end, &sg_copy, - m->sg_end - 1); - if (err) { - if (err != -ENOSPC) - goto wait_for_memory; - enospc = true; - copy = sg_copy; - } - - err = memcopy_from_iter(sk, m, &msg->msg_iter, copy); - if (err < 0) { - free_curr_sg(sk, m); - goto out_err; - } - - psock->sg_size += copy; - copied += copy; - sg_copy = 0; - - /* When bytes are being corked skip running BPF program and - * applying verdict unless there is no more buffer space. In - * the ENOSPC case simply run BPF prorgram with currently - * accumulated data. We don't have much choice at this point - * we could try extending the page frags or chaining complex - * frags but even in these cases _eventually_ we will hit an - * OOM scenario. More complex recovery schemes may be - * implemented in the future, but BPF programs must handle - * the case where apply_cork requests are not honored. The - * canonical method to verify this is to check data length. - */ - if (psock->cork_bytes) { - if (copy > psock->cork_bytes) - psock->cork_bytes = 0; - else - psock->cork_bytes -= copy; - - if (psock->cork_bytes && !enospc) - goto out_cork; - - /* All cork bytes accounted for re-run filter */ - psock->eval = __SK_NONE; - psock->cork_bytes = 0; - } - - err = bpf_exec_tx_verdict(psock, m, sk, &copied, flags); - if (unlikely(err < 0)) - goto out_err; - continue; -wait_for_sndbuf: - set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); -wait_for_memory: - err = sk_stream_wait_memory(sk, &timeo); - if (err) { - if (m && m != psock->cork) - free_start_sg(sk, m, true); - goto out_err; - } - } -out_err: - if (err < 0) - err = sk_stream_error(sk, msg->msg_flags, err); -out_cork: - release_sock(sk); - smap_release_sock(psock, sk); - return copied ? copied : err; -} - -static int bpf_tcp_sendpage(struct sock *sk, struct page *page, - int offset, size_t size, int flags) -{ - struct sk_msg_buff md = {0}, *m = NULL; - int err = 0, copied = 0; - struct smap_psock *psock; - struct scatterlist *sg; - bool enospc = false; - - rcu_read_lock(); - psock = smap_psock_sk(sk); - if (unlikely(!psock)) - goto accept; - - if (!refcount_inc_not_zero(&psock->refcnt)) - goto accept; - rcu_read_unlock(); - - lock_sock(sk); - - if (psock->cork_bytes) { - m = psock->cork; - sg = &m->sg_data[m->sg_end]; - } else { - m = &md; - sg = m->sg_data; - sg_init_marker(sg, MAX_SKB_FRAGS); - } - - /* Catch case where ring is full and sendpage is stalled. */ - if (unlikely(m->sg_end == m->sg_start && - m->sg_data[m->sg_end].length)) - goto out_err; - - psock->sg_size += size; - sg_set_page(sg, page, size, offset); - get_page(page); - m->sg_copy[m->sg_end] = true; - sk_mem_charge(sk, size); - m->sg_end++; - copied = size; - - if (m->sg_end == MAX_SKB_FRAGS) - m->sg_end = 0; - - if (m->sg_end == m->sg_start) - enospc = true; - - if (psock->cork_bytes) { - if (size > psock->cork_bytes) - psock->cork_bytes = 0; - else - psock->cork_bytes -= size; - - if (psock->cork_bytes && !enospc) - goto out_err; - - /* All cork bytes accounted for re-run filter */ - psock->eval = __SK_NONE; - psock->cork_bytes = 0; - } - - err = bpf_exec_tx_verdict(psock, m, sk, &copied, flags); -out_err: - release_sock(sk); - smap_release_sock(psock, sk); - return copied ? copied : err; -accept: - rcu_read_unlock(); - return tcp_sendpage(sk, page, offset, size, flags); -} - -static void bpf_tcp_msg_add(struct smap_psock *psock, - struct sock *sk, - struct bpf_prog *tx_msg) -{ - struct bpf_prog *orig_tx_msg; - - orig_tx_msg = xchg(&psock->bpf_tx_msg, tx_msg); - if (orig_tx_msg) - bpf_prog_put(orig_tx_msg); -} - -static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb) -{ - struct bpf_prog *prog = READ_ONCE(psock->bpf_verdict); - int rc; - - if (unlikely(!prog)) - return __SK_DROP; - - skb_orphan(skb); - /* We need to ensure that BPF metadata for maps is also cleared - * when we orphan the skb so that we don't have the possibility - * to reference a stale map. - */ - TCP_SKB_CB(skb)->bpf.sk_redir = NULL; - skb->sk = psock->sock; - bpf_compute_data_end_sk_skb(skb); - preempt_disable(); - rc = (*prog->bpf_func)(skb, prog->insnsi); - preempt_enable(); - skb->sk = NULL; - - /* Moving return codes from UAPI namespace into internal namespace */ - return rc == SK_PASS ? - (TCP_SKB_CB(skb)->bpf.sk_redir ? __SK_REDIRECT : __SK_PASS) : - __SK_DROP; -} - -static int smap_do_ingress(struct smap_psock *psock, struct sk_buff *skb) -{ - struct sock *sk = psock->sock; - int copied = 0, num_sg; - struct sk_msg_buff *r; - - r = kzalloc(sizeof(struct sk_msg_buff), __GFP_NOWARN | GFP_ATOMIC); - if (unlikely(!r)) - return -EAGAIN; - - if (!sk_rmem_schedule(sk, skb, skb->len)) { - kfree(r); - return -EAGAIN; - } - - sg_init_table(r->sg_data, MAX_SKB_FRAGS); - num_sg = skb_to_sgvec(skb, r->sg_data, 0, skb->len); - if (unlikely(num_sg < 0)) { - kfree(r); - return num_sg; - } - sk_mem_charge(sk, skb->len); - copied = skb->len; - r->sg_start = 0; - r->sg_end = num_sg == MAX_SKB_FRAGS ? 0 : num_sg; - r->skb = skb; - list_add_tail(&r->list, &psock->ingress); - sk->sk_data_ready(sk); - return copied; -} - -static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb) -{ - struct smap_psock *peer; - struct sock *sk; - __u32 in; - int rc; - - rc = smap_verdict_func(psock, skb); - switch (rc) { - case __SK_REDIRECT: - sk = do_sk_redirect_map(skb); - if (!sk) { - kfree_skb(skb); - break; - } - - peer = smap_psock_sk(sk); - in = (TCP_SKB_CB(skb)->bpf.flags) & BPF_F_INGRESS; - - if (unlikely(!peer || sock_flag(sk, SOCK_DEAD) || - !test_bit(SMAP_TX_RUNNING, &peer->state))) { - kfree_skb(skb); - break; - } - - if (!in && sock_writeable(sk)) { - skb_set_owner_w(skb, sk); - skb_queue_tail(&peer->rxqueue, skb); - schedule_work(&peer->tx_work); - break; - } else if (in && - atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) { - skb_queue_tail(&peer->rxqueue, skb); - schedule_work(&peer->tx_work); - break; - } - /* Fall through and free skb otherwise */ - case __SK_DROP: - default: - kfree_skb(skb); - } -} - -static void smap_report_sk_error(struct smap_psock *psock, int err) -{ - struct sock *sk = psock->sock; - - sk->sk_err = err; - sk->sk_error_report(sk); -} - -static void smap_read_sock_strparser(struct strparser *strp, - struct sk_buff *skb) -{ - struct smap_psock *psock; - - rcu_read_lock(); - psock = container_of(strp, struct smap_psock, strp); - smap_do_verdict(psock, skb); - rcu_read_unlock(); -} - -/* Called with lock held on socket */ -static void smap_data_ready(struct sock *sk) -{ - struct smap_psock *psock; - - rcu_read_lock(); - psock = smap_psock_sk(sk); - if (likely(psock)) { - write_lock_bh(&sk->sk_callback_lock); - strp_data_ready(&psock->strp); - write_unlock_bh(&sk->sk_callback_lock); - } - rcu_read_unlock(); -} - -static void smap_tx_work(struct work_struct *w) -{ - struct smap_psock *psock; - struct sk_buff *skb; - int rem, off, n; - - psock = container_of(w, struct smap_psock, tx_work); - - /* lock sock to avoid losing sk_socket at some point during loop */ - lock_sock(psock->sock); - if (psock->save_skb) { - skb = psock->save_skb; - rem = psock->save_rem; - off = psock->save_off; - psock->save_skb = NULL; - goto start; - } - - while ((skb = skb_dequeue(&psock->rxqueue))) { - __u32 flags; - - rem = skb->len; - off = 0; -start: - flags = (TCP_SKB_CB(skb)->bpf.flags) & BPF_F_INGRESS; - do { - if (likely(psock->sock->sk_socket)) { - if (flags) - n = smap_do_ingress(psock, skb); - else - n = skb_send_sock_locked(psock->sock, - skb, off, rem); - } else { - n = -EINVAL; - } - - if (n <= 0) { - if (n == -EAGAIN) { - /* Retry when space is available */ - psock->save_skb = skb; - psock->save_rem = rem; - psock->save_off = off; - goto out; - } - /* Hard errors break pipe and stop xmit */ - smap_report_sk_error(psock, n ? -n : EPIPE); - clear_bit(SMAP_TX_RUNNING, &psock->state); - kfree_skb(skb); - goto out; - } - rem -= n; - off += n; - } while (rem); - - if (!flags) - kfree_skb(skb); - } -out: - release_sock(psock->sock); -} - -static void smap_write_space(struct sock *sk) -{ - struct smap_psock *psock; - void (*write_space)(struct sock *sk); - - rcu_read_lock(); - psock = smap_psock_sk(sk); - if (likely(psock && test_bit(SMAP_TX_RUNNING, &psock->state))) - schedule_work(&psock->tx_work); - write_space = psock->save_write_space; - rcu_read_unlock(); - write_space(sk); -} - -static void smap_stop_sock(struct smap_psock *psock, struct sock *sk) -{ - if (!psock->strp_enabled) - return; - sk->sk_data_ready = psock->save_data_ready; - sk->sk_write_space = psock->save_write_space; - psock->save_data_ready = NULL; - psock->save_write_space = NULL; - strp_stop(&psock->strp); - psock->strp_enabled = false; -} - -static void smap_destroy_psock(struct rcu_head *rcu) -{ - struct smap_psock *psock = container_of(rcu, - struct smap_psock, rcu); - - /* Now that a grace period has passed there is no longer - * any reference to this sock in the sockmap so we can - * destroy the psock, strparser, and bpf programs. But, - * because we use workqueue sync operations we can not - * do it in rcu context - */ - schedule_work(&psock->gc_work); -} - -static bool psock_is_smap_sk(struct sock *sk) -{ - return inet_csk(sk)->icsk_ulp_ops == &bpf_tcp_ulp_ops; -} - -static void smap_release_sock(struct smap_psock *psock, struct sock *sock) -{ - if (refcount_dec_and_test(&psock->refcnt)) { - if (psock_is_smap_sk(sock)) - bpf_tcp_release(sock); - write_lock_bh(&sock->sk_callback_lock); - smap_stop_sock(psock, sock); - write_unlock_bh(&sock->sk_callback_lock); - clear_bit(SMAP_TX_RUNNING, &psock->state); - rcu_assign_sk_user_data(sock, NULL); - call_rcu_sched(&psock->rcu, smap_destroy_psock); - } -} - -static int smap_parse_func_strparser(struct strparser *strp, - struct sk_buff *skb) -{ - struct smap_psock *psock; - struct bpf_prog *prog; - int rc; - - rcu_read_lock(); - psock = container_of(strp, struct smap_psock, strp); - prog = READ_ONCE(psock->bpf_parse); - - if (unlikely(!prog)) { - rcu_read_unlock(); - return skb->len; - } - - /* Attach socket for bpf program to use if needed we can do this - * because strparser clones the skb before handing it to a upper - * layer, meaning skb_orphan has been called. We NULL sk on the - * way out to ensure we don't trigger a BUG_ON in skb/sk operations - * later and because we are not charging the memory of this skb to - * any socket yet. - */ - skb->sk = psock->sock; - bpf_compute_data_end_sk_skb(skb); - rc = (*prog->bpf_func)(skb, prog->insnsi); - skb->sk = NULL; - rcu_read_unlock(); - return rc; -} - -static int smap_read_sock_done(struct strparser *strp, int err) -{ - return err; -} - -static int smap_init_sock(struct smap_psock *psock, - struct sock *sk) -{ - static const struct strp_callbacks cb = { - .rcv_msg = smap_read_sock_strparser, - .parse_msg = smap_parse_func_strparser, - .read_sock_done = smap_read_sock_done, - }; - - return strp_init(&psock->strp, sk, &cb); -} - -static void smap_init_progs(struct smap_psock *psock, - struct bpf_prog *verdict, - struct bpf_prog *parse) -{ - struct bpf_prog *orig_parse, *orig_verdict; - - orig_parse = xchg(&psock->bpf_parse, parse); - orig_verdict = xchg(&psock->bpf_verdict, verdict); - - if (orig_verdict) - bpf_prog_put(orig_verdict); - if (orig_parse) - bpf_prog_put(orig_parse); -} - -static void smap_start_sock(struct smap_psock *psock, struct sock *sk) -{ - if (sk->sk_data_ready == smap_data_ready) - return; - psock->save_data_ready = sk->sk_data_ready; - psock->save_write_space = sk->sk_write_space; - sk->sk_data_ready = smap_data_ready; - sk->sk_write_space = smap_write_space; - psock->strp_enabled = true; -} - -static void sock_map_remove_complete(struct bpf_stab *stab) -{ - bpf_map_area_free(stab->sock_map); - kfree(stab); -} - -static void smap_gc_work(struct work_struct *w) -{ - struct smap_psock_map_entry *e, *tmp; - struct sk_msg_buff *md, *mtmp; - struct smap_psock *psock; - - psock = container_of(w, struct smap_psock, gc_work); - - /* no callback lock needed because we already detached sockmap ops */ - if (psock->strp_enabled) - strp_done(&psock->strp); - - cancel_work_sync(&psock->tx_work); - __skb_queue_purge(&psock->rxqueue); - - /* At this point all strparser and xmit work must be complete */ - if (psock->bpf_parse) - bpf_prog_put(psock->bpf_parse); - if (psock->bpf_verdict) - bpf_prog_put(psock->bpf_verdict); - if (psock->bpf_tx_msg) - bpf_prog_put(psock->bpf_tx_msg); - - if (psock->cork) { - free_start_sg(psock->sock, psock->cork, true); - kfree(psock->cork); - } - - list_for_each_entry_safe(md, mtmp, &psock->ingress, list) { - list_del(&md->list); - free_start_sg(psock->sock, md, true); - kfree(md); - } - - list_for_each_entry_safe(e, tmp, &psock->maps, list) { - list_del(&e->list); - kfree(e); - } - - if (psock->sk_redir) - sock_put(psock->sk_redir); - - sock_put(psock->sock); - kfree(psock); -} - -static struct smap_psock *smap_init_psock(struct sock *sock, int node) -{ - struct smap_psock *psock; - - psock = kzalloc_node(sizeof(struct smap_psock), - GFP_ATOMIC | __GFP_NOWARN, - node); - if (!psock) - return ERR_PTR(-ENOMEM); - - psock->eval = __SK_NONE; - psock->sock = sock; - skb_queue_head_init(&psock->rxqueue); - INIT_WORK(&psock->tx_work, smap_tx_work); - INIT_WORK(&psock->gc_work, smap_gc_work); - INIT_LIST_HEAD(&psock->maps); - INIT_LIST_HEAD(&psock->ingress); - refcount_set(&psock->refcnt, 1); - spin_lock_init(&psock->maps_lock); - - rcu_assign_sk_user_data(sock, psock); - sock_hold(sock); - return psock; -} - -static struct bpf_map *sock_map_alloc(union bpf_attr *attr) -{ - struct bpf_stab *stab; - u64 cost; - int err; - - if (!capable(CAP_NET_ADMIN)) - return ERR_PTR(-EPERM); - - /* check sanity of attributes */ - if (attr->max_entries == 0 || attr->key_size != 4 || - attr->value_size != 4 || attr->map_flags & ~SOCK_CREATE_FLAG_MASK) - return ERR_PTR(-EINVAL); - - stab = kzalloc(sizeof(*stab), GFP_USER); - if (!stab) - return ERR_PTR(-ENOMEM); - - bpf_map_init_from_attr(&stab->map, attr); - raw_spin_lock_init(&stab->lock); - - /* make sure page count doesn't overflow */ - cost = (u64) stab->map.max_entries * sizeof(struct sock *); - err = -EINVAL; - if (cost >= U32_MAX - PAGE_SIZE) - goto free_stab; - - stab->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; - - /* if map size is larger than memlock limit, reject it early */ - err = bpf_map_precharge_memlock(stab->map.pages); - if (err) - goto free_stab; - - err = -ENOMEM; - stab->sock_map = bpf_map_area_alloc(stab->map.max_entries * - sizeof(struct sock *), - stab->map.numa_node); - if (!stab->sock_map) - goto free_stab; - - return &stab->map; -free_stab: - kfree(stab); - return ERR_PTR(err); -} - -static void smap_list_map_remove(struct smap_psock *psock, - struct sock **entry) -{ - struct smap_psock_map_entry *e, *tmp; - - spin_lock_bh(&psock->maps_lock); - list_for_each_entry_safe(e, tmp, &psock->maps, list) { - if (e->entry == entry) { - list_del(&e->list); - kfree(e); - } - } - spin_unlock_bh(&psock->maps_lock); -} - -static void smap_list_hash_remove(struct smap_psock *psock, - struct htab_elem *hash_link) -{ - struct smap_psock_map_entry *e, *tmp; - - spin_lock_bh(&psock->maps_lock); - list_for_each_entry_safe(e, tmp, &psock->maps, list) { - struct htab_elem *c = rcu_dereference(e->hash_link); - - if (c == hash_link) { - list_del(&e->list); - kfree(e); - } - } - spin_unlock_bh(&psock->maps_lock); -} - -static void sock_map_free(struct bpf_map *map) -{ - struct bpf_stab *stab = container_of(map, struct bpf_stab, map); - int i; - - synchronize_rcu(); - - /* At this point no update, lookup or delete operations can happen. - * However, be aware we can still get a socket state event updates, - * and data ready callabacks that reference the psock from sk_user_data - * Also psock worker threads are still in-flight. So smap_release_sock - * will only free the psock after cancel_sync on the worker threads - * and a grace period expire to ensure psock is really safe to remove. - */ - rcu_read_lock(); - raw_spin_lock_bh(&stab->lock); - for (i = 0; i < stab->map.max_entries; i++) { - struct smap_psock *psock; - struct sock *sock; - - sock = stab->sock_map[i]; - if (!sock) - continue; - stab->sock_map[i] = NULL; - psock = smap_psock_sk(sock); - /* This check handles a racing sock event that can get the - * sk_callback_lock before this case but after xchg happens - * causing the refcnt to hit zero and sock user data (psock) - * to be null and queued for garbage collection. - */ - if (likely(psock)) { - smap_list_map_remove(psock, &stab->sock_map[i]); - smap_release_sock(psock, sock); - } - } - raw_spin_unlock_bh(&stab->lock); - rcu_read_unlock(); - - sock_map_remove_complete(stab); -} - -static int sock_map_get_next_key(struct bpf_map *map, void *key, void *next_key) -{ - struct bpf_stab *stab = container_of(map, struct bpf_stab, map); - u32 i = key ? *(u32 *)key : U32_MAX; - u32 *next = (u32 *)next_key; - - if (i >= stab->map.max_entries) { - *next = 0; - return 0; - } - - if (i == stab->map.max_entries - 1) - return -ENOENT; - - *next = i + 1; - return 0; -} - -struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key) -{ - struct bpf_stab *stab = container_of(map, struct bpf_stab, map); - - if (key >= map->max_entries) - return NULL; - - return READ_ONCE(stab->sock_map[key]); -} - -static int sock_map_delete_elem(struct bpf_map *map, void *key) -{ - struct bpf_stab *stab = container_of(map, struct bpf_stab, map); - struct smap_psock *psock; - int k = *(u32 *)key; - struct sock *sock; - - if (k >= map->max_entries) - return -EINVAL; - - raw_spin_lock_bh(&stab->lock); - sock = stab->sock_map[k]; - stab->sock_map[k] = NULL; - raw_spin_unlock_bh(&stab->lock); - if (!sock) - return -EINVAL; - - psock = smap_psock_sk(sock); - if (!psock) - return 0; - if (psock->bpf_parse) { - write_lock_bh(&sock->sk_callback_lock); - smap_stop_sock(psock, sock); - write_unlock_bh(&sock->sk_callback_lock); - } - smap_list_map_remove(psock, &stab->sock_map[k]); - smap_release_sock(psock, sock); - return 0; -} - -/* Locking notes: Concurrent updates, deletes, and lookups are allowed and are - * done inside rcu critical sections. This ensures on updates that the psock - * will not be released via smap_release_sock() until concurrent updates/deletes - * complete. All operations operate on sock_map using cmpxchg and xchg - * operations to ensure we do not get stale references. Any reads into the - * map must be done with READ_ONCE() because of this. - * - * A psock is destroyed via call_rcu and after any worker threads are cancelled - * and syncd so we are certain all references from the update/lookup/delete - * operations as well as references in the data path are no longer in use. - * - * Psocks may exist in multiple maps, but only a single set of parse/verdict - * programs may be inherited from the maps it belongs to. A reference count - * is kept with the total number of references to the psock from all maps. The - * psock will not be released until this reaches zero. The psock and sock - * user data data use the sk_callback_lock to protect critical data structures - * from concurrent access. This allows us to avoid two updates from modifying - * the user data in sock and the lock is required anyways for modifying - * callbacks, we simply increase its scope slightly. - * - * Rules to follow, - * - psock must always be read inside RCU critical section - * - sk_user_data must only be modified inside sk_callback_lock and read - * inside RCU critical section. - * - psock->maps list must only be read & modified inside sk_callback_lock - * - sock_map must use READ_ONCE and (cmp)xchg operations - * - BPF verdict/parse programs must use READ_ONCE and xchg operations - */ - -static int __sock_map_ctx_update_elem(struct bpf_map *map, - struct bpf_sock_progs *progs, - struct sock *sock, - void *key) -{ - struct bpf_prog *verdict, *parse, *tx_msg; - struct smap_psock *psock; - bool new = false; - int err = 0; - - /* 1. If sock map has BPF programs those will be inherited by the - * sock being added. If the sock is already attached to BPF programs - * this results in an error. - */ - verdict = READ_ONCE(progs->bpf_verdict); - parse = READ_ONCE(progs->bpf_parse); - tx_msg = READ_ONCE(progs->bpf_tx_msg); - - if (parse && verdict) { - /* bpf prog refcnt may be zero if a concurrent attach operation - * removes the program after the above READ_ONCE() but before - * we increment the refcnt. If this is the case abort with an - * error. - */ - verdict = bpf_prog_inc_not_zero(verdict); - if (IS_ERR(verdict)) - return PTR_ERR(verdict); - - parse = bpf_prog_inc_not_zero(parse); - if (IS_ERR(parse)) { - bpf_prog_put(verdict); - return PTR_ERR(parse); - } - } - - if (tx_msg) { - tx_msg = bpf_prog_inc_not_zero(tx_msg); - if (IS_ERR(tx_msg)) { - if (parse && verdict) { - bpf_prog_put(parse); - bpf_prog_put(verdict); - } - return PTR_ERR(tx_msg); - } - } - - psock = smap_psock_sk(sock); - - /* 2. Do not allow inheriting programs if psock exists and has - * already inherited programs. This would create confusion on - * which parser/verdict program is running. If no psock exists - * create one. Inside sk_callback_lock to ensure concurrent create - * doesn't update user data. - */ - if (psock) { - if (!psock_is_smap_sk(sock)) { - err = -EBUSY; - goto out_progs; - } - if (READ_ONCE(psock->bpf_parse) && parse) { - err = -EBUSY; - goto out_progs; - } - if (READ_ONCE(psock->bpf_tx_msg) && tx_msg) { - err = -EBUSY; - goto out_progs; - } - if (!refcount_inc_not_zero(&psock->refcnt)) { - err = -EAGAIN; - goto out_progs; - } - } else { - psock = smap_init_psock(sock, map->numa_node); - if (IS_ERR(psock)) { - err = PTR_ERR(psock); - goto out_progs; - } - - set_bit(SMAP_TX_RUNNING, &psock->state); - new = true; - } - - /* 3. At this point we have a reference to a valid psock that is - * running. Attach any BPF programs needed. - */ - if (tx_msg) - bpf_tcp_msg_add(psock, sock, tx_msg); - if (new) { - err = bpf_tcp_init(sock); - if (err) - goto out_free; - } - - if (parse && verdict && !psock->strp_enabled) { - err = smap_init_sock(psock, sock); - if (err) - goto out_free; - smap_init_progs(psock, verdict, parse); - write_lock_bh(&sock->sk_callback_lock); - smap_start_sock(psock, sock); - write_unlock_bh(&sock->sk_callback_lock); - } - - return err; -out_free: - smap_release_sock(psock, sock); -out_progs: - if (parse && verdict) { - bpf_prog_put(parse); - bpf_prog_put(verdict); - } - if (tx_msg) - bpf_prog_put(tx_msg); - return err; -} - -static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops, - struct bpf_map *map, - void *key, u64 flags) -{ - struct bpf_stab *stab = container_of(map, struct bpf_stab, map); - struct bpf_sock_progs *progs = &stab->progs; - struct sock *osock, *sock = skops->sk; - struct smap_psock_map_entry *e; - struct smap_psock *psock; - u32 i = *(u32 *)key; - int err; - - if (unlikely(flags > BPF_EXIST)) - return -EINVAL; - if (unlikely(i >= stab->map.max_entries)) - return -E2BIG; - - e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN); - if (!e) - return -ENOMEM; - - err = __sock_map_ctx_update_elem(map, progs, sock, key); - if (err) - goto out; - - /* psock guaranteed to be present. */ - psock = smap_psock_sk(sock); - raw_spin_lock_bh(&stab->lock); - osock = stab->sock_map[i]; - if (osock && flags == BPF_NOEXIST) { - err = -EEXIST; - goto out_unlock; - } - if (!osock && flags == BPF_EXIST) { - err = -ENOENT; - goto out_unlock; - } - - e->entry = &stab->sock_map[i]; - e->map = map; - spin_lock_bh(&psock->maps_lock); - list_add_tail(&e->list, &psock->maps); - spin_unlock_bh(&psock->maps_lock); - - stab->sock_map[i] = sock; - if (osock) { - psock = smap_psock_sk(osock); - smap_list_map_remove(psock, &stab->sock_map[i]); - smap_release_sock(psock, osock); - } - raw_spin_unlock_bh(&stab->lock); - return 0; -out_unlock: - smap_release_sock(psock, sock); - raw_spin_unlock_bh(&stab->lock); -out: - kfree(e); - return err; -} - -int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type) -{ - struct bpf_sock_progs *progs; - struct bpf_prog *orig; - - if (map->map_type == BPF_MAP_TYPE_SOCKMAP) { - struct bpf_stab *stab = container_of(map, struct bpf_stab, map); - - progs = &stab->progs; - } else if (map->map_type == BPF_MAP_TYPE_SOCKHASH) { - struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - - progs = &htab->progs; - } else { - return -EINVAL; - } - - switch (type) { - case BPF_SK_MSG_VERDICT: - orig = xchg(&progs->bpf_tx_msg, prog); - break; - case BPF_SK_SKB_STREAM_PARSER: - orig = xchg(&progs->bpf_parse, prog); - break; - case BPF_SK_SKB_STREAM_VERDICT: - orig = xchg(&progs->bpf_verdict, prog); - break; - default: - return -EOPNOTSUPP; - } - - if (orig) - bpf_prog_put(orig); - - return 0; -} - -int sockmap_get_from_fd(const union bpf_attr *attr, int type, - struct bpf_prog *prog) -{ - int ufd = attr->target_fd; - struct bpf_map *map; - struct fd f; - int err; - - f = fdget(ufd); - map = __bpf_map_get(f); - if (IS_ERR(map)) - return PTR_ERR(map); - - err = sock_map_prog(map, prog, attr->attach_type); - fdput(f); - return err; -} - -static void *sock_map_lookup(struct bpf_map *map, void *key) -{ - return ERR_PTR(-EOPNOTSUPP); -} - -static int sock_map_update_elem(struct bpf_map *map, - void *key, void *value, u64 flags) -{ - struct bpf_sock_ops_kern skops; - u32 fd = *(u32 *)value; - struct socket *socket; - int err; - - socket = sockfd_lookup(fd, &err); - if (!socket) - return err; - - skops.sk = socket->sk; - if (!skops.sk) { - fput(socket->file); - return -EINVAL; - } - - /* ULPs are currently supported only for TCP sockets in ESTABLISHED - * state. - */ - if (skops.sk->sk_type != SOCK_STREAM || - skops.sk->sk_protocol != IPPROTO_TCP || - skops.sk->sk_state != TCP_ESTABLISHED) { - fput(socket->file); - return -EOPNOTSUPP; - } - - lock_sock(skops.sk); - preempt_disable(); - rcu_read_lock(); - err = sock_map_ctx_update_elem(&skops, map, key, flags); - rcu_read_unlock(); - preempt_enable(); - release_sock(skops.sk); - fput(socket->file); - return err; -} - -static void sock_map_release(struct bpf_map *map) -{ - struct bpf_sock_progs *progs; - struct bpf_prog *orig; - - if (map->map_type == BPF_MAP_TYPE_SOCKMAP) { - struct bpf_stab *stab = container_of(map, struct bpf_stab, map); - - progs = &stab->progs; - } else { - struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - - progs = &htab->progs; - } - - orig = xchg(&progs->bpf_parse, NULL); - if (orig) - bpf_prog_put(orig); - orig = xchg(&progs->bpf_verdict, NULL); - if (orig) - bpf_prog_put(orig); - - orig = xchg(&progs->bpf_tx_msg, NULL); - if (orig) - bpf_prog_put(orig); -} - -static struct bpf_map *sock_hash_alloc(union bpf_attr *attr) -{ - struct bpf_htab *htab; - int i, err; - u64 cost; - - if (!capable(CAP_NET_ADMIN)) - return ERR_PTR(-EPERM); - - /* check sanity of attributes */ - if (attr->max_entries == 0 || - attr->key_size == 0 || - attr->value_size != 4 || - attr->map_flags & ~SOCK_CREATE_FLAG_MASK) - return ERR_PTR(-EINVAL); - - if (attr->key_size > MAX_BPF_STACK) - /* eBPF programs initialize keys on stack, so they cannot be - * larger than max stack size - */ - return ERR_PTR(-E2BIG); - - htab = kzalloc(sizeof(*htab), GFP_USER); - if (!htab) - return ERR_PTR(-ENOMEM); - - bpf_map_init_from_attr(&htab->map, attr); - - htab->n_buckets = roundup_pow_of_two(htab->map.max_entries); - htab->elem_size = sizeof(struct htab_elem) + - round_up(htab->map.key_size, 8); - err = -EINVAL; - if (htab->n_buckets == 0 || - htab->n_buckets > U32_MAX / sizeof(struct bucket)) - goto free_htab; - - cost = (u64) htab->n_buckets * sizeof(struct bucket) + - (u64) htab->elem_size * htab->map.max_entries; - - if (cost >= U32_MAX - PAGE_SIZE) - goto free_htab; - - htab->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; - err = bpf_map_precharge_memlock(htab->map.pages); - if (err) - goto free_htab; - - err = -ENOMEM; - htab->buckets = bpf_map_area_alloc( - htab->n_buckets * sizeof(struct bucket), - htab->map.numa_node); - if (!htab->buckets) - goto free_htab; - - for (i = 0; i < htab->n_buckets; i++) { - INIT_HLIST_HEAD(&htab->buckets[i].head); - raw_spin_lock_init(&htab->buckets[i].lock); - } - - return &htab->map; -free_htab: - kfree(htab); - return ERR_PTR(err); -} - -static void __bpf_htab_free(struct rcu_head *rcu) -{ - struct bpf_htab *htab; - - htab = container_of(rcu, struct bpf_htab, rcu); - bpf_map_area_free(htab->buckets); - kfree(htab); -} - -static void sock_hash_free(struct bpf_map *map) -{ - struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - int i; - - synchronize_rcu(); - - /* At this point no update, lookup or delete operations can happen. - * However, be aware we can still get a socket state event updates, - * and data ready callabacks that reference the psock from sk_user_data - * Also psock worker threads are still in-flight. So smap_release_sock - * will only free the psock after cancel_sync on the worker threads - * and a grace period expire to ensure psock is really safe to remove. - */ - rcu_read_lock(); - for (i = 0; i < htab->n_buckets; i++) { - struct bucket *b = __select_bucket(htab, i); - struct hlist_head *head; - struct hlist_node *n; - struct htab_elem *l; - - raw_spin_lock_bh(&b->lock); - head = &b->head; - hlist_for_each_entry_safe(l, n, head, hash_node) { - struct sock *sock = l->sk; - struct smap_psock *psock; - - hlist_del_rcu(&l->hash_node); - psock = smap_psock_sk(sock); - /* This check handles a racing sock event that can get - * the sk_callback_lock before this case but after xchg - * causing the refcnt to hit zero and sock user data - * (psock) to be null and queued for garbage collection. - */ - if (likely(psock)) { - smap_list_hash_remove(psock, l); - smap_release_sock(psock, sock); - } - free_htab_elem(htab, l); - } - raw_spin_unlock_bh(&b->lock); - } - rcu_read_unlock(); - call_rcu(&htab->rcu, __bpf_htab_free); -} - -static struct htab_elem *alloc_sock_hash_elem(struct bpf_htab *htab, - void *key, u32 key_size, u32 hash, - struct sock *sk, - struct htab_elem *old_elem) -{ - struct htab_elem *l_new; - - if (atomic_inc_return(&htab->count) > htab->map.max_entries) { - if (!old_elem) { - atomic_dec(&htab->count); - return ERR_PTR(-E2BIG); - } - } - l_new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN, - htab->map.numa_node); - if (!l_new) { - atomic_dec(&htab->count); - return ERR_PTR(-ENOMEM); - } - - memcpy(l_new->key, key, key_size); - l_new->sk = sk; - l_new->hash = hash; - return l_new; -} - -static inline u32 htab_map_hash(const void *key, u32 key_len) -{ - return jhash(key, key_len, 0); -} - -static int sock_hash_get_next_key(struct bpf_map *map, - void *key, void *next_key) -{ - struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - struct htab_elem *l, *next_l; - struct hlist_head *h; - u32 hash, key_size; - int i = 0; - - WARN_ON_ONCE(!rcu_read_lock_held()); - - key_size = map->key_size; - if (!key) - goto find_first_elem; - hash = htab_map_hash(key, key_size); - h = select_bucket(htab, hash); - - l = lookup_elem_raw(h, hash, key, key_size); - if (!l) - goto find_first_elem; - next_l = hlist_entry_safe( - rcu_dereference_raw(hlist_next_rcu(&l->hash_node)), - struct htab_elem, hash_node); - if (next_l) { - memcpy(next_key, next_l->key, key_size); - return 0; - } - - /* no more elements in this hash list, go to the next bucket */ - i = hash & (htab->n_buckets - 1); - i++; - -find_first_elem: - /* iterate over buckets */ - for (; i < htab->n_buckets; i++) { - h = select_bucket(htab, i); - - /* pick first element in the bucket */ - next_l = hlist_entry_safe( - rcu_dereference_raw(hlist_first_rcu(h)), - struct htab_elem, hash_node); - if (next_l) { - /* if it's not empty, just return it */ - memcpy(next_key, next_l->key, key_size); - return 0; - } - } - - /* iterated over all buckets and all elements */ - return -ENOENT; -} - -static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops, - struct bpf_map *map, - void *key, u64 map_flags) -{ - struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - struct bpf_sock_progs *progs = &htab->progs; - struct htab_elem *l_new = NULL, *l_old; - struct smap_psock_map_entry *e = NULL; - struct hlist_head *head; - struct smap_psock *psock; - u32 key_size, hash; - struct sock *sock; - struct bucket *b; - int err; - - sock = skops->sk; - - if (sock->sk_type != SOCK_STREAM || - sock->sk_protocol != IPPROTO_TCP) - return -EOPNOTSUPP; - - if (unlikely(map_flags > BPF_EXIST)) - return -EINVAL; - - e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN); - if (!e) - return -ENOMEM; - - WARN_ON_ONCE(!rcu_read_lock_held()); - key_size = map->key_size; - hash = htab_map_hash(key, key_size); - b = __select_bucket(htab, hash); - head = &b->head; - - err = __sock_map_ctx_update_elem(map, progs, sock, key); - if (err) - goto err; - - /* psock is valid here because otherwise above *ctx_update_elem would - * have thrown an error. It is safe to skip error check. - */ - psock = smap_psock_sk(sock); - raw_spin_lock_bh(&b->lock); - l_old = lookup_elem_raw(head, hash, key, key_size); - if (l_old && map_flags == BPF_NOEXIST) { - err = -EEXIST; - goto bucket_err; - } - if (!l_old && map_flags == BPF_EXIST) { - err = -ENOENT; - goto bucket_err; - } - - l_new = alloc_sock_hash_elem(htab, key, key_size, hash, sock, l_old); - if (IS_ERR(l_new)) { - err = PTR_ERR(l_new); - goto bucket_err; - } - - rcu_assign_pointer(e->hash_link, l_new); - e->map = map; - spin_lock_bh(&psock->maps_lock); - list_add_tail(&e->list, &psock->maps); - spin_unlock_bh(&psock->maps_lock); - - /* add new element to the head of the list, so that - * concurrent search will find it before old elem - */ - hlist_add_head_rcu(&l_new->hash_node, head); - if (l_old) { - psock = smap_psock_sk(l_old->sk); - - hlist_del_rcu(&l_old->hash_node); - smap_list_hash_remove(psock, l_old); - smap_release_sock(psock, l_old->sk); - free_htab_elem(htab, l_old); - } - raw_spin_unlock_bh(&b->lock); - return 0; -bucket_err: - smap_release_sock(psock, sock); - raw_spin_unlock_bh(&b->lock); -err: - kfree(e); - return err; -} - -static int sock_hash_update_elem(struct bpf_map *map, - void *key, void *value, u64 flags) -{ - struct bpf_sock_ops_kern skops; - u32 fd = *(u32 *)value; - struct socket *socket; - int err; - - socket = sockfd_lookup(fd, &err); - if (!socket) - return err; - - skops.sk = socket->sk; - if (!skops.sk) { - fput(socket->file); - return -EINVAL; - } - - /* ULPs are currently supported only for TCP sockets in ESTABLISHED - * state. - */ - if (skops.sk->sk_type != SOCK_STREAM || - skops.sk->sk_protocol != IPPROTO_TCP || - skops.sk->sk_state != TCP_ESTABLISHED) { - fput(socket->file); - return -EOPNOTSUPP; - } - - lock_sock(skops.sk); - preempt_disable(); - rcu_read_lock(); - err = sock_hash_ctx_update_elem(&skops, map, key, flags); - rcu_read_unlock(); - preempt_enable(); - release_sock(skops.sk); - fput(socket->file); - return err; -} - -static int sock_hash_delete_elem(struct bpf_map *map, void *key) -{ - struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - struct hlist_head *head; - struct bucket *b; - struct htab_elem *l; - u32 hash, key_size; - int ret = -ENOENT; - - key_size = map->key_size; - hash = htab_map_hash(key, key_size); - b = __select_bucket(htab, hash); - head = &b->head; - - raw_spin_lock_bh(&b->lock); - l = lookup_elem_raw(head, hash, key, key_size); - if (l) { - struct sock *sock = l->sk; - struct smap_psock *psock; - - hlist_del_rcu(&l->hash_node); - psock = smap_psock_sk(sock); - /* This check handles a racing sock event that can get the - * sk_callback_lock before this case but after xchg happens - * causing the refcnt to hit zero and sock user data (psock) - * to be null and queued for garbage collection. - */ - if (likely(psock)) { - smap_list_hash_remove(psock, l); - smap_release_sock(psock, sock); - } - free_htab_elem(htab, l); - ret = 0; - } - raw_spin_unlock_bh(&b->lock); - return ret; -} - -struct sock *__sock_hash_lookup_elem(struct bpf_map *map, void *key) -{ - struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - struct hlist_head *head; - struct htab_elem *l; - u32 key_size, hash; - struct bucket *b; - struct sock *sk; - - key_size = map->key_size; - hash = htab_map_hash(key, key_size); - b = __select_bucket(htab, hash); - head = &b->head; - - l = lookup_elem_raw(head, hash, key, key_size); - sk = l ? l->sk : NULL; - return sk; -} - -const struct bpf_map_ops sock_map_ops = { - .map_alloc = sock_map_alloc, - .map_free = sock_map_free, - .map_lookup_elem = sock_map_lookup, - .map_get_next_key = sock_map_get_next_key, - .map_update_elem = sock_map_update_elem, - .map_delete_elem = sock_map_delete_elem, - .map_release_uref = sock_map_release, - .map_check_btf = map_check_no_btf, -}; - -const struct bpf_map_ops sock_hash_ops = { - .map_alloc = sock_hash_alloc, - .map_free = sock_hash_free, - .map_lookup_elem = sock_map_lookup, - .map_get_next_key = sock_hash_get_next_key, - .map_update_elem = sock_hash_update_elem, - .map_delete_elem = sock_hash_delete_elem, - .map_release_uref = sock_map_release, - .map_check_btf = map_check_no_btf, -}; - -static bool bpf_is_valid_sock_op(struct bpf_sock_ops_kern *ops) -{ - return ops->op == BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB || - ops->op == BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB; -} -BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock, - struct bpf_map *, map, void *, key, u64, flags) -{ - WARN_ON_ONCE(!rcu_read_lock_held()); - - /* ULPs are currently supported only for TCP sockets in ESTABLISHED - * state. This checks that the sock ops triggering the update is - * one indicating we are (or will be soon) in an ESTABLISHED state. - */ - if (!bpf_is_valid_sock_op(bpf_sock)) - return -EOPNOTSUPP; - return sock_map_ctx_update_elem(bpf_sock, map, key, flags); -} - -const struct bpf_func_proto bpf_sock_map_update_proto = { - .func = bpf_sock_map_update, - .gpl_only = false, - .pkt_access = true, - .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_CONST_MAP_PTR, - .arg3_type = ARG_PTR_TO_MAP_KEY, - .arg4_type = ARG_ANYTHING, -}; - -BPF_CALL_4(bpf_sock_hash_update, struct bpf_sock_ops_kern *, bpf_sock, - struct bpf_map *, map, void *, key, u64, flags) -{ - WARN_ON_ONCE(!rcu_read_lock_held()); - - if (!bpf_is_valid_sock_op(bpf_sock)) - return -EOPNOTSUPP; - return sock_hash_ctx_update_elem(bpf_sock, map, key, flags); -} - -const struct bpf_func_proto bpf_sock_hash_update_proto = { - .func = bpf_sock_hash_update, - .gpl_only = false, - .pkt_access = true, - .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_CONST_MAP_PTR, - .arg3_type = ARG_PTR_TO_MAP_KEY, - .arg4_type = ARG_ANYTHING, -}; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 53968f82b919..f4ecd6ed2252 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1664,7 +1664,7 @@ static int bpf_prog_attach(const union bpf_attr *attr) switch (ptype) { case BPF_PROG_TYPE_SK_SKB: case BPF_PROG_TYPE_SK_MSG: - ret = sockmap_get_from_fd(attr, ptype, prog); + ret = sock_map_get_from_fd(attr, prog); break; case BPF_PROG_TYPE_LIRC_MODE2: ret = lirc_prog_attach(attr, prog); @@ -1718,10 +1718,10 @@ static int bpf_prog_detach(const union bpf_attr *attr) ptype = BPF_PROG_TYPE_CGROUP_DEVICE; break; case BPF_SK_MSG_VERDICT: - return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, NULL); + return sock_map_get_from_fd(attr, NULL); case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: - return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, NULL); + return sock_map_get_from_fd(attr, NULL); case BPF_LIRC_MODE2: return lirc_prog_detach(attr); case BPF_FLOW_DISSECTOR: diff --git a/net/Kconfig b/net/Kconfig index 228dfa382eec..f235edb593ba 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -300,8 +300,11 @@ config BPF_JIT config BPF_STREAM_PARSER bool "enable BPF STREAM_PARSER" + depends on INET depends on BPF_SYSCALL + depends on CGROUP_BPF select STREAM_PARSER + select NET_SOCK_MSG ---help--- Enabling this allows a stream parser to be used with BPF_MAP_TYPE_SOCKMAP. @@ -413,6 +416,14 @@ config GRO_CELLS config SOCK_VALIDATE_XMIT bool +config NET_SOCK_MSG + bool + default n + help + The NET_SOCK_MSG provides a framework for plain sockets (e.g. TCP) or + ULPs (upper layer modules, e.g. TLS) to process L7 application data + with the help of BPF programs. + config NET_DEVLINK tristate "Network physical/parent device Netlink interface" help diff --git a/net/core/Makefile b/net/core/Makefile index 80175e6a2eb8..fccd31e0e7f7 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -16,6 +16,7 @@ obj-y += dev.o ethtool.o dev_addr_lists.o dst.o netevent.o \ obj-y += net-sysfs.o obj-$(CONFIG_PAGE_POOL) += page_pool.o obj-$(CONFIG_PROC_FS) += net-procfs.o +obj-$(CONFIG_NET_SOCK_MSG) += skmsg.o obj-$(CONFIG_NET_PKTGEN) += pktgen.o obj-$(CONFIG_NETPOLL) += netpoll.o obj-$(CONFIG_FIB_RULES) += fib_rules.o @@ -27,6 +28,7 @@ obj-$(CONFIG_CGROUP_NET_PRIO) += netprio_cgroup.o obj-$(CONFIG_CGROUP_NET_CLASSID) += netclassid_cgroup.o obj-$(CONFIG_LWTUNNEL) += lwtunnel.o obj-$(CONFIG_LWTUNNEL_BPF) += lwt_bpf.o +obj-$(CONFIG_BPF_STREAM_PARSER) += sock_map.o obj-$(CONFIG_DST_CACHE) += dst_cache.o obj-$(CONFIG_HWBM) += hwbm.o obj-$(CONFIG_NET_DEVLINK) += devlink.o diff --git a/net/core/filter.c b/net/core/filter.c index b844761b5d4c..0f5260b04bfe 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -38,6 +38,7 @@ #include #include #include +#include #include #include #include @@ -2142,123 +2143,7 @@ static const struct bpf_func_proto bpf_redirect_proto = { .arg2_type = ARG_ANYTHING, }; -BPF_CALL_4(bpf_sk_redirect_hash, struct sk_buff *, skb, - struct bpf_map *, map, void *, key, u64, flags) -{ - struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); - - /* If user passes invalid input drop the packet. */ - if (unlikely(flags & ~(BPF_F_INGRESS))) - return SK_DROP; - - tcb->bpf.flags = flags; - tcb->bpf.sk_redir = __sock_hash_lookup_elem(map, key); - if (!tcb->bpf.sk_redir) - return SK_DROP; - - return SK_PASS; -} - -static const struct bpf_func_proto bpf_sk_redirect_hash_proto = { - .func = bpf_sk_redirect_hash, - .gpl_only = false, - .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_CONST_MAP_PTR, - .arg3_type = ARG_PTR_TO_MAP_KEY, - .arg4_type = ARG_ANYTHING, -}; - -BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb, - struct bpf_map *, map, u32, key, u64, flags) -{ - struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); - - /* If user passes invalid input drop the packet. */ - if (unlikely(flags & ~(BPF_F_INGRESS))) - return SK_DROP; - - tcb->bpf.flags = flags; - tcb->bpf.sk_redir = __sock_map_lookup_elem(map, key); - if (!tcb->bpf.sk_redir) - return SK_DROP; - - return SK_PASS; -} - -struct sock *do_sk_redirect_map(struct sk_buff *skb) -{ - struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); - - return tcb->bpf.sk_redir; -} - -static const struct bpf_func_proto bpf_sk_redirect_map_proto = { - .func = bpf_sk_redirect_map, - .gpl_only = false, - .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_CONST_MAP_PTR, - .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_ANYTHING, -}; - -BPF_CALL_4(bpf_msg_redirect_hash, struct sk_msg_buff *, msg, - struct bpf_map *, map, void *, key, u64, flags) -{ - /* If user passes invalid input drop the packet. */ - if (unlikely(flags & ~(BPF_F_INGRESS))) - return SK_DROP; - - msg->flags = flags; - msg->sk_redir = __sock_hash_lookup_elem(map, key); - if (!msg->sk_redir) - return SK_DROP; - - return SK_PASS; -} - -static const struct bpf_func_proto bpf_msg_redirect_hash_proto = { - .func = bpf_msg_redirect_hash, - .gpl_only = false, - .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_CONST_MAP_PTR, - .arg3_type = ARG_PTR_TO_MAP_KEY, - .arg4_type = ARG_ANYTHING, -}; - -BPF_CALL_4(bpf_msg_redirect_map, struct sk_msg_buff *, msg, - struct bpf_map *, map, u32, key, u64, flags) -{ - /* If user passes invalid input drop the packet. */ - if (unlikely(flags & ~(BPF_F_INGRESS))) - return SK_DROP; - - msg->flags = flags; - msg->sk_redir = __sock_map_lookup_elem(map, key); - if (!msg->sk_redir) - return SK_DROP; - - return SK_PASS; -} - -struct sock *do_msg_redirect_map(struct sk_msg_buff *msg) -{ - return msg->sk_redir; -} - -static const struct bpf_func_proto bpf_msg_redirect_map_proto = { - .func = bpf_msg_redirect_map, - .gpl_only = false, - .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_CONST_MAP_PTR, - .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_ANYTHING, -}; - -BPF_CALL_2(bpf_msg_apply_bytes, struct sk_msg_buff *, msg, u32, bytes) +BPF_CALL_2(bpf_msg_apply_bytes, struct sk_msg *, msg, u32, bytes) { msg->apply_bytes = bytes; return 0; @@ -2272,7 +2157,7 @@ static const struct bpf_func_proto bpf_msg_apply_bytes_proto = { .arg2_type = ARG_ANYTHING, }; -BPF_CALL_2(bpf_msg_cork_bytes, struct sk_msg_buff *, msg, u32, bytes) +BPF_CALL_2(bpf_msg_cork_bytes, struct sk_msg *, msg, u32, bytes) { msg->cork_bytes = bytes; return 0; @@ -2286,45 +2171,37 @@ static const struct bpf_func_proto bpf_msg_cork_bytes_proto = { .arg2_type = ARG_ANYTHING, }; -#define sk_msg_iter_var(var) \ - do { \ - var++; \ - if (var == MAX_SKB_FRAGS) \ - var = 0; \ - } while (0) - -BPF_CALL_4(bpf_msg_pull_data, - struct sk_msg_buff *, msg, u32, start, u32, end, u64, flags) +BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start, + u32, end, u64, flags) { - unsigned int len = 0, offset = 0, copy = 0, poffset = 0; - int bytes = end - start, bytes_sg_total; - struct scatterlist *sg = msg->sg_data; - int first_sg, last_sg, i, shift; - unsigned char *p, *to, *from; + u32 len = 0, offset = 0, copy = 0, poffset = 0, bytes = end - start; + u32 first_sge, last_sge, i, shift, bytes_sg_total; + struct scatterlist *sge; + u8 *raw, *to, *from; struct page *page; if (unlikely(flags || end <= start)) return -EINVAL; /* First find the starting scatterlist element */ - i = msg->sg_start; + i = msg->sg.start; do { - len = sg[i].length; + len = sk_msg_elem(msg, i)->length; if (start < offset + len) break; offset += len; - sk_msg_iter_var(i); - } while (i != msg->sg_end); + sk_msg_iter_var_next(i); + } while (i != msg->sg.end); if (unlikely(start >= offset + len)) return -EINVAL; - first_sg = i; + first_sge = i; /* The start may point into the sg element so we need to also * account for the headroom. */ bytes_sg_total = start - offset + bytes; - if (!msg->sg_copy[i] && bytes_sg_total <= len) + if (!msg->sg.copy[i] && bytes_sg_total <= len) goto out; /* At this point we need to linearize multiple scatterlist @@ -2338,12 +2215,12 @@ BPF_CALL_4(bpf_msg_pull_data, * will copy the entire sg entry. */ do { - copy += sg[i].length; - sk_msg_iter_var(i); + copy += sk_msg_elem(msg, i)->length; + sk_msg_iter_var_next(i); if (bytes_sg_total <= copy) break; - } while (i != msg->sg_end); - last_sg = i; + } while (i != msg->sg.end); + last_sge = i; if (unlikely(bytes_sg_total > copy)) return -EINVAL; @@ -2352,63 +2229,61 @@ BPF_CALL_4(bpf_msg_pull_data, get_order(copy)); if (unlikely(!page)) return -ENOMEM; - p = page_address(page); - i = first_sg; + raw = page_address(page); + i = first_sge; do { - from = sg_virt(&sg[i]); - len = sg[i].length; - to = p + poffset; + sge = sk_msg_elem(msg, i); + from = sg_virt(sge); + len = sge->length; + to = raw + poffset; memcpy(to, from, len); poffset += len; - sg[i].length = 0; - put_page(sg_page(&sg[i])); + sge->length = 0; + put_page(sg_page(sge)); - sk_msg_iter_var(i); - } while (i != last_sg); + sk_msg_iter_var_next(i); + } while (i != last_sge); - sg[first_sg].length = copy; - sg_set_page(&sg[first_sg], page, copy, 0); + sg_set_page(&msg->sg.data[first_sge], page, copy, 0); /* To repair sg ring we need to shift entries. If we only * had a single entry though we can just replace it and * be done. Otherwise walk the ring and shift the entries. */ - WARN_ON_ONCE(last_sg == first_sg); - shift = last_sg > first_sg ? - last_sg - first_sg - 1 : - MAX_SKB_FRAGS - first_sg + last_sg - 1; + WARN_ON_ONCE(last_sge == first_sge); + shift = last_sge > first_sge ? + last_sge - first_sge - 1 : + MAX_SKB_FRAGS - first_sge + last_sge - 1; if (!shift) goto out; - i = first_sg; - sk_msg_iter_var(i); + i = first_sge; + sk_msg_iter_var_next(i); do { - int move_from; + u32 move_from; - if (i + shift >= MAX_SKB_FRAGS) - move_from = i + shift - MAX_SKB_FRAGS; + if (i + shift >= MAX_MSG_FRAGS) + move_from = i + shift - MAX_MSG_FRAGS; else move_from = i + shift; - - if (move_from == msg->sg_end) + if (move_from == msg->sg.end) break; - sg[i] = sg[move_from]; - sg[move_from].length = 0; - sg[move_from].page_link = 0; - sg[move_from].offset = 0; - - sk_msg_iter_var(i); + msg->sg.data[i] = msg->sg.data[move_from]; + msg->sg.data[move_from].length = 0; + msg->sg.data[move_from].page_link = 0; + msg->sg.data[move_from].offset = 0; + sk_msg_iter_var_next(i); } while (1); - msg->sg_end -= shift; - if (msg->sg_end < 0) - msg->sg_end += MAX_SKB_FRAGS; + + msg->sg.end = msg->sg.end - shift > msg->sg.end ? + msg->sg.end - shift + MAX_MSG_FRAGS : + msg->sg.end - shift; out: - msg->data = sg_virt(&sg[first_sg]) + start - offset; + msg->data = sg_virt(&msg->sg.data[first_sge]) + start - offset; msg->data_end = msg->data + bytes; - return 0; } @@ -5203,6 +5078,9 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) } } +const struct bpf_func_proto bpf_sock_map_update_proto __weak; +const struct bpf_func_proto bpf_sock_hash_update_proto __weak; + static const struct bpf_func_proto * sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -5226,6 +5104,9 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) } } +const struct bpf_func_proto bpf_msg_redirect_map_proto __weak; +const struct bpf_func_proto bpf_msg_redirect_hash_proto __weak; + static const struct bpf_func_proto * sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -5247,6 +5128,9 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) } } +const struct bpf_func_proto bpf_sk_redirect_map_proto __weak; +const struct bpf_func_proto bpf_sk_redirect_hash_proto __weak; + static const struct bpf_func_proto * sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -7001,22 +6885,22 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, switch (si->off) { case offsetof(struct sk_msg_md, data): - *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg_buff, data), + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg, data), si->dst_reg, si->src_reg, - offsetof(struct sk_msg_buff, data)); + offsetof(struct sk_msg, data)); break; case offsetof(struct sk_msg_md, data_end): - *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg_buff, data_end), + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg, data_end), si->dst_reg, si->src_reg, - offsetof(struct sk_msg_buff, data_end)); + offsetof(struct sk_msg, data_end)); break; case offsetof(struct sk_msg_md, family): BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_family) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( - struct sk_msg_buff, sk), + struct sk_msg, sk), si->dst_reg, si->src_reg, - offsetof(struct sk_msg_buff, sk)); + offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_family)); break; @@ -7025,9 +6909,9 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_daddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( - struct sk_msg_buff, sk), + struct sk_msg, sk), si->dst_reg, si->src_reg, - offsetof(struct sk_msg_buff, sk)); + offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_daddr)); break; @@ -7037,9 +6921,9 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, skc_rcv_saddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( - struct sk_msg_buff, sk), + struct sk_msg, sk), si->dst_reg, si->src_reg, - offsetof(struct sk_msg_buff, sk)); + offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_rcv_saddr)); @@ -7054,9 +6938,9 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, off = si->off; off -= offsetof(struct sk_msg_md, remote_ip6[0]); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( - struct sk_msg_buff, sk), + struct sk_msg, sk), si->dst_reg, si->src_reg, - offsetof(struct sk_msg_buff, sk)); + offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_v6_daddr.s6_addr32[0]) + @@ -7075,9 +6959,9 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, off = si->off; off -= offsetof(struct sk_msg_md, local_ip6[0]); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( - struct sk_msg_buff, sk), + struct sk_msg, sk), si->dst_reg, si->src_reg, - offsetof(struct sk_msg_buff, sk)); + offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) + @@ -7091,9 +6975,9 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_dport) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( - struct sk_msg_buff, sk), + struct sk_msg, sk), si->dst_reg, si->src_reg, - offsetof(struct sk_msg_buff, sk)); + offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_dport)); #ifndef __BIG_ENDIAN_BITFIELD @@ -7105,9 +6989,9 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_num) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( - struct sk_msg_buff, sk), + struct sk_msg, sk), si->dst_reg, si->src_reg, - offsetof(struct sk_msg_buff, sk)); + offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_num)); break; diff --git a/net/core/skmsg.c b/net/core/skmsg.c new file mode 100644 index 000000000000..ae2b281c9c57 --- /dev/null +++ b/net/core/skmsg.c @@ -0,0 +1,763 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2017 - 2018 Covalent IO, Inc. http://covalent.io */ + +#include +#include +#include + +#include +#include + +static bool sk_msg_try_coalesce_ok(struct sk_msg *msg, int elem_first_coalesce) +{ + if (msg->sg.end > msg->sg.start && + elem_first_coalesce < msg->sg.end) + return true; + + if (msg->sg.end < msg->sg.start && + (elem_first_coalesce > msg->sg.start || + elem_first_coalesce < msg->sg.end)) + return true; + + return false; +} + +int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len, + int elem_first_coalesce) +{ + struct page_frag *pfrag = sk_page_frag(sk); + int ret = 0; + + len -= msg->sg.size; + while (len > 0) { + struct scatterlist *sge; + u32 orig_offset; + int use, i; + + if (!sk_page_frag_refill(sk, pfrag)) + return -ENOMEM; + + orig_offset = pfrag->offset; + use = min_t(int, len, pfrag->size - orig_offset); + if (!sk_wmem_schedule(sk, use)) + return -ENOMEM; + + i = msg->sg.end; + sk_msg_iter_var_prev(i); + sge = &msg->sg.data[i]; + + if (sk_msg_try_coalesce_ok(msg, elem_first_coalesce) && + sg_page(sge) == pfrag->page && + sge->offset + sge->length == orig_offset) { + sge->length += use; + } else { + if (sk_msg_full(msg)) { + ret = -ENOSPC; + break; + } + + sge = &msg->sg.data[msg->sg.end]; + sg_unmark_end(sge); + sg_set_page(sge, pfrag->page, use, orig_offset); + get_page(pfrag->page); + sk_msg_iter_next(msg, end); + } + + sk_mem_charge(sk, use); + msg->sg.size += use; + pfrag->offset += use; + len -= use; + } + + return ret; +} +EXPORT_SYMBOL_GPL(sk_msg_alloc); + +void sk_msg_return_zero(struct sock *sk, struct sk_msg *msg, int bytes) +{ + int i = msg->sg.start; + + do { + struct scatterlist *sge = sk_msg_elem(msg, i); + + if (bytes < sge->length) { + sge->length -= bytes; + sge->offset += bytes; + sk_mem_uncharge(sk, bytes); + break; + } + + sk_mem_uncharge(sk, sge->length); + bytes -= sge->length; + sge->length = 0; + sge->offset = 0; + sk_msg_iter_var_next(i); + } while (bytes && i != msg->sg.end); + msg->sg.start = i; +} +EXPORT_SYMBOL_GPL(sk_msg_return_zero); + +void sk_msg_return(struct sock *sk, struct sk_msg *msg, int bytes) +{ + int i = msg->sg.start; + + do { + struct scatterlist *sge = &msg->sg.data[i]; + int uncharge = (bytes < sge->length) ? bytes : sge->length; + + sk_mem_uncharge(sk, uncharge); + bytes -= uncharge; + sk_msg_iter_var_next(i); + } while (i != msg->sg.end); +} +EXPORT_SYMBOL_GPL(sk_msg_return); + +static int sk_msg_free_elem(struct sock *sk, struct sk_msg *msg, u32 i, + bool charge) +{ + struct scatterlist *sge = sk_msg_elem(msg, i); + u32 len = sge->length; + + if (charge) + sk_mem_uncharge(sk, len); + if (!msg->skb) + put_page(sg_page(sge)); + memset(sge, 0, sizeof(*sge)); + return len; +} + +static int __sk_msg_free(struct sock *sk, struct sk_msg *msg, u32 i, + bool charge) +{ + struct scatterlist *sge = sk_msg_elem(msg, i); + int freed = 0; + + while (msg->sg.size) { + msg->sg.size -= sge->length; + freed += sk_msg_free_elem(sk, msg, i, charge); + sk_msg_iter_var_next(i); + sk_msg_check_to_free(msg, i, msg->sg.size); + sge = sk_msg_elem(msg, i); + } + if (msg->skb) + consume_skb(msg->skb); + sk_msg_init(msg); + return freed; +} + +int sk_msg_free_nocharge(struct sock *sk, struct sk_msg *msg) +{ + return __sk_msg_free(sk, msg, msg->sg.start, false); +} +EXPORT_SYMBOL_GPL(sk_msg_free_nocharge); + +int sk_msg_free(struct sock *sk, struct sk_msg *msg) +{ + return __sk_msg_free(sk, msg, msg->sg.start, true); +} +EXPORT_SYMBOL_GPL(sk_msg_free); + +static void __sk_msg_free_partial(struct sock *sk, struct sk_msg *msg, + u32 bytes, bool charge) +{ + struct scatterlist *sge; + u32 i = msg->sg.start; + + while (bytes) { + sge = sk_msg_elem(msg, i); + if (!sge->length) + break; + if (bytes < sge->length) { + if (charge) + sk_mem_uncharge(sk, bytes); + sge->length -= bytes; + sge->offset += bytes; + msg->sg.size -= bytes; + break; + } + + msg->sg.size -= sge->length; + bytes -= sge->length; + sk_msg_free_elem(sk, msg, i, charge); + sk_msg_iter_var_next(i); + sk_msg_check_to_free(msg, i, bytes); + } + msg->sg.start = i; +} + +void sk_msg_free_partial(struct sock *sk, struct sk_msg *msg, u32 bytes) +{ + __sk_msg_free_partial(sk, msg, bytes, true); +} +EXPORT_SYMBOL_GPL(sk_msg_free_partial); + +void sk_msg_free_partial_nocharge(struct sock *sk, struct sk_msg *msg, + u32 bytes) +{ + __sk_msg_free_partial(sk, msg, bytes, false); +} + +void sk_msg_trim(struct sock *sk, struct sk_msg *msg, int len) +{ + int trim = msg->sg.size - len; + u32 i = msg->sg.end; + + if (trim <= 0) { + WARN_ON(trim < 0); + return; + } + + sk_msg_iter_var_prev(i); + msg->sg.size = len; + while (msg->sg.data[i].length && + trim >= msg->sg.data[i].length) { + trim -= msg->sg.data[i].length; + sk_msg_free_elem(sk, msg, i, true); + sk_msg_iter_var_prev(i); + if (!trim) + goto out; + } + + msg->sg.data[i].length -= trim; + sk_mem_uncharge(sk, trim); +out: + /* If we trim data before curr pointer update copybreak and current + * so that any future copy operations start at new copy location. + * However trimed data that has not yet been used in a copy op + * does not require an update. + */ + if (msg->sg.curr >= i) { + msg->sg.curr = i; + msg->sg.copybreak = msg->sg.data[i].length; + } + sk_msg_iter_var_next(i); + msg->sg.end = i; +} +EXPORT_SYMBOL_GPL(sk_msg_trim); + +int sk_msg_zerocopy_from_iter(struct sock *sk, struct iov_iter *from, + struct sk_msg *msg, u32 bytes) +{ + int i, maxpages, ret = 0, num_elems = sk_msg_elem_used(msg); + const int to_max_pages = MAX_MSG_FRAGS; + struct page *pages[MAX_MSG_FRAGS]; + ssize_t orig, copied, use, offset; + + orig = msg->sg.size; + while (bytes > 0) { + i = 0; + maxpages = to_max_pages - num_elems; + if (maxpages == 0) { + ret = -EFAULT; + goto out; + } + + copied = iov_iter_get_pages(from, pages, bytes, maxpages, + &offset); + if (copied <= 0) { + ret = -EFAULT; + goto out; + } + + iov_iter_advance(from, copied); + bytes -= copied; + msg->sg.size += copied; + + while (copied) { + use = min_t(int, copied, PAGE_SIZE - offset); + sg_set_page(&msg->sg.data[msg->sg.end], + pages[i], use, offset); + sg_unmark_end(&msg->sg.data[msg->sg.end]); + sk_mem_charge(sk, use); + + offset = 0; + copied -= use; + sk_msg_iter_next(msg, end); + num_elems++; + i++; + } + /* When zerocopy is mixed with sk_msg_*copy* operations we + * may have a copybreak set in this case clear and prefer + * zerocopy remainder when possible. + */ + msg->sg.copybreak = 0; + msg->sg.curr = msg->sg.end; + } +out: + /* Revert iov_iter updates, msg will need to use 'trim' later if it + * also needs to be cleared. + */ + if (ret) + iov_iter_revert(from, msg->sg.size - orig); + return ret; +} +EXPORT_SYMBOL_GPL(sk_msg_zerocopy_from_iter); + +int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from, + struct sk_msg *msg, u32 bytes) +{ + int ret = -ENOSPC, i = msg->sg.curr; + struct scatterlist *sge; + u32 copy, buf_size; + void *to; + + do { + sge = sk_msg_elem(msg, i); + /* This is possible if a trim operation shrunk the buffer */ + if (msg->sg.copybreak >= sge->length) { + msg->sg.copybreak = 0; + sk_msg_iter_var_next(i); + if (i == msg->sg.end) + break; + sge = sk_msg_elem(msg, i); + } + + buf_size = sge->length - msg->sg.copybreak; + copy = (buf_size > bytes) ? bytes : buf_size; + to = sg_virt(sge) + msg->sg.copybreak; + msg->sg.copybreak += copy; + if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY) + ret = copy_from_iter_nocache(to, copy, from); + else + ret = copy_from_iter(to, copy, from); + if (ret != copy) { + ret = -EFAULT; + goto out; + } + bytes -= copy; + if (!bytes) + break; + msg->sg.copybreak = 0; + sk_msg_iter_var_next(i); + } while (i != msg->sg.end); +out: + msg->sg.curr = i; + return ret; +} +EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter); + +static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) +{ + struct sock *sk = psock->sk; + int copied = 0, num_sge; + struct sk_msg *msg; + + msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC); + if (unlikely(!msg)) + return -EAGAIN; + if (!sk_rmem_schedule(sk, skb, skb->len)) { + kfree(msg); + return -EAGAIN; + } + + sk_msg_init(msg); + num_sge = skb_to_sgvec(skb, msg->sg.data, 0, skb->len); + if (unlikely(num_sge < 0)) { + kfree(msg); + return num_sge; + } + + sk_mem_charge(sk, skb->len); + copied = skb->len; + msg->sg.start = 0; + msg->sg.end = num_sge == MAX_MSG_FRAGS ? 0 : num_sge; + msg->skb = skb; + + sk_psock_queue_msg(psock, msg); + sk->sk_data_ready(sk); + return copied; +} + +static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb, + u32 off, u32 len, bool ingress) +{ + if (ingress) + return sk_psock_skb_ingress(psock, skb); + else + return skb_send_sock_locked(psock->sk, skb, off, len); +} + +static void sk_psock_backlog(struct work_struct *work) +{ + struct sk_psock *psock = container_of(work, struct sk_psock, work); + struct sk_psock_work_state *state = &psock->work_state; + struct sk_buff *skb; + bool ingress; + u32 len, off; + int ret; + + /* Lock sock to avoid losing sk_socket during loop. */ + lock_sock(psock->sk); + if (state->skb) { + skb = state->skb; + len = state->len; + off = state->off; + state->skb = NULL; + goto start; + } + + while ((skb = skb_dequeue(&psock->ingress_skb))) { + len = skb->len; + off = 0; +start: + ingress = tcp_skb_bpf_ingress(skb); + do { + ret = -EIO; + if (likely(psock->sk->sk_socket)) + ret = sk_psock_handle_skb(psock, skb, off, + len, ingress); + if (ret <= 0) { + if (ret == -EAGAIN) { + state->skb = skb; + state->len = len; + state->off = off; + goto end; + } + /* Hard errors break pipe and stop xmit. */ + sk_psock_report_error(psock, ret ? -ret : EPIPE); + sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED); + kfree_skb(skb); + goto end; + } + off += ret; + len -= ret; + } while (len); + + if (!ingress) + kfree_skb(skb); + } +end: + release_sock(psock->sk); +} + +struct sk_psock *sk_psock_init(struct sock *sk, int node) +{ + struct sk_psock *psock = kzalloc_node(sizeof(*psock), + GFP_ATOMIC | __GFP_NOWARN, + node); + if (!psock) + return NULL; + + psock->sk = sk; + psock->eval = __SK_NONE; + + INIT_LIST_HEAD(&psock->link); + spin_lock_init(&psock->link_lock); + + INIT_WORK(&psock->work, sk_psock_backlog); + INIT_LIST_HEAD(&psock->ingress_msg); + skb_queue_head_init(&psock->ingress_skb); + + sk_psock_set_state(psock, SK_PSOCK_TX_ENABLED); + refcount_set(&psock->refcnt, 1); + + rcu_assign_sk_user_data(sk, psock); + sock_hold(sk); + + return psock; +} +EXPORT_SYMBOL_GPL(sk_psock_init); + +struct sk_psock_link *sk_psock_link_pop(struct sk_psock *psock) +{ + struct sk_psock_link *link; + + spin_lock_bh(&psock->link_lock); + link = list_first_entry_or_null(&psock->link, struct sk_psock_link, + list); + if (link) + list_del(&link->list); + spin_unlock_bh(&psock->link_lock); + return link; +} + +void __sk_psock_purge_ingress_msg(struct sk_psock *psock) +{ + struct sk_msg *msg, *tmp; + + list_for_each_entry_safe(msg, tmp, &psock->ingress_msg, list) { + list_del(&msg->list); + sk_msg_free(psock->sk, msg); + kfree(msg); + } +} + +static void sk_psock_zap_ingress(struct sk_psock *psock) +{ + __skb_queue_purge(&psock->ingress_skb); + __sk_psock_purge_ingress_msg(psock); +} + +static void sk_psock_link_destroy(struct sk_psock *psock) +{ + struct sk_psock_link *link, *tmp; + + list_for_each_entry_safe(link, tmp, &psock->link, list) { + list_del(&link->list); + sk_psock_free_link(link); + } +} + +static void sk_psock_destroy_deferred(struct work_struct *gc) +{ + struct sk_psock *psock = container_of(gc, struct sk_psock, gc); + + /* No sk_callback_lock since already detached. */ + if (psock->parser.enabled) + strp_done(&psock->parser.strp); + + cancel_work_sync(&psock->work); + + psock_progs_drop(&psock->progs); + + sk_psock_link_destroy(psock); + sk_psock_cork_free(psock); + sk_psock_zap_ingress(psock); + + if (psock->sk_redir) + sock_put(psock->sk_redir); + sock_put(psock->sk); + kfree(psock); +} + +void sk_psock_destroy(struct rcu_head *rcu) +{ + struct sk_psock *psock = container_of(rcu, struct sk_psock, rcu); + + INIT_WORK(&psock->gc, sk_psock_destroy_deferred); + schedule_work(&psock->gc); +} +EXPORT_SYMBOL_GPL(sk_psock_destroy); + +void sk_psock_drop(struct sock *sk, struct sk_psock *psock) +{ + rcu_assign_sk_user_data(sk, NULL); + sk_psock_cork_free(psock); + sk_psock_restore_proto(sk, psock); + + write_lock_bh(&sk->sk_callback_lock); + if (psock->progs.skb_parser) + sk_psock_stop_strp(sk, psock); + write_unlock_bh(&sk->sk_callback_lock); + sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED); + + call_rcu_sched(&psock->rcu, sk_psock_destroy); +} +EXPORT_SYMBOL_GPL(sk_psock_drop); + +static int sk_psock_map_verd(int verdict, bool redir) +{ + switch (verdict) { + case SK_PASS: + return redir ? __SK_REDIRECT : __SK_PASS; + case SK_DROP: + default: + break; + } + + return __SK_DROP; +} + +int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock, + struct sk_msg *msg) +{ + struct bpf_prog *prog; + int ret; + + preempt_disable(); + rcu_read_lock(); + prog = READ_ONCE(psock->progs.msg_parser); + if (unlikely(!prog)) { + ret = __SK_PASS; + goto out; + } + + sk_msg_compute_data_pointers(msg); + msg->sk = sk; + ret = BPF_PROG_RUN(prog, msg); + ret = sk_psock_map_verd(ret, msg->sk_redir); + psock->apply_bytes = msg->apply_bytes; + if (ret == __SK_REDIRECT) { + if (psock->sk_redir) + sock_put(psock->sk_redir); + psock->sk_redir = msg->sk_redir; + if (!psock->sk_redir) { + ret = __SK_DROP; + goto out; + } + sock_hold(psock->sk_redir); + } +out: + rcu_read_unlock(); + preempt_enable(); + return ret; +} +EXPORT_SYMBOL_GPL(sk_psock_msg_verdict); + +static int sk_psock_bpf_run(struct sk_psock *psock, struct bpf_prog *prog, + struct sk_buff *skb) +{ + int ret; + + skb->sk = psock->sk; + bpf_compute_data_end_sk_skb(skb); + preempt_disable(); + ret = BPF_PROG_RUN(prog, skb); + preempt_enable(); + /* strparser clones the skb before handing it to a upper layer, + * meaning skb_orphan has been called. We NULL sk on the way out + * to ensure we don't trigger a BUG_ON() in skb/sk operations + * later and because we are not charging the memory of this skb + * to any socket yet. + */ + skb->sk = NULL; + return ret; +} + +static struct sk_psock *sk_psock_from_strp(struct strparser *strp) +{ + struct sk_psock_parser *parser; + + parser = container_of(strp, struct sk_psock_parser, strp); + return container_of(parser, struct sk_psock, parser); +} + +static void sk_psock_verdict_apply(struct sk_psock *psock, + struct sk_buff *skb, int verdict) +{ + struct sk_psock *psock_other; + struct sock *sk_other; + bool ingress; + + switch (verdict) { + case __SK_REDIRECT: + sk_other = tcp_skb_bpf_redirect_fetch(skb); + if (unlikely(!sk_other)) + goto out_free; + psock_other = sk_psock(sk_other); + if (!psock_other || sock_flag(sk_other, SOCK_DEAD) || + !sk_psock_test_state(psock_other, SK_PSOCK_TX_ENABLED)) + goto out_free; + ingress = tcp_skb_bpf_ingress(skb); + if ((!ingress && sock_writeable(sk_other)) || + (ingress && + atomic_read(&sk_other->sk_rmem_alloc) <= + sk_other->sk_rcvbuf)) { + if (!ingress) + skb_set_owner_w(skb, sk_other); + skb_queue_tail(&psock_other->ingress_skb, skb); + schedule_work(&psock_other->work); + break; + } + /* fall-through */ + case __SK_DROP: + /* fall-through */ + default: +out_free: + kfree_skb(skb); + } +} + +static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) +{ + struct sk_psock *psock = sk_psock_from_strp(strp); + struct bpf_prog *prog; + int ret = __SK_DROP; + + rcu_read_lock(); + prog = READ_ONCE(psock->progs.skb_verdict); + if (likely(prog)) { + skb_orphan(skb); + tcp_skb_bpf_redirect_clear(skb); + ret = sk_psock_bpf_run(psock, prog, skb); + ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb)); + } + rcu_read_unlock(); + sk_psock_verdict_apply(psock, skb, ret); +} + +static int sk_psock_strp_read_done(struct strparser *strp, int err) +{ + return err; +} + +static int sk_psock_strp_parse(struct strparser *strp, struct sk_buff *skb) +{ + struct sk_psock *psock = sk_psock_from_strp(strp); + struct bpf_prog *prog; + int ret = skb->len; + + rcu_read_lock(); + prog = READ_ONCE(psock->progs.skb_parser); + if (likely(prog)) + ret = sk_psock_bpf_run(psock, prog, skb); + rcu_read_unlock(); + return ret; +} + +/* Called with socket lock held. */ +static void sk_psock_data_ready(struct sock *sk) +{ + struct sk_psock *psock; + + rcu_read_lock(); + psock = sk_psock(sk); + if (likely(psock)) { + write_lock_bh(&sk->sk_callback_lock); + strp_data_ready(&psock->parser.strp); + write_unlock_bh(&sk->sk_callback_lock); + } + rcu_read_unlock(); +} + +static void sk_psock_write_space(struct sock *sk) +{ + struct sk_psock *psock; + void (*write_space)(struct sock *sk); + + rcu_read_lock(); + psock = sk_psock(sk); + if (likely(psock && sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED))) + schedule_work(&psock->work); + write_space = psock->saved_write_space; + rcu_read_unlock(); + write_space(sk); +} + +int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock) +{ + static const struct strp_callbacks cb = { + .rcv_msg = sk_psock_strp_read, + .read_sock_done = sk_psock_strp_read_done, + .parse_msg = sk_psock_strp_parse, + }; + + psock->parser.enabled = false; + return strp_init(&psock->parser.strp, sk, &cb); +} + +void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock) +{ + struct sk_psock_parser *parser = &psock->parser; + + if (parser->enabled) + return; + + parser->saved_data_ready = sk->sk_data_ready; + sk->sk_data_ready = sk_psock_data_ready; + sk->sk_write_space = sk_psock_write_space; + parser->enabled = true; +} + +void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock) +{ + struct sk_psock_parser *parser = &psock->parser; + + if (!parser->enabled) + return; + + sk->sk_data_ready = parser->saved_data_ready; + parser->saved_data_ready = NULL; + strp_stop(&parser->strp); + parser->enabled = false; +} diff --git a/net/core/sock_map.c b/net/core/sock_map.c new file mode 100644 index 000000000000..3c0e44cb811a --- /dev/null +++ b/net/core/sock_map.c @@ -0,0 +1,1002 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2017 - 2018 Covalent IO, Inc. http://covalent.io */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct bpf_stab { + struct bpf_map map; + struct sock **sks; + struct sk_psock_progs progs; + raw_spinlock_t lock; +}; + +#define SOCK_CREATE_FLAG_MASK \ + (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) + +static struct bpf_map *sock_map_alloc(union bpf_attr *attr) +{ + struct bpf_stab *stab; + u64 cost; + int err; + + if (!capable(CAP_NET_ADMIN)) + return ERR_PTR(-EPERM); + if (attr->max_entries == 0 || + attr->key_size != 4 || + attr->value_size != 4 || + attr->map_flags & ~SOCK_CREATE_FLAG_MASK) + return ERR_PTR(-EINVAL); + + stab = kzalloc(sizeof(*stab), GFP_USER); + if (!stab) + return ERR_PTR(-ENOMEM); + + bpf_map_init_from_attr(&stab->map, attr); + raw_spin_lock_init(&stab->lock); + + /* Make sure page count doesn't overflow. */ + cost = (u64) stab->map.max_entries * sizeof(struct sock *); + if (cost >= U32_MAX - PAGE_SIZE) { + err = -EINVAL; + goto free_stab; + } + + stab->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + err = bpf_map_precharge_memlock(stab->map.pages); + if (err) + goto free_stab; + + stab->sks = bpf_map_area_alloc(stab->map.max_entries * + sizeof(struct sock *), + stab->map.numa_node); + if (stab->sks) + return &stab->map; + err = -ENOMEM; +free_stab: + kfree(stab); + return ERR_PTR(err); +} + +int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog) +{ + u32 ufd = attr->target_fd; + struct bpf_map *map; + struct fd f; + int ret; + + f = fdget(ufd); + map = __bpf_map_get(f); + if (IS_ERR(map)) + return PTR_ERR(map); + ret = sock_map_prog_update(map, prog, attr->attach_type); + fdput(f); + return ret; +} + +static void sock_map_sk_acquire(struct sock *sk) + __acquires(&sk->sk_lock.slock) +{ + lock_sock(sk); + preempt_disable(); + rcu_read_lock(); +} + +static void sock_map_sk_release(struct sock *sk) + __releases(&sk->sk_lock.slock) +{ + rcu_read_unlock(); + preempt_enable(); + release_sock(sk); +} + +static void sock_map_add_link(struct sk_psock *psock, + struct sk_psock_link *link, + struct bpf_map *map, void *link_raw) +{ + link->link_raw = link_raw; + link->map = map; + spin_lock_bh(&psock->link_lock); + list_add_tail(&link->list, &psock->link); + spin_unlock_bh(&psock->link_lock); +} + +static void sock_map_del_link(struct sock *sk, + struct sk_psock *psock, void *link_raw) +{ + struct sk_psock_link *link, *tmp; + bool strp_stop = false; + + spin_lock_bh(&psock->link_lock); + list_for_each_entry_safe(link, tmp, &psock->link, list) { + if (link->link_raw == link_raw) { + struct bpf_map *map = link->map; + struct bpf_stab *stab = container_of(map, struct bpf_stab, + map); + if (psock->parser.enabled && stab->progs.skb_parser) + strp_stop = true; + list_del(&link->list); + sk_psock_free_link(link); + } + } + spin_unlock_bh(&psock->link_lock); + if (strp_stop) { + write_lock_bh(&sk->sk_callback_lock); + sk_psock_stop_strp(sk, psock); + write_unlock_bh(&sk->sk_callback_lock); + } +} + +static void sock_map_unref(struct sock *sk, void *link_raw) +{ + struct sk_psock *psock = sk_psock(sk); + + if (likely(psock)) { + sock_map_del_link(sk, psock, link_raw); + sk_psock_put(sk, psock); + } +} + +static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs, + struct sock *sk) +{ + struct bpf_prog *msg_parser, *skb_parser, *skb_verdict; + bool skb_progs, sk_psock_is_new = false; + struct sk_psock *psock; + int ret; + + skb_verdict = READ_ONCE(progs->skb_verdict); + skb_parser = READ_ONCE(progs->skb_parser); + skb_progs = skb_parser && skb_verdict; + if (skb_progs) { + skb_verdict = bpf_prog_inc_not_zero(skb_verdict); + if (IS_ERR(skb_verdict)) + return PTR_ERR(skb_verdict); + skb_parser = bpf_prog_inc_not_zero(skb_parser); + if (IS_ERR(skb_parser)) { + bpf_prog_put(skb_verdict); + return PTR_ERR(skb_parser); + } + } + + msg_parser = READ_ONCE(progs->msg_parser); + if (msg_parser) { + msg_parser = bpf_prog_inc_not_zero(msg_parser); + if (IS_ERR(msg_parser)) { + ret = PTR_ERR(msg_parser); + goto out; + } + } + + psock = sk_psock_get(sk); + if (psock) { + if (!sk_has_psock(sk)) { + ret = -EBUSY; + goto out_progs; + } + if ((msg_parser && READ_ONCE(psock->progs.msg_parser)) || + (skb_progs && READ_ONCE(psock->progs.skb_parser))) { + sk_psock_put(sk, psock); + ret = -EBUSY; + goto out_progs; + } + } else { + psock = sk_psock_init(sk, map->numa_node); + if (!psock) { + ret = -ENOMEM; + goto out_progs; + } + sk_psock_is_new = true; + } + + if (msg_parser) + psock_set_prog(&psock->progs.msg_parser, msg_parser); + if (sk_psock_is_new) { + ret = tcp_bpf_init(sk); + if (ret < 0) + goto out_drop; + } else { + tcp_bpf_reinit(sk); + } + + write_lock_bh(&sk->sk_callback_lock); + if (skb_progs && !psock->parser.enabled) { + ret = sk_psock_init_strp(sk, psock); + if (ret) { + write_unlock_bh(&sk->sk_callback_lock); + goto out_drop; + } + psock_set_prog(&psock->progs.skb_verdict, skb_verdict); + psock_set_prog(&psock->progs.skb_parser, skb_parser); + sk_psock_start_strp(sk, psock); + } + write_unlock_bh(&sk->sk_callback_lock); + return 0; +out_drop: + sk_psock_put(sk, psock); +out_progs: + if (msg_parser) + bpf_prog_put(msg_parser); +out: + if (skb_progs) { + bpf_prog_put(skb_verdict); + bpf_prog_put(skb_parser); + } + return ret; +} + +static void sock_map_free(struct bpf_map *map) +{ + struct bpf_stab *stab = container_of(map, struct bpf_stab, map); + int i; + + synchronize_rcu(); + rcu_read_lock(); + raw_spin_lock_bh(&stab->lock); + for (i = 0; i < stab->map.max_entries; i++) { + struct sock **psk = &stab->sks[i]; + struct sock *sk; + + sk = xchg(psk, NULL); + if (sk) + sock_map_unref(sk, psk); + } + raw_spin_unlock_bh(&stab->lock); + rcu_read_unlock(); + + bpf_map_area_free(stab->sks); + kfree(stab); +} + +static void sock_map_release_progs(struct bpf_map *map) +{ + psock_progs_drop(&container_of(map, struct bpf_stab, map)->progs); +} + +static struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key) +{ + struct bpf_stab *stab = container_of(map, struct bpf_stab, map); + + WARN_ON_ONCE(!rcu_read_lock_held()); + + if (unlikely(key >= map->max_entries)) + return NULL; + return READ_ONCE(stab->sks[key]); +} + +static void *sock_map_lookup(struct bpf_map *map, void *key) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test, + struct sock **psk) +{ + struct sock *sk; + + raw_spin_lock_bh(&stab->lock); + sk = *psk; + if (!sk_test || sk_test == sk) + *psk = NULL; + raw_spin_unlock_bh(&stab->lock); + if (unlikely(!sk)) + return -EINVAL; + sock_map_unref(sk, psk); + return 0; +} + +static void sock_map_delete_from_link(struct bpf_map *map, struct sock *sk, + void *link_raw) +{ + struct bpf_stab *stab = container_of(map, struct bpf_stab, map); + + __sock_map_delete(stab, sk, link_raw); +} + +static int sock_map_delete_elem(struct bpf_map *map, void *key) +{ + struct bpf_stab *stab = container_of(map, struct bpf_stab, map); + u32 i = *(u32 *)key; + struct sock **psk; + + if (unlikely(i >= map->max_entries)) + return -EINVAL; + + psk = &stab->sks[i]; + return __sock_map_delete(stab, NULL, psk); +} + +static int sock_map_get_next_key(struct bpf_map *map, void *key, void *next) +{ + struct bpf_stab *stab = container_of(map, struct bpf_stab, map); + u32 i = key ? *(u32 *)key : U32_MAX; + u32 *key_next = next; + + if (i == stab->map.max_entries - 1) + return -ENOENT; + if (i >= stab->map.max_entries) + *key_next = 0; + else + *key_next = i + 1; + return 0; +} + +static int sock_map_update_common(struct bpf_map *map, u32 idx, + struct sock *sk, u64 flags) +{ + struct bpf_stab *stab = container_of(map, struct bpf_stab, map); + struct sk_psock_link *link; + struct sk_psock *psock; + struct sock *osk; + int ret; + + WARN_ON_ONCE(!rcu_read_lock_held()); + if (unlikely(flags > BPF_EXIST)) + return -EINVAL; + if (unlikely(idx >= map->max_entries)) + return -E2BIG; + + link = sk_psock_init_link(); + if (!link) + return -ENOMEM; + + ret = sock_map_link(map, &stab->progs, sk); + if (ret < 0) + goto out_free; + + psock = sk_psock(sk); + WARN_ON_ONCE(!psock); + + raw_spin_lock_bh(&stab->lock); + osk = stab->sks[idx]; + if (osk && flags == BPF_NOEXIST) { + ret = -EEXIST; + goto out_unlock; + } else if (!osk && flags == BPF_EXIST) { + ret = -ENOENT; + goto out_unlock; + } + + sock_map_add_link(psock, link, map, &stab->sks[idx]); + stab->sks[idx] = sk; + if (osk) + sock_map_unref(osk, &stab->sks[idx]); + raw_spin_unlock_bh(&stab->lock); + return 0; +out_unlock: + raw_spin_unlock_bh(&stab->lock); + if (psock) + sk_psock_put(sk, psock); +out_free: + sk_psock_free_link(link); + return ret; +} + +static bool sock_map_op_okay(const struct bpf_sock_ops_kern *ops) +{ + return ops->op == BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB || + ops->op == BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB; +} + +static bool sock_map_sk_is_suitable(const struct sock *sk) +{ + return sk->sk_type == SOCK_STREAM && + sk->sk_protocol == IPPROTO_TCP; +} + +static int sock_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 flags) +{ + u32 ufd = *(u32 *)value; + u32 idx = *(u32 *)key; + struct socket *sock; + struct sock *sk; + int ret; + + sock = sockfd_lookup(ufd, &ret); + if (!sock) + return ret; + sk = sock->sk; + if (!sk) { + ret = -EINVAL; + goto out; + } + if (!sock_map_sk_is_suitable(sk) || + sk->sk_state != TCP_ESTABLISHED) { + ret = -EOPNOTSUPP; + goto out; + } + + sock_map_sk_acquire(sk); + ret = sock_map_update_common(map, idx, sk, flags); + sock_map_sk_release(sk); +out: + fput(sock->file); + return ret; +} + +BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, sops, + struct bpf_map *, map, void *, key, u64, flags) +{ + WARN_ON_ONCE(!rcu_read_lock_held()); + + if (likely(sock_map_sk_is_suitable(sops->sk) && + sock_map_op_okay(sops))) + return sock_map_update_common(map, *(u32 *)key, sops->sk, + flags); + return -EOPNOTSUPP; +} + +const struct bpf_func_proto bpf_sock_map_update_proto = { + .func = bpf_sock_map_update, + .gpl_only = false, + .pkt_access = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_CONST_MAP_PTR, + .arg3_type = ARG_PTR_TO_MAP_KEY, + .arg4_type = ARG_ANYTHING, +}; + +BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb, + struct bpf_map *, map, u32, key, u64, flags) +{ + struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); + + if (unlikely(flags & ~(BPF_F_INGRESS))) + return SK_DROP; + tcb->bpf.flags = flags; + tcb->bpf.sk_redir = __sock_map_lookup_elem(map, key); + if (!tcb->bpf.sk_redir) + return SK_DROP; + return SK_PASS; +} + +const struct bpf_func_proto bpf_sk_redirect_map_proto = { + .func = bpf_sk_redirect_map, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_CONST_MAP_PTR, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_ANYTHING, +}; + +BPF_CALL_4(bpf_msg_redirect_map, struct sk_msg *, msg, + struct bpf_map *, map, u32, key, u64, flags) +{ + if (unlikely(flags & ~(BPF_F_INGRESS))) + return SK_DROP; + msg->flags = flags; + msg->sk_redir = __sock_map_lookup_elem(map, key); + if (!msg->sk_redir) + return SK_DROP; + return SK_PASS; +} + +const struct bpf_func_proto bpf_msg_redirect_map_proto = { + .func = bpf_msg_redirect_map, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_CONST_MAP_PTR, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_ANYTHING, +}; + +const struct bpf_map_ops sock_map_ops = { + .map_alloc = sock_map_alloc, + .map_free = sock_map_free, + .map_get_next_key = sock_map_get_next_key, + .map_update_elem = sock_map_update_elem, + .map_delete_elem = sock_map_delete_elem, + .map_lookup_elem = sock_map_lookup, + .map_release_uref = sock_map_release_progs, + .map_check_btf = map_check_no_btf, +}; + +struct bpf_htab_elem { + struct rcu_head rcu; + u32 hash; + struct sock *sk; + struct hlist_node node; + u8 key[0]; +}; + +struct bpf_htab_bucket { + struct hlist_head head; + raw_spinlock_t lock; +}; + +struct bpf_htab { + struct bpf_map map; + struct bpf_htab_bucket *buckets; + u32 buckets_num; + u32 elem_size; + struct sk_psock_progs progs; + atomic_t count; +}; + +static inline u32 sock_hash_bucket_hash(const void *key, u32 len) +{ + return jhash(key, len, 0); +} + +static struct bpf_htab_bucket *sock_hash_select_bucket(struct bpf_htab *htab, + u32 hash) +{ + return &htab->buckets[hash & (htab->buckets_num - 1)]; +} + +static struct bpf_htab_elem * +sock_hash_lookup_elem_raw(struct hlist_head *head, u32 hash, void *key, + u32 key_size) +{ + struct bpf_htab_elem *elem; + + hlist_for_each_entry_rcu(elem, head, node) { + if (elem->hash == hash && + !memcmp(&elem->key, key, key_size)) + return elem; + } + + return NULL; +} + +static struct sock *__sock_hash_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + u32 key_size = map->key_size, hash; + struct bpf_htab_bucket *bucket; + struct bpf_htab_elem *elem; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + hash = sock_hash_bucket_hash(key, key_size); + bucket = sock_hash_select_bucket(htab, hash); + elem = sock_hash_lookup_elem_raw(&bucket->head, hash, key, key_size); + + return elem ? elem->sk : NULL; +} + +static void sock_hash_free_elem(struct bpf_htab *htab, + struct bpf_htab_elem *elem) +{ + atomic_dec(&htab->count); + kfree_rcu(elem, rcu); +} + +static void sock_hash_delete_from_link(struct bpf_map *map, struct sock *sk, + void *link_raw) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + struct bpf_htab_elem *elem_probe, *elem = link_raw; + struct bpf_htab_bucket *bucket; + + WARN_ON_ONCE(!rcu_read_lock_held()); + bucket = sock_hash_select_bucket(htab, elem->hash); + + /* elem may be deleted in parallel from the map, but access here + * is okay since it's going away only after RCU grace period. + * However, we need to check whether it's still present. + */ + raw_spin_lock_bh(&bucket->lock); + elem_probe = sock_hash_lookup_elem_raw(&bucket->head, elem->hash, + elem->key, map->key_size); + if (elem_probe && elem_probe == elem) { + hlist_del_rcu(&elem->node); + sock_map_unref(elem->sk, elem); + sock_hash_free_elem(htab, elem); + } + raw_spin_unlock_bh(&bucket->lock); +} + +static int sock_hash_delete_elem(struct bpf_map *map, void *key) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + u32 hash, key_size = map->key_size; + struct bpf_htab_bucket *bucket; + struct bpf_htab_elem *elem; + int ret = -ENOENT; + + hash = sock_hash_bucket_hash(key, key_size); + bucket = sock_hash_select_bucket(htab, hash); + + raw_spin_lock_bh(&bucket->lock); + elem = sock_hash_lookup_elem_raw(&bucket->head, hash, key, key_size); + if (elem) { + hlist_del_rcu(&elem->node); + sock_map_unref(elem->sk, elem); + sock_hash_free_elem(htab, elem); + ret = 0; + } + raw_spin_unlock_bh(&bucket->lock); + return ret; +} + +static struct bpf_htab_elem *sock_hash_alloc_elem(struct bpf_htab *htab, + void *key, u32 key_size, + u32 hash, struct sock *sk, + struct bpf_htab_elem *old) +{ + struct bpf_htab_elem *new; + + if (atomic_inc_return(&htab->count) > htab->map.max_entries) { + if (!old) { + atomic_dec(&htab->count); + return ERR_PTR(-E2BIG); + } + } + + new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN, + htab->map.numa_node); + if (!new) { + atomic_dec(&htab->count); + return ERR_PTR(-ENOMEM); + } + memcpy(new->key, key, key_size); + new->sk = sk; + new->hash = hash; + return new; +} + +static int sock_hash_update_common(struct bpf_map *map, void *key, + struct sock *sk, u64 flags) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + u32 key_size = map->key_size, hash; + struct bpf_htab_elem *elem, *elem_new; + struct bpf_htab_bucket *bucket; + struct sk_psock_link *link; + struct sk_psock *psock; + int ret; + + WARN_ON_ONCE(!rcu_read_lock_held()); + if (unlikely(flags > BPF_EXIST)) + return -EINVAL; + + link = sk_psock_init_link(); + if (!link) + return -ENOMEM; + + ret = sock_map_link(map, &htab->progs, sk); + if (ret < 0) + goto out_free; + + psock = sk_psock(sk); + WARN_ON_ONCE(!psock); + + hash = sock_hash_bucket_hash(key, key_size); + bucket = sock_hash_select_bucket(htab, hash); + + raw_spin_lock_bh(&bucket->lock); + elem = sock_hash_lookup_elem_raw(&bucket->head, hash, key, key_size); + if (elem && flags == BPF_NOEXIST) { + ret = -EEXIST; + goto out_unlock; + } else if (!elem && flags == BPF_EXIST) { + ret = -ENOENT; + goto out_unlock; + } + + elem_new = sock_hash_alloc_elem(htab, key, key_size, hash, sk, elem); + if (IS_ERR(elem_new)) { + ret = PTR_ERR(elem_new); + goto out_unlock; + } + + sock_map_add_link(psock, link, map, elem_new); + /* Add new element to the head of the list, so that + * concurrent search will find it before old elem. + */ + hlist_add_head_rcu(&elem_new->node, &bucket->head); + if (elem) { + hlist_del_rcu(&elem->node); + sock_map_unref(elem->sk, elem); + sock_hash_free_elem(htab, elem); + } + raw_spin_unlock_bh(&bucket->lock); + return 0; +out_unlock: + raw_spin_unlock_bh(&bucket->lock); + sk_psock_put(sk, psock); +out_free: + sk_psock_free_link(link); + return ret; +} + +static int sock_hash_update_elem(struct bpf_map *map, void *key, + void *value, u64 flags) +{ + u32 ufd = *(u32 *)value; + struct socket *sock; + struct sock *sk; + int ret; + + sock = sockfd_lookup(ufd, &ret); + if (!sock) + return ret; + sk = sock->sk; + if (!sk) { + ret = -EINVAL; + goto out; + } + if (!sock_map_sk_is_suitable(sk) || + sk->sk_state != TCP_ESTABLISHED) { + ret = -EOPNOTSUPP; + goto out; + } + + sock_map_sk_acquire(sk); + ret = sock_hash_update_common(map, key, sk, flags); + sock_map_sk_release(sk); +out: + fput(sock->file); + return ret; +} + +static int sock_hash_get_next_key(struct bpf_map *map, void *key, + void *key_next) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + struct bpf_htab_elem *elem, *elem_next; + u32 hash, key_size = map->key_size; + struct hlist_head *head; + int i = 0; + + if (!key) + goto find_first_elem; + hash = sock_hash_bucket_hash(key, key_size); + head = &sock_hash_select_bucket(htab, hash)->head; + elem = sock_hash_lookup_elem_raw(head, hash, key, key_size); + if (!elem) + goto find_first_elem; + + elem_next = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(&elem->node)), + struct bpf_htab_elem, node); + if (elem_next) { + memcpy(key_next, elem_next->key, key_size); + return 0; + } + + i = hash & (htab->buckets_num - 1); + i++; +find_first_elem: + for (; i < htab->buckets_num; i++) { + head = &sock_hash_select_bucket(htab, i)->head; + elem_next = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)), + struct bpf_htab_elem, node); + if (elem_next) { + memcpy(key_next, elem_next->key, key_size); + return 0; + } + } + + return -ENOENT; +} + +static struct bpf_map *sock_hash_alloc(union bpf_attr *attr) +{ + struct bpf_htab *htab; + int i, err; + u64 cost; + + if (!capable(CAP_NET_ADMIN)) + return ERR_PTR(-EPERM); + if (attr->max_entries == 0 || + attr->key_size == 0 || + attr->value_size != 4 || + attr->map_flags & ~SOCK_CREATE_FLAG_MASK) + return ERR_PTR(-EINVAL); + if (attr->key_size > MAX_BPF_STACK) + return ERR_PTR(-E2BIG); + + htab = kzalloc(sizeof(*htab), GFP_USER); + if (!htab) + return ERR_PTR(-ENOMEM); + + bpf_map_init_from_attr(&htab->map, attr); + + htab->buckets_num = roundup_pow_of_two(htab->map.max_entries); + htab->elem_size = sizeof(struct bpf_htab_elem) + + round_up(htab->map.key_size, 8); + if (htab->buckets_num == 0 || + htab->buckets_num > U32_MAX / sizeof(struct bpf_htab_bucket)) { + err = -EINVAL; + goto free_htab; + } + + cost = (u64) htab->buckets_num * sizeof(struct bpf_htab_bucket) + + (u64) htab->elem_size * htab->map.max_entries; + if (cost >= U32_MAX - PAGE_SIZE) { + err = -EINVAL; + goto free_htab; + } + + htab->buckets = bpf_map_area_alloc(htab->buckets_num * + sizeof(struct bpf_htab_bucket), + htab->map.numa_node); + if (!htab->buckets) { + err = -ENOMEM; + goto free_htab; + } + + for (i = 0; i < htab->buckets_num; i++) { + INIT_HLIST_HEAD(&htab->buckets[i].head); + raw_spin_lock_init(&htab->buckets[i].lock); + } + + return &htab->map; +free_htab: + kfree(htab); + return ERR_PTR(err); +} + +static void sock_hash_free(struct bpf_map *map) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + struct bpf_htab_bucket *bucket; + struct bpf_htab_elem *elem; + struct hlist_node *node; + int i; + + synchronize_rcu(); + rcu_read_lock(); + for (i = 0; i < htab->buckets_num; i++) { + bucket = sock_hash_select_bucket(htab, i); + raw_spin_lock_bh(&bucket->lock); + hlist_for_each_entry_safe(elem, node, &bucket->head, node) { + hlist_del_rcu(&elem->node); + sock_map_unref(elem->sk, elem); + } + raw_spin_unlock_bh(&bucket->lock); + } + rcu_read_unlock(); + + bpf_map_area_free(htab->buckets); + kfree(htab); +} + +static void sock_hash_release_progs(struct bpf_map *map) +{ + psock_progs_drop(&container_of(map, struct bpf_htab, map)->progs); +} + +BPF_CALL_4(bpf_sock_hash_update, struct bpf_sock_ops_kern *, sops, + struct bpf_map *, map, void *, key, u64, flags) +{ + WARN_ON_ONCE(!rcu_read_lock_held()); + + if (likely(sock_map_sk_is_suitable(sops->sk) && + sock_map_op_okay(sops))) + return sock_hash_update_common(map, key, sops->sk, flags); + return -EOPNOTSUPP; +} + +const struct bpf_func_proto bpf_sock_hash_update_proto = { + .func = bpf_sock_hash_update, + .gpl_only = false, + .pkt_access = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_CONST_MAP_PTR, + .arg3_type = ARG_PTR_TO_MAP_KEY, + .arg4_type = ARG_ANYTHING, +}; + +BPF_CALL_4(bpf_sk_redirect_hash, struct sk_buff *, skb, + struct bpf_map *, map, void *, key, u64, flags) +{ + struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); + + if (unlikely(flags & ~(BPF_F_INGRESS))) + return SK_DROP; + tcb->bpf.flags = flags; + tcb->bpf.sk_redir = __sock_hash_lookup_elem(map, key); + if (!tcb->bpf.sk_redir) + return SK_DROP; + return SK_PASS; +} + +const struct bpf_func_proto bpf_sk_redirect_hash_proto = { + .func = bpf_sk_redirect_hash, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_CONST_MAP_PTR, + .arg3_type = ARG_PTR_TO_MAP_KEY, + .arg4_type = ARG_ANYTHING, +}; + +BPF_CALL_4(bpf_msg_redirect_hash, struct sk_msg *, msg, + struct bpf_map *, map, void *, key, u64, flags) +{ + if (unlikely(flags & ~(BPF_F_INGRESS))) + return SK_DROP; + msg->flags = flags; + msg->sk_redir = __sock_hash_lookup_elem(map, key); + if (!msg->sk_redir) + return SK_DROP; + return SK_PASS; +} + +const struct bpf_func_proto bpf_msg_redirect_hash_proto = { + .func = bpf_msg_redirect_hash, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_CONST_MAP_PTR, + .arg3_type = ARG_PTR_TO_MAP_KEY, + .arg4_type = ARG_ANYTHING, +}; + +const struct bpf_map_ops sock_hash_ops = { + .map_alloc = sock_hash_alloc, + .map_free = sock_hash_free, + .map_get_next_key = sock_hash_get_next_key, + .map_update_elem = sock_hash_update_elem, + .map_delete_elem = sock_hash_delete_elem, + .map_lookup_elem = sock_map_lookup, + .map_release_uref = sock_hash_release_progs, + .map_check_btf = map_check_no_btf, +}; + +static struct sk_psock_progs *sock_map_progs(struct bpf_map *map) +{ + switch (map->map_type) { + case BPF_MAP_TYPE_SOCKMAP: + return &container_of(map, struct bpf_stab, map)->progs; + case BPF_MAP_TYPE_SOCKHASH: + return &container_of(map, struct bpf_htab, map)->progs; + default: + break; + } + + return NULL; +} + +int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, + u32 which) +{ + struct sk_psock_progs *progs = sock_map_progs(map); + + if (!progs) + return -EOPNOTSUPP; + + switch (which) { + case BPF_SK_MSG_VERDICT: + psock_set_prog(&progs->msg_parser, prog); + break; + case BPF_SK_SKB_STREAM_PARSER: + psock_set_prog(&progs->skb_parser, prog); + break; + case BPF_SK_SKB_STREAM_VERDICT: + psock_set_prog(&progs->skb_verdict, prog); + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + +void sk_psock_unlink(struct sock *sk, struct sk_psock_link *link) +{ + switch (link->map->map_type) { + case BPF_MAP_TYPE_SOCKMAP: + return sock_map_delete_from_link(link->map, sk, + link->link_raw); + case BPF_MAP_TYPE_SOCKHASH: + return sock_hash_delete_from_link(link->map, sk, + link->link_raw); + default: + break; + } +} diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index 7446b98661d8..58629314eae9 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -63,6 +63,7 @@ obj-$(CONFIG_TCP_CONG_SCALABLE) += tcp_scalable.o obj-$(CONFIG_TCP_CONG_LP) += tcp_lp.o obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o +obj-$(CONFIG_NET_SOCK_MSG) += tcp_bpf.o obj-$(CONFIG_NETLABEL) += cipso_ipv4.o obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \ diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c new file mode 100644 index 000000000000..80debb0daf37 --- /dev/null +++ b/net/ipv4/tcp_bpf.c @@ -0,0 +1,655 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2017 - 2018 Covalent IO, Inc. http://covalent.io */ + +#include +#include +#include +#include +#include + +#include + +static bool tcp_bpf_stream_read(const struct sock *sk) +{ + struct sk_psock *psock; + bool empty = true; + + rcu_read_lock(); + psock = sk_psock(sk); + if (likely(psock)) + empty = list_empty(&psock->ingress_msg); + rcu_read_unlock(); + return !empty; +} + +static int tcp_bpf_wait_data(struct sock *sk, struct sk_psock *psock, + int flags, long timeo, int *err) +{ + DEFINE_WAIT_FUNC(wait, woken_wake_function); + int ret; + + add_wait_queue(sk_sleep(sk), &wait); + sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); + ret = sk_wait_event(sk, &timeo, + !list_empty(&psock->ingress_msg) || + !skb_queue_empty(&sk->sk_receive_queue), &wait); + sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); + remove_wait_queue(sk_sleep(sk), &wait); + return ret; +} + +int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, + struct msghdr *msg, int len) +{ + struct iov_iter *iter = &msg->msg_iter; + int i, ret, copied = 0; + + while (copied != len) { + struct scatterlist *sge; + struct sk_msg *msg_rx; + + msg_rx = list_first_entry_or_null(&psock->ingress_msg, + struct sk_msg, list); + if (unlikely(!msg_rx)) + break; + + i = msg_rx->sg.start; + do { + struct page *page; + int copy; + + sge = sk_msg_elem(msg_rx, i); + copy = sge->length; + page = sg_page(sge); + if (copied + copy > len) + copy = len - copied; + ret = copy_page_to_iter(page, sge->offset, copy, iter); + if (ret != copy) { + msg_rx->sg.start = i; + return -EFAULT; + } + + copied += copy; + sge->offset += copy; + sge->length -= copy; + sk_mem_uncharge(sk, copy); + if (!sge->length) { + i++; + if (i == MAX_SKB_FRAGS) + i = 0; + if (!msg_rx->skb) + put_page(page); + } + + if (copied == len) + break; + } while (i != msg_rx->sg.end); + + msg_rx->sg.start = i; + if (!sge->length && msg_rx->sg.start == msg_rx->sg.end) { + list_del(&msg_rx->list); + if (msg_rx->skb) + consume_skb(msg_rx->skb); + kfree(msg_rx); + } + } + + return copied; +} +EXPORT_SYMBOL_GPL(__tcp_bpf_recvmsg); + +int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, + int nonblock, int flags, int *addr_len) +{ + struct sk_psock *psock; + int copied, ret; + + if (unlikely(flags & MSG_ERRQUEUE)) + return inet_recv_error(sk, msg, len, addr_len); + if (!skb_queue_empty(&sk->sk_receive_queue)) + return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); + + psock = sk_psock_get(sk); + if (unlikely(!psock)) + return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); + lock_sock(sk); +msg_bytes_ready: + copied = __tcp_bpf_recvmsg(sk, psock, msg, len); + if (!copied) { + int data, err = 0; + long timeo; + + timeo = sock_rcvtimeo(sk, nonblock); + data = tcp_bpf_wait_data(sk, psock, flags, timeo, &err); + if (data) { + if (skb_queue_empty(&sk->sk_receive_queue)) + goto msg_bytes_ready; + release_sock(sk); + sk_psock_put(sk, psock); + return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); + } + if (err) { + ret = err; + goto out; + } + } + ret = copied; +out: + release_sock(sk); + sk_psock_put(sk, psock); + return ret; +} + +static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock, + struct sk_msg *msg, u32 apply_bytes, int flags) +{ + bool apply = apply_bytes; + struct scatterlist *sge; + u32 size, copied = 0; + struct sk_msg *tmp; + int i, ret = 0; + + tmp = kzalloc(sizeof(*tmp), __GFP_NOWARN | GFP_KERNEL); + if (unlikely(!tmp)) + return -ENOMEM; + + lock_sock(sk); + tmp->sg.start = msg->sg.start; + i = msg->sg.start; + do { + sge = sk_msg_elem(msg, i); + size = (apply && apply_bytes < sge->length) ? + apply_bytes : sge->length; + if (!sk_wmem_schedule(sk, size)) { + if (!copied) + ret = -ENOMEM; + break; + } + + sk_mem_charge(sk, size); + sk_msg_xfer(tmp, msg, i, size); + copied += size; + if (sge->length) + get_page(sk_msg_page(tmp, i)); + sk_msg_iter_var_next(i); + tmp->sg.end = i; + if (apply) { + apply_bytes -= size; + if (!apply_bytes) + break; + } + } while (i != msg->sg.end); + + if (!ret) { + msg->sg.start = i; + msg->sg.size -= apply_bytes; + sk_psock_queue_msg(psock, tmp); + sk->sk_data_ready(sk); + } else { + sk_msg_free(sk, tmp); + kfree(tmp); + } + + release_sock(sk); + return ret; +} + +static int tcp_bpf_push(struct sock *sk, struct sk_msg *msg, u32 apply_bytes, + int flags, bool uncharge) +{ + bool apply = apply_bytes; + struct scatterlist *sge; + struct page *page; + int size, ret = 0; + u32 off; + + while (1) { + sge = sk_msg_elem(msg, msg->sg.start); + size = (apply && apply_bytes < sge->length) ? + apply_bytes : sge->length; + off = sge->offset; + page = sg_page(sge); + + tcp_rate_check_app_limited(sk); +retry: + ret = do_tcp_sendpages(sk, page, off, size, flags); + if (ret <= 0) + return ret; + if (apply) + apply_bytes -= ret; + msg->sg.size -= ret; + sge->offset += ret; + sge->length -= ret; + if (uncharge) + sk_mem_uncharge(sk, ret); + if (ret != size) { + size -= ret; + off += ret; + goto retry; + } + if (!sge->length) { + put_page(page); + sk_msg_iter_next(msg, start); + sg_init_table(sge, 1); + if (msg->sg.start == msg->sg.end) + break; + } + if (apply && !apply_bytes) + break; + } + + return 0; +} + +static int tcp_bpf_push_locked(struct sock *sk, struct sk_msg *msg, + u32 apply_bytes, int flags, bool uncharge) +{ + int ret; + + lock_sock(sk); + ret = tcp_bpf_push(sk, msg, apply_bytes, flags, uncharge); + release_sock(sk); + return ret; +} + +int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg, + u32 bytes, int flags) +{ + bool ingress = sk_msg_to_ingress(msg); + struct sk_psock *psock = sk_psock_get(sk); + int ret; + + if (unlikely(!psock)) { + sk_msg_free(sk, msg); + return 0; + } + ret = ingress ? bpf_tcp_ingress(sk, psock, msg, bytes, flags) : + tcp_bpf_push_locked(sk, msg, bytes, flags, false); + sk_psock_put(sk, psock); + return ret; +} +EXPORT_SYMBOL_GPL(tcp_bpf_sendmsg_redir); + +static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock, + struct sk_msg *msg, int *copied, int flags) +{ + bool cork = false, enospc = msg->sg.start == msg->sg.end; + struct sock *sk_redir; + u32 tosend; + int ret; + +more_data: + if (psock->eval == __SK_NONE) + psock->eval = sk_psock_msg_verdict(sk, psock, msg); + + if (msg->cork_bytes && + msg->cork_bytes > msg->sg.size && !enospc) { + psock->cork_bytes = msg->cork_bytes - msg->sg.size; + if (!psock->cork) { + psock->cork = kzalloc(sizeof(*psock->cork), + GFP_ATOMIC | __GFP_NOWARN); + if (!psock->cork) + return -ENOMEM; + } + memcpy(psock->cork, msg, sizeof(*msg)); + return 0; + } + + tosend = msg->sg.size; + if (psock->apply_bytes && psock->apply_bytes < tosend) + tosend = psock->apply_bytes; + + switch (psock->eval) { + case __SK_PASS: + ret = tcp_bpf_push(sk, msg, tosend, flags, true); + if (unlikely(ret)) { + *copied -= sk_msg_free(sk, msg); + break; + } + sk_msg_apply_bytes(psock, tosend); + break; + case __SK_REDIRECT: + sk_redir = psock->sk_redir; + sk_msg_apply_bytes(psock, tosend); + if (psock->cork) { + cork = true; + psock->cork = NULL; + } + sk_msg_return(sk, msg, tosend); + release_sock(sk); + ret = tcp_bpf_sendmsg_redir(sk_redir, msg, tosend, flags); + lock_sock(sk); + if (unlikely(ret < 0)) { + int free = sk_msg_free_nocharge(sk, msg); + + if (!cork) + *copied -= free; + } + if (cork) { + sk_msg_free(sk, msg); + kfree(msg); + msg = NULL; + ret = 0; + } + break; + case __SK_DROP: + default: + sk_msg_free_partial(sk, msg, tosend); + sk_msg_apply_bytes(psock, tosend); + *copied -= tosend; + return -EACCES; + } + + if (likely(!ret)) { + if (!psock->apply_bytes) { + psock->eval = __SK_NONE; + if (psock->sk_redir) { + sock_put(psock->sk_redir); + psock->sk_redir = NULL; + } + } + if (msg && + msg->sg.data[msg->sg.start].page_link && + msg->sg.data[msg->sg.start].length) + goto more_data; + } + return ret; +} + +static int tcp_bpf_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) +{ + struct sk_msg tmp, *msg_tx = NULL; + int flags = msg->msg_flags | MSG_NO_SHARED_FRAGS; + int copied = 0, err = 0; + struct sk_psock *psock; + long timeo; + + psock = sk_psock_get(sk); + if (unlikely(!psock)) + return tcp_sendmsg(sk, msg, size); + + lock_sock(sk); + timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); + while (msg_data_left(msg)) { + bool enospc = false; + u32 copy, osize; + + if (sk->sk_err) { + err = -sk->sk_err; + goto out_err; + } + + copy = msg_data_left(msg); + if (!sk_stream_memory_free(sk)) + goto wait_for_sndbuf; + if (psock->cork) { + msg_tx = psock->cork; + } else { + msg_tx = &tmp; + sk_msg_init(msg_tx); + } + + osize = msg_tx->sg.size; + err = sk_msg_alloc(sk, msg_tx, msg_tx->sg.size + copy, msg_tx->sg.end - 1); + if (err) { + if (err != -ENOSPC) + goto wait_for_memory; + enospc = true; + copy = msg_tx->sg.size - osize; + } + + err = sk_msg_memcopy_from_iter(sk, &msg->msg_iter, msg_tx, + copy); + if (err < 0) { + sk_msg_trim(sk, msg_tx, osize); + goto out_err; + } + + copied += copy; + if (psock->cork_bytes) { + if (size > psock->cork_bytes) + psock->cork_bytes = 0; + else + psock->cork_bytes -= size; + if (psock->cork_bytes && !enospc) + goto out_err; + /* All cork bytes are accounted, rerun the prog. */ + psock->eval = __SK_NONE; + psock->cork_bytes = 0; + } + + err = tcp_bpf_send_verdict(sk, psock, msg_tx, &copied, flags); + if (unlikely(err < 0)) + goto out_err; + continue; +wait_for_sndbuf: + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); +wait_for_memory: + err = sk_stream_wait_memory(sk, &timeo); + if (err) { + if (msg_tx && msg_tx != psock->cork) + sk_msg_free(sk, msg_tx); + goto out_err; + } + } +out_err: + if (err < 0) + err = sk_stream_error(sk, msg->msg_flags, err); + release_sock(sk); + sk_psock_put(sk, psock); + return copied ? copied : err; +} + +static int tcp_bpf_sendpage(struct sock *sk, struct page *page, int offset, + size_t size, int flags) +{ + struct sk_msg tmp, *msg = NULL; + int err = 0, copied = 0; + struct sk_psock *psock; + bool enospc = false; + + psock = sk_psock_get(sk); + if (unlikely(!psock)) + return tcp_sendpage(sk, page, offset, size, flags); + + lock_sock(sk); + if (psock->cork) { + msg = psock->cork; + } else { + msg = &tmp; + sk_msg_init(msg); + } + + /* Catch case where ring is full and sendpage is stalled. */ + if (unlikely(sk_msg_full(msg))) + goto out_err; + + sk_msg_page_add(msg, page, size, offset); + sk_mem_charge(sk, size); + copied = size; + if (sk_msg_full(msg)) + enospc = true; + if (psock->cork_bytes) { + if (size > psock->cork_bytes) + psock->cork_bytes = 0; + else + psock->cork_bytes -= size; + if (psock->cork_bytes && !enospc) + goto out_err; + /* All cork bytes are accounted, rerun the prog. */ + psock->eval = __SK_NONE; + psock->cork_bytes = 0; + } + + err = tcp_bpf_send_verdict(sk, psock, msg, &copied, flags); +out_err: + release_sock(sk); + sk_psock_put(sk, psock); + return copied ? copied : err; +} + +static void tcp_bpf_remove(struct sock *sk, struct sk_psock *psock) +{ + struct sk_psock_link *link; + + sk_psock_cork_free(psock); + __sk_psock_purge_ingress_msg(psock); + while ((link = sk_psock_link_pop(psock))) { + sk_psock_unlink(sk, link); + sk_psock_free_link(link); + } +} + +static void tcp_bpf_unhash(struct sock *sk) +{ + void (*saved_unhash)(struct sock *sk); + struct sk_psock *psock; + + rcu_read_lock(); + psock = sk_psock(sk); + if (unlikely(!psock)) { + rcu_read_unlock(); + if (sk->sk_prot->unhash) + sk->sk_prot->unhash(sk); + return; + } + + saved_unhash = psock->saved_unhash; + tcp_bpf_remove(sk, psock); + rcu_read_unlock(); + saved_unhash(sk); +} + +static void tcp_bpf_close(struct sock *sk, long timeout) +{ + void (*saved_close)(struct sock *sk, long timeout); + struct sk_psock *psock; + + lock_sock(sk); + rcu_read_lock(); + psock = sk_psock(sk); + if (unlikely(!psock)) { + rcu_read_unlock(); + release_sock(sk); + return sk->sk_prot->close(sk, timeout); + } + + saved_close = psock->saved_close; + tcp_bpf_remove(sk, psock); + rcu_read_unlock(); + release_sock(sk); + saved_close(sk, timeout); +} + +enum { + TCP_BPF_IPV4, + TCP_BPF_IPV6, + TCP_BPF_NUM_PROTS, +}; + +enum { + TCP_BPF_BASE, + TCP_BPF_TX, + TCP_BPF_NUM_CFGS, +}; + +static struct proto *tcpv6_prot_saved __read_mostly; +static DEFINE_SPINLOCK(tcpv6_prot_lock); +static struct proto tcp_bpf_prots[TCP_BPF_NUM_PROTS][TCP_BPF_NUM_CFGS]; + +static void tcp_bpf_rebuild_protos(struct proto prot[TCP_BPF_NUM_CFGS], + struct proto *base) +{ + prot[TCP_BPF_BASE] = *base; + prot[TCP_BPF_BASE].unhash = tcp_bpf_unhash; + prot[TCP_BPF_BASE].close = tcp_bpf_close; + prot[TCP_BPF_BASE].recvmsg = tcp_bpf_recvmsg; + prot[TCP_BPF_BASE].stream_memory_read = tcp_bpf_stream_read; + + prot[TCP_BPF_TX] = prot[TCP_BPF_BASE]; + prot[TCP_BPF_TX].sendmsg = tcp_bpf_sendmsg; + prot[TCP_BPF_TX].sendpage = tcp_bpf_sendpage; +} + +static void tcp_bpf_check_v6_needs_rebuild(struct sock *sk, struct proto *ops) +{ + if (sk->sk_family == AF_INET6 && + unlikely(ops != smp_load_acquire(&tcpv6_prot_saved))) { + spin_lock_bh(&tcpv6_prot_lock); + if (likely(ops != tcpv6_prot_saved)) { + tcp_bpf_rebuild_protos(tcp_bpf_prots[TCP_BPF_IPV6], ops); + smp_store_release(&tcpv6_prot_saved, ops); + } + spin_unlock_bh(&tcpv6_prot_lock); + } +} + +static int __init tcp_bpf_v4_build_proto(void) +{ + tcp_bpf_rebuild_protos(tcp_bpf_prots[TCP_BPF_IPV4], &tcp_prot); + return 0; +} +core_initcall(tcp_bpf_v4_build_proto); + +static void tcp_bpf_update_sk_prot(struct sock *sk, struct sk_psock *psock) +{ + int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4; + int config = psock->progs.msg_parser ? TCP_BPF_TX : TCP_BPF_BASE; + + sk_psock_update_proto(sk, psock, &tcp_bpf_prots[family][config]); +} + +static void tcp_bpf_reinit_sk_prot(struct sock *sk, struct sk_psock *psock) +{ + int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4; + int config = psock->progs.msg_parser ? TCP_BPF_TX : TCP_BPF_BASE; + + /* Reinit occurs when program types change e.g. TCP_BPF_TX is removed + * or added requiring sk_prot hook updates. We keep original saved + * hooks in this case. + */ + sk->sk_prot = &tcp_bpf_prots[family][config]; +} + +static int tcp_bpf_assert_proto_ops(struct proto *ops) +{ + /* In order to avoid retpoline, we make assumptions when we call + * into ops if e.g. a psock is not present. Make sure they are + * indeed valid assumptions. + */ + return ops->recvmsg == tcp_recvmsg && + ops->sendmsg == tcp_sendmsg && + ops->sendpage == tcp_sendpage ? 0 : -ENOTSUPP; +} + +void tcp_bpf_reinit(struct sock *sk) +{ + struct sk_psock *psock; + + sock_owned_by_me(sk); + + rcu_read_lock(); + psock = sk_psock(sk); + tcp_bpf_reinit_sk_prot(sk, psock); + rcu_read_unlock(); +} + +int tcp_bpf_init(struct sock *sk) +{ + struct proto *ops = READ_ONCE(sk->sk_prot); + struct sk_psock *psock; + + sock_owned_by_me(sk); + + rcu_read_lock(); + psock = sk_psock(sk); + if (unlikely(!psock || psock->sk_proto || + tcp_bpf_assert_proto_ops(ops))) { + rcu_read_unlock(); + return -EINVAL; + } + tcp_bpf_check_v6_needs_rebuild(sk, ops); + tcp_bpf_update_sk_prot(sk, psock); + rcu_read_unlock(); + return 0; +} diff --git a/net/strparser/Kconfig b/net/strparser/Kconfig index 6cff3f6d0c3a..94da19a2a220 100644 --- a/net/strparser/Kconfig +++ b/net/strparser/Kconfig @@ -1,4 +1,2 @@ - config STREAM_PARSER - tristate - default n + def_bool n -- cgit v1.2.3 From d829e9c4112b52f4f00195900fd4c685f61365ab Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 13 Oct 2018 02:45:59 +0200 Subject: tls: convert to generic sk_msg interface Convert kTLS over to make use of sk_msg interface for plaintext and encrypted scattergather data, so it reuses all the sk_msg helpers and data structure which later on in a second step enables to glue this to BPF. This also allows to remove quite a bit of open coded helpers which are covered by the sk_msg API. Recent changes in kTLs 80ece6a03aaf ("tls: Remove redundant vars from tls record structure") and 4e6d47206c32 ("tls: Add support for inplace records encryption") changed the data path handling a bit; while we've kept the latter optimization intact, we had to undo the former change to better fit the sk_msg model, hence the sg_aead_in and sg_aead_out have been brought back and are linked into the sk_msg sgs. Now the kTLS record contains a msg_plaintext and msg_encrypted sk_msg each. In the original code, the zerocopy_from_iter() has been used out of TX but also RX path. For the strparser skb-based RX path, we've left the zerocopy_from_iter() in decrypt_internal() mostly untouched, meaning it has been moved into tls_setup_from_iter() with charging logic removed (as not used from RX). Given RX path is not based on sk_msg objects, we haven't pursued setting up a dummy sk_msg to call into sk_msg_zerocopy_from_iter(), but it could be an option to prusue in a later step. Joint work with John. Signed-off-by: Daniel Borkmann Signed-off-by: John Fastabend Signed-off-by: Alexei Starovoitov --- include/linux/skmsg.h | 2 + include/net/sock.h | 4 - include/net/tls.h | 18 +- net/core/skmsg.c | 39 ++++ net/core/sock.c | 61 ------ net/tls/Kconfig | 1 + net/tls/tls_device.c | 2 +- net/tls/tls_sw.c | 511 ++++++++++++++++++-------------------------------- 8 files changed, 236 insertions(+), 402 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 95678103c4a0..4e84b3c2eff8 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -102,6 +102,8 @@ struct sk_psock { int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len, int elem_first_coalesce); +int sk_msg_clone(struct sock *sk, struct sk_msg *dst, struct sk_msg *src, + u32 off, u32 len); void sk_msg_trim(struct sock *sk, struct sk_msg *msg, int len); int sk_msg_free(struct sock *sk, struct sk_msg *msg); int sk_msg_free_nocharge(struct sock *sk, struct sk_msg *msg); diff --git a/include/net/sock.h b/include/net/sock.h index 751549ac0a84..7470c45d182d 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2214,10 +2214,6 @@ static inline struct page_frag *sk_page_frag(struct sock *sk) bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag); -int sk_alloc_sg(struct sock *sk, int len, struct scatterlist *sg, - int sg_start, int *sg_curr, unsigned int *sg_size, - int first_coalesce); - /* * Default write policy as shown to user space via poll/select/SIGIO */ diff --git a/include/net/tls.h b/include/net/tls.h index 5e853835597e..3d22d8a59be7 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -39,6 +39,8 @@ #include #include #include +#include + #include #include #include @@ -103,15 +105,13 @@ struct tls_rec { int tx_flags; int inplace_crypto; - /* AAD | sg_plaintext_data | sg_tag */ - struct scatterlist sg_plaintext_data[MAX_SKB_FRAGS + 1]; - /* AAD | sg_encrypted_data (data contain overhead for hdr&iv&tag) */ - struct scatterlist sg_encrypted_data[MAX_SKB_FRAGS + 1]; + struct sk_msg msg_plaintext; + struct sk_msg msg_encrypted; - unsigned int sg_plaintext_size; - unsigned int sg_encrypted_size; - int sg_plaintext_num_elem; - int sg_encrypted_num_elem; + /* AAD | msg_plaintext.sg.data | sg_tag */ + struct scatterlist sg_aead_in[2]; + /* AAD | msg_encrypted.sg.data (data contains overhead for hdr & iv & tag) */ + struct scatterlist sg_aead_out[2]; char aad_space[TLS_AAD_SPACE_SIZE]; struct aead_request aead_req; @@ -223,8 +223,8 @@ struct tls_context { unsigned long flags; bool in_tcp_sendpages; + bool pending_open_record_frags; - u16 pending_open_record_frags; int (*push_pending_record)(struct sock *sk, int flags); void (*sk_write_space)(struct sock *sk); diff --git a/net/core/skmsg.c b/net/core/skmsg.c index ae2b281c9c57..56a99d0c9aa0 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -73,6 +73,45 @@ int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len, } EXPORT_SYMBOL_GPL(sk_msg_alloc); +int sk_msg_clone(struct sock *sk, struct sk_msg *dst, struct sk_msg *src, + u32 off, u32 len) +{ + int i = src->sg.start; + struct scatterlist *sge = sk_msg_elem(src, i); + u32 sge_len, sge_off; + + if (sk_msg_full(dst)) + return -ENOSPC; + + while (off) { + if (sge->length > off) + break; + off -= sge->length; + sk_msg_iter_var_next(i); + if (i == src->sg.end && off) + return -ENOSPC; + sge = sk_msg_elem(src, i); + } + + while (len) { + sge_len = sge->length - off; + sge_off = sge->offset + off; + if (sge_len > len) + sge_len = len; + off = 0; + len -= sge_len; + sk_msg_page_add(dst, sg_page(sge), sge_len, sge_off); + sk_mem_charge(sk, sge_len); + sk_msg_iter_var_next(i); + if (i == src->sg.end && len) + return -ENOSPC; + sge = sk_msg_elem(src, i); + } + + return 0; +} +EXPORT_SYMBOL_GPL(sk_msg_clone); + void sk_msg_return_zero(struct sock *sk, struct sk_msg *msg, int bytes) { int i = msg->sg.start; diff --git a/net/core/sock.c b/net/core/sock.c index 7e8796a6a089..52e4f1c16b1e 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2238,67 +2238,6 @@ bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag) } EXPORT_SYMBOL(sk_page_frag_refill); -int sk_alloc_sg(struct sock *sk, int len, struct scatterlist *sg, - int sg_start, int *sg_curr_index, unsigned int *sg_curr_size, - int first_coalesce) -{ - int sg_curr = *sg_curr_index, use = 0, rc = 0; - unsigned int size = *sg_curr_size; - struct page_frag *pfrag; - struct scatterlist *sge; - - len -= size; - pfrag = sk_page_frag(sk); - - while (len > 0) { - unsigned int orig_offset; - - if (!sk_page_frag_refill(sk, pfrag)) { - rc = -ENOMEM; - goto out; - } - - use = min_t(int, len, pfrag->size - pfrag->offset); - - if (!sk_wmem_schedule(sk, use)) { - rc = -ENOMEM; - goto out; - } - - sk_mem_charge(sk, use); - size += use; - orig_offset = pfrag->offset; - pfrag->offset += use; - - sge = sg + sg_curr - 1; - if (sg_curr > first_coalesce && sg_page(sge) == pfrag->page && - sge->offset + sge->length == orig_offset) { - sge->length += use; - } else { - sge = sg + sg_curr; - sg_unmark_end(sge); - sg_set_page(sge, pfrag->page, use, orig_offset); - get_page(pfrag->page); - sg_curr++; - - if (sg_curr == MAX_SKB_FRAGS) - sg_curr = 0; - - if (sg_curr == sg_start) { - rc = -ENOSPC; - break; - } - } - - len -= use; - } -out: - *sg_curr_size = size; - *sg_curr_index = sg_curr; - return rc; -} -EXPORT_SYMBOL(sk_alloc_sg); - static void __lock_sock(struct sock *sk) __releases(&sk->sk_lock.slock) __acquires(&sk->sk_lock.slock) diff --git a/net/tls/Kconfig b/net/tls/Kconfig index 73f05ece53d0..99c1a19c17b1 100644 --- a/net/tls/Kconfig +++ b/net/tls/Kconfig @@ -8,6 +8,7 @@ config TLS select CRYPTO_AES select CRYPTO_GCM select STREAM_PARSER + select NET_SOCK_MSG default n ---help--- Enable kernel support for TLS protocol. This allows symmetric diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 961b07d4d41c..276edbc04f38 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -421,7 +421,7 @@ last_record: tls_push_record_flags = flags; if (more) { tls_ctx->pending_open_record_frags = - record->num_frags; + !!record->num_frags; break; } diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index aa9fdce272b6..5043b0be1448 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -213,153 +213,49 @@ static int tls_do_decryption(struct sock *sk, return ret; } -static void trim_sg(struct sock *sk, struct scatterlist *sg, - int *sg_num_elem, unsigned int *sg_size, int target_size) -{ - int i = *sg_num_elem - 1; - int trim = *sg_size - target_size; - - if (trim <= 0) { - WARN_ON(trim < 0); - return; - } - - *sg_size = target_size; - while (trim >= sg[i].length) { - trim -= sg[i].length; - sk_mem_uncharge(sk, sg[i].length); - put_page(sg_page(&sg[i])); - i--; - - if (i < 0) - goto out; - } - - sg[i].length -= trim; - sk_mem_uncharge(sk, trim); - -out: - *sg_num_elem = i + 1; -} - -static void trim_both_sgl(struct sock *sk, int target_size) +static void tls_trim_both_msgs(struct sock *sk, int target_size) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); struct tls_rec *rec = ctx->open_rec; - trim_sg(sk, &rec->sg_plaintext_data[1], - &rec->sg_plaintext_num_elem, - &rec->sg_plaintext_size, - target_size); - + sk_msg_trim(sk, &rec->msg_plaintext, target_size); if (target_size > 0) target_size += tls_ctx->tx.overhead_size; - - trim_sg(sk, &rec->sg_encrypted_data[1], - &rec->sg_encrypted_num_elem, - &rec->sg_encrypted_size, - target_size); + sk_msg_trim(sk, &rec->msg_encrypted, target_size); } -static int alloc_encrypted_sg(struct sock *sk, int len) +static int tls_alloc_encrypted_msg(struct sock *sk, int len) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); struct tls_rec *rec = ctx->open_rec; - int rc = 0; - - rc = sk_alloc_sg(sk, len, - &rec->sg_encrypted_data[1], 0, - &rec->sg_encrypted_num_elem, - &rec->sg_encrypted_size, 0); - - if (rc == -ENOSPC) - rec->sg_encrypted_num_elem = - ARRAY_SIZE(rec->sg_encrypted_data) - 1; + struct sk_msg *msg_en = &rec->msg_encrypted; - return rc; + return sk_msg_alloc(sk, msg_en, len, 0); } -static int move_to_plaintext_sg(struct sock *sk, int required_size) +static int tls_clone_plaintext_msg(struct sock *sk, int required) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); struct tls_rec *rec = ctx->open_rec; - struct scatterlist *plain_sg = &rec->sg_plaintext_data[1]; - struct scatterlist *enc_sg = &rec->sg_encrypted_data[1]; - int enc_sg_idx = 0; + struct sk_msg *msg_pl = &rec->msg_plaintext; + struct sk_msg *msg_en = &rec->msg_encrypted; int skip, len; - if (rec->sg_plaintext_num_elem == MAX_SKB_FRAGS) - return -ENOSPC; - - /* We add page references worth len bytes from enc_sg at the - * end of plain_sg. It is guaranteed that sg_encrypted_data + /* We add page references worth len bytes from encrypted sg + * at the end of plaintext sg. It is guaranteed that msg_en * has enough required room (ensured by caller). */ - len = required_size - rec->sg_plaintext_size; + len = required - msg_pl->sg.size; - /* Skip initial bytes in sg_encrypted_data to be able - * to use same offset of both plain and encrypted data. + /* Skip initial bytes in msg_en's data to be able to use + * same offset of both plain and encrypted data. */ - skip = tls_ctx->tx.prepend_size + rec->sg_plaintext_size; - - while (enc_sg_idx < rec->sg_encrypted_num_elem) { - if (enc_sg[enc_sg_idx].length > skip) - break; - - skip -= enc_sg[enc_sg_idx].length; - enc_sg_idx++; - } + skip = tls_ctx->tx.prepend_size + msg_pl->sg.size; - /* unmark the end of plain_sg*/ - sg_unmark_end(plain_sg + rec->sg_plaintext_num_elem - 1); - - while (len) { - struct page *page = sg_page(&enc_sg[enc_sg_idx]); - int bytes = enc_sg[enc_sg_idx].length - skip; - int offset = enc_sg[enc_sg_idx].offset + skip; - - if (bytes > len) - bytes = len; - else - enc_sg_idx++; - - /* Skipping is required only one time */ - skip = 0; - - /* Increment page reference */ - get_page(page); - - sg_set_page(&plain_sg[rec->sg_plaintext_num_elem], page, - bytes, offset); - - sk_mem_charge(sk, bytes); - - len -= bytes; - rec->sg_plaintext_size += bytes; - - rec->sg_plaintext_num_elem++; - - if (rec->sg_plaintext_num_elem == MAX_SKB_FRAGS) - return -ENOSPC; - } - - return 0; -} - -static void free_sg(struct sock *sk, struct scatterlist *sg, - int *sg_num_elem, unsigned int *sg_size) -{ - int i, n = *sg_num_elem; - - for (i = 0; i < n; ++i) { - sk_mem_uncharge(sk, sg[i].length); - put_page(sg_page(&sg[i])); - } - *sg_num_elem = 0; - *sg_size = 0; + return sk_msg_clone(sk, msg_pl, msg_en, skip, len); } static void tls_free_open_rec(struct sock *sk) @@ -372,14 +268,8 @@ static void tls_free_open_rec(struct sock *sk) if (!rec) return; - free_sg(sk, &rec->sg_encrypted_data[1], - &rec->sg_encrypted_num_elem, - &rec->sg_encrypted_size); - - free_sg(sk, &rec->sg_plaintext_data[1], - &rec->sg_plaintext_num_elem, - &rec->sg_plaintext_size); - + sk_msg_free(sk, &rec->msg_encrypted); + sk_msg_free(sk, &rec->msg_plaintext); kfree(rec); } @@ -388,6 +278,7 @@ int tls_tx_records(struct sock *sk, int flags) struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); struct tls_rec *rec, *tmp; + struct sk_msg *msg_en; int tx_flags, rc = 0; if (tls_is_partially_sent_record(tls_ctx)) { @@ -407,9 +298,7 @@ int tls_tx_records(struct sock *sk, int flags) * Remove the head of tx_list */ list_del(&rec->list); - free_sg(sk, &rec->sg_plaintext_data[1], - &rec->sg_plaintext_num_elem, &rec->sg_plaintext_size); - + sk_msg_free(sk, &rec->msg_plaintext); kfree(rec); } @@ -421,17 +310,15 @@ int tls_tx_records(struct sock *sk, int flags) else tx_flags = flags; + msg_en = &rec->msg_encrypted; rc = tls_push_sg(sk, tls_ctx, - &rec->sg_encrypted_data[1], + &msg_en->sg.data[msg_en->sg.curr], 0, tx_flags); if (rc) goto tx_err; list_del(&rec->list); - free_sg(sk, &rec->sg_plaintext_data[1], - &rec->sg_plaintext_num_elem, - &rec->sg_plaintext_size); - + sk_msg_free(sk, &rec->msg_plaintext); kfree(rec); } else { break; @@ -451,15 +338,18 @@ static void tls_encrypt_done(struct crypto_async_request *req, int err) struct sock *sk = req->data; struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); + struct scatterlist *sge; + struct sk_msg *msg_en; struct tls_rec *rec; bool ready = false; int pending; rec = container_of(aead_req, struct tls_rec, aead_req); + msg_en = &rec->msg_encrypted; - rec->sg_encrypted_data[1].offset -= tls_ctx->tx.prepend_size; - rec->sg_encrypted_data[1].length += tls_ctx->tx.prepend_size; - + sge = sk_msg_elem(msg_en, msg_en->sg.curr); + sge->offset -= tls_ctx->tx.prepend_size; + sge->length += tls_ctx->tx.prepend_size; /* Check if error is previously set on socket */ if (err || sk->sk_err) { @@ -497,31 +387,29 @@ static void tls_encrypt_done(struct crypto_async_request *req, int err) /* Schedule the transmission */ if (!test_and_set_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) - schedule_delayed_work(&ctx->tx_work.work, 2); + schedule_delayed_work(&ctx->tx_work.work, 1); } static int tls_do_encryption(struct sock *sk, struct tls_context *tls_ctx, struct tls_sw_context_tx *ctx, struct aead_request *aead_req, - size_t data_len) + size_t data_len, u32 start) { struct tls_rec *rec = ctx->open_rec; - struct scatterlist *plain_sg = rec->sg_plaintext_data; - struct scatterlist *enc_sg = rec->sg_encrypted_data; + struct sk_msg *msg_en = &rec->msg_encrypted; + struct scatterlist *sge = sk_msg_elem(msg_en, start); int rc; - /* Skip the first index as it contains AAD data */ - rec->sg_encrypted_data[1].offset += tls_ctx->tx.prepend_size; - rec->sg_encrypted_data[1].length -= tls_ctx->tx.prepend_size; + sge->offset += tls_ctx->tx.prepend_size; + sge->length -= tls_ctx->tx.prepend_size; - /* If it is inplace crypto, then pass same SG list as both src, dst */ - if (rec->inplace_crypto) - plain_sg = enc_sg; + msg_en->sg.curr = start; aead_request_set_tfm(aead_req, ctx->aead_send); aead_request_set_ad(aead_req, TLS_AAD_SPACE_SIZE); - aead_request_set_crypt(aead_req, plain_sg, enc_sg, + aead_request_set_crypt(aead_req, rec->sg_aead_in, + rec->sg_aead_out, data_len, tls_ctx->tx.iv); aead_request_set_callback(aead_req, CRYPTO_TFM_REQ_MAY_BACKLOG, @@ -534,8 +422,8 @@ static int tls_do_encryption(struct sock *sk, rc = crypto_aead_encrypt(aead_req); if (!rc || rc != -EINPROGRESS) { atomic_dec(&ctx->encrypt_pending); - rec->sg_encrypted_data[1].offset -= tls_ctx->tx.prepend_size; - rec->sg_encrypted_data[1].length += tls_ctx->tx.prepend_size; + sge->offset -= tls_ctx->tx.prepend_size; + sge->length += tls_ctx->tx.prepend_size; } if (!rc) { @@ -557,35 +445,50 @@ static int tls_push_record(struct sock *sk, int flags, struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); struct tls_rec *rec = ctx->open_rec; + struct sk_msg *msg_pl, *msg_en; struct aead_request *req; int rc; + u32 i; if (!rec) return 0; + msg_pl = &rec->msg_plaintext; + msg_en = &rec->msg_encrypted; + rec->tx_flags = flags; req = &rec->aead_req; - sg_mark_end(rec->sg_plaintext_data + rec->sg_plaintext_num_elem); - sg_mark_end(rec->sg_encrypted_data + rec->sg_encrypted_num_elem); + i = msg_pl->sg.end; + sk_msg_iter_var_prev(i); + sg_mark_end(sk_msg_elem(msg_pl, i)); - tls_make_aad(rec->aad_space, rec->sg_plaintext_size, + i = msg_pl->sg.start; + sg_chain(rec->sg_aead_in, 2, rec->inplace_crypto ? + &msg_en->sg.data[i] : &msg_pl->sg.data[i]); + + i = msg_en->sg.end; + sk_msg_iter_var_prev(i); + sg_mark_end(sk_msg_elem(msg_en, i)); + + i = msg_en->sg.start; + sg_chain(rec->sg_aead_out, 2, &msg_en->sg.data[i]); + + tls_make_aad(rec->aad_space, msg_pl->sg.size, tls_ctx->tx.rec_seq, tls_ctx->tx.rec_seq_size, record_type); tls_fill_prepend(tls_ctx, - page_address(sg_page(&rec->sg_encrypted_data[1])) + - rec->sg_encrypted_data[1].offset, - rec->sg_plaintext_size, record_type); + page_address(sg_page(&msg_en->sg.data[i])) + + msg_en->sg.data[i].offset, msg_pl->sg.size, + record_type); - tls_ctx->pending_open_record_frags = 0; - - rc = tls_do_encryption(sk, tls_ctx, ctx, req, rec->sg_plaintext_size); - if (rc == -EINPROGRESS) - return -EINPROGRESS; + tls_ctx->pending_open_record_frags = false; + rc = tls_do_encryption(sk, tls_ctx, ctx, req, msg_pl->sg.size, i); if (rc < 0) { - tls_err_abort(sk, EBADMSG); + if (rc != -EINPROGRESS) + tls_err_abort(sk, EBADMSG); return rc; } @@ -597,104 +500,11 @@ static int tls_sw_push_pending_record(struct sock *sk, int flags) return tls_push_record(sk, flags, TLS_RECORD_TYPE_DATA); } -static int zerocopy_from_iter(struct sock *sk, struct iov_iter *from, - int length, int *pages_used, - unsigned int *size_used, - struct scatterlist *to, int to_max_pages, - bool charge) -{ - struct page *pages[MAX_SKB_FRAGS]; - - size_t offset; - ssize_t copied, use; - int i = 0; - unsigned int size = *size_used; - int num_elem = *pages_used; - int rc = 0; - int maxpages; - - while (length > 0) { - i = 0; - maxpages = to_max_pages - num_elem; - if (maxpages == 0) { - rc = -EFAULT; - goto out; - } - copied = iov_iter_get_pages(from, pages, - length, - maxpages, &offset); - if (copied <= 0) { - rc = -EFAULT; - goto out; - } - - iov_iter_advance(from, copied); - - length -= copied; - size += copied; - while (copied) { - use = min_t(int, copied, PAGE_SIZE - offset); - - sg_set_page(&to[num_elem], - pages[i], use, offset); - sg_unmark_end(&to[num_elem]); - if (charge) - sk_mem_charge(sk, use); - - offset = 0; - copied -= use; - - ++i; - ++num_elem; - } - } - - /* Mark the end in the last sg entry if newly added */ - if (num_elem > *pages_used) - sg_mark_end(&to[num_elem - 1]); -out: - if (rc) - iov_iter_revert(from, size - *size_used); - *size_used = size; - *pages_used = num_elem; - - return rc; -} - -static int memcopy_from_iter(struct sock *sk, struct iov_iter *from, - int bytes) -{ - struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); - struct tls_rec *rec = ctx->open_rec; - struct scatterlist *sg = &rec->sg_plaintext_data[1]; - int copy, i, rc = 0; - - for (i = tls_ctx->pending_open_record_frags; - i < rec->sg_plaintext_num_elem; ++i) { - copy = sg[i].length; - if (copy_from_iter( - page_address(sg_page(&sg[i])) + sg[i].offset, - copy, from) != copy) { - rc = -EFAULT; - goto out; - } - bytes -= copy; - - ++tls_ctx->pending_open_record_frags; - - if (!bytes) - break; - } - -out: - return rc; -} - static struct tls_rec *get_rec(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); + struct sk_msg *msg_pl, *msg_en; struct tls_rec *rec; int mem_size; @@ -708,15 +518,21 @@ static struct tls_rec *get_rec(struct sock *sk) if (!rec) return NULL; - sg_init_table(&rec->sg_plaintext_data[0], - ARRAY_SIZE(rec->sg_plaintext_data)); - sg_init_table(&rec->sg_encrypted_data[0], - ARRAY_SIZE(rec->sg_encrypted_data)); + msg_pl = &rec->msg_plaintext; + msg_en = &rec->msg_encrypted; + + sk_msg_init(msg_pl); + sk_msg_init(msg_en); - sg_set_buf(&rec->sg_plaintext_data[0], rec->aad_space, + sg_init_table(rec->sg_aead_in, 2); + sg_set_buf(&rec->sg_aead_in[0], rec->aad_space, sizeof(rec->aad_space)); - sg_set_buf(&rec->sg_encrypted_data[0], rec->aad_space, + sg_unmark_end(&rec->sg_aead_in[1]); + + sg_init_table(rec->sg_aead_out, 2); + sg_set_buf(&rec->sg_aead_out[0], rec->aad_space, sizeof(rec->aad_space)); + sg_unmark_end(&rec->sg_aead_out[1]); ctx->open_rec = rec; rec->inplace_crypto = 1; @@ -735,6 +551,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) bool is_kvec = msg->msg_iter.type & ITER_KVEC; bool eor = !(msg->msg_flags & MSG_MORE); size_t try_to_copy, copied = 0; + struct sk_msg *msg_pl, *msg_en; struct tls_rec *rec; int required_size; int num_async = 0; @@ -778,23 +595,26 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) goto send_end; } - orig_size = rec->sg_plaintext_size; + msg_pl = &rec->msg_plaintext; + msg_en = &rec->msg_encrypted; + + orig_size = msg_pl->sg.size; full_record = false; try_to_copy = msg_data_left(msg); - record_room = TLS_MAX_PAYLOAD_SIZE - rec->sg_plaintext_size; + record_room = TLS_MAX_PAYLOAD_SIZE - msg_pl->sg.size; if (try_to_copy >= record_room) { try_to_copy = record_room; full_record = true; } - required_size = rec->sg_plaintext_size + try_to_copy + + required_size = msg_pl->sg.size + try_to_copy + tls_ctx->tx.overhead_size; if (!sk_stream_memory_free(sk)) goto wait_for_sndbuf; alloc_encrypted: - ret = alloc_encrypted_sg(sk, required_size); + ret = tls_alloc_encrypted_msg(sk, required_size); if (ret) { if (ret != -ENOSPC) goto wait_for_memory; @@ -803,17 +623,13 @@ alloc_encrypted: * actually allocated. The difference is due * to max sg elements limit */ - try_to_copy -= required_size - rec->sg_encrypted_size; + try_to_copy -= required_size - msg_en->sg.size; full_record = true; } if (!is_kvec && (full_record || eor) && !async_capable) { - ret = zerocopy_from_iter(sk, &msg->msg_iter, - try_to_copy, &rec->sg_plaintext_num_elem, - &rec->sg_plaintext_size, - &rec->sg_plaintext_data[1], - ARRAY_SIZE(rec->sg_plaintext_data) - 1, - true); + ret = sk_msg_zerocopy_from_iter(sk, &msg->msg_iter, + msg_pl, try_to_copy); if (ret) goto fallback_to_reg_send; @@ -831,15 +647,12 @@ alloc_encrypted: continue; fallback_to_reg_send: - trim_sg(sk, &rec->sg_plaintext_data[1], - &rec->sg_plaintext_num_elem, - &rec->sg_plaintext_size, - orig_size); + sk_msg_trim(sk, msg_pl, orig_size); } - required_size = rec->sg_plaintext_size + try_to_copy; + required_size = msg_pl->sg.size + try_to_copy; - ret = move_to_plaintext_sg(sk, required_size); + ret = tls_clone_plaintext_msg(sk, required_size); if (ret) { if (ret != -ENOSPC) goto send_end; @@ -848,20 +661,21 @@ fallback_to_reg_send: * actually allocated. The difference is due * to max sg elements limit */ - try_to_copy -= required_size - rec->sg_plaintext_size; + try_to_copy -= required_size - msg_pl->sg.size; full_record = true; - - trim_sg(sk, &rec->sg_encrypted_data[1], - &rec->sg_encrypted_num_elem, - &rec->sg_encrypted_size, - rec->sg_plaintext_size + - tls_ctx->tx.overhead_size); + sk_msg_trim(sk, msg_en, msg_pl->sg.size + + tls_ctx->tx.overhead_size); } - ret = memcopy_from_iter(sk, &msg->msg_iter, try_to_copy); - if (ret) + ret = sk_msg_memcopy_from_iter(sk, &msg->msg_iter, msg_pl, + try_to_copy); + if (ret < 0) goto trim_sgl; + /* Open records defined only if successfully copied, otherwise + * we would trim the sg but not reset the open record frags. + */ + tls_ctx->pending_open_record_frags = true; copied += try_to_copy; if (full_record || eor) { ret = tls_push_record(sk, msg->msg_flags, record_type); @@ -881,11 +695,11 @@ wait_for_memory: ret = sk_stream_wait_memory(sk, &timeo); if (ret) { trim_sgl: - trim_both_sgl(sk, orig_size); + tls_trim_both_msgs(sk, orig_size); goto send_end; } - if (rec->sg_encrypted_size < required_size) + if (msg_en->sg.size < required_size) goto alloc_encrypted; } @@ -929,7 +743,7 @@ int tls_sw_sendpage(struct sock *sk, struct page *page, struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); unsigned char record_type = TLS_RECORD_TYPE_DATA; size_t orig_size = size; - struct scatterlist *sg; + struct sk_msg *msg_pl; struct tls_rec *rec; int num_async = 0; bool full_record; @@ -970,20 +784,23 @@ int tls_sw_sendpage(struct sock *sk, struct page *page, goto sendpage_end; } + msg_pl = &rec->msg_plaintext; + full_record = false; - record_room = TLS_MAX_PAYLOAD_SIZE - rec->sg_plaintext_size; + record_room = TLS_MAX_PAYLOAD_SIZE - msg_pl->sg.size; copy = size; if (copy >= record_room) { copy = record_room; full_record = true; } - required_size = rec->sg_plaintext_size + copy + - tls_ctx->tx.overhead_size; + + required_size = msg_pl->sg.size + copy + + tls_ctx->tx.overhead_size; if (!sk_stream_memory_free(sk)) goto wait_for_sndbuf; alloc_payload: - ret = alloc_encrypted_sg(sk, required_size); + ret = tls_alloc_encrypted_msg(sk, required_size); if (ret) { if (ret != -ENOSPC) goto wait_for_memory; @@ -992,26 +809,18 @@ alloc_payload: * actually allocated. The difference is due * to max sg elements limit */ - copy -= required_size - rec->sg_plaintext_size; + copy -= required_size - msg_pl->sg.size; full_record = true; } - get_page(page); - sg = &rec->sg_plaintext_data[1] + rec->sg_plaintext_num_elem; - sg_set_page(sg, page, copy, offset); - sg_unmark_end(sg); - - rec->sg_plaintext_num_elem++; - + sk_msg_page_add(msg_pl, page, copy, offset); sk_mem_charge(sk, copy); + offset += copy; size -= copy; - rec->sg_plaintext_size += copy; - tls_ctx->pending_open_record_frags = rec->sg_plaintext_num_elem; - if (full_record || eor || - rec->sg_plaintext_num_elem == - ARRAY_SIZE(rec->sg_plaintext_data) - 1) { + tls_ctx->pending_open_record_frags = true; + if (full_record || eor || sk_msg_full(msg_pl)) { rec->inplace_crypto = 0; ret = tls_push_record(sk, flags, record_type); if (ret) { @@ -1027,7 +836,7 @@ wait_for_sndbuf: wait_for_memory: ret = sk_stream_wait_memory(sk, &timeo); if (ret) { - trim_both_sgl(sk, rec->sg_plaintext_size); + tls_trim_both_msgs(sk, msg_pl->sg.size); goto sendpage_end; } @@ -1092,6 +901,64 @@ static struct sk_buff *tls_wait_data(struct sock *sk, int flags, return skb; } +static int tls_setup_from_iter(struct sock *sk, struct iov_iter *from, + int length, int *pages_used, + unsigned int *size_used, + struct scatterlist *to, + int to_max_pages) +{ + int rc = 0, i = 0, num_elem = *pages_used, maxpages; + struct page *pages[MAX_SKB_FRAGS]; + unsigned int size = *size_used; + ssize_t copied, use; + size_t offset; + + while (length > 0) { + i = 0; + maxpages = to_max_pages - num_elem; + if (maxpages == 0) { + rc = -EFAULT; + goto out; + } + copied = iov_iter_get_pages(from, pages, + length, + maxpages, &offset); + if (copied <= 0) { + rc = -EFAULT; + goto out; + } + + iov_iter_advance(from, copied); + + length -= copied; + size += copied; + while (copied) { + use = min_t(int, copied, PAGE_SIZE - offset); + + sg_set_page(&to[num_elem], + pages[i], use, offset); + sg_unmark_end(&to[num_elem]); + /* We do not uncharge memory from this API */ + + offset = 0; + copied -= use; + + i++; + num_elem++; + } + } + /* Mark the end in the last sg entry if newly added */ + if (num_elem > *pages_used) + sg_mark_end(&to[num_elem - 1]); +out: + if (rc) + iov_iter_revert(from, size - *size_used); + *size_used = size; + *pages_used = num_elem; + + return rc; +} + /* This function decrypts the input skb into either out_iov or in out_sg * or in skb buffers itself. The input parameter 'zc' indicates if * zero-copy mode needs to be tried or not. With zero-copy mode, either @@ -1189,9 +1056,9 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb, sg_set_buf(&sgout[0], aad, TLS_AAD_SPACE_SIZE); *chunk = 0; - err = zerocopy_from_iter(sk, out_iov, data_len, &pages, - chunk, &sgout[1], - (n_sgout - 1), false); + err = tls_setup_from_iter(sk, out_iov, data_len, + &pages, chunk, &sgout[1], + (n_sgout - 1)); if (err < 0) goto fallback_to_reg_recv; } else if (out_sg) { @@ -1619,25 +1486,15 @@ void tls_sw_free_resources_tx(struct sock *sk) rec = list_first_entry(&ctx->tx_list, struct tls_rec, list); - - free_sg(sk, &rec->sg_plaintext_data[1], - &rec->sg_plaintext_num_elem, - &rec->sg_plaintext_size); - list_del(&rec->list); + sk_msg_free(sk, &rec->msg_plaintext); kfree(rec); } list_for_each_entry_safe(rec, tmp, &ctx->tx_list, list) { - free_sg(sk, &rec->sg_encrypted_data[1], - &rec->sg_encrypted_num_elem, - &rec->sg_encrypted_size); - - free_sg(sk, &rec->sg_plaintext_data[1], - &rec->sg_plaintext_num_elem, - &rec->sg_plaintext_size); - list_del(&rec->list); + sk_msg_free(sk, &rec->msg_encrypted); + sk_msg_free(sk, &rec->msg_plaintext); kfree(rec); } -- cgit v1.2.3 From d3b18ad31f93d0b6bae105c679018a1ba7daa9ca Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Sat, 13 Oct 2018 02:46:01 +0200 Subject: tls: add bpf support to sk_msg handling This work adds BPF sk_msg verdict program support to kTLS allowing BPF and kTLS to be combined together. Previously kTLS and sk_msg verdict programs were mutually exclusive in the ULP layer which created challenges for the orchestrator when trying to apply TCP based policy, for example. To resolve this, leveraging the work from previous patches that consolidates the use of sk_msg, we can finally enable BPF sk_msg verdict programs so they continue to run after the kTLS socket is created. No change in behavior when kTLS is not used in combination with BPF, the kselftest suite for kTLS also runs successfully. Joint work with Daniel. Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov --- include/linux/skmsg.h | 41 ++++- net/tls/tls_sw.c | 439 ++++++++++++++++++++++++++++++++++++++++++-------- 2 files changed, 414 insertions(+), 66 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 4e84b3c2eff8..0b919f0bc6d6 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -29,7 +29,11 @@ struct sk_msg_sg { u32 size; u32 copybreak; bool copy[MAX_MSG_FRAGS]; - struct scatterlist data[MAX_MSG_FRAGS]; + /* The extra element is used for chaining the front and sections when + * the list becomes partitioned (e.g. end < start). The crypto APIs + * require the chaining. + */ + struct scatterlist data[MAX_MSG_FRAGS + 1]; }; struct sk_msg { @@ -112,6 +116,7 @@ void sk_msg_free_partial_nocharge(struct sock *sk, struct sk_msg *msg, u32 bytes); void sk_msg_return(struct sock *sk, struct sk_msg *msg, int bytes); +void sk_msg_return_zero(struct sock *sk, struct sk_msg *msg, int bytes); int sk_msg_zerocopy_from_iter(struct sock *sk, struct iov_iter *from, struct sk_msg *msg, u32 bytes); @@ -161,8 +166,9 @@ static inline void sk_msg_clear_meta(struct sk_msg *msg) static inline void sk_msg_init(struct sk_msg *msg) { + BUILD_BUG_ON(ARRAY_SIZE(msg->sg.data) - 1 != MAX_MSG_FRAGS); memset(msg, 0, sizeof(*msg)); - sg_init_marker(msg->sg.data, ARRAY_SIZE(msg->sg.data)); + sg_init_marker(msg->sg.data, MAX_MSG_FRAGS); } static inline void sk_msg_xfer(struct sk_msg *dst, struct sk_msg *src, @@ -174,6 +180,12 @@ static inline void sk_msg_xfer(struct sk_msg *dst, struct sk_msg *src, src->sg.data[which].offset += size; } +static inline void sk_msg_xfer_full(struct sk_msg *dst, struct sk_msg *src) +{ + memcpy(dst, src, sizeof(*src)); + sk_msg_init(src); +} + static inline u32 sk_msg_elem_used(const struct sk_msg *msg) { return msg->sg.end >= msg->sg.start ? @@ -229,6 +241,26 @@ static inline void sk_msg_page_add(struct sk_msg *msg, struct page *page, sk_msg_iter_next(msg, end); } +static inline void sk_msg_sg_copy(struct sk_msg *msg, u32 i, bool copy_state) +{ + do { + msg->sg.copy[i] = copy_state; + sk_msg_iter_var_next(i); + if (i == msg->sg.end) + break; + } while (1); +} + +static inline void sk_msg_sg_copy_set(struct sk_msg *msg, u32 start) +{ + sk_msg_sg_copy(msg, start, true); +} + +static inline void sk_msg_sg_copy_clear(struct sk_msg *msg, u32 start) +{ + sk_msg_sg_copy(msg, start, false); +} + static inline struct sk_psock *sk_psock(const struct sock *sk) { return rcu_dereference_sk_user_data(sk); @@ -245,6 +277,11 @@ static inline void sk_psock_queue_msg(struct sk_psock *psock, list_add_tail(&msg->list, &psock->ingress_msg); } +static inline bool sk_psock_queue_empty(const struct sk_psock *psock) +{ + return psock ? list_empty(&psock->ingress_msg) : true; +} + static inline void sk_psock_report_error(struct sk_psock *psock, int err) { struct sock *sk = psock->sk; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 3b75e0dd51a2..a525fc4c2a4b 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -4,6 +4,7 @@ * Copyright (c) 2016-2017, Lance Chao . All rights reserved. * Copyright (c) 2016, Fridolin Pokorny . All rights reserved. * Copyright (c) 2016, Nikos Mavrogiannopoulos . All rights reserved. + * Copyright (c) 2018, Covalent IO, Inc. http://covalent.io * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU @@ -258,21 +259,58 @@ static int tls_clone_plaintext_msg(struct sock *sk, int required) return sk_msg_clone(sk, msg_pl, msg_en, skip, len); } -static void tls_free_open_rec(struct sock *sk) +static struct tls_rec *tls_get_rec(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); - struct tls_rec *rec = ctx->open_rec; + struct sk_msg *msg_pl, *msg_en; + struct tls_rec *rec; + int mem_size; - /* Return if there is no open record */ + mem_size = sizeof(struct tls_rec) + crypto_aead_reqsize(ctx->aead_send); + + rec = kzalloc(mem_size, sk->sk_allocation); if (!rec) - return; + return NULL; + msg_pl = &rec->msg_plaintext; + msg_en = &rec->msg_encrypted; + + sk_msg_init(msg_pl); + sk_msg_init(msg_en); + + sg_init_table(rec->sg_aead_in, 2); + sg_set_buf(&rec->sg_aead_in[0], rec->aad_space, + sizeof(rec->aad_space)); + sg_unmark_end(&rec->sg_aead_in[1]); + + sg_init_table(rec->sg_aead_out, 2); + sg_set_buf(&rec->sg_aead_out[0], rec->aad_space, + sizeof(rec->aad_space)); + sg_unmark_end(&rec->sg_aead_out[1]); + + return rec; +} + +static void tls_free_rec(struct sock *sk, struct tls_rec *rec) +{ sk_msg_free(sk, &rec->msg_encrypted); sk_msg_free(sk, &rec->msg_plaintext); kfree(rec); } +static void tls_free_open_rec(struct sock *sk) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); + struct tls_rec *rec = ctx->open_rec; + + if (rec) { + tls_free_rec(sk, rec); + ctx->open_rec = NULL; + } +} + int tls_tx_records(struct sock *sk, int flags) { struct tls_context *tls_ctx = tls_get_ctx(sk); @@ -439,16 +477,135 @@ static int tls_do_encryption(struct sock *sk, return rc; } +static int tls_split_open_record(struct sock *sk, struct tls_rec *from, + struct tls_rec **to, struct sk_msg *msg_opl, + struct sk_msg *msg_oen, u32 split_point, + u32 tx_overhead_size, u32 *orig_end) +{ + u32 i, j, bytes = 0, apply = msg_opl->apply_bytes; + struct scatterlist *sge, *osge, *nsge; + u32 orig_size = msg_opl->sg.size; + struct scatterlist tmp = { }; + struct sk_msg *msg_npl; + struct tls_rec *new; + int ret; + + new = tls_get_rec(sk); + if (!new) + return -ENOMEM; + ret = sk_msg_alloc(sk, &new->msg_encrypted, msg_opl->sg.size + + tx_overhead_size, 0); + if (ret < 0) { + tls_free_rec(sk, new); + return ret; + } + + *orig_end = msg_opl->sg.end; + i = msg_opl->sg.start; + sge = sk_msg_elem(msg_opl, i); + while (apply && sge->length) { + if (sge->length > apply) { + u32 len = sge->length - apply; + + get_page(sg_page(sge)); + sg_set_page(&tmp, sg_page(sge), len, + sge->offset + apply); + sge->length = apply; + bytes += apply; + apply = 0; + } else { + apply -= sge->length; + bytes += sge->length; + } + + sk_msg_iter_var_next(i); + if (i == msg_opl->sg.end) + break; + sge = sk_msg_elem(msg_opl, i); + } + + msg_opl->sg.end = i; + msg_opl->sg.curr = i; + msg_opl->sg.copybreak = 0; + msg_opl->apply_bytes = 0; + msg_opl->sg.size = bytes; + + msg_npl = &new->msg_plaintext; + msg_npl->apply_bytes = apply; + msg_npl->sg.size = orig_size - bytes; + + j = msg_npl->sg.start; + nsge = sk_msg_elem(msg_npl, j); + if (tmp.length) { + memcpy(nsge, &tmp, sizeof(*nsge)); + sk_msg_iter_var_next(j); + nsge = sk_msg_elem(msg_npl, j); + } + + osge = sk_msg_elem(msg_opl, i); + while (osge->length) { + memcpy(nsge, osge, sizeof(*nsge)); + sg_unmark_end(nsge); + sk_msg_iter_var_next(i); + sk_msg_iter_var_next(j); + if (i == *orig_end) + break; + osge = sk_msg_elem(msg_opl, i); + nsge = sk_msg_elem(msg_npl, j); + } + + msg_npl->sg.end = j; + msg_npl->sg.curr = j; + msg_npl->sg.copybreak = 0; + + *to = new; + return 0; +} + +static void tls_merge_open_record(struct sock *sk, struct tls_rec *to, + struct tls_rec *from, u32 orig_end) +{ + struct sk_msg *msg_npl = &from->msg_plaintext; + struct sk_msg *msg_opl = &to->msg_plaintext; + struct scatterlist *osge, *nsge; + u32 i, j; + + i = msg_opl->sg.end; + sk_msg_iter_var_prev(i); + j = msg_npl->sg.start; + + osge = sk_msg_elem(msg_opl, i); + nsge = sk_msg_elem(msg_npl, j); + + if (sg_page(osge) == sg_page(nsge) && + osge->offset + osge->length == nsge->offset) { + osge->length += nsge->length; + put_page(sg_page(nsge)); + } + + msg_opl->sg.end = orig_end; + msg_opl->sg.curr = orig_end; + msg_opl->sg.copybreak = 0; + msg_opl->apply_bytes = msg_opl->sg.size + msg_npl->sg.size; + msg_opl->sg.size += msg_npl->sg.size; + + sk_msg_free(sk, &to->msg_encrypted); + sk_msg_xfer_full(&to->msg_encrypted, &from->msg_encrypted); + + kfree(from); +} + static int tls_push_record(struct sock *sk, int flags, unsigned char record_type) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); - struct tls_rec *rec = ctx->open_rec; + struct tls_rec *rec = ctx->open_rec, *tmp = NULL; + u32 i, split_point, uninitialized_var(orig_end); struct sk_msg *msg_pl, *msg_en; struct aead_request *req; + bool split; int rc; - u32 i; if (!rec) return 0; @@ -456,6 +613,18 @@ static int tls_push_record(struct sock *sk, int flags, msg_pl = &rec->msg_plaintext; msg_en = &rec->msg_encrypted; + split_point = msg_pl->apply_bytes; + split = split_point && split_point < msg_pl->sg.size; + if (split) { + rc = tls_split_open_record(sk, rec, &tmp, msg_pl, msg_en, + split_point, tls_ctx->tx.overhead_size, + &orig_end); + if (rc < 0) + return rc; + sk_msg_trim(sk, msg_en, msg_pl->sg.size + + tls_ctx->tx.overhead_size); + } + rec->tx_flags = flags; req = &rec->aead_req; @@ -487,57 +656,139 @@ static int tls_push_record(struct sock *sk, int flags, rc = tls_do_encryption(sk, tls_ctx, ctx, req, msg_pl->sg.size, i); if (rc < 0) { - if (rc != -EINPROGRESS) + if (rc != -EINPROGRESS) { tls_err_abort(sk, EBADMSG); + if (split) { + tls_ctx->pending_open_record_frags = true; + tls_merge_open_record(sk, rec, tmp, orig_end); + } + } return rc; + } else if (split) { + msg_pl = &tmp->msg_plaintext; + msg_en = &tmp->msg_encrypted; + sk_msg_trim(sk, msg_en, msg_pl->sg.size + + tls_ctx->tx.overhead_size); + tls_ctx->pending_open_record_frags = true; + ctx->open_rec = tmp; } return tls_tx_records(sk, flags); } -static int tls_sw_push_pending_record(struct sock *sk, int flags) -{ - return tls_push_record(sk, flags, TLS_RECORD_TYPE_DATA); -} - -static struct tls_rec *get_rec(struct sock *sk) +static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk, + bool full_record, u8 record_type, + size_t *copied, int flags) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); - struct sk_msg *msg_pl, *msg_en; + struct sk_msg msg_redir = { }; + struct sk_psock *psock; + struct sock *sk_redir; struct tls_rec *rec; - int mem_size; + int err = 0, send; + bool enospc; + + psock = sk_psock_get(sk); + if (!psock) + return tls_push_record(sk, flags, record_type); +more_data: + enospc = sk_msg_full(msg); + if (psock->eval == __SK_NONE) + psock->eval = sk_psock_msg_verdict(sk, psock, msg); + if (msg->cork_bytes && msg->cork_bytes > msg->sg.size && + !enospc && !full_record) { + err = -ENOSPC; + goto out_err; + } + msg->cork_bytes = 0; + send = msg->sg.size; + if (msg->apply_bytes && msg->apply_bytes < send) + send = msg->apply_bytes; + + switch (psock->eval) { + case __SK_PASS: + err = tls_push_record(sk, flags, record_type); + if (err < 0) { + *copied -= sk_msg_free(sk, msg); + tls_free_open_rec(sk); + goto out_err; + } + break; + case __SK_REDIRECT: + sk_redir = psock->sk_redir; + memcpy(&msg_redir, msg, sizeof(*msg)); + if (msg->apply_bytes < send) + msg->apply_bytes = 0; + else + msg->apply_bytes -= send; + sk_msg_return_zero(sk, msg, send); + msg->sg.size -= send; + release_sock(sk); + err = tcp_bpf_sendmsg_redir(sk_redir, &msg_redir, send, flags); + lock_sock(sk); + if (err < 0) { + *copied -= sk_msg_free_nocharge(sk, &msg_redir); + msg->sg.size = 0; + } + if (msg->sg.size == 0) + tls_free_open_rec(sk); + break; + case __SK_DROP: + default: + sk_msg_free_partial(sk, msg, send); + if (msg->apply_bytes < send) + msg->apply_bytes = 0; + else + msg->apply_bytes -= send; + if (msg->sg.size == 0) + tls_free_open_rec(sk); + *copied -= send; + err = -EACCES; + } - /* Return if we already have an open record */ - if (ctx->open_rec) - return ctx->open_rec; + if (likely(!err)) { + bool reset_eval = !ctx->open_rec; - mem_size = sizeof(struct tls_rec) + crypto_aead_reqsize(ctx->aead_send); + rec = ctx->open_rec; + if (rec) { + msg = &rec->msg_plaintext; + if (!msg->apply_bytes) + reset_eval = true; + } + if (reset_eval) { + psock->eval = __SK_NONE; + if (psock->sk_redir) { + sock_put(psock->sk_redir); + psock->sk_redir = NULL; + } + } + if (rec) + goto more_data; + } + out_err: + sk_psock_put(sk, psock); + return err; +} + +static int tls_sw_push_pending_record(struct sock *sk, int flags) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); + struct tls_rec *rec = ctx->open_rec; + struct sk_msg *msg_pl; + size_t copied; - rec = kzalloc(mem_size, sk->sk_allocation); if (!rec) - return NULL; + return 0; msg_pl = &rec->msg_plaintext; - msg_en = &rec->msg_encrypted; - - sk_msg_init(msg_pl); - sk_msg_init(msg_en); - - sg_init_table(rec->sg_aead_in, 2); - sg_set_buf(&rec->sg_aead_in[0], rec->aad_space, - sizeof(rec->aad_space)); - sg_unmark_end(&rec->sg_aead_in[1]); - - sg_init_table(rec->sg_aead_out, 2); - sg_set_buf(&rec->sg_aead_out[0], rec->aad_space, - sizeof(rec->aad_space)); - sg_unmark_end(&rec->sg_aead_out[1]); - - ctx->open_rec = rec; - rec->inplace_crypto = 1; + copied = msg_pl->sg.size; + if (!copied) + return 0; - return rec; + return bpf_exec_tx_verdict(msg_pl, sk, true, TLS_RECORD_TYPE_DATA, + &copied, flags); } int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) @@ -589,7 +840,10 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) goto send_end; } - rec = get_rec(sk); + if (ctx->open_rec) + rec = ctx->open_rec; + else + rec = ctx->open_rec = tls_get_rec(sk); if (!rec) { ret = -ENOMEM; goto send_end; @@ -628,6 +882,8 @@ alloc_encrypted: } if (!is_kvec && (full_record || eor) && !async_capable) { + u32 first = msg_pl->sg.end; + ret = sk_msg_zerocopy_from_iter(sk, &msg->msg_iter, msg_pl, try_to_copy); if (ret) @@ -637,15 +893,27 @@ alloc_encrypted: num_zc++; copied += try_to_copy; - ret = tls_push_record(sk, msg->msg_flags, record_type); + + sk_msg_sg_copy_set(msg_pl, first); + ret = bpf_exec_tx_verdict(msg_pl, sk, full_record, + record_type, &copied, + msg->msg_flags); if (ret) { if (ret == -EINPROGRESS) num_async++; + else if (ret == -ENOMEM) + goto wait_for_memory; + else if (ret == -ENOSPC) + goto rollback_iter; else if (ret != -EAGAIN) goto send_end; } continue; - +rollback_iter: + copied -= try_to_copy; + sk_msg_sg_copy_clear(msg_pl, first); + iov_iter_revert(&msg->msg_iter, + msg_pl->sg.size - orig_size); fallback_to_reg_send: sk_msg_trim(sk, msg_pl, orig_size); } @@ -678,12 +946,19 @@ fallback_to_reg_send: tls_ctx->pending_open_record_frags = true; copied += try_to_copy; if (full_record || eor) { - ret = tls_push_record(sk, msg->msg_flags, record_type); + ret = bpf_exec_tx_verdict(msg_pl, sk, full_record, + record_type, &copied, + msg->msg_flags); if (ret) { if (ret == -EINPROGRESS) num_async++; - else if (ret != -EAGAIN) + else if (ret == -ENOMEM) + goto wait_for_memory; + else if (ret != -EAGAIN) { + if (ret == -ENOSPC) + ret = 0; goto send_end; + } } } @@ -742,10 +1017,10 @@ int tls_sw_sendpage(struct sock *sk, struct page *page, struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); unsigned char record_type = TLS_RECORD_TYPE_DATA; - size_t orig_size = size; struct sk_msg *msg_pl; struct tls_rec *rec; int num_async = 0; + size_t copied = 0; bool full_record; int record_room; int ret = 0; @@ -778,7 +1053,10 @@ int tls_sw_sendpage(struct sock *sk, struct page *page, goto sendpage_end; } - rec = get_rec(sk); + if (ctx->open_rec) + rec = ctx->open_rec; + else + rec = ctx->open_rec = tls_get_rec(sk); if (!rec) { ret = -ENOMEM; goto sendpage_end; @@ -788,6 +1066,7 @@ int tls_sw_sendpage(struct sock *sk, struct page *page, full_record = false; record_room = TLS_MAX_PAYLOAD_SIZE - msg_pl->sg.size; + copied = 0; copy = size; if (copy >= record_room) { copy = record_room; @@ -818,16 +1097,23 @@ alloc_payload: offset += copy; size -= copy; + copied += copy; tls_ctx->pending_open_record_frags = true; if (full_record || eor || sk_msg_full(msg_pl)) { rec->inplace_crypto = 0; - ret = tls_push_record(sk, flags, record_type); + ret = bpf_exec_tx_verdict(msg_pl, sk, full_record, + record_type, &copied, flags); if (ret) { if (ret == -EINPROGRESS) num_async++; - else if (ret != -EAGAIN) + else if (ret == -ENOMEM) + goto wait_for_memory; + else if (ret != -EAGAIN) { + if (ret == -ENOSPC) + ret = 0; goto sendpage_end; + } } } continue; @@ -851,24 +1137,20 @@ wait_for_memory: } } sendpage_end: - if (orig_size > size) - ret = orig_size - size; - else - ret = sk_stream_error(sk, flags, ret); - + ret = sk_stream_error(sk, flags, ret); release_sock(sk); - return ret; + return copied ? copied : ret; } -static struct sk_buff *tls_wait_data(struct sock *sk, int flags, - long timeo, int *err) +static struct sk_buff *tls_wait_data(struct sock *sk, struct sk_psock *psock, + int flags, long timeo, int *err) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); struct sk_buff *skb; DEFINE_WAIT_FUNC(wait, woken_wake_function); - while (!(skb = ctx->recv_pkt)) { + while (!(skb = ctx->recv_pkt) && sk_psock_queue_empty(psock)) { if (sk->sk_err) { *err = sock_error(sk); return NULL; @@ -887,7 +1169,10 @@ static struct sk_buff *tls_wait_data(struct sock *sk, int flags, add_wait_queue(sk_sleep(sk), &wait); sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); - sk_wait_event(sk, &timeo, ctx->recv_pkt != skb, &wait); + sk_wait_event(sk, &timeo, + ctx->recv_pkt != skb || + !sk_psock_queue_empty(psock), + &wait); sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); remove_wait_queue(sk_sleep(sk), &wait); @@ -1164,6 +1449,7 @@ int tls_sw_recvmsg(struct sock *sk, { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); + struct sk_psock *psock; unsigned char control; struct strp_msg *rxm; struct sk_buff *skb; @@ -1179,6 +1465,7 @@ int tls_sw_recvmsg(struct sock *sk, if (unlikely(flags & MSG_ERRQUEUE)) return sock_recv_errqueue(sk, msg, len, SOL_IP, IP_RECVERR); + psock = sk_psock_get(sk); lock_sock(sk); target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); @@ -1188,9 +1475,19 @@ int tls_sw_recvmsg(struct sock *sk, bool async = false; int chunk = 0; - skb = tls_wait_data(sk, flags, timeo, &err); - if (!skb) + skb = tls_wait_data(sk, psock, flags, timeo, &err); + if (!skb) { + if (psock) { + int ret = __tcp_bpf_recvmsg(sk, psock, msg, len); + + if (ret > 0) { + copied += ret; + len -= ret; + continue; + } + } goto recv_end; + } rxm = strp_msg(skb); @@ -1296,6 +1593,8 @@ recv_end: } release_sock(sk); + if (psock) + sk_psock_put(sk, psock); return copied ? : err; } @@ -1318,7 +1617,7 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); - skb = tls_wait_data(sk, flags, timeo, &err); + skb = tls_wait_data(sk, NULL, flags, timeo, &err); if (!skb) goto splice_read_end; @@ -1356,11 +1655,16 @@ bool tls_sw_stream_read(const struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); + bool ingress_empty = true; + struct sk_psock *psock; - if (ctx->recv_pkt) - return true; + rcu_read_lock(); + psock = sk_psock(sk); + if (psock) + ingress_empty = list_empty(&psock->ingress_msg); + rcu_read_unlock(); - return false; + return !ingress_empty || ctx->recv_pkt; } static int tls_read_size(struct strparser *strp, struct sk_buff *skb) @@ -1439,8 +1743,15 @@ static void tls_data_ready(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); + struct sk_psock *psock; strp_data_ready(&ctx->strp); + + psock = sk_psock_get(sk); + if (psock && !list_empty(&psock->ingress_msg)) { + ctx->saved_data_ready(sk); + sk_psock_put(sk, psock); + } } void tls_sw_free_resources_tx(struct sock *sk) -- cgit v1.2.3 From 25ab0bc334b43bbbe4eabc255006ce42a9424da2 Mon Sep 17 00:00:00 2001 From: Nicholas Bellinger Date: Wed, 10 Oct 2018 03:23:09 +0000 Subject: scsi: sched/wait: Add wait_event_lock_irq_timeout for TASK_UNINTERRUPTIBLE usage Short of reverting commit 00d909a10710 ("scsi: target: Make the session shutdown code also wait for commands that are being aborted") for v4.19, target-core needs a wait_event_t macro can be executed using TASK_UNINTERRUPTIBLE to function correctly with existing fabric drivers that expect to run with signals pending during session shutdown and active se_cmd I/O quiesce. The most notable is iscsi-target/iser-target, while ibmvscsi_tgt invokes session shutdown logic from userspace via configfs attribute that could also potentially have signals pending. So go ahead and introduce wait_event_lock_irq_timeout() to achieve this, and update + rename __wait_event_lock_irq_timeout() to make it accept 'state' as a parameter. Fixes: 00d909a10710 ("scsi: target: Make the session shutdown code also wait for commands that are being aborted") Cc: # v4.19+ Cc: Bart Van Assche Cc: Mike Christie Cc: Hannes Reinecke Cc: Christoph Hellwig Cc: Sagi Grimberg Cc: Bryant G. Ly Cc: Peter Zijlstra (Intel) Tested-by: Nicholas Bellinger Signed-off-by: Nicholas Bellinger Reviewed-by: Bryant G. Ly Acked-by: Peter Zijlstra (Intel) Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- include/linux/wait.h | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index d9f131ecf708..ed7c122cb31f 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -1052,10 +1052,9 @@ do { \ __ret; \ }) -#define __wait_event_interruptible_lock_irq_timeout(wq_head, condition, \ - lock, timeout) \ +#define __wait_event_lock_irq_timeout(wq_head, condition, lock, timeout, state) \ ___wait_event(wq_head, ___wait_cond_timeout(condition), \ - TASK_INTERRUPTIBLE, 0, timeout, \ + state, 0, timeout, \ spin_unlock_irq(&lock); \ __ret = schedule_timeout(__ret); \ spin_lock_irq(&lock)); @@ -1089,8 +1088,19 @@ do { \ ({ \ long __ret = timeout; \ if (!___wait_cond_timeout(condition)) \ - __ret = __wait_event_interruptible_lock_irq_timeout( \ - wq_head, condition, lock, timeout); \ + __ret = __wait_event_lock_irq_timeout( \ + wq_head, condition, lock, timeout, \ + TASK_INTERRUPTIBLE); \ + __ret; \ +}) + +#define wait_event_lock_irq_timeout(wq_head, condition, lock, timeout) \ +({ \ + long __ret = timeout; \ + if (!___wait_cond_timeout(condition)) \ + __ret = __wait_event_lock_irq_timeout( \ + wq_head, condition, lock, timeout, \ + TASK_UNINTERRUPTIBLE); \ __ret; \ }) -- cgit v1.2.3 From 9f9a742db40f95f4dc20fc7293de4ea6ddb24e47 Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Tue, 9 Oct 2018 23:57:49 +0100 Subject: FDDI: defza: Support capturing outgoing SMT traffic DEC FDDIcontroller 700 (DEFZA) uses a Tx/Rx queue pair to communicate SMT frames with adapter's firmware. Any SMT frame received from the RMC via the Rx queue is queued back by the driver to the SMT Rx queue for the firmware to process. Similarly the firmware uses the SMT Tx queue to supply the driver with SMT frames which are queued back to the Tx queue for the RMC to send to the ring. When a network tap is attached to an FDDI interface handled by `defza' any incoming SMT frames captured are queued to our usual processing of network data received, which in turn delivers them to any listening taps. However the outgoing SMT frames produced by the firmware bypass our network protocol stack and are therefore not delivered to taps. This in turn means that taps are missing a part of network traffic sent by the adapter, which may make it more difficult to track down network problems or do general traffic analysis. Call `dev_queue_xmit_nit' then in the SMT Tx path, having checked that a network tap is attached, with a newly-created `dev_nit_active' helper wrapping the usual condition used in the transmit path. Signed-off-by: Maciej W. Rozycki Signed-off-by: David S. Miller --- drivers/net/fddi/defza.c | 33 +++++++++++++++++++++++++++++++-- include/linux/netdevice.h | 1 + net/core/dev.c | 13 ++++++++++++- 3 files changed, 44 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/fddi/defza.c b/drivers/net/fddi/defza.c index 7d01b70f7ed8..3b7f10a5f06a 100644 --- a/drivers/net/fddi/defza.c +++ b/drivers/net/fddi/defza.c @@ -797,11 +797,40 @@ static void fza_tx_smt(struct net_device *dev) smt_tx_ptr = fp->mmio + readl_u(&fp->ring_smt_tx[i].buffer); len = readl_u(&fp->ring_smt_tx[i].rmc) & FZA_RING_PBC_MASK; - /* Queue the frame to the RMC transmit ring. */ - if (!netif_queue_stopped(dev)) + if (!netif_queue_stopped(dev)) { + if (dev_nit_active(dev)) { + struct sk_buff *skb; + + /* Length must be a multiple of 4 as only word + * reads are permitted! + */ + skb = fza_alloc_skb_irq(dev, (len + 3) & ~3); + if (!skb) + goto err_no_skb; /* Drop. */ + + skb_data_ptr = (struct fza_buffer_tx *) + skb->data; + + fza_reads(smt_tx_ptr, skb_data_ptr, + (len + 3) & ~3); + skb->dev = dev; + skb_reserve(skb, 3); /* Skip over PRH. */ + skb_put(skb, len - 3); + skb_reset_network_header(skb); + + dev_queue_xmit_nit(skb, dev); + + dev_kfree_skb_irq(skb); + +err_no_skb: + ; + } + + /* Queue the frame to the RMC transmit ring. */ fza_do_xmit((union fza_buffer_txp) { .mmio_ptr = smt_tx_ptr }, len, dev, 1); + } writel_o(FZA_RING_OWN_FZA, &fp->ring_smt_tx[i].own); fp->ring_smt_tx_index = diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 22e4ef7bb701..dc1d9ed33b31 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3645,6 +3645,7 @@ static __always_inline int ____dev_forward_skb(struct net_device *dev, return 0; } +bool dev_nit_active(struct net_device *dev); void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev); extern int netdev_budget; diff --git a/net/core/dev.c b/net/core/dev.c index a4d39b87b4e5..8497feea8fb5 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1976,6 +1976,17 @@ static inline bool skb_loop_sk(struct packet_type *ptype, struct sk_buff *skb) return false; } +/** + * dev_nit_active - return true if any network interface taps are in use + * + * @dev: network device to check for the presence of taps + */ +bool dev_nit_active(struct net_device *dev) +{ + return !list_empty(&ptype_all) || !list_empty(&dev->ptype_all); +} +EXPORT_SYMBOL_GPL(dev_nit_active); + /* * Support routine. Sends outgoing frames to any network * taps currently in use. @@ -3233,7 +3244,7 @@ static int xmit_one(struct sk_buff *skb, struct net_device *dev, unsigned int len; int rc; - if (!list_empty(&ptype_all) || !list_empty(&dev->ptype_all)) + if (dev_nit_active(dev)) dev_queue_xmit_nit(skb, dev); len = skb->len; -- cgit v1.2.3 From 5f6188a8003d080e3753b8f14f4a5a2325ae1ff6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 15 Oct 2018 09:37:52 -0700 Subject: tcp: do not change tcp_wstamp_ns in tcp_mstamp_refresh In EDT design, I made the mistake of using tcp_wstamp_ns to store the last tcp_clock_ns() sample and to store the pacing virtual timer. This causes major regressions at high speed flows. Introduce tcp_clock_cache to store last tcp_clock_ns(). This is needed because some arches have slow high-resolution kernel time service. tcp_wstamp_ns is only updated when a packet is sent. Note that we can remove tcp_mstamp in the future since tcp_mstamp is essentially tcp_clock_cache/1000, so the apparent socket size increase is temporary. Fixes: 9799ccb0e984 ("tcp: add tcp_wstamp_ns socket field") Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + net/ipv4/tcp_output.c | 9 ++++++--- net/ipv4/tcp_timer.c | 2 +- 3 files changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 848f5b25e178..8ed77bb4ed86 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -249,6 +249,7 @@ struct tcp_sock { u32 tlp_high_seq; /* snd_nxt at the time of TLP retransmit. */ u64 tcp_wstamp_ns; /* departure time for next sent data packet */ + u64 tcp_clock_cache; /* cache last tcp_clock_ns() (see tcp_mstamp_refresh()) */ /* RTT measurement */ u64 tcp_mstamp; /* most recent packet received/sent */ diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 059b67af28b1..f14df66a0c85 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -52,9 +52,8 @@ void tcp_mstamp_refresh(struct tcp_sock *tp) { u64 val = tcp_clock_ns(); - /* departure time for next data packet */ - if (val > tp->tcp_wstamp_ns) - tp->tcp_wstamp_ns = val; + if (val > tp->tcp_clock_cache) + tp->tcp_clock_cache = val; val = div_u64(val, NSEC_PER_USEC); if (val > tp->tcp_mstamp) @@ -1050,6 +1049,10 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, if (unlikely(!skb)) return -ENOBUFS; } + + /* TODO: might take care of jitter here */ + tp->tcp_wstamp_ns = max(tp->tcp_wstamp_ns, tp->tcp_clock_cache); + skb->skb_mstamp_ns = tp->tcp_wstamp_ns; inet = inet_sk(sk); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 61023d50cd60..676020663ce8 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -360,7 +360,7 @@ static void tcp_probe_timer(struct sock *sk) */ start_ts = tcp_skb_timestamp(skb); if (!start_ts) - skb->skb_mstamp_ns = tp->tcp_wstamp_ns; + skb->skb_mstamp_ns = tp->tcp_clock_cache; else if (icsk->icsk_user_timeout && (s32)(tcp_time_stamp(tp) - start_ts) > icsk->icsk_user_timeout) goto abort; -- cgit v1.2.3 From 22e6c58b8c2843337ec4e8464b1ce6e869ca5bf4 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 15 Oct 2018 18:56:41 -0700 Subject: netlink: Add answer_flags to netlink_callback With dump filtering we need a way to ensure the NLM_F_DUMP_FILTERED flag is set on a message back to the user if the data returned is influenced by some input attributes. Normally this can be done as messages are added to the skb, but if the filter results in no data being returned, the user could be confused as to why. This patch adds answer_flags to the netlink_callback allowing dump handlers to set the NLM_F_DUMP_FILTERED at a minimum in the NLMSG_DONE message ensuring the flag gets back to the user. The netlink_callback space is initialized to 0 via a memset in __netlink_dump_start, so init of the new answer_flags is covered. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netlink.h | 1 + net/netlink/af_netlink.c | 3 ++- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 72580f1a72a2..4da90a6ab536 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -180,6 +180,7 @@ struct netlink_callback { u16 family; u16 min_dump_alloc; bool strict_check; + u16 answer_flags; unsigned int prev_seq, seq; long args[6]; }; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index e613a9f89600..6bb9f3cde0b0 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2257,7 +2257,8 @@ static int netlink_dump(struct sock *sk) } nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE, - sizeof(nlk->dump_done_errno), NLM_F_MULTI); + sizeof(nlk->dump_done_errno), + NLM_F_MULTI | cb->answer_flags); if (WARN_ON(!nlh)) goto errout_skb; -- cgit v1.2.3 From e1cedae1ba6b09ae8376c1486712bf91ea0dfc41 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 15 Oct 2018 18:56:46 -0700 Subject: ipmr: Refactor mr_rtm_dumproute Move per-table loops from mr_rtm_dumproute to mr_table_dump and export mr_table_dump for dumps by specific table id. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/mroute_base.h | 6 ++++ net/ipv4/ipmr_base.c | 88 ++++++++++++++++++++++++++++----------------- 2 files changed, 61 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h index 6675b9f81979..db85373c8d15 100644 --- a/include/linux/mroute_base.h +++ b/include/linux/mroute_base.h @@ -283,6 +283,12 @@ void *mr_mfc_find_any(struct mr_table *mrt, int vifi, void *hasharg); int mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, struct mr_mfc *c, struct rtmsg *rtm); +int mr_table_dump(struct mr_table *mrt, struct sk_buff *skb, + struct netlink_callback *cb, + int (*fill)(struct mr_table *mrt, struct sk_buff *skb, + u32 portid, u32 seq, struct mr_mfc *c, + int cmd, int flags), + spinlock_t *lock); int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, struct mr_table *(*iter)(struct net *net, struct mr_table *mrt), diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c index 1ad9aa62a97b..132dd2613ca5 100644 --- a/net/ipv4/ipmr_base.c +++ b/net/ipv4/ipmr_base.c @@ -268,6 +268,55 @@ int mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, } EXPORT_SYMBOL(mr_fill_mroute); +int mr_table_dump(struct mr_table *mrt, struct sk_buff *skb, + struct netlink_callback *cb, + int (*fill)(struct mr_table *mrt, struct sk_buff *skb, + u32 portid, u32 seq, struct mr_mfc *c, + int cmd, int flags), + spinlock_t *lock) +{ + unsigned int e = 0, s_e = cb->args[1]; + unsigned int flags = NLM_F_MULTI; + struct mr_mfc *mfc; + int err; + + list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) { + if (e < s_e) + goto next_entry; + + err = fill(mrt, skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, mfc, RTM_NEWROUTE, flags); + if (err < 0) + goto out; +next_entry: + e++; + } + e = 0; + s_e = 0; + + spin_lock_bh(lock); + list_for_each_entry(mfc, &mrt->mfc_unres_queue, list) { + if (e < s_e) + goto next_entry2; + + err = fill(mrt, skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, mfc, RTM_NEWROUTE, flags); + if (err < 0) { + spin_unlock_bh(lock); + goto out; + } +next_entry2: + e++; + } + spin_unlock_bh(lock); + err = 0; + e = 0; + +out: + cb->args[1] = e; + return err; +} + int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, struct mr_table *(*iter)(struct net *net, struct mr_table *mrt), @@ -277,51 +326,24 @@ int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, int cmd, int flags), spinlock_t *lock) { - unsigned int t = 0, e = 0, s_t = cb->args[0], s_e = cb->args[1]; + unsigned int t = 0, s_t = cb->args[0]; struct net *net = sock_net(skb->sk); struct mr_table *mrt; - struct mr_mfc *mfc; + int err; rcu_read_lock(); for (mrt = iter(net, NULL); mrt; mrt = iter(net, mrt)) { if (t < s_t) goto next_table; - list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) { - if (e < s_e) - goto next_entry; - if (fill(mrt, skb, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, mfc, - RTM_NEWROUTE, NLM_F_MULTI) < 0) - goto done; -next_entry: - e++; - } - e = 0; - s_e = 0; - - spin_lock_bh(lock); - list_for_each_entry(mfc, &mrt->mfc_unres_queue, list) { - if (e < s_e) - goto next_entry2; - if (fill(mrt, skb, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, mfc, - RTM_NEWROUTE, NLM_F_MULTI) < 0) { - spin_unlock_bh(lock); - goto done; - } -next_entry2: - e++; - } - spin_unlock_bh(lock); - e = 0; - s_e = 0; + + err = mr_table_dump(mrt, skb, cb, fill, lock); + if (err < 0) + break; next_table: t++; } -done: rcu_read_unlock(); - cb->args[1] = e; cb->args[0] = t; return skb->len; -- cgit v1.2.3 From cb167893f41e21e6bd283d78e53489289dc0592d Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 15 Oct 2018 18:56:47 -0700 Subject: net: Plumb support for filtering ipv4 and ipv6 multicast route dumps Implement kernel side filtering of routes by egress device index and table id. If the table id is given in the filter, lookup table and call mr_table_dump directly for it. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/mroute_base.h | 7 ++++--- net/ipv4/ipmr.c | 18 +++++++++++++++--- net/ipv4/ipmr_base.c | 43 ++++++++++++++++++++++++++++++++++++++++--- net/ipv6/ip6mr.c | 18 +++++++++++++++--- 4 files changed, 74 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h index db85373c8d15..34de06b426ef 100644 --- a/include/linux/mroute_base.h +++ b/include/linux/mroute_base.h @@ -7,6 +7,7 @@ #include #include #include +#include /** * struct vif_device - interface representor for multicast routing @@ -288,7 +289,7 @@ int mr_table_dump(struct mr_table *mrt, struct sk_buff *skb, int (*fill)(struct mr_table *mrt, struct sk_buff *skb, u32 portid, u32 seq, struct mr_mfc *c, int cmd, int flags), - spinlock_t *lock); + spinlock_t *lock, struct fib_dump_filter *filter); int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, struct mr_table *(*iter)(struct net *net, struct mr_table *mrt), @@ -296,7 +297,7 @@ int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, struct sk_buff *skb, u32 portid, u32 seq, struct mr_mfc *c, int cmd, int flags), - spinlock_t *lock); + spinlock_t *lock, struct fib_dump_filter *filter); int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family, int (*rules_dump)(struct net *net, @@ -346,7 +347,7 @@ mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, struct sk_buff *skb, u32 portid, u32 seq, struct mr_mfc *c, int cmd, int flags), - spinlock_t *lock) + spinlock_t *lock, struct fib_dump_filter *filter) { return -EINVAL; } diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 44d777058960..3fa988e6a3df 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -2528,18 +2528,30 @@ errout_free: static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) { struct fib_dump_filter filter = {}; + int err; if (cb->strict_check) { - int err; - err = ip_valid_fib_dump_req(sock_net(skb->sk), cb->nlh, &filter, cb->extack); if (err < 0) return err; } + if (filter.table_id) { + struct mr_table *mrt; + + mrt = ipmr_get_table(sock_net(skb->sk), filter.table_id); + if (!mrt) { + NL_SET_ERR_MSG(cb->extack, "ipv4: MR table does not exist"); + return -ENOENT; + } + err = mr_table_dump(mrt, skb, cb, _ipmr_fill_mroute, + &mfc_unres_lock, &filter); + return skb->len ? : err; + } + return mr_rtm_dumproute(skb, cb, ipmr_mr_table_iter, - _ipmr_fill_mroute, &mfc_unres_lock); + _ipmr_fill_mroute, &mfc_unres_lock, &filter); } static const struct nla_policy rtm_ipmr_policy[RTA_MAX + 1] = { diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c index 132dd2613ca5..844806120f44 100644 --- a/net/ipv4/ipmr_base.c +++ b/net/ipv4/ipmr_base.c @@ -268,21 +268,45 @@ int mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, } EXPORT_SYMBOL(mr_fill_mroute); +static bool mr_mfc_uses_dev(const struct mr_table *mrt, + const struct mr_mfc *c, + const struct net_device *dev) +{ + int ct; + + for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) { + if (VIF_EXISTS(mrt, ct) && c->mfc_un.res.ttls[ct] < 255) { + const struct vif_device *vif; + + vif = &mrt->vif_table[ct]; + if (vif->dev == dev) + return true; + } + } + return false; +} + int mr_table_dump(struct mr_table *mrt, struct sk_buff *skb, struct netlink_callback *cb, int (*fill)(struct mr_table *mrt, struct sk_buff *skb, u32 portid, u32 seq, struct mr_mfc *c, int cmd, int flags), - spinlock_t *lock) + spinlock_t *lock, struct fib_dump_filter *filter) { unsigned int e = 0, s_e = cb->args[1]; unsigned int flags = NLM_F_MULTI; struct mr_mfc *mfc; int err; + if (filter->filter_set) + flags |= NLM_F_DUMP_FILTERED; + list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) { if (e < s_e) goto next_entry; + if (filter->dev && + !mr_mfc_uses_dev(mrt, mfc, filter->dev)) + goto next_entry; err = fill(mrt, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, mfc, RTM_NEWROUTE, flags); @@ -298,6 +322,9 @@ next_entry: list_for_each_entry(mfc, &mrt->mfc_unres_queue, list) { if (e < s_e) goto next_entry2; + if (filter->dev && + !mr_mfc_uses_dev(mrt, mfc, filter->dev)) + goto next_entry2; err = fill(mrt, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, mfc, RTM_NEWROUTE, flags); @@ -316,6 +343,7 @@ out: cb->args[1] = e; return err; } +EXPORT_SYMBOL(mr_table_dump); int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, struct mr_table *(*iter)(struct net *net, @@ -324,19 +352,28 @@ int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, struct sk_buff *skb, u32 portid, u32 seq, struct mr_mfc *c, int cmd, int flags), - spinlock_t *lock) + spinlock_t *lock, struct fib_dump_filter *filter) { unsigned int t = 0, s_t = cb->args[0]; struct net *net = sock_net(skb->sk); struct mr_table *mrt; int err; + /* multicast does not track protocol or have route type other + * than RTN_MULTICAST + */ + if (filter->filter_set) { + if (filter->protocol || filter->flags || + (filter->rt_type && filter->rt_type != RTN_MULTICAST)) + return skb->len; + } + rcu_read_lock(); for (mrt = iter(net, NULL); mrt; mrt = iter(net, mrt)) { if (t < s_t) goto next_table; - err = mr_table_dump(mrt, skb, cb, fill, lock); + err = mr_table_dump(mrt, skb, cb, fill, lock, filter); if (err < 0) break; next_table: diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index dbd5166c5599..9759b0aecdd6 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -2459,16 +2459,28 @@ static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; struct fib_dump_filter filter = {}; + int err; if (cb->strict_check) { - int err; - err = ip_valid_fib_dump_req(sock_net(skb->sk), nlh, &filter, cb->extack); if (err < 0) return err; } + if (filter.table_id) { + struct mr_table *mrt; + + mrt = ip6mr_get_table(sock_net(skb->sk), filter.table_id); + if (!mrt) { + NL_SET_ERR_MSG_MOD(cb->extack, "MR table does not exist"); + return -ENOENT; + } + err = mr_table_dump(mrt, skb, cb, _ip6mr_fill_mroute, + &mfc_unres_lock, &filter); + return skb->len ? : err; + } + return mr_rtm_dumproute(skb, cb, ip6mr_mr_table_iter, - _ip6mr_fill_mroute, &mfc_unres_lock); + _ip6mr_fill_mroute, &mfc_unres_lock, &filter); } -- cgit v1.2.3 From a218dc82f0b5c6c8ad3d58c9870ed69e26c08b3e Mon Sep 17 00:00:00 2001 From: Fernando Fernandez Mancera Date: Wed, 10 Oct 2018 09:57:13 +0200 Subject: netfilter: nft_osf: Add ttl option support Add ttl option support to the nftables "osf" expression. Signed-off-by: Fernando Fernandez Mancera Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nfnetlink_osf.h | 3 ++- include/uapi/linux/netfilter/nf_tables.h | 7 +++++ net/netfilter/nfnetlink_osf.c | 46 +++++++++++++++----------------- net/netfilter/nft_osf.c | 15 ++++++++++- 4 files changed, 44 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink_osf.h b/include/linux/netfilter/nfnetlink_osf.h index ecf7dab81e9e..c6000046c966 100644 --- a/include/linux/netfilter/nfnetlink_osf.h +++ b/include/linux/netfilter/nfnetlink_osf.h @@ -27,6 +27,7 @@ bool nf_osf_match(const struct sk_buff *skb, u_int8_t family, const struct list_head *nf_osf_fingers); const char *nf_osf_find(const struct sk_buff *skb, - const struct list_head *nf_osf_fingers); + const struct list_head *nf_osf_fingers, + const int ttl_check); #endif /* _NFOSF_H */ diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 5444e76870bb..579974b0bf0d 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1511,9 +1511,16 @@ enum nft_flowtable_hook_attributes { }; #define NFTA_FLOWTABLE_HOOK_MAX (__NFTA_FLOWTABLE_HOOK_MAX - 1) +/** + * enum nft_osf_attributes - nftables osf expression netlink attributes + * + * @NFTA_OSF_DREG: destination register (NLA_U32: nft_registers) + * @NFTA_OSF_TTL: Value of the TTL osf option (NLA_U8) + */ enum nft_osf_attributes { NFTA_OSF_UNSPEC, NFTA_OSF_DREG, + NFTA_OSF_TTL, __NFTA_OSF_MAX, }; #define NFTA_OSF_MAX (__NFTA_OSF_MAX - 1) diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c index 00db27dfd2ff..6f41dd74729d 100644 --- a/net/netfilter/nfnetlink_osf.c +++ b/net/netfilter/nfnetlink_osf.c @@ -30,32 +30,27 @@ EXPORT_SYMBOL_GPL(nf_osf_fingers); static inline int nf_osf_ttl(const struct sk_buff *skb, int ttl_check, unsigned char f_ttl) { + struct in_device *in_dev = __in_dev_get_rcu(skb->dev); const struct iphdr *ip = ip_hdr(skb); - - if (ttl_check != -1) { - if (ttl_check == NF_OSF_TTL_TRUE) - return ip->ttl == f_ttl; - if (ttl_check == NF_OSF_TTL_NOCHECK) - return 1; - else if (ip->ttl <= f_ttl) - return 1; - else { - struct in_device *in_dev = __in_dev_get_rcu(skb->dev); - int ret = 0; - - for_ifa(in_dev) { - if (inet_ifa_match(ip->saddr, ifa)) { - ret = (ip->ttl == f_ttl); - break; - } - } - endfor_ifa(in_dev); - - return ret; + int ret = 0; + + if (ttl_check == NF_OSF_TTL_TRUE) + return ip->ttl == f_ttl; + if (ttl_check == NF_OSF_TTL_NOCHECK) + return 1; + else if (ip->ttl <= f_ttl) + return 1; + + for_ifa(in_dev) { + if (inet_ifa_match(ip->saddr, ifa)) { + ret = (ip->ttl == f_ttl); + break; } } - return ip->ttl == f_ttl; + endfor_ifa(in_dev); + + return ret; } struct nf_osf_hdr_ctx { @@ -213,7 +208,7 @@ nf_osf_match(const struct sk_buff *skb, u_int8_t family, if (!tcp) return false; - ttl_check = (info->flags & NF_OSF_TTL) ? info->ttl : -1; + ttl_check = (info->flags & NF_OSF_TTL) ? info->ttl : 0; list_for_each_entry_rcu(kf, &nf_osf_fingers[ctx.df], finger_entry) { @@ -257,7 +252,8 @@ nf_osf_match(const struct sk_buff *skb, u_int8_t family, EXPORT_SYMBOL_GPL(nf_osf_match); const char *nf_osf_find(const struct sk_buff *skb, - const struct list_head *nf_osf_fingers) + const struct list_head *nf_osf_fingers, + const int ttl_check) { const struct iphdr *ip = ip_hdr(skb); const struct nf_osf_user_finger *f; @@ -275,7 +271,7 @@ const char *nf_osf_find(const struct sk_buff *skb, list_for_each_entry_rcu(kf, &nf_osf_fingers[ctx.df], finger_entry) { f = &kf->finger; - if (!nf_osf_match_one(skb, f, -1, &ctx)) + if (!nf_osf_match_one(skb, f, ttl_check, &ctx)) continue; genre = f->genre; diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c index a35fb59ace73..0b452fd470c4 100644 --- a/net/netfilter/nft_osf.c +++ b/net/netfilter/nft_osf.c @@ -6,10 +6,12 @@ struct nft_osf { enum nft_registers dreg:8; + u8 ttl; }; static const struct nla_policy nft_osf_policy[NFTA_OSF_MAX + 1] = { [NFTA_OSF_DREG] = { .type = NLA_U32 }, + [NFTA_OSF_TTL] = { .type = NLA_U8 }, }; static void nft_osf_eval(const struct nft_expr *expr, struct nft_regs *regs, @@ -33,7 +35,7 @@ static void nft_osf_eval(const struct nft_expr *expr, struct nft_regs *regs, return; } - os_name = nf_osf_find(skb, nf_osf_fingers); + os_name = nf_osf_find(skb, nf_osf_fingers, priv->ttl); if (!os_name) strncpy((char *)dest, "unknown", NFT_OSF_MAXGENRELEN); else @@ -46,6 +48,14 @@ static int nft_osf_init(const struct nft_ctx *ctx, { struct nft_osf *priv = nft_expr_priv(expr); int err; + u8 ttl; + + if (nla_get_u8(tb[NFTA_OSF_TTL])) { + ttl = nla_get_u8(tb[NFTA_OSF_TTL]); + if (ttl > 2) + return -EINVAL; + priv->ttl = ttl; + } priv->dreg = nft_parse_register(tb[NFTA_OSF_DREG]); err = nft_validate_register_store(ctx, priv->dreg, NULL, @@ -60,6 +70,9 @@ static int nft_osf_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_osf *priv = nft_expr_priv(expr); + if (nla_put_u8(skb, NFTA_OSF_TTL, priv->ttl)) + goto nla_put_failure; + if (nft_dump_register(skb, NFTA_OSF_DREG, priv->dreg)) goto nla_put_failure; -- cgit v1.2.3 From 4cf841e398503990df640f7a7c5b2ea56f11c08c Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Mon, 15 Oct 2018 16:11:31 -0700 Subject: ACPI/ADXL: Add address translation interface using an ACPI DSM Some new Intel servers provide an interface so that the OS can ask the BIOS to translate a system physical address to a memory address (socket, memory controller, channel, rank, dimm, etc.). This is useful for EDAC drivers that want to take the address of an error reported in a machine check bank and let the user know which DIMM may need to be replaced. Specification for this interface is available at: https://cdrdv2.intel.com/v1/dl/getContent/603354 [ Based on earlier code by Qiuxu Zhuo . ] [ bp: Make the first pr_info() in adxl_init() pr_debug() so that it doesn't pollute every dmesg. ] Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov Acked-by: Rafael J. Wysocki Tested-by: Qiuxu Zhuo CC: Len Brown CC: linux-acpi@vger.kernel.org CC: linux-edac@vger.kernel.org Link: http://lkml.kernel.org/r/20181015202620.23610-1-tony.luck@intel.com --- drivers/acpi/Kconfig | 3 + drivers/acpi/Makefile | 3 + drivers/acpi/acpi_adxl.c | 192 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/adxl.h | 13 ++++ 4 files changed, 211 insertions(+) create mode 100644 drivers/acpi/acpi_adxl.c create mode 100644 include/linux/adxl.h (limited to 'include/linux') diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index dd1eea90f67f..09991cc91b89 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -498,6 +498,9 @@ config ACPI_EXTLOG driver adds support for that functionality with corresponding tracepoint which carries that information to userspace. +config ACPI_ADXL + bool + menuconfig PMIC_OPREGION bool "PMIC (Power Management Integrated Circuit) operation region support" help diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile index 6d59aa109a91..edc039313cd6 100644 --- a/drivers/acpi/Makefile +++ b/drivers/acpi/Makefile @@ -61,6 +61,9 @@ acpi-$(CONFIG_ACPI_LPIT) += acpi_lpit.o acpi-$(CONFIG_ACPI_GENERIC_GSI) += irq.o acpi-$(CONFIG_ACPI_WATCHDOG) += acpi_watchdog.o +# Address translation +acpi-$(CONFIG_ACPI_ADXL) += acpi_adxl.o + # These are (potentially) separate modules # IPMI may be used by other drivers, so it has to initialise before them diff --git a/drivers/acpi/acpi_adxl.c b/drivers/acpi/acpi_adxl.c new file mode 100644 index 000000000000..13c8f7b50c46 --- /dev/null +++ b/drivers/acpi/acpi_adxl.c @@ -0,0 +1,192 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Address translation interface via ACPI DSM. + * Copyright (C) 2018 Intel Corporation + * + * Specification for this interface is available at: + * + * https://cdrdv2.intel.com/v1/dl/getContent/603354 + */ + +#include +#include + +#define ADXL_REVISION 0x1 +#define ADXL_IDX_GET_ADDR_PARAMS 0x1 +#define ADXL_IDX_FORWARD_TRANSLATE 0x2 +#define ACPI_ADXL_PATH "\\_SB.ADXL" + +/* + * The specification doesn't provide a limit on how many + * components are in a memory address. But since we allocate + * memory based on the number the BIOS tells us, we should + * defend against insane values. + */ +#define ADXL_MAX_COMPONENTS 500 + +#undef pr_fmt +#define pr_fmt(fmt) "ADXL: " fmt + +static acpi_handle handle; +static union acpi_object *params; +static const guid_t adxl_guid = + GUID_INIT(0xAA3C050A, 0x7EA4, 0x4C1F, + 0xAF, 0xDA, 0x12, 0x67, 0xDF, 0xD3, 0xD4, 0x8D); + +static int adxl_count; +static char **adxl_component_names; + +static union acpi_object *adxl_dsm(int cmd, union acpi_object argv[]) +{ + union acpi_object *obj, *o; + + obj = acpi_evaluate_dsm_typed(handle, &adxl_guid, ADXL_REVISION, + cmd, argv, ACPI_TYPE_PACKAGE); + if (!obj) { + pr_info("DSM call failed for cmd=%d\n", cmd); + return NULL; + } + + if (obj->package.count != 2) { + pr_info("Bad pkg count %d\n", obj->package.count); + goto err; + } + + o = obj->package.elements; + if (o->type != ACPI_TYPE_INTEGER) { + pr_info("Bad 1st element type %d\n", o->type); + goto err; + } + if (o->integer.value) { + pr_info("Bad ret val %llu\n", o->integer.value); + goto err; + } + + o = obj->package.elements + 1; + if (o->type != ACPI_TYPE_PACKAGE) { + pr_info("Bad 2nd element type %d\n", o->type); + goto err; + } + return obj; + +err: + ACPI_FREE(obj); + return NULL; +} + +/** + * adxl_get_component_names - get list of memory component names + * Returns NULL terminated list of string names + * + * Give the caller a pointer to the list of memory component names + * e.g. { "SystemAddress", "ProcessorSocketId", "ChannelId", ... NULL } + * Caller should count how many strings in order to allocate a buffer + * for the return from adxl_decode(). + */ +const char * const *adxl_get_component_names(void) +{ + return (const char * const *)adxl_component_names; +} +EXPORT_SYMBOL_GPL(adxl_get_component_names); + +/** + * adxl_decode - ask BIOS to decode a system address to memory address + * @addr: the address to decode + * @component_values: pointer to array of values for each component + * Returns 0 on success, negative error code otherwise + * + * The index of each value returned in the array matches the index of + * each component name returned by adxl_get_component_names(). + * Components that are not defined for this address translation (e.g. + * mirror channel number for a non-mirrored address) are set to ~0ull. + */ +int adxl_decode(u64 addr, u64 component_values[]) +{ + union acpi_object argv4[2], *results, *r; + int i, cnt; + + if (!adxl_component_names) + return -EOPNOTSUPP; + + argv4[0].type = ACPI_TYPE_PACKAGE; + argv4[0].package.count = 1; + argv4[0].package.elements = &argv4[1]; + argv4[1].integer.type = ACPI_TYPE_INTEGER; + argv4[1].integer.value = addr; + + results = adxl_dsm(ADXL_IDX_FORWARD_TRANSLATE, argv4); + if (!results) + return -EINVAL; + + r = results->package.elements + 1; + cnt = r->package.count; + if (cnt != adxl_count) { + ACPI_FREE(results); + return -EINVAL; + } + r = r->package.elements; + + for (i = 0; i < cnt; i++) + component_values[i] = r[i].integer.value; + + ACPI_FREE(results); + + return 0; +} +EXPORT_SYMBOL_GPL(adxl_decode); + +static int __init adxl_init(void) +{ + char *path = ACPI_ADXL_PATH; + union acpi_object *p; + acpi_status status; + int i; + + status = acpi_get_handle(NULL, path, &handle); + if (ACPI_FAILURE(status)) { + pr_debug("No ACPI handle for path %s\n", path); + return -ENODEV; + } + + if (!acpi_has_method(handle, "_DSM")) { + pr_info("No DSM method\n"); + return -ENODEV; + } + + if (!acpi_check_dsm(handle, &adxl_guid, ADXL_REVISION, + ADXL_IDX_GET_ADDR_PARAMS | + ADXL_IDX_FORWARD_TRANSLATE)) { + pr_info("DSM method does not support forward translate\n"); + return -ENODEV; + } + + params = adxl_dsm(ADXL_IDX_GET_ADDR_PARAMS, NULL); + if (!params) { + pr_info("Failed to get component names\n"); + return -ENODEV; + } + + p = params->package.elements + 1; + adxl_count = p->package.count; + if (adxl_count > ADXL_MAX_COMPONENTS) { + pr_info("Insane number of address component names %d\n", adxl_count); + ACPI_FREE(params); + return -ENODEV; + } + p = p->package.elements; + + /* + * Allocate one extra for NULL termination. + */ + adxl_component_names = kcalloc(adxl_count + 1, sizeof(char *), GFP_KERNEL); + if (!adxl_component_names) { + ACPI_FREE(params); + return -ENOMEM; + } + + for (i = 0; i < adxl_count; i++) + adxl_component_names[i] = p[i].string.pointer; + + return 0; +} +subsys_initcall(adxl_init); diff --git a/include/linux/adxl.h b/include/linux/adxl.h new file mode 100644 index 000000000000..2a629acb4c3f --- /dev/null +++ b/include/linux/adxl.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Address translation interface via ACPI DSM. + * Copyright (C) 2018 Intel Corporation + */ + +#ifndef _LINUX_ADXL_H +#define _LINUX_ADXL_H + +const char * const *adxl_get_component_names(void); +int adxl_decode(u64 addr, u64 component_values[]); + +#endif /* _LINUX_ADXL_H */ -- cgit v1.2.3 From 084181fe8cc7472695b907f0018f4cd00934cb12 Mon Sep 17 00:00:00 2001 From: Alan Tull Date: Mon, 15 Oct 2018 17:20:01 -0500 Subject: fpga: mgr: add devm_fpga_mgr_create Add devm_fpga_mgr_create() which is the managed version of fpga_mgr_create(). Change current FPGA manager drivers to use devm_fpga_mgr_create() Signed-off-by: Alan Tull Suggested-by: Federico Vaga Acked-by: Moritz Fischer Signed-off-by: Greg Kroah-Hartman --- Documentation/driver-api/fpga/fpga-mgr.rst | 13 +++--- drivers/fpga/altera-cvp.c | 8 ++-- drivers/fpga/altera-pr-ip-core.c | 9 +---- drivers/fpga/altera-ps-spi.c | 11 ++--- drivers/fpga/dfl-fme-mgr.c | 11 ++--- drivers/fpga/fpga-mgr.c | 64 ++++++++++++++++++++++++++---- drivers/fpga/ice40-spi.c | 10 ++--- drivers/fpga/machxo2-spi.c | 11 ++--- drivers/fpga/socfpga-a10.c | 5 +-- drivers/fpga/socfpga.c | 10 ++--- drivers/fpga/ts73xx-fpga.c | 11 ++--- drivers/fpga/xilinx-spi.c | 12 ++---- drivers/fpga/zynq-fpga.c | 5 +-- include/linux/fpga/fpga-mgr.h | 4 ++ 14 files changed, 97 insertions(+), 87 deletions(-) (limited to 'include/linux') diff --git a/Documentation/driver-api/fpga/fpga-mgr.rst b/Documentation/driver-api/fpga/fpga-mgr.rst index 82b6dbbd31cd..db8885efbc22 100644 --- a/Documentation/driver-api/fpga/fpga-mgr.rst +++ b/Documentation/driver-api/fpga/fpga-mgr.rst @@ -49,18 +49,14 @@ probe function calls fpga_mgr_register(), such as:: * them in priv */ - mgr = fpga_mgr_create(dev, "Altera SOCFPGA FPGA Manager", - &socfpga_fpga_ops, priv); + mgr = devm_fpga_mgr_create(dev, "Altera SOCFPGA FPGA Manager", + &socfpga_fpga_ops, priv); if (!mgr) return -ENOMEM; platform_set_drvdata(pdev, mgr); - ret = fpga_mgr_register(mgr); - if (ret) - fpga_mgr_free(mgr); - - return ret; + return fpga_mgr_register(mgr); } static int socfpga_fpga_remove(struct platform_device *pdev) @@ -169,6 +165,9 @@ API for implementing a new FPGA Manager driver .. kernel-doc:: include/linux/fpga/fpga-mgr.h :functions: fpga_manager_ops +.. kernel-doc:: drivers/fpga/fpga-mgr.c + :functions: devm_fpga_mgr_create + .. kernel-doc:: drivers/fpga/fpga-mgr.c :functions: fpga_mgr_create diff --git a/drivers/fpga/altera-cvp.c b/drivers/fpga/altera-cvp.c index 7fa793672a7a..610a1558e0ed 100644 --- a/drivers/fpga/altera-cvp.c +++ b/drivers/fpga/altera-cvp.c @@ -453,8 +453,8 @@ static int altera_cvp_probe(struct pci_dev *pdev, snprintf(conf->mgr_name, sizeof(conf->mgr_name), "%s @%s", ALTERA_CVP_MGR_NAME, pci_name(pdev)); - mgr = fpga_mgr_create(&pdev->dev, conf->mgr_name, - &altera_cvp_ops, conf); + mgr = devm_fpga_mgr_create(&pdev->dev, conf->mgr_name, + &altera_cvp_ops, conf); if (!mgr) { ret = -ENOMEM; goto err_unmap; @@ -463,10 +463,8 @@ static int altera_cvp_probe(struct pci_dev *pdev, pci_set_drvdata(pdev, mgr); ret = fpga_mgr_register(mgr); - if (ret) { - fpga_mgr_free(mgr); + if (ret) goto err_unmap; - } ret = driver_create_file(&altera_cvp_driver.driver, &driver_attr_chkcfg); diff --git a/drivers/fpga/altera-pr-ip-core.c b/drivers/fpga/altera-pr-ip-core.c index 65e0b6a2c031..a7a3bf0b5202 100644 --- a/drivers/fpga/altera-pr-ip-core.c +++ b/drivers/fpga/altera-pr-ip-core.c @@ -177,7 +177,6 @@ int alt_pr_register(struct device *dev, void __iomem *reg_base) { struct alt_pr_priv *priv; struct fpga_manager *mgr; - int ret; u32 val; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); @@ -192,17 +191,13 @@ int alt_pr_register(struct device *dev, void __iomem *reg_base) (val & ALT_PR_CSR_STATUS_MSK) >> ALT_PR_CSR_STATUS_SFT, (int)(val & ALT_PR_CSR_PR_START)); - mgr = fpga_mgr_create(dev, dev_name(dev), &alt_pr_ops, priv); + mgr = devm_fpga_mgr_create(dev, dev_name(dev), &alt_pr_ops, priv); if (!mgr) return -ENOMEM; dev_set_drvdata(dev, mgr); - ret = fpga_mgr_register(mgr); - if (ret) - fpga_mgr_free(mgr); - - return ret; + return fpga_mgr_register(mgr); } EXPORT_SYMBOL_GPL(alt_pr_register); diff --git a/drivers/fpga/altera-ps-spi.c b/drivers/fpga/altera-ps-spi.c index 24b25c626036..33aafda50af5 100644 --- a/drivers/fpga/altera-ps-spi.c +++ b/drivers/fpga/altera-ps-spi.c @@ -239,7 +239,6 @@ static int altera_ps_probe(struct spi_device *spi) struct altera_ps_conf *conf; const struct of_device_id *of_id; struct fpga_manager *mgr; - int ret; conf = devm_kzalloc(&spi->dev, sizeof(*conf), GFP_KERNEL); if (!conf) @@ -275,18 +274,14 @@ static int altera_ps_probe(struct spi_device *spi) snprintf(conf->mgr_name, sizeof(conf->mgr_name), "%s %s", dev_driver_string(&spi->dev), dev_name(&spi->dev)); - mgr = fpga_mgr_create(&spi->dev, conf->mgr_name, - &altera_ps_ops, conf); + mgr = devm_fpga_mgr_create(&spi->dev, conf->mgr_name, + &altera_ps_ops, conf); if (!mgr) return -ENOMEM; spi_set_drvdata(spi, mgr); - ret = fpga_mgr_register(mgr); - if (ret) - fpga_mgr_free(mgr); - - return ret; + return fpga_mgr_register(mgr); } static int altera_ps_remove(struct spi_device *spi) diff --git a/drivers/fpga/dfl-fme-mgr.c b/drivers/fpga/dfl-fme-mgr.c index 9f045d058cfd..76f37709dd1a 100644 --- a/drivers/fpga/dfl-fme-mgr.c +++ b/drivers/fpga/dfl-fme-mgr.c @@ -287,7 +287,6 @@ static int fme_mgr_probe(struct platform_device *pdev) struct fme_mgr_priv *priv; struct fpga_manager *mgr; struct resource *res; - int ret; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); if (!priv) @@ -309,19 +308,15 @@ static int fme_mgr_probe(struct platform_device *pdev) fme_mgr_get_compat_id(priv->ioaddr, compat_id); - mgr = fpga_mgr_create(dev, "DFL FME FPGA Manager", - &fme_mgr_ops, priv); + mgr = devm_fpga_mgr_create(dev, "DFL FME FPGA Manager", + &fme_mgr_ops, priv); if (!mgr) return -ENOMEM; mgr->compat_id = compat_id; platform_set_drvdata(pdev, mgr); - ret = fpga_mgr_register(mgr); - if (ret) - fpga_mgr_free(mgr); - - return ret; + return fpga_mgr_register(mgr); } static int fme_mgr_remove(struct platform_device *pdev) diff --git a/drivers/fpga/fpga-mgr.c b/drivers/fpga/fpga-mgr.c index a41b07e37884..c3866816456a 100644 --- a/drivers/fpga/fpga-mgr.c +++ b/drivers/fpga/fpga-mgr.c @@ -558,6 +558,9 @@ EXPORT_SYMBOL_GPL(fpga_mgr_unlock); * @mops: pointer to structure of fpga manager ops * @priv: fpga manager private data * + * The caller of this function is responsible for freeing the struct with + * fpga_mgr_free(). Using devm_fpga_mgr_create() instead is recommended. + * * Return: pointer to struct fpga_manager or NULL */ struct fpga_manager *fpga_mgr_create(struct device *dev, const char *name, @@ -618,8 +621,8 @@ error_kfree: EXPORT_SYMBOL_GPL(fpga_mgr_create); /** - * fpga_mgr_free - deallocate a FPGA manager - * @mgr: fpga manager struct created by fpga_mgr_create + * fpga_mgr_free - free a FPGA manager created with fpga_mgr_create() + * @mgr: fpga manager struct */ void fpga_mgr_free(struct fpga_manager *mgr) { @@ -628,9 +631,55 @@ void fpga_mgr_free(struct fpga_manager *mgr) } EXPORT_SYMBOL_GPL(fpga_mgr_free); +static void devm_fpga_mgr_release(struct device *dev, void *res) +{ + struct fpga_manager *mgr = *(struct fpga_manager **)res; + + fpga_mgr_free(mgr); +} + +/** + * devm_fpga_mgr_create - create and initialize a managed FPGA manager struct + * @dev: fpga manager device from pdev + * @name: fpga manager name + * @mops: pointer to structure of fpga manager ops + * @priv: fpga manager private data + * + * This function is intended for use in a FPGA manager driver's probe function. + * After the manager driver creates the manager struct with + * devm_fpga_mgr_create(), it should register it with fpga_mgr_register(). The + * manager driver's remove function should call fpga_mgr_unregister(). The + * manager struct allocated with this function will be freed automatically on + * driver detach. This includes the case of a probe function returning error + * before calling fpga_mgr_register(), the struct will still get cleaned up. + * + * Return: pointer to struct fpga_manager or NULL + */ +struct fpga_manager *devm_fpga_mgr_create(struct device *dev, const char *name, + const struct fpga_manager_ops *mops, + void *priv) +{ + struct fpga_manager **ptr, *mgr; + + ptr = devres_alloc(devm_fpga_mgr_release, sizeof(*ptr), GFP_KERNEL); + if (!ptr) + return NULL; + + mgr = fpga_mgr_create(dev, name, mops, priv); + if (!mgr) { + devres_free(ptr); + } else { + *ptr = mgr; + devres_add(dev, ptr); + } + + return mgr; +} +EXPORT_SYMBOL_GPL(devm_fpga_mgr_create); + /** * fpga_mgr_register - register a FPGA manager - * @mgr: fpga manager struct created by fpga_mgr_create + * @mgr: fpga manager struct * * Return: 0 on success, negative error code otherwise. */ @@ -661,8 +710,10 @@ error_device: EXPORT_SYMBOL_GPL(fpga_mgr_register); /** - * fpga_mgr_unregister - unregister and free a FPGA manager - * @mgr: fpga manager struct + * fpga_mgr_unregister - unregister a FPGA manager + * @mgr: fpga manager struct + * + * This function is intended for use in a FPGA manager driver's remove function. */ void fpga_mgr_unregister(struct fpga_manager *mgr) { @@ -681,9 +732,6 @@ EXPORT_SYMBOL_GPL(fpga_mgr_unregister); static void fpga_mgr_dev_release(struct device *dev) { - struct fpga_manager *mgr = to_fpga_manager(dev); - - fpga_mgr_free(mgr); } static int __init fpga_mgr_class_init(void) diff --git a/drivers/fpga/ice40-spi.c b/drivers/fpga/ice40-spi.c index 5981c7ee7a7d..6154661b8f76 100644 --- a/drivers/fpga/ice40-spi.c +++ b/drivers/fpga/ice40-spi.c @@ -175,18 +175,14 @@ static int ice40_fpga_probe(struct spi_device *spi) return ret; } - mgr = fpga_mgr_create(dev, "Lattice iCE40 FPGA Manager", - &ice40_fpga_ops, priv); + mgr = devm_fpga_mgr_create(dev, "Lattice iCE40 FPGA Manager", + &ice40_fpga_ops, priv); if (!mgr) return -ENOMEM; spi_set_drvdata(spi, mgr); - ret = fpga_mgr_register(mgr); - if (ret) - fpga_mgr_free(mgr); - - return ret; + return fpga_mgr_register(mgr); } static int ice40_fpga_remove(struct spi_device *spi) diff --git a/drivers/fpga/machxo2-spi.c b/drivers/fpga/machxo2-spi.c index a582e0000c97..4d8a87641587 100644 --- a/drivers/fpga/machxo2-spi.c +++ b/drivers/fpga/machxo2-spi.c @@ -356,25 +356,20 @@ static int machxo2_spi_probe(struct spi_device *spi) { struct device *dev = &spi->dev; struct fpga_manager *mgr; - int ret; if (spi->max_speed_hz > MACHXO2_MAX_SPEED) { dev_err(dev, "Speed is too high\n"); return -EINVAL; } - mgr = fpga_mgr_create(dev, "Lattice MachXO2 SPI FPGA Manager", - &machxo2_ops, spi); + mgr = devm_fpga_mgr_create(dev, "Lattice MachXO2 SPI FPGA Manager", + &machxo2_ops, spi); if (!mgr) return -ENOMEM; spi_set_drvdata(spi, mgr); - ret = fpga_mgr_register(mgr); - if (ret) - fpga_mgr_free(mgr); - - return ret; + return fpga_mgr_register(mgr); } static int machxo2_spi_remove(struct spi_device *spi) diff --git a/drivers/fpga/socfpga-a10.c b/drivers/fpga/socfpga-a10.c index be30c48eb6e4..573d88bdf730 100644 --- a/drivers/fpga/socfpga-a10.c +++ b/drivers/fpga/socfpga-a10.c @@ -508,8 +508,8 @@ static int socfpga_a10_fpga_probe(struct platform_device *pdev) return -EBUSY; } - mgr = fpga_mgr_create(dev, "SoCFPGA Arria10 FPGA Manager", - &socfpga_a10_fpga_mgr_ops, priv); + mgr = devm_fpga_mgr_create(dev, "SoCFPGA Arria10 FPGA Manager", + &socfpga_a10_fpga_mgr_ops, priv); if (!mgr) return -ENOMEM; @@ -517,7 +517,6 @@ static int socfpga_a10_fpga_probe(struct platform_device *pdev) ret = fpga_mgr_register(mgr); if (ret) { - fpga_mgr_free(mgr); clk_disable_unprepare(priv->clk); return ret; } diff --git a/drivers/fpga/socfpga.c b/drivers/fpga/socfpga.c index 959d71f26896..4a8a2fcd4e6c 100644 --- a/drivers/fpga/socfpga.c +++ b/drivers/fpga/socfpga.c @@ -571,18 +571,14 @@ static int socfpga_fpga_probe(struct platform_device *pdev) if (ret) return ret; - mgr = fpga_mgr_create(dev, "Altera SOCFPGA FPGA Manager", - &socfpga_fpga_ops, priv); + mgr = devm_fpga_mgr_create(dev, "Altera SOCFPGA FPGA Manager", + &socfpga_fpga_ops, priv); if (!mgr) return -ENOMEM; platform_set_drvdata(pdev, mgr); - ret = fpga_mgr_register(mgr); - if (ret) - fpga_mgr_free(mgr); - - return ret; + return fpga_mgr_register(mgr); } static int socfpga_fpga_remove(struct platform_device *pdev) diff --git a/drivers/fpga/ts73xx-fpga.c b/drivers/fpga/ts73xx-fpga.c index 08efd1895b1b..dc22a5842609 100644 --- a/drivers/fpga/ts73xx-fpga.c +++ b/drivers/fpga/ts73xx-fpga.c @@ -118,7 +118,6 @@ static int ts73xx_fpga_probe(struct platform_device *pdev) struct ts73xx_fpga_priv *priv; struct fpga_manager *mgr; struct resource *res; - int ret; priv = devm_kzalloc(kdev, sizeof(*priv), GFP_KERNEL); if (!priv) @@ -133,18 +132,14 @@ static int ts73xx_fpga_probe(struct platform_device *pdev) return PTR_ERR(priv->io_base); } - mgr = fpga_mgr_create(kdev, "TS-73xx FPGA Manager", - &ts73xx_fpga_ops, priv); + mgr = devm_fpga_mgr_create(kdev, "TS-73xx FPGA Manager", + &ts73xx_fpga_ops, priv); if (!mgr) return -ENOMEM; platform_set_drvdata(pdev, mgr); - ret = fpga_mgr_register(mgr); - if (ret) - fpga_mgr_free(mgr); - - return ret; + return fpga_mgr_register(mgr); } static int ts73xx_fpga_remove(struct platform_device *pdev) diff --git a/drivers/fpga/xilinx-spi.c b/drivers/fpga/xilinx-spi.c index 8d1945966533..469486be20c4 100644 --- a/drivers/fpga/xilinx-spi.c +++ b/drivers/fpga/xilinx-spi.c @@ -144,7 +144,6 @@ static int xilinx_spi_probe(struct spi_device *spi) { struct xilinx_spi_conf *conf; struct fpga_manager *mgr; - int ret; conf = devm_kzalloc(&spi->dev, sizeof(*conf), GFP_KERNEL); if (!conf) @@ -167,18 +166,15 @@ static int xilinx_spi_probe(struct spi_device *spi) return PTR_ERR(conf->done); } - mgr = fpga_mgr_create(&spi->dev, "Xilinx Slave Serial FPGA Manager", - &xilinx_spi_ops, conf); + mgr = devm_fpga_mgr_create(&spi->dev, + "Xilinx Slave Serial FPGA Manager", + &xilinx_spi_ops, conf); if (!mgr) return -ENOMEM; spi_set_drvdata(spi, mgr); - ret = fpga_mgr_register(mgr); - if (ret) - fpga_mgr_free(mgr); - - return ret; + return fpga_mgr_register(mgr); } static int xilinx_spi_remove(struct spi_device *spi) diff --git a/drivers/fpga/zynq-fpga.c b/drivers/fpga/zynq-fpga.c index 3110e00121ca..bb82efeebb9d 100644 --- a/drivers/fpga/zynq-fpga.c +++ b/drivers/fpga/zynq-fpga.c @@ -614,8 +614,8 @@ static int zynq_fpga_probe(struct platform_device *pdev) clk_disable(priv->clk); - mgr = fpga_mgr_create(dev, "Xilinx Zynq FPGA Manager", - &zynq_fpga_ops, priv); + mgr = devm_fpga_mgr_create(dev, "Xilinx Zynq FPGA Manager", + &zynq_fpga_ops, priv); if (!mgr) return -ENOMEM; @@ -624,7 +624,6 @@ static int zynq_fpga_probe(struct platform_device *pdev) err = fpga_mgr_register(mgr); if (err) { dev_err(dev, "unable to register FPGA manager\n"); - fpga_mgr_free(mgr); clk_unprepare(priv->clk); return err; } diff --git a/include/linux/fpga/fpga-mgr.h b/include/linux/fpga/fpga-mgr.h index 8ab5df769923..e8ca62b2cb5b 100644 --- a/include/linux/fpga/fpga-mgr.h +++ b/include/linux/fpga/fpga-mgr.h @@ -198,4 +198,8 @@ void fpga_mgr_free(struct fpga_manager *mgr); int fpga_mgr_register(struct fpga_manager *mgr); void fpga_mgr_unregister(struct fpga_manager *mgr); +struct fpga_manager *devm_fpga_mgr_create(struct device *dev, const char *name, + const struct fpga_manager_ops *mops, + void *priv); + #endif /*_LINUX_FPGA_MGR_H */ -- cgit v1.2.3 From 213befe049c70cfcfcbb4f6010bd5276dbc1f7b9 Mon Sep 17 00:00:00 2001 From: Alan Tull Date: Mon, 15 Oct 2018 17:20:02 -0500 Subject: fpga: bridge: add devm_fpga_bridge_create Add devm_fpga_bridge_create() which is the managed version of fpga_bridge_create(). Change current bridge drivers to use devm_fpga_bridge_create(). Signed-off-by: Alan Tull Suggested-by: Federico Vaga Acked-by: Moritz Fischer Signed-off-by: Greg Kroah-Hartman --- Documentation/driver-api/fpga/fpga-bridge.rst | 3 ++ drivers/fpga/altera-fpga2sdram.c | 8 ++-- drivers/fpga/altera-freeze-bridge.c | 13 ++--- drivers/fpga/altera-hps2fpga.c | 7 ++- drivers/fpga/dfl-fme-br.c | 11 ++--- drivers/fpga/fpga-bridge.c | 68 +++++++++++++++++++++++---- drivers/fpga/xilinx-pr-decoupler.c | 4 +- include/linux/fpga/fpga-bridge.h | 4 ++ 8 files changed, 80 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/Documentation/driver-api/fpga/fpga-bridge.rst b/Documentation/driver-api/fpga/fpga-bridge.rst index 2c2aaca894bf..ebbcbde687b3 100644 --- a/Documentation/driver-api/fpga/fpga-bridge.rst +++ b/Documentation/driver-api/fpga/fpga-bridge.rst @@ -10,6 +10,9 @@ API to implement a new FPGA bridge .. kernel-doc:: include/linux/fpga/fpga-bridge.h :functions: fpga_bridge_ops +.. kernel-doc:: drivers/fpga/fpga-bridge.c + :functions: devm_fpga_bridge_create + .. kernel-doc:: drivers/fpga/fpga-bridge.c :functions: fpga_bridge_create diff --git a/drivers/fpga/altera-fpga2sdram.c b/drivers/fpga/altera-fpga2sdram.c index 23660ccd634b..a78e49c63c64 100644 --- a/drivers/fpga/altera-fpga2sdram.c +++ b/drivers/fpga/altera-fpga2sdram.c @@ -121,18 +121,16 @@ static int alt_fpga_bridge_probe(struct platform_device *pdev) /* Get f2s bridge configuration saved in handoff register */ regmap_read(sysmgr, SYSMGR_ISWGRP_HANDOFF3, &priv->mask); - br = fpga_bridge_create(dev, F2S_BRIDGE_NAME, - &altera_fpga2sdram_br_ops, priv); + br = devm_fpga_bridge_create(dev, F2S_BRIDGE_NAME, + &altera_fpga2sdram_br_ops, priv); if (!br) return -ENOMEM; platform_set_drvdata(pdev, br); ret = fpga_bridge_register(br); - if (ret) { - fpga_bridge_free(br); + if (ret) return ret; - } dev_info(dev, "driver initialized with handoff %08x\n", priv->mask); diff --git a/drivers/fpga/altera-freeze-bridge.c b/drivers/fpga/altera-freeze-bridge.c index ffd586c48ecf..dd58c4aea92e 100644 --- a/drivers/fpga/altera-freeze-bridge.c +++ b/drivers/fpga/altera-freeze-bridge.c @@ -213,7 +213,6 @@ static int altera_freeze_br_probe(struct platform_device *pdev) struct fpga_bridge *br; struct resource *res; u32 status, revision; - int ret; if (!np) return -ENODEV; @@ -245,20 +244,14 @@ static int altera_freeze_br_probe(struct platform_device *pdev) priv->base_addr = base_addr; - br = fpga_bridge_create(dev, FREEZE_BRIDGE_NAME, - &altera_freeze_br_br_ops, priv); + br = devm_fpga_bridge_create(dev, FREEZE_BRIDGE_NAME, + &altera_freeze_br_br_ops, priv); if (!br) return -ENOMEM; platform_set_drvdata(pdev, br); - ret = fpga_bridge_register(br); - if (ret) { - fpga_bridge_free(br); - return ret; - } - - return 0; + return fpga_bridge_register(br); } static int altera_freeze_br_remove(struct platform_device *pdev) diff --git a/drivers/fpga/altera-hps2fpga.c b/drivers/fpga/altera-hps2fpga.c index a974d3f60321..77b95f251821 100644 --- a/drivers/fpga/altera-hps2fpga.c +++ b/drivers/fpga/altera-hps2fpga.c @@ -180,7 +180,8 @@ static int alt_fpga_bridge_probe(struct platform_device *pdev) } } - br = fpga_bridge_create(dev, priv->name, &altera_hps2fpga_br_ops, priv); + br = devm_fpga_bridge_create(dev, priv->name, + &altera_hps2fpga_br_ops, priv); if (!br) { ret = -ENOMEM; goto err; @@ -190,12 +191,10 @@ static int alt_fpga_bridge_probe(struct platform_device *pdev) ret = fpga_bridge_register(br); if (ret) - goto err_free; + goto err; return 0; -err_free: - fpga_bridge_free(br); err: clk_disable_unprepare(priv->clk); diff --git a/drivers/fpga/dfl-fme-br.c b/drivers/fpga/dfl-fme-br.c index 7cc041def8b3..3ff9f3a687ce 100644 --- a/drivers/fpga/dfl-fme-br.c +++ b/drivers/fpga/dfl-fme-br.c @@ -61,7 +61,6 @@ static int fme_br_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct fme_br_priv *priv; struct fpga_bridge *br; - int ret; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); if (!priv) @@ -69,18 +68,14 @@ static int fme_br_probe(struct platform_device *pdev) priv->pdata = dev_get_platdata(dev); - br = fpga_bridge_create(dev, "DFL FPGA FME Bridge", - &fme_bridge_ops, priv); + br = devm_fpga_bridge_create(dev, "DFL FPGA FME Bridge", + &fme_bridge_ops, priv); if (!br) return -ENOMEM; platform_set_drvdata(pdev, br); - ret = fpga_bridge_register(br); - if (ret) - fpga_bridge_free(br); - - return ret; + return fpga_bridge_register(br); } static int fme_br_remove(struct platform_device *pdev) diff --git a/drivers/fpga/fpga-bridge.c b/drivers/fpga/fpga-bridge.c index c983dac97501..80bd8f1b2aa6 100644 --- a/drivers/fpga/fpga-bridge.c +++ b/drivers/fpga/fpga-bridge.c @@ -324,6 +324,9 @@ ATTRIBUTE_GROUPS(fpga_bridge); * @br_ops: pointer to structure of fpga bridge ops * @priv: FPGA bridge private data * + * The caller of this function is responsible for freeing the bridge with + * fpga_bridge_free(). Using devm_fpga_bridge_create() instead is recommended. + * * Return: struct fpga_bridge or NULL */ struct fpga_bridge *fpga_bridge_create(struct device *dev, const char *name, @@ -378,8 +381,8 @@ error_kfree: EXPORT_SYMBOL_GPL(fpga_bridge_create); /** - * fpga_bridge_free - free a fpga bridge and its id - * @bridge: FPGA bridge struct created by fpga_bridge_create + * fpga_bridge_free - free a fpga bridge created by fpga_bridge_create() + * @bridge: FPGA bridge struct */ void fpga_bridge_free(struct fpga_bridge *bridge) { @@ -388,9 +391,56 @@ void fpga_bridge_free(struct fpga_bridge *bridge) } EXPORT_SYMBOL_GPL(fpga_bridge_free); +static void devm_fpga_bridge_release(struct device *dev, void *res) +{ + struct fpga_bridge *bridge = *(struct fpga_bridge **)res; + + fpga_bridge_free(bridge); +} + /** - * fpga_bridge_register - register a fpga bridge - * @bridge: FPGA bridge struct created by fpga_bridge_create + * devm_fpga_bridge_create - create and init a managed struct fpga_bridge + * @dev: FPGA bridge device from pdev + * @name: FPGA bridge name + * @br_ops: pointer to structure of fpga bridge ops + * @priv: FPGA bridge private data + * + * This function is intended for use in a FPGA bridge driver's probe function. + * After the bridge driver creates the struct with devm_fpga_bridge_create(), it + * should register the bridge with fpga_bridge_register(). The bridge driver's + * remove function should call fpga_bridge_unregister(). The bridge struct + * allocated with this function will be freed automatically on driver detach. + * This includes the case of a probe function returning error before calling + * fpga_bridge_register(), the struct will still get cleaned up. + * + * Return: struct fpga_bridge or NULL + */ +struct fpga_bridge +*devm_fpga_bridge_create(struct device *dev, const char *name, + const struct fpga_bridge_ops *br_ops, void *priv) +{ + struct fpga_bridge **ptr, *bridge; + + ptr = devres_alloc(devm_fpga_bridge_release, sizeof(*ptr), GFP_KERNEL); + if (!ptr) + return NULL; + + bridge = fpga_bridge_create(dev, name, br_ops, priv); + if (!bridge) { + devres_free(ptr); + } else { + *ptr = bridge; + devres_add(dev, ptr); + } + + return bridge; +} +EXPORT_SYMBOL_GPL(devm_fpga_bridge_create); + +/** + * fpga_bridge_register - register a FPGA bridge + * + * @bridge: FPGA bridge struct * * Return: 0 for success, error code otherwise. */ @@ -412,8 +462,11 @@ int fpga_bridge_register(struct fpga_bridge *bridge) EXPORT_SYMBOL_GPL(fpga_bridge_register); /** - * fpga_bridge_unregister - unregister and free a fpga bridge - * @bridge: FPGA bridge struct created by fpga_bridge_create + * fpga_bridge_unregister - unregister a FPGA bridge + * + * @bridge: FPGA bridge struct + * + * This function is intended for use in a FPGA bridge driver's remove function. */ void fpga_bridge_unregister(struct fpga_bridge *bridge) { @@ -430,9 +483,6 @@ EXPORT_SYMBOL_GPL(fpga_bridge_unregister); static void fpga_bridge_dev_release(struct device *dev) { - struct fpga_bridge *bridge = to_fpga_bridge(dev); - - fpga_bridge_free(bridge); } static int __init fpga_bridge_dev_init(void) diff --git a/drivers/fpga/xilinx-pr-decoupler.c b/drivers/fpga/xilinx-pr-decoupler.c index 07ba1539e82c..641036135207 100644 --- a/drivers/fpga/xilinx-pr-decoupler.c +++ b/drivers/fpga/xilinx-pr-decoupler.c @@ -121,8 +121,8 @@ static int xlnx_pr_decoupler_probe(struct platform_device *pdev) clk_disable(priv->clk); - br = fpga_bridge_create(&pdev->dev, "Xilinx PR Decoupler", - &xlnx_pr_decoupler_br_ops, priv); + br = devm_fpga_bridge_create(&pdev->dev, "Xilinx PR Decoupler", + &xlnx_pr_decoupler_br_ops, priv); if (!br) { err = -ENOMEM; goto err_clk; diff --git a/include/linux/fpga/fpga-bridge.h b/include/linux/fpga/fpga-bridge.h index ce550fcf6360..817600a32c93 100644 --- a/include/linux/fpga/fpga-bridge.h +++ b/include/linux/fpga/fpga-bridge.h @@ -69,4 +69,8 @@ void fpga_bridge_free(struct fpga_bridge *br); int fpga_bridge_register(struct fpga_bridge *br); void fpga_bridge_unregister(struct fpga_bridge *br); +struct fpga_bridge +*devm_fpga_bridge_create(struct device *dev, const char *name, + const struct fpga_bridge_ops *br_ops, void *priv); + #endif /* _LINUX_FPGA_BRIDGE_H */ -- cgit v1.2.3 From fea82b7f6670002ff36bf1bc77d0345b0b2f2d1c Mon Sep 17 00:00:00 2001 From: Alan Tull Date: Mon, 15 Oct 2018 17:20:03 -0500 Subject: fpga: add devm_fpga_region_create Add devm_fpga_region_create() which is the managed version of fpga_region_create(). Change current region drivers to use devm_fpga_region_create(). Signed-off-by: Alan Tull Suggested-by: Federico Vaga Acked-by: Moritz Fischer Signed-off-by: Greg Kroah-Hartman --- Documentation/driver-api/fpga/fpga-region.rst | 3 ++ drivers/fpga/dfl-fme-region.c | 6 +-- drivers/fpga/dfl.c | 6 +-- drivers/fpga/fpga-region.c | 65 +++++++++++++++++++++++---- drivers/fpga/of-fpga-region.c | 6 +-- include/linux/fpga/fpga-region.h | 4 ++ 6 files changed, 70 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/Documentation/driver-api/fpga/fpga-region.rst b/Documentation/driver-api/fpga/fpga-region.rst index f30333ce828e..dc9f75cc3352 100644 --- a/Documentation/driver-api/fpga/fpga-region.rst +++ b/Documentation/driver-api/fpga/fpga-region.rst @@ -89,6 +89,9 @@ API to add a new FPGA region .. kernel-doc:: include/linux/fpga/fpga-region.h :functions: fpga_region +.. kernel-doc:: drivers/fpga/fpga-region.c + :functions: devm_fpga_region_create + .. kernel-doc:: drivers/fpga/fpga-region.c :functions: fpga_region_create diff --git a/drivers/fpga/dfl-fme-region.c b/drivers/fpga/dfl-fme-region.c index 51a5ac2293a7..ec134ec93f08 100644 --- a/drivers/fpga/dfl-fme-region.c +++ b/drivers/fpga/dfl-fme-region.c @@ -39,7 +39,7 @@ static int fme_region_probe(struct platform_device *pdev) if (IS_ERR(mgr)) return -EPROBE_DEFER; - region = fpga_region_create(dev, mgr, fme_region_get_bridges); + region = devm_fpga_region_create(dev, mgr, fme_region_get_bridges); if (!region) { ret = -ENOMEM; goto eprobe_mgr_put; @@ -51,14 +51,12 @@ static int fme_region_probe(struct platform_device *pdev) ret = fpga_region_register(region); if (ret) - goto region_free; + goto eprobe_mgr_put; dev_dbg(dev, "DFL FME FPGA Region probed\n"); return 0; -region_free: - fpga_region_free(region); eprobe_mgr_put: fpga_mgr_put(mgr); return ret; diff --git a/drivers/fpga/dfl.c b/drivers/fpga/dfl.c index a9b521bccb06..2c09e502e721 100644 --- a/drivers/fpga/dfl.c +++ b/drivers/fpga/dfl.c @@ -899,7 +899,7 @@ dfl_fpga_feature_devs_enumerate(struct dfl_fpga_enum_info *info) if (!cdev) return ERR_PTR(-ENOMEM); - cdev->region = fpga_region_create(info->dev, NULL, NULL); + cdev->region = devm_fpga_region_create(info->dev, NULL, NULL); if (!cdev->region) { ret = -ENOMEM; goto free_cdev_exit; @@ -911,7 +911,7 @@ dfl_fpga_feature_devs_enumerate(struct dfl_fpga_enum_info *info) ret = fpga_region_register(cdev->region); if (ret) - goto free_region_exit; + goto free_cdev_exit; /* create and init build info for enumeration */ binfo = devm_kzalloc(info->dev, sizeof(*binfo), GFP_KERNEL); @@ -942,8 +942,6 @@ dfl_fpga_feature_devs_enumerate(struct dfl_fpga_enum_info *info) unregister_region_exit: fpga_region_unregister(cdev->region); -free_region_exit: - fpga_region_free(cdev->region); free_cdev_exit: devm_kfree(info->dev, cdev); return ERR_PTR(ret); diff --git a/drivers/fpga/fpga-region.c b/drivers/fpga/fpga-region.c index 0d65220d5ec5..bde5a9d460c5 100644 --- a/drivers/fpga/fpga-region.c +++ b/drivers/fpga/fpga-region.c @@ -185,6 +185,10 @@ ATTRIBUTE_GROUPS(fpga_region); * @mgr: manager that programs this region * @get_bridges: optional function to get bridges to a list * + * The caller of this function is responsible for freeing the resulting region + * struct with fpga_region_free(). Using devm_fpga_region_create() instead is + * recommended. + * * Return: struct fpga_region or NULL */ struct fpga_region @@ -230,8 +234,8 @@ err_free: EXPORT_SYMBOL_GPL(fpga_region_create); /** - * fpga_region_free - free a struct fpga_region - * @region: FPGA region created by fpga_region_create + * fpga_region_free - free a FPGA region created by fpga_region_create() + * @region: FPGA region */ void fpga_region_free(struct fpga_region *region) { @@ -240,21 +244,69 @@ void fpga_region_free(struct fpga_region *region) } EXPORT_SYMBOL_GPL(fpga_region_free); +static void devm_fpga_region_release(struct device *dev, void *res) +{ + struct fpga_region *region = *(struct fpga_region **)res; + + fpga_region_free(region); +} + +/** + * devm_fpga_region_create - create and initialize a managed FPGA region struct + * @dev: device parent + * @mgr: manager that programs this region + * @get_bridges: optional function to get bridges to a list + * + * This function is intended for use in a FPGA region driver's probe function. + * After the region driver creates the region struct with + * devm_fpga_region_create(), it should register it with fpga_region_register(). + * The region driver's remove function should call fpga_region_unregister(). + * The region struct allocated with this function will be freed automatically on + * driver detach. This includes the case of a probe function returning error + * before calling fpga_region_register(), the struct will still get cleaned up. + * + * Return: struct fpga_region or NULL + */ +struct fpga_region +*devm_fpga_region_create(struct device *dev, + struct fpga_manager *mgr, + int (*get_bridges)(struct fpga_region *)) +{ + struct fpga_region **ptr, *region; + + ptr = devres_alloc(devm_fpga_region_release, sizeof(*ptr), GFP_KERNEL); + if (!ptr) + return NULL; + + region = fpga_region_create(dev, mgr, get_bridges); + if (!region) { + devres_free(ptr); + } else { + *ptr = region; + devres_add(dev, ptr); + } + + return region; +} +EXPORT_SYMBOL_GPL(devm_fpga_region_create); + /** * fpga_region_register - register a FPGA region - * @region: FPGA region created by fpga_region_create + * @region: FPGA region + * * Return: 0 or -errno */ int fpga_region_register(struct fpga_region *region) { return device_add(®ion->dev); - } EXPORT_SYMBOL_GPL(fpga_region_register); /** - * fpga_region_unregister - unregister and free a FPGA region + * fpga_region_unregister - unregister a FPGA region * @region: FPGA region + * + * This function is intended for use in a FPGA region driver's remove function. */ void fpga_region_unregister(struct fpga_region *region) { @@ -264,9 +316,6 @@ EXPORT_SYMBOL_GPL(fpga_region_unregister); static void fpga_region_dev_release(struct device *dev) { - struct fpga_region *region = to_fpga_region(dev); - - fpga_region_free(region); } /** diff --git a/drivers/fpga/of-fpga-region.c b/drivers/fpga/of-fpga-region.c index 052a1342ab7e..122286fd255a 100644 --- a/drivers/fpga/of-fpga-region.c +++ b/drivers/fpga/of-fpga-region.c @@ -410,7 +410,7 @@ static int of_fpga_region_probe(struct platform_device *pdev) if (IS_ERR(mgr)) return -EPROBE_DEFER; - region = fpga_region_create(dev, mgr, of_fpga_region_get_bridges); + region = devm_fpga_region_create(dev, mgr, of_fpga_region_get_bridges); if (!region) { ret = -ENOMEM; goto eprobe_mgr_put; @@ -418,7 +418,7 @@ static int of_fpga_region_probe(struct platform_device *pdev) ret = fpga_region_register(region); if (ret) - goto eprobe_free; + goto eprobe_mgr_put; of_platform_populate(np, fpga_region_of_match, NULL, ®ion->dev); dev_set_drvdata(dev, region); @@ -427,8 +427,6 @@ static int of_fpga_region_probe(struct platform_device *pdev) return 0; -eprobe_free: - fpga_region_free(region); eprobe_mgr_put: fpga_mgr_put(mgr); return ret; diff --git a/include/linux/fpga/fpga-region.h b/include/linux/fpga/fpga-region.h index 0521b7f577a4..27cb706275db 100644 --- a/include/linux/fpga/fpga-region.h +++ b/include/linux/fpga/fpga-region.h @@ -44,4 +44,8 @@ void fpga_region_free(struct fpga_region *region); int fpga_region_register(struct fpga_region *region); void fpga_region_unregister(struct fpga_region *region); +struct fpga_region +*devm_fpga_region_create(struct device *dev, struct fpga_manager *mgr, + int (*get_bridges)(struct fpga_region *)); + #endif /* _FPGA_REGION_H */ -- cgit v1.2.3 From 8514c470dc18e58f27dee10a787175ef8f31162f Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 11 Jul 2018 15:20:32 +0200 Subject: driver core: add BUS_ATTR_WO() macro Many bus attributes are write-only, so provide a simple macro for that to be able to match the other driver core attribute macros. Cc: "Rafael J. Wysocki" Cc: Ioana Ciornei Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 8f882549edee..767cf1938b14 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -55,6 +55,8 @@ struct bus_attribute { struct bus_attribute bus_attr_##_name = __ATTR_RW(_name) #define BUS_ATTR_RO(_name) \ struct bus_attribute bus_attr_##_name = __ATTR_RO(_name) +#define BUS_ATTR_WO(_name) \ + struct bus_attribute bus_attr_##_name = __ATTR_WO(_name) extern int __must_check bus_create_file(struct bus_type *, struct bus_attribute *); -- cgit v1.2.3 From 0571967dfb5d2573c2a06871517d748932a899d1 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Sun, 14 Oct 2018 17:20:07 +0200 Subject: devres: constify p in devm_kfree() Make devm_kfree() signature uniform with that of kfree(). To avoid compiler warnings: cast p to (void *) when calling devres_destroy(). Signed-off-by: Bartosz Golaszewski Reviewed-by: Bjorn Andersson Reviewed-by: Geert Uytterhoeven Acked-by: Rasmus Villemoes Reviewed-by: Andy Shevchenko Signed-off-by: Greg Kroah-Hartman --- drivers/base/devres.c | 5 +++-- include/linux/device.h | 2 +- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/devres.c b/drivers/base/devres.c index f98a097e73f2..438c91a43508 100644 --- a/drivers/base/devres.c +++ b/drivers/base/devres.c @@ -885,11 +885,12 @@ EXPORT_SYMBOL_GPL(devm_kasprintf); * * Free memory allocated with devm_kmalloc(). */ -void devm_kfree(struct device *dev, void *p) +void devm_kfree(struct device *dev, const void *p) { int rc; - rc = devres_destroy(dev, devm_kmalloc_release, devm_kmalloc_match, p); + rc = devres_destroy(dev, devm_kmalloc_release, + devm_kmalloc_match, (void *)p); WARN_ON(rc); } EXPORT_SYMBOL_GPL(devm_kfree); diff --git a/include/linux/device.h b/include/linux/device.h index 767cf1938b14..c2022c1daef6 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -694,7 +694,7 @@ static inline void *devm_kcalloc(struct device *dev, { return devm_kmalloc_array(dev, n, size, flags | __GFP_ZERO); } -extern void devm_kfree(struct device *dev, void *p); +extern void devm_kfree(struct device *dev, const void *p); extern char *devm_kstrdup(struct device *dev, const char *s, gfp_t gfp) __malloc; extern void *devm_kmemdup(struct device *dev, const void *src, size_t len, gfp_t gfp); -- cgit v1.2.3 From 09d1ea1c7309c8ca91151778bb3efe514f2e03ed Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Sun, 14 Oct 2018 17:20:09 +0200 Subject: devres: provide devm_kstrdup_const() Provide a resource managed version of kstrdup_const(). This variant internally calls devm_kstrdup() on pointers that are outside of .rodata section and returns the string as is otherwise. Make devm_kfree() check if the passed pointer doesn't point to .rodata and if so - don't actually destroy the resource. Signed-off-by: Bartosz Golaszewski Reviewed-by: Bjorn Andersson Acked-by: Mike Rapoport Acked-by: Rasmus Villemoes Reviewed-by: Geert Uytterhoeven Reviewed-by: Andy Shevchenko Signed-off-by: Greg Kroah-Hartman --- drivers/base/devres.c | 31 +++++++++++++++++++++++++++++++ include/linux/device.h | 2 ++ 2 files changed, 33 insertions(+) (limited to 'include/linux') diff --git a/drivers/base/devres.c b/drivers/base/devres.c index 438c91a43508..4aaf00d2098b 100644 --- a/drivers/base/devres.c +++ b/drivers/base/devres.c @@ -11,6 +11,8 @@ #include #include +#include + #include "base.h" struct devres_node { @@ -822,6 +824,28 @@ char *devm_kstrdup(struct device *dev, const char *s, gfp_t gfp) } EXPORT_SYMBOL_GPL(devm_kstrdup); +/** + * devm_kstrdup_const - resource managed conditional string duplication + * @dev: device for which to duplicate the string + * @s: the string to duplicate + * @gfp: the GFP mask used in the kmalloc() call when allocating memory + * + * Strings allocated by devm_kstrdup_const will be automatically freed when + * the associated device is detached. + * + * RETURNS: + * Source string if it is in .rodata section otherwise it falls back to + * devm_kstrdup. + */ +const char *devm_kstrdup_const(struct device *dev, const char *s, gfp_t gfp) +{ + if (is_kernel_rodata((unsigned long)s)) + return s; + + return devm_kstrdup(dev, s, gfp); +} +EXPORT_SYMBOL_GPL(devm_kstrdup_const); + /** * devm_kvasprintf - Allocate resource managed space and format a string * into that. @@ -889,6 +913,13 @@ void devm_kfree(struct device *dev, const void *p) { int rc; + /* + * Special case: pointer to a string in .rodata returned by + * devm_kstrdup_const(). + */ + if (unlikely(is_kernel_rodata((unsigned long)p))) + return; + rc = devres_destroy(dev, devm_kmalloc_release, devm_kmalloc_match, (void *)p); WARN_ON(rc); diff --git a/include/linux/device.h b/include/linux/device.h index c2022c1daef6..fecd9722400e 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -696,6 +696,8 @@ static inline void *devm_kcalloc(struct device *dev, } extern void devm_kfree(struct device *dev, const void *p); extern char *devm_kstrdup(struct device *dev, const char *s, gfp_t gfp) __malloc; +extern const char *devm_kstrdup_const(struct device *dev, + const char *s, gfp_t gfp); extern void *devm_kmemdup(struct device *dev, const void *src, size_t len, gfp_t gfp); -- cgit v1.2.3 From 4354994f097d068a894aa1a0860da54571df3582 Mon Sep 17 00:00:00 2001 From: Daniel Rosenberg Date: Mon, 20 Aug 2018 19:21:43 -0700 Subject: f2fs: checkpoint disabling Note that, it requires "f2fs: return correct errno in f2fs_gc". This adds a lightweight non-persistent snapshotting scheme to f2fs. To use, mount with the option checkpoint=disable, and to return to normal operation, remount with checkpoint=enable. If the filesystem is shut down before remounting with checkpoint=enable, it will revert back to its apparent state when it was first mounted with checkpoint=disable. This is useful for situations where you wish to be able to roll back the state of the disk in case of some critical failure. Signed-off-by: Daniel Rosenberg [Jaegeuk Kim: use SB_RDONLY instead of MS_RDONLY] Signed-off-by: Jaegeuk Kim --- Documentation/filesystems/f2fs.txt | 5 ++ fs/f2fs/checkpoint.c | 12 ++++ fs/f2fs/data.c | 14 ++++- fs/f2fs/debug.c | 3 +- fs/f2fs/f2fs.h | 18 +++++- fs/f2fs/file.c | 12 +++- fs/f2fs/gc.c | 9 ++- fs/f2fs/inode.c | 6 +- fs/f2fs/namei.c | 19 ++++++ fs/f2fs/segment.c | 98 +++++++++++++++++++++++++++-- fs/f2fs/segment.h | 15 +++++ fs/f2fs/super.c | 126 ++++++++++++++++++++++++++++++++++++- include/linux/f2fs_fs.h | 1 + 13 files changed, 324 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt index bde3e91e5372..e46c2147ddf8 100644 --- a/Documentation/filesystems/f2fs.txt +++ b/Documentation/filesystems/f2fs.txt @@ -212,6 +212,11 @@ fsync_mode=%s Control the policy of fsync. Currently supports "posix", non-atomic files likewise "nobarrier" mount option. test_dummy_encryption Enable dummy encryption, which provides a fake fscrypt context. The fake fscrypt context is used by xfstests. +checkpoint=%s Set to "disable" to turn off checkpointing. Set to "enable" + to reenable checkpointing. Is enabled by default. While + disabled, any unmounting or unexpected shutdowns will cause + the filesystem contents to appear as they did when the + filesystem was mounted with that option. ================================================================================ DEBUGFS ENTRIES diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 97b429ba2911..eb6ac79640f8 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -1210,6 +1210,11 @@ static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc) if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) __set_ckpt_flags(ckpt, CP_FSCK_FLAG); + if (is_sbi_flag_set(sbi, SBI_CP_DISABLED)) + __set_ckpt_flags(ckpt, CP_DISABLED_FLAG); + else + __clear_ckpt_flags(ckpt, CP_DISABLED_FLAG); + /* set this flag to activate crc|cp_ver for recovery */ __set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG); __clear_ckpt_flags(ckpt, CP_NOCRC_RECOVERY_FLAG); @@ -1417,6 +1422,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) clear_sbi_flag(sbi, SBI_IS_DIRTY); clear_sbi_flag(sbi, SBI_NEED_CP); + sbi->unusable_block_count = 0; __set_cp_next_pack(sbi); /* @@ -1441,6 +1447,12 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) unsigned long long ckpt_ver; int err = 0; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { + if (cpc->reason != CP_PAUSE) + return 0; + f2fs_msg(sbi->sb, KERN_WARNING, + "Start checkpoint disabled!"); + } mutex_lock(&sbi->cp_mutex); if (!is_sbi_flag_set(sbi, SBI_IS_DIRTY) && diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 873f9ea7769f..9ef6f1f01eda 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -537,7 +537,8 @@ skip: if (fio->in_list) goto next; out: - if (is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN)) + if (is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN) || + f2fs_is_checkpoint_ready(sbi)) __submit_merged_bio(io); up_write(&io->io_rwsem); } @@ -1703,6 +1704,10 @@ static inline bool check_inplace_update_policy(struct inode *inode, is_inode_flag_set(inode, FI_NEED_IPU)) return true; + if (unlikely(fio && is_sbi_flag_set(sbi, SBI_CP_DISABLED) && + !f2fs_is_checkpointed_data(sbi, fio->old_blkaddr))) + return true; + return false; } @@ -1733,6 +1738,9 @@ bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio) return true; if (IS_ATOMIC_WRITTEN_PAGE(fio->page)) return true; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED) && + f2fs_is_checkpointed_data(sbi, fio->old_blkaddr))) + return true; } return false; } @@ -2353,6 +2361,10 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping, trace_f2fs_write_begin(inode, pos, len, flags); + err = f2fs_is_checkpoint_ready(sbi); + if (err) + goto fail; + if ((f2fs_is_atomic_file(inode) && !f2fs_available_free_memory(sbi, INMEM_PAGES)) || is_inode_flag_set(inode, FI_ATOMIC_REVOKE_REQUEST)) { diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c index 75bc62edc4c1..026e10f30889 100644 --- a/fs/f2fs/debug.c +++ b/fs/f2fs/debug.c @@ -272,7 +272,8 @@ static int stat_show(struct seq_file *s, void *v) seq_printf(s, "\n=====[ partition info(%pg). #%d, %s, CP: %s]=====\n", si->sbi->sb->s_bdev, i++, f2fs_readonly(si->sbi->sb) ? "RO": "RW", - f2fs_cp_error(si->sbi) ? "Error": "Good"); + is_set_ckpt_flags(si->sbi, CP_DISABLED_FLAG) ? + "Disabled": (f2fs_cp_error(si->sbi) ? "Error": "Good")); seq_printf(s, "[SB: 1] [CP: 2] [SIT: %d] [NAT: %d] ", si->sit_area_segs, si->nat_area_segs); seq_printf(s, "[SSA: %d] [MAIN: %d", diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 95d9edd8ff6e..ff540f523a3b 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -99,6 +99,7 @@ extern char *f2fs_fault_name[FAULT_MAX]; #define F2FS_MOUNT_QUOTA 0x00400000 #define F2FS_MOUNT_INLINE_XATTR_SIZE 0x00800000 #define F2FS_MOUNT_RESERVE_ROOT 0x01000000 +#define F2FS_MOUNT_DISABLE_CHECKPOINT 0x02000000 #define F2FS_OPTION(sbi) ((sbi)->mount_opt) #define clear_opt(sbi, option) (F2FS_OPTION(sbi).opt &= ~F2FS_MOUNT_##option) @@ -178,6 +179,7 @@ enum { #define CP_RECOVERY 0x00000008 #define CP_DISCARD 0x00000010 #define CP_TRIMMED 0x00000020 +#define CP_PAUSE 0x00000040 #define MAX_DISCARD_BLOCKS(sbi) BLKS_PER_SEC(sbi) #define DEF_MAX_DISCARD_REQUEST 8 /* issue 8 discards per round */ @@ -187,6 +189,7 @@ enum { #define DEF_DISCARD_URGENT_UTIL 80 /* do more discard over 80% */ #define DEF_CP_INTERVAL 60 /* 60 secs */ #define DEF_IDLE_INTERVAL 5 /* 5 secs */ +#define DEF_DISABLE_INTERVAL 5 /* 5 secs */ struct cp_control { int reason; @@ -1092,6 +1095,7 @@ enum { SBI_NEED_CP, /* need to checkpoint */ SBI_IS_SHUTDOWN, /* shutdown by ioctl */ SBI_IS_RECOVERED, /* recovered orphan/data */ + SBI_CP_DISABLED, /* CP was disabled last mount */ }; enum { @@ -1099,6 +1103,7 @@ enum { REQ_TIME, DISCARD_TIME, GC_TIME, + DISABLE_TIME, MAX_TIME, }; @@ -1225,6 +1230,9 @@ struct f2fs_sb_info { block_t reserved_blocks; /* configurable reserved blocks */ block_t current_reserved_blocks; /* current reserved blocks */ + /* Additional tracking for no checkpoint mode */ + block_t unusable_block_count; /* # of blocks saved by last cp */ + unsigned int nquota_files; /* # of quota sysfile */ u32 s_next_generation; /* for NFS support */ @@ -1735,7 +1743,8 @@ static inline int inc_valid_block_count(struct f2fs_sb_info *sbi, if (!__allow_reserved_blocks(sbi, inode, true)) avail_user_block_count -= F2FS_OPTION(sbi).root_reserved_blocks; - + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) + avail_user_block_count -= sbi->unusable_block_count; if (unlikely(sbi->total_valid_block_count > avail_user_block_count)) { diff = sbi->total_valid_block_count - avail_user_block_count; if (diff > *count) @@ -1942,6 +1951,8 @@ static inline int inc_valid_node_count(struct f2fs_sb_info *sbi, if (!__allow_reserved_blocks(sbi, inode, false)) valid_block_count += F2FS_OPTION(sbi).root_reserved_blocks; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) + valid_block_count += sbi->unusable_block_count; if (unlikely(valid_block_count > sbi->user_block_count)) { spin_unlock(&sbi->stat_lock); @@ -2945,6 +2956,8 @@ void f2fs_stop_discard_thread(struct f2fs_sb_info *sbi); bool f2fs_wait_discard_bios(struct f2fs_sb_info *sbi); void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc); +void f2fs_dirty_to_prefree(struct f2fs_sb_info *sbi); +int f2fs_disable_cp_again(struct f2fs_sb_info *sbi); void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi); int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra); void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi); @@ -3532,6 +3545,9 @@ static inline bool f2fs_force_buffered_io(struct inode *inode, if (test_opt(sbi, LFS) && (rw == WRITE) && block_unaligned_IO(inode, iocb, iter)) return true; + if (is_sbi_flag_set(F2FS_I_SB(inode), SBI_CP_DISABLED)) + return true; + return false; } diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index e29715ea736f..b1aaa73e1eeb 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -210,7 +210,8 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end, }; unsigned int seq_id = 0; - if (unlikely(f2fs_readonly(inode->i_sb))) + if (unlikely(f2fs_readonly(inode->i_sb) || + is_sbi_flag_set(sbi, SBI_CP_DISABLED))) return 0; trace_f2fs_sync_file_enter(inode); @@ -2157,6 +2158,12 @@ static int f2fs_ioc_write_checkpoint(struct file *filp, unsigned long arg) if (f2fs_readonly(sbi->sb)) return -EROFS; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { + f2fs_msg(sbi->sb, KERN_INFO, + "Skipping Checkpoint. Checkpoints currently disabled."); + return -EINVAL; + } + ret = mnt_want_write_file(filp); if (ret) return ret; @@ -2528,6 +2535,9 @@ static int f2fs_ioc_flush_device(struct file *filp, unsigned long arg) if (f2fs_readonly(sbi->sb)) return -EROFS; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) + return -EINVAL; + if (copy_from_user(&range, (struct f2fs_flush_device __user *)arg, sizeof(range))) return -EFAULT; diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 99ed8a5d9249..78288c54b68c 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -370,6 +370,10 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi, if (sec_usage_check(sbi, secno)) goto next; + /* Don't touch checkpointed data */ + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED) && + get_ckpt_valid_blocks(sbi, segno))) + goto next; if (gc_type == BG_GC && test_bit(secno, dirty_i->victim_secmap)) goto next; @@ -1189,7 +1193,8 @@ gc_more: * threshold, we can make them free by checkpoint. Then, we * secure free segments which doesn't need fggc any more. */ - if (prefree_segments(sbi)) { + if (prefree_segments(sbi) && + !is_sbi_flag_set(sbi, SBI_CP_DISABLED)) { ret = f2fs_write_checkpoint(sbi, &cpc); if (ret) goto stop; @@ -1241,7 +1246,7 @@ gc_more: segno = NULL_SEGNO; goto gc_more; } - if (gc_type == FG_GC) + if (gc_type == FG_GC && !is_sbi_flag_set(sbi, SBI_CP_DISABLED)) ret = f2fs_write_checkpoint(sbi, &cpc); } stop: diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 86e7333d60c1..4ee9d6c4b719 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -607,6 +607,9 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc) if (!is_inode_flag_set(inode, FI_DIRTY_INODE)) return 0; + if (f2fs_is_checkpoint_ready(sbi)) + return -ENOSPC; + /* * We need to balance fs here to prevent from producing dirty node pages * during the urgent cleaning time when runing out of free sections. @@ -688,7 +691,8 @@ no_delete: stat_dec_inline_dir(inode); stat_dec_inline_inode(inode); - if (likely(!is_set_ckpt_flags(sbi, CP_ERROR_FLAG))) + if (likely(!is_set_ckpt_flags(sbi, CP_ERROR_FLAG) && + !is_sbi_flag_set(sbi, SBI_CP_DISABLED))) f2fs_bug_on(sbi, is_inode_flag_set(inode, FI_DIRTY_INODE)); else f2fs_inode_synced(inode); diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index ded185baa9ae..a14632744a6a 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -16,6 +16,7 @@ #include "f2fs.h" #include "node.h" +#include "segment.h" #include "xattr.h" #include "acl.h" #include @@ -269,6 +270,9 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode, if (unlikely(f2fs_cp_error(sbi))) return -EIO; + err = f2fs_is_checkpoint_ready(sbi); + if (err) + return err; err = dquot_initialize(dir); if (err) @@ -315,6 +319,9 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir, if (unlikely(f2fs_cp_error(sbi))) return -EIO; + err = f2fs_is_checkpoint_ready(sbi); + if (err) + return err; err = fscrypt_prepare_link(old_dentry, dir, dentry); if (err) @@ -561,6 +568,9 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry, if (unlikely(f2fs_cp_error(sbi))) return -EIO; + err = f2fs_is_checkpoint_ready(sbi); + if (err) + return err; err = fscrypt_prepare_symlink(dir, symname, len, dir->i_sb->s_blocksize, &disk_link); @@ -690,6 +700,9 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry, if (unlikely(f2fs_cp_error(sbi))) return -EIO; + err = f2fs_is_checkpoint_ready(sbi); + if (err) + return err; err = dquot_initialize(dir); if (err) @@ -824,6 +837,9 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, if (unlikely(f2fs_cp_error(sbi))) return -EIO; + err = f2fs_is_checkpoint_ready(sbi); + if (err) + return err; if (is_inode_flag_set(new_dir, FI_PROJ_INHERIT) && (!projid_eq(F2FS_I(new_dir)->i_projid, @@ -1014,6 +1030,9 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, if (unlikely(f2fs_cp_error(sbi))) return -EIO; + err = f2fs_is_checkpoint_ready(sbi); + if (err) + return err; if ((is_inode_flag_set(new_dir, FI_PROJ_INHERIT) && !projid_eq(F2FS_I(new_dir)->i_projid, diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index e16dae0f0a5b..195dc8142bff 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -176,6 +176,8 @@ bool f2fs_need_SSR(struct f2fs_sb_info *sbi) return false; if (sbi->gc_mode == GC_URGENT) return true; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) + return true; return free_sections(sbi) <= (node_secs + 2 * dent_secs + imeta_secs + SM_I(sbi)->min_ssr_sections + reserved_sections(sbi)); @@ -480,6 +482,9 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need) if (need && excess_cached_nats(sbi)) f2fs_balance_fs_bg(sbi); + if (f2fs_is_checkpoint_ready(sbi)) + return; + /* * We should do GC or end up with checkpoint, if there are so many dirty * dir/node pages without enough free segments. @@ -796,7 +801,7 @@ static void __remove_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno, static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno) { struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); - unsigned short valid_blocks; + unsigned short valid_blocks, ckpt_valid_blocks; if (segno == NULL_SEGNO || IS_CURSEG(sbi, segno)) return; @@ -804,8 +809,10 @@ static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno) mutex_lock(&dirty_i->seglist_lock); valid_blocks = get_valid_blocks(sbi, segno, false); + ckpt_valid_blocks = get_ckpt_valid_blocks(sbi, segno); - if (valid_blocks == 0) { + if (valid_blocks == 0 && (!is_sbi_flag_set(sbi, SBI_CP_DISABLED) || + ckpt_valid_blocks == sbi->blocks_per_seg)) { __locate_dirty_segment(sbi, segno, PRE); __remove_dirty_segment(sbi, segno, DIRTY); } else if (valid_blocks < sbi->blocks_per_seg) { @@ -818,6 +825,66 @@ static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno) mutex_unlock(&dirty_i->seglist_lock); } +/* This moves currently empty dirty blocks to prefree. Must hold seglist_lock */ +void f2fs_dirty_to_prefree(struct f2fs_sb_info *sbi) +{ + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + unsigned int segno; + + mutex_lock(&dirty_i->seglist_lock); + for_each_set_bit(segno, dirty_i->dirty_segmap[DIRTY], MAIN_SEGS(sbi)) { + if (get_valid_blocks(sbi, segno, false)) + continue; + if (IS_CURSEG(sbi, segno)) + continue; + __locate_dirty_segment(sbi, segno, PRE); + __remove_dirty_segment(sbi, segno, DIRTY); + } + mutex_unlock(&dirty_i->seglist_lock); +} + +int f2fs_disable_cp_again(struct f2fs_sb_info *sbi) +{ + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + block_t ovp = overprovision_segments(sbi) << sbi->log_blocks_per_seg; + block_t holes[2] = {0, 0}; /* DATA and NODE */ + struct seg_entry *se; + unsigned int segno; + + mutex_lock(&dirty_i->seglist_lock); + for_each_set_bit(segno, dirty_i->dirty_segmap[DIRTY], MAIN_SEGS(sbi)) { + se = get_seg_entry(sbi, segno); + if (IS_NODESEG(se->type)) + holes[NODE] += sbi->blocks_per_seg - se->valid_blocks; + else + holes[DATA] += sbi->blocks_per_seg - se->valid_blocks; + } + mutex_unlock(&dirty_i->seglist_lock); + + if (holes[DATA] > ovp || holes[NODE] > ovp) + return -EAGAIN; + return 0; +} + +/* This is only used by SBI_CP_DISABLED */ +static unsigned int get_free_segment(struct f2fs_sb_info *sbi) +{ + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + unsigned int segno = 0; + + mutex_lock(&dirty_i->seglist_lock); + for_each_set_bit(segno, dirty_i->dirty_segmap[DIRTY], MAIN_SEGS(sbi)) { + if (get_valid_blocks(sbi, segno, false)) + continue; + if (get_ckpt_valid_blocks(sbi, segno)) + continue; + mutex_unlock(&dirty_i->seglist_lock); + return segno; + } + mutex_unlock(&dirty_i->seglist_lock); + return NULL_SEGNO; +} + static struct discard_cmd *__create_discard_cmd(struct f2fs_sb_info *sbi, struct block_device *bdev, block_t lstart, block_t start, block_t len) @@ -2028,7 +2095,8 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) sbi->discard_blks--; /* don't overwrite by SSR to keep node chain */ - if (IS_NODESEG(se->type)) { + if (IS_NODESEG(se->type) && + !is_sbi_flag_set(sbi, SBI_CP_DISABLED)) { if (!f2fs_test_and_set_bit(offset, se->ckpt_valid_map)) se->ckpt_valid_blocks++; } @@ -2050,6 +2118,15 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) f2fs_bug_on(sbi, 1); se->valid_blocks++; del = 0; + } else if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { + /* + * If checkpoints are off, we must not reuse data that + * was used in the previous checkpoint. If it was used + * before, we must track that to know how much space we + * really have. + */ + if (f2fs_test_bit(offset, se->ckpt_valid_map)) + sbi->unusable_block_count++; } if (f2fs_test_and_clear_bit(offset, se->discard_map)) @@ -2332,6 +2409,9 @@ static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type) if (sbi->segs_per_sec != 1) return CURSEG_I(sbi, type)->segno; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) + return 0; + if (test_opt(sbi, NOHEAP) && (type == CURSEG_HOT_DATA || IS_NODESEG(type))) return 0; @@ -2476,6 +2556,15 @@ static int get_ssr_segment(struct f2fs_sb_info *sbi, int type) return 1; } } + + /* find valid_blocks=0 in dirty list */ + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { + segno = get_free_segment(sbi); + if (segno != NULL_SEGNO) { + curseg->next_segno = segno; + return 1; + } + } return 0; } @@ -2493,7 +2582,8 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi, else if (!is_set_ckpt_flags(sbi, CP_CRC_RECOVERY_FLAG) && type == CURSEG_WARM_NODE) new_curseg(sbi, type, false); - else if (curseg->alloc_type == LFS && is_next_segment_free(sbi, type)) + else if (curseg->alloc_type == LFS && is_next_segment_free(sbi, type) && + likely(!is_sbi_flag_set(sbi, SBI_CP_DISABLED))) new_curseg(sbi, type, false); else if (f2fs_need_SSR(sbi) && get_ssr_segment(sbi, type)) change_curseg(sbi, type); diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index 086150028c6d..ab3465faddf1 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -339,6 +339,12 @@ static inline unsigned int get_valid_blocks(struct f2fs_sb_info *sbi, return get_seg_entry(sbi, segno)->valid_blocks; } +static inline unsigned int get_ckpt_valid_blocks(struct f2fs_sb_info *sbi, + unsigned int segno) +{ + return get_seg_entry(sbi, segno)->ckpt_valid_blocks; +} + static inline void seg_info_from_raw_sit(struct seg_entry *se, struct f2fs_sit_entry *rs) { @@ -576,6 +582,15 @@ static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, reserved_sections(sbi) + needed); } +static inline int f2fs_is_checkpoint_ready(struct f2fs_sb_info *sbi) +{ + if (likely(!is_sbi_flag_set(sbi, SBI_CP_DISABLED))) + return 0; + if (likely(!has_not_enough_free_secs(sbi, 0, 0))) + return 0; + return -ENOSPC; +} + static inline bool excess_prefree_segs(struct f2fs_sb_info *sbi) { return prefree_segments(sbi) > SM_I(sbi)->rec_prefree_segments; diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index a44913224e3b..19933d839008 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -136,6 +136,7 @@ enum { Opt_alloc, Opt_fsync, Opt_test_dummy_encryption, + Opt_checkpoint, Opt_err, }; @@ -194,6 +195,7 @@ static match_table_t f2fs_tokens = { {Opt_alloc, "alloc_mode=%s"}, {Opt_fsync, "fsync_mode=%s"}, {Opt_test_dummy_encryption, "test_dummy_encryption"}, + {Opt_checkpoint, "checkpoint=%s"}, {Opt_err, NULL}, }; @@ -769,6 +771,23 @@ static int parse_options(struct super_block *sb, char *options) "Test dummy encryption mount option ignored"); #endif break; + case Opt_checkpoint: + name = match_strdup(&args[0]); + if (!name) + return -ENOMEM; + + if (strlen(name) == 6 && + !strncmp(name, "enable", 6)) { + clear_opt(sbi, DISABLE_CHECKPOINT); + } else if (strlen(name) == 7 && + !strncmp(name, "disable", 7)) { + set_opt(sbi, DISABLE_CHECKPOINT); + } else { + kfree(name); + return -EINVAL; + } + kfree(name); + break; default: f2fs_msg(sb, KERN_ERR, "Unrecognized mount option \"%s\" or missing value", @@ -827,6 +846,12 @@ static int parse_options(struct super_block *sb, char *options) } } + if (test_opt(sbi, DISABLE_CHECKPOINT) && test_opt(sbi, LFS)) { + f2fs_msg(sb, KERN_ERR, + "LFS not compatible with checkpoint=disable\n"); + return -EINVAL; + } + /* Not pass down write hints if the number of active logs is lesser * than NR_CURSEG_TYPE. */ @@ -1014,8 +1039,8 @@ static void f2fs_put_super(struct super_block *sb) * But, the previous checkpoint was not done by umount, it needs to do * clean checkpoint again. */ - if (is_sbi_flag_set(sbi, SBI_IS_DIRTY) || - !is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) { + if ((is_sbi_flag_set(sbi, SBI_IS_DIRTY) || + !is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG))) { struct cp_control cpc = { .reason = CP_UMOUNT, }; @@ -1087,6 +1112,8 @@ int f2fs_sync_fs(struct super_block *sb, int sync) if (unlikely(f2fs_cp_error(sbi))) return 0; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) + return 0; trace_f2fs_sync_fs(sb, sync); @@ -1186,6 +1213,11 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_blocks = total_count - start_count; buf->f_bfree = user_block_count - valid_user_blocks(sbi) - sbi->current_reserved_blocks; + if (unlikely(buf->f_bfree <= sbi->unusable_block_count)) + buf->f_bfree = 0; + else + buf->f_bfree -= sbi->unusable_block_count; + if (buf->f_bfree > F2FS_OPTION(sbi).root_reserved_blocks) buf->f_bavail = buf->f_bfree - F2FS_OPTION(sbi).root_reserved_blocks; @@ -1365,6 +1397,9 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) else if (F2FS_OPTION(sbi).alloc_mode == ALLOC_MODE_REUSE) seq_printf(seq, ",alloc_mode=%s", "reuse"); + if (test_opt(sbi, DISABLE_CHECKPOINT)) + seq_puts(seq, ",checkpoint=disable"); + if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_POSIX) seq_printf(seq, ",fsync_mode=%s", "posix"); else if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT) @@ -1392,6 +1427,7 @@ static void default_options(struct f2fs_sb_info *sbi) set_opt(sbi, INLINE_DENTRY); set_opt(sbi, EXTENT_CACHE); set_opt(sbi, NOHEAP); + clear_opt(sbi, DISABLE_CHECKPOINT); sbi->sb->s_flags |= SB_LAZYTIME; set_opt(sbi, FLUSH_MERGE); set_opt(sbi, DISCARD); @@ -1413,6 +1449,57 @@ static void default_options(struct f2fs_sb_info *sbi) #ifdef CONFIG_QUOTA static int f2fs_enable_quotas(struct super_block *sb); #endif + +static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi) +{ + struct cp_control cpc; + int err; + + sbi->sb->s_flags |= SB_ACTIVE; + + mutex_lock(&sbi->gc_mutex); + f2fs_update_time(sbi, DISABLE_TIME); + + while (!f2fs_time_over(sbi, DISABLE_TIME)) { + err = f2fs_gc(sbi, true, false, NULL_SEGNO); + if (err == -ENODATA) + break; + if (err && err != -EAGAIN) { + mutex_unlock(&sbi->gc_mutex); + return err; + } + } + mutex_unlock(&sbi->gc_mutex); + + err = sync_filesystem(sbi->sb); + if (err) + return err; + + if (f2fs_disable_cp_again(sbi)) + return -EAGAIN; + + mutex_lock(&sbi->gc_mutex); + cpc.reason = CP_PAUSE; + set_sbi_flag(sbi, SBI_CP_DISABLED); + f2fs_write_checkpoint(sbi, &cpc); + + sbi->unusable_block_count = 0; + mutex_unlock(&sbi->gc_mutex); + return 0; +} + +static void f2fs_enable_checkpoint(struct f2fs_sb_info *sbi) +{ + mutex_lock(&sbi->gc_mutex); + f2fs_dirty_to_prefree(sbi); + + clear_sbi_flag(sbi, SBI_CP_DISABLED); + set_sbi_flag(sbi, SBI_IS_DIRTY); + mutex_unlock(&sbi->gc_mutex); + + f2fs_sync_fs(sbi->sb, 1); +} + static int f2fs_remount(struct super_block *sb, int *flags, char *data) { struct f2fs_sb_info *sbi = F2FS_SB(sb); @@ -1422,6 +1509,8 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) bool need_restart_gc = false; bool need_stop_gc = false; bool no_extent_cache = !test_opt(sbi, EXTENT_CACHE); + bool disable_checkpoint = test_opt(sbi, DISABLE_CHECKPOINT); + bool checkpoint_changed; #ifdef CONFIG_QUOTA int i, j; #endif @@ -1466,6 +1555,8 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) err = parse_options(sb, data); if (err) goto restore_opts; + checkpoint_changed = + disable_checkpoint != test_opt(sbi, DISABLE_CHECKPOINT); /* * Previous and new state of filesystem is RO, @@ -1479,7 +1570,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) err = dquot_suspend(sb, -1); if (err < 0) goto restore_opts; - } else if (f2fs_readonly(sb) && !(*flags & MS_RDONLY)) { + } else if (f2fs_readonly(sb) && !(*flags & SB_RDONLY)) { /* dquot_resume needs RW */ sb->s_flags &= ~SB_RDONLY; if (sb_any_quota_suspended(sb)) { @@ -1499,6 +1590,13 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) goto restore_opts; } + if ((*flags & SB_RDONLY) && test_opt(sbi, DISABLE_CHECKPOINT)) { + err = -EINVAL; + f2fs_msg(sbi->sb, KERN_WARNING, + "disabling checkpoint not compatible with read-only"); + goto restore_opts; + } + /* * We stop the GC thread if FS is mounted as RO * or if background_gc = off is passed in mount @@ -1527,6 +1625,16 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) clear_sbi_flag(sbi, SBI_IS_CLOSE); } + if (checkpoint_changed) { + if (test_opt(sbi, DISABLE_CHECKPOINT)) { + err = f2fs_disable_checkpoint(sbi); + if (err) + goto restore_gc; + } else { + f2fs_enable_checkpoint(sbi); + } + } + /* * We stop issue flush thread if FS is mounted as RO * or if flush_merge is not passed in mount option. @@ -2485,6 +2593,7 @@ static void init_sb_info(struct f2fs_sb_info *sbi) sbi->interval_time[REQ_TIME] = DEF_IDLE_INTERVAL; sbi->interval_time[DISCARD_TIME] = DEF_IDLE_INTERVAL; sbi->interval_time[GC_TIME] = DEF_IDLE_INTERVAL; + sbi->interval_time[DISABLE_TIME] = DEF_DISABLE_INTERVAL; clear_sbi_flag(sbi, SBI_NEED_FSCK); for (i = 0; i < NR_COUNT_TYPE; i++) @@ -3093,6 +3202,9 @@ try_onemore: if (err) goto free_meta; + if (unlikely(is_set_ckpt_flags(sbi, CP_DISABLED_FLAG))) + goto skip_recovery; + /* recover fsynced data */ if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) { /* @@ -3132,6 +3244,14 @@ skip_recovery: /* f2fs_recover_fsync_data() cleared this already */ clear_sbi_flag(sbi, SBI_POR_DOING); + if (test_opt(sbi, DISABLE_CHECKPOINT)) { + err = f2fs_disable_checkpoint(sbi); + if (err) + goto free_meta; + } else if (is_set_ckpt_flags(sbi, CP_DISABLED_FLAG)) { + f2fs_enable_checkpoint(sbi); + } + /* * If filesystem is not mounted as read-only then * do start the gc_thread. diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 1db13ff9a3f4..8b9c7dc0260c 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -116,6 +116,7 @@ struct f2fs_super_block { /* * For checkpoint */ +#define CP_DISABLED_FLAG 0x00001000 #define CP_LARGE_NAT_BITMAP_FLAG 0x00000400 #define CP_NOCRC_RECOVERY_FLAG 0x00000200 #define CP_TRIMMED_FLAG 0x00000100 -- cgit v1.2.3 From c56a8be7e7aa855ebcccf0e9d9eba2216514d399 Mon Sep 17 00:00:00 2001 From: Rahul Verma Date: Tue, 16 Oct 2018 03:59:20 -0700 Subject: qed: Add supported link and advertise link to display in ethtool. Added transceiver type, speed capability and board types in HSI, are utilizing to display the accurate link information in ethtool. Signed-off-by: Rahul Verma Signed-off-by: Ariel Elior Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_main.c | 199 ++++++++++++++++++------ drivers/net/ethernet/qlogic/qed/qed_mcp.c | 182 ++++++++++++++++++++++ drivers/net/ethernet/qlogic/qed/qed_mcp.h | 46 ++++++ drivers/net/ethernet/qlogic/qede/qede_ethtool.c | 31 +++- include/linux/qed/qed_if.h | 26 +++- 5 files changed, 426 insertions(+), 58 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index 8c7cbbde65a6..e762881fdb38 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -58,6 +58,7 @@ #include "qed_iscsi.h" #include "qed_mcp.h" +#include "qed_reg_addr.h" #include "qed_hw.h" #include "qed_selftest.h" #include "qed_debug.h" @@ -1330,8 +1331,7 @@ static int qed_set_link(struct qed_dev *cdev, struct qed_link_params *params) link_params->speed.autoneg = params->autoneg; if (params->override_flags & QED_LINK_OVERRIDE_SPEED_ADV_SPEEDS) { link_params->speed.advertised_speeds = 0; - if ((params->adv_speeds & QED_LM_1000baseT_Half_BIT) || - (params->adv_speeds & QED_LM_1000baseT_Full_BIT)) + if (params->adv_speeds & QED_LM_1000baseT_Full_BIT) link_params->speed.advertised_speeds |= NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_1G; if (params->adv_speeds & QED_LM_10000baseKR_Full_BIT) @@ -1462,13 +1462,149 @@ static int qed_get_link_data(struct qed_hwfn *hwfn, return 0; } +static void qed_fill_link_capability(struct qed_hwfn *hwfn, + struct qed_ptt *ptt, u32 capability, + u32 *if_capability) +{ + u32 media_type, tcvr_state, tcvr_type; + u32 speed_mask, board_cfg; + + if (qed_mcp_get_media_type(hwfn, ptt, &media_type)) + media_type = MEDIA_UNSPECIFIED; + + if (qed_mcp_get_transceiver_data(hwfn, ptt, &tcvr_state, &tcvr_type)) + tcvr_type = ETH_TRANSCEIVER_STATE_UNPLUGGED; + + if (qed_mcp_trans_speed_mask(hwfn, ptt, &speed_mask)) + speed_mask = 0xFFFFFFFF; + + if (qed_mcp_get_board_config(hwfn, ptt, &board_cfg)) + board_cfg = NVM_CFG1_PORT_PORT_TYPE_UNDEFINED; + + DP_VERBOSE(hwfn->cdev, NETIF_MSG_DRV, + "Media_type = 0x%x tcvr_state = 0x%x tcvr_type = 0x%x speed_mask = 0x%x board_cfg = 0x%x\n", + media_type, tcvr_state, tcvr_type, speed_mask, board_cfg); + + switch (media_type) { + case MEDIA_DA_TWINAX: + if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_20G) + *if_capability |= QED_LM_20000baseKR2_Full_BIT; + /* For DAC media multiple speed capabilities are supported*/ + capability = capability & speed_mask; + if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_1G) + *if_capability |= QED_LM_1000baseKX_Full_BIT; + if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_10G) + *if_capability |= QED_LM_10000baseCR_Full_BIT; + if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_40G) + *if_capability |= QED_LM_40000baseCR4_Full_BIT; + if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_25G) + *if_capability |= QED_LM_25000baseCR_Full_BIT; + if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_50G) + *if_capability |= QED_LM_50000baseCR2_Full_BIT; + if (capability & + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_BB_100G) + *if_capability |= QED_LM_100000baseCR4_Full_BIT; + break; + case MEDIA_BASE_T: + if (board_cfg & NVM_CFG1_PORT_PORT_TYPE_EXT_PHY) { + if (capability & + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_1G) { + *if_capability |= QED_LM_1000baseT_Full_BIT; + } + if (capability & + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_10G) { + *if_capability |= QED_LM_10000baseT_Full_BIT; + } + } + if (board_cfg & NVM_CFG1_PORT_PORT_TYPE_MODULE) { + if (tcvr_type == ETH_TRANSCEIVER_TYPE_1000BASET) + *if_capability |= QED_LM_1000baseT_Full_BIT; + if (tcvr_type == ETH_TRANSCEIVER_TYPE_10G_BASET) + *if_capability |= QED_LM_10000baseT_Full_BIT; + } + break; + case MEDIA_SFP_1G_FIBER: + case MEDIA_SFPP_10G_FIBER: + case MEDIA_XFP_FIBER: + case MEDIA_MODULE_FIBER: + if (capability & + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_1G) { + if ((tcvr_type == ETH_TRANSCEIVER_TYPE_1G_LX) || + (tcvr_type == ETH_TRANSCEIVER_TYPE_1G_SX)) + *if_capability |= QED_LM_1000baseKX_Full_BIT; + } + if (capability & + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_10G) { + if (tcvr_type == ETH_TRANSCEIVER_TYPE_10G_SR) + *if_capability |= QED_LM_10000baseSR_Full_BIT; + if (tcvr_type == ETH_TRANSCEIVER_TYPE_10G_LR) + *if_capability |= QED_LM_10000baseLR_Full_BIT; + if (tcvr_type == ETH_TRANSCEIVER_TYPE_10G_LRM) + *if_capability |= QED_LM_10000baseLRM_Full_BIT; + if (tcvr_type == ETH_TRANSCEIVER_TYPE_10G_ER) + *if_capability |= QED_LM_10000baseR_FEC_BIT; + } + if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_20G) + *if_capability |= QED_LM_20000baseKR2_Full_BIT; + if (capability & + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_25G) { + if (tcvr_type == ETH_TRANSCEIVER_TYPE_25G_SR) + *if_capability |= QED_LM_25000baseSR_Full_BIT; + } + if (capability & + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_40G) { + if (tcvr_type == ETH_TRANSCEIVER_TYPE_40G_LR4) + *if_capability |= QED_LM_40000baseLR4_Full_BIT; + if (tcvr_type == ETH_TRANSCEIVER_TYPE_40G_SR4) + *if_capability |= QED_LM_40000baseSR4_Full_BIT; + } + if (capability & + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_50G) + *if_capability |= QED_LM_50000baseKR2_Full_BIT; + if (capability & + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_BB_100G) { + if (tcvr_type == ETH_TRANSCEIVER_TYPE_100G_SR4) + *if_capability |= QED_LM_100000baseSR4_Full_BIT; + } + + break; + case MEDIA_KR: + if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_20G) + *if_capability |= QED_LM_20000baseKR2_Full_BIT; + if (capability & + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_1G) + *if_capability |= QED_LM_1000baseKX_Full_BIT; + if (capability & + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_10G) + *if_capability |= QED_LM_10000baseKR_Full_BIT; + if (capability & + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_25G) + *if_capability |= QED_LM_25000baseKR_Full_BIT; + if (capability & + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_40G) + *if_capability |= QED_LM_40000baseKR4_Full_BIT; + if (capability & + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_50G) + *if_capability |= QED_LM_50000baseKR2_Full_BIT; + if (capability & + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_BB_100G) + *if_capability |= QED_LM_100000baseKR4_Full_BIT; + break; + case MEDIA_UNSPECIFIED: + case MEDIA_NOT_PRESENT: + DP_VERBOSE(hwfn->cdev, QED_MSG_DEBUG, + "Unknown media and transceiver type;\n"); + break; + } +} + static void qed_fill_link(struct qed_hwfn *hwfn, struct qed_ptt *ptt, struct qed_link_output *if_link) { + struct qed_mcp_link_capabilities link_caps; struct qed_mcp_link_params params; struct qed_mcp_link_state link; - struct qed_mcp_link_capabilities link_caps; u32 media_type; memset(if_link, 0, sizeof(*if_link)); @@ -1499,51 +1635,13 @@ static void qed_fill_link(struct qed_hwfn *hwfn, if_link->advertised_caps |= QED_LM_Autoneg_BIT; else if_link->advertised_caps &= ~QED_LM_Autoneg_BIT; - if (params.speed.advertised_speeds & - NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_1G) - if_link->advertised_caps |= QED_LM_1000baseT_Half_BIT | - QED_LM_1000baseT_Full_BIT; - if (params.speed.advertised_speeds & - NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_10G) - if_link->advertised_caps |= QED_LM_10000baseKR_Full_BIT; - if (params.speed.advertised_speeds & - NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_20G) - if_link->advertised_caps |= QED_LM_20000baseKR2_Full_BIT; - if (params.speed.advertised_speeds & - NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_25G) - if_link->advertised_caps |= QED_LM_25000baseKR_Full_BIT; - if (params.speed.advertised_speeds & - NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_40G) - if_link->advertised_caps |= QED_LM_40000baseLR4_Full_BIT; - if (params.speed.advertised_speeds & - NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_50G) - if_link->advertised_caps |= QED_LM_50000baseKR2_Full_BIT; - if (params.speed.advertised_speeds & - NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_BB_100G) - if_link->advertised_caps |= QED_LM_100000baseKR4_Full_BIT; - - if (link_caps.speed_capabilities & - NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_1G) - if_link->supported_caps |= QED_LM_1000baseT_Half_BIT | - QED_LM_1000baseT_Full_BIT; - if (link_caps.speed_capabilities & - NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_10G) - if_link->supported_caps |= QED_LM_10000baseKR_Full_BIT; - if (link_caps.speed_capabilities & - NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_20G) - if_link->supported_caps |= QED_LM_20000baseKR2_Full_BIT; - if (link_caps.speed_capabilities & - NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_25G) - if_link->supported_caps |= QED_LM_25000baseKR_Full_BIT; - if (link_caps.speed_capabilities & - NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_40G) - if_link->supported_caps |= QED_LM_40000baseLR4_Full_BIT; - if (link_caps.speed_capabilities & - NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_50G) - if_link->supported_caps |= QED_LM_50000baseKR2_Full_BIT; - if (link_caps.speed_capabilities & - NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_BB_100G) - if_link->supported_caps |= QED_LM_100000baseKR4_Full_BIT; + + /* Fill link advertised capability*/ + qed_fill_link_capability(hwfn, ptt, params.speed.advertised_speeds, + &if_link->advertised_caps); + /* Fill link supported capability*/ + qed_fill_link_capability(hwfn, ptt, link_caps.speed_capabilities, + &if_link->supported_caps); if (link.link_up) if_link->speed = link.speed; @@ -1563,9 +1661,8 @@ static void qed_fill_link(struct qed_hwfn *hwfn, if_link->pause_config |= QED_LINK_PAUSE_TX_ENABLE; /* Link partner capabilities */ - if (link.partner_adv_speed & QED_LINK_PARTNER_SPEED_1G_HD) - if_link->lp_caps |= QED_LM_1000baseT_Half_BIT; - if (link.partner_adv_speed & QED_LINK_PARTNER_SPEED_1G_FD) + if (link.partner_adv_speed & + QED_LINK_PARTNER_SPEED_1G_FD) if_link->lp_caps |= QED_LM_1000baseT_Full_BIT; if (link.partner_adv_speed & QED_LINK_PARTNER_SPEED_10G) if_link->lp_caps |= QED_LM_10000baseKR_Full_BIT; diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index 92c5950ad156..554d57ac1629 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -1870,6 +1870,8 @@ int qed_mcp_get_mbi_ver(struct qed_hwfn *p_hwfn, int qed_mcp_get_media_type(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 *p_media_type) { + *p_media_type = MEDIA_UNSPECIFIED; + if (IS_VF(p_hwfn->cdev)) return -EINVAL; @@ -1891,6 +1893,186 @@ int qed_mcp_get_media_type(struct qed_hwfn *p_hwfn, return 0; } +int qed_mcp_get_transceiver_data(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *p_transceiver_state, + u32 *p_transceiver_type) +{ + u32 transceiver_info; + + if (IS_VF(p_hwfn->cdev)) + return -EINVAL; + + if (!qed_mcp_is_init(p_hwfn)) { + DP_NOTICE(p_hwfn, "MFW is not initialized!\n"); + return -EBUSY; + } + + *p_transceiver_type = ETH_TRANSCEIVER_TYPE_NONE; + *p_transceiver_state = ETH_TRANSCEIVER_STATE_UPDATING; + + transceiver_info = qed_rd(p_hwfn, p_ptt, + p_hwfn->mcp_info->port_addr + + offsetof(struct public_port, + transceiver_data)); + + *p_transceiver_state = (transceiver_info & + ETH_TRANSCEIVER_STATE_MASK) >> + ETH_TRANSCEIVER_STATE_OFFSET; + + if (*p_transceiver_state == ETH_TRANSCEIVER_STATE_PRESENT) + *p_transceiver_type = (transceiver_info & + ETH_TRANSCEIVER_TYPE_MASK) >> + ETH_TRANSCEIVER_TYPE_OFFSET; + else + *p_transceiver_type = ETH_TRANSCEIVER_TYPE_UNKNOWN; + + return 0; +} +static bool qed_is_transceiver_ready(u32 transceiver_state, + u32 transceiver_type) +{ + if ((transceiver_state & ETH_TRANSCEIVER_STATE_PRESENT) && + ((transceiver_state & ETH_TRANSCEIVER_STATE_UPDATING) == 0x0) && + (transceiver_type != ETH_TRANSCEIVER_TYPE_NONE)) + return true; + + return false; +} + +int qed_mcp_trans_speed_mask(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, u32 *p_speed_mask) +{ + u32 transceiver_type, transceiver_state; + + qed_mcp_get_transceiver_data(p_hwfn, p_ptt, &transceiver_state, + &transceiver_type); + + if (qed_is_transceiver_ready(transceiver_state, transceiver_type) == + false) + return -EINVAL; + + switch (transceiver_type) { + case ETH_TRANSCEIVER_TYPE_1G_LX: + case ETH_TRANSCEIVER_TYPE_1G_SX: + case ETH_TRANSCEIVER_TYPE_1G_PCC: + case ETH_TRANSCEIVER_TYPE_1G_ACC: + case ETH_TRANSCEIVER_TYPE_1000BASET: + *p_speed_mask = NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_1G; + break; + case ETH_TRANSCEIVER_TYPE_10G_SR: + case ETH_TRANSCEIVER_TYPE_10G_LR: + case ETH_TRANSCEIVER_TYPE_10G_LRM: + case ETH_TRANSCEIVER_TYPE_10G_ER: + case ETH_TRANSCEIVER_TYPE_10G_PCC: + case ETH_TRANSCEIVER_TYPE_10G_ACC: + case ETH_TRANSCEIVER_TYPE_4x10G: + *p_speed_mask = NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_10G; + break; + case ETH_TRANSCEIVER_TYPE_40G_LR4: + case ETH_TRANSCEIVER_TYPE_40G_SR4: + case ETH_TRANSCEIVER_TYPE_MULTI_RATE_10G_40G_SR: + case ETH_TRANSCEIVER_TYPE_MULTI_RATE_10G_40G_LR: + *p_speed_mask = NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_40G | + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_10G; + break; + case ETH_TRANSCEIVER_TYPE_100G_AOC: + case ETH_TRANSCEIVER_TYPE_100G_SR4: + case ETH_TRANSCEIVER_TYPE_100G_LR4: + case ETH_TRANSCEIVER_TYPE_100G_ER4: + case ETH_TRANSCEIVER_TYPE_100G_ACC: + *p_speed_mask = + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_BB_100G | + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_25G; + break; + case ETH_TRANSCEIVER_TYPE_25G_SR: + case ETH_TRANSCEIVER_TYPE_25G_LR: + case ETH_TRANSCEIVER_TYPE_25G_AOC: + case ETH_TRANSCEIVER_TYPE_25G_ACC_S: + case ETH_TRANSCEIVER_TYPE_25G_ACC_M: + case ETH_TRANSCEIVER_TYPE_25G_ACC_L: + *p_speed_mask = NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_25G; + break; + case ETH_TRANSCEIVER_TYPE_25G_CA_N: + case ETH_TRANSCEIVER_TYPE_25G_CA_S: + case ETH_TRANSCEIVER_TYPE_25G_CA_L: + case ETH_TRANSCEIVER_TYPE_4x25G_CR: + *p_speed_mask = NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_25G | + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_10G | + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_1G; + break; + case ETH_TRANSCEIVER_TYPE_40G_CR4: + case ETH_TRANSCEIVER_TYPE_MULTI_RATE_10G_40G_CR: + *p_speed_mask = NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_40G | + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_10G | + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_1G; + break; + case ETH_TRANSCEIVER_TYPE_100G_CR4: + case ETH_TRANSCEIVER_TYPE_MULTI_RATE_40G_100G_CR: + *p_speed_mask = + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_BB_100G | + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_50G | + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_40G | + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_25G | + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_20G | + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_10G | + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_1G; + break; + case ETH_TRANSCEIVER_TYPE_MULTI_RATE_40G_100G_SR: + case ETH_TRANSCEIVER_TYPE_MULTI_RATE_40G_100G_LR: + case ETH_TRANSCEIVER_TYPE_MULTI_RATE_40G_100G_AOC: + *p_speed_mask = + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_BB_100G | + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_40G | + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_25G | + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_10G; + break; + case ETH_TRANSCEIVER_TYPE_XLPPI: + *p_speed_mask = NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_40G; + break; + case ETH_TRANSCEIVER_TYPE_10G_BASET: + *p_speed_mask = NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_10G | + NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_1G; + break; + default: + DP_INFO(p_hwfn, "Unknown transcevier type 0x%x\n", + transceiver_type); + *p_speed_mask = 0xff; + break; + } + + return 0; +} + +int qed_mcp_get_board_config(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, u32 *p_board_config) +{ + u32 nvm_cfg_addr, nvm_cfg1_offset, port_cfg_addr; + + if (IS_VF(p_hwfn->cdev)) + return -EINVAL; + + if (!qed_mcp_is_init(p_hwfn)) { + DP_NOTICE(p_hwfn, "MFW is not initialized!\n"); + return -EBUSY; + } + if (!p_ptt) { + *p_board_config = NVM_CFG1_PORT_PORT_TYPE_UNDEFINED; + return -EINVAL; + } + + nvm_cfg_addr = qed_rd(p_hwfn, p_ptt, MISC_REG_GEN_PURP_CR0); + nvm_cfg1_offset = qed_rd(p_hwfn, p_ptt, nvm_cfg_addr + 4); + port_cfg_addr = MCP_REG_SCRATCH + nvm_cfg1_offset + + offsetof(struct nvm_cfg1, port[MFW_PORT(p_hwfn)]); + *p_board_config = qed_rd(p_hwfn, p_ptt, + port_cfg_addr + + offsetof(struct nvm_cfg1_port, + board_cfg)); + + return 0; +} + /* Old MFW has a global configuration for all PFs regarding RDMA support */ static void qed_mcp_get_shmem_proto_legacy(struct qed_hwfn *p_hwfn, diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h index 80a6b5d1ff33..1adfe52b3905 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h @@ -332,6 +332,52 @@ int qed_mcp_get_mbi_ver(struct qed_hwfn *p_hwfn, int qed_mcp_get_media_type(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 *media_type); +/** + * @brief Get transceiver data of the port. + * + * @param cdev - qed dev pointer + * @param p_ptt + * @param p_transceiver_state - transceiver state. + * @param p_transceiver_type - media type value + * + * @return int - + * 0 - Operation was successful. + * -EBUSY - Operation failed + */ +int qed_mcp_get_transceiver_data(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 *p_transceiver_state, + u32 *p_tranceiver_type); + +/** + * @brief Get transceiver supported speed mask. + * + * @param cdev - qed dev pointer + * @param p_ptt + * @param p_speed_mask - Bit mask of all supported speeds. + * + * @return int - + * 0 - Operation was successful. + * -EBUSY - Operation failed + */ + +int qed_mcp_trans_speed_mask(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, u32 *p_speed_mask); + +/** + * @brief Get board configuration. + * + * @param cdev - qed dev pointer + * @param p_ptt + * @param p_board_config - Board config. + * + * @return int - + * 0 - Operation was successful. + * -EBUSY - Operation failed + */ +int qed_mcp_get_board_config(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, u32 *p_board_config); + /** * @brief General function for sending commands to the MCP * mailbox. It acquire mutex lock for the entire diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c index 7ff50b4488f6..df3ad591140d 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c @@ -413,19 +413,42 @@ struct qede_link_mode_mapping { }; static const struct qede_link_mode_mapping qed_lm_map[] = { - {QED_LM_FIBRE_BIT, ETHTOOL_LINK_MODE_FIBRE_BIT}, {QED_LM_Autoneg_BIT, ETHTOOL_LINK_MODE_Autoneg_BIT}, {QED_LM_Asym_Pause_BIT, ETHTOOL_LINK_MODE_Asym_Pause_BIT}, {QED_LM_Pause_BIT, ETHTOOL_LINK_MODE_Pause_BIT}, - {QED_LM_1000baseT_Half_BIT, ETHTOOL_LINK_MODE_1000baseT_Half_BIT}, {QED_LM_1000baseT_Full_BIT, ETHTOOL_LINK_MODE_1000baseT_Full_BIT}, + {QED_LM_10000baseT_Full_BIT, ETHTOOL_LINK_MODE_10000baseT_Full_BIT}, + {QED_LM_2500baseX_Full_BIT, ETHTOOL_LINK_MODE_2500baseX_Full_BIT}, + {QED_LM_Backplane_BIT, ETHTOOL_LINK_MODE_Backplane_BIT}, + {QED_LM_1000baseKX_Full_BIT, ETHTOOL_LINK_MODE_1000baseKX_Full_BIT}, + {QED_LM_10000baseKX4_Full_BIT, ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT}, {QED_LM_10000baseKR_Full_BIT, ETHTOOL_LINK_MODE_10000baseKR_Full_BIT}, + {QED_LM_10000baseKR_Full_BIT, ETHTOOL_LINK_MODE_10000baseKR_Full_BIT}, + {QED_LM_10000baseR_FEC_BIT, ETHTOOL_LINK_MODE_10000baseR_FEC_BIT}, {QED_LM_20000baseKR2_Full_BIT, ETHTOOL_LINK_MODE_20000baseKR2_Full_BIT}, - {QED_LM_25000baseKR_Full_BIT, ETHTOOL_LINK_MODE_25000baseKR_Full_BIT}, + {QED_LM_40000baseKR4_Full_BIT, ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT}, + {QED_LM_40000baseCR4_Full_BIT, ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT}, + {QED_LM_40000baseSR4_Full_BIT, ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT}, {QED_LM_40000baseLR4_Full_BIT, ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT}, + {QED_LM_25000baseCR_Full_BIT, ETHTOOL_LINK_MODE_25000baseCR_Full_BIT}, + {QED_LM_25000baseKR_Full_BIT, ETHTOOL_LINK_MODE_25000baseKR_Full_BIT}, + {QED_LM_25000baseSR_Full_BIT, ETHTOOL_LINK_MODE_25000baseSR_Full_BIT}, + {QED_LM_50000baseCR2_Full_BIT, ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT}, {QED_LM_50000baseKR2_Full_BIT, ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT}, {QED_LM_100000baseKR4_Full_BIT, - ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT}, + ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT}, + {QED_LM_100000baseSR4_Full_BIT, + ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT}, + {QED_LM_100000baseCR4_Full_BIT, + ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT}, + {QED_LM_100000baseLR4_ER4_Full_BIT, + ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT}, + {QED_LM_50000baseSR2_Full_BIT, ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT}, + {QED_LM_1000baseX_Full_BIT, ETHTOOL_LINK_MODE_1000baseX_Full_BIT}, + {QED_LM_10000baseCR_Full_BIT, ETHTOOL_LINK_MODE_10000baseCR_Full_BIT}, + {QED_LM_10000baseSR_Full_BIT, ETHTOOL_LINK_MODE_10000baseSR_Full_BIT}, + {QED_LM_10000baseLR_Full_BIT, ETHTOOL_LINK_MODE_10000baseLR_Full_BIT}, + {QED_LM_10000baseLRM_Full_BIT, ETHTOOL_LINK_MODE_10000baseLRM_Full_BIT}, }; #define QEDE_DRV_TO_ETHTOOL_CAPS(caps, lk_ksettings, name) \ diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index dee3c9c744f7..a47321a0d572 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -667,15 +667,35 @@ enum qed_link_mode_bits { QED_LM_Autoneg_BIT = BIT(1), QED_LM_Asym_Pause_BIT = BIT(2), QED_LM_Pause_BIT = BIT(3), - QED_LM_1000baseT_Half_BIT = BIT(4), - QED_LM_1000baseT_Full_BIT = BIT(5), + QED_LM_1000baseT_Full_BIT = BIT(4), + QED_LM_10000baseT_Full_BIT = BIT(5), QED_LM_10000baseKR_Full_BIT = BIT(6), QED_LM_20000baseKR2_Full_BIT = BIT(7), QED_LM_25000baseKR_Full_BIT = BIT(8), QED_LM_40000baseLR4_Full_BIT = BIT(9), QED_LM_50000baseKR2_Full_BIT = BIT(10), QED_LM_100000baseKR4_Full_BIT = BIT(11), - QED_LM_COUNT = 11 + QED_LM_2500baseX_Full_BIT = BIT(12), + QED_LM_Backplane_BIT = BIT(13), + QED_LM_1000baseKX_Full_BIT = BIT(14), + QED_LM_10000baseKX4_Full_BIT = BIT(15), + QED_LM_10000baseR_FEC_BIT = BIT(16), + QED_LM_40000baseKR4_Full_BIT = BIT(17), + QED_LM_40000baseCR4_Full_BIT = BIT(18), + QED_LM_40000baseSR4_Full_BIT = BIT(19), + QED_LM_25000baseCR_Full_BIT = BIT(20), + QED_LM_25000baseSR_Full_BIT = BIT(21), + QED_LM_50000baseCR2_Full_BIT = BIT(22), + QED_LM_100000baseSR4_Full_BIT = BIT(23), + QED_LM_100000baseCR4_Full_BIT = BIT(24), + QED_LM_100000baseLR4_ER4_Full_BIT = BIT(25), + QED_LM_50000baseSR2_Full_BIT = BIT(26), + QED_LM_1000baseX_Full_BIT = BIT(27), + QED_LM_10000baseCR_Full_BIT = BIT(28), + QED_LM_10000baseSR_Full_BIT = BIT(29), + QED_LM_10000baseLR_Full_BIT = BIT(30), + QED_LM_10000baseLRM_Full_BIT = BIT(31), + QED_LM_COUNT = 32 }; struct qed_link_params { -- cgit v1.2.3 From 94a04d1d3d3681adde1a3e022b25dbac7b345b7e Mon Sep 17 00:00:00 2001 From: Yonatan Cohen Date: Tue, 9 Oct 2018 12:05:12 +0300 Subject: net/mlx5: Expose DC scatter to CQE capability bit dc_req_scat_data_cqe capability bit determines if requester scatter to cqe is available for 64 bytes CQE over DC transport type. Signed-off-by: Yonatan Cohen Reviewed-by: Guy Levi Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 68f4d5f9d929..0f460fb22c31 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1005,7 +1005,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 umr_modify_atomic_disabled[0x1]; u8 umr_indirect_mkey_disabled[0x1]; u8 umr_fence[0x2]; - u8 reserved_at_20c[0x3]; + u8 dc_req_scat_data_cqe[0x1]; + u8 reserved_at_20d[0x2]; u8 drain_sigerr[0x1]; u8 cmdif_checksum[0x2]; u8 sigerr_cqe[0x1]; -- cgit v1.2.3 From 3f4c3127d332000530349db4843deece27fe5e0c Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 16 Oct 2018 10:36:01 -0700 Subject: bpf: sockmap, fix skmsg recvmsg handler to track size correctly When converting sockmap to new skmsg generic data structures we missed that the recvmsg handler did not correctly use sg.size and instead was using individual elements length. The result is if a sock is closed with outstanding data we omit the call to sk_mem_uncharge() and can get the warning below. [ 66.728282] WARNING: CPU: 6 PID: 5783 at net/core/stream.c:206 sk_stream_kill_queues+0x1fa/0x210 To fix this correct the redirect handler to xfer the size along with the scatterlist and also decrement the size from the recvmsg handler. Now when a sock is closed the remaining 'size' will be decremented with sk_mem_uncharge(). Signed-off-by: John Fastabend Acked-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- include/linux/skmsg.h | 1 + net/ipv4/tcp_bpf.c | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 0b919f0bc6d6..31df0d9fa536 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -176,6 +176,7 @@ static inline void sk_msg_xfer(struct sk_msg *dst, struct sk_msg *src, { dst->sg.data[which] = src->sg.data[which]; dst->sg.data[which].length = size; + dst->sg.size += size; src->sg.data[which].length -= size; src->sg.data[which].offset += size; } diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 80debb0daf37..f9d3cf185827 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -73,6 +73,7 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, sge->offset += copy; sge->length -= copy; sk_mem_uncharge(sk, copy); + msg_rx->sg.size -= copy; if (!sge->length) { i++; if (i == MAX_SKB_FRAGS) -- cgit v1.2.3 From 8734a162c13b1a893e7dff8de0df81fed04c51a6 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 16 Oct 2018 11:07:59 -0700 Subject: bpf: skmsg, improve sk_msg_used_element to work in cork context Currently sk_msg_used_element is only called in zerocopy context where cork is not possible and if this case happens we fallback to copy mode. However the helper is more useful if it works in all contexts. This patch resolved the case where if end == head indicating a full or empty ring the helper always reports an empty ring. To fix this add a test for the full ring case to avoid reporting a full ring has 0 elements. This additional functionality will be used in the next patches from recvmsg context where end = head with a full ring is a valid case. Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann --- include/linux/skmsg.h | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 31df0d9fa536..22347b08e1f8 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -187,18 +187,21 @@ static inline void sk_msg_xfer_full(struct sk_msg *dst, struct sk_msg *src) sk_msg_init(src); } +static inline bool sk_msg_full(const struct sk_msg *msg) +{ + return (msg->sg.end == msg->sg.start) && msg->sg.size; +} + static inline u32 sk_msg_elem_used(const struct sk_msg *msg) { + if (sk_msg_full(msg)) + return MAX_MSG_FRAGS; + return msg->sg.end >= msg->sg.start ? msg->sg.end - msg->sg.start : msg->sg.end + (MAX_MSG_FRAGS - msg->sg.start); } -static inline bool sk_msg_full(const struct sk_msg *msg) -{ - return (msg->sg.end == msg->sg.start) && msg->sg.size; -} - static inline struct scatterlist *sk_msg_elem(struct sk_msg *msg, int which) { return &msg->sg.data[which]; -- cgit v1.2.3 From a60109dc9a954ef9eddba6577e2d2e9e7952e487 Mon Sep 17 00:00:00 2001 From: Yonatan Cohen Date: Wed, 10 Oct 2018 09:25:16 +0300 Subject: IB/mlx5: Add support for extended atomic operations Extended atomic operations cmp&swp and fetch&add is a Mellanox feature extending the standard atomic operation to use, varied operand sizes, as apposed to normal atomic operation that use an 8 byte operand only. Extended atomics allows masking the results and arguments. This patch configures QP to support extended atomic operation with the maximum size possible, as exposed by HCA capabilities. Signed-off-by: Yonatan Cohen Reviewed-by: Guy Levi Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/qp.c | 96 +++++++++++++++++++++++++++++++++++------ include/linux/mlx5/driver.h | 23 +++++----- 2 files changed, 95 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 368728e6f980..6841c0f9237f 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -1733,6 +1733,53 @@ static void configure_requester_scat_cqe(struct mlx5_ib_dev *dev, MLX5_SET(qpc, qpc, cs_req, MLX5_REQ_SCAT_DATA32_CQE); } +static int atomic_size_to_mode(int size_mask) +{ + /* driver does not support atomic_size > 256B + * and does not know how to translate bigger sizes + */ + int supported_size_mask = size_mask & 0x1ff; + int log_max_size; + + if (!supported_size_mask) + return -EOPNOTSUPP; + + log_max_size = __fls(supported_size_mask); + + if (log_max_size > 3) + return log_max_size; + + return MLX5_ATOMIC_MODE_8B; +} + +static int get_atomic_mode(struct mlx5_ib_dev *dev, + enum ib_qp_type qp_type) +{ + u8 atomic_operations = MLX5_CAP_ATOMIC(dev->mdev, atomic_operations); + u8 atomic = MLX5_CAP_GEN(dev->mdev, atomic); + int atomic_mode = -EOPNOTSUPP; + int atomic_size_mask; + + if (!atomic) + return -EOPNOTSUPP; + + if (qp_type == MLX5_IB_QPT_DCT) + atomic_size_mask = MLX5_CAP_ATOMIC(dev->mdev, atomic_size_dc); + else + atomic_size_mask = MLX5_CAP_ATOMIC(dev->mdev, atomic_size_qp); + + if ((atomic_operations & MLX5_ATOMIC_OPS_EXTENDED_CMP_SWAP) || + (atomic_operations & MLX5_ATOMIC_OPS_EXTENDED_FETCH_ADD)) + atomic_mode = atomic_size_to_mode(atomic_size_mask); + + if (atomic_mode <= 0 && + (atomic_operations & MLX5_ATOMIC_OPS_CMP_SWAP && + atomic_operations & MLX5_ATOMIC_OPS_FETCH_ADD)) + atomic_mode = MLX5_ATOMIC_MODE_IB_COMP; + + return atomic_mode; +} + static inline bool check_flags_mask(uint64_t input, uint64_t supported) { return (input & ~supported) == 0; @@ -2562,13 +2609,15 @@ int mlx5_ib_destroy_qp(struct ib_qp *qp) return 0; } -static __be32 to_mlx5_access_flags(struct mlx5_ib_qp *qp, const struct ib_qp_attr *attr, - int attr_mask) +static int to_mlx5_access_flags(struct mlx5_ib_qp *qp, + const struct ib_qp_attr *attr, + int attr_mask, __be32 *hw_access_flags) { - u32 hw_access_flags = 0; u8 dest_rd_atomic; u32 access_flags; + struct mlx5_ib_dev *dev = to_mdev(qp->ibqp.device); + if (attr_mask & IB_QP_MAX_DEST_RD_ATOMIC) dest_rd_atomic = attr->max_dest_rd_atomic; else @@ -2583,13 +2632,25 @@ static __be32 to_mlx5_access_flags(struct mlx5_ib_qp *qp, const struct ib_qp_att access_flags &= IB_ACCESS_REMOTE_WRITE; if (access_flags & IB_ACCESS_REMOTE_READ) - hw_access_flags |= MLX5_QP_BIT_RRE; - if (access_flags & IB_ACCESS_REMOTE_ATOMIC) - hw_access_flags |= (MLX5_QP_BIT_RAE | MLX5_ATOMIC_MODE_CX); + *hw_access_flags |= MLX5_QP_BIT_RRE; + if ((access_flags & IB_ACCESS_REMOTE_ATOMIC) && + qp->ibqp.qp_type == IB_QPT_RC) { + int atomic_mode; + + atomic_mode = get_atomic_mode(dev, qp->ibqp.qp_type); + if (atomic_mode < 0) + return -EOPNOTSUPP; + + *hw_access_flags |= MLX5_QP_BIT_RAE; + *hw_access_flags |= atomic_mode << MLX5_ATOMIC_MODE_OFFSET; + } + if (access_flags & IB_ACCESS_REMOTE_WRITE) - hw_access_flags |= MLX5_QP_BIT_RWE; + *hw_access_flags |= MLX5_QP_BIT_RWE; + + *hw_access_flags = cpu_to_be32(*hw_access_flags); - return cpu_to_be32(hw_access_flags); + return 0; } enum { @@ -3287,8 +3348,15 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp, cpu_to_be32(fls(attr->max_dest_rd_atomic - 1) << 21); } - if (attr_mask & (IB_QP_ACCESS_FLAGS | IB_QP_MAX_DEST_RD_ATOMIC)) - context->params2 |= to_mlx5_access_flags(qp, attr, attr_mask); + if (attr_mask & (IB_QP_ACCESS_FLAGS | IB_QP_MAX_DEST_RD_ATOMIC)) { + __be32 access_flags = 0; + + err = to_mlx5_access_flags(qp, attr, attr_mask, &access_flags); + if (err) + goto out; + + context->params2 |= access_flags; + } if (attr_mask & IB_QP_MIN_RNR_TIMER) context->rnr_nextrecvpsn |= cpu_to_be32(attr->min_rnr_timer << 24); @@ -3504,10 +3572,14 @@ static int mlx5_ib_modify_dct(struct ib_qp *ibqp, struct ib_qp_attr *attr, if (attr->qp_access_flags & IB_ACCESS_REMOTE_WRITE) MLX5_SET(dctc, dctc, rwe, 1); if (attr->qp_access_flags & IB_ACCESS_REMOTE_ATOMIC) { - if (!mlx5_ib_dc_atomic_is_supported(dev)) + int atomic_mode; + + atomic_mode = get_atomic_mode(dev, MLX5_IB_QPT_DCT); + if (atomic_mode < 0) return -EOPNOTSUPP; + + MLX5_SET(dctc, dctc, atomic_mode, atomic_mode); MLX5_SET(dctc, dctc, rae, 1); - MLX5_SET(dctc, dctc, atomic_mode, MLX5_ATOMIC_MODE_DCT_CX); } MLX5_SET(dctc, dctc, pkey_index, attr->pkey_index); MLX5_SET(dctc, dctc, port, attr->port_num); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 8fb072aa8671..a73c701edd16 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -97,14 +97,15 @@ enum { }; enum { - MLX5_ATOMIC_MODE_IB_COMP = 1 << 16, - MLX5_ATOMIC_MODE_CX = 2 << 16, - MLX5_ATOMIC_MODE_8B = 3 << 16, - MLX5_ATOMIC_MODE_16B = 4 << 16, - MLX5_ATOMIC_MODE_32B = 5 << 16, - MLX5_ATOMIC_MODE_64B = 6 << 16, - MLX5_ATOMIC_MODE_128B = 7 << 16, - MLX5_ATOMIC_MODE_256B = 8 << 16, + MLX5_ATOMIC_MODE_OFFSET = 16, + MLX5_ATOMIC_MODE_IB_COMP = 1, + MLX5_ATOMIC_MODE_CX = 2, + MLX5_ATOMIC_MODE_8B = 3, + MLX5_ATOMIC_MODE_16B = 4, + MLX5_ATOMIC_MODE_32B = 5, + MLX5_ATOMIC_MODE_64B = 6, + MLX5_ATOMIC_MODE_128B = 7, + MLX5_ATOMIC_MODE_256B = 8, }; enum { @@ -162,13 +163,11 @@ enum mlx5_dcbx_oper_mode { MLX5E_DCBX_PARAM_VER_OPER_AUTO = 0x3, }; -enum mlx5_dct_atomic_mode { - MLX5_ATOMIC_MODE_DCT_CX = 2, -}; - enum { MLX5_ATOMIC_OPS_CMP_SWAP = 1 << 0, MLX5_ATOMIC_OPS_FETCH_ADD = 1 << 1, + MLX5_ATOMIC_OPS_EXTENDED_CMP_SWAP = 1 << 2, + MLX5_ATOMIC_OPS_EXTENDED_FETCH_ADD = 1 << 3, }; enum mlx5_page_fault_resume_flags { -- cgit v1.2.3 From 977196b8c5b20b901acb0042579e30d7fa55790a Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Thu, 4 Oct 2018 15:27:37 -0600 Subject: PCI/P2PDMA: Add PCI p2pmem DMA mappings to adjust the bus offset The DMA address used when mapping PCI P2P memory must be the PCI bus address. Thus, introduce pci_p2pmem_map_sg() to map the correct addresses when using P2P memory. Memory mapped in this way does not need to be unmapped and thus if we provided pci_p2pmem_unmap_sg() it would be empty. This breaks the expected balance between map/unmap but was left out as an empty function doesn't really provide any benefit. In the future, if this call becomes necessary it can be added without much difficulty. For this, we assume that an SGL passed to these functions contain all P2P memory or no P2P memory. Signed-off-by: Logan Gunthorpe Signed-off-by: Bjorn Helgaas Reviewed-by: Christoph Hellwig --- drivers/pci/p2pdma.c | 43 +++++++++++++++++++++++++++++++++++++++++++ include/linux/memremap.h | 1 + include/linux/pci-p2pdma.h | 7 +++++++ 3 files changed, 51 insertions(+) (limited to 'include/linux') diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c index a8d484ddc5ad..09b3146c145c 100644 --- a/drivers/pci/p2pdma.c +++ b/drivers/pci/p2pdma.c @@ -194,6 +194,8 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size, pgmap->res.flags = pci_resource_flags(pdev, bar); pgmap->ref = &pdev->p2pdma->devmap_ref; pgmap->type = MEMORY_DEVICE_PCI_P2PDMA; + pgmap->pci_p2pdma_bus_offset = pci_bus_address(pdev, bar) - + pci_resource_start(pdev, bar); addr = devm_memremap_pages(&pdev->dev, pgmap); if (IS_ERR(addr)) { @@ -678,3 +680,44 @@ void pci_p2pmem_publish(struct pci_dev *pdev, bool publish) pdev->p2pdma->p2pmem_published = publish; } EXPORT_SYMBOL_GPL(pci_p2pmem_publish); + +/** + * pci_p2pdma_map_sg - map a PCI peer-to-peer scatterlist for DMA + * @dev: device doing the DMA request + * @sg: scatter list to map + * @nents: elements in the scatterlist + * @dir: DMA direction + * + * Scatterlists mapped with this function should not be unmapped in any way. + * + * Returns the number of SG entries mapped or 0 on error. + */ +int pci_p2pdma_map_sg(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction dir) +{ + struct dev_pagemap *pgmap; + struct scatterlist *s; + phys_addr_t paddr; + int i; + + /* + * p2pdma mappings are not compatible with devices that use + * dma_virt_ops. If the upper layers do the right thing + * this should never happen because it will be prevented + * by the check in pci_p2pdma_add_client() + */ + if (WARN_ON_ONCE(IS_ENABLED(CONFIG_DMA_VIRT_OPS) && + dev->dma_ops == &dma_virt_ops)) + return 0; + + for_each_sg(sg, s, nents, i) { + pgmap = sg_page(s)->pgmap; + paddr = sg_phys(s); + + s->dma_address = paddr - pgmap->pci_p2pdma_bus_offset; + sg_dma_len(s) = s->length; + } + + return nents; +} +EXPORT_SYMBOL_GPL(pci_p2pdma_map_sg); diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 9553370ebdad..0ac69ddf5fc4 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -125,6 +125,7 @@ struct dev_pagemap { struct device *dev; void *data; enum memory_type type; + u64 pci_p2pdma_bus_offset; }; #ifdef CONFIG_ZONE_DEVICE diff --git a/include/linux/pci-p2pdma.h b/include/linux/pci-p2pdma.h index 7bdaacfd5892..b6dfb6dc2e53 100644 --- a/include/linux/pci-p2pdma.h +++ b/include/linux/pci-p2pdma.h @@ -30,6 +30,8 @@ struct scatterlist *pci_p2pmem_alloc_sgl(struct pci_dev *pdev, unsigned int *nents, u32 length); void pci_p2pmem_free_sgl(struct pci_dev *pdev, struct scatterlist *sgl); void pci_p2pmem_publish(struct pci_dev *pdev, bool publish); +int pci_p2pdma_map_sg(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction dir); #else /* CONFIG_PCI_P2PDMA */ static inline int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size, u64 offset) @@ -75,6 +77,11 @@ static inline void pci_p2pmem_free_sgl(struct pci_dev *pdev, static inline void pci_p2pmem_publish(struct pci_dev *pdev, bool publish) { } +static inline int pci_p2pdma_map_sg(struct device *dev, + struct scatterlist *sg, int nents, enum dma_data_direction dir) +{ + return 0; +} #endif /* CONFIG_PCI_P2PDMA */ -- cgit v1.2.3 From 2d7bc010f450d803db9fed1a25da6144ff6140d3 Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Thu, 4 Oct 2018 15:27:38 -0600 Subject: PCI/P2PDMA: Introduce configfs/sysfs enable attribute helpers Users of the P2PDMA infrastructure will typically need a way for the user to tell the kernel to use P2P resources. Typically this will be a simple on/off boolean operation but sometimes it may be desirable for the user to specify the exact device to use for the P2P operation. Add new helpers for attributes which take a boolean or a PCI device. Any boolean as accepted by strtobool() turn P2P on or off (such as 'y', 'n', '1', '0', etc). Specifying a full PCI device name/BDF will select the specific device. Signed-off-by: Logan Gunthorpe Signed-off-by: Bjorn Helgaas Reviewed-by: Christoph Hellwig --- drivers/pci/p2pdma.c | 82 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/pci-p2pdma.h | 15 +++++++++ 2 files changed, 97 insertions(+) (limited to 'include/linux') diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c index 09b3146c145c..ae3c5b25dcc7 100644 --- a/drivers/pci/p2pdma.c +++ b/drivers/pci/p2pdma.c @@ -8,6 +8,8 @@ * Copyright (c) 2018, Eideticom Inc. */ +#define pr_fmt(fmt) "pci-p2pdma: " fmt +#include #include #include #include @@ -721,3 +723,83 @@ int pci_p2pdma_map_sg(struct device *dev, struct scatterlist *sg, int nents, return nents; } EXPORT_SYMBOL_GPL(pci_p2pdma_map_sg); + +/** + * pci_p2pdma_enable_store - parse a configfs/sysfs attribute store + * to enable p2pdma + * @page: contents of the value to be stored + * @p2p_dev: returns the PCI device that was selected to be used + * (if one was specified in the stored value) + * @use_p2pdma: returns whether to enable p2pdma or not + * + * Parses an attribute value to decide whether to enable p2pdma. + * The value can select a PCI device (using it's full BDF device + * name) or a boolean (in any format strtobool() accepts). A false + * value disables p2pdma, a true value expects the caller + * to automatically find a compatible device and specifying a PCI device + * expects the caller to use the specific provider. + * + * pci_p2pdma_enable_show() should be used as the show operation for + * the attribute. + * + * Returns 0 on success + */ +int pci_p2pdma_enable_store(const char *page, struct pci_dev **p2p_dev, + bool *use_p2pdma) +{ + struct device *dev; + + dev = bus_find_device_by_name(&pci_bus_type, NULL, page); + if (dev) { + *use_p2pdma = true; + *p2p_dev = to_pci_dev(dev); + + if (!pci_has_p2pmem(*p2p_dev)) { + pci_err(*p2p_dev, + "PCI device has no peer-to-peer memory: %s\n", + page); + pci_dev_put(*p2p_dev); + return -ENODEV; + } + + return 0; + } else if ((page[0] == '0' || page[0] == '1') && !iscntrl(page[1])) { + /* + * If the user enters a PCI device that doesn't exist + * like "0000:01:00.1", we don't want strtobool to think + * it's a '0' when it's clearly not what the user wanted. + * So we require 0's and 1's to be exactly one character. + */ + } else if (!strtobool(page, use_p2pdma)) { + return 0; + } + + pr_err("No such PCI device: %.*s\n", (int)strcspn(page, "\n"), page); + return -ENODEV; +} +EXPORT_SYMBOL_GPL(pci_p2pdma_enable_store); + +/** + * pci_p2pdma_enable_show - show a configfs/sysfs attribute indicating + * whether p2pdma is enabled + * @page: contents of the stored value + * @p2p_dev: the selected p2p device (NULL if no device is selected) + * @use_p2pdma: whether p2pdme has been enabled + * + * Attributes that use pci_p2pdma_enable_store() should use this function + * to show the value of the attribute. + * + * Returns 0 on success + */ +ssize_t pci_p2pdma_enable_show(char *page, struct pci_dev *p2p_dev, + bool use_p2pdma) +{ + if (!use_p2pdma) + return sprintf(page, "0\n"); + + if (!p2p_dev) + return sprintf(page, "1\n"); + + return sprintf(page, "%s\n", pci_name(p2p_dev)); +} +EXPORT_SYMBOL_GPL(pci_p2pdma_enable_show); diff --git a/include/linux/pci-p2pdma.h b/include/linux/pci-p2pdma.h index b6dfb6dc2e53..bca9bc3e5be7 100644 --- a/include/linux/pci-p2pdma.h +++ b/include/linux/pci-p2pdma.h @@ -32,6 +32,10 @@ void pci_p2pmem_free_sgl(struct pci_dev *pdev, struct scatterlist *sgl); void pci_p2pmem_publish(struct pci_dev *pdev, bool publish); int pci_p2pdma_map_sg(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir); +int pci_p2pdma_enable_store(const char *page, struct pci_dev **p2p_dev, + bool *use_p2pdma); +ssize_t pci_p2pdma_enable_show(char *page, struct pci_dev *p2p_dev, + bool use_p2pdma); #else /* CONFIG_PCI_P2PDMA */ static inline int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size, u64 offset) @@ -82,6 +86,17 @@ static inline int pci_p2pdma_map_sg(struct device *dev, { return 0; } +static inline int pci_p2pdma_enable_store(const char *page, + struct pci_dev **p2p_dev, bool *use_p2pdma) +{ + *use_p2pdma = false; + return 0; +} +static inline ssize_t pci_p2pdma_enable_show(char *page, + struct pci_dev *p2p_dev, bool use_p2pdma) +{ + return sprintf(page, "none\n"); +} #endif /* CONFIG_PCI_P2PDMA */ -- cgit v1.2.3 From 49d92c0dd64ae769c2d67fe27ac260ae31259ba6 Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Thu, 4 Oct 2018 15:27:41 -0600 Subject: block: Add PCI P2P flag for request queue Add QUEUE_FLAG_PCI_P2P, meaning a driver's request queue supports targeting P2P memory. This will be used by P2P providers and orchestrators (in subsequent patches) to ensure block devices can support P2P memory before submitting P2P-backed pages to submit_bio(). Signed-off-by: Logan Gunthorpe Signed-off-by: Bjorn Helgaas Reviewed-by: Christoph Hellwig Acked-by: Jens Axboe --- include/linux/blkdev.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6980014357d4..c32f7171899b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -699,6 +699,7 @@ struct request_queue { #define QUEUE_FLAG_SCSI_PASSTHROUGH 27 /* queue supports SCSI commands */ #define QUEUE_FLAG_QUIESCED 28 /* queue has been quiesced */ #define QUEUE_FLAG_PREEMPT_ONLY 29 /* only process REQ_PREEMPT requests */ +#define QUEUE_FLAG_PCI_P2PDMA 30 /* device supports PCI p2p requests */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_SAME_COMP) | \ @@ -731,6 +732,8 @@ bool blk_queue_flag_test_and_clear(unsigned int flag, struct request_queue *q); #define blk_queue_dax(q) test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags) #define blk_queue_scsi_passthrough(q) \ test_bit(QUEUE_FLAG_SCSI_PASSTHROUGH, &(q)->queue_flags) +#define blk_queue_pci_p2pdma(q) \ + test_bit(QUEUE_FLAG_PCI_P2PDMA, &(q)->queue_flags) #define blk_noretry_request(rq) \ ((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \ -- cgit v1.2.3 From f366d322aea782cf786aa821d5accdc1609f9e10 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 6 Sep 2018 10:19:30 +0100 Subject: UAPI: ndctl: Remove use of PAGE_SIZE The macro PAGE_SIZE isn't valid outside of the kernel, so it should not appear in UAPI headers. Furthermore, the actual machine page size could theoretically change from an application's point of view if it's running in a container that gets migrated to another machine (say 4K/ppc64 to 64K/ppc64). Fixes: f2ba5a5baecf ("libnvdimm, namespace: make min namespace size 4K") Signed-off-by: David Howells Signed-off-by: Dan Williams --- include/linux/ndctl.h | 22 ++++++++++++++++++++++ include/uapi/linux/ndctl.h | 4 ---- 2 files changed, 22 insertions(+), 4 deletions(-) create mode 100644 include/linux/ndctl.h (limited to 'include/linux') diff --git a/include/linux/ndctl.h b/include/linux/ndctl.h new file mode 100644 index 000000000000..cd5a293ce3ae --- /dev/null +++ b/include/linux/ndctl.h @@ -0,0 +1,22 @@ +/* + * Copyright (c) 2014-2016, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU Lesser General Public License, + * version 2.1, 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 Lesser General Public License for + * more details. + */ +#ifndef _LINUX_NDCTL_H +#define _LINUX_NDCTL_H + +#include + +enum { + ND_MIN_NAMESPACE_SIZE = PAGE_SIZE, +}; + +#endif /* _LINUX_NDCTL_H */ diff --git a/include/uapi/linux/ndctl.h b/include/uapi/linux/ndctl.h index 2f2c43d633c5..f57c9e434d2d 100644 --- a/include/uapi/linux/ndctl.h +++ b/include/uapi/linux/ndctl.h @@ -202,10 +202,6 @@ enum nd_driver_flags { ND_DRIVER_DAX_PMEM = 1 << ND_DEVICE_DAX_PMEM, }; -enum { - ND_MIN_NAMESPACE_SIZE = PAGE_SIZE, -}; - enum ars_masks { ARS_STATUS_MASK = 0x0000FFFF, ARS_EXT_STATUS_SHIFT = 16, -- cgit v1.2.3 From b8aee82250b7d90a32b11ba208656f52dbaca342 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 2 Oct 2018 22:57:24 +0000 Subject: net/mlx5: E-Switch, Get counters for offloaded flows from callers There's no real reason for the e-switch logic to manage the creation of counters for offloaded flows. The API already has the directive for the caller to denote they want to attach a counter to the created flow. As such, we go and move the management of flow counters to the mlx5e tc offload logic. This also lets us remove an inelegant interface where the FS layer had to provide a way to retrieve a counter from a flow rule. Signed-off-by: Mark Bloch Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 32 ++++++++++++++++++++-- drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 1 + .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 20 ++------------ drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 15 ---------- include/linux/mlx5/fs.h | 1 - 5 files changed, 33 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index acf7a847f561..8a27c0813a18 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -61,6 +61,7 @@ struct mlx5_nic_flow_attr { u32 hairpin_tirn; u8 match_level; struct mlx5_flow_table *hairpin_ft; + struct mlx5_fc *counter; }; #define MLX5E_TC_FLOW_BASE (MLX5E_TC_LAST_EXPORTED_BIT + 1) @@ -721,6 +722,7 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, dest[dest_ix].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; dest[dest_ix].counter = counter; dest_ix++; + attr->counter = counter; } if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { @@ -797,7 +799,7 @@ static void mlx5e_tc_del_nic_flow(struct mlx5e_priv *priv, struct mlx5_nic_flow_attr *attr = flow->nic_attr; struct mlx5_fc *counter = NULL; - counter = mlx5_flow_rule_counter(flow->rule[0]); + counter = attr->counter; mlx5_del_flow_rules(flow->rule[0]); mlx5_fc_destroy(priv->mdev, counter); @@ -833,6 +835,7 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, struct mlx5_esw_flow_attr *attr = flow->esw_attr; struct net_device *out_dev, *encap_dev = NULL; struct mlx5_flow_handle *rule = NULL; + struct mlx5_fc *counter = NULL; struct mlx5e_rep_priv *rpriv; struct mlx5e_priv *out_priv; int err; @@ -868,6 +871,16 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, } } + if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) { + counter = mlx5_fc_create(esw->dev, true); + if (IS_ERR(counter)) { + rule = ERR_CAST(counter); + goto err_create_counter; + } + + attr->counter = counter; + } + /* we get here if (1) there's no error (rule being null) or when * (2) there's an encap action and we're on -EAGAIN (no valid neigh) */ @@ -888,6 +901,8 @@ err_fwd_rule: mlx5_eswitch_del_offloaded_rule(esw, rule, attr); rule = flow->rule[1]; err_add_rule: + mlx5_fc_destroy(esw->dev, counter); +err_create_counter: if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) mlx5e_detach_mod_hdr(priv, flow); err_mod_hdr: @@ -921,6 +936,9 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) mlx5e_detach_mod_hdr(priv, flow); + + if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) + mlx5_fc_destroy(esw->dev, attr->counter); } void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv, @@ -992,6 +1010,14 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv, } } +static struct mlx5_fc *mlx5e_tc_get_counter(struct mlx5e_tc_flow *flow) +{ + if (flow->flags & MLX5E_TC_FLOW_ESWITCH) + return flow->esw_attr->counter; + else + return flow->nic_attr->counter; +} + void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe) { struct mlx5e_neigh *m_neigh = &nhe->m_neigh; @@ -1017,7 +1043,7 @@ void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe) continue; list_for_each_entry(flow, &e->flows, encap) { if (flow->flags & MLX5E_TC_FLOW_OFFLOADED) { - counter = mlx5_flow_rule_counter(flow->rule[0]); + counter = mlx5e_tc_get_counter(flow); mlx5_fc_query_cached(counter, &bytes, &packets, &lastuse); if (time_after((unsigned long)lastuse, nhe->reported_lastuse)) { neigh_used = true; @@ -3019,7 +3045,7 @@ int mlx5e_stats_flower(struct mlx5e_priv *priv, if (!(flow->flags & MLX5E_TC_FLOW_OFFLOADED)) return 0; - counter = mlx5_flow_rule_counter(flow->rule[0]); + counter = mlx5e_tc_get_counter(flow); if (!counter) return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index dfc642de4e6d..c1b627577003 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -266,6 +266,7 @@ struct mlx5_esw_flow_attr { u32 encap_id; u32 mod_hdr_id; u8 match_level; + struct mlx5_fc *counter; struct mlx5e_tc_flow_parse_attr *parse_attr; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 0741683f7d70..a2f2d726c99b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -51,7 +51,6 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, struct mlx5_flow_destination dest[MLX5_MAX_FLOW_FWD_VPORTS + 1] = {}; struct mlx5_flow_act flow_act = {0}; struct mlx5_flow_table *ft = NULL; - struct mlx5_fc *counter = NULL; struct mlx5_flow_handle *rule; int j, i = 0; void *misc; @@ -91,13 +90,8 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, } } if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_COUNT) { - counter = mlx5_fc_create(esw->dev, true); - if (IS_ERR(counter)) { - rule = ERR_CAST(counter); - goto err_counter_alloc; - } dest[i].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; - dest[i].counter = counter; + dest[i].counter = attr->counter; i++; } @@ -132,15 +126,11 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, rule = mlx5_add_flow_rules(ft, spec, &flow_act, dest, i); if (IS_ERR(rule)) - goto err_add_rule; + goto out; else esw->offloads.num_flows++; - return rule; - -err_add_rule: - mlx5_fc_destroy(esw->dev, counter); -err_counter_alloc: +out: return rule; } @@ -200,11 +190,7 @@ mlx5_eswitch_del_offloaded_rule(struct mlx5_eswitch *esw, struct mlx5_flow_handle *rule, struct mlx5_esw_flow_attr *attr) { - struct mlx5_fc *counter = NULL; - - counter = mlx5_flow_rule_counter(rule); mlx5_del_flow_rules(rule); - mlx5_fc_destroy(esw->dev, counter); esw->offloads.num_flows--; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 8d340e5181f8..9e18e6c0a8b3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1474,21 +1474,6 @@ static struct mlx5_flow_handle *add_rule_fg(struct mlx5_flow_group *fg, return handle; } -struct mlx5_fc *mlx5_flow_rule_counter(struct mlx5_flow_handle *handle) -{ - struct mlx5_flow_rule *dst; - struct fs_fte *fte; - - fs_get_obj(fte, handle->rule[0]->node.parent); - - fs_for_each_dst(dst, fte) { - if (dst->dest_attr.type == MLX5_FLOW_DESTINATION_TYPE_COUNTER) - return dst->dest_attr.counter; - } - - return NULL; -} - static bool counter_is_valid(struct mlx5_fc *counter, u32 action) { if (!(action & MLX5_FLOW_CONTEXT_ACTION_COUNT)) diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index b1c026f1c8ba..74d0ea146c9a 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -186,7 +186,6 @@ int mlx5_modify_rule_destination(struct mlx5_flow_handle *handler, struct mlx5_flow_destination *new_dest, struct mlx5_flow_destination *old_dest); -struct mlx5_fc *mlx5_flow_rule_counter(struct mlx5_flow_handle *handler); struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging); void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter); void mlx5_fc_query_cached(struct mlx5_fc *counter, -- cgit v1.2.3 From 171c7625bef999848ee6032c6dde96e7330c4d15 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Wed, 3 Oct 2018 00:03:35 +0000 Subject: net/mlx5: Use flow counter IDs and not the wrapping cache object Currently, when a flow rule is created using the FS core layer, the caller has to pass the entire flow counter object and not just the counter HW handle (ID). This requires both the FS core and the caller to have knowledge about the inner implementation of the FS layer flow counters cache and limits the possible users. Move to use the counter ID across the place when dealing with flows. Doing this decoupling, now can we privatize the inner implementation of the flow counters. Signed-off-by: Mark Bloch Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- drivers/infiniband/hw/mlx5/main.c | 7 +++++-- drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h | 6 +++--- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 10 ++-------- drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c | 6 ++++++ include/linux/mlx5/fs.h | 3 ++- 9 files changed, 23 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 5d9b7f62a0ba..5ced0cc46ba1 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -3320,15 +3320,18 @@ static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev, } if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_COUNT) { + struct mlx5_ib_mcounters *mcounters; + err = flow_counters_set_data(flow_act.counters, ucmd); if (err) goto free; + mcounters = to_mcounters(flow_act.counters); handler->ibcounters = flow_act.counters; dest_arr[dest_num].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; - dest_arr[dest_num].counter = - to_mcounters(flow_act.counters)->hw_cntrs_hndl; + dest_arr[dest_num].counter_id = + mlx5_fc_id(mcounters->hw_cntrs_hndl); dest_num++; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h index e83dda441a81..d027ce00c8ce 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h @@ -252,10 +252,10 @@ TRACE_EVENT(mlx5_fs_add_rule, memcpy(__entry->destination, &rule->dest_attr, sizeof(__entry->destination)); - if (rule->dest_attr.type & MLX5_FLOW_DESTINATION_TYPE_COUNTER && - rule->dest_attr.counter) + if (rule->dest_attr.type & + MLX5_FLOW_DESTINATION_TYPE_COUNTER) __entry->counter_id = - rule->dest_attr.counter->id; + rule->dest_attr.counter_id; ), TP_printk("rule=%p fte=%p index=%u sw_action=<%s> [dst] %s\n", __entry->rule, __entry->fte, __entry->index, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 8a27c0813a18..5ce87f54852d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -720,7 +720,7 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, goto err_fc_create; } dest[dest_ix].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; - dest[dest_ix].counter = counter; + dest[dest_ix].counter_id = mlx5_fc_id(counter); dest_ix++; attr->counter = counter; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index e1d47fa5ab83..9c893d7d273e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1198,7 +1198,7 @@ static int esw_vport_ingress_config(struct mlx5_eswitch *esw, if (counter) { flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_COUNT; drop_ctr_dst.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; - drop_ctr_dst.counter = counter; + drop_ctr_dst.counter_id = mlx5_fc_id(counter); dst = &drop_ctr_dst; dest_num++; } @@ -1285,7 +1285,7 @@ static int esw_vport_egress_config(struct mlx5_eswitch *esw, if (counter) { flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_COUNT; drop_ctr_dst.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; - drop_ctr_dst.counter = counter; + drop_ctr_dst.counter_id = mlx5_fc_id(counter); dst = &drop_ctr_dst; dest_num++; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index a2f2d726c99b..39932dce15cb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -91,7 +91,7 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, } if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_COUNT) { dest[i].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; - dest[i].counter = attr->counter; + dest[i].counter_id = mlx5_fc_id(attr->counter); i++; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index dc8d7f6b52c2..08a891f9aade 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -419,7 +419,7 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, continue; MLX5_SET(flow_counter_list, in_dests, flow_counter_id, - dst->dest_attr.counter->id); + dst->dest_attr.counter_id); in_dests += MLX5_ST_SZ_BYTES(dest_format_struct); list_size++; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 9e18e6c0a8b3..cdcbf9d0ae6c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1474,14 +1474,8 @@ static struct mlx5_flow_handle *add_rule_fg(struct mlx5_flow_group *fg, return handle; } -static bool counter_is_valid(struct mlx5_fc *counter, u32 action) +static bool counter_is_valid(u32 action) { - if (!(action & MLX5_FLOW_CONTEXT_ACTION_COUNT)) - return !counter; - - if (!counter) - return false; - return (action & (MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_FWD_DEST)); } @@ -1491,7 +1485,7 @@ static bool dest_is_valid(struct mlx5_flow_destination *dest, struct mlx5_flow_table *ft) { if (dest && (dest->type == MLX5_FLOW_DESTINATION_TYPE_COUNTER)) - return counter_is_valid(dest->counter, action); + return counter_is_valid(action); if (!(action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST)) return true; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c index 09206c4acd9a..1329bc5b7969 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c @@ -258,6 +258,12 @@ err_out: } EXPORT_SYMBOL(mlx5_fc_create); +u32 mlx5_fc_id(struct mlx5_fc *counter) +{ + return counter->id; +} +EXPORT_SYMBOL(mlx5_fc_id); + void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter) { struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 74d0ea146c9a..a5fc62184195 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -92,7 +92,7 @@ struct mlx5_flow_destination { u32 tir_num; u32 ft_num; struct mlx5_flow_table *ft; - struct mlx5_fc *counter; + u32 counter_id; struct { u16 num; u16 vhca_id; @@ -192,6 +192,7 @@ void mlx5_fc_query_cached(struct mlx5_fc *counter, u64 *bytes, u64 *packets, u64 *lastuse); int mlx5_fc_query(struct mlx5_core_dev *dev, struct mlx5_fc *counter, u64 *packets, u64 *bytes); +u32 mlx5_fc_id(struct mlx5_fc *counter); int mlx5_fs_add_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn); int mlx5_fs_remove_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn); -- cgit v1.2.3 From b9aa0ba17af5afa13605eb6ea91f1974da97a2e2 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Thu, 31 May 2018 11:50:23 +0300 Subject: net/mlx5: Add cap bits for multi fdb encap If set, the firmware supports creating of flow tables with encap enabled while VFs are configured, if we already created one (restriction still applies on the first creation). Signed-off-by: Paul Blakey Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 15e36198f85f..963611820006 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -584,7 +584,9 @@ struct mlx5_ifc_flow_table_nic_cap_bits { struct mlx5_ifc_flow_table_eswitch_cap_bits { u8 reserved_at_0[0x1c]; u8 fdb_multi_path_to_table[0x1]; - u8 reserved_at_1d[0x1e3]; + u8 reserved_at_1d[0x1]; + u8 multi_fdb_encap[0x1]; + u8 reserved_at_1e[0x1e1]; struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_esw_fdb; -- cgit v1.2.3 From 328edb499f99126946845ece477c9c1afe8631af Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Tue, 3 Jul 2018 11:13:00 +0300 Subject: net/mlx5: Split FDB fast path prio to multiple namespaces Towards supporting multi-chains and priorities, split the FDB fast path to multiple namespaces (sub namespaces), each with multiple priorities. This patch adds a new flow steering type, FS_TYPE_PRIO_CHAINS, which is like current FS_TYPE_PRIO, but may contain only namespaces, and those will be in parallel to one another in terms of managing of the flow tables connections inside them. Meaning, while searching for the next or previous flow table to connect for a new table inside such namespace we skip the parallel namespaces in the same level under the FS_TYPE_PRIO_CHAINS prio we originated from. We use this new type for splitting the fast path prio into multiple parallel namespaces, each containing normal prios. The prios inside them (and their tables) will be connected to one another, but not from one parallel namespace to another, instead the last prio in each namespace will be connected to the next prio in the containing FDB namespace, which is the slow path prio. Signed-off-by: Paul Blakey Acked-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 7 ++ drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 88 ++++++++++++++++++++--- drivers/net/ethernet/mellanox/mlx5/core/fs_core.h | 13 ++++ include/linux/mlx5/fs.h | 2 + 5 files changed, 101 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 9c893d7d273e..d004957328f9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -263,7 +263,7 @@ static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw) esw_debug(dev, "Create FDB log_max_size(%d)\n", MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size)); - root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB); + root_ns = mlx5_get_fdb_sub_ns(dev, 0); if (!root_ns) { esw_warn(dev, "Failed to get FDB flow namespace\n"); return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index c1b627577003..1698a322a7c4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -59,6 +59,9 @@ #define mlx5_esw_has_fwd_fdb(dev) \ MLX5_CAP_ESW_FLOWTABLE(dev, fdb_multi_path_to_table) +#define FDB_MAX_CHAIN 3 +#define FDB_MAX_PRIO 16 + struct vport_ingress { struct mlx5_flow_table *acl; struct mlx5_flow_group *allow_untagged_spoofchk_grp; @@ -319,6 +322,10 @@ static inline void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) {} static inline void mlx5_eswitch_vport_event(struct mlx5_eswitch *esw, struct mlx5_eqe *eqe) {} static inline int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) { return 0; } static inline void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw) {} + +#define FDB_MAX_CHAIN 1 +#define FDB_MAX_PRIO 1 + #endif /* CONFIG_MLX5_ESWITCH */ #endif /* __MLX5_ESWITCH_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index cdcbf9d0ae6c..7eb6d58733ac 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -40,6 +40,7 @@ #include "diag/fs_tracepoint.h" #include "accel/ipsec.h" #include "fpga/ipsec.h" +#include "eswitch.h" #define INIT_TREE_NODE_ARRAY_SIZE(...) (sizeof((struct init_tree_node[]){__VA_ARGS__}) /\ sizeof(struct init_tree_node)) @@ -713,7 +714,7 @@ static struct mlx5_flow_table *find_closest_ft_recursive(struct fs_node *root, struct fs_node *iter = list_entry(start, struct fs_node, list); struct mlx5_flow_table *ft = NULL; - if (!root) + if (!root || root->type == FS_TYPE_PRIO_CHAINS) return NULL; list_for_each_advance_continue(iter, &root->children, reverse) { @@ -1973,6 +1974,18 @@ void mlx5_destroy_flow_group(struct mlx5_flow_group *fg) fg->id); } +struct mlx5_flow_namespace *mlx5_get_fdb_sub_ns(struct mlx5_core_dev *dev, + int n) +{ + struct mlx5_flow_steering *steering = dev->priv.steering; + + if (!steering || !steering->fdb_sub_ns) + return NULL; + + return steering->fdb_sub_ns[n]; +} +EXPORT_SYMBOL(mlx5_get_fdb_sub_ns); + struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type type) { @@ -2051,8 +2064,10 @@ struct mlx5_flow_namespace *mlx5_get_flow_vport_acl_namespace(struct mlx5_core_d } } -static struct fs_prio *fs_create_prio(struct mlx5_flow_namespace *ns, - unsigned int prio, int num_levels) +static struct fs_prio *_fs_create_prio(struct mlx5_flow_namespace *ns, + unsigned int prio, + int num_levels, + enum fs_node_type type) { struct fs_prio *fs_prio; @@ -2060,7 +2075,7 @@ static struct fs_prio *fs_create_prio(struct mlx5_flow_namespace *ns, if (!fs_prio) return ERR_PTR(-ENOMEM); - fs_prio->node.type = FS_TYPE_PRIO; + fs_prio->node.type = type; tree_init_node(&fs_prio->node, NULL, del_sw_prio); tree_add_node(&fs_prio->node, &ns->node); fs_prio->num_levels = num_levels; @@ -2070,6 +2085,19 @@ static struct fs_prio *fs_create_prio(struct mlx5_flow_namespace *ns, return fs_prio; } +static struct fs_prio *fs_create_prio_chained(struct mlx5_flow_namespace *ns, + unsigned int prio, + int num_levels) +{ + return _fs_create_prio(ns, prio, num_levels, FS_TYPE_PRIO_CHAINS); +} + +static struct fs_prio *fs_create_prio(struct mlx5_flow_namespace *ns, + unsigned int prio, int num_levels) +{ + return _fs_create_prio(ns, prio, num_levels, FS_TYPE_PRIO); +} + static struct mlx5_flow_namespace *fs_init_namespace(struct mlx5_flow_namespace *ns) { @@ -2374,6 +2402,9 @@ void mlx5_cleanup_fs(struct mlx5_core_dev *dev) cleanup_egress_acls_root_ns(dev); cleanup_ingress_acls_root_ns(dev); cleanup_root_ns(steering->fdb_root_ns); + steering->fdb_root_ns = NULL; + kfree(steering->fdb_sub_ns); + steering->fdb_sub_ns = NULL; cleanup_root_ns(steering->sniffer_rx_root_ns); cleanup_root_ns(steering->sniffer_tx_root_ns); cleanup_root_ns(steering->egress_root_ns); @@ -2419,27 +2450,64 @@ static int init_sniffer_rx_root_ns(struct mlx5_flow_steering *steering) static int init_fdb_root_ns(struct mlx5_flow_steering *steering) { - struct fs_prio *prio; + struct mlx5_flow_namespace *ns; + struct fs_prio *maj_prio; + struct fs_prio *min_prio; + int levels; + int chain; + int prio; + int err; steering->fdb_root_ns = create_root_ns(steering, FS_FT_FDB); if (!steering->fdb_root_ns) return -ENOMEM; - prio = fs_create_prio(&steering->fdb_root_ns->ns, 0, 2); - if (IS_ERR(prio)) + steering->fdb_sub_ns = kzalloc(sizeof(steering->fdb_sub_ns) * + FDB_MAX_CHAIN + 1, GFP_KERNEL); + if (!steering->fdb_sub_ns) + return -ENOMEM; + + levels = 2 * FDB_MAX_PRIO * (FDB_MAX_CHAIN + 1); + maj_prio = fs_create_prio_chained(&steering->fdb_root_ns->ns, 0, + levels); + if (IS_ERR(maj_prio)) { + err = PTR_ERR(maj_prio); goto out_err; + } - prio = fs_create_prio(&steering->fdb_root_ns->ns, 1, 1); - if (IS_ERR(prio)) + for (chain = 0; chain <= FDB_MAX_CHAIN; chain++) { + ns = fs_create_namespace(maj_prio); + if (IS_ERR(ns)) { + err = PTR_ERR(ns); + goto out_err; + } + + for (prio = 0; prio < FDB_MAX_PRIO * (chain + 1); prio++) { + min_prio = fs_create_prio(ns, prio, 2); + if (IS_ERR(min_prio)) { + err = PTR_ERR(min_prio); + goto out_err; + } + } + + steering->fdb_sub_ns[chain] = ns; + } + + maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, 1, 1); + if (IS_ERR(maj_prio)) { + err = PTR_ERR(maj_prio); goto out_err; + } set_prio_attrs(steering->fdb_root_ns); return 0; out_err: cleanup_root_ns(steering->fdb_root_ns); + kfree(steering->fdb_sub_ns); + steering->fdb_sub_ns = NULL; steering->fdb_root_ns = NULL; - return PTR_ERR(prio); + return err; } static int init_egress_acl_root_ns(struct mlx5_flow_steering *steering, int vport) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index a06f83c0c2b6..b51ad217da32 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -38,9 +38,21 @@ #include #include +/* FS_TYPE_PRIO_CHAINS is a PRIO that will have namespaces only, + * and those are in parallel to one another when going over them to connect + * a new flow table. Meaning the last flow table in a TYPE_PRIO prio in one + * parallel namespace will not automatically connect to the first flow table + * found in any prio in any next namespace, but skip the entire containing + * TYPE_PRIO_CHAINS prio. + * + * This is used to implement tc chains, each chain of prios is a different + * namespace inside a containing TYPE_PRIO_CHAINS prio. + */ + enum fs_node_type { FS_TYPE_NAMESPACE, FS_TYPE_PRIO, + FS_TYPE_PRIO_CHAINS, FS_TYPE_FLOW_TABLE, FS_TYPE_FLOW_GROUP, FS_TYPE_FLOW_ENTRY, @@ -73,6 +85,7 @@ struct mlx5_flow_steering { struct kmem_cache *ftes_cache; struct mlx5_flow_root_namespace *root_ns; struct mlx5_flow_root_namespace *fdb_root_ns; + struct mlx5_flow_namespace **fdb_sub_ns; struct mlx5_flow_root_namespace **esw_egress_root_ns; struct mlx5_flow_root_namespace **esw_ingress_root_ns; struct mlx5_flow_root_namespace *sniffer_tx_root_ns; diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index a5fc62184195..f8d00872c7d3 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -101,6 +101,8 @@ struct mlx5_flow_destination { }; }; +struct mlx5_flow_namespace * +mlx5_get_fdb_sub_ns(struct mlx5_core_dev *dev, int n); struct mlx5_flow_namespace * mlx5_get_flow_namespace(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type type); -- cgit v1.2.3 From d5634fee245f9e92787e3a34ef621fc12b2cbf16 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Thu, 20 Sep 2018 12:17:48 +0200 Subject: net/mlx5: Add a no-append flow insertion mode If no-append flag is set, we will add a new FTE, instead of appending the actions of the inserted rule when the same match already exists. While here, move the has_flow_tag boolean indicator to be a flag too. This patch doesn't change any functionality. Signed-off-by: Paul Blakey Reviewed-by: Or Gerlitz Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- drivers/infiniband/hw/mlx5/main.c | 6 +++--- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 9 ++++++++- include/linux/mlx5/fs.h | 14 +++++++++++--- 5 files changed, 24 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 5ced0cc46ba1..af32899bb72a 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -2793,7 +2793,7 @@ static int parse_flow_attr(struct mlx5_core_dev *mdev, u32 *match_c, return -EINVAL; action->flow_tag = ib_spec->flow_tag.tag_id; - action->has_flow_tag = true; + action->flags |= FLOW_ACT_HAS_TAG; break; case IB_FLOW_SPEC_ACTION_DROP: if (FIELDS_NOT_SUPPORTED(ib_spec->drop, @@ -2886,7 +2886,7 @@ is_valid_esp_aes_gcm(struct mlx5_core_dev *mdev, return egress ? VALID_SPEC_INVALID : VALID_SPEC_NA; return is_crypto && is_ipsec && - (!egress || (!is_drop && !flow_act->has_flow_tag)) ? + (!egress || (!is_drop && !(flow_act->flags & FLOW_ACT_HAS_TAG))) ? VALID_SPEC_VALID : VALID_SPEC_INVALID; } @@ -3349,7 +3349,7 @@ static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev, MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO; } - if (flow_act.has_flow_tag && + if ((flow_act.flags & FLOW_ACT_HAS_TAG) && (flow_attr->type == IB_FLOW_ATTR_ALL_DEFAULT || flow_attr->type == IB_FLOW_ATTR_MC_DEFAULT)) { mlx5_ib_warn(dev, "Flow tag %u and attribute type %x isn't allowed in leftovers\n", diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 6c04e11f9a05..a9c68b7859b4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -684,9 +684,9 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, struct mlx5_flow_destination dest[2] = {}; struct mlx5_flow_act flow_act = { .action = attr->action, - .has_flow_tag = true, .flow_tag = attr->flow_tag, .reformat_id = 0, + .flags = FLOW_ACT_HAS_TAG, }; struct mlx5_fc *counter = NULL; bool table_created = false; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c index 5645a4facad2..28aa8c968a80 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c @@ -650,7 +650,7 @@ static bool mlx5_is_fpga_egress_ipsec_rule(struct mlx5_core_dev *dev, (match_criteria_enable & ~(MLX5_MATCH_OUTER_HEADERS | MLX5_MATCH_MISC_PARAMETERS)) || (flow_act->action & ~(MLX5_FLOW_CONTEXT_ACTION_ENCRYPT | MLX5_FLOW_CONTEXT_ACTION_ALLOW)) || - flow_act->has_flow_tag) + (flow_act->flags & FLOW_ACT_HAS_TAG)) return false; return true; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 7eb6d58733ac..67ba4c975d81 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1428,7 +1428,7 @@ static int check_conflicting_ftes(struct fs_fte *fte, const struct mlx5_flow_act return -EEXIST; } - if (flow_act->has_flow_tag && + if ((flow_act->flags & FLOW_ACT_HAS_TAG) && fte->action.flow_tag != flow_act->flow_tag) { mlx5_core_warn(get_dev(&fte->node), "FTE flow tag %u already exists with different flow tag %u\n", @@ -1628,6 +1628,8 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft, search_again_locked: version = matched_fgs_get_version(match_head); + if (flow_act->flags & FLOW_ACT_NO_APPEND) + goto skip_search; /* Try to find a fg that already contains a matching fte */ list_for_each_entry(iter, match_head, list) { struct fs_fte *fte_tmp; @@ -1644,6 +1646,11 @@ search_again_locked: return rule; } +skip_search: + /* No group with matching fte found, or we skipped the search. + * Try to add a new fte to any matching fg. + */ + /* Check the ft version, for case that new flow group * was added while the fgs weren't locked */ diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index f8d00872c7d3..5660f07d3be0 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -158,20 +158,28 @@ struct mlx5_fs_vlan { #define MLX5_FS_VLAN_DEPTH 2 +enum { + FLOW_ACT_HAS_TAG = BIT(0), + FLOW_ACT_NO_APPEND = BIT(1), +}; + struct mlx5_flow_act { u32 action; - bool has_flow_tag; u32 flow_tag; u32 reformat_id; u32 modify_id; uintptr_t esp_id; + u32 flags; struct mlx5_fs_vlan vlan[MLX5_FS_VLAN_DEPTH]; struct ib_counters *counters; }; #define MLX5_DECLARE_FLOW_ACT(name) \ - struct mlx5_flow_act name = {MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,\ - MLX5_FS_DEFAULT_FLOW_TAG, 0, 0} + struct mlx5_flow_act name = { .action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,\ + .flow_tag = MLX5_FS_DEFAULT_FLOW_TAG, \ + .reformat_id = 0, \ + .modify_id = 0, \ + .flags = 0, } /* Single destination per rule. * Group ID is implied by the match criteria. -- cgit v1.2.3 From 82385b0d2d2504aee51aa3fb40ebfb03603f64c3 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Wed, 17 Oct 2018 15:01:37 +0200 Subject: net: skbuff.h: Mark expected switch fall-throughs In preparation to enabling -Wimplicit-fallthrough, mark switch cases where we are expecting to fall through. Acked-by: Kees Cook Signed-off-by: Gustavo A. R. Silva Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 119d092c6b13..0ba687454267 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3505,13 +3505,19 @@ static inline bool __skb_metadata_differs(const struct sk_buff *skb_a, #define __it(x, op) (x -= sizeof(u##op)) #define __it_diff(a, b, op) (*(u##op *)__it(a, op)) ^ (*(u##op *)__it(b, op)) case 32: diffs |= __it_diff(a, b, 64); + /* fall through */ case 24: diffs |= __it_diff(a, b, 64); + /* fall through */ case 16: diffs |= __it_diff(a, b, 64); + /* fall through */ case 8: diffs |= __it_diff(a, b, 64); break; case 28: diffs |= __it_diff(a, b, 64); + /* fall through */ case 20: diffs |= __it_diff(a, b, 64); + /* fall through */ case 12: diffs |= __it_diff(a, b, 64); + /* fall through */ case 4: diffs |= __it_diff(a, b, 32); break; } -- cgit v1.2.3 From f349b0a3e1f0d184374936f1b2a49352f8a4b1c8 Mon Sep 17 00:00:00 2001 From: MichaÅ‚ MirosÅ‚aw Date: Tue, 9 Oct 2018 22:13:42 +0200 Subject: dm: add dm_table_device_name() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a shortcut for dm_device_name(dm_table_get_md(t)). Signed-off-by: MichaÅ‚ MirosÅ‚aw Signed-off-by: Mike Snitzer --- drivers/md/dm-table.c | 6 ++++++ include/linux/device-mapper.h | 1 + 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 618edfc3846f..49ab0cbef739 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -2059,6 +2059,12 @@ struct mapped_device *dm_table_get_md(struct dm_table *t) } EXPORT_SYMBOL(dm_table_get_md); +const char *dm_table_device_name(struct dm_table *t) +{ + return dm_device_name(t->md); +} +EXPORT_SYMBOL_GPL(dm_table_device_name); + void dm_table_run_md_queue_async(struct dm_table *t) { struct mapped_device *md; diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 8d937754aa0c..d7bee8669f10 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -489,6 +489,7 @@ sector_t dm_table_get_size(struct dm_table *t); unsigned int dm_table_get_num_targets(struct dm_table *t); fmode_t dm_table_get_mode(struct dm_table *t); struct mapped_device *dm_table_get_md(struct dm_table *t); +const char *dm_table_device_name(struct dm_table *t); /* * Trigger an event. -- cgit v1.2.3 From 4972e6fa3a04032830bc3d6bb343d08ab3546773 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Wed, 12 Sep 2018 15:36:41 +0300 Subject: net/mlx5: Refactor fragmented buffer struct fields and init flow Take struct mlx5_frag_buf out of mlx5_frag_buf_ctrl, as it is not needed to manage and control the datapath of the fragmented buffers API. struct mlx5_frag_buf contains control info to manage the allocation and de-allocation of the fragmented buffer. Its fields are not relevant for datapath, so here I take them out of the struct mlx5_frag_buf_ctrl, except for the fragments array itself. In addition, modified mlx5_fill_fbc to initialise the frags pointers as well. This implies that the buffer must be allocated before the function is called. A set of type-specific *_get_byte_size() functions are replaced by a generic one. Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/infiniband/hw/mlx5/cq.c | 31 +++---- drivers/infiniband/hw/mlx5/mlx5_ib.h | 1 + drivers/net/ethernet/mellanox/mlx5/core/wq.c | 120 +++++++++++---------------- include/linux/mlx5/driver.h | 22 ++--- 4 files changed, 69 insertions(+), 105 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c index 088205d7f1a1..cca1820802b8 100644 --- a/drivers/infiniband/hw/mlx5/cq.c +++ b/drivers/infiniband/hw/mlx5/cq.c @@ -393,7 +393,7 @@ static void handle_atomics(struct mlx5_ib_qp *qp, struct mlx5_cqe64 *cqe64, static void free_cq_buf(struct mlx5_ib_dev *dev, struct mlx5_ib_cq_buf *buf) { - mlx5_frag_buf_free(dev->mdev, &buf->fbc.frag_buf); + mlx5_frag_buf_free(dev->mdev, &buf->frag_buf); } static void get_sig_err_item(struct mlx5_sig_err_cqe *cqe, @@ -728,16 +728,11 @@ static int alloc_cq_frag_buf(struct mlx5_ib_dev *dev, int nent, int cqe_size) { - struct mlx5_frag_buf_ctrl *c = &buf->fbc; - struct mlx5_frag_buf *frag_buf = &c->frag_buf; - u32 cqc_buff[MLX5_ST_SZ_DW(cqc)] = {0}; + struct mlx5_frag_buf *frag_buf = &buf->frag_buf; + u8 log_wq_stride = 6 + (cqe_size == 128 ? 1 : 0); + u8 log_wq_sz = ilog2(cqe_size); int err; - MLX5_SET(cqc, cqc_buff, log_cq_size, ilog2(cqe_size)); - MLX5_SET(cqc, cqc_buff, cqe_sz, (cqe_size == 128) ? 1 : 0); - - mlx5_core_init_cq_frag_buf(&buf->fbc, cqc_buff); - err = mlx5_frag_buf_alloc_node(dev->mdev, nent * cqe_size, frag_buf, @@ -745,6 +740,8 @@ static int alloc_cq_frag_buf(struct mlx5_ib_dev *dev, if (err) return err; + mlx5_init_fbc(frag_buf->frags, log_wq_stride, log_wq_sz, &buf->fbc); + buf->cqe_size = cqe_size; buf->nent = nent; @@ -934,7 +931,7 @@ static int create_cq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq, *inlen = MLX5_ST_SZ_BYTES(create_cq_in) + MLX5_FLD_SZ_BYTES(create_cq_in, pas[0]) * - cq->buf.fbc.frag_buf.npages; + cq->buf.frag_buf.npages; *cqb = kvzalloc(*inlen, GFP_KERNEL); if (!*cqb) { err = -ENOMEM; @@ -942,11 +939,11 @@ static int create_cq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq, } pas = (__be64 *)MLX5_ADDR_OF(create_cq_in, *cqb, pas); - mlx5_fill_page_frag_array(&cq->buf.fbc.frag_buf, pas); + mlx5_fill_page_frag_array(&cq->buf.frag_buf, pas); cqc = MLX5_ADDR_OF(create_cq_in, *cqb, cq_context); MLX5_SET(cqc, cqc, log_page_size, - cq->buf.fbc.frag_buf.page_shift - + cq->buf.frag_buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT); *index = dev->mdev->priv.uar->index; @@ -1365,11 +1362,10 @@ int mlx5_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata) cqe_size = 64; err = resize_kernel(dev, cq, entries, cqe_size); if (!err) { - struct mlx5_frag_buf_ctrl *c; + struct mlx5_frag_buf *frag_buf = &cq->resize_buf->frag_buf; - c = &cq->resize_buf->fbc; - npas = c->frag_buf.npages; - page_shift = c->frag_buf.page_shift; + npas = frag_buf->npages; + page_shift = frag_buf->page_shift; } } @@ -1390,8 +1386,7 @@ int mlx5_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata) mlx5_ib_populate_pas(dev, cq->resize_umem, page_shift, pas, 0); else - mlx5_fill_page_frag_array(&cq->resize_buf->fbc.frag_buf, - pas); + mlx5_fill_page_frag_array(&cq->resize_buf->frag_buf, pas); MLX5_SET(modify_cq_in, in, modify_field_select_resize_field_select.resize_field_select.resize_field_select, diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index 320d4dfe8c2f..289c18db2611 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -435,6 +435,7 @@ struct mlx5_ib_qp { struct mlx5_ib_cq_buf { struct mlx5_frag_buf_ctrl fbc; + struct mlx5_frag_buf frag_buf; struct ib_umem *umem; int cqe_size; int nent; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c index 68e7f8df2a6d..9007e91ad53f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c @@ -54,54 +54,37 @@ u32 mlx5_wq_ll_get_size(struct mlx5_wq_ll *wq) return (u32)wq->fbc.sz_m1 + 1; } -static u32 mlx5_wq_cyc_get_byte_size(struct mlx5_wq_cyc *wq) +static u32 wq_get_byte_sz(u8 log_sz, u8 log_stride) { - return mlx5_wq_cyc_get_size(wq) << wq->fbc.log_stride; -} - -static u32 mlx5_wq_qp_get_byte_size(struct mlx5_wq_qp *wq) -{ - return mlx5_wq_cyc_get_byte_size(&wq->rq) + - mlx5_wq_cyc_get_byte_size(&wq->sq); -} - -static u32 mlx5_cqwq_get_byte_size(struct mlx5_cqwq *wq) -{ - return mlx5_cqwq_get_size(wq) << wq->fbc.log_stride; -} - -static u32 mlx5_wq_ll_get_byte_size(struct mlx5_wq_ll *wq) -{ - return mlx5_wq_ll_get_size(wq) << wq->fbc.log_stride; + return ((u32)1 << log_sz) << log_stride; } int mlx5_wq_cyc_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *wqc, struct mlx5_wq_cyc *wq, struct mlx5_wq_ctrl *wq_ctrl) { + u8 log_wq_stride = MLX5_GET(wq, wqc, log_wq_stride); + u8 log_wq_sz = MLX5_GET(wq, wqc, log_wq_sz); struct mlx5_frag_buf_ctrl *fbc = &wq->fbc; int err; - mlx5_fill_fbc(MLX5_GET(wq, wqc, log_wq_stride), - MLX5_GET(wq, wqc, log_wq_sz), - fbc); - wq->sz = wq->fbc.sz_m1 + 1; - err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node); if (err) { mlx5_core_warn(mdev, "mlx5_db_alloc_node() failed, %d\n", err); return err; } - err = mlx5_frag_buf_alloc_node(mdev, mlx5_wq_cyc_get_byte_size(wq), + wq->db = wq_ctrl->db.db; + + err = mlx5_frag_buf_alloc_node(mdev, wq_get_byte_sz(log_wq_sz, log_wq_stride), &wq_ctrl->buf, param->buf_numa_node); if (err) { mlx5_core_warn(mdev, "mlx5_frag_buf_alloc_node() failed, %d\n", err); goto err_db_free; } - fbc->frag_buf = wq_ctrl->buf; - wq->db = wq_ctrl->db.db; + mlx5_init_fbc(wq_ctrl->buf.frags, log_wq_stride, log_wq_sz, fbc); + wq->sz = mlx5_wq_cyc_get_size(wq); wq_ctrl->mdev = mdev; @@ -113,46 +96,19 @@ err_db_free: return err; } -static void mlx5_qp_set_frag_buf(struct mlx5_frag_buf *buf, - struct mlx5_wq_qp *qp) -{ - struct mlx5_frag_buf_ctrl *sq_fbc; - struct mlx5_frag_buf *rqb, *sqb; - - rqb = &qp->rq.fbc.frag_buf; - *rqb = *buf; - rqb->size = mlx5_wq_cyc_get_byte_size(&qp->rq); - rqb->npages = DIV_ROUND_UP(rqb->size, PAGE_SIZE); - - sq_fbc = &qp->sq.fbc; - sqb = &sq_fbc->frag_buf; - *sqb = *buf; - sqb->size = mlx5_wq_cyc_get_byte_size(&qp->sq); - sqb->npages = DIV_ROUND_UP(sqb->size, PAGE_SIZE); - sqb->frags += rqb->npages; /* first part is for the rq */ - if (sq_fbc->strides_offset) - sqb->frags--; -} - int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *qpc, struct mlx5_wq_qp *wq, struct mlx5_wq_ctrl *wq_ctrl) { - u16 sq_strides_offset; - u32 rq_pg_remainder; - int err; + u8 log_rq_stride = MLX5_GET(qpc, qpc, log_rq_stride) + 4; + u8 log_rq_sz = MLX5_GET(qpc, qpc, log_rq_size); + u8 log_sq_stride = ilog2(MLX5_SEND_WQE_BB); + u8 log_sq_sz = MLX5_GET(qpc, qpc, log_sq_size); - mlx5_fill_fbc(MLX5_GET(qpc, qpc, log_rq_stride) + 4, - MLX5_GET(qpc, qpc, log_rq_size), - &wq->rq.fbc); + u32 rq_byte_size; + int err; - rq_pg_remainder = mlx5_wq_cyc_get_byte_size(&wq->rq) % PAGE_SIZE; - sq_strides_offset = rq_pg_remainder / MLX5_SEND_WQE_BB; - mlx5_fill_fbc_offset(ilog2(MLX5_SEND_WQE_BB), - MLX5_GET(qpc, qpc, log_sq_size), - sq_strides_offset, - &wq->sq.fbc); err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node); if (err) { @@ -160,14 +116,32 @@ int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, return err; } - err = mlx5_frag_buf_alloc_node(mdev, mlx5_wq_qp_get_byte_size(wq), + err = mlx5_frag_buf_alloc_node(mdev, + wq_get_byte_sz(log_rq_sz, log_rq_stride) + + wq_get_byte_sz(log_sq_sz, log_sq_stride), &wq_ctrl->buf, param->buf_numa_node); if (err) { mlx5_core_warn(mdev, "mlx5_frag_buf_alloc_node() failed, %d\n", err); goto err_db_free; } - mlx5_qp_set_frag_buf(&wq_ctrl->buf, wq); + mlx5_init_fbc(wq_ctrl->buf.frags, log_rq_stride, log_rq_sz, &wq->rq.fbc); + + rq_byte_size = wq_get_byte_sz(log_rq_sz, log_rq_stride); + + if (rq_byte_size < PAGE_SIZE) { + /* SQ starts within the same page of the RQ */ + u16 sq_strides_offset = rq_byte_size / MLX5_SEND_WQE_BB; + + mlx5_init_fbc_offset(wq_ctrl->buf.frags, + log_sq_stride, log_sq_sz, sq_strides_offset, + &wq->sq.fbc); + } else { + u16 rq_npages = rq_byte_size >> PAGE_SHIFT; + + mlx5_init_fbc(wq_ctrl->buf.frags + rq_npages, + log_sq_stride, log_sq_sz, &wq->sq.fbc); + } wq->rq.db = &wq_ctrl->db.db[MLX5_RCV_DBR]; wq->sq.db = &wq_ctrl->db.db[MLX5_SND_DBR]; @@ -186,17 +160,19 @@ int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *cqc, struct mlx5_cqwq *wq, struct mlx5_wq_ctrl *wq_ctrl) { + u8 log_wq_stride = MLX5_GET(cqc, cqc, cqe_sz) + 6; + u8 log_wq_sz = MLX5_GET(cqc, cqc, log_cq_size); int err; - mlx5_core_init_cq_frag_buf(&wq->fbc, cqc); - err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node); if (err) { mlx5_core_warn(mdev, "mlx5_db_alloc_node() failed, %d\n", err); return err; } - err = mlx5_frag_buf_alloc_node(mdev, mlx5_cqwq_get_byte_size(wq), + wq->db = wq_ctrl->db.db; + + err = mlx5_frag_buf_alloc_node(mdev, wq_get_byte_sz(log_wq_sz, log_wq_stride), &wq_ctrl->buf, param->buf_numa_node); if (err) { @@ -205,8 +181,7 @@ int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, goto err_db_free; } - wq->fbc.frag_buf = wq_ctrl->buf; - wq->db = wq_ctrl->db.db; + mlx5_init_fbc(wq_ctrl->buf.frags, log_wq_stride, log_wq_sz, &wq->fbc); wq_ctrl->mdev = mdev; @@ -222,30 +197,29 @@ int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *wqc, struct mlx5_wq_ll *wq, struct mlx5_wq_ctrl *wq_ctrl) { + u8 log_wq_stride = MLX5_GET(wq, wqc, log_wq_stride); + u8 log_wq_sz = MLX5_GET(wq, wqc, log_wq_sz); struct mlx5_frag_buf_ctrl *fbc = &wq->fbc; struct mlx5_wqe_srq_next_seg *next_seg; int err; int i; - mlx5_fill_fbc(MLX5_GET(wq, wqc, log_wq_stride), - MLX5_GET(wq, wqc, log_wq_sz), - fbc); - err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node); if (err) { mlx5_core_warn(mdev, "mlx5_db_alloc_node() failed, %d\n", err); return err; } - err = mlx5_frag_buf_alloc_node(mdev, mlx5_wq_ll_get_byte_size(wq), + wq->db = wq_ctrl->db.db; + + err = mlx5_frag_buf_alloc_node(mdev, wq_get_byte_sz(log_wq_sz, log_wq_stride), &wq_ctrl->buf, param->buf_numa_node); if (err) { mlx5_core_warn(mdev, "mlx5_frag_buf_alloc_node() failed, %d\n", err); goto err_db_free; } - wq->fbc.frag_buf = wq_ctrl->buf; - wq->db = wq_ctrl->db.db; + mlx5_init_fbc(wq_ctrl->buf.frags, log_wq_stride, log_wq_sz, fbc); for (i = 0; i < fbc->sz_m1; i++) { next_seg = mlx5_wq_ll_get_wqe(wq, i); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 94ffd02af7cd..e10f61a1f77d 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -357,7 +357,7 @@ struct mlx5_frag_buf { }; struct mlx5_frag_buf_ctrl { - struct mlx5_frag_buf frag_buf; + struct mlx5_buf_list *frags; u32 sz_m1; u16 frag_sz_m1; u16 strides_offset; @@ -994,10 +994,12 @@ static inline u32 mlx5_base_mkey(const u32 key) return key & 0xffffff00u; } -static inline void mlx5_fill_fbc_offset(u8 log_stride, u8 log_sz, +static inline void mlx5_init_fbc_offset(struct mlx5_buf_list *frags, + u8 log_stride, u8 log_sz, u16 strides_offset, struct mlx5_frag_buf_ctrl *fbc) { + fbc->frags = frags; fbc->log_stride = log_stride; fbc->log_sz = log_sz; fbc->sz_m1 = (1 << fbc->log_sz) - 1; @@ -1006,18 +1008,11 @@ static inline void mlx5_fill_fbc_offset(u8 log_stride, u8 log_sz, fbc->strides_offset = strides_offset; } -static inline void mlx5_fill_fbc(u8 log_stride, u8 log_sz, +static inline void mlx5_init_fbc(struct mlx5_buf_list *frags, + u8 log_stride, u8 log_sz, struct mlx5_frag_buf_ctrl *fbc) { - mlx5_fill_fbc_offset(log_stride, log_sz, 0, fbc); -} - -static inline void mlx5_core_init_cq_frag_buf(struct mlx5_frag_buf_ctrl *fbc, - void *cqc) -{ - mlx5_fill_fbc(6 + MLX5_GET(cqc, cqc, cqe_sz), - MLX5_GET(cqc, cqc, log_cq_size), - fbc); + mlx5_init_fbc_offset(frags, log_stride, log_sz, 0, fbc); } static inline void *mlx5_frag_buf_get_wqe(struct mlx5_frag_buf_ctrl *fbc, @@ -1028,8 +1023,7 @@ static inline void *mlx5_frag_buf_get_wqe(struct mlx5_frag_buf_ctrl *fbc, ix += fbc->strides_offset; frag = ix >> fbc->log_frag_strides; - return fbc->frag_buf.frags[frag].buf + - ((fbc->frag_sz_m1 & ix) << fbc->log_stride); + return fbc->frags[frag].buf + ((fbc->frag_sz_m1 & ix) << fbc->log_stride); } int mlx5_cmd_init(struct mlx5_core_dev *dev); -- cgit v1.2.3 From 4b5b9c7d972e8a7b1e7691c7c921ec0d6dec33b9 Mon Sep 17 00:00:00 2001 From: Shay Agroskin Date: Tue, 9 Oct 2018 14:16:43 +0300 Subject: net/mlx5: Add FEC fields to Port Phy Link Mode (PPLM) reg Added FEC related fields to PPLM layout. These fields are needed to set and query FEC policy for different link speeds. Signed-off-by: Shay Agroskin Reviewed-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 + include/linux/mlx5/mlx5_ifc.h | 39 ++++++++++++++++++++++++++++----------- 2 files changed, 29 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index e10f61a1f77d..696ed3f7f894 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -133,6 +133,7 @@ enum { MLX5_REG_PVLC = 0x500f, MLX5_REG_PCMR = 0x5041, MLX5_REG_PMLP = 0x5002, + MLX5_REG_PPLM = 0x5023, MLX5_REG_PCAM = 0x507f, MLX5_REG_NODE_DESC = 0x6001, MLX5_REG_HOST_ENDIANNESS = 0x7004, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 963611820006..47b09a742ae5 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -7828,20 +7828,34 @@ struct mlx5_ifc_pplr_reg_bits { struct mlx5_ifc_pplm_reg_bits { u8 reserved_at_0[0x8]; - u8 local_port[0x8]; - u8 reserved_at_10[0x10]; + u8 local_port[0x8]; + u8 reserved_at_10[0x10]; - u8 reserved_at_20[0x20]; + u8 reserved_at_20[0x20]; - u8 port_profile_mode[0x8]; - u8 static_port_profile[0x8]; - u8 active_port_profile[0x8]; - u8 reserved_at_58[0x8]; + u8 port_profile_mode[0x8]; + u8 static_port_profile[0x8]; + u8 active_port_profile[0x8]; + u8 reserved_at_58[0x8]; - u8 retransmission_active[0x8]; - u8 fec_mode_active[0x18]; + u8 retransmission_active[0x8]; + u8 fec_mode_active[0x18]; - u8 reserved_at_80[0x20]; + u8 rs_fec_correction_bypass_cap[0x4]; + u8 reserved_at_84[0x8]; + u8 fec_override_cap_56g[0x4]; + u8 fec_override_cap_100g[0x4]; + u8 fec_override_cap_50g[0x4]; + u8 fec_override_cap_25g[0x4]; + u8 fec_override_cap_10g_40g[0x4]; + + u8 rs_fec_correction_bypass_admin[0x4]; + u8 reserved_at_a4[0x8]; + u8 fec_override_admin_56g[0x4]; + u8 fec_override_admin_100g[0x4]; + u8 fec_override_admin_50g[0x4]; + u8 fec_override_admin_25g[0x4]; + u8 fec_override_admin_10g_40g[0x4]; }; struct mlx5_ifc_ppcnt_reg_bits { @@ -8137,7 +8151,10 @@ struct mlx5_ifc_pcam_enhanced_features_bits { struct mlx5_ifc_pcam_regs_5000_to_507f_bits { u8 port_access_reg_cap_mask_127_to_96[0x20]; u8 port_access_reg_cap_mask_95_to_64[0x20]; - u8 port_access_reg_cap_mask_63_to_32[0x20]; + + u8 port_access_reg_cap_mask_63_to_36[0x1c]; + u8 pplm[0x1]; + u8 port_access_reg_cap_mask_34_to_32[0x3]; u8 port_access_reg_cap_mask_31_to_13[0x13]; u8 pbmc[0x1]; -- cgit v1.2.3 From 67daf1186086ad4b2ec09b8078b835936977d06a Mon Sep 17 00:00:00 2001 From: Shay Agroskin Date: Sun, 30 Sep 2018 09:58:08 +0300 Subject: net/mlx5: Added "per_lane_error_counters" cap bit to PCAM Added "Per lane raw errors" capability bit in Ports Capabilities Mask (PCAM) enhanced features layout. This bit determines if the fields "phy_raw_errors_laneX" in "Physical Layer statistical" counters group are supported. Signed-off-by: Shay Agroskin Reviewed-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 47b09a742ae5..dbff9ff28f2c 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -8140,7 +8140,8 @@ struct mlx5_ifc_pcam_enhanced_features_bits { u8 rx_icrc_encapsulated_counter[0x1]; u8 reserved_at_6e[0x8]; u8 pfcc_mask[0x1]; - u8 reserved_at_77[0x4]; + u8 reserved_at_77[0x3]; + u8 per_lane_error_counters[0x1]; u8 rx_buffer_fullness_counters[0x1]; u8 ptys_connector_type[0x1]; u8 reserved_at_7d[0x1]; -- cgit v1.2.3 From b65125c6acf38388d3342b37c18c3b6cc97eeb75 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 12 Apr 2018 14:49:23 +0200 Subject: swiotlb: mark is_swiotlb_buffer static Signed-off-by: Christoph Hellwig Reviewed-by: Robin Murphy Reviewed-by: Konrad Rzeszutek Wilk --- include/linux/swiotlb.h | 1 - kernel/dma/swiotlb.c | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 965be92c33b5..7ef541ce8f34 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -121,7 +121,6 @@ static inline unsigned int swiotlb_max_segment(void) { return 0; } #endif extern void swiotlb_print_info(void); -extern int is_swiotlb_buffer(phys_addr_t paddr); extern void swiotlb_set_max_segment(unsigned int); extern const struct dma_map_ops swiotlb_dma_ops; diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 9062b14bc7f4..26d3af52956f 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -429,7 +429,7 @@ void __init swiotlb_exit(void) max_segment = 0; } -int is_swiotlb_buffer(phys_addr_t paddr) +static int is_swiotlb_buffer(phys_addr_t paddr) { return paddr >= io_tlb_start && paddr < io_tlb_end; } -- cgit v1.2.3 From dff8d6c1ed584de65aac40494d3e7468c50980c3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 16 Aug 2018 15:30:39 +0300 Subject: swiotlb: remove the overflow buffer Like all other dma mapping drivers just return an error code instead of an actual memory buffer. The reason for the overflow buffer was that at the time swiotlb was invented there was no way to check for dma mapping errors, but this has long been fixed. Signed-off-by: Christoph Hellwig Acked-by: Catalin Marinas Reviewed-by: Robin Murphy Reviewed-by: Konrad Rzeszutek Wilk --- arch/arm64/mm/dma-mapping.c | 2 +- arch/powerpc/kernel/dma-swiotlb.c | 4 +-- include/linux/dma-direct.h | 2 ++ include/linux/swiotlb.h | 3 -- kernel/dma/direct.c | 2 -- kernel/dma/swiotlb.c | 59 ++------------------------------------- 6 files changed, 8 insertions(+), 64 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 072c51fb07d7..8d91b927e09e 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -324,7 +324,7 @@ static int __swiotlb_dma_supported(struct device *hwdev, u64 mask) static int __swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t addr) { if (swiotlb) - return swiotlb_dma_mapping_error(hwdev, addr); + return dma_direct_mapping_error(hwdev, addr); return 0; } diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c index 88f3963ca30f..5fc335f4d9cd 100644 --- a/arch/powerpc/kernel/dma-swiotlb.c +++ b/arch/powerpc/kernel/dma-swiotlb.c @@ -11,7 +11,7 @@ * */ -#include +#include #include #include #include @@ -59,7 +59,7 @@ const struct dma_map_ops powerpc_swiotlb_dma_ops = { .sync_single_for_device = swiotlb_sync_single_for_device, .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu, .sync_sg_for_device = swiotlb_sync_sg_for_device, - .mapping_error = swiotlb_dma_mapping_error, + .mapping_error = dma_direct_mapping_error, .get_required_mask = swiotlb_powerpc_get_required, }; diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index fbca184ff5a0..bd73e7a91410 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -5,6 +5,8 @@ #include #include +#define DIRECT_MAPPING_ERROR 0 + #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA #include #else diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 7ef541ce8f34..f847c1b265c4 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -106,9 +106,6 @@ extern void swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg, int nelems, enum dma_data_direction dir); -extern int -swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr); - extern int swiotlb_dma_supported(struct device *hwdev, u64 mask); diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 87a6bc2a96c0..f14c376937e5 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -14,8 +14,6 @@ #include #include -#define DIRECT_MAPPING_ERROR 0 - /* * Most architectures use ZONE_DMA for the first 16 Megabytes, but * some use it for entirely different regions: diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 69bf305ee5f8..11dbcd80b4a6 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -72,13 +72,6 @@ static phys_addr_t io_tlb_start, io_tlb_end; */ static unsigned long io_tlb_nslabs; -/* - * When the IOMMU overflows we return a fallback buffer. This sets the size. - */ -static unsigned long io_tlb_overflow = 32*1024; - -static phys_addr_t io_tlb_overflow_buffer; - /* * This is a free list describing the number of free entries available from * each index @@ -126,7 +119,6 @@ setup_io_tlb_npages(char *str) return 0; } early_param("swiotlb", setup_io_tlb_npages); -/* make io_tlb_overflow tunable too? */ unsigned long swiotlb_nr_tbl(void) { @@ -194,16 +186,10 @@ void __init swiotlb_update_mem_attributes(void) bytes = PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT); set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT); memset(vaddr, 0, bytes); - - vaddr = phys_to_virt(io_tlb_overflow_buffer); - bytes = PAGE_ALIGN(io_tlb_overflow); - set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT); - memset(vaddr, 0, bytes); } int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) { - void *v_overflow_buffer; unsigned long i, bytes; bytes = nslabs << IO_TLB_SHIFT; @@ -212,17 +198,6 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) io_tlb_start = __pa(tlb); io_tlb_end = io_tlb_start + bytes; - /* - * Get the overflow emergency buffer - */ - v_overflow_buffer = memblock_virt_alloc_low_nopanic( - PAGE_ALIGN(io_tlb_overflow), - PAGE_SIZE); - if (!v_overflow_buffer) - return -ENOMEM; - - io_tlb_overflow_buffer = __pa(v_overflow_buffer); - /* * Allocate and initialize the free list array. This array is used * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE @@ -330,7 +305,6 @@ int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) { unsigned long i, bytes; - unsigned char *v_overflow_buffer; bytes = nslabs << IO_TLB_SHIFT; @@ -341,19 +315,6 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) set_memory_decrypted((unsigned long)tlb, bytes >> PAGE_SHIFT); memset(tlb, 0, bytes); - /* - * Get the overflow emergency buffer - */ - v_overflow_buffer = (void *)__get_free_pages(GFP_DMA, - get_order(io_tlb_overflow)); - if (!v_overflow_buffer) - goto cleanup2; - - set_memory_decrypted((unsigned long)v_overflow_buffer, - io_tlb_overflow >> PAGE_SHIFT); - memset(v_overflow_buffer, 0, io_tlb_overflow); - io_tlb_overflow_buffer = virt_to_phys(v_overflow_buffer); - /* * Allocate and initialize the free list array. This array is used * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE @@ -390,10 +351,6 @@ cleanup4: sizeof(int))); io_tlb_list = NULL; cleanup3: - free_pages((unsigned long)v_overflow_buffer, - get_order(io_tlb_overflow)); - io_tlb_overflow_buffer = 0; -cleanup2: io_tlb_end = 0; io_tlb_start = 0; io_tlb_nslabs = 0; @@ -407,8 +364,6 @@ void __init swiotlb_exit(void) return; if (late_alloc) { - free_pages((unsigned long)phys_to_virt(io_tlb_overflow_buffer), - get_order(io_tlb_overflow)); free_pages((unsigned long)io_tlb_orig_addr, get_order(io_tlb_nslabs * sizeof(phys_addr_t))); free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs * @@ -416,8 +371,6 @@ void __init swiotlb_exit(void) free_pages((unsigned long)phys_to_virt(io_tlb_start), get_order(io_tlb_nslabs << IO_TLB_SHIFT)); } else { - memblock_free_late(io_tlb_overflow_buffer, - PAGE_ALIGN(io_tlb_overflow)); memblock_free_late(__pa(io_tlb_orig_addr), PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t))); memblock_free_late(__pa(io_tlb_list), @@ -790,7 +743,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, /* Oh well, have to allocate and map a bounce buffer. */ map = map_single(dev, phys, size, dir, attrs); if (map == SWIOTLB_MAP_ERROR) - return __phys_to_dma(dev, io_tlb_overflow_buffer); + return DIRECT_MAPPING_ERROR; dev_addr = __phys_to_dma(dev, map); @@ -801,7 +754,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, attrs |= DMA_ATTR_SKIP_CPU_SYNC; swiotlb_tbl_unmap_single(dev, map, size, dir, attrs); - return __phys_to_dma(dev, io_tlb_overflow_buffer); + return DIRECT_MAPPING_ERROR; } /* @@ -985,12 +938,6 @@ swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg, swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_DEVICE); } -int -swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr) -{ - return (dma_addr == __phys_to_dma(hwdev, io_tlb_overflow_buffer)); -} - /* * Return whether the given device DMA address mask can be supported * properly. For example, if your device can only drive the low 24-bits @@ -1033,7 +980,7 @@ void swiotlb_free(struct device *dev, size_t size, void *vaddr, } const struct dma_map_ops swiotlb_dma_ops = { - .mapping_error = swiotlb_dma_mapping_error, + .mapping_error = dma_direct_mapping_error, .alloc = swiotlb_alloc, .free = swiotlb_free, .sync_single_for_cpu = swiotlb_sync_single_for_cpu, -- cgit v1.2.3 From fafadcd16595c1df82df399f62421718ec9bf70a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 30 Sep 2018 16:13:33 -0700 Subject: swiotlb: don't dip into swiotlb pool for coherent allocations All architectures that support swiotlb also have a zone that backs up these less than full addressing allocations (usually ZONE_DMA32). Because of that it is rather pointless to fall back to the global swiotlb buffer if the normal dma direct allocation failed - the only thing this will do is to eat up bounce buffers that would be more useful to serve streaming mappings. Signed-off-by: Christoph Hellwig Acked-by: Catalin Marinas Acked-by: Konrad Rzeszutek Wilk --- arch/arm64/mm/dma-mapping.c | 6 +-- include/linux/swiotlb.h | 5 --- kernel/dma/swiotlb.c | 105 +------------------------------------------- 3 files changed, 5 insertions(+), 111 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 8d91b927e09e..eee6cfcfde9e 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -112,7 +112,7 @@ static void *__dma_alloc(struct device *dev, size_t size, return addr; } - ptr = swiotlb_alloc(dev, size, dma_handle, flags, attrs); + ptr = dma_direct_alloc_pages(dev, size, dma_handle, flags, attrs); if (!ptr) goto no_mem; @@ -133,7 +133,7 @@ static void *__dma_alloc(struct device *dev, size_t size, return coherent_ptr; no_map: - swiotlb_free(dev, size, ptr, *dma_handle, attrs); + dma_direct_free_pages(dev, size, ptr, *dma_handle, attrs); no_mem: return NULL; } @@ -151,7 +151,7 @@ static void __dma_free(struct device *dev, size_t size, return; vunmap(vaddr); } - swiotlb_free(dev, size, swiotlb_addr, dma_handle, attrs); + dma_direct_free_pages(dev, size, swiotlb_addr, dma_handle, attrs); } static dma_addr_t __swiotlb_map_page(struct device *dev, struct page *page, diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index f847c1b265c4..a387b59640a4 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -67,11 +67,6 @@ extern void swiotlb_tbl_sync_single(struct device *hwdev, /* Accessory functions. */ -void *swiotlb_alloc(struct device *hwdev, size_t size, dma_addr_t *dma_handle, - gfp_t flags, unsigned long attrs); -void swiotlb_free(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_addr, unsigned long attrs); - extern dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 57507b18caa4..1a01b0ac0a5e 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -622,78 +622,6 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr, } } -static inline bool dma_coherent_ok(struct device *dev, dma_addr_t addr, - size_t size) -{ - u64 mask = DMA_BIT_MASK(32); - - if (dev && dev->coherent_dma_mask) - mask = dev->coherent_dma_mask; - return addr + size - 1 <= mask; -} - -static void * -swiotlb_alloc_buffer(struct device *dev, size_t size, dma_addr_t *dma_handle, - unsigned long attrs) -{ - phys_addr_t phys_addr; - - if (swiotlb_force == SWIOTLB_NO_FORCE) - goto out_warn; - - phys_addr = swiotlb_tbl_map_single(dev, - __phys_to_dma(dev, io_tlb_start), - 0, size, DMA_FROM_DEVICE, attrs); - if (phys_addr == SWIOTLB_MAP_ERROR) - goto out_warn; - - *dma_handle = __phys_to_dma(dev, phys_addr); - if (!dma_coherent_ok(dev, *dma_handle, size)) - goto out_unmap; - - memset(phys_to_virt(phys_addr), 0, size); - return phys_to_virt(phys_addr); - -out_unmap: - dev_warn(dev, "hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016Lx\n", - (unsigned long long)dev->coherent_dma_mask, - (unsigned long long)*dma_handle); - - /* - * DMA_TO_DEVICE to avoid memcpy in unmap_single. - * DMA_ATTR_SKIP_CPU_SYNC is optional. - */ - swiotlb_tbl_unmap_single(dev, phys_addr, size, DMA_TO_DEVICE, - DMA_ATTR_SKIP_CPU_SYNC); -out_warn: - if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit()) { - dev_warn(dev, - "swiotlb: coherent allocation failed, size=%zu\n", - size); - dump_stack(); - } - return NULL; -} - -static bool swiotlb_free_buffer(struct device *dev, size_t size, - dma_addr_t dma_addr) -{ - phys_addr_t phys_addr = dma_to_phys(dev, dma_addr); - - WARN_ON_ONCE(irqs_disabled()); - - if (!is_swiotlb_buffer(phys_addr)) - return false; - - /* - * DMA_TO_DEVICE to avoid memcpy in swiotlb_tbl_unmap_single. - * DMA_ATTR_SKIP_CPU_SYNC is optional. - */ - swiotlb_tbl_unmap_single(dev, phys_addr, size, DMA_TO_DEVICE, - DMA_ATTR_SKIP_CPU_SYNC); - return true; -} - static dma_addr_t swiotlb_bounce_page(struct device *dev, phys_addr_t *phys, size_t size, enum dma_data_direction dir, unsigned long attrs) { @@ -926,39 +854,10 @@ swiotlb_dma_supported(struct device *hwdev, u64 mask) return __phys_to_dma(hwdev, io_tlb_end - 1) <= mask; } -void *swiotlb_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, - gfp_t gfp, unsigned long attrs) -{ - void *vaddr; - - /* temporary workaround: */ - if (gfp & __GFP_NOWARN) - attrs |= DMA_ATTR_NO_WARN; - - /* - * Don't print a warning when the first allocation attempt fails. - * swiotlb_alloc_coherent() will print a warning when the DMA memory - * allocation ultimately failed. - */ - gfp |= __GFP_NOWARN; - - vaddr = dma_direct_alloc(dev, size, dma_handle, gfp, attrs); - if (!vaddr) - vaddr = swiotlb_alloc_buffer(dev, size, dma_handle, attrs); - return vaddr; -} - -void swiotlb_free(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_addr, unsigned long attrs) -{ - if (!swiotlb_free_buffer(dev, size, dma_addr)) - dma_direct_free(dev, size, vaddr, dma_addr, attrs); -} - const struct dma_map_ops swiotlb_dma_ops = { .mapping_error = dma_direct_mapping_error, - .alloc = swiotlb_alloc, - .free = swiotlb_free, + .alloc = dma_direct_alloc, + .free = dma_direct_free, .sync_single_for_cpu = swiotlb_sync_single_for_cpu, .sync_single_for_device = swiotlb_sync_single_for_device, .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu, -- cgit v1.2.3 From 144991602e6a14d667b295f1b099e609ce857772 Mon Sep 17 00:00:00 2001 From: Mauricio Vasquez B Date: Thu, 18 Oct 2018 15:16:09 +0200 Subject: bpf: rename stack trace map operations In the following patches queue and stack maps (FIFO and LIFO datastructures) will be implemented. In order to avoid confusion and a possible name clash rename stack_map_ops to stack_trace_map_ops Signed-off-by: Mauricio Vasquez B Acked-by: Song Liu Signed-off-by: Alexei Starovoitov --- include/linux/bpf_types.h | 2 +- kernel/bpf/stackmap.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index fa48343a5ea1..7bad4e1947ed 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -51,7 +51,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_LRU_HASH, htab_lru_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_LRU_PERCPU_HASH, htab_lru_percpu_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_LPM_TRIE, trie_map_ops) #ifdef CONFIG_PERF_EVENTS -BPF_MAP_TYPE(BPF_MAP_TYPE_STACK_TRACE, stack_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_STACK_TRACE, stack_trace_map_ops) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops) diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index b2ade10f7ec3..90daf285de03 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -600,7 +600,7 @@ static void stack_map_free(struct bpf_map *map) put_callchain_buffers(); } -const struct bpf_map_ops stack_map_ops = { +const struct bpf_map_ops stack_trace_map_ops = { .map_alloc = stack_map_alloc, .map_free = stack_map_free, .map_get_next_key = stack_map_get_next_key, -- cgit v1.2.3 From 2ea864c58f19bf70a0e2415f9f1c53814e07f1b4 Mon Sep 17 00:00:00 2001 From: Mauricio Vasquez B Date: Thu, 18 Oct 2018 15:16:20 +0200 Subject: bpf/verifier: add ARG_PTR_TO_UNINIT_MAP_VALUE ARG_PTR_TO_UNINIT_MAP_VALUE argument is a pointer to a memory zone used to save the value of a map. Basically the same as ARG_PTR_TO_UNINIT_MEM, but the size has not be passed as an extra argument. This will be used in the following patch that implements some new helpers that receive a pointer to be filled with a map value. Signed-off-by: Mauricio Vasquez B Acked-by: Song Liu Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + kernel/bpf/verifier.c | 9 ++++++--- 2 files changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e60fff48288b..0f8b863e0229 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -138,6 +138,7 @@ enum bpf_arg_type { ARG_CONST_MAP_PTR, /* const argument used as pointer to bpf_map */ ARG_PTR_TO_MAP_KEY, /* pointer to stack used as map key */ ARG_PTR_TO_MAP_VALUE, /* pointer to stack used as map value */ + ARG_PTR_TO_UNINIT_MAP_VALUE, /* pointer to valid memory used to store a map value */ /* the following constraints used to prototype bpf_memcmp() and other * functions that access data on eBPF program stack diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 3f93a548a642..d84c91ac3b70 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2117,7 +2117,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, } if (arg_type == ARG_PTR_TO_MAP_KEY || - arg_type == ARG_PTR_TO_MAP_VALUE) { + arg_type == ARG_PTR_TO_MAP_VALUE || + arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE) { expected_type = PTR_TO_STACK; if (!type_is_pkt_pointer(type) && type != PTR_TO_MAP_VALUE && type != expected_type) @@ -2187,7 +2188,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, err = check_helper_mem_access(env, regno, meta->map_ptr->key_size, false, NULL); - } else if (arg_type == ARG_PTR_TO_MAP_VALUE) { + } else if (arg_type == ARG_PTR_TO_MAP_VALUE || + arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE) { /* bpf_map_xxx(..., map_ptr, ..., value) call: * check [value, value + map->value_size) validity */ @@ -2196,9 +2198,10 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, verbose(env, "invalid map_ptr to access map->value\n"); return -EACCES; } + meta->raw_mode = (arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE); err = check_helper_mem_access(env, regno, meta->map_ptr->value_size, false, - NULL); + meta); } else if (arg_type_is_mem_size(arg_type)) { bool zero_size_allowed = (arg_type == ARG_CONST_SIZE_OR_ZERO); -- cgit v1.2.3 From f1a2e44a3aeccb3ff18d3ccc0b0203e70b95bd92 Mon Sep 17 00:00:00 2001 From: Mauricio Vasquez B Date: Thu, 18 Oct 2018 15:16:25 +0200 Subject: bpf: add queue and stack maps Queue/stack maps implement a FIFO/LIFO data storage for ebpf programs. These maps support peek, pop and push operations that are exposed to eBPF programs through the new bpf_map[peek/pop/push] helpers. Those operations are exposed to userspace applications through the already existing syscalls in the following way: BPF_MAP_LOOKUP_ELEM -> peek BPF_MAP_LOOKUP_AND_DELETE_ELEM -> pop BPF_MAP_UPDATE_ELEM -> push Queue/stack maps are implemented using a buffer, tail and head indexes, hence BPF_F_NO_PREALLOC is not supported. As opposite to other maps, queue and stack do not use RCU for protecting maps values, the bpf_map[peek/pop] have a ARG_PTR_TO_UNINIT_MAP_VALUE argument that is a pointer to a memory zone where to save the value of a map. Basically the same as ARG_PTR_TO_UNINIT_MEM, but the size has not be passed as an extra argument. Our main motivation for implementing queue/stack maps was to keep track of a pool of elements, like network ports in a SNAT, however we forsee other use cases, like for exampling saving last N kernel events in a map and then analysing from userspace. Signed-off-by: Mauricio Vasquez B Acked-by: Song Liu Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 6 + include/linux/bpf_types.h | 2 + include/uapi/linux/bpf.h | 29 ++++- kernel/bpf/Makefile | 2 +- kernel/bpf/core.c | 3 + kernel/bpf/helpers.c | 43 +++++++ kernel/bpf/queue_stack_maps.c | 288 ++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 6 + kernel/bpf/verifier.c | 19 ++- net/core/filter.c | 6 + 10 files changed, 401 insertions(+), 3 deletions(-) create mode 100644 kernel/bpf/queue_stack_maps.c (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 0f8b863e0229..33014ae73103 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -39,6 +39,9 @@ struct bpf_map_ops { void *(*map_lookup_elem)(struct bpf_map *map, void *key); int (*map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags); int (*map_delete_elem)(struct bpf_map *map, void *key); + int (*map_push_elem)(struct bpf_map *map, void *value, u64 flags); + int (*map_pop_elem)(struct bpf_map *map, void *value); + int (*map_peek_elem)(struct bpf_map *map, void *value); /* funcs called by prog_array and perf_event_array map */ void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file, @@ -811,6 +814,9 @@ static inline int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, extern const struct bpf_func_proto bpf_map_lookup_elem_proto; extern const struct bpf_func_proto bpf_map_update_elem_proto; extern const struct bpf_func_proto bpf_map_delete_elem_proto; +extern const struct bpf_func_proto bpf_map_push_elem_proto; +extern const struct bpf_func_proto bpf_map_pop_elem_proto; +extern const struct bpf_func_proto bpf_map_peek_elem_proto; extern const struct bpf_func_proto bpf_get_prandom_u32_proto; extern const struct bpf_func_proto bpf_get_smp_processor_id_proto; diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 7bad4e1947ed..44d9ab4809bd 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -69,3 +69,5 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, reuseport_array_ops) #endif #endif +BPF_MAP_TYPE(BPF_MAP_TYPE_QUEUE, queue_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_STACK, stack_map_ops) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 5e46f6732781..70082cb626b4 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -128,6 +128,8 @@ enum bpf_map_type { BPF_MAP_TYPE_CGROUP_STORAGE, BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, + BPF_MAP_TYPE_QUEUE, + BPF_MAP_TYPE_STACK, }; enum bpf_prog_type { @@ -462,6 +464,28 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * + * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags) + * Description + * Push an element *value* in *map*. *flags* is one of: + * + * **BPF_EXIST** + * If the queue/stack is full, the oldest element is removed to + * make room for this. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_map_pop_elem(struct bpf_map *map, void *value) + * Description + * Pop an element from *map*. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_map_peek_elem(struct bpf_map *map, void *value) + * Description + * Get an element from *map* without removing it. + * Return + * 0 on success, or a negative error in case of failure. + * * int bpf_probe_read(void *dst, u32 size, const void *src) * Description * For tracing programs, safely attempt to read *size* bytes from @@ -2303,7 +2327,10 @@ union bpf_attr { FN(skb_ancestor_cgroup_id), \ FN(sk_lookup_tcp), \ FN(sk_lookup_udp), \ - FN(sk_release), + FN(sk_release), \ + FN(map_push_elem), \ + FN(map_pop_elem), \ + FN(map_peek_elem), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index ff8262626b8f..4c2fa3ac56f6 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -3,7 +3,7 @@ obj-y := core.o obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o -obj-$(CONFIG_BPF_SYSCALL) += local_storage.o +obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o obj-$(CONFIG_BPF_SYSCALL) += disasm.o obj-$(CONFIG_BPF_SYSCALL) += btf.o ifeq ($(CONFIG_NET),y) diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index defcf4df6d91..7c7eeea8cffc 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1783,6 +1783,9 @@ BPF_CALL_0(bpf_user_rnd_u32) const struct bpf_func_proto bpf_map_lookup_elem_proto __weak; const struct bpf_func_proto bpf_map_update_elem_proto __weak; const struct bpf_func_proto bpf_map_delete_elem_proto __weak; +const struct bpf_func_proto bpf_map_push_elem_proto __weak; +const struct bpf_func_proto bpf_map_pop_elem_proto __weak; +const struct bpf_func_proto bpf_map_peek_elem_proto __weak; const struct bpf_func_proto bpf_get_prandom_u32_proto __weak; const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 6502115e8f55..ab0d5e3f9892 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -76,6 +76,49 @@ const struct bpf_func_proto bpf_map_delete_elem_proto = { .arg2_type = ARG_PTR_TO_MAP_KEY, }; +BPF_CALL_3(bpf_map_push_elem, struct bpf_map *, map, void *, value, u64, flags) +{ + return map->ops->map_push_elem(map, value, flags); +} + +const struct bpf_func_proto bpf_map_push_elem_proto = { + .func = bpf_map_push_elem, + .gpl_only = false, + .pkt_access = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_MAP_VALUE, + .arg3_type = ARG_ANYTHING, +}; + +BPF_CALL_2(bpf_map_pop_elem, struct bpf_map *, map, void *, value) +{ + return map->ops->map_pop_elem(map, value); +} + +const struct bpf_func_proto bpf_map_pop_elem_proto = { + .func = bpf_map_pop_elem, + .gpl_only = false, + .pkt_access = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_UNINIT_MAP_VALUE, +}; + +BPF_CALL_2(bpf_map_peek_elem, struct bpf_map *, map, void *, value) +{ + return map->ops->map_peek_elem(map, value); +} + +const struct bpf_func_proto bpf_map_peek_elem_proto = { + .func = bpf_map_pop_elem, + .gpl_only = false, + .pkt_access = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_UNINIT_MAP_VALUE, +}; + const struct bpf_func_proto bpf_get_prandom_u32_proto = { .func = bpf_user_rnd_u32, .gpl_only = false, diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c new file mode 100644 index 000000000000..12a93fb37449 --- /dev/null +++ b/kernel/bpf/queue_stack_maps.c @@ -0,0 +1,288 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * queue_stack_maps.c: BPF queue and stack maps + * + * Copyright (c) 2018 Politecnico di Torino + */ +#include +#include +#include +#include "percpu_freelist.h" + +#define QUEUE_STACK_CREATE_FLAG_MASK \ + (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) + + +struct bpf_queue_stack { + struct bpf_map map; + raw_spinlock_t lock; + u32 head, tail; + u32 size; /* max_entries + 1 */ + + char elements[0] __aligned(8); +}; + +static struct bpf_queue_stack *bpf_queue_stack(struct bpf_map *map) +{ + return container_of(map, struct bpf_queue_stack, map); +} + +static bool queue_stack_map_is_empty(struct bpf_queue_stack *qs) +{ + return qs->head == qs->tail; +} + +static bool queue_stack_map_is_full(struct bpf_queue_stack *qs) +{ + u32 head = qs->head + 1; + + if (unlikely(head >= qs->size)) + head = 0; + + return head == qs->tail; +} + +/* Called from syscall */ +static int queue_stack_map_alloc_check(union bpf_attr *attr) +{ + /* check sanity of attributes */ + if (attr->max_entries == 0 || attr->key_size != 0 || + attr->map_flags & ~QUEUE_STACK_CREATE_FLAG_MASK) + return -EINVAL; + + if (attr->value_size > KMALLOC_MAX_SIZE) + /* if value_size is bigger, the user space won't be able to + * access the elements. + */ + return -E2BIG; + + return 0; +} + +static struct bpf_map *queue_stack_map_alloc(union bpf_attr *attr) +{ + int ret, numa_node = bpf_map_attr_numa_node(attr); + struct bpf_queue_stack *qs; + u32 size, value_size; + u64 queue_size, cost; + + size = attr->max_entries + 1; + value_size = attr->value_size; + + queue_size = sizeof(*qs) + (u64) value_size * size; + + cost = queue_size; + if (cost >= U32_MAX - PAGE_SIZE) + return ERR_PTR(-E2BIG); + + cost = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + + ret = bpf_map_precharge_memlock(cost); + if (ret < 0) + return ERR_PTR(ret); + + qs = bpf_map_area_alloc(queue_size, numa_node); + if (!qs) + return ERR_PTR(-ENOMEM); + + memset(qs, 0, sizeof(*qs)); + + bpf_map_init_from_attr(&qs->map, attr); + + qs->map.pages = cost; + qs->size = size; + + raw_spin_lock_init(&qs->lock); + + return &qs->map; +} + +/* Called when map->refcnt goes to zero, either from workqueue or from syscall */ +static void queue_stack_map_free(struct bpf_map *map) +{ + struct bpf_queue_stack *qs = bpf_queue_stack(map); + + /* at this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0, + * so the programs (can be more than one that used this map) were + * disconnected from events. Wait for outstanding critical sections in + * these programs to complete + */ + synchronize_rcu(); + + bpf_map_area_free(qs); +} + +static int __queue_map_get(struct bpf_map *map, void *value, bool delete) +{ + struct bpf_queue_stack *qs = bpf_queue_stack(map); + unsigned long flags; + int err = 0; + void *ptr; + + raw_spin_lock_irqsave(&qs->lock, flags); + + if (queue_stack_map_is_empty(qs)) { + err = -ENOENT; + goto out; + } + + ptr = &qs->elements[qs->tail * qs->map.value_size]; + memcpy(value, ptr, qs->map.value_size); + + if (delete) { + if (unlikely(++qs->tail >= qs->size)) + qs->tail = 0; + } + +out: + raw_spin_unlock_irqrestore(&qs->lock, flags); + return err; +} + + +static int __stack_map_get(struct bpf_map *map, void *value, bool delete) +{ + struct bpf_queue_stack *qs = bpf_queue_stack(map); + unsigned long flags; + int err = 0; + void *ptr; + u32 index; + + raw_spin_lock_irqsave(&qs->lock, flags); + + if (queue_stack_map_is_empty(qs)) { + err = -ENOENT; + goto out; + } + + index = qs->head - 1; + if (unlikely(index >= qs->size)) + index = qs->size - 1; + + ptr = &qs->elements[index * qs->map.value_size]; + memcpy(value, ptr, qs->map.value_size); + + if (delete) + qs->head = index; + +out: + raw_spin_unlock_irqrestore(&qs->lock, flags); + return err; +} + +/* Called from syscall or from eBPF program */ +static int queue_map_peek_elem(struct bpf_map *map, void *value) +{ + return __queue_map_get(map, value, false); +} + +/* Called from syscall or from eBPF program */ +static int stack_map_peek_elem(struct bpf_map *map, void *value) +{ + return __stack_map_get(map, value, false); +} + +/* Called from syscall or from eBPF program */ +static int queue_map_pop_elem(struct bpf_map *map, void *value) +{ + return __queue_map_get(map, value, true); +} + +/* Called from syscall or from eBPF program */ +static int stack_map_pop_elem(struct bpf_map *map, void *value) +{ + return __stack_map_get(map, value, true); +} + +/* Called from syscall or from eBPF program */ +static int queue_stack_map_push_elem(struct bpf_map *map, void *value, + u64 flags) +{ + struct bpf_queue_stack *qs = bpf_queue_stack(map); + unsigned long irq_flags; + int err = 0; + void *dst; + + /* BPF_EXIST is used to force making room for a new element in case the + * map is full + */ + bool replace = (flags & BPF_EXIST); + + /* Check supported flags for queue and stack maps */ + if (flags & BPF_NOEXIST || flags > BPF_EXIST) + return -EINVAL; + + raw_spin_lock_irqsave(&qs->lock, irq_flags); + + if (queue_stack_map_is_full(qs)) { + if (!replace) { + err = -E2BIG; + goto out; + } + /* advance tail pointer to overwrite oldest element */ + if (unlikely(++qs->tail >= qs->size)) + qs->tail = 0; + } + + dst = &qs->elements[qs->head * qs->map.value_size]; + memcpy(dst, value, qs->map.value_size); + + if (unlikely(++qs->head >= qs->size)) + qs->head = 0; + +out: + raw_spin_unlock_irqrestore(&qs->lock, irq_flags); + return err; +} + +/* Called from syscall or from eBPF program */ +static void *queue_stack_map_lookup_elem(struct bpf_map *map, void *key) +{ + return NULL; +} + +/* Called from syscall or from eBPF program */ +static int queue_stack_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 flags) +{ + return -EINVAL; +} + +/* Called from syscall or from eBPF program */ +static int queue_stack_map_delete_elem(struct bpf_map *map, void *key) +{ + return -EINVAL; +} + +/* Called from syscall */ +static int queue_stack_map_get_next_key(struct bpf_map *map, void *key, + void *next_key) +{ + return -EINVAL; +} + +const struct bpf_map_ops queue_map_ops = { + .map_alloc_check = queue_stack_map_alloc_check, + .map_alloc = queue_stack_map_alloc, + .map_free = queue_stack_map_free, + .map_lookup_elem = queue_stack_map_lookup_elem, + .map_update_elem = queue_stack_map_update_elem, + .map_delete_elem = queue_stack_map_delete_elem, + .map_push_elem = queue_stack_map_push_elem, + .map_pop_elem = queue_map_pop_elem, + .map_peek_elem = queue_map_peek_elem, + .map_get_next_key = queue_stack_map_get_next_key, +}; + +const struct bpf_map_ops stack_map_ops = { + .map_alloc_check = queue_stack_map_alloc_check, + .map_alloc = queue_stack_map_alloc, + .map_free = queue_stack_map_free, + .map_lookup_elem = queue_stack_map_lookup_elem, + .map_update_elem = queue_stack_map_update_elem, + .map_delete_elem = queue_stack_map_delete_elem, + .map_push_elem = queue_stack_map_push_elem, + .map_pop_elem = stack_map_pop_elem, + .map_peek_elem = stack_map_peek_elem, + .map_get_next_key = queue_stack_map_get_next_key, +}; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 78d9dd95e25f..1617407f9ee5 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -727,6 +727,9 @@ static int map_lookup_elem(union bpf_attr *attr) err = bpf_fd_htab_map_lookup_elem(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { err = bpf_fd_reuseport_array_lookup_elem(map, key, value); + } else if (map->map_type == BPF_MAP_TYPE_QUEUE || + map->map_type == BPF_MAP_TYPE_STACK) { + err = map->ops->map_peek_elem(map, value); } else { rcu_read_lock(); ptr = map->ops->map_lookup_elem(map, key); @@ -857,6 +860,9 @@ static int map_update_elem(union bpf_attr *attr) /* rcu_read_lock() is not needed */ err = bpf_fd_reuseport_array_update_elem(map, key, value, attr->flags); + } else if (map->map_type == BPF_MAP_TYPE_QUEUE || + map->map_type == BPF_MAP_TYPE_STACK) { + err = map->ops->map_push_elem(map, value, attr->flags); } else { rcu_read_lock(); err = map->ops->map_update_elem(map, key, value, attr->flags); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index d84c91ac3b70..7d6d9cf9ebd5 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2324,6 +2324,13 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, if (func_id != BPF_FUNC_sk_select_reuseport) goto error; break; + case BPF_MAP_TYPE_QUEUE: + case BPF_MAP_TYPE_STACK: + if (func_id != BPF_FUNC_map_peek_elem && + func_id != BPF_FUNC_map_pop_elem && + func_id != BPF_FUNC_map_push_elem) + goto error; + break; default: break; } @@ -2380,6 +2387,13 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, if (map->map_type != BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) goto error; break; + case BPF_FUNC_map_peek_elem: + case BPF_FUNC_map_pop_elem: + case BPF_FUNC_map_push_elem: + if (map->map_type != BPF_MAP_TYPE_QUEUE && + map->map_type != BPF_MAP_TYPE_STACK) + goto error; + break; default: break; } @@ -2675,7 +2689,10 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, if (func_id != BPF_FUNC_tail_call && func_id != BPF_FUNC_map_lookup_elem && func_id != BPF_FUNC_map_update_elem && - func_id != BPF_FUNC_map_delete_elem) + func_id != BPF_FUNC_map_delete_elem && + func_id != BPF_FUNC_map_push_elem && + func_id != BPF_FUNC_map_pop_elem && + func_id != BPF_FUNC_map_peek_elem) return 0; if (meta->map_ptr == NULL) { diff --git a/net/core/filter.c b/net/core/filter.c index 1a3ac6c46873..ea48ec789b5c 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4876,6 +4876,12 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_map_update_elem_proto; case BPF_FUNC_map_delete_elem: return &bpf_map_delete_elem_proto; + case BPF_FUNC_map_push_elem: + return &bpf_map_push_elem_proto; + case BPF_FUNC_map_pop_elem: + return &bpf_map_pop_elem_proto; + case BPF_FUNC_map_peek_elem: + return &bpf_map_peek_elem_proto; case BPF_FUNC_get_prandom_u32: return &bpf_get_prandom_u32_proto; case BPF_FUNC_get_smp_processor_id: -- cgit v1.2.3 From b39b5f411dcfce28ff954e5d6acb2c11be3cb0ec Mon Sep 17 00:00:00 2001 From: Song Liu Date: Fri, 19 Oct 2018 09:57:57 -0700 Subject: bpf: add cg_skb_is_valid_access for BPF_PROG_TYPE_CGROUP_SKB BPF programs of BPF_PROG_TYPE_CGROUP_SKB need to access headers in the skb. This patch enables direct access of skb for these programs. Two helper functions bpf_compute_and_save_data_end() and bpf_restore_data_end() are introduced. There are used in __cgroup_bpf_run_filter_skb(), to compute proper data_end for the BPF program, and restore original data afterwards. Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 21 +++++++++++++++++++++ kernel/bpf/cgroup.c | 6 ++++++ net/core/filter.c | 36 +++++++++++++++++++++++++++++++++++- 3 files changed, 62 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 5771874bc01e..91b4c934f02e 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -548,6 +548,27 @@ static inline void bpf_compute_data_pointers(struct sk_buff *skb) cb->data_end = skb->data + skb_headlen(skb); } +/* Similar to bpf_compute_data_pointers(), except that save orginal + * data in cb->data and cb->meta_data for restore. + */ +static inline void bpf_compute_and_save_data_end( + struct sk_buff *skb, void **saved_data_end) +{ + struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; + + *saved_data_end = cb->data_end; + cb->data_end = skb->data + skb_headlen(skb); +} + +/* Restore data saved by bpf_compute_data_pointers(). */ +static inline void bpf_restore_data_end( + struct sk_buff *skb, void *saved_data_end) +{ + struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; + + cb->data_end = saved_data_end; +} + static inline u8 *bpf_skb_cb(struct sk_buff *skb) { /* eBPF programs may read/write skb->cb[] area to transfer meta diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 00f6ed2e4f9a..9425c2fb872f 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -553,6 +553,7 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk, { unsigned int offset = skb->data - skb_network_header(skb); struct sock *save_sk; + void *saved_data_end; struct cgroup *cgrp; int ret; @@ -566,8 +567,13 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk, save_sk = skb->sk; skb->sk = sk; __skb_push(skb, offset); + + /* compute pointers for the bpf prog */ + bpf_compute_and_save_data_end(skb, &saved_data_end); + ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], skb, bpf_prog_run_save_cb); + bpf_restore_data_end(skb, saved_data_end); __skb_pull(skb, offset); skb->sk = save_sk; return ret == 1 ? 0 : -EPERM; diff --git a/net/core/filter.c b/net/core/filter.c index ea48ec789b5c..5fd5139e8638 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5352,6 +5352,40 @@ static bool sk_filter_is_valid_access(int off, int size, return bpf_skb_is_valid_access(off, size, type, prog, info); } +static bool cg_skb_is_valid_access(int off, int size, + enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + switch (off) { + case bpf_ctx_range(struct __sk_buff, tc_classid): + case bpf_ctx_range(struct __sk_buff, data_meta): + case bpf_ctx_range(struct __sk_buff, flow_keys): + return false; + } + if (type == BPF_WRITE) { + switch (off) { + case bpf_ctx_range(struct __sk_buff, mark): + case bpf_ctx_range(struct __sk_buff, priority): + case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): + break; + default: + return false; + } + } + + switch (off) { + case bpf_ctx_range(struct __sk_buff, data): + info->reg_type = PTR_TO_PACKET; + break; + case bpf_ctx_range(struct __sk_buff, data_end): + info->reg_type = PTR_TO_PACKET_END; + break; + } + + return bpf_skb_is_valid_access(off, size, type, prog, info); +} + static bool lwt_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, @@ -7044,7 +7078,7 @@ const struct bpf_prog_ops xdp_prog_ops = { const struct bpf_verifier_ops cg_skb_verifier_ops = { .get_func_proto = cg_skb_func_proto, - .is_valid_access = sk_filter_is_valid_access, + .is_valid_access = cg_skb_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, }; -- cgit v1.2.3 From 5032d079909d1ac5c2535acc32d5f01cd245d8ea Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Thu, 18 Oct 2018 13:58:35 -0700 Subject: bpf: skmsg, fix psock create on existing kcm/tls port Before using the psock returned by sk_psock_get() when adding it to a sockmap we need to ensure it is actually a sockmap based psock. Previously we were only checking this after incrementing the reference counter which was an error. This resulted in a slab-out-of-bounds error when the psock was not actually a sockmap type. This moves the check up so the reference counter is only used if it is a sockmap psock. Eric reported the following KASAN BUG, BUG: KASAN: slab-out-of-bounds in atomic_read include/asm-generic/atomic-instrumented.h:21 [inline] BUG: KASAN: slab-out-of-bounds in refcount_inc_not_zero_checked+0x97/0x2f0 lib/refcount.c:120 Read of size 4 at addr ffff88019548be58 by task syz-executor4/22387 CPU: 1 PID: 22387 Comm: syz-executor4 Not tainted 4.19.0-rc7+ #264 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x1c4/0x2b4 lib/dump_stack.c:113 print_address_description.cold.8+0x9/0x1ff mm/kasan/report.c:256 kasan_report_error mm/kasan/report.c:354 [inline] kasan_report.cold.9+0x242/0x309 mm/kasan/report.c:412 check_memory_region_inline mm/kasan/kasan.c:260 [inline] check_memory_region+0x13e/0x1b0 mm/kasan/kasan.c:267 kasan_check_read+0x11/0x20 mm/kasan/kasan.c:272 atomic_read include/asm-generic/atomic-instrumented.h:21 [inline] refcount_inc_not_zero_checked+0x97/0x2f0 lib/refcount.c:120 sk_psock_get include/linux/skmsg.h:379 [inline] sock_map_link.isra.6+0x41f/0xe30 net/core/sock_map.c:178 sock_hash_update_common+0x19b/0x11e0 net/core/sock_map.c:669 sock_hash_update_elem+0x306/0x470 net/core/sock_map.c:738 map_update_elem+0x819/0xdf0 kernel/bpf/syscall.c:818 Signed-off-by: John Fastabend Reported-by: Eric Dumazet Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Daniel Borkmann --- include/linux/skmsg.h | 25 ++++++++++++++++++++----- net/core/sock_map.c | 11 ++++++----- 2 files changed, 26 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 22347b08e1f8..84e18863f6a4 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -270,11 +270,6 @@ static inline struct sk_psock *sk_psock(const struct sock *sk) return rcu_dereference_sk_user_data(sk); } -static inline bool sk_has_psock(struct sock *sk) -{ - return sk_psock(sk) != NULL && sk->sk_prot->recvmsg == tcp_bpf_recvmsg; -} - static inline void sk_psock_queue_msg(struct sk_psock *psock, struct sk_msg *msg) { @@ -374,6 +369,26 @@ static inline bool sk_psock_test_state(const struct sk_psock *psock, return test_bit(bit, &psock->state); } +static inline struct sk_psock *sk_psock_get_checked(struct sock *sk) +{ + struct sk_psock *psock; + + rcu_read_lock(); + psock = sk_psock(sk); + if (psock) { + if (sk->sk_prot->recvmsg != tcp_bpf_recvmsg) { + psock = ERR_PTR(-EBUSY); + goto out; + } + + if (!refcount_inc_not_zero(&psock->refcnt)) + psock = ERR_PTR(-EBUSY); + } +out: + rcu_read_unlock(); + return psock; +} + static inline struct sk_psock *sk_psock_get(struct sock *sk) { struct sk_psock *psock; diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 3c0e44cb811a..be6092ac69f8 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -175,12 +175,13 @@ static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs, } } - psock = sk_psock_get(sk); + psock = sk_psock_get_checked(sk); + if (IS_ERR(psock)) { + ret = PTR_ERR(psock); + goto out_progs; + } + if (psock) { - if (!sk_has_psock(sk)) { - ret = -EBUSY; - goto out_progs; - } if ((msg_parser && READ_ONCE(psock->progs.msg_parser)) || (skb_progs && READ_ONCE(psock->progs.skb_parser))) { sk_psock_put(sk, psock); -- cgit v1.2.3 From c9fbd71f73094311b31ee703a918e9e0df502cef Mon Sep 17 00:00:00 2001 From: Debabrata Banerjee Date: Thu, 18 Oct 2018 11:18:26 -0400 Subject: netpoll: allow cleanup to be synchronous This fixes a problem introduced by: commit 2cde6acd49da ("netpoll: Fix __netpoll_rcu_free so that it can hold the rtnl lock") When using netconsole on a bond, __netpoll_cleanup can asynchronously recurse multiple times, each __netpoll_free_async call can result in more __netpoll_free_async's. This means there is now a race between cleanup_work queues on multiple netpoll_info's on multiple devices and the configuration of a new netpoll. For example if a netconsole is set to enable 0, reconfigured, and enable 1 immediately, this netconsole will likely not work. Given the reason for __netpoll_free_async is it can be called when rtnl is not locked, if it is locked, we should be able to execute synchronously. It appears to be locked everywhere it's called from. Generalize the design pattern from the teaming driver for current callers of __netpoll_free_async. CC: Neil Horman CC: "David S. Miller" Signed-off-by: Debabrata Banerjee Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 3 ++- drivers/net/macvlan.c | 2 +- drivers/net/team/team.c | 5 +---- include/linux/netpoll.h | 4 +--- net/8021q/vlan_dev.c | 3 +-- net/bridge/br_device.c | 2 +- net/core/netpoll.c | 21 +++++---------------- net/dsa/slave.c | 2 +- 8 files changed, 13 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index ee28ec9e0aba..ffa37adb7681 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -963,7 +963,8 @@ static inline void slave_disable_netpoll(struct slave *slave) return; slave->np = NULL; - __netpoll_free_async(np); + + __netpoll_free(np); } static void bond_poll_controller(struct net_device *bond_dev) diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index cfda146f3b3b..fc8d5f1ee1ad 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -1077,7 +1077,7 @@ static void macvlan_dev_netpoll_cleanup(struct net_device *dev) vlan->netpoll = NULL; - __netpoll_free_async(netpoll); + __netpoll_free(netpoll); } #endif /* CONFIG_NET_POLL_CONTROLLER */ diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index d887016e54b6..db633ae9f784 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1104,10 +1104,7 @@ static void team_port_disable_netpoll(struct team_port *port) return; port->np = NULL; - /* Wait for transmitting packets to finish before freeing. */ - synchronize_rcu_bh(); - __netpoll_cleanup(np); - kfree(np); + __netpoll_free(np); } #else static int team_port_enable_netpoll(struct team_port *port) diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index 3ef82d3a78db..676f1ff161a9 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -31,8 +31,6 @@ struct netpoll { bool ipv6; u16 local_port, remote_port; u8 remote_mac[ETH_ALEN]; - - struct work_struct cleanup_work; }; struct netpoll_info { @@ -63,7 +61,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt); int __netpoll_setup(struct netpoll *np, struct net_device *ndev); int netpoll_setup(struct netpoll *np); void __netpoll_cleanup(struct netpoll *np); -void __netpoll_free_async(struct netpoll *np); +void __netpoll_free(struct netpoll *np); void netpoll_cleanup(struct netpoll *np); void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, struct net_device *dev); diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 546af0e73ac3..ff720f1ebf73 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -756,8 +756,7 @@ static void vlan_dev_netpoll_cleanup(struct net_device *dev) return; vlan->netpoll = NULL; - - __netpoll_free_async(netpoll); + __netpoll_free(netpoll); } #endif /* CONFIG_NET_POLL_CONTROLLER */ diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index e053a4e43758..c6abf927f0c9 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -344,7 +344,7 @@ void br_netpoll_disable(struct net_bridge_port *p) p->np = NULL; - __netpoll_free_async(np); + __netpoll_free(np); } #endif diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 3ae899805f8b..5da9552b186b 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -57,7 +57,6 @@ DEFINE_STATIC_SRCU(netpoll_srcu); MAX_UDP_CHUNK) static void zap_completion_queue(void); -static void netpoll_async_cleanup(struct work_struct *work); static unsigned int carrier_timeout = 4; module_param(carrier_timeout, uint, 0644); @@ -589,7 +588,6 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev) np->dev = ndev; strlcpy(np->dev_name, ndev->name, IFNAMSIZ); - INIT_WORK(&np->cleanup_work, netpoll_async_cleanup); if (ndev->priv_flags & IFF_DISABLE_NETPOLL) { np_err(np, "%s doesn't support polling, aborting\n", @@ -788,10 +786,6 @@ void __netpoll_cleanup(struct netpoll *np) { struct netpoll_info *npinfo; - /* rtnl_dereference would be preferable here but - * rcu_cleanup_netpoll path can put us in here safely without - * holding the rtnl, so plain rcu_dereference it is - */ npinfo = rtnl_dereference(np->dev->npinfo); if (!npinfo) return; @@ -812,21 +806,16 @@ void __netpoll_cleanup(struct netpoll *np) } EXPORT_SYMBOL_GPL(__netpoll_cleanup); -static void netpoll_async_cleanup(struct work_struct *work) +void __netpoll_free(struct netpoll *np) { - struct netpoll *np = container_of(work, struct netpoll, cleanup_work); + ASSERT_RTNL(); - rtnl_lock(); + /* Wait for transmitting packets to finish before freeing. */ + synchronize_rcu_bh(); __netpoll_cleanup(np); - rtnl_unlock(); kfree(np); } - -void __netpoll_free_async(struct netpoll *np) -{ - schedule_work(&np->cleanup_work); -} -EXPORT_SYMBOL_GPL(__netpoll_free_async); +EXPORT_SYMBOL_GPL(__netpoll_free); void netpoll_cleanup(struct netpoll *np) { diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 5428ef529019..7d0c19e7edcf 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -722,7 +722,7 @@ static void dsa_slave_netpoll_cleanup(struct net_device *dev) p->netpoll = NULL; - __netpoll_free_async(netpoll); + __netpoll_free(netpoll); } static void dsa_slave_poll_controller(struct net_device *dev) -- cgit v1.2.3 From bff5b4b3737219195ca0caef4ff7884303cb5dc1 Mon Sep 17 00:00:00 2001 From: Yuiko Oshino Date: Thu, 18 Oct 2018 15:06:01 -0400 Subject: net: phy: micrel: add Microchip KSZ9131 initial driver Add support for Microchip Technology KSZ9131 10/100/1000 Ethernet PHY Signed-off-by: Yuiko Oshino Signed-off-by: David S. Miller --- drivers/net/phy/micrel.c | 130 ++++++++++++++++++++++++++++++++++++++++++++- include/linux/micrel_phy.h | 1 + 2 files changed, 130 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 3db06b40580d..9265dea79412 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -14,7 +14,7 @@ * option) any later version. * * Support : Micrel Phys: - * Giga phys: ksz9021, ksz9031 + * Giga phys: ksz9021, ksz9031, ksz9131 * 100/10 Phys : ksz8001, ksz8721, ksz8737, ksz8041 * ksz8021, ksz8031, ksz8051, * ksz8081, ksz8091, @@ -609,6 +609,116 @@ err_force_master: return result; } +#define KSZ9131_SKEW_5BIT_MAX 2400 +#define KSZ9131_SKEW_4BIT_MAX 800 +#define KSZ9131_OFFSET 700 +#define KSZ9131_STEP 100 + +static int ksz9131_of_load_skew_values(struct phy_device *phydev, + struct device_node *of_node, + u16 reg, size_t field_sz, + char *field[], u8 numfields) +{ + int val[4] = {-(1 + KSZ9131_OFFSET), -(2 + KSZ9131_OFFSET), + -(3 + KSZ9131_OFFSET), -(4 + KSZ9131_OFFSET)}; + int skewval, skewmax = 0; + int matches = 0; + u16 maxval; + u16 newval; + u16 mask; + int i; + + /* psec properties in dts should mean x pico seconds */ + if (field_sz == 5) + skewmax = KSZ9131_SKEW_5BIT_MAX; + else + skewmax = KSZ9131_SKEW_4BIT_MAX; + + for (i = 0; i < numfields; i++) + if (!of_property_read_s32(of_node, field[i], &skewval)) { + if (skewval < -KSZ9131_OFFSET) + skewval = -KSZ9131_OFFSET; + else if (skewval > skewmax) + skewval = skewmax; + + val[i] = skewval + KSZ9131_OFFSET; + matches++; + } + + if (!matches) + return 0; + + if (matches < numfields) + newval = ksz9031_extended_read(phydev, OP_DATA, 2, reg); + else + newval = 0; + + maxval = (field_sz == 4) ? 0xf : 0x1f; + for (i = 0; i < numfields; i++) + if (val[i] != -(i + 1 + KSZ9131_OFFSET)) { + mask = 0xffff; + mask ^= maxval << (field_sz * i); + newval = (newval & mask) | + (((val[i] / KSZ9131_STEP) & maxval) + << (field_sz * i)); + } + + return ksz9031_extended_write(phydev, OP_DATA, 2, reg, newval); +} + +static int ksz9131_config_init(struct phy_device *phydev) +{ + const struct device *dev = &phydev->mdio.dev; + struct device_node *of_node = dev->of_node; + char *clk_skews[2] = {"rxc-skew-psec", "txc-skew-psec"}; + char *rx_data_skews[4] = { + "rxd0-skew-psec", "rxd1-skew-psec", + "rxd2-skew-psec", "rxd3-skew-psec" + }; + char *tx_data_skews[4] = { + "txd0-skew-psec", "txd1-skew-psec", + "txd2-skew-psec", "txd3-skew-psec" + }; + char *control_skews[2] = {"txen-skew-psec", "rxdv-skew-psec"}; + const struct device *dev_walker; + int ret; + + dev_walker = &phydev->mdio.dev; + do { + of_node = dev_walker->of_node; + dev_walker = dev_walker->parent; + } while (!of_node && dev_walker); + + if (!of_node) + return 0; + + ret = ksz9131_of_load_skew_values(phydev, of_node, + MII_KSZ9031RN_CLK_PAD_SKEW, 5, + clk_skews, 2); + if (ret < 0) + return ret; + + ret = ksz9131_of_load_skew_values(phydev, of_node, + MII_KSZ9031RN_CONTROL_PAD_SKEW, 4, + control_skews, 2); + if (ret < 0) + return ret; + + ret = ksz9131_of_load_skew_values(phydev, of_node, + MII_KSZ9031RN_RX_DATA_PAD_SKEW, 4, + rx_data_skews, 4); + if (ret < 0) + return ret; + + ret = ksz9131_of_load_skew_values(phydev, of_node, + MII_KSZ9031RN_TX_DATA_PAD_SKEW, 4, + tx_data_skews, 4); + if (ret < 0) + return ret; + + return 0; +} + #define KSZ8873MLL_GLOBAL_CONTROL_4 0x06 #define KSZ8873MLL_GLOBAL_CONTROL_4_DUPLEX BIT(6) #define KSZ8873MLL_GLOBAL_CONTROL_4_SPEED BIT(4) @@ -974,6 +1084,23 @@ static struct phy_driver ksphy_driver[] = { .get_stats = kszphy_get_stats, .suspend = genphy_suspend, .resume = kszphy_resume, +}, { + .phy_id = PHY_ID_KSZ9131, + .phy_id_mask = MICREL_PHY_ID_MASK, + .name = "Microchip KSZ9131 Gigabit PHY", + .features = PHY_GBIT_FEATURES, + .flags = PHY_HAS_INTERRUPT, + .driver_data = &ksz9021_type, + .probe = kszphy_probe, + .config_init = ksz9131_config_init, + .read_status = ksz9031_read_status, + .ack_interrupt = kszphy_ack_interrupt, + .config_intr = kszphy_config_intr, + .get_sset_count = kszphy_get_sset_count, + .get_strings = kszphy_get_strings, + .get_stats = kszphy_get_stats, + .suspend = genphy_suspend, + .resume = kszphy_resume, }, { .phy_id = PHY_ID_KSZ8873MLL, .phy_id_mask = MICREL_PHY_ID_MASK, @@ -1022,6 +1149,7 @@ MODULE_LICENSE("GPL"); static struct mdio_device_id __maybe_unused micrel_tbl[] = { { PHY_ID_KSZ9021, 0x000ffffe }, { PHY_ID_KSZ9031, MICREL_PHY_ID_MASK }, + { PHY_ID_KSZ9131, MICREL_PHY_ID_MASK }, { PHY_ID_KSZ8001, 0x00fffffc }, { PHY_ID_KS8737, MICREL_PHY_ID_MASK }, { PHY_ID_KSZ8021, 0x00ffffff }, diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index 472fa4d4ea62..7361cd3fddc1 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -31,6 +31,7 @@ #define PHY_ID_KSZ8081 0x00221560 #define PHY_ID_KSZ8061 0x00221570 #define PHY_ID_KSZ9031 0x00221620 +#define PHY_ID_KSZ9131 0x00221640 #define PHY_ID_KSZ886X 0x00221430 #define PHY_ID_KSZ8863 0x00221435 -- cgit v1.2.3 From 6fff607e2f14bd7c63c06c464a6f93b8efbabe28 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 19 Oct 2018 19:56:49 -0700 Subject: bpf: sk_msg program helper bpf_msg_push_data This allows user to push data into a msg using sk_msg program types. The format is as follows, bpf_msg_push_data(msg, offset, len, flags) this will insert 'len' bytes at offset 'offset'. For example to prepend 10 bytes at the front of the message the user can, bpf_msg_push_data(msg, 0, 10, 0); This will invalidate data bounds so BPF user will have to then recheck data bounds after calling this. After this the msg size will have been updated and the user is free to write into the added bytes. We allow any offset/len as long as it is within the (data, data_end) range. However, a copy will be required if the ring is full and its possible for the helper to fail with ENOMEM or EINVAL errors which need to be handled by the BPF program. This can be used similar to XDP metadata to pass data between sk_msg layer and lower layers. Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann --- include/linux/skmsg.h | 5 ++ include/uapi/linux/bpf.h | 20 ++++++- net/core/filter.c | 134 +++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 158 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 84e18863f6a4..2a11e9d91dfa 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -207,6 +207,11 @@ static inline struct scatterlist *sk_msg_elem(struct sk_msg *msg, int which) return &msg->sg.data[which]; } +static inline struct scatterlist sk_msg_elem_cpy(struct sk_msg *msg, int which) +{ + return msg->sg.data[which]; +} + static inline struct page *sk_msg_page(struct sk_msg *msg, int which) { return sg_page(sk_msg_elem(msg, which)); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a2fb333290dc..852dc17ab47a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2240,6 +2240,23 @@ union bpf_attr { * pointer that was returned from bpf_sk_lookup_xxx\ (). * Return * 0 on success, or a negative error in case of failure. + * + * int bpf_msg_push_data(struct sk_buff *skb, u32 start, u32 len, u64 flags) + * Description + * For socket policies, insert *len* bytes into msg at offset + * *start*. + * + * If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a + * *msg* it may want to insert metadata or options into the msg. + * This can later be read and used by any of the lower layer BPF + * hooks. + * + * This helper may fail if under memory pressure (a malloc + * fails) in these cases BPF programs will get an appropriate + * error and BPF programs will need to handle them. + * + * Return + * 0 on success, or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2331,7 +2348,8 @@ union bpf_attr { FN(sk_release), \ FN(map_push_elem), \ FN(map_pop_elem), \ - FN(map_peek_elem), + FN(map_peek_elem), \ + FN(msg_push_data), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/net/core/filter.c b/net/core/filter.c index 5fd5139e8638..35c6933c2622 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2297,6 +2297,137 @@ static const struct bpf_func_proto bpf_msg_pull_data_proto = { .arg4_type = ARG_ANYTHING, }; +BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start, + u32, len, u64, flags) +{ + struct scatterlist sge, nsge, nnsge, rsge = {0}, *psge; + u32 new, i = 0, l, space, copy = 0, offset = 0; + u8 *raw, *to, *from; + struct page *page; + + if (unlikely(flags)) + return -EINVAL; + + /* First find the starting scatterlist element */ + i = msg->sg.start; + do { + l = sk_msg_elem(msg, i)->length; + + if (start < offset + l) + break; + offset += l; + sk_msg_iter_var_next(i); + } while (i != msg->sg.end); + + if (start >= offset + l) + return -EINVAL; + + space = MAX_MSG_FRAGS - sk_msg_elem_used(msg); + + /* If no space available will fallback to copy, we need at + * least one scatterlist elem available to push data into + * when start aligns to the beginning of an element or two + * when it falls inside an element. We handle the start equals + * offset case because its the common case for inserting a + * header. + */ + if (!space || (space == 1 && start != offset)) + copy = msg->sg.data[i].length; + + page = alloc_pages(__GFP_NOWARN | GFP_ATOMIC | __GFP_COMP, + get_order(copy + len)); + if (unlikely(!page)) + return -ENOMEM; + + if (copy) { + int front, back; + + raw = page_address(page); + + psge = sk_msg_elem(msg, i); + front = start - offset; + back = psge->length - front; + from = sg_virt(psge); + + if (front) + memcpy(raw, from, front); + + if (back) { + from += front; + to = raw + front + len; + + memcpy(to, from, back); + } + + put_page(sg_page(psge)); + } else if (start - offset) { + psge = sk_msg_elem(msg, i); + rsge = sk_msg_elem_cpy(msg, i); + + psge->length = start - offset; + rsge.length -= psge->length; + rsge.offset += start; + + sk_msg_iter_var_next(i); + sg_unmark_end(psge); + sk_msg_iter_next(msg, end); + } + + /* Slot(s) to place newly allocated data */ + new = i; + + /* Shift one or two slots as needed */ + if (!copy) { + sge = sk_msg_elem_cpy(msg, i); + + sk_msg_iter_var_next(i); + sg_unmark_end(&sge); + sk_msg_iter_next(msg, end); + + nsge = sk_msg_elem_cpy(msg, i); + if (rsge.length) { + sk_msg_iter_var_next(i); + nnsge = sk_msg_elem_cpy(msg, i); + } + + while (i != msg->sg.end) { + msg->sg.data[i] = sge; + sge = nsge; + sk_msg_iter_var_next(i); + if (rsge.length) { + nsge = nnsge; + nnsge = sk_msg_elem_cpy(msg, i); + } else { + nsge = sk_msg_elem_cpy(msg, i); + } + } + } + + /* Place newly allocated data buffer */ + sk_mem_charge(msg->sk, len); + msg->sg.size += len; + msg->sg.copy[new] = false; + sg_set_page(&msg->sg.data[new], page, len + copy, 0); + if (rsge.length) { + get_page(sg_page(&rsge)); + sk_msg_iter_var_next(new); + msg->sg.data[new] = rsge; + } + + sk_msg_compute_data_pointers(msg); + return 0; +} + +static const struct bpf_func_proto bpf_msg_push_data_proto = { + .func = bpf_msg_push_data, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_ANYTHING, +}; + BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb) { return task_get_classid(skb); @@ -4854,6 +4985,7 @@ bool bpf_helper_changes_pkt_data(void *func) func == bpf_xdp_adjust_head || func == bpf_xdp_adjust_meta || func == bpf_msg_pull_data || + func == bpf_msg_push_data || func == bpf_xdp_adjust_tail || #if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) func == bpf_lwt_seg6_store_bytes || @@ -5130,6 +5262,8 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_msg_cork_bytes_proto; case BPF_FUNC_msg_pull_data: return &bpf_msg_pull_data_proto; + case BPF_FUNC_msg_push_data: + return &bpf_msg_push_data_proto; case BPF_FUNC_get_local_storage: return &bpf_get_local_storage_proto; default: -- cgit v1.2.3 From 1227daa43bce1318ff6fb54e6cd862b4f60245c7 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 17 Oct 2018 17:20:35 -0700 Subject: pstore/ram: Clarify resource reservation labels When ramoops reserved a memory region in the kernel, it had an unhelpful label of "persistent_memory". When reading /proc/iomem, it would be repeated many times, did not hint that it was ramoops in particular, and didn't clarify very much about what each was used for: 400000000-407ffffff : Persistent Memory (legacy) 400000000-400000fff : persistent_memory 400001000-400001fff : persistent_memory ... 4000ff000-4000fffff : persistent_memory Instead, this adds meaningful labels for how the various regions are being used: 400000000-407ffffff : Persistent Memory (legacy) 400000000-400000fff : ramoops:dump(0/252) 400001000-400001fff : ramoops:dump(1/252) ... 4000fc000-4000fcfff : ramoops:dump(252/252) 4000fd000-4000fdfff : ramoops:console 4000fe000-4000fe3ff : ramoops:ftrace(0/3) 4000fe400-4000fe7ff : ramoops:ftrace(1/3) 4000fe800-4000febff : ramoops:ftrace(2/3) 4000fec00-4000fefff : ramoops:ftrace(3/3) 4000ff000-4000fffff : ramoops:pmsg Signed-off-by: Kees Cook Reviewed-by: Joel Fernandes (Google) Tested-by: Sai Prakash Ranjan Tested-by: Guenter Roeck --- fs/pstore/ram.c | 16 +++++++++++++--- fs/pstore/ram_core.c | 11 +++++++---- include/linux/pstore_ram.h | 3 ++- 3 files changed, 22 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index 98e48d1a9776..712960e117fe 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -587,9 +587,16 @@ static int ramoops_init_przs(const char *name, goto fail; for (i = 0; i < *cnt; i++) { + char *label; + + if (*cnt == 1) + label = kasprintf(GFP_KERNEL, "ramoops:%s", name); + else + label = kasprintf(GFP_KERNEL, "ramoops:%s(%d/%d)", + name, i, *cnt - 1); prz_ar[i] = persistent_ram_new(*paddr, zone_sz, sig, - &cxt->ecc_info, - cxt->memtype, flags); + &cxt->ecc_info, + cxt->memtype, flags, label); if (IS_ERR(prz_ar[i])) { err = PTR_ERR(prz_ar[i]); dev_err(dev, "failed to request %s mem region (0x%zx@0x%llx): %d\n", @@ -619,6 +626,8 @@ static int ramoops_init_prz(const char *name, struct persistent_ram_zone **prz, phys_addr_t *paddr, size_t sz, u32 sig) { + char *label; + if (!sz) return 0; @@ -629,8 +638,9 @@ static int ramoops_init_prz(const char *name, return -ENOMEM; } + label = kasprintf(GFP_KERNEL, "ramoops:%s", name); *prz = persistent_ram_new(*paddr, sz, sig, &cxt->ecc_info, - cxt->memtype, 0); + cxt->memtype, 0, label); if (IS_ERR(*prz)) { int err = PTR_ERR(*prz); diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c index 951a14edcf51..f200dcefb3b4 100644 --- a/fs/pstore/ram_core.c +++ b/fs/pstore/ram_core.c @@ -433,11 +433,11 @@ static void *persistent_ram_vmap(phys_addr_t start, size_t size, } static void *persistent_ram_iomap(phys_addr_t start, size_t size, - unsigned int memtype) + unsigned int memtype, char *label) { void *va; - if (!request_mem_region(start, size, "persistent_ram")) { + if (!request_mem_region(start, size, label ?: "ramoops")) { pr_err("request mem region (0x%llx@0x%llx) failed\n", (unsigned long long)size, (unsigned long long)start); return NULL; @@ -460,7 +460,8 @@ static int persistent_ram_buffer_map(phys_addr_t start, phys_addr_t size, if (pfn_valid(start >> PAGE_SHIFT)) prz->vaddr = persistent_ram_vmap(start, size, memtype); else - prz->vaddr = persistent_ram_iomap(start, size, memtype); + prz->vaddr = persistent_ram_iomap(start, size, memtype, + prz->label); if (!prz->vaddr) { pr_err("%s: Failed to map 0x%llx pages at 0x%llx\n", __func__, @@ -530,12 +531,13 @@ void persistent_ram_free(struct persistent_ram_zone *prz) prz->ecc_info.par = NULL; persistent_ram_free_old(prz); + kfree(prz->label); kfree(prz); } struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size, u32 sig, struct persistent_ram_ecc_info *ecc_info, - unsigned int memtype, u32 flags) + unsigned int memtype, u32 flags, char *label) { struct persistent_ram_zone *prz; int ret = -ENOMEM; @@ -549,6 +551,7 @@ struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size, /* Initialize general buffer state. */ raw_spin_lock_init(&prz->buffer_lock); prz->flags = flags; + prz->label = label; ret = persistent_ram_buffer_map(start, size, prz, memtype); if (ret) diff --git a/include/linux/pstore_ram.h b/include/linux/pstore_ram.h index e6d226464838..602d64725222 100644 --- a/include/linux/pstore_ram.h +++ b/include/linux/pstore_ram.h @@ -46,6 +46,7 @@ struct persistent_ram_zone { phys_addr_t paddr; size_t size; void *vaddr; + char *label; struct persistent_ram_buffer *buffer; size_t buffer_size; u32 flags; @@ -65,7 +66,7 @@ struct persistent_ram_zone { struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size, u32 sig, struct persistent_ram_ecc_info *ecc_info, - unsigned int memtype, u32 flags); + unsigned int memtype, u32 flags, char *label); void persistent_ram_free(struct persistent_ram_zone *prz); void persistent_ram_zap(struct persistent_ram_zone *prz); -- cgit v1.2.3 From af033b2aa8a874fd5737fafe90d159136527b5b4 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Thu, 20 Sep 2018 20:05:00 +0800 Subject: f2fs: guarantee journalled quota data by checkpoint For journalled quota mode, let checkpoint to flush dquot dirty data and quota file data to guarntee persistence of all quota sysfile in last checkpoint, by this way, we can avoid corrupting quota sysfile when encountering SPO. The implementation is as below: 1. add a global state SBI_QUOTA_NEED_FLUSH to indicate that there is cached dquot metadata changes in quota subsystem, and later checkpoint should: a) flush dquot metadata into quota file. b) flush quota file to storage to keep file usage be consistent. 2. add a global state SBI_QUOTA_NEED_REPAIR to indicate that quota operation failed due to -EIO or -ENOSPC, so later, a) checkpoint will skip syncing dquot metadata. b) CP_QUOTA_NEED_FSCK_FLAG will be set in last cp pack to give a hint for fsck repairing. 3. add a global state SBI_QUOTA_SKIP_FLUSH, in checkpoint, if quota data updating is very heavy, it may cause hungtask in block_operation(). To avoid this, if our retry time exceed threshold, let's just skip flushing and retry in next checkpoint(). Signed-off-by: Weichao Guo Signed-off-by: Chao Yu [Jaegeuk Kim: avoid warnings and set fsck flag] Signed-off-by: Jaegeuk Kim --- fs/f2fs/checkpoint.c | 62 +++++++++++++++++++++++-- fs/f2fs/data.c | 16 +++++-- fs/f2fs/f2fs.h | 49 ++++++++++++++++---- fs/f2fs/file.c | 31 ++++++++++--- fs/f2fs/inline.c | 4 +- fs/f2fs/inode.c | 11 +++-- fs/f2fs/namei.c | 4 -- fs/f2fs/recovery.c | 43 +++++++++++++++-- fs/f2fs/super.c | 121 +++++++++++++++++++++++++++++++++++++++++++----- include/linux/f2fs_fs.h | 1 + 10 files changed, 294 insertions(+), 48 deletions(-) (limited to 'include/linux') diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index eb6ac79640f8..9c28ea439e0b 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -1079,6 +1079,21 @@ static void __prepare_cp_block(struct f2fs_sb_info *sbi) ckpt->next_free_nid = cpu_to_le32(last_nid); } +static bool __need_flush_quota(struct f2fs_sb_info *sbi) +{ + if (!is_journalled_quota(sbi)) + return false; + if (is_sbi_flag_set(sbi, SBI_QUOTA_SKIP_FLUSH)) + return false; + if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_REPAIR)) + return false; + if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_FLUSH)) + return true; + if (get_pages(sbi, F2FS_DIRTY_QDATA)) + return true; + return false; +} + /* * Freeze all the FS-operations for checkpoint. */ @@ -1090,12 +1105,36 @@ static int block_operations(struct f2fs_sb_info *sbi) .for_reclaim = 0, }; struct blk_plug plug; - int err = 0; + int err = 0, cnt = 0; blk_start_plug(&plug); -retry_flush_dents: +retry_flush_quotas: + if (__need_flush_quota(sbi)) { + int locked; + + if (++cnt > DEFAULT_RETRY_QUOTA_FLUSH_COUNT) { + set_sbi_flag(sbi, SBI_QUOTA_SKIP_FLUSH); + f2fs_lock_all(sbi); + goto retry_flush_dents; + } + clear_sbi_flag(sbi, SBI_QUOTA_NEED_FLUSH); + + /* only failed during mount/umount/freeze/quotactl */ + locked = down_read_trylock(&sbi->sb->s_umount); + f2fs_quota_sync(sbi->sb, -1); + if (locked) + up_read(&sbi->sb->s_umount); + } + f2fs_lock_all(sbi); + if (__need_flush_quota(sbi)) { + f2fs_unlock_all(sbi); + cond_resched(); + goto retry_flush_quotas; + } + +retry_flush_dents: /* write all the dirty dentry pages */ if (get_pages(sbi, F2FS_DIRTY_DENTS)) { f2fs_unlock_all(sbi); @@ -1103,7 +1142,7 @@ retry_flush_dents: if (err) goto out; cond_resched(); - goto retry_flush_dents; + goto retry_flush_quotas; } /* @@ -1112,6 +1151,12 @@ retry_flush_dents: */ down_write(&sbi->node_change); + if (__need_flush_quota(sbi)) { + up_write(&sbi->node_change); + f2fs_unlock_all(sbi); + goto retry_flush_quotas; + } + if (get_pages(sbi, F2FS_DIRTY_IMETA)) { up_write(&sbi->node_change); f2fs_unlock_all(sbi); @@ -1119,7 +1164,7 @@ retry_flush_dents: if (err) goto out; cond_resched(); - goto retry_flush_dents; + goto retry_flush_quotas; } retry_flush_nodes: @@ -1215,6 +1260,14 @@ static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc) else __clear_ckpt_flags(ckpt, CP_DISABLED_FLAG); + if (is_sbi_flag_set(sbi, SBI_QUOTA_SKIP_FLUSH)) + __set_ckpt_flags(ckpt, CP_QUOTA_NEED_FSCK_FLAG); + else + __clear_ckpt_flags(ckpt, CP_QUOTA_NEED_FSCK_FLAG); + + if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_REPAIR)) + __set_ckpt_flags(ckpt, CP_QUOTA_NEED_FSCK_FLAG); + /* set this flag to activate crc|cp_ver for recovery */ __set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG); __clear_ckpt_flags(ckpt, CP_NOCRC_RECOVERY_FLAG); @@ -1422,6 +1475,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) clear_sbi_flag(sbi, SBI_IS_DIRTY); clear_sbi_flag(sbi, SBI_NEED_CP); + clear_sbi_flag(sbi, SBI_QUOTA_SKIP_FLUSH); sbi->unusable_block_count = 0; __set_cp_next_pack(sbi); diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 00b37a1bd15c..106f116466bf 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -46,7 +46,7 @@ static bool __is_cp_guaranteed(struct page *page) inode->i_ino == F2FS_NODE_INO(sbi) || S_ISDIR(inode->i_mode) || (S_ISREG(inode->i_mode) && - is_inode_flag_set(inode, FI_ATOMIC_FILE)) || + (f2fs_is_atomic_file(inode) || IS_NOQUOTA(inode))) || is_cold_data(page)) return true; return false; @@ -1766,6 +1766,8 @@ bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio) return true; if (S_ISDIR(inode->i_mode)) return true; + if (IS_NOQUOTA(inode)) + return true; if (f2fs_is_atomic_file(inode)) return true; if (fio) { @@ -2016,7 +2018,7 @@ out: } unlock_page(page); - if (!S_ISDIR(inode->i_mode)) + if (!S_ISDIR(inode->i_mode) && !IS_NOQUOTA(inode)) f2fs_balance_fs(sbi, need_balance_fs); if (unlikely(f2fs_cp_error(sbi))) { @@ -2207,6 +2209,8 @@ static inline bool __should_serialize_io(struct inode *inode, { if (!S_ISREG(inode->i_mode)) return false; + if (IS_NOQUOTA(inode)) + return false; if (wbc->sync_mode != WB_SYNC_ALL) return true; if (get_dirty_pages(inode) >= SM_I(F2FS_I_SB(inode))->min_seq_blocks) @@ -2236,7 +2240,8 @@ static int __f2fs_write_data_pages(struct address_space *mapping, if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) goto skip_write; - if (S_ISDIR(inode->i_mode) && wbc->sync_mode == WB_SYNC_NONE && + if ((S_ISDIR(inode->i_mode) || IS_NOQUOTA(inode)) && + wbc->sync_mode == WB_SYNC_NONE && get_dirty_pages(inode) < nr_pages_to_skip(sbi, DATA) && f2fs_available_free_memory(sbi, DIRTY_DENTS)) goto skip_write; @@ -2301,7 +2306,7 @@ static void f2fs_write_failed(struct address_space *mapping, loff_t to) down_write(&F2FS_I(inode)->i_mmap_sem); truncate_pagecache(inode, i_size); - f2fs_truncate_blocks(inode, i_size, true); + f2fs_truncate_blocks(inode, i_size, true, true); up_write(&F2FS_I(inode)->i_mmap_sem); up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); @@ -2440,7 +2445,8 @@ repeat: if (err) goto fail; - if (need_balance && has_not_enough_free_secs(sbi, 0, 0)) { + if (need_balance && !IS_NOQUOTA(inode) && + has_not_enough_free_secs(sbi, 0, 0)) { unlock_page(page); f2fs_balance_fs(sbi, true); lock_page(page); diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 5c80eca194b5..f447cbc2295f 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -531,6 +531,9 @@ enum { #define DEFAULT_RETRY_IO_COUNT 8 /* maximum retry read IO count */ +/* maximum retry quota flush count */ +#define DEFAULT_RETRY_QUOTA_FLUSH_COUNT 8 + #define F2FS_LINK_MAX 0xffffffff /* maximum link count per file */ #define MAX_DIR_RA_PAGES 4 /* maximum ra pages of dir */ @@ -1099,6 +1102,9 @@ enum { SBI_IS_SHUTDOWN, /* shutdown by ioctl */ SBI_IS_RECOVERED, /* recovered orphan/data */ SBI_CP_DISABLED, /* CP was disabled last mount */ + SBI_QUOTA_NEED_FLUSH, /* need to flush quota info in CP */ + SBI_QUOTA_SKIP_FLUSH, /* skip flushing quota in current CP */ + SBI_QUOTA_NEED_REPAIR, /* quota file may be corrupted */ }; enum { @@ -1923,12 +1929,18 @@ static inline int inc_valid_node_count(struct f2fs_sb_info *sbi, { block_t valid_block_count; unsigned int valid_node_count; - bool quota = inode && !is_inode; + int err; - if (quota) { - int ret = dquot_reserve_block(inode, 1); - if (ret) - return ret; + if (is_inode) { + if (inode) { + err = dquot_alloc_inode(inode); + if (err) + return err; + } + } else { + err = dquot_reserve_block(inode, 1); + if (err) + return err; } if (time_to_inject(sbi, FAULT_BLOCK)) { @@ -1972,8 +1984,12 @@ static inline int inc_valid_node_count(struct f2fs_sb_info *sbi, return 0; enospc: - if (quota) + if (is_inode) { + if (inode) + dquot_free_inode(inode); + } else { dquot_release_reservation_block(inode, 1); + } return -ENOSPC; } @@ -1994,7 +2010,9 @@ static inline void dec_valid_node_count(struct f2fs_sb_info *sbi, spin_unlock(&sbi->stat_lock); - if (!is_inode) + if (is_inode) + dquot_free_inode(inode); + else f2fs_i_blocks_write(inode, 1, false, true); } @@ -2782,7 +2800,8 @@ static inline bool is_valid_data_blkaddr(struct f2fs_sb_info *sbi, */ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync); void f2fs_truncate_data_blocks(struct dnode_of_data *dn); -int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock); +int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock, + bool buf_write); int f2fs_truncate(struct inode *inode); int f2fs_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags); @@ -2870,6 +2889,7 @@ static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode) int f2fs_inode_dirtied(struct inode *inode, bool sync); void f2fs_inode_synced(struct inode *inode); int f2fs_enable_quota_files(struct f2fs_sb_info *sbi, bool rdonly); +int f2fs_quota_sync(struct super_block *sb, int type); void f2fs_quota_off_umount(struct super_block *sb); int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover); int f2fs_sync_fs(struct super_block *sb, int sync); @@ -3564,3 +3584,16 @@ extern void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate, #endif #endif + +static inline bool is_journalled_quota(struct f2fs_sb_info *sbi) +{ +#ifdef CONFIG_QUOTA + if (f2fs_sb_has_quota_ino(sbi->sb)) + return true; + if (F2FS_OPTION(sbi).s_qf_names[USRQUOTA] || + F2FS_OPTION(sbi).s_qf_names[GRPQUOTA] || + F2FS_OPTION(sbi).s_qf_names[PRJQUOTA]) + return true; +#endif + return false; +} diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 543c742f8bd7..971463e0589e 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -586,7 +586,8 @@ truncate_out: return 0; } -int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock) +int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock, + bool buf_write) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct dnode_of_data dn; @@ -594,6 +595,7 @@ int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock) int count = 0, err = 0; struct page *ipage; bool truncate_page = false; + int flag = buf_write ? F2FS_GET_BLOCK_PRE_AIO : F2FS_GET_BLOCK_PRE_DIO; trace_f2fs_truncate_blocks_enter(inode, from); @@ -603,7 +605,7 @@ int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock) goto free_partial; if (lock) - f2fs_lock_op(sbi); + __do_map_lock(sbi, flag, true); ipage = f2fs_get_node_page(sbi, inode->i_ino); if (IS_ERR(ipage)) { @@ -641,7 +643,7 @@ free_next: err = f2fs_truncate_inode_blocks(inode, free_from); out: if (lock) - f2fs_unlock_op(sbi); + __do_map_lock(sbi, flag, false); free_partial: /* lastly zero out the first data page */ if (!err) @@ -676,7 +678,7 @@ int f2fs_truncate(struct inode *inode) return err; } - err = f2fs_truncate_blocks(inode, i_size_read(inode), true); + err = f2fs_truncate_blocks(inode, i_size_read(inode), true, false); if (err) return err; @@ -785,9 +787,24 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) !uid_eq(attr->ia_uid, inode->i_uid)) || (attr->ia_valid & ATTR_GID && !gid_eq(attr->ia_gid, inode->i_gid))) { + f2fs_lock_op(F2FS_I_SB(inode)); err = dquot_transfer(inode, attr); - if (err) + if (err) { + set_sbi_flag(F2FS_I_SB(inode), + SBI_QUOTA_NEED_REPAIR); + f2fs_unlock_op(F2FS_I_SB(inode)); return err; + } + /* + * update uid/gid under lock_op(), so that dquot and inode can + * be updated atomically. + */ + if (attr->ia_valid & ATTR_UID) + inode->i_uid = attr->ia_uid; + if (attr->ia_valid & ATTR_GID) + inode->i_gid = attr->ia_gid; + f2fs_mark_inode_dirty_sync(inode, true); + f2fs_unlock_op(F2FS_I_SB(inode)); } if (attr->ia_valid & ATTR_SIZE) { @@ -1242,7 +1259,7 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len) new_size = i_size_read(inode) - len; truncate_pagecache(inode, new_size); - ret = f2fs_truncate_blocks(inode, new_size, true); + ret = f2fs_truncate_blocks(inode, new_size, true, false); up_write(&F2FS_I(inode)->i_mmap_sem); if (!ret) f2fs_i_size_write(inode, new_size); @@ -1427,7 +1444,7 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len) f2fs_balance_fs(sbi, true); down_write(&F2FS_I(inode)->i_mmap_sem); - ret = f2fs_truncate_blocks(inode, i_size_read(inode), true); + ret = f2fs_truncate_blocks(inode, i_size_read(inode), true, false); up_write(&F2FS_I(inode)->i_mmap_sem); if (ret) return ret; diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 425d740f87fd..cb31a719b048 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -298,7 +298,7 @@ process_inline: clear_inode_flag(inode, FI_INLINE_DATA); f2fs_put_page(ipage, 1); } else if (ri && (ri->i_inline & F2FS_INLINE_DATA)) { - if (f2fs_truncate_blocks(inode, 0, false)) + if (f2fs_truncate_blocks(inode, 0, false, false)) return false; goto process_inline; } @@ -470,7 +470,7 @@ static int f2fs_add_inline_entries(struct inode *dir, void *inline_dentry) return 0; punch_dentry_pages: truncate_inode_pages(&dir->i_data, 0); - f2fs_truncate_blocks(dir, 0, false); + f2fs_truncate_blocks(dir, 0, false, false); f2fs_remove_dirty_inode(dir); return err; } diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 57a7a15239d6..91ceee0ed4c4 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -654,7 +654,11 @@ void f2fs_evict_inode(struct inode *inode) if (inode->i_nlink || is_bad_inode(inode)) goto no_delete; - dquot_initialize(inode); + err = dquot_initialize(inode); + if (err) { + err = 0; + set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); + } f2fs_remove_ino_entry(sbi, inode->i_ino, APPEND_INO); f2fs_remove_ino_entry(sbi, inode->i_ino, UPDATE_INO); @@ -686,9 +690,10 @@ retry: goto retry; } - if (err) + if (err) { f2fs_update_inode_page(inode); - dquot_free_inode(inode); + set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); + } sb_end_intwrite(inode->i_sb); no_delete: dquot_drop(inode); diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 54295b5c1822..99299ede7429 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -72,10 +72,6 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) if (err) goto fail_drop; - err = dquot_alloc_inode(inode); - if (err) - goto fail_drop; - set_inode_flag(inode, FI_NEW_INODE); /* If the directory encrypted, then we should encrypt the inode. */ diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 875d2e205791..df2123759ac7 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -195,6 +195,33 @@ out: return err; } +static int recover_quota_data(struct inode *inode, struct page *page) +{ + struct f2fs_inode *raw = F2FS_INODE(page); + struct iattr attr; + uid_t i_uid = le32_to_cpu(raw->i_uid); + gid_t i_gid = le32_to_cpu(raw->i_gid); + int err; + + memset(&attr, 0, sizeof(attr)); + + attr.ia_uid = make_kuid(inode->i_sb->s_user_ns, i_uid); + attr.ia_gid = make_kgid(inode->i_sb->s_user_ns, i_gid); + + if (!uid_eq(attr.ia_uid, inode->i_uid)) + attr.ia_valid |= ATTR_UID; + if (!gid_eq(attr.ia_gid, inode->i_gid)) + attr.ia_valid |= ATTR_GID; + + if (!attr.ia_valid) + return 0; + + err = dquot_transfer(inode, &attr); + if (err) + set_sbi_flag(F2FS_I_SB(inode), SBI_QUOTA_NEED_REPAIR); + return err; +} + static void recover_inline_flags(struct inode *inode, struct f2fs_inode *ri) { if (ri->i_inline & F2FS_PIN_FILE) @@ -207,12 +234,18 @@ static void recover_inline_flags(struct inode *inode, struct f2fs_inode *ri) clear_inode_flag(inode, FI_DATA_EXIST); } -static void recover_inode(struct inode *inode, struct page *page) +static int recover_inode(struct inode *inode, struct page *page) { struct f2fs_inode *raw = F2FS_INODE(page); char *name; + int err; inode->i_mode = le16_to_cpu(raw->i_mode); + + err = recover_quota_data(inode, page); + if (err) + return err; + i_uid_write(inode, le32_to_cpu(raw->i_uid)); i_gid_write(inode, le32_to_cpu(raw->i_gid)); @@ -254,6 +287,7 @@ static void recover_inode(struct inode *inode, struct page *page) f2fs_msg(inode->i_sb, KERN_NOTICE, "recover_inode: ino = %x, name = %s, inline = %x", ino_of_node(page), name, raw->i_inline); + return 0; } static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head, @@ -622,8 +656,11 @@ static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list, * In this case, we can lose the latest inode(x). * So, call recover_inode for the inode update. */ - if (IS_INODE(page)) - recover_inode(entry->inode, page); + if (IS_INODE(page)) { + err = recover_inode(entry->inode, page); + if (err) + break; + } if (entry->last_dentry == blkaddr) { err = recover_dentry(entry->inode, page, dir_list); if (err) { diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index f7814bb26a13..af58b2cc21b8 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1711,6 +1711,7 @@ repeat: congestion_wait(BLK_RW_ASYNC, HZ/50); goto repeat; } + set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); return PTR_ERR(page); } @@ -1722,6 +1723,7 @@ repeat: } if (unlikely(!PageUptodate(page))) { f2fs_put_page(page, 1); + set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); return -EIO; } @@ -1763,6 +1765,7 @@ retry: congestion_wait(BLK_RW_ASYNC, HZ/50); goto retry; } + set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); break; } @@ -1799,6 +1802,12 @@ static qsize_t *f2fs_get_reserved_space(struct inode *inode) static int f2fs_quota_on_mount(struct f2fs_sb_info *sbi, int type) { + if (is_set_ckpt_flags(sbi, CP_QUOTA_NEED_FSCK_FLAG)) { + f2fs_msg(sbi->sb, KERN_ERR, + "quota sysfile may be corrupted, skip loading it"); + return 0; + } + return dquot_quota_on_mount(sbi->sb, F2FS_OPTION(sbi).s_qf_names[type], F2FS_OPTION(sbi).s_jquota_fmt, type); } @@ -1869,7 +1878,14 @@ static int f2fs_enable_quotas(struct super_block *sb) test_opt(F2FS_SB(sb), PRJQUOTA), }; - sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE | DQUOT_NOLIST_DIRTY; + if (is_set_ckpt_flags(F2FS_SB(sb), CP_QUOTA_NEED_FSCK_FLAG)) { + f2fs_msg(sb, KERN_ERR, + "quota file may be corrupted, skip loading it"); + return 0; + } + + sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE; + for (type = 0; type < MAXQUOTAS; type++) { qf_inum = f2fs_qf_ino(sb, type); if (qf_inum) { @@ -1883,6 +1899,8 @@ static int f2fs_enable_quotas(struct super_block *sb) "fsck to fix.", type, err); for (type--; type >= 0; type--) dquot_quota_off(sb, type); + set_sbi_flag(F2FS_SB(sb), + SBI_QUOTA_NEED_REPAIR); return err; } } @@ -1890,35 +1908,51 @@ static int f2fs_enable_quotas(struct super_block *sb) return 0; } -static int f2fs_quota_sync(struct super_block *sb, int type) +int f2fs_quota_sync(struct super_block *sb, int type) { + struct f2fs_sb_info *sbi = F2FS_SB(sb); struct quota_info *dqopt = sb_dqopt(sb); int cnt; int ret; ret = dquot_writeback_dquots(sb, type); if (ret) - return ret; + goto out; /* * Now when everything is written we can discard the pagecache so * that userspace sees the changes. */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { + struct address_space *mapping; + if (type != -1 && cnt != type) continue; if (!sb_has_quota_active(sb, cnt)) continue; - ret = filemap_write_and_wait(dqopt->files[cnt]->i_mapping); + mapping = dqopt->files[cnt]->i_mapping; + + ret = filemap_fdatawrite(mapping); if (ret) - return ret; + goto out; + + /* if we are using journalled quota */ + if (is_journalled_quota(sbi)) + continue; + + ret = filemap_fdatawait(mapping); + if (ret) + set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); inode_lock(dqopt->files[cnt]); truncate_inode_pages(&dqopt->files[cnt]->i_data, 0); inode_unlock(dqopt->files[cnt]); } - return 0; +out: + if (ret) + set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); + return ret; } static int f2fs_quota_on(struct super_block *sb, int type, int format_id, @@ -1986,7 +2020,7 @@ void f2fs_quota_off_umount(struct super_block *sb) "Fail to turn off disk quota " "(type: %d, err: %d, ret:%d), Please " "run fsck to fix it.", type, err, ret); - set_sbi_flag(F2FS_SB(sb), SBI_NEED_FSCK); + set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); } } } @@ -2003,6 +2037,61 @@ static void f2fs_truncate_quota_inode_pages(struct super_block *sb) } } +static int f2fs_dquot_commit(struct dquot *dquot) +{ + int ret; + + ret = dquot_commit(dquot); + if (ret < 0) + set_sbi_flag(F2FS_SB(dquot->dq_sb), SBI_QUOTA_NEED_REPAIR); + return ret; +} + +static int f2fs_dquot_acquire(struct dquot *dquot) +{ + int ret; + + ret = dquot_acquire(dquot); + if (ret < 0) + set_sbi_flag(F2FS_SB(dquot->dq_sb), SBI_QUOTA_NEED_REPAIR); + + return ret; +} + +static int f2fs_dquot_release(struct dquot *dquot) +{ + int ret; + + ret = dquot_release(dquot); + if (ret < 0) + set_sbi_flag(F2FS_SB(dquot->dq_sb), SBI_QUOTA_NEED_REPAIR); + return ret; +} + +static int f2fs_dquot_mark_dquot_dirty(struct dquot *dquot) +{ + struct super_block *sb = dquot->dq_sb; + struct f2fs_sb_info *sbi = F2FS_SB(sb); + int ret; + + ret = dquot_mark_dquot_dirty(dquot); + + /* if we are using journalled quota */ + if (is_journalled_quota(sbi)) + set_sbi_flag(sbi, SBI_QUOTA_NEED_FLUSH); + + return ret; +} + +static int f2fs_dquot_commit_info(struct super_block *sb, int type) +{ + int ret; + + ret = dquot_commit_info(sb, type); + if (ret < 0) + set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); + return ret; +} static int f2fs_get_projid(struct inode *inode, kprojid_t *projid) { @@ -2012,11 +2101,11 @@ static int f2fs_get_projid(struct inode *inode, kprojid_t *projid) static const struct dquot_operations f2fs_quota_operations = { .get_reserved_space = f2fs_get_reserved_space, - .write_dquot = dquot_commit, - .acquire_dquot = dquot_acquire, - .release_dquot = dquot_release, - .mark_dirty = dquot_mark_dquot_dirty, - .write_info = dquot_commit_info, + .write_dquot = f2fs_dquot_commit, + .acquire_dquot = f2fs_dquot_acquire, + .release_dquot = f2fs_dquot_release, + .mark_dirty = f2fs_dquot_mark_dquot_dirty, + .write_info = f2fs_dquot_commit_info, .alloc_dquot = dquot_alloc, .destroy_dquot = dquot_destroy, .get_projid = f2fs_get_projid, @@ -2034,6 +2123,11 @@ static const struct quotactl_ops f2fs_quotactl_ops = { .get_nextdqblk = dquot_get_next_dqblk, }; #else +int f2fs_quota_sync(struct super_block *sb, int type) +{ + return 0; +} + void f2fs_quota_off_umount(struct super_block *sb) { } @@ -3104,6 +3198,9 @@ try_onemore: goto free_meta_inode; } + if (__is_set_ckpt_flags(F2FS_CKPT(sbi), CP_QUOTA_NEED_FSCK_FLAG)) + set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); + /* Initialize device list */ err = f2fs_scan_devices(sbi); if (err) { diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 8b9c7dc0260c..d7711048ef93 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -117,6 +117,7 @@ struct f2fs_super_block { * For checkpoint */ #define CP_DISABLED_FLAG 0x00001000 +#define CP_QUOTA_NEED_FSCK_FLAG 0x00000800 #define CP_LARGE_NAT_BITMAP_FLAG 0x00000400 #define CP_NOCRC_RECOVERY_FLAG 0x00000200 #define CP_TRIMMED_FLAG 0x00000100 -- cgit v1.2.3 From 876dcf2f3aaa0f68d437b368b93a4c4b81521191 Mon Sep 17 00:00:00 2001 From: Olivier Brunel Date: Sat, 20 Oct 2018 19:39:56 +0200 Subject: umh: Add command line to user mode helpers User mode helpers were spawned without a command line, and because an empty command line is used by many tools to identify processes as kernel threads, this could cause some issues. Notably during killing spree on shutdown, since such helper would then be skipped (i.e. not killed) which would result in the process remaining alive, and thus preventing unmouting of the rootfs (as experienced with the bpfilter umh). Fixes: 449325b52b7a ("umh: introduce fork_usermode_blob() helper") Signed-off-by: Olivier Brunel Signed-off-by: David S. Miller --- include/linux/umh.h | 1 + kernel/umh.c | 16 ++++++++++++++-- 2 files changed, 15 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/umh.h b/include/linux/umh.h index 5c812acbb80a..235f51b62c71 100644 --- a/include/linux/umh.h +++ b/include/linux/umh.h @@ -44,6 +44,7 @@ struct subprocess_info *call_usermodehelper_setup_file(struct file *file, int (*init)(struct subprocess_info *info, struct cred *new), void (*cleanup)(struct subprocess_info *), void *data); struct umh_info { + const char *cmdline; struct file *pipe_to_umh; struct file *pipe_from_umh; pid_t pid; diff --git a/kernel/umh.c b/kernel/umh.c index c449858946af..0baa672e023c 100644 --- a/kernel/umh.c +++ b/kernel/umh.c @@ -405,11 +405,19 @@ struct subprocess_info *call_usermodehelper_setup_file(struct file *file, void (*cleanup)(struct subprocess_info *info), void *data) { struct subprocess_info *sub_info; + struct umh_info *info = data; + const char *cmdline = (info->cmdline) ? info->cmdline : "usermodehelper"; sub_info = kzalloc(sizeof(struct subprocess_info), GFP_KERNEL); if (!sub_info) return NULL; + sub_info->argv = argv_split(GFP_KERNEL, cmdline, NULL); + if (!sub_info->argv) { + kfree(sub_info); + return NULL; + } + INIT_WORK(&sub_info->work, call_usermodehelper_exec_work); sub_info->path = "none"; sub_info->file = file; @@ -458,10 +466,11 @@ static int umh_pipe_setup(struct subprocess_info *info, struct cred *new) return 0; } -static void umh_save_pid(struct subprocess_info *info) +static void umh_clean_and_save_pid(struct subprocess_info *info) { struct umh_info *umh_info = info->data; + argv_free(info->argv); umh_info->pid = info->pid; } @@ -471,6 +480,9 @@ static void umh_save_pid(struct subprocess_info *info) * @len: length of the blob * @info: information about usermode process (shouldn't be NULL) * + * If info->cmdline is set it will be used as command line for the + * user process, else "usermodehelper" is used. + * * Returns either negative error or zero which indicates success * in executing a blob of bytes as a usermode process. In such * case 'struct umh_info *info' is populated with two pipes @@ -500,7 +512,7 @@ int fork_usermode_blob(void *data, size_t len, struct umh_info *info) err = -ENOMEM; sub_info = call_usermodehelper_setup_file(file, umh_pipe_setup, - umh_save_pid, info); + umh_clean_and_save_pid, info); if (!sub_info) goto out; -- cgit v1.2.3 From 39b27ad9c71cb72b07c9cd85191a8fe723e5b21a Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 7 Aug 2018 18:11:22 +0200 Subject: mfd: sec-core: Add SPDX license identifiers Replace GPL v2.0+ license statements with SPDX license identifiers. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Lee Jones --- drivers/mfd/sec-core.c | 16 ++++------------ drivers/mfd/sec-irq.c | 16 ++++------------ include/linux/mfd/samsung/core.h | 11 ++--------- include/linux/mfd/samsung/irq.h | 10 ++-------- include/linux/mfd/samsung/rtc.h | 15 ++------------- include/linux/mfd/samsung/s2mpa01.h | 7 +------ include/linux/mfd/samsung/s2mps11.h | 9 +-------- include/linux/mfd/samsung/s2mps13.h | 14 +------------- include/linux/mfd/samsung/s2mps14.h | 14 +------------- include/linux/mfd/samsung/s2mps15.h | 11 +---------- include/linux/mfd/samsung/s2mpu02.h | 14 +------------- include/linux/mfd/samsung/s5m8763.h | 10 ++-------- include/linux/mfd/samsung/s5m8767.h | 10 ++-------- 13 files changed, 24 insertions(+), 133 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/sec-core.c b/drivers/mfd/sec-core.c index 9613b4257302..e0835c9df7a1 100644 --- a/drivers/mfd/sec-core.c +++ b/drivers/mfd/sec-core.c @@ -1,15 +1,7 @@ -/* - * sec-core.c - * - * Copyright (c) 2012 Samsung Electronics Co., Ltd - * http://www.samsung.com - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * - */ +// SPDX-License-Identifier: GPL-2.0+ +// +// Copyright (c) 2012 Samsung Electronics Co., Ltd +// http://www.samsung.com #include #include diff --git a/drivers/mfd/sec-irq.c b/drivers/mfd/sec-irq.c index 5eb59c233d52..295d24d4501d 100644 --- a/drivers/mfd/sec-irq.c +++ b/drivers/mfd/sec-irq.c @@ -1,15 +1,7 @@ -/* - * sec-irq.c - * - * Copyright (c) 2011-2014 Samsung Electronics Co., Ltd - * http://www.samsung.com - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * - */ +// SPDX-License-Identifier: GPL-2.0+ +// +// Copyright (c) 2011-2014 Samsung Electronics Co., Ltd +// http://www.samsung.com #include #include diff --git a/include/linux/mfd/samsung/core.h b/include/linux/mfd/samsung/core.h index 28f4ae76271d..3ca17eb89aa2 100644 --- a/include/linux/mfd/samsung/core.h +++ b/include/linux/mfd/samsung/core.h @@ -1,14 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* - * core.h - * - * copyright (c) 2011 Samsung Electronics Co., Ltd + * Copyright (c) 2011 Samsung Electronics Co., Ltd * http://www.samsung.com - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * */ #ifndef __LINUX_MFD_SEC_CORE_H diff --git a/include/linux/mfd/samsung/irq.h b/include/linux/mfd/samsung/irq.h index 667aa40486dd..6cfe4201a106 100644 --- a/include/linux/mfd/samsung/irq.h +++ b/include/linux/mfd/samsung/irq.h @@ -1,13 +1,7 @@ -/* irq.h - * +/* SPDX-License-Identifier: GPL-2.0+ */ +/* * Copyright (c) 2012 Samsung Electronics Co., Ltd * http://www.samsung.com - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * */ #ifndef __LINUX_MFD_SEC_IRQ_H diff --git a/include/linux/mfd/samsung/rtc.h b/include/linux/mfd/samsung/rtc.h index 9ed2871ea335..0204decfc9aa 100644 --- a/include/linux/mfd/samsung/rtc.h +++ b/include/linux/mfd/samsung/rtc.h @@ -1,18 +1,7 @@ -/* rtc.h - * +/* SPDX-License-Identifier: GPL-2.0+ */ +/* * Copyright (c) 2011-2014 Samsung Electronics Co., Ltd * http://www.samsung.com - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * */ #ifndef __LINUX_MFD_SEC_RTC_H diff --git a/include/linux/mfd/samsung/s2mpa01.h b/include/linux/mfd/samsung/s2mpa01.h index 2766108bca2f..0762e9de6f2f 100644 --- a/include/linux/mfd/samsung/s2mpa01.h +++ b/include/linux/mfd/samsung/s2mpa01.h @@ -1,12 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * Copyright (c) 2013 Samsung Electronics Co., Ltd * http://www.samsung.com - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * */ #ifndef __LINUX_MFD_S2MPA01_H diff --git a/include/linux/mfd/samsung/s2mps11.h b/include/linux/mfd/samsung/s2mps11.h index 2c14eeca46f0..6e7668a389a1 100644 --- a/include/linux/mfd/samsung/s2mps11.h +++ b/include/linux/mfd/samsung/s2mps11.h @@ -1,14 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* - * s2mps11.h - * * Copyright (c) 2012 Samsung Electronics Co., Ltd * http://www.samsung.com - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * */ #ifndef __LINUX_MFD_S2MPS11_H diff --git a/include/linux/mfd/samsung/s2mps13.h b/include/linux/mfd/samsung/s2mps13.h index 239e977ba45d..b96d8a11dcd3 100644 --- a/include/linux/mfd/samsung/s2mps13.h +++ b/include/linux/mfd/samsung/s2mps13.h @@ -1,19 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* - * s2mps13.h - * * Copyright (c) 2014 Samsung Electronics Co., Ltd * http://www.samsung.com - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * */ #ifndef __LINUX_MFD_S2MPS13_H diff --git a/include/linux/mfd/samsung/s2mps14.h b/include/linux/mfd/samsung/s2mps14.h index c92f4782afb5..f4afa0cfc24f 100644 --- a/include/linux/mfd/samsung/s2mps14.h +++ b/include/linux/mfd/samsung/s2mps14.h @@ -1,19 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* - * s2mps14.h - * * Copyright (c) 2014 Samsung Electronics Co., Ltd * http://www.samsung.com - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * */ #ifndef __LINUX_MFD_S2MPS14_H diff --git a/include/linux/mfd/samsung/s2mps15.h b/include/linux/mfd/samsung/s2mps15.h index 36d35287c3c0..eac6bf74b72e 100644 --- a/include/linux/mfd/samsung/s2mps15.h +++ b/include/linux/mfd/samsung/s2mps15.h @@ -1,16 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * Copyright (c) 2015 Samsung Electronics Co., Ltd * http://www.samsung.com - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #ifndef __LINUX_MFD_S2MPS15_H diff --git a/include/linux/mfd/samsung/s2mpu02.h b/include/linux/mfd/samsung/s2mpu02.h index 47ae9bc583a7..76cd5380cf0f 100644 --- a/include/linux/mfd/samsung/s2mpu02.h +++ b/include/linux/mfd/samsung/s2mpu02.h @@ -1,19 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* - * s2mpu02.h - * * Copyright (c) 2014 Samsung Electronics Co., Ltd * http://www.samsung.com - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * */ #ifndef __LINUX_MFD_S2MPU02_H diff --git a/include/linux/mfd/samsung/s5m8763.h b/include/linux/mfd/samsung/s5m8763.h index e025418e5589..c534f086ca16 100644 --- a/include/linux/mfd/samsung/s5m8763.h +++ b/include/linux/mfd/samsung/s5m8763.h @@ -1,13 +1,7 @@ -/* s5m8763.h - * +/* SPDX-License-Identifier: GPL-2.0+ */ +/* * Copyright (c) 2011 Samsung Electronics Co., Ltd * http://www.samsung.com - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * */ #ifndef __LINUX_MFD_S5M8763_H diff --git a/include/linux/mfd/samsung/s5m8767.h b/include/linux/mfd/samsung/s5m8767.h index 243b58fec33d..704f8d80e96e 100644 --- a/include/linux/mfd/samsung/s5m8767.h +++ b/include/linux/mfd/samsung/s5m8767.h @@ -1,13 +1,7 @@ -/* s5m8767.h - * +/* SPDX-License-Identifier: GPL-2.0+ */ +/* * Copyright (c) 2011 Samsung Electronics Co., Ltd * http://www.samsung.com - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * */ #ifndef __LINUX_MFD_S5M8767_H -- cgit v1.2.3 From d7d8d7a2405f8b6296660648e893fc3442269d81 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 7 Aug 2018 18:11:23 +0200 Subject: mfd: maxim: Add SPDX license identifiers Replace GPL v2.0+ license statements with SPDX license identifiers. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Lee Jones --- drivers/mfd/max14577.c | 28 +++++++++------------------- drivers/mfd/max77686.c | 32 +++++++++----------------------- drivers/mfd/max77693.c | 34 ++++++++++------------------------ drivers/mfd/max77843.c | 19 +++++++------------ drivers/mfd/max8997-irq.c | 30 ++++++++---------------------- drivers/mfd/max8997.c | 30 ++++++++---------------------- drivers/mfd/max8998-irq.c | 18 ++++++------------ drivers/mfd/max8998.c | 28 +++++++--------------------- include/linux/mfd/max14577-private.h | 11 +---------- include/linux/mfd/max14577.h | 11 +---------- include/linux/mfd/max77686-private.h | 15 +-------------- include/linux/mfd/max77686.h | 15 +-------------- include/linux/mfd/max77693-common.h | 6 +----- include/linux/mfd/max77693-private.h | 15 +-------------- include/linux/mfd/max77693.h | 15 +-------------- include/linux/mfd/max77843-private.h | 6 +----- include/linux/mfd/max8997-private.h | 15 +-------------- include/linux/mfd/max8997.h | 15 +-------------- include/linux/mfd/max8998-private.h | 15 +-------------- include/linux/mfd/max8998.h | 15 +-------------- 20 files changed, 76 insertions(+), 297 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/max14577.c b/drivers/mfd/max14577.c index 6cbe96b28f42..ebb13d5de530 100644 --- a/drivers/mfd/max14577.c +++ b/drivers/mfd/max14577.c @@ -1,22 +1,12 @@ -/* - * max14577.c - mfd core driver for the Maxim 14577/77836 - * - * Copyright (C) 2014 Samsung Electronics - * Chanwoo Choi - * Krzysztof Kozlowski - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * This driver is based on max8997.c - */ +// SPDX-License-Identifier: GPL-2.0+ +// +// max14577.c - mfd core driver for the Maxim 14577/77836 +// +// Copyright (C) 2014 Samsung Electronics +// Chanwoo Choi +// Krzysztof Kozlowski +// +// This driver is based on max8997.c #include #include diff --git a/drivers/mfd/max77686.c b/drivers/mfd/max77686.c index b0e8e13c0049..71faf503844b 100644 --- a/drivers/mfd/max77686.c +++ b/drivers/mfd/max77686.c @@ -1,26 +1,12 @@ -/* - * max77686.c - mfd core driver for the Maxim 77686/802 - * - * Copyright (C) 2012 Samsung Electronics - * Chiwoong Byun - * Jonghwa Lee - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * - * This driver is based on max8997.c - */ +// SPDX-License-Identifier: GPL-2.0+ +// +// max77686.c - mfd core driver for the Maxim 77686/802 +// +// Copyright (C) 2012 Samsung Electronics +// Chiwoong Byun +// Jonghwa Lee +// +//This driver is based on max8997.c #include #include diff --git a/drivers/mfd/max77693.c b/drivers/mfd/max77693.c index 1c05ea0cba61..901d99d65924 100644 --- a/drivers/mfd/max77693.c +++ b/drivers/mfd/max77693.c @@ -1,27 +1,13 @@ -/* - * max77693.c - mfd core driver for the MAX 77693 - * - * Copyright (C) 2012 Samsung Electronics - * SangYoung Son - * - * This program is not provided / owned by Maxim Integrated Products. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * - * This driver is based on max8997.c - */ +// SPDX-License-Identifier: GPL-2.0+ +// +// max77693.c - mfd core driver for the MAX 77693 +// +// Copyright (C) 2012 Samsung Electronics +// SangYoung Son +// +// This program is not provided / owned by Maxim Integrated Products. +// +// This driver is based on max8997.c #include #include diff --git a/drivers/mfd/max77843.c b/drivers/mfd/max77843.c index da9612dbb222..25cbb2242b26 100644 --- a/drivers/mfd/max77843.c +++ b/drivers/mfd/max77843.c @@ -1,15 +1,10 @@ -/* - * MFD core driver for the Maxim MAX77843 - * - * Copyright (C) 2015 Samsung Electronics - * Author: Jaewon Kim - * Author: Beomho Seo - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ +// SPDX-License-Identifier: GPL-2.0+ +// +// MFD core driver for the Maxim MAX77843 +// +// Copyright (C) 2015 Samsung Electronics +// Author: Jaewon Kim +// Author: Beomho Seo #include #include diff --git a/drivers/mfd/max8997-irq.c b/drivers/mfd/max8997-irq.c index 326f17b632a7..93a3b1698d9c 100644 --- a/drivers/mfd/max8997-irq.c +++ b/drivers/mfd/max8997-irq.c @@ -1,25 +1,11 @@ -/* - * max8997-irq.c - Interrupt controller support for MAX8997 - * - * Copyright (C) 2011 Samsung Electronics Co.Ltd - * MyungJoo Ham - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * - * This driver is based on max8998-irq.c - */ +// SPDX-License-Identifier: GPL-2.0+ +// +// max8997-irq.c - Interrupt controller support for MAX8997 +// +// Copyright (C) 2011 Samsung Electronics Co.Ltd +// MyungJoo Ham +// +// This driver is based on max8998-irq.c #include #include diff --git a/drivers/mfd/max8997.c b/drivers/mfd/max8997.c index 3f554c447521..8dbae31911a1 100644 --- a/drivers/mfd/max8997.c +++ b/drivers/mfd/max8997.c @@ -1,25 +1,11 @@ -/* - * max8997.c - mfd core driver for the Maxim 8966 and 8997 - * - * Copyright (C) 2011 Samsung Electronics - * MyungJoo Ham - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * - * This driver is based on max8998.c - */ +// SPDX-License-Identifier: GPL-2.0+ +// +// max8997.c - mfd core driver for the Maxim 8966 and 8997 +// +// Copyright (C) 2011 Samsung Electronics +// MyungJoo Ham +// +// This driver is based on max8998.c #include #include diff --git a/drivers/mfd/max8998-irq.c b/drivers/mfd/max8998-irq.c index 90bad9ffa7e2..83b6f510bc05 100644 --- a/drivers/mfd/max8998-irq.c +++ b/drivers/mfd/max8998-irq.c @@ -1,15 +1,9 @@ -/* - * Interrupt controller support for MAX8998 - * - * Copyright (C) 2010 Samsung Electronics Co.Ltd - * Author: Joonyoung Shim - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * - */ +// SPDX-License-Identifier: GPL-2.0+ +// +// Interrupt controller support for MAX8998 +// +// Copyright (C) 2010 Samsung Electronics Co.Ltd +// Author: Joonyoung Shim #include #include diff --git a/drivers/mfd/max8998.c b/drivers/mfd/max8998.c index b1d3f70782d9..56409df120f8 100644 --- a/drivers/mfd/max8998.c +++ b/drivers/mfd/max8998.c @@ -1,24 +1,10 @@ -/* - * max8998.c - mfd core driver for the Maxim 8998 - * - * Copyright (C) 2009-2010 Samsung Electronics - * Kyungmin Park - * Marek Szyprowski - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ +// SPDX-License-Identifier: GPL-2.0+ +// +// max8998.c - mfd core driver for the Maxim 8998 +// +// Copyright (C) 2009-2010 Samsung Electronics +// Kyungmin Park +// Marek Szyprowski #include #include diff --git a/include/linux/mfd/max14577-private.h b/include/linux/mfd/max14577-private.h index df75234f979d..a21374f8ad26 100644 --- a/include/linux/mfd/max14577-private.h +++ b/include/linux/mfd/max14577-private.h @@ -1,19 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * max14577-private.h - Common API for the Maxim 14577/77836 internal sub chip * * Copyright (C) 2014 Samsung Electrnoics * Chanwoo Choi * Krzysztof Kozlowski - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #ifndef __MAX14577_PRIVATE_H__ diff --git a/include/linux/mfd/max14577.h b/include/linux/mfd/max14577.h index d81b52bb8bee..8b3ef891ba42 100644 --- a/include/linux/mfd/max14577.h +++ b/include/linux/mfd/max14577.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * max14577.h - Driver for the Maxim 14577/77836 * @@ -5,16 +6,6 @@ * Chanwoo Choi * Krzysztof Kozlowski * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * This driver is based on max8997.h * * MAX14577 has MUIC, Charger devices. diff --git a/include/linux/mfd/max77686-private.h b/include/linux/mfd/max77686-private.h index 643dae777b43..833e578e051e 100644 --- a/include/linux/mfd/max77686-private.h +++ b/include/linux/mfd/max77686-private.h @@ -1,22 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * max77686-private.h - Voltage regulator driver for the Maxim 77686/802 * * Copyright (C) 2012 Samsung Electrnoics * Chiwoong Byun - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef __LINUX_MFD_MAX77686_PRIV_H diff --git a/include/linux/mfd/max77686.h b/include/linux/mfd/max77686.h index d4b72d519115..d0fb510875e6 100644 --- a/include/linux/mfd/max77686.h +++ b/include/linux/mfd/max77686.h @@ -1,23 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * max77686.h - Driver for the Maxim 77686/802 * * Copyright (C) 2012 Samsung Electrnoics * Chiwoong Byun * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * * This driver is based on max8997.h * * MAX77686 has PMIC, RTC devices. diff --git a/include/linux/mfd/max77693-common.h b/include/linux/mfd/max77693-common.h index 095b121aa725..a5bce099f1ed 100644 --- a/include/linux/mfd/max77693-common.h +++ b/include/linux/mfd/max77693-common.h @@ -1,12 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * Common data shared between Maxim 77693 and 77843 drivers * * Copyright (C) 2015 Samsung Electronics - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. */ #ifndef __LINUX_MFD_MAX77693_COMMON_H diff --git a/include/linux/mfd/max77693-private.h b/include/linux/mfd/max77693-private.h index 3c7a63b98ad6..e798c81aec31 100644 --- a/include/linux/mfd/max77693-private.h +++ b/include/linux/mfd/max77693-private.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * max77693-private.h - Voltage regulator driver for the Maxim 77693 * @@ -5,20 +6,6 @@ * SangYoung Son * * This program is not provided / owned by Maxim Integrated Products. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef __LINUX_MFD_MAX77693_PRIV_H diff --git a/include/linux/mfd/max77693.h b/include/linux/mfd/max77693.h index d450f687301b..c67c16ba8649 100644 --- a/include/linux/mfd/max77693.h +++ b/include/linux/mfd/max77693.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * max77693.h - Driver for the Maxim 77693 * @@ -6,20 +7,6 @@ * * This program is not provided / owned by Maxim Integrated Products. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * * This driver is based on max8997.h * * MAX77693 has PMIC, Charger, Flash LED, Haptic, MUIC devices. diff --git a/include/linux/mfd/max77843-private.h b/include/linux/mfd/max77843-private.h index b8908bf8d315..0bc7454c4dbe 100644 --- a/include/linux/mfd/max77843-private.h +++ b/include/linux/mfd/max77843-private.h @@ -1,14 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * Common variables for the Maxim MAX77843 driver * * Copyright (C) 2015 Samsung Electronics * Author: Jaewon Kim * Author: Beomho Seo - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. */ #ifndef __MAX77843_PRIVATE_H_ diff --git a/include/linux/mfd/max8997-private.h b/include/linux/mfd/max8997-private.h index 78c76cd4d37b..a10cd6945232 100644 --- a/include/linux/mfd/max8997-private.h +++ b/include/linux/mfd/max8997-private.h @@ -1,22 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * max8997-private.h - Voltage regulator driver for the Maxim 8997 * * Copyright (C) 2010 Samsung Electrnoics * MyungJoo Ham - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef __LINUX_MFD_MAX8997_PRIV_H diff --git a/include/linux/mfd/max8997.h b/include/linux/mfd/max8997.h index cf815577bd68..3c4e920b4727 100644 --- a/include/linux/mfd/max8997.h +++ b/include/linux/mfd/max8997.h @@ -1,23 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * max8997.h - Driver for the Maxim 8997/8966 * * Copyright (C) 2009-2010 Samsung Electrnoics * MyungJoo Ham * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * * This driver is based on max8998.h * * MAX8997 has PMIC, MUIC, HAPTIC, RTC, FLASH, and Fuel Gauge devices. diff --git a/include/linux/mfd/max8998-private.h b/include/linux/mfd/max8998-private.h index d68ada502ff3..6deb5f577602 100644 --- a/include/linux/mfd/max8998-private.h +++ b/include/linux/mfd/max8998-private.h @@ -1,23 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * max8998-private.h - Voltage regulator driver for the Maxim 8998 * * Copyright (C) 2009-2010 Samsung Electrnoics * Kyungmin Park * Marek Szyprowski - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef __LINUX_MFD_MAX8998_PRIV_H diff --git a/include/linux/mfd/max8998.h b/include/linux/mfd/max8998.h index e3956a654cbc..061af220dcd3 100644 --- a/include/linux/mfd/max8998.h +++ b/include/linux/mfd/max8998.h @@ -1,23 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * max8998.h - Voltage regulator driver for the Maxim 8998 * * Copyright (C) 2009-2010 Samsung Electrnoics * Kyungmin Park * Marek Szyprowski - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef __LINUX_MFD_MAX8998_H -- cgit v1.2.3 From 3d51ec93a564a0f87d1276f067732be904816a53 Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Tue, 21 Aug 2018 19:16:12 +0200 Subject: mfd: Add ingenic-tcu.h header This header contains macros for the registers that are present in the regmap shared by all the drivers related to the TCU (Timer Counter Unit) of the Ingenic JZ47xx SoCs. Signed-off-by: Paul Cercueil Signed-off-by: Lee Jones --- include/linux/mfd/ingenic-tcu.h | 56 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 56 insertions(+) create mode 100644 include/linux/mfd/ingenic-tcu.h (limited to 'include/linux') diff --git a/include/linux/mfd/ingenic-tcu.h b/include/linux/mfd/ingenic-tcu.h new file mode 100644 index 000000000000..ab16ad283def --- /dev/null +++ b/include/linux/mfd/ingenic-tcu.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Header file for the Ingenic JZ47xx TCU driver + */ +#ifndef __LINUX_MFD_INGENIC_TCU_H_ +#define __LINUX_MFD_INGENIC_TCU_H_ + +#include + +#define TCU_REG_WDT_TDR 0x00 +#define TCU_REG_WDT_TCER 0x04 +#define TCU_REG_WDT_TCNT 0x08 +#define TCU_REG_WDT_TCSR 0x0c +#define TCU_REG_TER 0x10 +#define TCU_REG_TESR 0x14 +#define TCU_REG_TECR 0x18 +#define TCU_REG_TSR 0x1c +#define TCU_REG_TFR 0x20 +#define TCU_REG_TFSR 0x24 +#define TCU_REG_TFCR 0x28 +#define TCU_REG_TSSR 0x2c +#define TCU_REG_TMR 0x30 +#define TCU_REG_TMSR 0x34 +#define TCU_REG_TMCR 0x38 +#define TCU_REG_TSCR 0x3c +#define TCU_REG_TDFR0 0x40 +#define TCU_REG_TDHR0 0x44 +#define TCU_REG_TCNT0 0x48 +#define TCU_REG_TCSR0 0x4c +#define TCU_REG_OST_DR 0xe0 +#define TCU_REG_OST_CNTL 0xe4 +#define TCU_REG_OST_CNTH 0xe8 +#define TCU_REG_OST_TCSR 0xec +#define TCU_REG_TSTR 0xf0 +#define TCU_REG_TSTSR 0xf4 +#define TCU_REG_TSTCR 0xf8 +#define TCU_REG_OST_CNTHBUF 0xfc + +#define TCU_TCSR_RESERVED_BITS 0x3f +#define TCU_TCSR_PARENT_CLOCK_MASK 0x07 +#define TCU_TCSR_PRESCALE_LSB 3 +#define TCU_TCSR_PRESCALE_MASK 0x38 + +#define TCU_TCSR_PWM_SD BIT(9) /* 0: Shutdown abruptly 1: gracefully */ +#define TCU_TCSR_PWM_INITL_HIGH BIT(8) /* Sets the initial output level */ +#define TCU_TCSR_PWM_EN BIT(7) /* PWM pin output enable */ + +#define TCU_WDT_TCER_TCEN BIT(0) /* Watchdog timer enable */ + +#define TCU_CHANNEL_STRIDE 0x10 +#define TCU_REG_TDFRc(c) (TCU_REG_TDFR0 + ((c) * TCU_CHANNEL_STRIDE)) +#define TCU_REG_TDHRc(c) (TCU_REG_TDHR0 + ((c) * TCU_CHANNEL_STRIDE)) +#define TCU_REG_TCNTc(c) (TCU_REG_TCNT0 + ((c) * TCU_CHANNEL_STRIDE)) +#define TCU_REG_TCSRc(c) (TCU_REG_TCSR0 + ((c) * TCU_CHANNEL_STRIDE)) + +#endif /* __LINUX_MFD_INGENIC_TCU_H_ */ -- cgit v1.2.3 From 6360e40f421fba0a11bbabaa211c9c22c5cf5e61 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Tue, 28 Aug 2018 09:41:58 +0100 Subject: mfd: madera: Remove unused forward reference The madera_irqchip_pdata struct was replaced by the irq_flags member of struct madera_pdata so the forward reference is obsolete. Signed-off-by: Richard Fitzgerald Signed-off-by: Lee Jones --- include/linux/mfd/madera/pdata.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/madera/pdata.h b/include/linux/mfd/madera/pdata.h index 0b311f39c8f4..8dc852402dbb 100644 --- a/include/linux/mfd/madera/pdata.h +++ b/include/linux/mfd/madera/pdata.h @@ -24,7 +24,6 @@ struct gpio_desc; struct pinctrl_map; -struct madera_irqchip_pdata; struct madera_codec_pdata; /** -- cgit v1.2.3 From 55143439b7b501882bea9d95a54adfe00ffc79a3 Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Tue, 28 Aug 2018 17:02:40 -0300 Subject: mfd: mc13xxx-core: Fix PMIC shutdown when reading ADC values When trying to read any MC13892 ADC channel on a imx51-babbage board: The MC13892 PMIC shutdowns completely. After debugging this issue and comparing the MC13892 and MC13783 initializations done in the vendor kernel, it was noticed that the CHRGRAWDIV bit of the ADC0 register was not being set. This bit is set by default after power on, but the driver was clearing it. After setting this bit it is possible to read the ADC values correctly. Signed-off-by: Fabio Estevam Tested-by: Chris Healy Signed-off-by: Lee Jones --- drivers/mfd/mc13xxx-core.c | 3 ++- include/linux/mfd/mc13xxx.h | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/mfd/mc13xxx-core.c b/drivers/mfd/mc13xxx-core.c index c63e331738c1..f475e848252f 100644 --- a/drivers/mfd/mc13xxx-core.c +++ b/drivers/mfd/mc13xxx-core.c @@ -276,7 +276,8 @@ int mc13xxx_adc_do_conversion(struct mc13xxx *mc13xxx, unsigned int mode, mc13xxx_reg_read(mc13xxx, MC13XXX_ADC0, &old_adc0); - adc0 = MC13XXX_ADC0_ADINC1 | MC13XXX_ADC0_ADINC2; + adc0 = MC13XXX_ADC0_ADINC1 | MC13XXX_ADC0_ADINC2 | + MC13XXX_ADC0_CHRGRAWDIV; adc1 = MC13XXX_ADC1_ADEN | MC13XXX_ADC1_ADTRIGIGN | MC13XXX_ADC1_ASC; /* diff --git a/include/linux/mfd/mc13xxx.h b/include/linux/mfd/mc13xxx.h index 54a3cd808f9e..2ad9bdc0a5ec 100644 --- a/include/linux/mfd/mc13xxx.h +++ b/include/linux/mfd/mc13xxx.h @@ -249,6 +249,7 @@ struct mc13xxx_platform_data { #define MC13XXX_ADC0_TSMOD0 (1 << 12) #define MC13XXX_ADC0_TSMOD1 (1 << 13) #define MC13XXX_ADC0_TSMOD2 (1 << 14) +#define MC13XXX_ADC0_CHRGRAWDIV (1 << 15) #define MC13XXX_ADC0_ADINC1 (1 << 16) #define MC13XXX_ADC0_ADINC2 (1 << 17) -- cgit v1.2.3 From 9f8ddee1dab836ca758ca8fc555ab5a3aaa5d3fd Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 30 Aug 2018 19:52:52 +0300 Subject: mfd: intel_soc_pmic_bxtwc: Chain power button IRQs as well Power button IRQ actually has a second level of interrupts to distinguish between UI and POWER buttons. Moreover, current implementation looks awkward in approach to handle second level IRQs by first level related IRQ chip. To address above issues, split power button IRQ to be chained as well. Signed-off-by: Andy Shevchenko Reviewed-by: Mika Westerberg Signed-off-by: Lee Jones --- drivers/mfd/intel_soc_pmic_bxtwc.c | 41 ++++++++++++++++++++++++++++---------- include/linux/mfd/intel_soc_pmic.h | 1 + 2 files changed, 32 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/intel_soc_pmic_bxtwc.c b/drivers/mfd/intel_soc_pmic_bxtwc.c index 15bc052704a6..9ca1f8c015de 100644 --- a/drivers/mfd/intel_soc_pmic_bxtwc.c +++ b/drivers/mfd/intel_soc_pmic_bxtwc.c @@ -31,8 +31,8 @@ /* Interrupt Status Registers */ #define BXTWC_IRQLVL1 0x4E02 -#define BXTWC_PWRBTNIRQ 0x4E03 +#define BXTWC_PWRBTNIRQ 0x4E03 #define BXTWC_THRM0IRQ 0x4E04 #define BXTWC_THRM1IRQ 0x4E05 #define BXTWC_THRM2IRQ 0x4E06 @@ -47,10 +47,9 @@ /* Interrupt MASK Registers */ #define BXTWC_MIRQLVL1 0x4E0E -#define BXTWC_MPWRTNIRQ 0x4E0F - #define BXTWC_MIRQLVL1_MCHGR BIT(5) +#define BXTWC_MPWRBTNIRQ 0x4E0F #define BXTWC_MTHRM0IRQ 0x4E12 #define BXTWC_MTHRM1IRQ 0x4E13 #define BXTWC_MTHRM2IRQ 0x4E14 @@ -66,9 +65,7 @@ /* Whiskey Cove PMIC share same ACPI ID between different platforms */ #define BROXTON_PMIC_WC_HRV 4 -/* Manage in two IRQ chips since mask registers are not consecutive */ enum bxtwc_irqs { - /* Level 1 */ BXTWC_PWRBTN_LVL1_IRQ = 0, BXTWC_TMU_LVL1_IRQ, BXTWC_THRM_LVL1_IRQ, @@ -77,9 +74,11 @@ enum bxtwc_irqs { BXTWC_CHGR_LVL1_IRQ, BXTWC_GPIO_LVL1_IRQ, BXTWC_CRIT_LVL1_IRQ, +}; - /* Level 2 */ - BXTWC_PWRBTN_IRQ, +enum bxtwc_irqs_pwrbtn { + BXTWC_PWRBTN_IRQ = 0, + BXTWC_UIBTN_IRQ, }; enum bxtwc_irqs_bcu { @@ -113,7 +112,10 @@ static const struct regmap_irq bxtwc_regmap_irqs[] = { REGMAP_IRQ_REG(BXTWC_CHGR_LVL1_IRQ, 0, BIT(5)), REGMAP_IRQ_REG(BXTWC_GPIO_LVL1_IRQ, 0, BIT(6)), REGMAP_IRQ_REG(BXTWC_CRIT_LVL1_IRQ, 0, BIT(7)), - REGMAP_IRQ_REG(BXTWC_PWRBTN_IRQ, 1, 0x03), +}; + +static const struct regmap_irq bxtwc_regmap_irqs_pwrbtn[] = { + REGMAP_IRQ_REG(BXTWC_PWRBTN_IRQ, 0, 0x01), }; static const struct regmap_irq bxtwc_regmap_irqs_bcu[] = { @@ -125,7 +127,7 @@ static const struct regmap_irq bxtwc_regmap_irqs_adc[] = { }; static const struct regmap_irq bxtwc_regmap_irqs_chgr[] = { - REGMAP_IRQ_REG(BXTWC_USBC_IRQ, 0, BIT(5)), + REGMAP_IRQ_REG(BXTWC_USBC_IRQ, 0, 0x20), REGMAP_IRQ_REG(BXTWC_CHGR0_IRQ, 0, 0x1f), REGMAP_IRQ_REG(BXTWC_CHGR1_IRQ, 1, 0x1f), }; @@ -144,7 +146,16 @@ static struct regmap_irq_chip bxtwc_regmap_irq_chip = { .mask_base = BXTWC_MIRQLVL1, .irqs = bxtwc_regmap_irqs, .num_irqs = ARRAY_SIZE(bxtwc_regmap_irqs), - .num_regs = 2, + .num_regs = 1, +}; + +static struct regmap_irq_chip bxtwc_regmap_irq_chip_pwrbtn = { + .name = "bxtwc_irq_chip_pwrbtn", + .status_base = BXTWC_PWRBTNIRQ, + .mask_base = BXTWC_MPWRBTNIRQ, + .irqs = bxtwc_regmap_irqs_pwrbtn, + .num_irqs = ARRAY_SIZE(bxtwc_regmap_irqs_pwrbtn), + .num_regs = 1, }; static struct regmap_irq_chip bxtwc_regmap_irq_chip_tmu = { @@ -472,6 +483,16 @@ static int bxtwc_probe(struct platform_device *pdev) return ret; } + ret = bxtwc_add_chained_irq_chip(pmic, pmic->irq_chip_data, + BXTWC_PWRBTN_LVL1_IRQ, + IRQF_ONESHOT, + &bxtwc_regmap_irq_chip_pwrbtn, + &pmic->irq_chip_data_pwrbtn); + if (ret) { + dev_err(&pdev->dev, "Failed to add PWRBTN IRQ chip\n"); + return ret; + } + ret = bxtwc_add_chained_irq_chip(pmic, pmic->irq_chip_data, BXTWC_TMU_LVL1_IRQ, IRQF_ONESHOT, diff --git a/include/linux/mfd/intel_soc_pmic.h b/include/linux/mfd/intel_soc_pmic.h index 5aacdb017a9f..806a4f095312 100644 --- a/include/linux/mfd/intel_soc_pmic.h +++ b/include/linux/mfd/intel_soc_pmic.h @@ -25,6 +25,7 @@ struct intel_soc_pmic { int irq; struct regmap *regmap; struct regmap_irq_chip_data *irq_chip_data; + struct regmap_irq_chip_data *irq_chip_data_pwrbtn; struct regmap_irq_chip_data *irq_chip_data_tmu; struct regmap_irq_chip_data *irq_chip_data_bcu; struct regmap_irq_chip_data *irq_chip_data_adc; -- cgit v1.2.3 From 26c7e05a69d3843abb0e5389e7f538cd175c0f09 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 30 Aug 2018 19:52:54 +0300 Subject: mfd: Convert Intel PMIC drivers to use SPDX identifier 1;5201;0c Reduce size of duplicated comments by switching to use SPDX identifier. No functional change. Signed-off-by: Andy Shevchenko Reviewed-by: Mika Westerberg Signed-off-by: Lee Jones --- drivers/mfd/intel_msic.c | 5 +---- drivers/mfd/intel_soc_pmic_bxtwc.c | 10 +--------- drivers/mfd/intel_soc_pmic_chtdc_ti.c | 5 +---- drivers/mfd/intel_soc_pmic_chtwc.c | 5 +---- drivers/mfd/intel_soc_pmic_core.c | 12 ++---------- drivers/mfd/intel_soc_pmic_core.h | 12 ++---------- drivers/mfd/intel_soc_pmic_crc.c | 12 ++---------- include/linux/mfd/intel_msic.h | 7 ++----- include/linux/mfd/intel_soc_pmic.h | 12 ++---------- include/linux/mfd/intel_soc_pmic_bxtwc.h | 10 +--------- 10 files changed, 15 insertions(+), 75 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/intel_msic.c b/drivers/mfd/intel_msic.c index 441de7b3d231..bb24c2a07900 100644 --- a/drivers/mfd/intel_msic.c +++ b/drivers/mfd/intel_msic.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Driver for Intel MSIC * * Copyright (C) 2011, Intel Corporation * Author: Mika Westerberg - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include diff --git a/drivers/mfd/intel_soc_pmic_bxtwc.c b/drivers/mfd/intel_soc_pmic_bxtwc.c index c878724497a9..6310c3bdb991 100644 --- a/drivers/mfd/intel_soc_pmic_bxtwc.c +++ b/drivers/mfd/intel_soc_pmic_bxtwc.c @@ -1,16 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 /* * MFD core driver for Intel Broxton Whiskey Cove PMIC * * Copyright (C) 2015 Intel 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. */ #include diff --git a/drivers/mfd/intel_soc_pmic_chtdc_ti.c b/drivers/mfd/intel_soc_pmic_chtdc_ti.c index 861277c6580a..64b5c3cc30e7 100644 --- a/drivers/mfd/intel_soc_pmic_chtdc_ti.c +++ b/drivers/mfd/intel_soc_pmic_chtdc_ti.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Device access for Dollar Cove TI PMIC * @@ -6,10 +7,6 @@ * * Cleanup and forward-ported * Copyright (c) 2017 Takashi Iwai - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include diff --git a/drivers/mfd/intel_soc_pmic_chtwc.c b/drivers/mfd/intel_soc_pmic_chtwc.c index b35da01d5bcf..64a3aece9c5e 100644 --- a/drivers/mfd/intel_soc_pmic_chtwc.c +++ b/drivers/mfd/intel_soc_pmic_chtwc.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * MFD core driver for Intel Cherrytrail Whiskey Cove PMIC * @@ -5,10 +6,6 @@ * * Based on various non upstream patches to support the CHT Whiskey Cove PMIC: * Copyright (C) 2013-2015 Intel Corporation. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include diff --git a/drivers/mfd/intel_soc_pmic_core.c b/drivers/mfd/intel_soc_pmic_core.c index 170d5ed16a3b..c9f35378d391 100644 --- a/drivers/mfd/intel_soc_pmic_core.c +++ b/drivers/mfd/intel_soc_pmic_core.c @@ -1,17 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * intel_soc_pmic_core.c - Intel SoC PMIC MFD Driver + * Intel SoC PMIC MFD Driver * * Copyright (C) 2013, 2014 Intel Corporation. All rights reserved. * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version - * 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Author: Yang, Bin * Author: Zhu, Lejun */ diff --git a/drivers/mfd/intel_soc_pmic_core.h b/drivers/mfd/intel_soc_pmic_core.h index 90a1416d4dac..d490685845eb 100644 --- a/drivers/mfd/intel_soc_pmic_core.h +++ b/drivers/mfd/intel_soc_pmic_core.h @@ -1,17 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* - * intel_soc_pmic_core.h - Intel SoC PMIC MFD Driver + * Intel SoC PMIC MFD Driver * * Copyright (C) 2012-2014 Intel Corporation. All rights reserved. * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version - * 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Author: Yang, Bin * Author: Zhu, Lejun */ diff --git a/drivers/mfd/intel_soc_pmic_crc.c b/drivers/mfd/intel_soc_pmic_crc.c index 5ac6f3710294..b6ab72fa0569 100644 --- a/drivers/mfd/intel_soc_pmic_crc.c +++ b/drivers/mfd/intel_soc_pmic_crc.c @@ -1,17 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * intel_soc_pmic_crc.c - Device access for Crystal Cove PMIC + * Device access for Crystal Cove PMIC * * Copyright (C) 2013, 2014 Intel Corporation. All rights reserved. * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version - * 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Author: Yang, Bin * Author: Zhu, Lejun */ diff --git a/include/linux/mfd/intel_msic.h b/include/linux/mfd/intel_msic.h index 439a7a617bc9..317e8608cf41 100644 --- a/include/linux/mfd/intel_msic.h +++ b/include/linux/mfd/intel_msic.h @@ -1,12 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* - * include/linux/mfd/intel_msic.h - Core interface for Intel MSIC + * Core interface for Intel MSIC * * Copyright (C) 2011, Intel Corporation * Author: Mika Westerberg - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef __LINUX_MFD_INTEL_MSIC_H__ diff --git a/include/linux/mfd/intel_soc_pmic.h b/include/linux/mfd/intel_soc_pmic.h index 806a4f095312..ed1dfba5e5f9 100644 --- a/include/linux/mfd/intel_soc_pmic.h +++ b/include/linux/mfd/intel_soc_pmic.h @@ -1,17 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* - * intel_soc_pmic.h - Intel SoC PMIC Driver + * Intel SoC PMIC Driver * * Copyright (C) 2012-2014 Intel Corporation. All rights reserved. * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version - * 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Author: Yang, Bin * Author: Zhu, Lejun */ diff --git a/include/linux/mfd/intel_soc_pmic_bxtwc.h b/include/linux/mfd/intel_soc_pmic_bxtwc.h index 0c351bc85d2d..9be566cc58c6 100644 --- a/include/linux/mfd/intel_soc_pmic_bxtwc.h +++ b/include/linux/mfd/intel_soc_pmic_bxtwc.h @@ -1,16 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Header file for Intel Broxton Whiskey Cove PMIC * * Copyright (C) 2015 Intel 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. */ #ifndef __INTEL_BXTWC_H__ -- cgit v1.2.3 From efddff27c886e729a7f84a7205bd84d7d4af7336 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Wed, 5 Sep 2018 13:54:07 +0200 Subject: mfd: max8997: Enale irq-wakeup unconditionally IRQ wake up support for MAX8997 driver was initially configured by respective property in pdata. However, after the driver conversion to device-tree, setting it was left as 'todo'. Nowadays most of other PMIC MFD drivers initialized from device-tree assume that they can be an irq wakeup source, so enable it also for MAX8997. This fixes support for wakeup from MAX8997 RTC alarm. Signed-off-by: Marek Szyprowski Reviewed-by: Krzysztof Kozlowski Signed-off-by: Lee Jones --- drivers/mfd/max8997.c | 8 +------- include/linux/mfd/max8997.h | 1 - 2 files changed, 1 insertion(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/max8997.c b/drivers/mfd/max8997.c index 8dbae31911a1..f99e8da99782 100644 --- a/drivers/mfd/max8997.c +++ b/drivers/mfd/max8997.c @@ -139,12 +139,6 @@ static struct max8997_platform_data *max8997_i2c_parse_dt_pdata( pd->ono = irq_of_parse_and_map(dev->of_node, 1); - /* - * ToDo: the 'wakeup' member in the platform data is more of a linux - * specfic information. Hence, there is no binding for that yet and - * not parsed here. - */ - return pd; } @@ -232,7 +226,7 @@ static int max8997_i2c_probe(struct i2c_client *i2c, */ /* MAX8997 has a power button input. */ - device_init_wakeup(max8997->dev, pdata->wakeup); + device_init_wakeup(max8997->dev, true); return ret; diff --git a/include/linux/mfd/max8997.h b/include/linux/mfd/max8997.h index 3c4e920b4727..e955e2f0a2cc 100644 --- a/include/linux/mfd/max8997.h +++ b/include/linux/mfd/max8997.h @@ -165,7 +165,6 @@ struct max8997_led_platform_data { struct max8997_platform_data { /* IRQ */ int ono; - int wakeup; /* ---- PMIC ---- */ struct max8997_regulator_data *regulators; -- cgit v1.2.3 From 7a6a395b16c3fdcd2ede2b0ce4bf63f6dafc1fea Mon Sep 17 00:00:00 2001 From: Pavel Machek Date: Tue, 11 Sep 2018 23:01:33 +0200 Subject: mfd: ti-lmu: Switch to GPIOD Use new descriptor based API instead of the legacy one. Signed-off-by: Sebastian Reichel Signed-off-by: Pavel Machek Signed-off-by: Lee Jones --- drivers/mfd/ti-lmu.c | 28 ++++++++++++---------------- include/linux/mfd/ti-lmu.h | 3 ++- 2 files changed, 14 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/ti-lmu.c b/drivers/mfd/ti-lmu.c index 990437e5ed0a..e14cb9f41b44 100644 --- a/drivers/mfd/ti-lmu.c +++ b/drivers/mfd/ti-lmu.c @@ -12,7 +12,7 @@ #include #include -#include +#include #include #include #include @@ -21,7 +21,6 @@ #include #include #include -#include #include struct ti_lmu_data { @@ -32,17 +31,8 @@ struct ti_lmu_data { static int ti_lmu_enable_hw(struct ti_lmu *lmu, enum ti_lmu_id id) { - int ret; - - if (gpio_is_valid(lmu->en_gpio)) { - ret = devm_gpio_request_one(lmu->dev, lmu->en_gpio, - GPIOF_OUT_INIT_HIGH, "lmu_hwen"); - if (ret) { - dev_err(lmu->dev, "Can not request enable GPIO: %d\n", - ret); - return ret; - } - } + if (lmu->en_gpio) + gpiod_set_value(lmu->en_gpio, 1); /* Delay about 1ms after HW enable pin control */ usleep_range(1000, 1500); @@ -59,8 +49,8 @@ static int ti_lmu_enable_hw(struct ti_lmu *lmu, enum ti_lmu_id id) static void ti_lmu_disable_hw(struct ti_lmu *lmu) { - if (gpio_is_valid(lmu->en_gpio)) - gpio_set_value(lmu->en_gpio, 0); + if (lmu->en_gpio) + gpiod_set_value(lmu->en_gpio, 0); } static const struct mfd_cell lm3532_devices[] = { @@ -204,7 +194,13 @@ static int ti_lmu_probe(struct i2c_client *cl, const struct i2c_device_id *id) return PTR_ERR(lmu->regmap); /* HW enable pin control and additional power up sequence if required */ - lmu->en_gpio = of_get_named_gpio(dev->of_node, "enable-gpios", 0); + lmu->en_gpio = devm_gpiod_get_optional(dev, "enable", GPIOD_OUT_HIGH); + if (IS_ERR(lmu->en_gpio)) { + ret = PTR_ERR(lmu->en_gpio); + dev_err(dev, "Can not request enable GPIO: %d\n", ret); + return ret; + } + ret = ti_lmu_enable_hw(lmu, id->driver_data); if (ret) return ret; diff --git a/include/linux/mfd/ti-lmu.h b/include/linux/mfd/ti-lmu.h index 09d5f30384e5..1ef51ed36be5 100644 --- a/include/linux/mfd/ti-lmu.h +++ b/include/linux/mfd/ti-lmu.h @@ -16,6 +16,7 @@ #include #include #include +#include /* Notifier event */ #define LMU_EVENT_MONITOR_DONE 0x01 @@ -81,7 +82,7 @@ enum lm363x_regulator_id { struct ti_lmu { struct device *dev; struct regmap *regmap; - int en_gpio; + struct gpio_desc *en_gpio; struct blocking_notifier_head notifier; }; #endif -- cgit v1.2.3 From 07d02a67b7faae56e184f6c35f78de47f06da37f Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 12 Oct 2018 13:28:26 -0400 Subject: SUNRPC: Simplify lookup code We no longer need to worry about whether or not the entry is hashed in order to figure out if the contents are valid. We only care whether or not the refcount is non-zero. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/auth.h | 12 +++++------- net/sunrpc/auth.c | 19 ++++++++----------- 2 files changed, 13 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index 2c97a3933ef9..a7fc8f5a2dad 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -206,11 +206,11 @@ bool rpcauth_cred_key_to_expire(struct rpc_auth *, struct rpc_cred *); char * rpcauth_stringify_acceptor(struct rpc_cred *); static inline -struct rpc_cred * get_rpccred(struct rpc_cred *cred) +struct rpc_cred *get_rpccred(struct rpc_cred *cred) { - if (cred != NULL) - atomic_inc(&cred->cr_count); - return cred; + if (cred != NULL && atomic_inc_not_zero(&cred->cr_count)) + return cred; + return NULL; } /** @@ -226,9 +226,7 @@ struct rpc_cred * get_rpccred(struct rpc_cred *cred) static inline struct rpc_cred * get_rpccred_rcu(struct rpc_cred *cred) { - if (atomic_inc_not_zero(&cred->cr_count)) - return cred; - return NULL; + return get_rpccred(cred); } #endif /* __KERNEL__ */ diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index c1576b110974..77748e572686 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -588,19 +588,15 @@ rpcauth_lookup_credcache(struct rpc_auth *auth, struct auth_cred * acred, if (!entry->cr_ops->crmatch(acred, entry, flags)) continue; if (flags & RPCAUTH_LOOKUP_RCU) { - if (test_bit(RPCAUTH_CRED_HASHED, &entry->cr_flags) && - !test_bit(RPCAUTH_CRED_NEW, &entry->cr_flags)) - cred = entry; + if (test_bit(RPCAUTH_CRED_NEW, &entry->cr_flags) || + atomic_read(&entry->cr_count) == 0) + continue; + cred = entry; break; } - spin_lock(&cache->lock); - if (test_bit(RPCAUTH_CRED_HASHED, &entry->cr_flags) == 0) { - spin_unlock(&cache->lock); - continue; - } cred = get_rpccred(entry); - spin_unlock(&cache->lock); - break; + if (cred) + break; } rcu_read_unlock(); @@ -621,7 +617,8 @@ rpcauth_lookup_credcache(struct rpc_auth *auth, struct auth_cred * acred, if (!entry->cr_ops->crmatch(acred, entry, flags)) continue; cred = get_rpccred(entry); - break; + if (cred) + break; } if (cred == NULL) { cred = new; -- cgit v1.2.3 From 79b181810285a6b9b7a1aed25c365c9e1782e22a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 14 Oct 2018 10:34:31 -0400 Subject: SUNRPC: Convert auth creds to use refcount_t Signed-off-by: Trond Myklebust --- include/linux/sunrpc/auth.h | 4 ++-- net/sunrpc/auth.c | 14 +++++++------- net/sunrpc/auth_null.c | 2 +- 3 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index a7fc8f5a2dad..a71d4bd191e7 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -67,7 +67,7 @@ struct rpc_cred { const struct rpc_credops *cr_ops; unsigned long cr_expire; /* when to gc */ unsigned long cr_flags; /* various flags */ - atomic_t cr_count; /* ref count */ + refcount_t cr_count; /* ref count */ kuid_t cr_uid; @@ -208,7 +208,7 @@ char * rpcauth_stringify_acceptor(struct rpc_cred *); static inline struct rpc_cred *get_rpccred(struct rpc_cred *cred) { - if (cred != NULL && atomic_inc_not_zero(&cred->cr_count)) + if (cred != NULL && refcount_inc_not_zero(&cred->cr_count)) return cred; return NULL; } diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index 77748e572686..4903eda5dd61 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -495,7 +495,7 @@ rpcauth_prune_expired(struct list_head *free, int nr_to_scan) if (nr_to_scan-- == 0) break; - if (atomic_read(&cred->cr_count) > 1) { + if (refcount_read(&cred->cr_count) > 1) { rpcauth_lru_remove_locked(cred); continue; } @@ -589,7 +589,7 @@ rpcauth_lookup_credcache(struct rpc_auth *auth, struct auth_cred * acred, continue; if (flags & RPCAUTH_LOOKUP_RCU) { if (test_bit(RPCAUTH_CRED_NEW, &entry->cr_flags) || - atomic_read(&entry->cr_count) == 0) + refcount_read(&entry->cr_count) == 0) continue; cred = entry; break; @@ -623,7 +623,7 @@ rpcauth_lookup_credcache(struct rpc_auth *auth, struct auth_cred * acred, if (cred == NULL) { cred = new; set_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags); - atomic_inc(&cred->cr_count); + refcount_inc(&cred->cr_count); hlist_add_head_rcu(&cred->cr_hash, &cache->hashtable[nr]); } else list_add_tail(&new->cr_lru, &free); @@ -670,7 +670,7 @@ rpcauth_init_cred(struct rpc_cred *cred, const struct auth_cred *acred, { INIT_HLIST_NODE(&cred->cr_hash); INIT_LIST_HEAD(&cred->cr_lru); - atomic_set(&cred->cr_count, 1); + refcount_set(&cred->cr_count, 1); cred->cr_auth = auth; cred->cr_ops = ops; cred->cr_expire = jiffies; @@ -739,9 +739,9 @@ put_rpccred(struct rpc_cred *cred) if (cred == NULL) return; rcu_read_lock(); - if (atomic_dec_and_test(&cred->cr_count)) + if (refcount_dec_and_test(&cred->cr_count)) goto destroy; - if (atomic_read(&cred->cr_count) != 1 || + if (refcount_read(&cred->cr_count) != 1 || !test_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags)) goto out; if (test_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags) != 0) { @@ -752,7 +752,7 @@ put_rpccred(struct rpc_cred *cred) rpcauth_lru_remove(cred); } else if (rpcauth_unhash_cred(cred)) { rpcauth_lru_remove(cred); - if (atomic_dec_and_test(&cred->cr_count)) + if (refcount_dec_and_test(&cred->cr_count)) goto destroy; } out: diff --git a/net/sunrpc/auth_null.c b/net/sunrpc/auth_null.c index a7c00b4959f3..ea816d7000a4 100644 --- a/net/sunrpc/auth_null.c +++ b/net/sunrpc/auth_null.c @@ -138,6 +138,6 @@ struct rpc_cred null_cred = { .cr_lru = LIST_HEAD_INIT(null_cred.cr_lru), .cr_auth = &null_auth, .cr_ops = &null_credops, - .cr_count = ATOMIC_INIT(2), + .cr_count = REFCOUNT_INIT(2), .cr_flags = 1UL << RPCAUTH_CRED_UPTODATE, }; -- cgit v1.2.3 From 331bc71cb1751d78f6807ad8e6162b07c67cdd1b Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 14 Oct 2018 10:40:29 -0400 Subject: SUNRPC: Convert the auth cred cache to use refcount_t Signed-off-by: Trond Myklebust --- include/linux/sunrpc/auth.h | 2 +- net/sunrpc/auth.c | 2 +- net/sunrpc/auth_generic.c | 2 +- net/sunrpc/auth_gss/auth_gss.c | 4 ++-- net/sunrpc/auth_null.c | 4 ++-- net/sunrpc/auth_unix.c | 4 ++-- 6 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index a71d4bd191e7..c4db9424b63b 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -100,7 +100,7 @@ struct rpc_auth { * differ from the flavor in * au_ops->au_flavor in gss * case) */ - atomic_t au_count; /* Reference counter */ + refcount_t au_count; /* Reference counter */ struct rpc_cred_cache * au_credcache; /* per-flavor data */ diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index 4903eda5dd61..ad8ead738981 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -284,7 +284,7 @@ EXPORT_SYMBOL_GPL(rpcauth_create); void rpcauth_release(struct rpc_auth *auth) { - if (!atomic_dec_and_test(&auth->au_count)) + if (!refcount_dec_and_test(&auth->au_count)) return; auth->au_ops->destroy(auth); } diff --git a/net/sunrpc/auth_generic.c b/net/sunrpc/auth_generic.c index f1df9837f1ac..d8831b988b1e 100644 --- a/net/sunrpc/auth_generic.c +++ b/net/sunrpc/auth_generic.c @@ -274,7 +274,7 @@ static const struct rpc_authops generic_auth_ops = { static struct rpc_auth generic_auth = { .au_ops = &generic_auth_ops, - .au_count = ATOMIC_INIT(0), + .au_count = REFCOUNT_INIT(1), }; static bool generic_key_to_expire(struct rpc_cred *cred) diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index c898a7c75e84..30f970cdc7f6 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -1058,7 +1058,7 @@ gss_create_new(const struct rpc_auth_create_args *args, struct rpc_clnt *clnt) auth->au_flavor = flavor; if (gss_pseudoflavor_to_datatouch(gss_auth->mech, flavor)) auth->au_flags |= RPCAUTH_AUTH_DATATOUCH; - atomic_set(&auth->au_count, 1); + refcount_set(&auth->au_count, 1); kref_init(&gss_auth->kref); err = rpcauth_init_credcache(auth); @@ -1187,7 +1187,7 @@ gss_auth_find_or_add_hashed(const struct rpc_auth_create_args *args, if (strcmp(gss_auth->target_name, args->target_name)) continue; } - if (!atomic_inc_not_zero(&gss_auth->rpc_auth.au_count)) + if (!refcount_inc_not_zero(&gss_auth->rpc_auth.au_count)) continue; goto out; } diff --git a/net/sunrpc/auth_null.c b/net/sunrpc/auth_null.c index ea816d7000a4..2694a1bc026b 100644 --- a/net/sunrpc/auth_null.c +++ b/net/sunrpc/auth_null.c @@ -21,7 +21,7 @@ static struct rpc_cred null_cred; static struct rpc_auth * nul_create(const struct rpc_auth_create_args *args, struct rpc_clnt *clnt) { - atomic_inc(&null_auth.au_count); + refcount_inc(&null_auth.au_count); return &null_auth; } @@ -119,7 +119,7 @@ struct rpc_auth null_auth = { .au_flags = RPCAUTH_AUTH_NO_CRKEY_TIMEOUT, .au_ops = &authnull_ops, .au_flavor = RPC_AUTH_NULL, - .au_count = ATOMIC_INIT(0), + .au_count = REFCOUNT_INIT(1), }; static diff --git a/net/sunrpc/auth_unix.c b/net/sunrpc/auth_unix.c index 185e56d4f9ae..4c1c7e56288f 100644 --- a/net/sunrpc/auth_unix.c +++ b/net/sunrpc/auth_unix.c @@ -34,7 +34,7 @@ unx_create(const struct rpc_auth_create_args *args, struct rpc_clnt *clnt) { dprintk("RPC: creating UNIX authenticator for client %p\n", clnt); - atomic_inc(&unix_auth.au_count); + refcount_inc(&unix_auth.au_count); return &unix_auth; } @@ -239,7 +239,7 @@ struct rpc_auth unix_auth = { .au_flags = RPCAUTH_AUTH_NO_CRKEY_TIMEOUT, .au_ops = &authunix_ops, .au_flavor = RPC_AUTH_UNIX, - .au_count = ATOMIC_INIT(0), + .au_count = REFCOUNT_INIT(1), }; static -- cgit v1.2.3 From a91e138022bc29b5d2bbc56b41de3e0db6261e28 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 12 Oct 2018 19:08:43 +0900 Subject: block: Introduce blkdev_nr_zones() helper Introduce the blkdev_nr_zones() helper function to get the total number of zones of a zoned block device. This number is always 0 for a regular block device (q->limits.zoned == BLK_ZONED_NONE case). Replace hard-coded number of zones calculation in dmz_get_zoned_device() with a call to this helper. Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- block/blk-zoned.c | 27 +++++++++++++++++++++++++++ drivers/md/dm-zoned-target.c | 3 +-- include/linux/blkdev.h | 5 +++++ 3 files changed, 33 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/block/blk-zoned.c b/block/blk-zoned.c index c461cf63f1f4..32e377f755d8 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -63,6 +63,33 @@ void __blk_req_zone_write_unlock(struct request *rq) } EXPORT_SYMBOL_GPL(__blk_req_zone_write_unlock); +static inline unsigned int __blkdev_nr_zones(struct request_queue *q, + sector_t nr_sectors) +{ + unsigned long zone_sectors = blk_queue_zone_sectors(q); + + return (nr_sectors + zone_sectors - 1) >> ilog2(zone_sectors); +} + +/** + * blkdev_nr_zones - Get number of zones + * @bdev: Target block device + * + * Description: + * Return the total number of zones of a zoned block device. + * For a regular block device, the number of zones is always 0. + */ +unsigned int blkdev_nr_zones(struct block_device *bdev) +{ + struct request_queue *q = bdev_get_queue(bdev); + + if (!blk_queue_is_zoned(q)) + return 0; + + return __blkdev_nr_zones(q, bdev->bd_part->nr_sects); +} +EXPORT_SYMBOL_GPL(blkdev_nr_zones); + /* * Check that a zone report belongs to the partition. * If yes, fix its start sector and write pointer, copy it in the diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c index a44183ff4be0..12d96a263623 100644 --- a/drivers/md/dm-zoned-target.c +++ b/drivers/md/dm-zoned-target.c @@ -702,8 +702,7 @@ static int dmz_get_zoned_device(struct dm_target *ti, char *path) dev->zone_nr_blocks = dmz_sect2blk(dev->zone_nr_sectors); dev->zone_nr_blocks_shift = ilog2(dev->zone_nr_blocks); - dev->nr_zones = (dev->capacity + dev->zone_nr_sectors - 1) - >> dev->zone_nr_sectors_shift; + dev->nr_zones = blkdev_nr_zones(dev->bdev); dmz->dev = dev; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 7d423721b327..ca5fdc1b7745 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -401,6 +401,7 @@ struct blk_zone_report_hdr { u8 padding[60]; }; +extern unsigned int blkdev_nr_zones(struct block_device *bdev); extern int blkdev_report_zones(struct block_device *bdev, sector_t sector, struct blk_zone *zones, unsigned int *nr_zones, gfp_t gfp_mask); @@ -414,6 +415,10 @@ extern int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode, #else /* CONFIG_BLK_DEV_ZONED */ +static inline unsigned int blkdev_nr_zones(struct block_device *bdev) +{ + return 0; +} static inline int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) -- cgit v1.2.3 From 965b652e901886ea54f93c60027b5be76328d958 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 12 Oct 2018 19:08:48 +0900 Subject: block: Expose queue nr_zones in sysfs Expose through sysfs the nr_zones field of struct request_queue. Exposing this value helps in debugging disk issues as well as facilitating scripts based use of the disk (e.g. blktests). For zoned block devices, the nr_zones field indicates the total number of zones of the device calculated using the known disk capacity and zone size. This number of zones is always 0 for regular block devices. Since nr_zones is defined conditionally with CONFIG_BLK_DEV_ZONED, introduce the blk_queue_nr_zones() function to return the correct value for any device, regardless if CONFIG_BLK_DEV_ZONED is set. Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- block/blk-sysfs.c | 11 +++++++++++ include/linux/blkdev.h | 10 ++++++++++ 2 files changed, 21 insertions(+) (limited to 'include/linux') diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 3772671cf2bc..92be8092ca4f 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -300,6 +300,11 @@ static ssize_t queue_zoned_show(struct request_queue *q, char *page) } } +static ssize_t queue_nr_zones_show(struct request_queue *q, char *page) +{ + return queue_var_show(blk_queue_nr_zones(q), page); +} + static ssize_t queue_nomerges_show(struct request_queue *q, char *page) { return queue_var_show((blk_queue_nomerges(q) << 1) | @@ -637,6 +642,11 @@ static struct queue_sysfs_entry queue_zoned_entry = { .show = queue_zoned_show, }; +static struct queue_sysfs_entry queue_nr_zones_entry = { + .attr = {.name = "nr_zones", .mode = 0444 }, + .show = queue_nr_zones_show, +}; + static struct queue_sysfs_entry queue_nomerges_entry = { .attr = {.name = "nomerges", .mode = 0644 }, .show = queue_nomerges_show, @@ -727,6 +737,7 @@ static struct attribute *default_attrs[] = { &queue_write_zeroes_max_entry.attr, &queue_nonrot_entry.attr, &queue_zoned_entry.attr, + &queue_nr_zones_entry.attr, &queue_nomerges_entry.attr, &queue_rq_affinity_entry.attr, &queue_iostats_entry.attr, diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index ca5fdc1b7745..6bb845f9601a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -811,6 +811,11 @@ static inline unsigned int blk_queue_zone_sectors(struct request_queue *q) } #ifdef CONFIG_BLK_DEV_ZONED +static inline unsigned int blk_queue_nr_zones(struct request_queue *q) +{ + return blk_queue_is_zoned(q) ? q->nr_zones : 0; +} + static inline unsigned int blk_queue_zone_no(struct request_queue *q, sector_t sector) { @@ -826,6 +831,11 @@ static inline bool blk_queue_zone_is_seq(struct request_queue *q, return false; return test_bit(blk_queue_zone_no(q, sector), q->seq_zones_bitmap); } +#else /* CONFIG_BLK_DEV_ZONED */ +static inline unsigned int blk_queue_nr_zones(struct request_queue *q) +{ + return 0; +} #endif /* CONFIG_BLK_DEV_ZONED */ static inline bool rq_is_sync(struct request *rq) -- cgit v1.2.3 From e76239a3748c90a8b0e197f8f4544a8ce52f126e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 12 Oct 2018 19:08:49 +0900 Subject: block: add a report_zones method Dispatching a report zones command through the request queue is a major pain due to the command reply payload rewriting necessary. Given that blkdev_report_zones() is executing everything synchronously, implement report zones as a block device file operation instead, allowing major simplification of the code in many places. sd, null-blk, dm-linear and dm-flakey being the only block device drivers supporting exposing zoned block devices, these drivers are modified to provide the device side implementation of the report_zones() block device file operation. For device mappers, a new report_zones() target type operation is defined so that the upper block layer calls blkdev_report_zones() can be propagated down to the underlying devices of the dm targets. Implementation for this new operation is added to the dm-linear and dm-flakey targets. Reviewed-by: Hannes Reinecke Signed-off-by: Christoph Hellwig [Damien] * Changed method block_device argument to gendisk * Various bug fixes and improvements * Added support for null_blk, dm-linear and dm-flakey. Reviewed-by: Martin K. Petersen Reviewed-by: Mike Snitzer Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- block/blk-core.c | 1 - block/blk-mq-debugfs.c | 1 - block/blk-zoned.c | 164 +++++++++++++-------------------------- drivers/block/null_blk.h | 11 ++- drivers/block/null_blk_main.c | 23 +----- drivers/block/null_blk_zoned.c | 57 ++++---------- drivers/md/dm-flakey.c | 30 +++++--- drivers/md/dm-linear.c | 35 +++++---- drivers/md/dm.c | 169 ++++++++++++++++++++--------------------- drivers/scsi/sd.c | 13 +--- drivers/scsi/sd.h | 11 ++- drivers/scsi/sd_zbc.c | 153 ++++++++++++------------------------- include/linux/blk_types.h | 2 - include/linux/blkdev.h | 8 +- include/linux/device-mapper.h | 12 ++- include/trace/events/f2fs.h | 1 - 16 files changed, 266 insertions(+), 425 deletions(-) (limited to 'include/linux') diff --git a/block/blk-core.c b/block/blk-core.c index 3ed60723e242..bc6ea87d10e0 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2300,7 +2300,6 @@ generic_make_request_checks(struct bio *bio) if (!q->limits.max_write_same_sectors) goto not_supported; break; - case REQ_OP_ZONE_REPORT: case REQ_OP_ZONE_RESET: if (!blk_queue_is_zoned(q)) goto not_supported; diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 41b86f50d126..10b284a1f18d 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -283,7 +283,6 @@ static const char *const op_name[] = { REQ_OP_NAME(WRITE), REQ_OP_NAME(FLUSH), REQ_OP_NAME(DISCARD), - REQ_OP_NAME(ZONE_REPORT), REQ_OP_NAME(SECURE_ERASE), REQ_OP_NAME(ZONE_RESET), REQ_OP_NAME(WRITE_SAME), diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 5d967fd39fbd..90cf503091d5 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -93,13 +93,10 @@ unsigned int blkdev_nr_zones(struct block_device *bdev) EXPORT_SYMBOL_GPL(blkdev_nr_zones); /* - * Check that a zone report belongs to the partition. - * If yes, fix its start sector and write pointer, copy it in the - * zone information array and return true. Return false otherwise. + * Check that a zone report belongs to this partition, and if yes, fix its start + * sector and write pointer and return true. Return false otherwise. */ -static bool blkdev_report_zone(struct block_device *bdev, - struct blk_zone *rep, - struct blk_zone *zone) +static bool blkdev_report_zone(struct block_device *bdev, struct blk_zone *rep) { sector_t offset = get_start_sect(bdev); @@ -114,11 +111,36 @@ static bool blkdev_report_zone(struct block_device *bdev, rep->wp = rep->start + rep->len; else rep->wp -= offset; - memcpy(zone, rep, sizeof(struct blk_zone)); - return true; } +static int blk_report_zones(struct gendisk *disk, sector_t sector, + struct blk_zone *zones, unsigned int *nr_zones, + gfp_t gfp_mask) +{ + struct request_queue *q = disk->queue; + unsigned int z = 0, n, nrz = *nr_zones; + sector_t capacity = get_capacity(disk); + int ret; + + while (z < nrz && sector < capacity) { + n = nrz - z; + ret = disk->fops->report_zones(disk, sector, &zones[z], &n, + gfp_mask); + if (ret) + return ret; + if (!n) + break; + sector += blk_queue_zone_sectors(q) * n; + z += n; + } + + WARN_ON(z > *nr_zones); + *nr_zones = z; + + return 0; +} + /** * blkdev_report_zones - Get zones information * @bdev: Target block device @@ -133,130 +155,46 @@ static bool blkdev_report_zone(struct block_device *bdev, * requested by @nr_zones. The number of zones actually reported is * returned in @nr_zones. */ -int blkdev_report_zones(struct block_device *bdev, - sector_t sector, - struct blk_zone *zones, - unsigned int *nr_zones, +int blkdev_report_zones(struct block_device *bdev, sector_t sector, + struct blk_zone *zones, unsigned int *nr_zones, gfp_t gfp_mask) { struct request_queue *q = bdev_get_queue(bdev); - struct blk_zone_report_hdr *hdr; - unsigned int nrz = *nr_zones; - struct page *page; - unsigned int nr_rep; - size_t rep_bytes; - unsigned int nr_pages; - struct bio *bio; - struct bio_vec *bv; - unsigned int i, n, nz; - unsigned int ofst; - void *addr; + unsigned int i, nrz; int ret; - if (!q) - return -ENXIO; - if (!blk_queue_is_zoned(q)) return -EOPNOTSUPP; - if (!nrz) - return 0; - - if (sector > bdev->bd_part->nr_sects) { - *nr_zones = 0; - return 0; - } - /* - * The zone report has a header. So make room for it in the - * payload. Also make sure that the report fits in a single BIO - * that will not be split down the stack. + * A block device that advertized itself as zoned must have a + * report_zones method. If it does not have one defined, the device + * driver has a bug. So warn about that. */ - rep_bytes = sizeof(struct blk_zone_report_hdr) + - sizeof(struct blk_zone) * nrz; - rep_bytes = (rep_bytes + PAGE_SIZE - 1) & PAGE_MASK; - if (rep_bytes > (queue_max_sectors(q) << 9)) - rep_bytes = queue_max_sectors(q) << 9; - - nr_pages = min_t(unsigned int, BIO_MAX_PAGES, - rep_bytes >> PAGE_SHIFT); - nr_pages = min_t(unsigned int, nr_pages, - queue_max_segments(q)); - - bio = bio_alloc(gfp_mask, nr_pages); - if (!bio) - return -ENOMEM; + if (WARN_ON_ONCE(!bdev->bd_disk->fops->report_zones)) + return -EOPNOTSUPP; - bio_set_dev(bio, bdev); - bio->bi_iter.bi_sector = blk_zone_start(q, sector); - bio_set_op_attrs(bio, REQ_OP_ZONE_REPORT, 0); - - for (i = 0; i < nr_pages; i++) { - page = alloc_page(gfp_mask); - if (!page) { - ret = -ENOMEM; - goto out; - } - if (!bio_add_page(bio, page, PAGE_SIZE, 0)) { - __free_page(page); - break; - } + if (!*nr_zones || sector >= bdev->bd_part->nr_sects) { + *nr_zones = 0; + return 0; } - if (i == 0) - ret = -ENOMEM; - else - ret = submit_bio_wait(bio); + nrz = min(*nr_zones, + __blkdev_nr_zones(q, bdev->bd_part->nr_sects - sector)); + ret = blk_report_zones(bdev->bd_disk, get_start_sect(bdev) + sector, + zones, &nrz, gfp_mask); if (ret) - goto out; - - /* - * Process the report result: skip the header and go through the - * reported zones to fixup and fixup the zone information for - * partitions. At the same time, return the zone information into - * the zone array. - */ - n = 0; - nz = 0; - nr_rep = 0; - bio_for_each_segment_all(bv, bio, i) { + return ret; - if (!bv->bv_page) + for (i = 0; i < nrz; i++) { + if (!blkdev_report_zone(bdev, zones)) break; - - addr = kmap_atomic(bv->bv_page); - - /* Get header in the first page */ - ofst = 0; - if (!nr_rep) { - hdr = addr; - nr_rep = hdr->nr_zones; - ofst = sizeof(struct blk_zone_report_hdr); - } - - /* Fixup and report zones */ - while (ofst < bv->bv_len && - n < nr_rep && nz < nrz) { - if (blkdev_report_zone(bdev, addr + ofst, &zones[nz])) - nz++; - ofst += sizeof(struct blk_zone); - n++; - } - - kunmap_atomic(addr); - - if (n >= nr_rep || nz >= nrz) - break; - + zones++; } - *nr_zones = nz; -out: - bio_for_each_segment_all(bv, bio, i) - __free_page(bv->bv_page); - bio_put(bio); + *nr_zones = i; - return ret; + return 0; } EXPORT_SYMBOL_GPL(blkdev_report_zones); diff --git a/drivers/block/null_blk.h b/drivers/block/null_blk.h index 34e0030f0592..7685df43f1ef 100644 --- a/drivers/block/null_blk.h +++ b/drivers/block/null_blk.h @@ -87,7 +87,9 @@ struct nullb { #ifdef CONFIG_BLK_DEV_ZONED int null_zone_init(struct nullb_device *dev); void null_zone_exit(struct nullb_device *dev); -blk_status_t null_zone_report(struct nullb *nullb, struct bio *bio); +int null_zone_report(struct gendisk *disk, sector_t sector, + struct blk_zone *zones, unsigned int *nr_zones, + gfp_t gfp_mask); void null_zone_write(struct nullb_cmd *cmd, sector_t sector, unsigned int nr_sectors); void null_zone_reset(struct nullb_cmd *cmd, sector_t sector); @@ -97,10 +99,11 @@ static inline int null_zone_init(struct nullb_device *dev) return -EINVAL; } static inline void null_zone_exit(struct nullb_device *dev) {} -static inline blk_status_t null_zone_report(struct nullb *nullb, - struct bio *bio) +static inline int null_zone_report(struct gendisk *disk, sector_t sector, + struct blk_zone *zones, + unsigned int *nr_zones, gfp_t gfp_mask) { - return BLK_STS_NOTSUPP; + return -EOPNOTSUPP; } static inline void null_zone_write(struct nullb_cmd *cmd, sector_t sector, unsigned int nr_sectors) diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c index e94591021682..5ba426dbf377 100644 --- a/drivers/block/null_blk_main.c +++ b/drivers/block/null_blk_main.c @@ -1129,34 +1129,12 @@ static void null_restart_queue_async(struct nullb *nullb) blk_mq_start_stopped_hw_queues(q, true); } -static bool cmd_report_zone(struct nullb *nullb, struct nullb_cmd *cmd) -{ - struct nullb_device *dev = cmd->nq->dev; - - if (dev->queue_mode == NULL_Q_BIO) { - if (bio_op(cmd->bio) == REQ_OP_ZONE_REPORT) { - cmd->error = null_zone_report(nullb, cmd->bio); - return true; - } - } else { - if (req_op(cmd->rq) == REQ_OP_ZONE_REPORT) { - cmd->error = null_zone_report(nullb, cmd->rq->bio); - return true; - } - } - - return false; -} - static blk_status_t null_handle_cmd(struct nullb_cmd *cmd) { struct nullb_device *dev = cmd->nq->dev; struct nullb *nullb = dev->nullb; int err = 0; - if (cmd_report_zone(nullb, cmd)) - goto out; - if (test_bit(NULLB_DEV_FL_THROTTLED, &dev->flags)) { struct request *rq = cmd->rq; @@ -1443,6 +1421,7 @@ static const struct block_device_operations null_fops = { .owner = THIS_MODULE, .open = null_open, .release = null_release, + .report_zones = null_zone_report, }; static void null_init_queue(struct nullb *nullb, struct nullb_queue *nq) diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk_zoned.c index 7c6b86d98700..c0b0e4a3fa8f 100644 --- a/drivers/block/null_blk_zoned.c +++ b/drivers/block/null_blk_zoned.c @@ -48,54 +48,27 @@ void null_zone_exit(struct nullb_device *dev) kvfree(dev->zones); } -static void null_zone_fill_bio(struct nullb_device *dev, struct bio *bio, - unsigned int zno, unsigned int nr_zones) +int null_zone_report(struct gendisk *disk, sector_t sector, + struct blk_zone *zones, unsigned int *nr_zones, + gfp_t gfp_mask) { - struct blk_zone_report_hdr *hdr = NULL; - struct bio_vec bvec; - struct bvec_iter iter; - void *addr; - unsigned int zones_to_cpy; - - bio_for_each_segment(bvec, bio, iter) { - addr = kmap_atomic(bvec.bv_page); - - zones_to_cpy = bvec.bv_len / sizeof(struct blk_zone); - - if (!hdr) { - hdr = (struct blk_zone_report_hdr *)addr; - hdr->nr_zones = nr_zones; - zones_to_cpy--; - addr += sizeof(struct blk_zone_report_hdr); - } - - zones_to_cpy = min_t(unsigned int, zones_to_cpy, nr_zones); - - memcpy(addr, &dev->zones[zno], - zones_to_cpy * sizeof(struct blk_zone)); - - kunmap_atomic(addr); + struct nullb *nullb = disk->private_data; + struct nullb_device *dev = nullb->dev; + unsigned int zno, nrz = 0; - nr_zones -= zones_to_cpy; - zno += zones_to_cpy; + if (!dev->zoned) + /* Not a zoned null device */ + return -EOPNOTSUPP; - if (!nr_zones) - break; + zno = null_zone_no(dev, sector); + if (zno < dev->nr_zones) { + nrz = min_t(unsigned int, *nr_zones, dev->nr_zones - zno); + memcpy(zones, &dev->zones[zno], nrz * sizeof(struct blk_zone)); } -} -blk_status_t null_zone_report(struct nullb *nullb, struct bio *bio) -{ - struct nullb_device *dev = nullb->dev; - unsigned int zno = null_zone_no(dev, bio->bi_iter.bi_sector); - unsigned int nr_zones = dev->nr_zones - zno; - unsigned int max_zones; + *nr_zones = nrz; - max_zones = (bio->bi_iter.bi_size / sizeof(struct blk_zone)) - 1; - nr_zones = min_t(unsigned int, nr_zones, max_zones); - null_zone_fill_bio(nullb->dev, bio, zno, nr_zones); - - return BLK_STS_OK; + return 0; } void null_zone_write(struct nullb_cmd *cmd, sector_t sector, diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c index 32aabe27b37c..3cb97fa4c11d 100644 --- a/drivers/md/dm-flakey.c +++ b/drivers/md/dm-flakey.c @@ -315,10 +315,6 @@ static int flakey_map(struct dm_target *ti, struct bio *bio) if (bio_op(bio) == REQ_OP_ZONE_RESET) goto map_bio; - /* We need to remap reported zones, so remember the BIO iter */ - if (bio_op(bio) == REQ_OP_ZONE_REPORT) - goto map_bio; - /* Are we alive ? */ elapsed = (jiffies - fc->start_time) / HZ; if (elapsed % (fc->up_interval + fc->down_interval) >= fc->up_interval) { @@ -380,11 +376,6 @@ static int flakey_end_io(struct dm_target *ti, struct bio *bio, if (bio_op(bio) == REQ_OP_ZONE_RESET) return DM_ENDIO_DONE; - if (bio_op(bio) == REQ_OP_ZONE_REPORT) { - dm_remap_zone_report(ti, bio, fc->start); - return DM_ENDIO_DONE; - } - if (!*error && pb->bio_submitted && (bio_data_dir(bio) == READ)) { if (fc->corrupt_bio_byte && (fc->corrupt_bio_rw == READ) && all_corrupt_bio_flags_match(bio, fc)) { @@ -457,6 +448,26 @@ static int flakey_prepare_ioctl(struct dm_target *ti, struct block_device **bdev return 0; } +#ifdef CONFIG_BLK_DEV_ZONED +static int flakey_report_zones(struct dm_target *ti, sector_t sector, + struct blk_zone *zones, unsigned int *nr_zones, + gfp_t gfp_mask) +{ + struct flakey_c *fc = ti->private; + int ret; + + /* Do report and remap it */ + ret = blkdev_report_zones(fc->dev->bdev, flakey_map_sector(ti, sector), + zones, nr_zones, gfp_mask); + if (ret != 0) + return ret; + + if (*nr_zones) + dm_remap_zone_report(ti, fc->start, zones, nr_zones); + return 0; +} +#endif + static int flakey_iterate_devices(struct dm_target *ti, iterate_devices_callout_fn fn, void *data) { struct flakey_c *fc = ti->private; @@ -469,6 +480,7 @@ static struct target_type flakey_target = { .version = {1, 5, 0}, #ifdef CONFIG_BLK_DEV_ZONED .features = DM_TARGET_ZONED_HM, + .report_zones = flakey_report_zones, #endif .module = THIS_MODULE, .ctr = flakey_ctr, diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index 2f7c44a006c4..8d7ddee6ac4d 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -102,19 +102,6 @@ static int linear_map(struct dm_target *ti, struct bio *bio) return DM_MAPIO_REMAPPED; } -#ifdef CONFIG_BLK_DEV_ZONED -static int linear_end_io(struct dm_target *ti, struct bio *bio, - blk_status_t *error) -{ - struct linear_c *lc = ti->private; - - if (!*error && bio_op(bio) == REQ_OP_ZONE_REPORT) - dm_remap_zone_report(ti, bio, lc->start); - - return DM_ENDIO_DONE; -} -#endif - static void linear_status(struct dm_target *ti, status_type_t type, unsigned status_flags, char *result, unsigned maxlen) { @@ -148,6 +135,26 @@ static int linear_prepare_ioctl(struct dm_target *ti, struct block_device **bdev return 0; } +#ifdef CONFIG_BLK_DEV_ZONED +static int linear_report_zones(struct dm_target *ti, sector_t sector, + struct blk_zone *zones, unsigned int *nr_zones, + gfp_t gfp_mask) +{ + struct linear_c *lc = (struct linear_c *) ti->private; + int ret; + + /* Do report and remap it */ + ret = blkdev_report_zones(lc->dev->bdev, linear_map_sector(ti, sector), + zones, nr_zones, gfp_mask); + if (ret != 0) + return ret; + + if (*nr_zones) + dm_remap_zone_report(ti, lc->start, zones, nr_zones); + return 0; +} +#endif + static int linear_iterate_devices(struct dm_target *ti, iterate_devices_callout_fn fn, void *data) { @@ -211,8 +218,8 @@ static struct target_type linear_target = { .name = "linear", .version = {1, 4, 0}, #ifdef CONFIG_BLK_DEV_ZONED - .end_io = linear_end_io, .features = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_ZONED_HM, + .report_zones = linear_report_zones, #else .features = DM_TARGET_PASSES_INTEGRITY, #endif diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 45abb54037fc..6be21dc210a1 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -458,6 +458,57 @@ static int dm_blk_getgeo(struct block_device *bdev, struct hd_geometry *geo) return dm_get_geometry(md, geo); } +static int dm_blk_report_zones(struct gendisk *disk, sector_t sector, + struct blk_zone *zones, unsigned int *nr_zones, + gfp_t gfp_mask) +{ +#ifdef CONFIG_BLK_DEV_ZONED + struct mapped_device *md = disk->private_data; + struct dm_target *tgt; + struct dm_table *map; + int srcu_idx, ret; + + if (dm_suspended_md(md)) + return -EAGAIN; + + map = dm_get_live_table(md, &srcu_idx); + if (!map) + return -EIO; + + tgt = dm_table_find_target(map, sector); + if (!dm_target_is_valid(tgt)) { + ret = -EIO; + goto out; + } + + /* + * If we are executing this, we already know that the block device + * is a zoned device and so each target should have support for that + * type of drive. A missing report_zones method means that the target + * driver has a problem. + */ + if (WARN_ON(!tgt->type->report_zones)) { + ret = -EIO; + goto out; + } + + /* + * blkdev_report_zones() will loop and call this again to cover all the + * zones of the target, eventually moving on to the next target. + * So there is no need to loop here trying to fill the entire array + * of zones. + */ + ret = tgt->type->report_zones(tgt, sector, zones, + nr_zones, gfp_mask); + +out: + dm_put_live_table(md, srcu_idx); + return ret; +#else + return -ENOTSUPP; +#endif +} + static int dm_prepare_ioctl(struct mapped_device *md, int *srcu_idx, struct block_device **bdev) __acquires(md->io_barrier) @@ -1155,93 +1206,49 @@ void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors) EXPORT_SYMBOL_GPL(dm_accept_partial_bio); /* - * The zone descriptors obtained with a zone report indicate zone positions - * within the target backing device, regardless of that device is a partition - * and regardless of the target mapping start sector on the device or partition. - * The zone descriptors start sector and write pointer position must be adjusted - * to match their relative position within the dm device. - * A target may call dm_remap_zone_report() after completion of a - * REQ_OP_ZONE_REPORT bio to remap the zone descriptors obtained from the - * backing device. + * The zone descriptors obtained with a zone report indicate + * zone positions within the underlying device of the target. The zone + * descriptors must be remapped to match their position within the dm device. + * The caller target should obtain the zones information using + * blkdev_report_zones() to ensure that remapping for partition offset is + * already handled. */ -void dm_remap_zone_report(struct dm_target *ti, struct bio *bio, sector_t start) +void dm_remap_zone_report(struct dm_target *ti, sector_t start, + struct blk_zone *zones, unsigned int *nr_zones) { #ifdef CONFIG_BLK_DEV_ZONED - struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone); - struct bio *report_bio = tio->io->orig_bio; - struct blk_zone_report_hdr *hdr = NULL; struct blk_zone *zone; - unsigned int nr_rep = 0; - unsigned int ofst; - sector_t part_offset; - struct bio_vec bvec; - struct bvec_iter iter; - void *addr; - - if (bio->bi_status) - return; - - /* - * bio sector was incremented by the request size on completion. Taking - * into account the original request sector, the target start offset on - * the backing device and the target mapping offset (ti->begin), the - * start sector of the backing device. The partition offset is always 0 - * if the target uses a whole device. - */ - part_offset = bio->bi_iter.bi_sector + ti->begin - (start + bio_end_sector(report_bio)); + unsigned int nrz = *nr_zones; + int i; /* - * Remap the start sector of the reported zones. For sequential zones, - * also remap the write pointer position. + * Remap the start sector and write pointer position of the zones in + * the array. Since we may have obtained from the target underlying + * device more zones that the target size, also adjust the number + * of zones. */ - bio_for_each_segment(bvec, report_bio, iter) { - addr = kmap_atomic(bvec.bv_page); - - /* Remember the report header in the first page */ - if (!hdr) { - hdr = addr; - ofst = sizeof(struct blk_zone_report_hdr); - } else - ofst = 0; - - /* Set zones start sector */ - while (hdr->nr_zones && ofst < bvec.bv_len) { - zone = addr + ofst; - zone->start -= part_offset; - if (zone->start >= start + ti->len) { - hdr->nr_zones = 0; - break; - } - zone->start = zone->start + ti->begin - start; - if (zone->type != BLK_ZONE_TYPE_CONVENTIONAL) { - if (zone->cond == BLK_ZONE_COND_FULL) - zone->wp = zone->start + zone->len; - else if (zone->cond == BLK_ZONE_COND_EMPTY) - zone->wp = zone->start; - else - zone->wp = zone->wp + ti->begin - start - part_offset; - } - ofst += sizeof(struct blk_zone); - hdr->nr_zones--; - nr_rep++; + for (i = 0; i < nrz; i++) { + zone = zones + i; + if (zone->start >= start + ti->len) { + memset(zone, 0, sizeof(struct blk_zone) * (nrz - i)); + break; } - if (addr != hdr) - kunmap_atomic(addr); + zone->start = zone->start + ti->begin - start; + if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL) + continue; - if (!hdr->nr_zones) - break; - } - - if (hdr) { - hdr->nr_zones = nr_rep; - kunmap_atomic(hdr); + if (zone->cond == BLK_ZONE_COND_FULL) + zone->wp = zone->start + zone->len; + else if (zone->cond == BLK_ZONE_COND_EMPTY) + zone->wp = zone->start; + else + zone->wp = zone->wp + ti->begin - start; } - bio_advance(report_bio, report_bio->bi_iter.bi_size); - + *nr_zones = i; #else /* !CONFIG_BLK_DEV_ZONED */ - bio->bi_status = BLK_STS_NOTSUPP; + *nr_zones = 0; #endif } EXPORT_SYMBOL_GPL(dm_remap_zone_report); @@ -1327,8 +1334,7 @@ static int clone_bio(struct dm_target_io *tio, struct bio *bio, return r; } - if (bio_op(bio) != REQ_OP_ZONE_REPORT) - bio_advance(clone, to_bytes(sector - clone->bi_iter.bi_sector)); + bio_advance(clone, to_bytes(sector - clone->bi_iter.bi_sector)); clone->bi_iter.bi_size = to_bytes(len); if (unlikely(bio_integrity(bio) != NULL)) @@ -1541,7 +1547,6 @@ static bool __process_abnormal_io(struct clone_info *ci, struct dm_target *ti, */ static int __split_and_process_non_flush(struct clone_info *ci) { - struct bio *bio = ci->bio; struct dm_target *ti; unsigned len; int r; @@ -1553,11 +1558,7 @@ static int __split_and_process_non_flush(struct clone_info *ci) if (unlikely(__process_abnormal_io(ci, ti, &r))) return r; - if (bio_op(bio) == REQ_OP_ZONE_REPORT) - len = ci->sector_count; - else - len = min_t(sector_t, max_io_len(ci->sector, ti), - ci->sector_count); + len = min_t(sector_t, max_io_len(ci->sector, ti), ci->sector_count); r = __clone_and_map_data_bio(ci, ti, ci->sector, &len); if (r < 0) @@ -1616,9 +1617,6 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md, * We take a clone of the original to store in * ci.io->orig_bio to be used by end_io_acct() and * for dec_pending to use for completion handling. - * As this path is not used for REQ_OP_ZONE_REPORT, - * the usage of io->orig_bio in dm_remap_zone_report() - * won't be affected by this reassignment. */ struct bio *b = bio_split(bio, bio_sectors(bio) - ci.sector_count, GFP_NOIO, &md->queue->bio_split); @@ -3167,6 +3165,7 @@ static const struct block_device_operations dm_blk_dops = { .release = dm_blk_close, .ioctl = dm_blk_ioctl, .getgeo = dm_blk_getgeo, + .report_zones = dm_blk_report_zones, .pr_ops = &dm_pr_ops, .owner = THIS_MODULE }; diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index b762d0fd773c..42c0f299021d 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1272,8 +1272,6 @@ static int sd_init_command(struct scsi_cmnd *cmd) case REQ_OP_READ: case REQ_OP_WRITE: return sd_setup_read_write_cmnd(cmd); - case REQ_OP_ZONE_REPORT: - return sd_zbc_setup_report_cmnd(cmd); case REQ_OP_ZONE_RESET: return sd_zbc_setup_reset_cmnd(cmd); default: @@ -1802,6 +1800,7 @@ static const struct block_device_operations sd_fops = { .check_events = sd_check_events, .revalidate_disk = sd_revalidate_disk, .unlock_native_capacity = sd_unlock_native_capacity, + .report_zones = sd_zbc_report_zones, .pr_ops = &sd_pr_ops, }; @@ -1953,16 +1952,6 @@ static int sd_done(struct scsi_cmnd *SCpnt) scsi_set_resid(SCpnt, blk_rq_bytes(req)); } break; - case REQ_OP_ZONE_REPORT: - if (!result) { - good_bytes = scsi_bufflen(SCpnt) - - scsi_get_resid(SCpnt); - scsi_set_resid(SCpnt, 0); - } else { - good_bytes = 0; - scsi_set_resid(SCpnt, blk_rq_bytes(req)); - } - break; default: /* * In case of bogus fw or device, we could end up having diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h index a7d4f50b67d4..f72f20fd0d8b 100644 --- a/drivers/scsi/sd.h +++ b/drivers/scsi/sd.h @@ -273,10 +273,12 @@ static inline int sd_is_zoned(struct scsi_disk *sdkp) extern int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buffer); extern void sd_zbc_remove(struct scsi_disk *sdkp); extern void sd_zbc_print_zones(struct scsi_disk *sdkp); -extern int sd_zbc_setup_report_cmnd(struct scsi_cmnd *cmd); extern int sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd); extern void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes, struct scsi_sense_hdr *sshdr); +extern int sd_zbc_report_zones(struct gendisk *disk, sector_t sector, + struct blk_zone *zones, unsigned int *nr_zones, + gfp_t gfp_mask); #else /* CONFIG_BLK_DEV_ZONED */ @@ -290,11 +292,6 @@ static inline void sd_zbc_remove(struct scsi_disk *sdkp) {} static inline void sd_zbc_print_zones(struct scsi_disk *sdkp) {} -static inline int sd_zbc_setup_report_cmnd(struct scsi_cmnd *cmd) -{ - return BLKPREP_INVALID; -} - static inline int sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd) { return BLKPREP_INVALID; @@ -304,6 +301,8 @@ static inline void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes, struct scsi_sense_hdr *sshdr) {} +#define sd_zbc_report_zones NULL + #endif /* CONFIG_BLK_DEV_ZONED */ #endif /* _SCSI_DISK_H */ diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index 0678e1e108b0..0f2cfc81fce3 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -62,7 +62,7 @@ static void sd_zbc_parse_report(struct scsi_disk *sdkp, u8 *buf, } /** - * sd_zbc_report_zones - Issue a REPORT ZONES scsi command. + * sd_zbc_do_report_zones - Issue a REPORT ZONES scsi command. * @sdkp: The target disk * @buf: Buffer to use for the reply * @buflen: the buffer size @@ -75,9 +75,9 @@ static void sd_zbc_parse_report(struct scsi_disk *sdkp, u8 *buf, * zones and will only report the count of zones fitting in the command reply * buffer. */ -static int sd_zbc_report_zones(struct scsi_disk *sdkp, unsigned char *buf, - unsigned int buflen, sector_t lba, - bool partial) +static int sd_zbc_do_report_zones(struct scsi_disk *sdkp, unsigned char *buf, + unsigned int buflen, sector_t lba, + bool partial) { struct scsi_device *sdp = sdkp->device; const int timeout = sdp->request_queue->rq_timeout; @@ -118,108 +118,56 @@ static int sd_zbc_report_zones(struct scsi_disk *sdkp, unsigned char *buf, } /** - * sd_zbc_setup_report_cmnd - Prepare a REPORT ZONES scsi command - * @cmd: The command to setup + * sd_zbc_report_zones - Disk report zones operation. + * @disk: The target disk + * @sector: Start 512B sector of the report + * @zones: Array of zone descriptors + * @nr_zones: Number of descriptors in the array + * @gfp_mask: Memory allocation mask * - * Call in sd_init_command() for a REQ_OP_ZONE_REPORT request. + * Execute a report zones command on the target disk. */ -int sd_zbc_setup_report_cmnd(struct scsi_cmnd *cmd) +int sd_zbc_report_zones(struct gendisk *disk, sector_t sector, + struct blk_zone *zones, unsigned int *nr_zones, + gfp_t gfp_mask) { - struct request *rq = cmd->request; - struct scsi_disk *sdkp = scsi_disk(rq->rq_disk); - sector_t lba, sector = blk_rq_pos(rq); - unsigned int nr_bytes = blk_rq_bytes(rq); - int ret; - - WARN_ON(nr_bytes == 0); + struct scsi_disk *sdkp = scsi_disk(disk); + unsigned int i, buflen, nrz = *nr_zones; + unsigned char *buf; + size_t offset = 0; + int ret = 0; if (!sd_is_zoned(sdkp)) /* Not a zoned device */ - return BLKPREP_KILL; - - ret = scsi_init_io(cmd); - if (ret != BLKPREP_OK) - return ret; - - cmd->cmd_len = 16; - memset(cmd->cmnd, 0, cmd->cmd_len); - cmd->cmnd[0] = ZBC_IN; - cmd->cmnd[1] = ZI_REPORT_ZONES; - lba = sectors_to_logical(sdkp->device, sector); - put_unaligned_be64(lba, &cmd->cmnd[2]); - put_unaligned_be32(nr_bytes, &cmd->cmnd[10]); - /* Do partial report for speeding things up */ - cmd->cmnd[14] = ZBC_REPORT_ZONE_PARTIAL; - - cmd->sc_data_direction = DMA_FROM_DEVICE; - cmd->sdb.length = nr_bytes; - cmd->transfersize = sdkp->device->sector_size; - cmd->allowed = 0; + return -EOPNOTSUPP; - return BLKPREP_OK; -} - -/** - * sd_zbc_report_zones_complete - Process a REPORT ZONES scsi command reply. - * @scmd: The completed report zones command - * @good_bytes: reply size in bytes - * - * Convert all reported zone descriptors to struct blk_zone. The conversion - * is done in-place, directly in the request specified sg buffer. - */ -static void sd_zbc_report_zones_complete(struct scsi_cmnd *scmd, - unsigned int good_bytes) -{ - struct request *rq = scmd->request; - struct scsi_disk *sdkp = scsi_disk(rq->rq_disk); - struct sg_mapping_iter miter; - struct blk_zone_report_hdr hdr; - struct blk_zone zone; - unsigned int offset, bytes = 0; - unsigned long flags; - u8 *buf; - - if (good_bytes < 64) - return; - - memset(&hdr, 0, sizeof(struct blk_zone_report_hdr)); - - sg_miter_start(&miter, scsi_sglist(scmd), scsi_sg_count(scmd), - SG_MITER_TO_SG | SG_MITER_ATOMIC); + /* + * Get a reply buffer for the number of requested zones plus a header. + * For ATA, buffers must be aligned to 512B. + */ + buflen = roundup((nrz + 1) * 64, 512); + buf = kmalloc(buflen, gfp_mask); + if (!buf) + return -ENOMEM; - local_irq_save(flags); - while (sg_miter_next(&miter) && bytes < good_bytes) { + ret = sd_zbc_do_report_zones(sdkp, buf, buflen, + sectors_to_logical(sdkp->device, sector), true); + if (ret) + goto out_free_buf; - buf = miter.addr; - offset = 0; + nrz = min(nrz, get_unaligned_be32(&buf[0]) / 64); + for (i = 0; i < nrz; i++) { + offset += 64; + sd_zbc_parse_report(sdkp, buf + offset, zones); + zones++; + } - if (bytes == 0) { - /* Set the report header */ - hdr.nr_zones = min_t(unsigned int, - (good_bytes - 64) / 64, - get_unaligned_be32(&buf[0]) / 64); - memcpy(buf, &hdr, sizeof(struct blk_zone_report_hdr)); - offset += 64; - bytes += 64; - } + *nr_zones = nrz; - /* Parse zone descriptors */ - while (offset < miter.length && hdr.nr_zones) { - WARN_ON(offset > miter.length); - buf = miter.addr + offset; - sd_zbc_parse_report(sdkp, buf, &zone); - memcpy(buf, &zone, sizeof(struct blk_zone)); - offset += 64; - bytes += 64; - hdr.nr_zones--; - } - - if (!hdr.nr_zones) - break; +out_free_buf: + kfree(buf); - } - sg_miter_stop(&miter); - local_irq_restore(flags); + return ret; } /** @@ -302,13 +250,6 @@ void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes, case REQ_OP_WRITE_ZEROES: case REQ_OP_WRITE_SAME: break; - - case REQ_OP_ZONE_REPORT: - - if (!result) - sd_zbc_report_zones_complete(cmd, good_bytes); - break; - } } @@ -390,7 +331,7 @@ static int sd_zbc_check_zones(struct scsi_disk *sdkp, u32 *zblocks) return -ENOMEM; /* Do a report zone to get max_lba and the same field */ - ret = sd_zbc_report_zones(sdkp, buf, SD_ZBC_BUF_SIZE, 0, false); + ret = sd_zbc_do_report_zones(sdkp, buf, SD_ZBC_BUF_SIZE, 0, false); if (ret) goto out_free; @@ -447,8 +388,8 @@ static int sd_zbc_check_zones(struct scsi_disk *sdkp, u32 *zblocks) } if (block < sdkp->capacity) { - ret = sd_zbc_report_zones(sdkp, buf, - SD_ZBC_BUF_SIZE, block, true); + ret = sd_zbc_do_report_zones(sdkp, buf, SD_ZBC_BUF_SIZE, + block, true); if (ret) goto out_free; } @@ -565,8 +506,8 @@ sd_zbc_setup_seq_zones_bitmap(struct scsi_disk *sdkp, u32 zone_shift, goto out; while (lba < sdkp->capacity) { - ret = sd_zbc_report_zones(sdkp, buf, SD_ZBC_BUF_SIZE, - lba, true); + ret = sd_zbc_do_report_zones(sdkp, buf, SD_ZBC_BUF_SIZE, lba, + true); if (ret) goto out; lba = sd_zbc_get_seq_zones(sdkp, buf, SD_ZBC_BUF_SIZE, diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 9578c7ab1eb6..093a818c5b68 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -283,8 +283,6 @@ enum req_opf { REQ_OP_FLUSH = 2, /* discard sectors */ REQ_OP_DISCARD = 3, - /* get zone information */ - REQ_OP_ZONE_REPORT = 4, /* securely erase sectors */ REQ_OP_SECURE_ERASE = 5, /* seset a zone write pointer */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6bb845f9601a..51fe6472ce02 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -396,11 +396,6 @@ struct queue_limits { #ifdef CONFIG_BLK_DEV_ZONED -struct blk_zone_report_hdr { - unsigned int nr_zones; - u8 padding[60]; -}; - extern unsigned int blkdev_nr_zones(struct block_device *bdev); extern int blkdev_report_zones(struct block_device *bdev, sector_t sector, struct blk_zone *zones, @@ -1867,6 +1862,9 @@ struct block_device_operations { int (*getgeo)(struct block_device *, struct hd_geometry *); /* this callback is with swap_lock and sometimes page table lock held */ void (*swap_slot_free_notify) (struct block_device *, unsigned long); + int (*report_zones)(struct gendisk *, sector_t sector, + struct blk_zone *zones, unsigned int *nr_zones, + gfp_t gfp_mask); struct module *owner; const struct pr_ops *pr_ops; }; diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 6fb0808e87c8..a23b396a8edc 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -92,6 +92,11 @@ typedef int (*dm_message_fn) (struct dm_target *ti, unsigned argc, char **argv, typedef int (*dm_prepare_ioctl_fn) (struct dm_target *ti, struct block_device **bdev); +typedef int (*dm_report_zones_fn) (struct dm_target *ti, sector_t sector, + struct blk_zone *zones, + unsigned int *nr_zones, + gfp_t gfp_mask); + /* * These iteration functions are typically used to check (and combine) * properties of underlying devices. @@ -180,6 +185,9 @@ struct target_type { dm_status_fn status; dm_message_fn message; dm_prepare_ioctl_fn prepare_ioctl; +#ifdef CONFIG_BLK_DEV_ZONED + dm_report_zones_fn report_zones; +#endif dm_busy_fn busy; dm_iterate_devices_fn iterate_devices; dm_io_hints_fn io_hints; @@ -420,8 +428,8 @@ struct gendisk *dm_disk(struct mapped_device *md); int dm_suspended(struct dm_target *ti); int dm_noflush_suspending(struct dm_target *ti); void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors); -void dm_remap_zone_report(struct dm_target *ti, struct bio *bio, - sector_t start); +void dm_remap_zone_report(struct dm_target *ti, sector_t start, + struct blk_zone *zones, unsigned int *nr_zones); union map_info *dm_get_rq_mapinfo(struct request *rq); struct queue_limits *dm_get_queue_limits(struct mapped_device *md); diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 795698925d20..3ec73f17ee2a 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -82,7 +82,6 @@ TRACE_DEFINE_ENUM(CP_TRIMMED); { REQ_OP_WRITE, "WRITE" }, \ { REQ_OP_FLUSH, "FLUSH" }, \ { REQ_OP_DISCARD, "DISCARD" }, \ - { REQ_OP_ZONE_REPORT, "ZONE_REPORT" }, \ { REQ_OP_SECURE_ERASE, "SECURE_ERASE" }, \ { REQ_OP_ZONE_RESET, "ZONE_RESET" }, \ { REQ_OP_WRITE_SAME, "WRITE_SAME" }, \ -- cgit v1.2.3 From bf5054569653c491ece544cc7ee333ae53b47121 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 12 Oct 2018 19:08:50 +0900 Subject: block: Introduce blk_revalidate_disk_zones() Drivers exposing zoned block devices have to initialize and maintain correctness (i.e. revalidate) of the device zone bitmaps attached to the device request queue (seq_zones_bitmap and seq_zones_wlock). To simplify coding this, introduce a generic helper function blk_revalidate_disk_zones() suitable for most (and likely all) cases. This new function always update the seq_zones_bitmap and seq_zones_wlock bitmaps as well as the queue nr_zones field when called for a disk using a request based queue. For a disk using a BIO based queue, only the number of zones is updated since these queues do not have schedulers and so do not need the zone bitmaps. With this change, the zone bitmap initialization code in sd_zbc.c can be replaced with a call to this function in sd_zbc_read_zones(), which is called from the disk revalidate block operation method. A call to blk_revalidate_disk_zones() is also added to the null_blk driver for devices created with the zoned mode enabled. Finally, to ensure that zoned devices created with dm-linear or dm-flakey expose the correct number of zones through sysfs, a call to blk_revalidate_disk_zones() is added to dm_table_set_restrictions(). The zone bitmaps allocated and initialized with blk_revalidate_disk_zones() are freed automatically from __blk_release_queue() using the block internal function blk_queue_free_zone_bitmaps(). Reviewed-by: Hannes Reinecke Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Reviewed-by: Mike Snitzer Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- block/blk-sysfs.c | 2 + block/blk-zoned.c | 136 ++++++++++++++++++++++++++ block/blk.h | 6 ++ drivers/block/null_blk_main.c | 7 ++ drivers/md/dm-table.c | 10 ++ drivers/scsi/sd.c | 2 - drivers/scsi/sd.h | 4 - drivers/scsi/sd_zbc.c | 218 +++++------------------------------------- include/linux/blkdev.h | 7 ++ 9 files changed, 194 insertions(+), 198 deletions(-) (limited to 'include/linux') diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 92be8092ca4f..0641533597f1 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -852,6 +852,8 @@ static void __blk_release_queue(struct work_struct *work) if (q->queue_tags) __blk_queue_free_tags(q); + blk_queue_free_zone_bitmaps(q); + if (!q->mq_ops) { if (q->exit_rq_fn) q->exit_rq_fn(q, q->fq->flush_rq); diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 90cf503091d5..13ba2011a306 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -12,6 +12,7 @@ #include #include #include +#include #include "blk.h" @@ -359,3 +360,138 @@ int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode, return blkdev_reset_zones(bdev, zrange.sector, zrange.nr_sectors, GFP_KERNEL); } + +static inline unsigned long *blk_alloc_zone_bitmap(int node, + unsigned int nr_zones) +{ + return kcalloc_node(BITS_TO_LONGS(nr_zones), sizeof(unsigned long), + GFP_NOIO, node); +} + +/* + * Allocate an array of struct blk_zone to get nr_zones zone information. + * The allocated array may be smaller than nr_zones. + */ +static struct blk_zone *blk_alloc_zones(int node, unsigned int *nr_zones) +{ + size_t size = *nr_zones * sizeof(struct blk_zone); + struct page *page; + int order; + + for (order = get_order(size); order > 0; order--) { + page = alloc_pages_node(node, GFP_NOIO | __GFP_ZERO, order); + if (page) { + *nr_zones = min_t(unsigned int, *nr_zones, + (PAGE_SIZE << order) / sizeof(struct blk_zone)); + return page_address(page); + } + } + + return NULL; +} + +void blk_queue_free_zone_bitmaps(struct request_queue *q) +{ + kfree(q->seq_zones_bitmap); + q->seq_zones_bitmap = NULL; + kfree(q->seq_zones_wlock); + q->seq_zones_wlock = NULL; +} + +/** + * blk_revalidate_disk_zones - (re)allocate and initialize zone bitmaps + * @disk: Target disk + * + * Helper function for low-level device drivers to (re) allocate and initialize + * a disk request queue zone bitmaps. This functions should normally be called + * within the disk ->revalidate method. For BIO based queues, no zone bitmap + * is allocated. + */ +int blk_revalidate_disk_zones(struct gendisk *disk) +{ + struct request_queue *q = disk->queue; + unsigned int nr_zones = __blkdev_nr_zones(q, get_capacity(disk)); + unsigned long *seq_zones_wlock = NULL, *seq_zones_bitmap = NULL; + unsigned int i, rep_nr_zones = 0, z = 0, nrz; + struct blk_zone *zones = NULL; + sector_t sector = 0; + int ret = 0; + + /* + * BIO based queues do not use a scheduler so only q->nr_zones + * needs to be updated so that the sysfs exposed value is correct. + */ + if (!queue_is_rq_based(q)) { + q->nr_zones = nr_zones; + return 0; + } + + if (!blk_queue_is_zoned(q) || !nr_zones) { + nr_zones = 0; + goto update; + } + + /* Allocate bitmaps */ + ret = -ENOMEM; + seq_zones_wlock = blk_alloc_zone_bitmap(q->node, nr_zones); + if (!seq_zones_wlock) + goto out; + seq_zones_bitmap = blk_alloc_zone_bitmap(q->node, nr_zones); + if (!seq_zones_bitmap) + goto out; + + /* Get zone information and initialize seq_zones_bitmap */ + rep_nr_zones = nr_zones; + zones = blk_alloc_zones(q->node, &rep_nr_zones); + if (!zones) + goto out; + + while (z < nr_zones) { + nrz = min(nr_zones - z, rep_nr_zones); + ret = blk_report_zones(disk, sector, zones, &nrz, GFP_NOIO); + if (ret) + goto out; + if (!nrz) + break; + for (i = 0; i < nrz; i++) { + if (zones[i].type != BLK_ZONE_TYPE_CONVENTIONAL) + set_bit(z, seq_zones_bitmap); + z++; + } + sector += nrz * blk_queue_zone_sectors(q); + } + + if (WARN_ON(z != nr_zones)) { + ret = -EIO; + goto out; + } + +update: + /* + * Install the new bitmaps, making sure the queue is stopped and + * all I/Os are completed (i.e. a scheduler is not referencing the + * bitmaps). + */ + blk_mq_freeze_queue(q); + q->nr_zones = nr_zones; + swap(q->seq_zones_wlock, seq_zones_wlock); + swap(q->seq_zones_bitmap, seq_zones_bitmap); + blk_mq_unfreeze_queue(q); + +out: + free_pages((unsigned long)zones, + get_order(rep_nr_zones * sizeof(struct blk_zone))); + kfree(seq_zones_wlock); + kfree(seq_zones_bitmap); + + if (ret) { + pr_warn("%s: failed to revalidate zones\n", disk->disk_name); + blk_mq_freeze_queue(q); + blk_queue_free_zone_bitmaps(q); + blk_mq_unfreeze_queue(q); + } + + return ret; +} +EXPORT_SYMBOL_GPL(blk_revalidate_disk_zones); + diff --git a/block/blk.h b/block/blk.h index 93574baaa6b8..a1841b8ff129 100644 --- a/block/blk.h +++ b/block/blk.h @@ -490,4 +490,10 @@ static inline int blk_iolatency_init(struct request_queue *q) { return 0; } struct bio *blk_next_bio(struct bio *bio, unsigned int nr_pages, gfp_t gfp); +#ifdef CONFIG_BLK_DEV_ZONED +void blk_queue_free_zone_bitmaps(struct request_queue *q); +#else +static inline void blk_queue_free_zone_bitmaps(struct request_queue *q) {} +#endif + #endif /* BLK_INTERNAL_H */ diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c index 5ba426dbf377..09339203dfba 100644 --- a/drivers/block/null_blk_main.c +++ b/drivers/block/null_blk_main.c @@ -1528,6 +1528,13 @@ static int null_gendisk_register(struct nullb *nullb) disk->queue = nullb->q; strncpy(disk->disk_name, nullb->disk_name, DISK_NAME_LEN); + if (nullb->dev->zoned) { + int ret = blk_revalidate_disk_zones(disk); + + if (ret != 0) + return ret; + } + add_disk(disk); return 0; } diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 3d0e2c198f06..fb4bea20657b 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -1937,6 +1937,16 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, */ if (blk_queue_add_random(q) && dm_table_all_devices_attribute(t, device_is_not_random)) blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, q); + + /* + * For a zoned target, the number of zones should be updated for the + * correct value to be exposed in sysfs queue/nr_zones. For a BIO based + * target, this is all that is needed. For a request based target, the + * queue zone bitmaps must also be updated. + * Use blk_revalidate_disk_zones() to handle this. + */ + if (blk_queue_is_zoned(q)) + blk_revalidate_disk_zones(t->md->disk); } unsigned int dm_table_get_num_targets(struct dm_table *t) diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 42c0f299021d..3bb2b3351e35 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3414,8 +3414,6 @@ static int sd_remove(struct device *dev) del_gendisk(sdkp->disk); sd_shutdown(dev); - sd_zbc_remove(sdkp); - free_opal_dev(sdkp->opal_dev); blk_register_region(devt, SD_MINORS, NULL, diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h index f72f20fd0d8b..1d63f3a23ffb 100644 --- a/drivers/scsi/sd.h +++ b/drivers/scsi/sd.h @@ -76,7 +76,6 @@ struct scsi_disk { #ifdef CONFIG_BLK_DEV_ZONED u32 nr_zones; u32 zone_blocks; - u32 zone_shift; u32 zones_optimal_open; u32 zones_optimal_nonseq; u32 zones_max_open; @@ -271,7 +270,6 @@ static inline int sd_is_zoned(struct scsi_disk *sdkp) #ifdef CONFIG_BLK_DEV_ZONED extern int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buffer); -extern void sd_zbc_remove(struct scsi_disk *sdkp); extern void sd_zbc_print_zones(struct scsi_disk *sdkp); extern int sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd); extern void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes, @@ -288,8 +286,6 @@ static inline int sd_zbc_read_zones(struct scsi_disk *sdkp, return 0; } -static inline void sd_zbc_remove(struct scsi_disk *sdkp) {} - static inline void sd_zbc_print_zones(struct scsi_disk *sdkp) {} static inline int sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd) diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index 0f2cfc81fce3..e06c48c866e4 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -425,191 +425,10 @@ out_free: return ret; } -/** - * sd_zbc_alloc_zone_bitmap - Allocate a zone bitmap (one bit per zone). - * @nr_zones: Number of zones to allocate space for. - * @numa_node: NUMA node to allocate the memory from. - */ -static inline unsigned long * -sd_zbc_alloc_zone_bitmap(u32 nr_zones, int numa_node) -{ - return kcalloc_node(BITS_TO_LONGS(nr_zones), sizeof(unsigned long), - GFP_KERNEL, numa_node); -} - -/** - * sd_zbc_get_seq_zones - Parse report zones reply to identify sequential zones - * @sdkp: disk used - * @buf: report reply buffer - * @buflen: length of @buf - * @zone_shift: logarithm base 2 of the number of blocks in a zone - * @seq_zones_bitmap: bitmap of sequential zones to set - * - * Parse reported zone descriptors in @buf to identify sequential zones and - * set the reported zone bit in @seq_zones_bitmap accordingly. - * Since read-only and offline zones cannot be written, do not - * mark them as sequential in the bitmap. - * Return the LBA after the last zone reported. - */ -static sector_t sd_zbc_get_seq_zones(struct scsi_disk *sdkp, unsigned char *buf, - unsigned int buflen, u32 zone_shift, - unsigned long *seq_zones_bitmap) -{ - sector_t lba, next_lba = sdkp->capacity; - unsigned int buf_len, list_length; - unsigned char *rec; - u8 type, cond; - - list_length = get_unaligned_be32(&buf[0]) + 64; - buf_len = min(list_length, buflen); - rec = buf + 64; - - while (rec < buf + buf_len) { - type = rec[0] & 0x0f; - cond = (rec[1] >> 4) & 0xf; - lba = get_unaligned_be64(&rec[16]); - if (type != ZBC_ZONE_TYPE_CONV && - cond != ZBC_ZONE_COND_READONLY && - cond != ZBC_ZONE_COND_OFFLINE) - set_bit(lba >> zone_shift, seq_zones_bitmap); - next_lba = lba + get_unaligned_be64(&rec[8]); - rec += 64; - } - - return next_lba; -} - -/** - * sd_zbc_setup_seq_zones_bitmap - Initialize a seq zone bitmap. - * @sdkp: target disk - * @zone_shift: logarithm base 2 of the number of blocks in a zone - * @nr_zones: number of zones to set up a seq zone bitmap for - * - * Allocate a zone bitmap and initialize it by identifying sequential zones. - */ -static unsigned long * -sd_zbc_setup_seq_zones_bitmap(struct scsi_disk *sdkp, u32 zone_shift, - u32 nr_zones) -{ - struct request_queue *q = sdkp->disk->queue; - unsigned long *seq_zones_bitmap; - sector_t lba = 0; - unsigned char *buf; - int ret = -ENOMEM; - - seq_zones_bitmap = sd_zbc_alloc_zone_bitmap(nr_zones, q->node); - if (!seq_zones_bitmap) - return ERR_PTR(-ENOMEM); - - buf = kmalloc(SD_ZBC_BUF_SIZE, GFP_KERNEL); - if (!buf) - goto out; - - while (lba < sdkp->capacity) { - ret = sd_zbc_do_report_zones(sdkp, buf, SD_ZBC_BUF_SIZE, lba, - true); - if (ret) - goto out; - lba = sd_zbc_get_seq_zones(sdkp, buf, SD_ZBC_BUF_SIZE, - zone_shift, seq_zones_bitmap); - } - - if (lba != sdkp->capacity) { - /* Something went wrong */ - ret = -EIO; - } - -out: - kfree(buf); - if (ret) { - kfree(seq_zones_bitmap); - return ERR_PTR(ret); - } - return seq_zones_bitmap; -} - -static void sd_zbc_cleanup(struct scsi_disk *sdkp) -{ - struct request_queue *q = sdkp->disk->queue; - - kfree(q->seq_zones_bitmap); - q->seq_zones_bitmap = NULL; - - kfree(q->seq_zones_wlock); - q->seq_zones_wlock = NULL; - - q->nr_zones = 0; -} - -static int sd_zbc_setup(struct scsi_disk *sdkp, u32 zone_blocks) -{ - struct request_queue *q = sdkp->disk->queue; - u32 zone_shift = ilog2(zone_blocks); - u32 nr_zones; - int ret; - - /* chunk_sectors indicates the zone size */ - blk_queue_chunk_sectors(q, - logical_to_sectors(sdkp->device, zone_blocks)); - nr_zones = round_up(sdkp->capacity, zone_blocks) >> zone_shift; - - /* - * Initialize the device request queue information if the number - * of zones changed. - */ - if (nr_zones != sdkp->nr_zones || nr_zones != q->nr_zones) { - unsigned long *seq_zones_wlock = NULL, *seq_zones_bitmap = NULL; - size_t zone_bitmap_size; - - if (nr_zones) { - seq_zones_wlock = sd_zbc_alloc_zone_bitmap(nr_zones, - q->node); - if (!seq_zones_wlock) { - ret = -ENOMEM; - goto err; - } - - seq_zones_bitmap = sd_zbc_setup_seq_zones_bitmap(sdkp, - zone_shift, nr_zones); - if (IS_ERR(seq_zones_bitmap)) { - ret = PTR_ERR(seq_zones_bitmap); - kfree(seq_zones_wlock); - goto err; - } - } - zone_bitmap_size = BITS_TO_LONGS(nr_zones) * - sizeof(unsigned long); - blk_mq_freeze_queue(q); - if (q->nr_zones != nr_zones) { - /* READ16/WRITE16 is mandatory for ZBC disks */ - sdkp->device->use_16_for_rw = 1; - sdkp->device->use_10_for_rw = 0; - - sdkp->zone_blocks = zone_blocks; - sdkp->zone_shift = zone_shift; - sdkp->nr_zones = nr_zones; - q->nr_zones = nr_zones; - swap(q->seq_zones_wlock, seq_zones_wlock); - swap(q->seq_zones_bitmap, seq_zones_bitmap); - } else if (memcmp(q->seq_zones_bitmap, seq_zones_bitmap, - zone_bitmap_size) != 0) { - memcpy(q->seq_zones_bitmap, seq_zones_bitmap, - zone_bitmap_size); - } - blk_mq_unfreeze_queue(q); - kfree(seq_zones_wlock); - kfree(seq_zones_bitmap); - } - - return 0; - -err: - sd_zbc_cleanup(sdkp); - return ret; -} - int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf) { + struct gendisk *disk = sdkp->disk; + unsigned int nr_zones; u32 zone_blocks; int ret; @@ -634,24 +453,39 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf) goto err; /* The drive satisfies the kernel restrictions: set it up */ - ret = sd_zbc_setup(sdkp, zone_blocks); - if (ret) - goto err; + blk_queue_chunk_sectors(sdkp->disk->queue, + logical_to_sectors(sdkp->device, zone_blocks)); + nr_zones = round_up(sdkp->capacity, zone_blocks) >> ilog2(zone_blocks); + + /* READ16/WRITE16 is mandatory for ZBC disks */ + sdkp->device->use_16_for_rw = 1; + sdkp->device->use_10_for_rw = 0; + + /* + * If something changed, revalidate the disk zone bitmaps once we have + * the capacity, that is on the second revalidate execution during disk + * scan and always during normal revalidate. + */ + if (sdkp->first_scan) + return 0; + if (sdkp->zone_blocks != zone_blocks || + sdkp->nr_zones != nr_zones || + disk->queue->nr_zones != nr_zones) { + ret = blk_revalidate_disk_zones(disk); + if (ret != 0) + goto err; + sdkp->zone_blocks = zone_blocks; + sdkp->nr_zones = nr_zones; + } return 0; err: sdkp->capacity = 0; - sd_zbc_cleanup(sdkp); return ret; } -void sd_zbc_remove(struct scsi_disk *sdkp) -{ - sd_zbc_cleanup(sdkp); -} - void sd_zbc_print_zones(struct scsi_disk *sdkp) { if (!sd_is_zoned(sdkp) || !sdkp->capacity) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 51fe6472ce02..4293dc1cd160 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -402,6 +402,7 @@ extern int blkdev_report_zones(struct block_device *bdev, unsigned int *nr_zones, gfp_t gfp_mask); extern int blkdev_reset_zones(struct block_device *bdev, sector_t sectors, sector_t nr_sectors, gfp_t gfp_mask); +extern int blk_revalidate_disk_zones(struct gendisk *disk); extern int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg); @@ -414,6 +415,12 @@ static inline unsigned int blkdev_nr_zones(struct block_device *bdev) { return 0; } + +static inline int blk_revalidate_disk_zones(struct gendisk *disk) +{ + return 0; +} + static inline int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) -- cgit v1.2.3 From 4d54954a197175c0dcb3c82af0c0740d0c5f827a Mon Sep 17 00:00:00 2001 From: Sebastien Boisvert Date: Fri, 26 Oct 2018 15:02:23 -0700 Subject: include/linux/pfn_t.h: force '~' to be parsed as an unary operator Tracing the event "fs_dax:dax_pmd_insert_mapping" with perf produces this warning: [fs_dax:dax_pmd_insert_mapping] unknown op '~' It is printed in process_op (tools/lib/traceevent/event-parse.c) because '~' is parsed as a binary operator. perf reads the format of fs_dax:dax_pmd_insert_mapping ("print fmt") from /sys/kernel/debug/tracing/events/fs_dax/dax_pmd_insert_mapping/format . The format contains: ~(((u64) ~(~(((1UL) << 12)-1))) ^ \ interpreted as a binary operator by process_op(). This part is generated in the declaration of the event class dax_pmd_insert_mapping_class in include/trace/events/fs_dax.h : __print_flags_u64(__entry->pfn_val & PFN_FLAGS_MASK, "|", PFN_FLAGS_TRACE), This patch adds a pair of parentheses in the declaration of PFN_FLAGS_MASK to make sure that '~' is parsed as a unary operator by perf. The part of the format that was problematic is now: ~(((u64) (~(~(((1UL) << 12)-1)))) Now, all the '~' are parsed as unary operators. Link: http://lkml.kernel.org/r/20181021145939.8760-1-sebhtml@videotron.qc.ca Signed-off-by: Sebastien Boisvert Acked-by: Dan Williams Cc: "Steven Rostedt (VMware)" Cc: Arnaldo Carvalho de Melo Cc: "Tzvetomir Stoyanov (VMware)" Cc: Namhyung Kim Cc: Ross Zwisler Cc: Elenie Godzaridis Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pfn_t.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h index 21713dc14ce2..673546ba7342 100644 --- a/include/linux/pfn_t.h +++ b/include/linux/pfn_t.h @@ -10,7 +10,7 @@ * PFN_DEV - pfn is not covered by system memmap by default * PFN_MAP - pfn has a dynamic page mapping established by a device driver */ -#define PFN_FLAGS_MASK (((u64) ~PAGE_MASK) << (BITS_PER_LONG_LONG - PAGE_SHIFT)) +#define PFN_FLAGS_MASK (((u64) (~PAGE_MASK)) << (BITS_PER_LONG_LONG - PAGE_SHIFT)) #define PFN_SG_CHAIN (1ULL << (BITS_PER_LONG_LONG - 1)) #define PFN_SG_LAST (1ULL << (BITS_PER_LONG_LONG - 2)) #define PFN_DEV (1ULL << (BITS_PER_LONG_LONG - 3)) -- cgit v1.2.3 From 74f213ea25b99fddcf34cbe07dabdb01136bcd86 Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Fri, 26 Oct 2018 15:02:27 -0700 Subject: include/linux/linkage.h: align weak symbols Since WEAK() supposed to be used instead of ENTRY() to define weak symbols, but unlike ENTRY() it doesn't have ALIGN directive. It seems there is no actual reason to not have, so let's add ALIGN to WEAK() too. Link: http://lkml.kernel.org/r/20180920135631.23833-1-aryabinin@virtuozzo.com Signed-off-by: Andrey Ryabinin Will Deacon , Catalin Marinas Cc: Kyeongdon Kim Cc: Ard Biesheuvel Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Mark Rutland Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/linkage.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/linkage.h b/include/linux/linkage.h index d7618c41f74c..7c47b1a471d4 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -90,6 +90,7 @@ #ifndef WEAK #define WEAK(name) \ .weak name ASM_NL \ + ALIGN ASM_NL \ name: #endif -- cgit v1.2.3 From 5780a02fd1e87641ad6a8dd6891a1e890cf45c5d Mon Sep 17 00:00:00 2001 From: Souptick Joarder Date: Fri, 26 Oct 2018 15:02:59 -0700 Subject: fs/iomap.c: change return type to vm_fault_t Change iomap_page_mkwrite() return type to vm_fault_t. see commit 1c8f422059ae ("mm: change return type to vm_fault_t") for reference. Link: http://lkml.kernel.org/r/20180827172050.GA18673@jordon-HP-15-Notebook-PC Signed-off-by: Souptick Joarder Reviewed-by: Matthew Wilcox Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/iomap.c | 2 +- include/linux/iomap.h | 4 +++- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/iomap.c b/fs/iomap.c index ec15cf2ec696..90c2febc93ac 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -1057,7 +1057,7 @@ iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length, return length; } -int iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops) +vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops) { struct page *page = vmf->page; struct inode *inode = file_inode(vmf->vma->vm_file); diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 3555d54bf79a..9a4258154b25 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -6,6 +6,7 @@ #include #include #include +#include struct address_space; struct fiemap_extent_info; @@ -141,7 +142,8 @@ int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, const struct iomap_ops *ops); int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, const struct iomap_ops *ops); -int iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops); +vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, + const struct iomap_ops *ops); int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, loff_t start, loff_t len, const struct iomap_ops *ops); loff_t iomap_seek_hole(struct inode *inode, loff_t offset, -- cgit v1.2.3 From 9b6f7e163cd0f468d1b9696b785659d3c27c8667 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 26 Oct 2018 15:03:19 -0700 Subject: mm: rework memcg kernel stack accounting If CONFIG_VMAP_STACK is set, kernel stacks are allocated using __vmalloc_node_range() with __GFP_ACCOUNT. So kernel stack pages are charged against corresponding memory cgroups on allocation and uncharged on releasing them. The problem is that we do cache kernel stacks in small per-cpu caches and do reuse them for new tasks, which can belong to different memory cgroups. Each stack page still holds a reference to the original cgroup, so the cgroup can't be released until the vmap area is released. To make this happen we need more than two subsequent exits without forks in between on the current cpu, which makes it very unlikely to happen. As a result, I saw a significant number of dying cgroups (in theory, up to 2 * number_of_cpu + number_of_tasks), which can't be released even by significant memory pressure. As a cgroup structure can take a significant amount of memory (first of all, per-cpu data like memcg statistics), it leads to a noticeable waste of memory. Link: http://lkml.kernel.org/r/20180827162621.30187-1-guro@fb.com Fixes: ac496bf48d97 ("fork: Optimize task creation by caching two thread stacks per CPU if CONFIG_VMAP_STACK=y") Signed-off-by: Roman Gushchin Reviewed-by: Shakeel Butt Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Andy Lutomirski Cc: Konstantin Khlebnikov Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 13 ++++++++++- kernel/fork.c | 55 +++++++++++++++++++++++++++++++++++++++++----- 2 files changed, 61 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 652f602167df..4399cc3f00e4 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1268,10 +1268,11 @@ struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep); void memcg_kmem_put_cache(struct kmem_cache *cachep); int memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order, struct mem_cgroup *memcg); + +#ifdef CONFIG_MEMCG_KMEM int memcg_kmem_charge(struct page *page, gfp_t gfp, int order); void memcg_kmem_uncharge(struct page *page, int order); -#ifdef CONFIG_MEMCG_KMEM extern struct static_key_false memcg_kmem_enabled_key; extern struct workqueue_struct *memcg_kmem_cache_wq; @@ -1307,6 +1308,16 @@ extern int memcg_expand_shrinker_maps(int new_id); extern void memcg_set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id); #else + +static inline int memcg_kmem_charge(struct page *page, gfp_t gfp, int order) +{ + return 0; +} + +static inline void memcg_kmem_uncharge(struct page *page, int order) +{ +} + #define for_each_memcg_cache_index(_idx) \ for (; NULL; ) diff --git a/kernel/fork.c b/kernel/fork.c index f0b58479534f..3c719fec46c5 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -223,9 +223,14 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) return s->addr; } + /* + * Allocated stacks are cached and later reused by new threads, + * so memcg accounting is performed manually on assigning/releasing + * stacks to tasks. Drop __GFP_ACCOUNT. + */ stack = __vmalloc_node_range(THREAD_SIZE, THREAD_ALIGN, VMALLOC_START, VMALLOC_END, - THREADINFO_GFP, + THREADINFO_GFP & ~__GFP_ACCOUNT, PAGE_KERNEL, 0, node, __builtin_return_address(0)); @@ -248,9 +253,19 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) static inline void free_thread_stack(struct task_struct *tsk) { #ifdef CONFIG_VMAP_STACK - if (task_stack_vm_area(tsk)) { + struct vm_struct *vm = task_stack_vm_area(tsk); + + if (vm) { int i; + for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) { + mod_memcg_page_state(vm->pages[i], + MEMCG_KERNEL_STACK_KB, + -(int)(PAGE_SIZE / 1024)); + + memcg_kmem_uncharge(vm->pages[i], 0); + } + for (i = 0; i < NR_CACHED_STACKS; i++) { if (this_cpu_cmpxchg(cached_stacks[i], NULL, tsk->stack_vm_area) != NULL) @@ -351,10 +366,6 @@ static void account_kernel_stack(struct task_struct *tsk, int account) NR_KERNEL_STACK_KB, PAGE_SIZE / 1024 * account); } - - /* All stack pages belong to the same memcg. */ - mod_memcg_page_state(vm->pages[0], MEMCG_KERNEL_STACK_KB, - account * (THREAD_SIZE / 1024)); } else { /* * All stack pages are in the same zone and belong to the @@ -370,6 +381,35 @@ static void account_kernel_stack(struct task_struct *tsk, int account) } } +static int memcg_charge_kernel_stack(struct task_struct *tsk) +{ +#ifdef CONFIG_VMAP_STACK + struct vm_struct *vm = task_stack_vm_area(tsk); + int ret; + + if (vm) { + int i; + + for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) { + /* + * If memcg_kmem_charge() fails, page->mem_cgroup + * pointer is NULL, and both memcg_kmem_uncharge() + * and mod_memcg_page_state() in free_thread_stack() + * will ignore this page. So it's safe. + */ + ret = memcg_kmem_charge(vm->pages[i], GFP_KERNEL, 0); + if (ret) + return ret; + + mod_memcg_page_state(vm->pages[i], + MEMCG_KERNEL_STACK_KB, + PAGE_SIZE / 1024); + } + } +#endif + return 0; +} + static void release_task_stack(struct task_struct *tsk) { if (WARN_ON(tsk->state != TASK_DEAD)) @@ -807,6 +847,9 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) if (!stack) goto free_tsk; + if (memcg_charge_kernel_stack(tsk)) + goto free_stack; + stack_vm_area = task_stack_vm_area(tsk); err = arch_dup_task_struct(tsk, orig); -- cgit v1.2.3 From 68600f623d69da428c6163275f97ca126e1a8ec5 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 26 Oct 2018 15:03:27 -0700 Subject: mm: don't miss the last page because of round-off error I've noticed, that dying memory cgroups are often pinned in memory by a single pagecache page. Even under moderate memory pressure they sometimes stayed in such state for a long time. That looked strange. My investigation showed that the problem is caused by applying the LRU pressure balancing math: scan = div64_u64(scan * fraction[lru], denominator), where denominator = fraction[anon] + fraction[file] + 1. Because fraction[lru] is always less than denominator, if the initial scan size is 1, the result is always 0. This means the last page is not scanned and has no chances to be reclaimed. Fix this by rounding up the result of the division. In practice this change significantly improves the speed of dying cgroups reclaim. [guro@fb.com: prevent double calculation of DIV64_U64_ROUND_UP() arguments] Link: http://lkml.kernel.org/r/20180829213311.GA13501@castle Link: http://lkml.kernel.org/r/20180827162621.30187-3-guro@fb.com Signed-off-by: Roman Gushchin Reviewed-by: Andrew Morton Cc: Johannes Weiner Cc: Michal Hocko Cc: Tejun Heo Cc: Rik van Riel Cc: Konstantin Khlebnikov Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/math64.h | 3 +++ mm/vmscan.c | 6 ++++-- 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/math64.h b/include/linux/math64.h index 837f2f2d1d34..bb2c84afb80c 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -281,4 +281,7 @@ static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 divisor) } #endif /* mul_u64_u32_div */ +#define DIV64_U64_ROUND_UP(ll, d) \ + ({ u64 _tmp = (d); div64_u64((ll) + _tmp - 1, _tmp); }) + #endif /* _LINUX_MATH64_H */ diff --git a/mm/vmscan.c b/mm/vmscan.c index c5ef7240cbcb..961401c46334 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2456,9 +2456,11 @@ out: /* * Scan types proportional to swappiness and * their relative recent reclaim efficiency. + * Make sure we don't miss the last page + * because of a round-off error. */ - scan = div64_u64(scan * fraction[file], - denominator); + scan = DIV64_U64_ROUND_UP(scan * fraction[file], + denominator); break; case SCAN_FILE: case SCAN_ANON: -- cgit v1.2.3 From 33490af3f5c15757448b6c454ca93b48a333aa1b Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 26 Oct 2018 15:03:35 -0700 Subject: mm, mmu_notifier: be explicit about range invalition non-blocking mode If invalidate_range_start() is called for !blocking mode then all callbacks have to guarantee they will no block/sleep. The same obviously applies to invalidate_range_end because this operation pairs with the former and they are called from the same context. Make sure this is appropriately documented. Link: http://lkml.kernel.org/r/20180827112623.8992-3-mhocko@kernel.org Signed-off-by: Michal Hocko Reviewed-by: Jerome Glisse Cc: Boris Ostrovsky Cc: David Rientjes Cc: Juergen Gross Cc: Tetsuo Handa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmu_notifier.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 133ba78820ee..698e371aafe3 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -153,7 +153,9 @@ struct mmu_notifier_ops { * * If blockable argument is set to false then the callback cannot * sleep and has to return with -EAGAIN. 0 should be returned - * otherwise. + * otherwise. Please note that if invalidate_range_start approves + * a non-blocking behavior then the same applies to + * invalidate_range_end. * */ int (*invalidate_range_start)(struct mmu_notifier *mn, -- cgit v1.2.3 From 4e15a073a168b62311db911a55c4d4f1500c2821 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 26 Oct 2018 15:03:39 -0700 Subject: Revert "mm, mmu_notifier: annotate mmu notifiers with blockable invalidate callbacks" Revert 5ff7091f5a2ca ("mm, mmu_notifier: annotate mmu notifiers with blockable invalidate callbacks"). MMU_INVALIDATE_DOES_NOT_BLOCK flags was the only one used and it is no longer needed since 93065ac753e4 ("mm, oom: distinguish blockable mode for mmu notifiers"). We now have a full support for per range !blocking behavior so we can drop the stop gap workaround which the per notifier flag was used for. Link: http://lkml.kernel.org/r/20180827112623.8992-4-mhocko@kernel.org Signed-off-by: Michal Hocko Cc: David Rientjes Cc: Boris Ostrovsky Cc: Jerome Glisse Cc: Juergen Gross Cc: Tetsuo Handa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/infiniband/hw/hfi1/mmu_rb.c | 1 - drivers/iommu/amd_iommu_v2.c | 1 - drivers/iommu/intel-svm.c | 1 - drivers/misc/sgi-gru/grutlbpurge.c | 1 - include/linux/mmu_notifier.h | 23 ----------------------- mm/mmu_notifier.c | 31 ------------------------------- virt/kvm/kvm_main.c | 1 - 7 files changed, 59 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.c b/drivers/infiniband/hw/hfi1/mmu_rb.c index e1c7996c018e..475b769e120c 100644 --- a/drivers/infiniband/hw/hfi1/mmu_rb.c +++ b/drivers/infiniband/hw/hfi1/mmu_rb.c @@ -77,7 +77,6 @@ static void do_remove(struct mmu_rb_handler *handler, static void handle_remove(struct work_struct *work); static const struct mmu_notifier_ops mn_opts = { - .flags = MMU_INVALIDATE_DOES_NOT_BLOCK, .invalidate_range_start = mmu_notifier_range_start, }; diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c index 58da65df03f5..fd552235bd13 100644 --- a/drivers/iommu/amd_iommu_v2.c +++ b/drivers/iommu/amd_iommu_v2.c @@ -427,7 +427,6 @@ static void mn_release(struct mmu_notifier *mn, struct mm_struct *mm) } static const struct mmu_notifier_ops iommu_mn = { - .flags = MMU_INVALIDATE_DOES_NOT_BLOCK, .release = mn_release, .clear_flush_young = mn_clear_flush_young, .invalidate_range = mn_invalidate_range, diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c index 4a03e5090952..db301efe126d 100644 --- a/drivers/iommu/intel-svm.c +++ b/drivers/iommu/intel-svm.c @@ -273,7 +273,6 @@ static void intel_mm_release(struct mmu_notifier *mn, struct mm_struct *mm) } static const struct mmu_notifier_ops intel_mmuops = { - .flags = MMU_INVALIDATE_DOES_NOT_BLOCK, .release = intel_mm_release, .change_pte = intel_change_pte, .invalidate_range = intel_invalidate_range, diff --git a/drivers/misc/sgi-gru/grutlbpurge.c b/drivers/misc/sgi-gru/grutlbpurge.c index be28f05bfafa..03b49d52092e 100644 --- a/drivers/misc/sgi-gru/grutlbpurge.c +++ b/drivers/misc/sgi-gru/grutlbpurge.c @@ -261,7 +261,6 @@ static void gru_release(struct mmu_notifier *mn, struct mm_struct *mm) static const struct mmu_notifier_ops gru_mmuops = { - .flags = MMU_INVALIDATE_DOES_NOT_BLOCK, .invalidate_range_start = gru_invalidate_range_start, .invalidate_range_end = gru_invalidate_range_end, .release = gru_release, diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 698e371aafe3..9893a6432adf 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -2,7 +2,6 @@ #ifndef _LINUX_MMU_NOTIFIER_H #define _LINUX_MMU_NOTIFIER_H -#include #include #include #include @@ -11,9 +10,6 @@ struct mmu_notifier; struct mmu_notifier_ops; -/* mmu_notifier_ops flags */ -#define MMU_INVALIDATE_DOES_NOT_BLOCK (0x01) - #ifdef CONFIG_MMU_NOTIFIER /* @@ -30,15 +26,6 @@ struct mmu_notifier_mm { }; struct mmu_notifier_ops { - /* - * Flags to specify behavior of callbacks for this MMU notifier. - * Used to determine which context an operation may be called. - * - * MMU_INVALIDATE_DOES_NOT_BLOCK: invalidate_range_* callbacks do not - * block - */ - int flags; - /* * Called either by mmu_notifier_unregister or when the mm is * being destroyed by exit_mmap, always before all pages are @@ -183,10 +170,6 @@ struct mmu_notifier_ops { * Note that this function might be called with just a sub-range * of what was passed to invalidate_range_start()/end(), if * called between those functions. - * - * If this callback cannot block, and invalidate_range_{start,end} - * cannot block, mmu_notifier_ops.flags should have - * MMU_INVALIDATE_DOES_NOT_BLOCK set. */ void (*invalidate_range)(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long start, unsigned long end); @@ -241,7 +224,6 @@ extern void __mmu_notifier_invalidate_range_end(struct mm_struct *mm, bool only_end); extern void __mmu_notifier_invalidate_range(struct mm_struct *mm, unsigned long start, unsigned long end); -extern bool mm_has_blockable_invalidate_notifiers(struct mm_struct *mm); static inline void mmu_notifier_release(struct mm_struct *mm) { @@ -495,11 +477,6 @@ static inline void mmu_notifier_invalidate_range(struct mm_struct *mm, { } -static inline bool mm_has_blockable_invalidate_notifiers(struct mm_struct *mm) -{ - return false; -} - static inline void mmu_notifier_mm_init(struct mm_struct *mm) { } diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c index 82bb1a939c0e..5119ff846769 100644 --- a/mm/mmu_notifier.c +++ b/mm/mmu_notifier.c @@ -247,37 +247,6 @@ void __mmu_notifier_invalidate_range(struct mm_struct *mm, } EXPORT_SYMBOL_GPL(__mmu_notifier_invalidate_range); -/* - * Must be called while holding mm->mmap_sem for either read or write. - * The result is guaranteed to be valid until mm->mmap_sem is dropped. - */ -bool mm_has_blockable_invalidate_notifiers(struct mm_struct *mm) -{ - struct mmu_notifier *mn; - int id; - bool ret = false; - - WARN_ON_ONCE(!rwsem_is_locked(&mm->mmap_sem)); - - if (!mm_has_notifiers(mm)) - return ret; - - id = srcu_read_lock(&srcu); - hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) { - if (!mn->ops->invalidate_range && - !mn->ops->invalidate_range_start && - !mn->ops->invalidate_range_end) - continue; - - if (!(mn->ops->flags & MMU_INVALIDATE_DOES_NOT_BLOCK)) { - ret = true; - break; - } - } - srcu_read_unlock(&srcu, id); - return ret; -} - static int do_mmu_notifier_register(struct mmu_notifier *mn, struct mm_struct *mm, int take_mmap_sem) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 786ade1843a2..2679e476b6c3 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -497,7 +497,6 @@ static void kvm_mmu_notifier_release(struct mmu_notifier *mn, } static const struct mmu_notifier_ops kvm_mmu_notifier_ops = { - .flags = MMU_INVALIDATE_DOES_NOT_BLOCK, .invalidate_range_start = kvm_mmu_notifier_invalidate_range_start, .invalidate_range_end = kvm_mmu_notifier_invalidate_range_end, .clear_flush_young = kvm_mmu_notifier_clear_flush_young, -- cgit v1.2.3 From 5d7476374564645b1a2d299e242ad7b17b1104ee Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 26 Oct 2018 15:04:10 -0700 Subject: mm: remove vm_insert_mixed() All callers are now converted to vmf_insert_mixed() so convert vmf_insert_mixed() from being a compatibility wrapper into the real function. Link: http://lkml.kernel.org/r/20180828145728.11873-3-willy@infradead.org Signed-off-by: Matthew Wilcox Reviewed-by: Andrew Morton Cc: Nicolas Pitre Cc: Souptick Joarder Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 15 +-------------- mm/memory.c | 14 ++++++++++---- 2 files changed, 11 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index daa2b8f1e9a8..ecc6f9347756 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2506,7 +2506,7 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); -int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, +vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); @@ -2525,19 +2525,6 @@ static inline vm_fault_t vmf_insert_page(struct vm_area_struct *vma, return VM_FAULT_NOPAGE; } -static inline vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, - unsigned long addr, pfn_t pfn) -{ - int err = vm_insert_mixed(vma, addr, pfn); - - if (err == -ENOMEM) - return VM_FAULT_OOM; - if (err < 0 && err != -EBUSY) - return VM_FAULT_SIGBUS; - - return VM_FAULT_NOPAGE; -} - static inline vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn) { diff --git a/mm/memory.c b/mm/memory.c index 21a5e6e4758b..200aaf291e98 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1693,13 +1693,19 @@ static int __vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, return insert_pfn(vma, addr, pfn, pgprot, mkwrite); } -int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, - pfn_t pfn) +vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, + pfn_t pfn) { - return __vm_insert_mixed(vma, addr, pfn, false); + int err = __vm_insert_mixed(vma, addr, pfn, false); + if (err == -ENOMEM) + return VM_FAULT_OOM; + if (err < 0 && err != -EBUSY) + return VM_FAULT_SIGBUS; + + return VM_FAULT_NOPAGE; } -EXPORT_SYMBOL(vm_insert_mixed); +EXPORT_SYMBOL(vmf_insert_mixed); /* * If the insertion of PTE failed because someone else already added a -- cgit v1.2.3 From f5e6d1d5f8f3080aa7a51acea1f77085f45abe9c Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 26 Oct 2018 15:04:13 -0700 Subject: mm: introduce vmf_insert_pfn_prot() Like vm_insert_pfn_prot(), but returns a vm_fault_t instead of an errno. Also unexport vm_insert_pfn_prot as it has no modular users. Link: http://lkml.kernel.org/r/20180828145728.11873-4-willy@infradead.org Signed-off-by: Matthew Wilcox Reviewed-by: Andrew Morton Cc: Nicolas Pitre Cc: Souptick Joarder Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ mm/memory.c | 47 +++++++++++++++++++++++++++++++---------------- 2 files changed, 33 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index ecc6f9347756..f1293bdc6de2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2506,6 +2506,8 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); +vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, pgprot_t pgprot); vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, diff --git a/mm/memory.c b/mm/memory.c index 200aaf291e98..b3eecb3aa65f 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1596,21 +1596,6 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, } EXPORT_SYMBOL(vm_insert_pfn); -/** - * vm_insert_pfn_prot - insert single pfn into user vma with specified pgprot - * @vma: user vma to map to - * @addr: target user address of this page - * @pfn: source kernel pfn - * @pgprot: pgprot flags for the inserted page - * - * This is exactly like vm_insert_pfn, except that it allows drivers to - * to override pgprot on a per-page basis. - * - * This only makes sense for IO mappings, and it makes no sense for - * cow mappings. In general, using multiple vmas is preferable; - * vm_insert_pfn_prot should only be used if using multiple VMAs is - * impractical. - */ int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot) { @@ -1640,7 +1625,37 @@ int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, return ret; } -EXPORT_SYMBOL(vm_insert_pfn_prot); + +/** + * vmf_insert_pfn_prot - insert single pfn into user vma with specified pgprot + * @vma: user vma to map to + * @addr: target user address of this page + * @pfn: source kernel pfn + * @pgprot: pgprot flags for the inserted page + * + * This is exactly like vmf_insert_pfn(), except that it allows drivers to + * to override pgprot on a per-page basis. + * + * This only makes sense for IO mappings, and it makes no sense for + * COW mappings. In general, using multiple vmas is preferable; + * vm_insert_pfn_prot should only be used if using multiple VMAs is + * impractical. + * + * Return: vm_fault_t value. + */ +vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, pgprot_t pgprot) +{ + int err = vm_insert_pfn_prot(vma, addr, pfn, pgprot); + + if (err == -ENOMEM) + return VM_FAULT_OOM; + if (err < 0 && err != -EBUSY) + return VM_FAULT_SIGBUS; + + return VM_FAULT_NOPAGE; +} +EXPORT_SYMBOL(vmf_insert_pfn_prot); static bool vm_mixed_ok(struct vm_area_struct *vma, pfn_t pfn) { -- cgit v1.2.3 From bc12e6ad9617831727e4201e7cbf5c3b868cc8fd Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 26 Oct 2018 15:04:21 -0700 Subject: mm: make vm_insert_pfn_prot() static Now this is no longer used outside mm/memory.c, make it static. Link: http://lkml.kernel.org/r/20180828145728.11873-6-willy@infradead.org Signed-off-by: Matthew Wilcox Reviewed-by: Andrew Morton Cc: Nicolas Pitre Cc: Souptick Joarder Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 -- mm/memory.c | 50 +++++++++++++++++++++++++------------------------- 2 files changed, 25 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index f1293bdc6de2..0f5db0455e61 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2504,8 +2504,6 @@ int remap_pfn_range(struct vm_area_struct *, unsigned long addr, int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *); int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); -int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, - unsigned long pfn, pgprot_t pgprot); vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, diff --git a/mm/memory.c b/mm/memory.c index b3eecb3aa65f..6365144f8267 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1572,31 +1572,7 @@ out: return retval; } -/** - * vm_insert_pfn - insert single pfn into user vma - * @vma: user vma to map to - * @addr: target user address of this page - * @pfn: source kernel pfn - * - * Similar to vm_insert_page, this allows drivers to insert individual pages - * they've allocated into a user vma. Same comments apply. - * - * This function should only be called from a vm_ops->fault handler, and - * in that case the handler should return NULL. - * - * vma cannot be a COW mapping. - * - * As this is called only for pages that do not currently exist, we - * do not need to flush old virtual caches or the TLB. - */ -int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, - unsigned long pfn) -{ - return vm_insert_pfn_prot(vma, addr, pfn, vma->vm_page_prot); -} -EXPORT_SYMBOL(vm_insert_pfn); - -int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, +static int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot) { int ret; @@ -1626,6 +1602,30 @@ int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, return ret; } +/** + * vm_insert_pfn - insert single pfn into user vma + * @vma: user vma to map to + * @addr: target user address of this page + * @pfn: source kernel pfn + * + * Similar to vm_insert_page, this allows drivers to insert individual pages + * they've allocated into a user vma. Same comments apply. + * + * This function should only be called from a vm_ops->fault handler, and + * in that case the handler should return NULL. + * + * vma cannot be a COW mapping. + * + * As this is called only for pages that do not currently exist, we + * do not need to flush old virtual caches or the TLB. + */ +int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn) +{ + return vm_insert_pfn_prot(vma, addr, pfn, vma->vm_page_prot); +} +EXPORT_SYMBOL(vm_insert_pfn); + /** * vmf_insert_pfn_prot - insert single pfn into user vma with specified pgprot * @vma: user vma to map to -- cgit v1.2.3 From 67fa1666223d7c825f6651add97f0011fe155f36 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 26 Oct 2018 15:04:26 -0700 Subject: mm: remove references to vm_insert_pfn() Documentation and comments. Link: http://lkml.kernel.org/r/20180828145728.11873-7-willy@infradead.org Signed-off-by: Matthew Wilcox Reviewed-by: Andrew Morton Cc: Nicolas Pitre Cc: Souptick Joarder Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/x86/pat.txt | 4 ++-- include/asm-generic/pgtable.h | 4 ++-- include/linux/hmm.h | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/Documentation/x86/pat.txt b/Documentation/x86/pat.txt index 2a4ee6302122..481d8d8536ac 100644 --- a/Documentation/x86/pat.txt +++ b/Documentation/x86/pat.txt @@ -90,12 +90,12 @@ pci proc | -- | -- | WC | Advanced APIs for drivers ------------------------- A. Exporting pages to users with remap_pfn_range, io_remap_pfn_range, -vm_insert_pfn +vmf_insert_pfn Drivers wanting to export some pages to userspace do it by using mmap interface and a combination of 1) pgprot_noncached() -2) io_remap_pfn_range() or remap_pfn_range() or vm_insert_pfn() +2) io_remap_pfn_range() or remap_pfn_range() or vmf_insert_pfn() With PAT support, a new API pgprot_writecombine is being added. So, drivers can continue to use the above sequence, with either pgprot_noncached() or diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 88ebc6102c7c..5657a20e0c59 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -757,7 +757,7 @@ static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd) /* * Interfaces that can be used by architecture code to keep track of * memory type of pfn mappings specified by the remap_pfn_range, - * vm_insert_pfn. + * vmf_insert_pfn. */ /* @@ -773,7 +773,7 @@ static inline int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, /* * track_pfn_insert is called when a _new_ single pfn is established - * by vm_insert_pfn(). + * by vmf_insert_pfn(). */ static inline void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, pfn_t pfn) diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 4c92e3ba3e16..dde947083d4e 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -107,7 +107,7 @@ enum hmm_pfn_flag_e { * HMM_PFN_ERROR: corresponding CPU page table entry points to poisoned memory * HMM_PFN_NONE: corresponding CPU page table entry is pte_none() * HMM_PFN_SPECIAL: corresponding CPU page table entry is special; i.e., the - * result of vm_insert_pfn() or vm_insert_page(). Therefore, it should not + * result of vmf_insert_pfn() or vm_insert_page(). Therefore, it should not * be mirrored by a device, because the entry will never have HMM_PFN_VALID * set and the pfn value is undefined. * -- cgit v1.2.3 From ae2b01f37044c10e975d22116755df56252b09d8 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 26 Oct 2018 15:04:29 -0700 Subject: mm: remove vm_insert_pfn() All callers are now converted to vmf_insert_pfn() so convert vmf_insert_pfn() from being a compatibility wrapper around vm_insert_pfn() to being a compatibility wrapper around vmf_insert_pfn_prot(). Link: http://lkml.kernel.org/r/20180828145728.11873-8-willy@infradead.org Signed-off-by: Matthew Wilcox Reviewed-by: Andrew Morton Cc: Nicolas Pitre Cc: Souptick Joarder Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 15 +-------------- mm/memory.c | 54 +++++++++++++++++++++++++++++------------------------- 2 files changed, 30 insertions(+), 39 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 0f5db0455e61..737279bb479c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2502,7 +2502,7 @@ struct vm_area_struct *find_extend_vma(struct mm_struct *, unsigned long addr); int remap_pfn_range(struct vm_area_struct *, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t); int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *); -int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, +vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); @@ -2525,19 +2525,6 @@ static inline vm_fault_t vmf_insert_page(struct vm_area_struct *vma, return VM_FAULT_NOPAGE; } -static inline vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, - unsigned long addr, unsigned long pfn) -{ - int err = vm_insert_pfn(vma, addr, pfn); - - if (err == -ENOMEM) - return VM_FAULT_OOM; - if (err < 0 && err != -EBUSY) - return VM_FAULT_SIGBUS; - - return VM_FAULT_NOPAGE; -} - static inline vm_fault_t vmf_error(int err) { if (err == -ENOMEM) diff --git a/mm/memory.c b/mm/memory.c index 6365144f8267..08653d0a795a 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1602,30 +1602,6 @@ static int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, return ret; } -/** - * vm_insert_pfn - insert single pfn into user vma - * @vma: user vma to map to - * @addr: target user address of this page - * @pfn: source kernel pfn - * - * Similar to vm_insert_page, this allows drivers to insert individual pages - * they've allocated into a user vma. Same comments apply. - * - * This function should only be called from a vm_ops->fault handler, and - * in that case the handler should return NULL. - * - * vma cannot be a COW mapping. - * - * As this is called only for pages that do not currently exist, we - * do not need to flush old virtual caches or the TLB. - */ -int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, - unsigned long pfn) -{ - return vm_insert_pfn_prot(vma, addr, pfn, vma->vm_page_prot); -} -EXPORT_SYMBOL(vm_insert_pfn); - /** * vmf_insert_pfn_prot - insert single pfn into user vma with specified pgprot * @vma: user vma to map to @@ -1638,9 +1614,10 @@ EXPORT_SYMBOL(vm_insert_pfn); * * This only makes sense for IO mappings, and it makes no sense for * COW mappings. In general, using multiple vmas is preferable; - * vm_insert_pfn_prot should only be used if using multiple VMAs is + * vmf_insert_pfn_prot should only be used if using multiple VMAs is * impractical. * + * Context: Process context. May allocate using %GFP_KERNEL. * Return: vm_fault_t value. */ vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, @@ -1657,6 +1634,33 @@ vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, } EXPORT_SYMBOL(vmf_insert_pfn_prot); +/** + * vmf_insert_pfn - insert single pfn into user vma + * @vma: user vma to map to + * @addr: target user address of this page + * @pfn: source kernel pfn + * + * Similar to vm_insert_page, this allows drivers to insert individual pages + * they've allocated into a user vma. Same comments apply. + * + * This function should only be called from a vm_ops->fault handler, and + * in that case the handler should return the result of this function. + * + * vma cannot be a COW mapping. + * + * As this is called only for pages that do not currently exist, we + * do not need to flush old virtual caches or the TLB. + * + * Context: Process context. May allocate using %GFP_KERNEL. + * Return: vm_fault_t value. + */ +vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn) +{ + return vmf_insert_pfn_prot(vma, addr, pfn, vma->vm_page_prot); +} +EXPORT_SYMBOL(vmf_insert_pfn); + static bool vm_mixed_ok(struct vm_area_struct *vma, pfn_t pfn) { /* these checks mirror the abort conditions in vm_normal_page */ -- cgit v1.2.3 From cc252eae85e09552f9c1e7ac0c3227f835efdf2d Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Fri, 26 Oct 2018 15:05:34 -0700 Subject: mm, slab: combine kmalloc_caches and kmalloc_dma_caches Patch series "kmalloc-reclaimable caches", v4. As discussed at LSF/MM [1] here's a patchset that introduces kmalloc-reclaimable caches (more details in the second patch) and uses them for dcache external names. That allows us to repurpose the NR_INDIRECTLY_RECLAIMABLE_BYTES counter later in the series. With patch 3/6, dcache external names are allocated from kmalloc-rcl-* caches, eliminating the need for manual accounting. More importantly, it also ensures the reclaimable kmalloc allocations are grouped in pages separate from the regular kmalloc allocations. The need for proper accounting of dcache external names has shown it's easy for misbehaving process to allocate lots of them, causing premature OOMs. Without the added grouping, it's likely that a similar workload can interleave the dcache external names allocations with regular kmalloc allocations (note: I haven't searched myself for an example of such regular kmalloc allocation, but I would be very surprised if there wasn't some). A pathological case would be e.g. one 64byte regular allocations with 63 external dcache names in a page (64x64=4096), which means the page is not freed even after reclaiming after all dcache names, and the process can thus "steal" the whole page with single 64byte allocation. If other kmalloc users similar to dcache external names become identified, they can also benefit from the new functionality simply by adding __GFP_RECLAIMABLE to the kmalloc calls. Side benefits of the patchset (that could be also merged separately) include removed branch for detecting __GFP_DMA kmalloc(), and shortening kmalloc cache names in /proc/slabinfo output. The latter is potentially an ABI break in case there are tools parsing the names and expecting the values to be in bytes. This is how /proc/slabinfo looks like after booting in virtme: ... kmalloc-rcl-4M 0 0 4194304 1 1024 : tunables 1 1 0 : slabdata 0 0 0 ... kmalloc-rcl-96 7 32 128 32 1 : tunables 120 60 8 : slabdata 1 1 0 kmalloc-rcl-64 25 128 64 64 1 : tunables 120 60 8 : slabdata 2 2 0 kmalloc-rcl-32 0 0 32 124 1 : tunables 120 60 8 : slabdata 0 0 0 kmalloc-4M 0 0 4194304 1 1024 : tunables 1 1 0 : slabdata 0 0 0 kmalloc-2M 0 0 2097152 1 512 : tunables 1 1 0 : slabdata 0 0 0 kmalloc-1M 0 0 1048576 1 256 : tunables 1 1 0 : slabdata 0 0 0 ... /proc/vmstat with renamed nr_indirectly_reclaimable_bytes counter: ... nr_slab_reclaimable 2817 nr_slab_unreclaimable 1781 ... nr_kernel_misc_reclaimable 0 ... /proc/meminfo with new KReclaimable counter: ... Shmem: 564 kB KReclaimable: 11260 kB Slab: 18368 kB SReclaimable: 11260 kB SUnreclaim: 7108 kB KernelStack: 1248 kB ... This patch (of 6): The kmalloc caches currently mainain separate (optional) array kmalloc_dma_caches for __GFP_DMA allocations. There are tests for __GFP_DMA in the allocation hotpaths. We can avoid the branches by combining kmalloc_caches and kmalloc_dma_caches into a single two-dimensional array where the outer dimension is cache "type". This will also allow to add kmalloc-reclaimable caches as a third type. Link: http://lkml.kernel.org/r/20180731090649.16028-2-vbabka@suse.cz Signed-off-by: Vlastimil Babka Acked-by: Mel Gorman Acked-by: Christoph Lameter Acked-by: Roman Gushchin Cc: Michal Hocko Cc: Johannes Weiner Cc: David Rientjes Cc: Joonsoo Kim Cc: Matthew Wilcox Cc: Laura Abbott Cc: Sumit Semwal Cc: Vijayanand Jitta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 42 +++++++++++++++++++++++++++++++----------- mm/slab.c | 4 ++-- mm/slab_common.c | 31 ++++++++++++------------------- mm/slub.c | 13 +++++++------ 4 files changed, 52 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index ed9cbddeb4a6..2a7137043e91 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -295,12 +295,29 @@ static inline void __check_heap_object(const void *ptr, unsigned long n, #define SLAB_OBJ_MIN_SIZE (KMALLOC_MIN_SIZE < 16 ? \ (KMALLOC_MIN_SIZE) : 16) +enum kmalloc_cache_type { + KMALLOC_NORMAL = 0, +#ifdef CONFIG_ZONE_DMA + KMALLOC_DMA, +#endif + NR_KMALLOC_TYPES +}; + #ifndef CONFIG_SLOB -extern struct kmem_cache *kmalloc_caches[KMALLOC_SHIFT_HIGH + 1]; +extern struct kmem_cache * +kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1]; + +static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags) +{ + int is_dma = 0; + #ifdef CONFIG_ZONE_DMA -extern struct kmem_cache *kmalloc_dma_caches[KMALLOC_SHIFT_HIGH + 1]; + is_dma = !!(flags & __GFP_DMA); #endif + return is_dma; +} + /* * Figure out which kmalloc slab an allocation of a certain size * belongs to. @@ -501,18 +518,20 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags) static __always_inline void *kmalloc(size_t size, gfp_t flags) { if (__builtin_constant_p(size)) { +#ifndef CONFIG_SLOB + unsigned int index; +#endif if (size > KMALLOC_MAX_CACHE_SIZE) return kmalloc_large(size, flags); #ifndef CONFIG_SLOB - if (!(flags & GFP_DMA)) { - unsigned int index = kmalloc_index(size); + index = kmalloc_index(size); - if (!index) - return ZERO_SIZE_PTR; + if (!index) + return ZERO_SIZE_PTR; - return kmem_cache_alloc_trace(kmalloc_caches[index], - flags, size); - } + return kmem_cache_alloc_trace( + kmalloc_caches[kmalloc_type(flags)][index], + flags, size); #endif } return __kmalloc(size, flags); @@ -542,13 +561,14 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) { #ifndef CONFIG_SLOB if (__builtin_constant_p(size) && - size <= KMALLOC_MAX_CACHE_SIZE && !(flags & GFP_DMA)) { + size <= KMALLOC_MAX_CACHE_SIZE) { unsigned int i = kmalloc_index(size); if (!i) return ZERO_SIZE_PTR; - return kmem_cache_alloc_node_trace(kmalloc_caches[i], + return kmem_cache_alloc_node_trace( + kmalloc_caches[kmalloc_type(flags)][i], flags, node, size); } #endif diff --git a/mm/slab.c b/mm/slab.c index d73c7a4820a4..2a5654bb3b3f 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -1288,7 +1288,7 @@ void __init kmem_cache_init(void) * Initialize the caches that provide memory for the kmem_cache_node * structures first. Without this, further allocations will bug. */ - kmalloc_caches[INDEX_NODE] = create_kmalloc_cache( + kmalloc_caches[KMALLOC_NORMAL][INDEX_NODE] = create_kmalloc_cache( kmalloc_info[INDEX_NODE].name, kmalloc_size(INDEX_NODE), ARCH_KMALLOC_FLAGS, 0, kmalloc_size(INDEX_NODE)); @@ -1304,7 +1304,7 @@ void __init kmem_cache_init(void) for_each_online_node(nid) { init_list(kmem_cache, &init_kmem_cache_node[CACHE_CACHE + nid], nid); - init_list(kmalloc_caches[INDEX_NODE], + init_list(kmalloc_caches[KMALLOC_NORMAL][INDEX_NODE], &init_kmem_cache_node[SIZE_NODE + nid], nid); } } diff --git a/mm/slab_common.c b/mm/slab_common.c index 3a7ac4f15194..d880b2a3c81b 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -973,14 +973,10 @@ struct kmem_cache *__init create_kmalloc_cache(const char *name, return s; } -struct kmem_cache *kmalloc_caches[KMALLOC_SHIFT_HIGH + 1] __ro_after_init; +struct kmem_cache * +kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1] __ro_after_init; EXPORT_SYMBOL(kmalloc_caches); -#ifdef CONFIG_ZONE_DMA -struct kmem_cache *kmalloc_dma_caches[KMALLOC_SHIFT_HIGH + 1] __ro_after_init; -EXPORT_SYMBOL(kmalloc_dma_caches); -#endif - /* * Conversion table for small slabs sizes / 8 to the index in the * kmalloc array. This is necessary for slabs < 192 since we have non power @@ -1040,12 +1036,7 @@ struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags) index = fls(size - 1); } -#ifdef CONFIG_ZONE_DMA - if (unlikely((flags & GFP_DMA))) - return kmalloc_dma_caches[index]; - -#endif - return kmalloc_caches[index]; + return kmalloc_caches[kmalloc_type(flags)][index]; } /* @@ -1119,7 +1110,8 @@ void __init setup_kmalloc_cache_index_table(void) static void __init new_kmalloc_cache(int idx, slab_flags_t flags) { - kmalloc_caches[idx] = create_kmalloc_cache(kmalloc_info[idx].name, + kmalloc_caches[KMALLOC_NORMAL][idx] = create_kmalloc_cache( + kmalloc_info[idx].name, kmalloc_info[idx].size, flags, 0, kmalloc_info[idx].size); } @@ -1132,9 +1124,10 @@ static void __init new_kmalloc_cache(int idx, slab_flags_t flags) void __init create_kmalloc_caches(slab_flags_t flags) { int i; + int type = KMALLOC_NORMAL; for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) { - if (!kmalloc_caches[i]) + if (!kmalloc_caches[type][i]) new_kmalloc_cache(i, flags); /* @@ -1142,9 +1135,9 @@ void __init create_kmalloc_caches(slab_flags_t flags) * These have to be created immediately after the * earlier power of two caches */ - if (KMALLOC_MIN_SIZE <= 32 && !kmalloc_caches[1] && i == 6) + if (KMALLOC_MIN_SIZE <= 32 && !kmalloc_caches[type][1] && i == 6) new_kmalloc_cache(1, flags); - if (KMALLOC_MIN_SIZE <= 64 && !kmalloc_caches[2] && i == 7) + if (KMALLOC_MIN_SIZE <= 64 && !kmalloc_caches[type][2] && i == 7) new_kmalloc_cache(2, flags); } @@ -1153,7 +1146,7 @@ void __init create_kmalloc_caches(slab_flags_t flags) #ifdef CONFIG_ZONE_DMA for (i = 0; i <= KMALLOC_SHIFT_HIGH; i++) { - struct kmem_cache *s = kmalloc_caches[i]; + struct kmem_cache *s = kmalloc_caches[KMALLOC_NORMAL][i]; if (s) { unsigned int size = kmalloc_size(i); @@ -1161,8 +1154,8 @@ void __init create_kmalloc_caches(slab_flags_t flags) "dma-kmalloc-%u", size); BUG_ON(!n); - kmalloc_dma_caches[i] = create_kmalloc_cache(n, - size, SLAB_CACHE_DMA | flags, 0, 0); + kmalloc_caches[KMALLOC_DMA][i] = create_kmalloc_cache( + n, size, SLAB_CACHE_DMA | flags, 0, 0); } } #endif diff --git a/mm/slub.c b/mm/slub.c index 18bd07daf4e4..e3629cd7aff1 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -4689,6 +4689,7 @@ static int list_locations(struct kmem_cache *s, char *buf, static void __init resiliency_test(void) { u8 *p; + int type = KMALLOC_NORMAL; BUILD_BUG_ON(KMALLOC_MIN_SIZE > 16 || KMALLOC_SHIFT_HIGH < 10); @@ -4701,7 +4702,7 @@ static void __init resiliency_test(void) pr_err("\n1. kmalloc-16: Clobber Redzone/next pointer 0x12->0x%p\n\n", p + 16); - validate_slab_cache(kmalloc_caches[4]); + validate_slab_cache(kmalloc_caches[type][4]); /* Hmmm... The next two are dangerous */ p = kzalloc(32, GFP_KERNEL); @@ -4710,33 +4711,33 @@ static void __init resiliency_test(void) p); pr_err("If allocated object is overwritten then not detectable\n\n"); - validate_slab_cache(kmalloc_caches[5]); + validate_slab_cache(kmalloc_caches[type][5]); p = kzalloc(64, GFP_KERNEL); p += 64 + (get_cycles() & 0xff) * sizeof(void *); *p = 0x56; pr_err("\n3. kmalloc-64: corrupting random byte 0x56->0x%p\n", p); pr_err("If allocated object is overwritten then not detectable\n\n"); - validate_slab_cache(kmalloc_caches[6]); + validate_slab_cache(kmalloc_caches[type][6]); pr_err("\nB. Corruption after free\n"); p = kzalloc(128, GFP_KERNEL); kfree(p); *p = 0x78; pr_err("1. kmalloc-128: Clobber first word 0x78->0x%p\n\n", p); - validate_slab_cache(kmalloc_caches[7]); + validate_slab_cache(kmalloc_caches[type][7]); p = kzalloc(256, GFP_KERNEL); kfree(p); p[50] = 0x9a; pr_err("\n2. kmalloc-256: Clobber 50th byte 0x9a->0x%p\n\n", p); - validate_slab_cache(kmalloc_caches[8]); + validate_slab_cache(kmalloc_caches[type][8]); p = kzalloc(512, GFP_KERNEL); kfree(p); p[512] = 0xab; pr_err("\n3. kmalloc-512: Clobber redzone 0xab->0x%p\n\n", p); - validate_slab_cache(kmalloc_caches[9]); + validate_slab_cache(kmalloc_caches[type][9]); } #else #ifdef CONFIG_SYSFS -- cgit v1.2.3 From 1291523f2c1d631fea34102fd241fb54a4e8f7a0 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Fri, 26 Oct 2018 15:05:38 -0700 Subject: mm, slab/slub: introduce kmalloc-reclaimable caches Kmem caches can be created with a SLAB_RECLAIM_ACCOUNT flag, which indicates they contain objects which can be reclaimed under memory pressure (typically through a shrinker). This makes the slab pages accounted as NR_SLAB_RECLAIMABLE in vmstat, which is reflected also the MemAvailable meminfo counter and in overcommit decisions. The slab pages are also allocated with __GFP_RECLAIMABLE, which is good for anti-fragmentation through grouping pages by mobility. The generic kmalloc-X caches are created without this flag, but sometimes are used also for objects that can be reclaimed, which due to varying size cannot have a dedicated kmem cache with SLAB_RECLAIM_ACCOUNT flag. A prominent example are dcache external names, which prompted the creation of a new, manually managed vmstat counter NR_INDIRECTLY_RECLAIMABLE_BYTES in commit f1782c9bc547 ("dcache: account external names as indirectly reclaimable memory"). To better handle this and any other similar cases, this patch introduces SLAB_RECLAIM_ACCOUNT variants of kmalloc caches, named kmalloc-rcl-X. They are used whenever the kmalloc() call passes __GFP_RECLAIMABLE among gfp flags. They are added to the kmalloc_caches array as a new type. Allocations with both __GFP_DMA and __GFP_RECLAIMABLE will use a dma type cache. This change only applies to SLAB and SLUB, not SLOB. This is fine, since SLOB's target are tiny system and this patch does add some overhead of kmem management objects. Link: http://lkml.kernel.org/r/20180731090649.16028-3-vbabka@suse.cz Signed-off-by: Vlastimil Babka Acked-by: Mel Gorman Acked-by: Christoph Lameter Acked-by: Roman Gushchin Cc: David Rientjes Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Laura Abbott Cc: Matthew Wilcox Cc: Michal Hocko Cc: Sumit Semwal Cc: Vijayanand Jitta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 16 +++++++++++++++- mm/slab_common.c | 48 +++++++++++++++++++++++++++++++----------------- 2 files changed, 46 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 2a7137043e91..918f374e7156 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -295,8 +295,13 @@ static inline void __check_heap_object(const void *ptr, unsigned long n, #define SLAB_OBJ_MIN_SIZE (KMALLOC_MIN_SIZE < 16 ? \ (KMALLOC_MIN_SIZE) : 16) +/* + * Whenever changing this, take care of that kmalloc_type() and + * create_kmalloc_caches() still work as intended. + */ enum kmalloc_cache_type { KMALLOC_NORMAL = 0, + KMALLOC_RECLAIM, #ifdef CONFIG_ZONE_DMA KMALLOC_DMA, #endif @@ -310,12 +315,21 @@ kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1]; static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags) { int is_dma = 0; + int type_dma = 0; + int is_reclaimable; #ifdef CONFIG_ZONE_DMA is_dma = !!(flags & __GFP_DMA); + type_dma = is_dma * KMALLOC_DMA; #endif - return is_dma; + is_reclaimable = !!(flags & __GFP_RECLAIMABLE); + + /* + * If an allocation is both __GFP_DMA and __GFP_RECLAIMABLE, return + * KMALLOC_DMA and effectively ignore __GFP_RECLAIMABLE + */ + return type_dma + (is_reclaimable & !is_dma) * KMALLOC_RECLAIM; } /* diff --git a/mm/slab_common.c b/mm/slab_common.c index d880b2a3c81b..5b19439fd862 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -1108,10 +1108,21 @@ void __init setup_kmalloc_cache_index_table(void) } } -static void __init new_kmalloc_cache(int idx, slab_flags_t flags) +static void __init +new_kmalloc_cache(int idx, int type, slab_flags_t flags) { - kmalloc_caches[KMALLOC_NORMAL][idx] = create_kmalloc_cache( - kmalloc_info[idx].name, + const char *name; + + if (type == KMALLOC_RECLAIM) { + flags |= SLAB_RECLAIM_ACCOUNT; + name = kasprintf(GFP_NOWAIT, "kmalloc-rcl-%u", + kmalloc_info[idx].size); + BUG_ON(!name); + } else { + name = kmalloc_info[idx].name; + } + + kmalloc_caches[type][idx] = create_kmalloc_cache(name, kmalloc_info[idx].size, flags, 0, kmalloc_info[idx].size); } @@ -1123,22 +1134,25 @@ static void __init new_kmalloc_cache(int idx, slab_flags_t flags) */ void __init create_kmalloc_caches(slab_flags_t flags) { - int i; - int type = KMALLOC_NORMAL; + int i, type; - for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) { - if (!kmalloc_caches[type][i]) - new_kmalloc_cache(i, flags); + for (type = KMALLOC_NORMAL; type <= KMALLOC_RECLAIM; type++) { + for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) { + if (!kmalloc_caches[type][i]) + new_kmalloc_cache(i, type, flags); - /* - * Caches that are not of the two-to-the-power-of size. - * These have to be created immediately after the - * earlier power of two caches - */ - if (KMALLOC_MIN_SIZE <= 32 && !kmalloc_caches[type][1] && i == 6) - new_kmalloc_cache(1, flags); - if (KMALLOC_MIN_SIZE <= 64 && !kmalloc_caches[type][2] && i == 7) - new_kmalloc_cache(2, flags); + /* + * Caches that are not of the two-to-the-power-of size. + * These have to be created immediately after the + * earlier power of two caches + */ + if (KMALLOC_MIN_SIZE <= 32 && i == 6 && + !kmalloc_caches[type][1]) + new_kmalloc_cache(1, type, flags); + if (KMALLOC_MIN_SIZE <= 64 && i == 7 && + !kmalloc_caches[type][2]) + new_kmalloc_cache(2, type, flags); + } } /* Kmalloc array is now usable */ -- cgit v1.2.3 From b29940c1abd7a4c3abeb926df0a5ec84d6902d47 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Fri, 26 Oct 2018 15:05:46 -0700 Subject: mm: rename and change semantics of nr_indirectly_reclaimable_bytes The vmstat counter NR_INDIRECTLY_RECLAIMABLE_BYTES was introduced by commit eb59254608bc ("mm: introduce NR_INDIRECTLY_RECLAIMABLE_BYTES") with the goal of accounting objects that can be reclaimed, but cannot be allocated via a SLAB_RECLAIM_ACCOUNT cache. This is now possible via kmalloc() with __GFP_RECLAIMABLE flag, and the dcache external names user is converted. The counter is however still useful for accounting direct page allocations (i.e. not slab) with a shrinker, such as the ION page pool. So keep it, and: - change granularity to pages to be more like other counters; sub-page allocations should be able to use kmalloc - rename the counter to NR_KERNEL_MISC_RECLAIMABLE - expose the counter again in vmstat as "nr_kernel_misc_reclaimable"; we can again remove the check for not printing "hidden" counters Link: http://lkml.kernel.org/r/20180731090649.16028-5-vbabka@suse.cz Signed-off-by: Vlastimil Babka Acked-by: Christoph Lameter Acked-by: Roman Gushchin Cc: Vijayanand Jitta Cc: Laura Abbott Cc: Sumit Semwal Cc: David Rientjes Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Matthew Wilcox Cc: Mel Gorman Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/staging/android/ion/ion_page_pool.c | 8 ++++---- include/linux/mmzone.h | 2 +- mm/page_alloc.c | 19 +++++++------------ mm/util.c | 3 +-- mm/vmstat.c | 6 +----- 5 files changed, 14 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/drivers/staging/android/ion/ion_page_pool.c b/drivers/staging/android/ion/ion_page_pool.c index 9bc56eb48d2a..0d2a95957ee8 100644 --- a/drivers/staging/android/ion/ion_page_pool.c +++ b/drivers/staging/android/ion/ion_page_pool.c @@ -33,8 +33,8 @@ static void ion_page_pool_add(struct ion_page_pool *pool, struct page *page) pool->low_count++; } - mod_node_page_state(page_pgdat(page), NR_INDIRECTLY_RECLAIMABLE_BYTES, - (1 << (PAGE_SHIFT + pool->order))); + mod_node_page_state(page_pgdat(page), NR_KERNEL_MISC_RECLAIMABLE, + 1 << pool->order); mutex_unlock(&pool->mutex); } @@ -53,8 +53,8 @@ static struct page *ion_page_pool_remove(struct ion_page_pool *pool, bool high) } list_del(&page->lru); - mod_node_page_state(page_pgdat(page), NR_INDIRECTLY_RECLAIMABLE_BYTES, - -(1 << (PAGE_SHIFT + pool->order))); + mod_node_page_state(page_pgdat(page), NR_KERNEL_MISC_RECLAIMABLE, + -(1 << pool->order)); return page; } diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index d4b0c79d2924..7bbeba21f6a3 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -180,7 +180,7 @@ enum node_stat_item { NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */ NR_DIRTIED, /* page dirtyings since bootup */ NR_WRITTEN, /* page writings since bootup */ - NR_INDIRECTLY_RECLAIMABLE_BYTES, /* measured in bytes */ + NR_KERNEL_MISC_RECLAIMABLE, /* reclaimable non-slab kernel pages */ NR_VM_NODE_STAT_ITEMS }; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 747031c2352d..20f25d06c00c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4701,6 +4701,7 @@ long si_mem_available(void) unsigned long pagecache; unsigned long wmark_low = 0; unsigned long pages[NR_LRU_LISTS]; + unsigned long reclaimable; struct zone *zone; int lru; @@ -4726,19 +4727,13 @@ long si_mem_available(void) available += pagecache; /* - * Part of the reclaimable slab consists of items that are in use, - * and cannot be freed. Cap this estimate at the low watermark. + * Part of the reclaimable slab and other kernel memory consists of + * items that are in use, and cannot be freed. Cap this estimate at the + * low watermark. */ - available += global_node_page_state(NR_SLAB_RECLAIMABLE) - - min(global_node_page_state(NR_SLAB_RECLAIMABLE) / 2, - wmark_low); - - /* - * Part of the kernel memory, which can be released under memory - * pressure. - */ - available += global_node_page_state(NR_INDIRECTLY_RECLAIMABLE_BYTES) >> - PAGE_SHIFT; + reclaimable = global_node_page_state(NR_SLAB_RECLAIMABLE) + + global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE); + available += reclaimable - min(reclaimable / 2, wmark_low); if (available < 0) available = 0; diff --git a/mm/util.c b/mm/util.c index 470f5cd80b64..f740754f5012 100644 --- a/mm/util.c +++ b/mm/util.c @@ -678,8 +678,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) * Part of the kernel memory, which can be released * under memory pressure. */ - free += global_node_page_state( - NR_INDIRECTLY_RECLAIMABLE_BYTES) >> PAGE_SHIFT; + free += global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE); /* * Leave reserved pages. The pages are not for anonymous pages. diff --git a/mm/vmstat.c b/mm/vmstat.c index 7878da76abf2..2cec2fa4c8ae 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1161,7 +1161,7 @@ const char * const vmstat_text[] = { "nr_vmscan_immediate_reclaim", "nr_dirtied", "nr_written", - "", /* nr_indirectly_reclaimable */ + "nr_kernel_misc_reclaimable", /* enum writeback_stat_item counters */ "nr_dirty_threshold", @@ -1706,10 +1706,6 @@ static int vmstat_show(struct seq_file *m, void *arg) unsigned long *l = arg; unsigned long off = l - (unsigned long *)m->private; - /* Skip hidden vmstat items. */ - if (*vmstat_text[off] == '\0') - return 0; - seq_puts(m, vmstat_text[off]); seq_put_decimal_ull(m, " ", *l); seq_putc(m, '\n'); -- cgit v1.2.3 From 1899ad18c6072d689896badafb81267b0a1092a4 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:04 -0700 Subject: mm: workingset: tell cache transitions from workingset thrashing Refaults happen during transitions between workingsets as well as in-place thrashing. Knowing the difference between the two has a range of applications, including measuring the impact of memory shortage on the system performance, as well as the ability to smarter balance pressure between the filesystem cache and the swap-backed workingset. During workingset transitions, inactive cache refaults and pushes out established active cache. When that active cache isn't stale, however, and also ends up refaulting, that's bonafide thrashing. Introduce a new page flag that tells on eviction whether the page has been active or not in its lifetime. This bit is then stored in the shadow entry, to classify refaults as transitioning or thrashing. How many page->flags does this leave us with on 32-bit? 20 bits are always page flags 21 if you have an MMU 23 with the zone bits for DMA, Normal, HighMem, Movable 29 with the sparsemem section bits 30 if PAE is enabled 31 with this patch. So on 32-bit PAE, that leaves 1 bit for distinguishing two NUMA nodes. If that's not enough, the system can switch to discontigmem and re-gain the 6 or 7 sparsemem section bits. Link: http://lkml.kernel.org/r/20180828172258.3185-3-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Peter Zijlstra (Intel) Tested-by: Daniel Drake Tested-by: Suren Baghdasaryan Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Tejun Heo Cc: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 + include/linux/page-flags.h | 5 ++- include/linux/swap.h | 2 +- include/trace/events/mmflags.h | 1 + mm/filemap.c | 9 ++-- mm/huge_memory.c | 1 + mm/migrate.c | 2 + mm/swap_state.c | 1 + mm/vmscan.c | 1 + mm/vmstat.c | 1 + mm/workingset.c | 95 +++++++++++++++++++++++++++--------------- 11 files changed, 77 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 7bbeba21f6a3..ba51d5bf7af1 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -163,6 +163,7 @@ enum node_stat_item { NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ WORKINGSET_REFAULT, WORKINGSET_ACTIVATE, + WORKINGSET_RESTORE, WORKINGSET_NODERECLAIM, NR_ANON_MAPPED, /* Mapped anonymous pages */ NR_FILE_MAPPED, /* pagecache pages mapped into pagetables. diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 74bee8cecf4c..4d99504f6496 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -69,13 +69,14 @@ */ enum pageflags { PG_locked, /* Page is locked. Don't touch. */ - PG_error, PG_referenced, PG_uptodate, PG_dirty, PG_lru, PG_active, + PG_workingset, PG_waiters, /* Page has waiters, check its waitqueue. Must be bit #7 and in the same byte as "PG_locked" */ + PG_error, PG_slab, PG_owner_priv_1, /* Owner use. If pagecache, fs may use*/ PG_arch_1, @@ -280,6 +281,8 @@ PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD) PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD) PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD) TESTCLEARFLAG(Active, active, PF_HEAD) +PAGEFLAG(Workingset, workingset, PF_HEAD) + TESTCLEARFLAG(Workingset, workingset, PF_HEAD) __PAGEFLAG(Slab, slab, PF_NO_TAIL) __PAGEFLAG(SlobFree, slob_free, PF_NO_TAIL) PAGEFLAG(Checked, checked, PF_NO_COMPOUND) /* Used by some filesystems */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 8e2c11e692ba..b93740d72e78 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -296,7 +296,7 @@ struct vma_swap_readahead { /* linux/mm/workingset.c */ void *workingset_eviction(struct address_space *mapping, struct page *page); -bool workingset_refault(void *shadow); +void workingset_refault(struct page *page, void *shadow); void workingset_activation(struct page *page); /* Do not use directly, use workingset_lookup_update */ diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index a81cffb76d89..a1675d43777e 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -88,6 +88,7 @@ {1UL << PG_dirty, "dirty" }, \ {1UL << PG_lru, "lru" }, \ {1UL << PG_active, "active" }, \ + {1UL << PG_workingset, "workingset" }, \ {1UL << PG_slab, "slab" }, \ {1UL << PG_owner_priv_1, "owner_priv_1" }, \ {1UL << PG_arch_1, "arch_1" }, \ diff --git a/mm/filemap.c b/mm/filemap.c index de6fed2a0815..7997adce5a29 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -915,12 +915,9 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping, * data from the working set, only to cache data that will * get overwritten with something else, is a waste of memory. */ - if (!(gfp_mask & __GFP_WRITE) && - shadow && workingset_refault(shadow)) { - SetPageActive(page); - workingset_activation(page); - } else - ClearPageActive(page); + WARN_ON_ONCE(PageActive(page)); + if (!(gfp_mask & __GFP_WRITE) && shadow) + workingset_refault(page, shadow); lru_cache_add(page); } return ret; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index deed97fba979..8ea1b36bd452 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2369,6 +2369,7 @@ static void __split_huge_page_tail(struct page *head, int tail, (1L << PG_mlocked) | (1L << PG_uptodate) | (1L << PG_active) | + (1L << PG_workingset) | (1L << PG_locked) | (1L << PG_unevictable) | (1L << PG_dirty))); diff --git a/mm/migrate.c b/mm/migrate.c index 84381b55b2bd..1ea27b343ccd 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -685,6 +685,8 @@ void migrate_page_states(struct page *newpage, struct page *page) SetPageActive(newpage); } else if (TestClearPageUnevictable(page)) SetPageUnevictable(newpage); + if (PageWorkingset(page)) + SetPageWorkingset(newpage); if (PageChecked(page)) SetPageChecked(newpage); if (PageMappedToDisk(page)) diff --git a/mm/swap_state.c b/mm/swap_state.c index ecee9c6c4cc1..0d6a7f268d2e 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -448,6 +448,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, /* * Initiate read into locked page and return. */ + SetPageWorkingset(new_page); lru_cache_add_anon(new_page); *new_page_allocated = true; return new_page; diff --git a/mm/vmscan.c b/mm/vmscan.c index 961401c46334..87e9fef341d2 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2145,6 +2145,7 @@ static void shrink_active_list(unsigned long nr_to_scan, } ClearPageActive(page); /* we are de-activating */ + SetPageWorkingset(page); list_add(&page->lru, &l_inactive); } diff --git a/mm/vmstat.c b/mm/vmstat.c index 2cec2fa4c8ae..d918f6192d15 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1145,6 +1145,7 @@ const char * const vmstat_text[] = { "nr_isolated_file", "workingset_refault", "workingset_activate", + "workingset_restore", "workingset_nodereclaim", "nr_anon_pages", "nr_mapped", diff --git a/mm/workingset.c b/mm/workingset.c index 7d5fa0dd2b38..99b7f7c09b13 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -121,7 +121,7 @@ * the only thing eating into inactive list space is active pages. * * - * Activating refaulting pages + * Refaulting inactive pages * * All that is known about the active list is that the pages have been * accessed more than once in the past. This means that at any given @@ -134,6 +134,10 @@ * used less frequently than the refaulting page - or even not used at * all anymore. * + * That means if inactive cache is refaulting with a suitable refault + * distance, we assume the cache workingset is transitioning and put + * pressure on the current active list. + * * If this is wrong and demotion kicks in, the pages which are truly * used more frequently will be reactivated while the less frequently * used once will be evicted from memory. @@ -141,6 +145,14 @@ * But if this is right, the stale pages will be pushed out of memory * and the used pages get to stay in cache. * + * Refaulting active pages + * + * If on the other hand the refaulting pages have recently been + * deactivated, it means that the active list is no longer protecting + * actively used cache from reclaim. The cache is NOT transitioning to + * a different workingset; the existing workingset is thrashing in the + * space allocated to the page cache. + * * * Implementation * @@ -156,8 +168,7 @@ */ #define EVICTION_SHIFT (RADIX_TREE_EXCEPTIONAL_ENTRY + \ - NODES_SHIFT + \ - MEM_CGROUP_ID_SHIFT) + 1 + NODES_SHIFT + MEM_CGROUP_ID_SHIFT) #define EVICTION_MASK (~0UL >> EVICTION_SHIFT) /* @@ -170,23 +181,28 @@ */ static unsigned int bucket_order __read_mostly; -static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction) +static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction, + bool workingset) { eviction >>= bucket_order; eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid; eviction = (eviction << NODES_SHIFT) | pgdat->node_id; + eviction = (eviction << 1) | workingset; eviction = (eviction << RADIX_TREE_EXCEPTIONAL_SHIFT); return (void *)(eviction | RADIX_TREE_EXCEPTIONAL_ENTRY); } static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, - unsigned long *evictionp) + unsigned long *evictionp, bool *workingsetp) { unsigned long entry = (unsigned long)shadow; int memcgid, nid; + bool workingset; entry >>= RADIX_TREE_EXCEPTIONAL_SHIFT; + workingset = entry & 1; + entry >>= 1; nid = entry & ((1UL << NODES_SHIFT) - 1); entry >>= NODES_SHIFT; memcgid = entry & ((1UL << MEM_CGROUP_ID_SHIFT) - 1); @@ -195,6 +211,7 @@ static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, *memcgidp = memcgid; *pgdat = NODE_DATA(nid); *evictionp = entry << bucket_order; + *workingsetp = workingset; } /** @@ -207,8 +224,8 @@ static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, */ void *workingset_eviction(struct address_space *mapping, struct page *page) { - struct mem_cgroup *memcg = page_memcg(page); struct pglist_data *pgdat = page_pgdat(page); + struct mem_cgroup *memcg = page_memcg(page); int memcgid = mem_cgroup_id(memcg); unsigned long eviction; struct lruvec *lruvec; @@ -220,30 +237,30 @@ void *workingset_eviction(struct address_space *mapping, struct page *page) lruvec = mem_cgroup_lruvec(pgdat, memcg); eviction = atomic_long_inc_return(&lruvec->inactive_age); - return pack_shadow(memcgid, pgdat, eviction); + return pack_shadow(memcgid, pgdat, eviction, PageWorkingset(page)); } /** * workingset_refault - evaluate the refault of a previously evicted page + * @page: the freshly allocated replacement page * @shadow: shadow entry of the evicted page * * Calculates and evaluates the refault distance of the previously * evicted page in the context of the node it was allocated in. - * - * Returns %true if the page should be activated, %false otherwise. */ -bool workingset_refault(void *shadow) +void workingset_refault(struct page *page, void *shadow) { unsigned long refault_distance; + struct pglist_data *pgdat; unsigned long active_file; struct mem_cgroup *memcg; unsigned long eviction; struct lruvec *lruvec; unsigned long refault; - struct pglist_data *pgdat; + bool workingset; int memcgid; - unpack_shadow(shadow, &memcgid, &pgdat, &eviction); + unpack_shadow(shadow, &memcgid, &pgdat, &eviction, &workingset); rcu_read_lock(); /* @@ -263,41 +280,51 @@ bool workingset_refault(void *shadow) * configurations instead. */ memcg = mem_cgroup_from_id(memcgid); - if (!mem_cgroup_disabled() && !memcg) { - rcu_read_unlock(); - return false; - } + if (!mem_cgroup_disabled() && !memcg) + goto out; lruvec = mem_cgroup_lruvec(pgdat, memcg); refault = atomic_long_read(&lruvec->inactive_age); active_file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES); /* - * The unsigned subtraction here gives an accurate distance - * across inactive_age overflows in most cases. + * Calculate the refault distance * - * There is a special case: usually, shadow entries have a - * short lifetime and are either refaulted or reclaimed along - * with the inode before they get too old. But it is not - * impossible for the inactive_age to lap a shadow entry in - * the field, which can then can result in a false small - * refault distance, leading to a false activation should this - * old entry actually refault again. However, earlier kernels - * used to deactivate unconditionally with *every* reclaim - * invocation for the longest time, so the occasional - * inappropriate activation leading to pressure on the active - * list is not a problem. + * The unsigned subtraction here gives an accurate distance + * across inactive_age overflows in most cases. There is a + * special case: usually, shadow entries have a short lifetime + * and are either refaulted or reclaimed along with the inode + * before they get too old. But it is not impossible for the + * inactive_age to lap a shadow entry in the field, which can + * then result in a false small refault distance, leading to a + * false activation should this old entry actually refault + * again. However, earlier kernels used to deactivate + * unconditionally with *every* reclaim invocation for the + * longest time, so the occasional inappropriate activation + * leading to pressure on the active list is not a problem. */ refault_distance = (refault - eviction) & EVICTION_MASK; inc_lruvec_state(lruvec, WORKINGSET_REFAULT); - if (refault_distance <= active_file) { - inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE); - rcu_read_unlock(); - return true; + /* + * Compare the distance to the existing workingset size. We + * don't act on pages that couldn't stay resident even if all + * the memory was available to the page cache. + */ + if (refault_distance > active_file) + goto out; + + SetPageActive(page); + atomic_long_inc(&lruvec->inactive_age); + inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE); + + /* Page was active prior to eviction */ + if (workingset) { + SetPageWorkingset(page); + inc_lruvec_state(lruvec, WORKINGSET_RESTORE); } +out: rcu_read_unlock(); - return false; } /** -- cgit v1.2.3 From b1d29ba82cf2bc784f4c963ddd6a2cf29e229b33 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:08 -0700 Subject: delayacct: track delays from thrashing cache pages Delay accounting already measures the time a task spends in direct reclaim and waiting for swapin, but in low memory situations tasks spend can spend a significant amount of their time waiting on thrashing page cache. This isn't tracked right now. To know the full impact of memory contention on an individual task, measure the delay when waiting for a recently evicted active cache page to read back into memory. Also update tools/accounting/getdelays.c: [hannes@computer accounting]$ sudo ./getdelays -d -p 1 print delayacct stats ON PID 1 CPU count real total virtual total delay total delay average 50318 745000000 847346785 400533713 0.008ms IO count delay total delay average 435 122601218 0ms SWAP count delay total delay average 0 0 0ms RECLAIM count delay total delay average 0 0 0ms THRASHING count delay total delay average 19 12621439 0ms Link: http://lkml.kernel.org/r/20180828172258.3185-4-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Peter Zijlstra (Intel) Tested-by: Daniel Drake Tested-by: Suren Baghdasaryan Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Tejun Heo Cc: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/delayacct.h | 23 +++++++++++++++++++++++ include/uapi/linux/taskstats.h | 6 +++++- kernel/delayacct.c | 15 +++++++++++++++ mm/filemap.c | 11 +++++++++++ tools/accounting/getdelays.c | 8 +++++++- 5 files changed, 61 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index 31c865d1842e..577d1b25fccd 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -57,7 +57,12 @@ struct task_delay_info { u64 freepages_start; u64 freepages_delay; /* wait for memory reclaim */ + + u64 thrashing_start; + u64 thrashing_delay; /* wait for thrashing page */ + u32 freepages_count; /* total count of memory reclaim */ + u32 thrashing_count; /* total count of thrash waits */ }; #endif @@ -76,6 +81,8 @@ extern int __delayacct_add_tsk(struct taskstats *, struct task_struct *); extern __u64 __delayacct_blkio_ticks(struct task_struct *); extern void __delayacct_freepages_start(void); extern void __delayacct_freepages_end(void); +extern void __delayacct_thrashing_start(void); +extern void __delayacct_thrashing_end(void); static inline int delayacct_is_task_waiting_on_io(struct task_struct *p) { @@ -156,6 +163,18 @@ static inline void delayacct_freepages_end(void) __delayacct_freepages_end(); } +static inline void delayacct_thrashing_start(void) +{ + if (current->delays) + __delayacct_thrashing_start(); +} + +static inline void delayacct_thrashing_end(void) +{ + if (current->delays) + __delayacct_thrashing_end(); +} + #else static inline void delayacct_set_flag(int flag) {} @@ -182,6 +201,10 @@ static inline void delayacct_freepages_start(void) {} static inline void delayacct_freepages_end(void) {} +static inline void delayacct_thrashing_start(void) +{} +static inline void delayacct_thrashing_end(void) +{} #endif /* CONFIG_TASK_DELAY_ACCT */ diff --git a/include/uapi/linux/taskstats.h b/include/uapi/linux/taskstats.h index b7aa7bb2349f..5e8ca16a9079 100644 --- a/include/uapi/linux/taskstats.h +++ b/include/uapi/linux/taskstats.h @@ -34,7 +34,7 @@ */ -#define TASKSTATS_VERSION 8 +#define TASKSTATS_VERSION 9 #define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ @@ -164,6 +164,10 @@ struct taskstats { /* Delay waiting for memory reclaim */ __u64 freepages_count; __u64 freepages_delay_total; + + /* Delay waiting for thrashing page */ + __u64 thrashing_count; + __u64 thrashing_delay_total; }; diff --git a/kernel/delayacct.c b/kernel/delayacct.c index ca8ac2824f0b..2a12b988c717 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -135,9 +135,12 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) d->swapin_delay_total = (tmp < d->swapin_delay_total) ? 0 : tmp; tmp = d->freepages_delay_total + tsk->delays->freepages_delay; d->freepages_delay_total = (tmp < d->freepages_delay_total) ? 0 : tmp; + tmp = d->thrashing_delay_total + tsk->delays->thrashing_delay; + d->thrashing_delay_total = (tmp < d->thrashing_delay_total) ? 0 : tmp; d->blkio_count += tsk->delays->blkio_count; d->swapin_count += tsk->delays->swapin_count; d->freepages_count += tsk->delays->freepages_count; + d->thrashing_count += tsk->delays->thrashing_count; raw_spin_unlock_irqrestore(&tsk->delays->lock, flags); return 0; @@ -169,3 +172,15 @@ void __delayacct_freepages_end(void) ¤t->delays->freepages_count); } +void __delayacct_thrashing_start(void) +{ + current->delays->thrashing_start = ktime_get_ns(); +} + +void __delayacct_thrashing_end(void) +{ + delayacct_end(¤t->delays->lock, + ¤t->delays->thrashing_start, + ¤t->delays->thrashing_delay, + ¤t->delays->thrashing_count); +} diff --git a/mm/filemap.c b/mm/filemap.c index 7997adce5a29..01a841f17bf4 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -36,6 +36,7 @@ #include #include #include +#include #include "internal.h" #define CREATE_TRACE_POINTS @@ -1073,8 +1074,15 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q, { struct wait_page_queue wait_page; wait_queue_entry_t *wait = &wait_page.wait; + bool thrashing = false; int ret = 0; + if (bit_nr == PG_locked && !PageSwapBacked(page) && + !PageUptodate(page) && PageWorkingset(page)) { + delayacct_thrashing_start(); + thrashing = true; + } + init_wait(wait); wait->flags = lock ? WQ_FLAG_EXCLUSIVE : 0; wait->func = wake_page_function; @@ -1113,6 +1121,9 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q, finish_wait(q, wait); + if (thrashing) + delayacct_thrashing_end(); + /* * A signal could leave PageWaiters set. Clearing it here if * !waitqueue_active would be possible (by open-coding finish_wait), diff --git a/tools/accounting/getdelays.c b/tools/accounting/getdelays.c index 9f420d98b5fb..8cb504d30384 100644 --- a/tools/accounting/getdelays.c +++ b/tools/accounting/getdelays.c @@ -203,6 +203,8 @@ static void print_delayacct(struct taskstats *t) "SWAP %15s%15s%15s\n" " %15llu%15llu%15llums\n" "RECLAIM %12s%15s%15s\n" + " %15llu%15llu%15llums\n" + "THRASHING%12s%15s%15s\n" " %15llu%15llu%15llums\n", "count", "real total", "virtual total", "delay total", "delay average", @@ -222,7 +224,11 @@ static void print_delayacct(struct taskstats *t) "count", "delay total", "delay average", (unsigned long long)t->freepages_count, (unsigned long long)t->freepages_delay_total, - average_ms(t->freepages_delay_total, t->freepages_count)); + average_ms(t->freepages_delay_total, t->freepages_count), + "count", "delay total", "delay average", + (unsigned long long)t->thrashing_count, + (unsigned long long)t->thrashing_delay_total, + average_ms(t->thrashing_delay_total, t->thrashing_count)); } static void task_context_switch_counts(struct taskstats *t) -- cgit v1.2.3 From 8508cf3ffad4defa202b303e5b6379efc4cd9054 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:11 -0700 Subject: sched: loadavg: consolidate LOAD_INT, LOAD_FRAC, CALC_LOAD There are several definitions of those functions/macros in places that mess with fixed-point load averages. Provide an official version. [akpm@linux-foundation.org: fix missed conversion in block/blk-iolatency.c] Link: http://lkml.kernel.org/r/20180828172258.3185-5-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Peter Zijlstra (Intel) Tested-by: Suren Baghdasaryan Tested-by: Daniel Drake Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Tejun Heo Cc: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/platforms/cell/cpufreq_spudemand.c | 2 +- arch/powerpc/platforms/cell/spufs/sched.c | 9 +++------ arch/s390/appldata/appldata_os.c | 4 ---- block/blk-iolatency.c | 8 +++++--- drivers/cpuidle/governors/menu.c | 4 ---- fs/proc/loadavg.c | 3 --- include/linux/sched/loadavg.h | 21 +++++++++++++++++---- kernel/debug/kdb/kdb_main.c | 7 +------ kernel/sched/loadavg.c | 15 --------------- 9 files changed, 27 insertions(+), 46 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/platforms/cell/cpufreq_spudemand.c b/arch/powerpc/platforms/cell/cpufreq_spudemand.c index 882944c36ef5..5d8e8b6bb1cc 100644 --- a/arch/powerpc/platforms/cell/cpufreq_spudemand.c +++ b/arch/powerpc/platforms/cell/cpufreq_spudemand.c @@ -49,7 +49,7 @@ static int calc_freq(struct spu_gov_info_struct *info) cpu = info->policy->cpu; busy_spus = atomic_read(&cbe_spu_info[cpu_to_node(cpu)].busy_spus); - CALC_LOAD(info->busy_spus, EXP, busy_spus * FIXED_1); + info->busy_spus = calc_load(info->busy_spus, EXP, busy_spus * FIXED_1); pr_debug("cpu %d: busy_spus=%d, info->busy_spus=%ld\n", cpu, busy_spus, info->busy_spus); diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c index c9ef3c532169..9fcccb4490b9 100644 --- a/arch/powerpc/platforms/cell/spufs/sched.c +++ b/arch/powerpc/platforms/cell/spufs/sched.c @@ -987,9 +987,9 @@ static void spu_calc_load(void) unsigned long active_tasks; /* fixed-point */ active_tasks = count_active_contexts() * FIXED_1; - CALC_LOAD(spu_avenrun[0], EXP_1, active_tasks); - CALC_LOAD(spu_avenrun[1], EXP_5, active_tasks); - CALC_LOAD(spu_avenrun[2], EXP_15, active_tasks); + spu_avenrun[0] = calc_load(spu_avenrun[0], EXP_1, active_tasks); + spu_avenrun[1] = calc_load(spu_avenrun[1], EXP_5, active_tasks); + spu_avenrun[2] = calc_load(spu_avenrun[2], EXP_15, active_tasks); } static void spusched_wake(struct timer_list *unused) @@ -1071,9 +1071,6 @@ void spuctx_switch_state(struct spu_context *ctx, } } -#define LOAD_INT(x) ((x) >> FSHIFT) -#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) - static int show_spu_loadavg(struct seq_file *s, void *private) { int a, b, c; diff --git a/arch/s390/appldata/appldata_os.c b/arch/s390/appldata/appldata_os.c index 433a994b1a89..54f375627532 100644 --- a/arch/s390/appldata/appldata_os.c +++ b/arch/s390/appldata/appldata_os.c @@ -25,10 +25,6 @@ #include "appldata.h" - -#define LOAD_INT(x) ((x) >> FSHIFT) -#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) - /* * OS data * diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c index 35c48d7b8f78..28f80d227528 100644 --- a/block/blk-iolatency.c +++ b/block/blk-iolatency.c @@ -153,7 +153,7 @@ struct iolatency_grp { #define BLKIOLATENCY_MAX_WIN_SIZE NSEC_PER_SEC /* * These are the constants used to fake the fixed-point moving average - * calculation just like load average. The call to CALC_LOAD folds + * calculation just like load average. The call to calc_load() folds * (FIXED_1 (2048) - exp_factor) * new_sample into lat_avg. The sampling * window size is bucketed to try to approximately calculate average * latency such that 1/exp (decay rate) is [1 min, 2.5 min) when windows @@ -248,7 +248,7 @@ static inline void iolat_update_total_lat_avg(struct iolatency_grp *iolat, return; /* - * CALC_LOAD takes in a number stored in fixed point representation. + * calc_load() takes in a number stored in fixed point representation. * Because we are using this for IO time in ns, the values stored * are significantly larger than the FIXED_1 denominator (2048). * Therefore, rounding errors in the calculation are negligible and @@ -257,7 +257,9 @@ static inline void iolat_update_total_lat_avg(struct iolatency_grp *iolat, exp_idx = min_t(int, BLKIOLATENCY_NR_EXP_FACTORS - 1, div64_u64(iolat->cur_win_nsec, BLKIOLATENCY_EXP_BUCKET_SIZE)); - CALC_LOAD(iolat->lat_avg, iolatency_exp_factors[exp_idx], stat->rqs.mean); + iolat->lat_avg = calc_load(iolat->lat_avg, + iolatency_exp_factors[exp_idx], + stat->rqs.mean); } static inline bool iolatency_may_queue(struct iolatency_grp *iolat, diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c index 575a68f31761..71979605246e 100644 --- a/drivers/cpuidle/governors/menu.c +++ b/drivers/cpuidle/governors/menu.c @@ -130,10 +130,6 @@ struct menu_device { int interval_ptr; }; - -#define LOAD_INT(x) ((x) >> FSHIFT) -#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) - static inline int get_loadavg(unsigned long load) { return LOAD_INT(load) * 10 + LOAD_FRAC(load) / 10; diff --git a/fs/proc/loadavg.c b/fs/proc/loadavg.c index d06694757201..8468baee951d 100644 --- a/fs/proc/loadavg.c +++ b/fs/proc/loadavg.c @@ -10,9 +10,6 @@ #include #include -#define LOAD_INT(x) ((x) >> FSHIFT) -#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) - static int loadavg_proc_show(struct seq_file *m, void *v) { unsigned long avnrun[3]; diff --git a/include/linux/sched/loadavg.h b/include/linux/sched/loadavg.h index 80bc84ba5d2a..cc9cc62bb1f8 100644 --- a/include/linux/sched/loadavg.h +++ b/include/linux/sched/loadavg.h @@ -22,10 +22,23 @@ extern void get_avenrun(unsigned long *loads, unsigned long offset, int shift); #define EXP_5 2014 /* 1/exp(5sec/5min) */ #define EXP_15 2037 /* 1/exp(5sec/15min) */ -#define CALC_LOAD(load,exp,n) \ - load *= exp; \ - load += n*(FIXED_1-exp); \ - load >>= FSHIFT; +/* + * a1 = a0 * e + a * (1 - e) + */ +static inline unsigned long +calc_load(unsigned long load, unsigned long exp, unsigned long active) +{ + unsigned long newload; + + newload = load * exp + active * (FIXED_1 - exp); + if (active >= load) + newload += FIXED_1-1; + + return newload / FIXED_1; +} + +#define LOAD_INT(x) ((x) >> FSHIFT) +#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) extern void calc_global_load(unsigned long ticks); diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 2ddfce8f1e8f..bb4fe4e1a601 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -2556,16 +2556,11 @@ static int kdb_summary(int argc, const char **argv) } kdb_printf("%02ld:%02ld\n", val.uptime/(60*60), (val.uptime/60)%60); - /* lifted from fs/proc/proc_misc.c::loadavg_read_proc() */ - -#define LOAD_INT(x) ((x) >> FSHIFT) -#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) kdb_printf("load avg %ld.%02ld %ld.%02ld %ld.%02ld\n", LOAD_INT(val.loads[0]), LOAD_FRAC(val.loads[0]), LOAD_INT(val.loads[1]), LOAD_FRAC(val.loads[1]), LOAD_INT(val.loads[2]), LOAD_FRAC(val.loads[2])); -#undef LOAD_INT -#undef LOAD_FRAC + /* Display in kilobytes */ #define K(x) ((x) << (PAGE_SHIFT - 10)) kdb_printf("\nMemTotal: %8lu kB\nMemFree: %8lu kB\n" diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c index a171c1258109..54fbdfb2d86c 100644 --- a/kernel/sched/loadavg.c +++ b/kernel/sched/loadavg.c @@ -91,21 +91,6 @@ long calc_load_fold_active(struct rq *this_rq, long adjust) return delta; } -/* - * a1 = a0 * e + a * (1 - e) - */ -static unsigned long -calc_load(unsigned long load, unsigned long exp, unsigned long active) -{ - unsigned long newload; - - newload = load * exp + active * (FIXED_1 - exp); - if (active >= load) - newload += FIXED_1-1; - - return newload / FIXED_1; -} - #ifdef CONFIG_NO_HZ_COMMON /* * Handle NO_HZ for the global load-average. -- cgit v1.2.3 From 5c54f5b9edb1aa2eabbb1091c458f1b6776a1896 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:16 -0700 Subject: sched: loadavg: make calc_load_n() public It's going to be used in a later patch. Keep the churn separate. Link: http://lkml.kernel.org/r/20180828172258.3185-6-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Peter Zijlstra (Intel) Tested-by: Suren Baghdasaryan Tested-by: Daniel Drake Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Tejun Heo Cc: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched/loadavg.h | 3 + kernel/sched/loadavg.c | 138 +++++++++++++++++++++--------------------- 2 files changed, 72 insertions(+), 69 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/loadavg.h b/include/linux/sched/loadavg.h index cc9cc62bb1f8..4859bea47a7b 100644 --- a/include/linux/sched/loadavg.h +++ b/include/linux/sched/loadavg.h @@ -37,6 +37,9 @@ calc_load(unsigned long load, unsigned long exp, unsigned long active) return newload / FIXED_1; } +extern unsigned long calc_load_n(unsigned long load, unsigned long exp, + unsigned long active, unsigned int n); + #define LOAD_INT(x) ((x) >> FSHIFT) #define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c index 54fbdfb2d86c..28a516575c18 100644 --- a/kernel/sched/loadavg.c +++ b/kernel/sched/loadavg.c @@ -91,6 +91,75 @@ long calc_load_fold_active(struct rq *this_rq, long adjust) return delta; } +/** + * fixed_power_int - compute: x^n, in O(log n) time + * + * @x: base of the power + * @frac_bits: fractional bits of @x + * @n: power to raise @x to. + * + * By exploiting the relation between the definition of the natural power + * function: x^n := x*x*...*x (x multiplied by itself for n times), and + * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i, + * (where: n_i \elem {0, 1}, the binary vector representing n), + * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is + * of course trivially computable in O(log_2 n), the length of our binary + * vector. + */ +static unsigned long +fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n) +{ + unsigned long result = 1UL << frac_bits; + + if (n) { + for (;;) { + if (n & 1) { + result *= x; + result += 1UL << (frac_bits - 1); + result >>= frac_bits; + } + n >>= 1; + if (!n) + break; + x *= x; + x += 1UL << (frac_bits - 1); + x >>= frac_bits; + } + } + + return result; +} + +/* + * a1 = a0 * e + a * (1 - e) + * + * a2 = a1 * e + a * (1 - e) + * = (a0 * e + a * (1 - e)) * e + a * (1 - e) + * = a0 * e^2 + a * (1 - e) * (1 + e) + * + * a3 = a2 * e + a * (1 - e) + * = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e) + * = a0 * e^3 + a * (1 - e) * (1 + e + e^2) + * + * ... + * + * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1] + * = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e) + * = a0 * e^n + a * (1 - e^n) + * + * [1] application of the geometric series: + * + * n 1 - x^(n+1) + * S_n := \Sum x^i = ------------- + * i=0 1 - x + */ +unsigned long +calc_load_n(unsigned long load, unsigned long exp, + unsigned long active, unsigned int n) +{ + return calc_load(load, fixed_power_int(exp, FSHIFT, n), active); +} + #ifdef CONFIG_NO_HZ_COMMON /* * Handle NO_HZ for the global load-average. @@ -210,75 +279,6 @@ static long calc_load_nohz_fold(void) return delta; } -/** - * fixed_power_int - compute: x^n, in O(log n) time - * - * @x: base of the power - * @frac_bits: fractional bits of @x - * @n: power to raise @x to. - * - * By exploiting the relation between the definition of the natural power - * function: x^n := x*x*...*x (x multiplied by itself for n times), and - * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i, - * (where: n_i \elem {0, 1}, the binary vector representing n), - * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is - * of course trivially computable in O(log_2 n), the length of our binary - * vector. - */ -static unsigned long -fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n) -{ - unsigned long result = 1UL << frac_bits; - - if (n) { - for (;;) { - if (n & 1) { - result *= x; - result += 1UL << (frac_bits - 1); - result >>= frac_bits; - } - n >>= 1; - if (!n) - break; - x *= x; - x += 1UL << (frac_bits - 1); - x >>= frac_bits; - } - } - - return result; -} - -/* - * a1 = a0 * e + a * (1 - e) - * - * a2 = a1 * e + a * (1 - e) - * = (a0 * e + a * (1 - e)) * e + a * (1 - e) - * = a0 * e^2 + a * (1 - e) * (1 + e) - * - * a3 = a2 * e + a * (1 - e) - * = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e) - * = a0 * e^3 + a * (1 - e) * (1 + e + e^2) - * - * ... - * - * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1] - * = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e) - * = a0 * e^n + a * (1 - e^n) - * - * [1] application of the geometric series: - * - * n 1 - x^(n+1) - * S_n := \Sum x^i = ------------- - * i=0 1 - x - */ -static unsigned long -calc_load_n(unsigned long load, unsigned long exp, - unsigned long active, unsigned int n) -{ - return calc_load(load, fixed_power_int(exp, FSHIFT, n), active); -} - /* * NO_HZ can leave us missing all per-CPU ticks calling * calc_load_fold_active(), but since a NO_HZ CPU folds its delta into -- cgit v1.2.3 From eb414681d5a07d28d2ff90dc05f69ec6b232ebd2 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:27 -0700 Subject: psi: pressure stall information for CPU, memory, and IO When systems are overcommitted and resources become contended, it's hard to tell exactly the impact this has on workload productivity, or how close the system is to lockups and OOM kills. In particular, when machines work multiple jobs concurrently, the impact of overcommit in terms of latency and throughput on the individual job can be enormous. In order to maximize hardware utilization without sacrificing individual job health or risk complete machine lockups, this patch implements a way to quantify resource pressure in the system. A kernel built with CONFIG_PSI=y creates files in /proc/pressure/ that expose the percentage of time the system is stalled on CPU, memory, or IO, respectively. Stall states are aggregate versions of the per-task delay accounting delays: cpu: some tasks are runnable but not executing on a CPU memory: tasks are reclaiming, or waiting for swapin or thrashing cache io: tasks are waiting for io completions These percentages of walltime can be thought of as pressure percentages, and they give a general sense of system health and productivity loss incurred by resource overcommit. They can also indicate when the system is approaching lockup scenarios and OOMs. To do this, psi keeps track of the task states associated with each CPU and samples the time they spend in stall states. Every 2 seconds, the samples are averaged across CPUs - weighted by the CPUs' non-idle time to eliminate artifacts from unused CPUs - and translated into percentages of walltime. A running average of those percentages is maintained over 10s, 1m, and 5m periods (similar to the loadaverage). [hannes@cmpxchg.org: doc fixlet, per Randy] Link: http://lkml.kernel.org/r/20180828205625.GA14030@cmpxchg.org [hannes@cmpxchg.org: code optimization] Link: http://lkml.kernel.org/r/20180907175015.GA8479@cmpxchg.org [hannes@cmpxchg.org: rename psi_clock() to psi_update_work(), per Peter] Link: http://lkml.kernel.org/r/20180907145404.GB11088@cmpxchg.org [hannes@cmpxchg.org: fix build] Link: http://lkml.kernel.org/r/20180913014222.GA2370@cmpxchg.org Link: http://lkml.kernel.org/r/20180828172258.3185-9-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Peter Zijlstra (Intel) Tested-by: Daniel Drake Tested-by: Suren Baghdasaryan Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Tejun Heo Cc: Vinayak Menon Cc: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/accounting/psi.txt | 64 ++++ include/linux/psi.h | 28 ++ include/linux/psi_types.h | 92 ++++++ include/linux/sched.h | 10 + init/Kconfig | 15 + kernel/fork.c | 4 + kernel/sched/Makefile | 1 + kernel/sched/core.c | 12 +- kernel/sched/psi.c | 657 +++++++++++++++++++++++++++++++++++++++ kernel/sched/sched.h | 2 + kernel/sched/stats.h | 86 +++++ mm/compaction.c | 5 + mm/filemap.c | 15 +- mm/page_alloc.c | 9 + mm/vmscan.c | 9 + 15 files changed, 1003 insertions(+), 6 deletions(-) create mode 100644 Documentation/accounting/psi.txt create mode 100644 include/linux/psi.h create mode 100644 include/linux/psi_types.h create mode 100644 kernel/sched/psi.c (limited to 'include/linux') diff --git a/Documentation/accounting/psi.txt b/Documentation/accounting/psi.txt new file mode 100644 index 000000000000..3753a82f1cf5 --- /dev/null +++ b/Documentation/accounting/psi.txt @@ -0,0 +1,64 @@ +================================ +PSI - Pressure Stall Information +================================ + +:Date: April, 2018 +:Author: Johannes Weiner + +When CPU, memory or IO devices are contended, workloads experience +latency spikes, throughput losses, and run the risk of OOM kills. + +Without an accurate measure of such contention, users are forced to +either play it safe and under-utilize their hardware resources, or +roll the dice and frequently suffer the disruptions resulting from +excessive overcommit. + +The psi feature identifies and quantifies the disruptions caused by +such resource crunches and the time impact it has on complex workloads +or even entire systems. + +Having an accurate measure of productivity losses caused by resource +scarcity aids users in sizing workloads to hardware--or provisioning +hardware according to workload demand. + +As psi aggregates this information in realtime, systems can be managed +dynamically using techniques such as load shedding, migrating jobs to +other systems or data centers, or strategically pausing or killing low +priority or restartable batch jobs. + +This allows maximizing hardware utilization without sacrificing +workload health or risking major disruptions such as OOM kills. + +Pressure interface +================== + +Pressure information for each resource is exported through the +respective file in /proc/pressure/ -- cpu, memory, and io. + +The format for CPU is as such: + +some avg10=0.00 avg60=0.00 avg300=0.00 total=0 + +and for memory and IO: + +some avg10=0.00 avg60=0.00 avg300=0.00 total=0 +full avg10=0.00 avg60=0.00 avg300=0.00 total=0 + +The "some" line indicates the share of time in which at least some +tasks are stalled on a given resource. + +The "full" line indicates the share of time in which all non-idle +tasks are stalled on a given resource simultaneously. In this state +actual CPU cycles are going to waste, and a workload that spends +extended time in this state is considered to be thrashing. This has +severe impact on performance, and it's useful to distinguish this +situation from a state where some tasks are stalled but the CPU is +still doing productive work. As such, time spent in this subset of the +stall state is tracked separately and exported in the "full" averages. + +The ratios are tracked as recent trends over ten, sixty, and three +hundred second windows, which gives insight into short term events as +well as medium and long term trends. The total absolute stall time is +tracked and exported as well, to allow detection of latency spikes +which wouldn't necessarily make a dent in the time averages, or to +average trends over custom time frames. diff --git a/include/linux/psi.h b/include/linux/psi.h new file mode 100644 index 000000000000..b0daf050de58 --- /dev/null +++ b/include/linux/psi.h @@ -0,0 +1,28 @@ +#ifndef _LINUX_PSI_H +#define _LINUX_PSI_H + +#include +#include + +#ifdef CONFIG_PSI + +extern bool psi_disabled; + +void psi_init(void); + +void psi_task_change(struct task_struct *task, int clear, int set); + +void psi_memstall_tick(struct task_struct *task, int cpu); +void psi_memstall_enter(unsigned long *flags); +void psi_memstall_leave(unsigned long *flags); + +#else /* CONFIG_PSI */ + +static inline void psi_init(void) {} + +static inline void psi_memstall_enter(unsigned long *flags) {} +static inline void psi_memstall_leave(unsigned long *flags) {} + +#endif /* CONFIG_PSI */ + +#endif /* _LINUX_PSI_H */ diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h new file mode 100644 index 000000000000..2cf422db5d18 --- /dev/null +++ b/include/linux/psi_types.h @@ -0,0 +1,92 @@ +#ifndef _LINUX_PSI_TYPES_H +#define _LINUX_PSI_TYPES_H + +#include +#include + +#ifdef CONFIG_PSI + +/* Tracked task states */ +enum psi_task_count { + NR_IOWAIT, + NR_MEMSTALL, + NR_RUNNING, + NR_PSI_TASK_COUNTS, +}; + +/* Task state bitmasks */ +#define TSK_IOWAIT (1 << NR_IOWAIT) +#define TSK_MEMSTALL (1 << NR_MEMSTALL) +#define TSK_RUNNING (1 << NR_RUNNING) + +/* Resources that workloads could be stalled on */ +enum psi_res { + PSI_IO, + PSI_MEM, + PSI_CPU, + NR_PSI_RESOURCES, +}; + +/* + * Pressure states for each resource: + * + * SOME: Stalled tasks & working tasks + * FULL: Stalled tasks & no working tasks + */ +enum psi_states { + PSI_IO_SOME, + PSI_IO_FULL, + PSI_MEM_SOME, + PSI_MEM_FULL, + PSI_CPU_SOME, + /* Only per-CPU, to weigh the CPU in the global average: */ + PSI_NONIDLE, + NR_PSI_STATES, +}; + +struct psi_group_cpu { + /* 1st cacheline updated by the scheduler */ + + /* Aggregator needs to know of concurrent changes */ + seqcount_t seq ____cacheline_aligned_in_smp; + + /* States of the tasks belonging to this group */ + unsigned int tasks[NR_PSI_TASK_COUNTS]; + + /* Period time sampling buckets for each state of interest (ns) */ + u32 times[NR_PSI_STATES]; + + /* Time of last task change in this group (rq_clock) */ + u64 state_start; + + /* 2nd cacheline updated by the aggregator */ + + /* Delta detection against the sampling buckets */ + u32 times_prev[NR_PSI_STATES] ____cacheline_aligned_in_smp; +}; + +struct psi_group { + /* Protects data updated during an aggregation */ + struct mutex stat_lock; + + /* Per-cpu task state & time tracking */ + struct psi_group_cpu __percpu *pcpu; + + /* Periodic aggregation state */ + u64 total_prev[NR_PSI_STATES - 1]; + u64 last_update; + u64 next_update; + struct delayed_work clock_work; + + /* Total stall times and sampled pressure averages */ + u64 total[NR_PSI_STATES - 1]; + unsigned long avg[NR_PSI_STATES - 1][3]; +}; + +#else /* CONFIG_PSI */ + +struct psi_group { }; + +#endif /* CONFIG_PSI */ + +#endif /* _LINUX_PSI_TYPES_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index adfb3f9a7597..b8fcc6b3080c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -706,6 +707,10 @@ struct task_struct { unsigned sched_contributes_to_load:1; unsigned sched_migrated:1; unsigned sched_remote_wakeup:1; +#ifdef CONFIG_PSI + unsigned sched_psi_wake_requeue:1; +#endif + /* Force alignment to the next boundary: */ unsigned :0; @@ -965,6 +970,10 @@ struct task_struct { kernel_siginfo_t *last_siginfo; struct task_io_accounting ioac; +#ifdef CONFIG_PSI + /* Pressure stall state */ + unsigned int psi_flags; +#endif #ifdef CONFIG_TASK_XACCT /* Accumulated RSS usage: */ u64 acct_rss_mem1; @@ -1391,6 +1400,7 @@ extern struct pid *cad_pid; #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */ #define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */ +#define PF_MEMSTALL 0x01000000 /* Stalled due to lack of memory */ #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_allowed */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */ diff --git a/init/Kconfig b/init/Kconfig index 317d5ccb5191..26e639df5517 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -490,6 +490,21 @@ config TASK_IO_ACCOUNTING Say N if unsure. +config PSI + bool "Pressure stall information tracking" + help + Collect metrics that indicate how overcommitted the CPU, memory, + and IO capacity are in the system. + + If you say Y here, the kernel will create /proc/pressure/ with the + pressure statistics files cpu, memory, and io. These will indicate + the share of walltime in which some or all tasks in the system are + delayed due to contention of the respective resource. + + For more details see Documentation/accounting/psi.txt. + + Say N if unsure. + endmenu # "CPU/Task time and stats accounting" config CPU_ISOLATION diff --git a/kernel/fork.c b/kernel/fork.c index 3c719fec46c5..8f82a3bdcb8f 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1822,6 +1822,10 @@ static __latent_entropy struct task_struct *copy_process( p->default_timer_slack_ns = current->timer_slack_ns; +#ifdef CONFIG_PSI + p->psi_flags = 0; +#endif + task_io_accounting_init(&p->ioac); acct_clear_integrals(p); diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index 7fe183404c38..21fb5a5662b5 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -29,3 +29,4 @@ obj-$(CONFIG_CPU_FREQ) += cpufreq.o obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o obj-$(CONFIG_MEMBARRIER) += membarrier.o obj-$(CONFIG_CPU_ISOLATION) += isolation.o +obj-$(CONFIG_PSI) += psi.o diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f3efef387797..fd2fce8a001b 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -722,8 +722,10 @@ static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags) if (!(flags & ENQUEUE_NOCLOCK)) update_rq_clock(rq); - if (!(flags & ENQUEUE_RESTORE)) + if (!(flags & ENQUEUE_RESTORE)) { sched_info_queued(rq, p); + psi_enqueue(p, flags & ENQUEUE_WAKEUP); + } p->sched_class->enqueue_task(rq, p, flags); } @@ -733,8 +735,10 @@ static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags) if (!(flags & DEQUEUE_NOCLOCK)) update_rq_clock(rq); - if (!(flags & DEQUEUE_SAVE)) + if (!(flags & DEQUEUE_SAVE)) { sched_info_dequeued(rq, p); + psi_dequeue(p, flags & DEQUEUE_SLEEP); + } p->sched_class->dequeue_task(rq, p, flags); } @@ -2037,6 +2041,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags); if (task_cpu(p) != cpu) { wake_flags |= WF_MIGRATED; + psi_ttwu_dequeue(p); set_task_cpu(p, cpu); } @@ -3051,6 +3056,7 @@ void scheduler_tick(void) curr->sched_class->task_tick(rq, curr, 0); cpu_load_update_active(rq); calc_global_load_tick(rq); + psi_task_tick(rq); rq_unlock(rq, &rf); @@ -6067,6 +6073,8 @@ void __init sched_init(void) init_schedstats(); + psi_init(); + scheduler_running = 1; } diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c new file mode 100644 index 000000000000..595414599b98 --- /dev/null +++ b/kernel/sched/psi.c @@ -0,0 +1,657 @@ +/* + * Pressure stall information for CPU, memory and IO + * + * Copyright (c) 2018 Facebook, Inc. + * Author: Johannes Weiner + * + * When CPU, memory and IO are contended, tasks experience delays that + * reduce throughput and introduce latencies into the workload. Memory + * and IO contention, in addition, can cause a full loss of forward + * progress in which the CPU goes idle. + * + * This code aggregates individual task delays into resource pressure + * metrics that indicate problems with both workload health and + * resource utilization. + * + * Model + * + * The time in which a task can execute on a CPU is our baseline for + * productivity. Pressure expresses the amount of time in which this + * potential cannot be realized due to resource contention. + * + * This concept of productivity has two components: the workload and + * the CPU. To measure the impact of pressure on both, we define two + * contention states for a resource: SOME and FULL. + * + * In the SOME state of a given resource, one or more tasks are + * delayed on that resource. This affects the workload's ability to + * perform work, but the CPU may still be executing other tasks. + * + * In the FULL state of a given resource, all non-idle tasks are + * delayed on that resource such that nobody is advancing and the CPU + * goes idle. This leaves both workload and CPU unproductive. + * + * (Naturally, the FULL state doesn't exist for the CPU resource.) + * + * SOME = nr_delayed_tasks != 0 + * FULL = nr_delayed_tasks != 0 && nr_running_tasks == 0 + * + * The percentage of wallclock time spent in those compound stall + * states gives pressure numbers between 0 and 100 for each resource, + * where the SOME percentage indicates workload slowdowns and the FULL + * percentage indicates reduced CPU utilization: + * + * %SOME = time(SOME) / period + * %FULL = time(FULL) / period + * + * Multiple CPUs + * + * The more tasks and available CPUs there are, the more work can be + * performed concurrently. This means that the potential that can go + * unrealized due to resource contention *also* scales with non-idle + * tasks and CPUs. + * + * Consider a scenario where 257 number crunching tasks are trying to + * run concurrently on 256 CPUs. If we simply aggregated the task + * states, we would have to conclude a CPU SOME pressure number of + * 100%, since *somebody* is waiting on a runqueue at all + * times. However, that is clearly not the amount of contention the + * workload is experiencing: only one out of 256 possible exceution + * threads will be contended at any given time, or about 0.4%. + * + * Conversely, consider a scenario of 4 tasks and 4 CPUs where at any + * given time *one* of the tasks is delayed due to a lack of memory. + * Again, looking purely at the task state would yield a memory FULL + * pressure number of 0%, since *somebody* is always making forward + * progress. But again this wouldn't capture the amount of execution + * potential lost, which is 1 out of 4 CPUs, or 25%. + * + * To calculate wasted potential (pressure) with multiple processors, + * we have to base our calculation on the number of non-idle tasks in + * conjunction with the number of available CPUs, which is the number + * of potential execution threads. SOME becomes then the proportion of + * delayed tasks to possibe threads, and FULL is the share of possible + * threads that are unproductive due to delays: + * + * threads = min(nr_nonidle_tasks, nr_cpus) + * SOME = min(nr_delayed_tasks / threads, 1) + * FULL = (threads - min(nr_running_tasks, threads)) / threads + * + * For the 257 number crunchers on 256 CPUs, this yields: + * + * threads = min(257, 256) + * SOME = min(1 / 256, 1) = 0.4% + * FULL = (256 - min(257, 256)) / 256 = 0% + * + * For the 1 out of 4 memory-delayed tasks, this yields: + * + * threads = min(4, 4) + * SOME = min(1 / 4, 1) = 25% + * FULL = (4 - min(3, 4)) / 4 = 25% + * + * [ Substitute nr_cpus with 1, and you can see that it's a natural + * extension of the single-CPU model. ] + * + * Implementation + * + * To assess the precise time spent in each such state, we would have + * to freeze the system on task changes and start/stop the state + * clocks accordingly. Obviously that doesn't scale in practice. + * + * Because the scheduler aims to distribute the compute load evenly + * among the available CPUs, we can track task state locally to each + * CPU and, at much lower frequency, extrapolate the global state for + * the cumulative stall times and the running averages. + * + * For each runqueue, we track: + * + * tSOME[cpu] = time(nr_delayed_tasks[cpu] != 0) + * tFULL[cpu] = time(nr_delayed_tasks[cpu] && !nr_running_tasks[cpu]) + * tNONIDLE[cpu] = time(nr_nonidle_tasks[cpu] != 0) + * + * and then periodically aggregate: + * + * tNONIDLE = sum(tNONIDLE[i]) + * + * tSOME = sum(tSOME[i] * tNONIDLE[i]) / tNONIDLE + * tFULL = sum(tFULL[i] * tNONIDLE[i]) / tNONIDLE + * + * %SOME = tSOME / period + * %FULL = tFULL / period + * + * This gives us an approximation of pressure that is practical + * cost-wise, yet way more sensitive and accurate than periodic + * sampling of the aggregate task states would be. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include "sched.h" + +static int psi_bug __read_mostly; + +bool psi_disabled __read_mostly; +core_param(psi_disabled, psi_disabled, bool, 0644); + +/* Running averages - we need to be higher-res than loadavg */ +#define PSI_FREQ (2*HZ+1) /* 2 sec intervals */ +#define EXP_10s 1677 /* 1/exp(2s/10s) as fixed-point */ +#define EXP_60s 1981 /* 1/exp(2s/60s) */ +#define EXP_300s 2034 /* 1/exp(2s/300s) */ + +/* Sampling frequency in nanoseconds */ +static u64 psi_period __read_mostly; + +/* System-level pressure and stall tracking */ +static DEFINE_PER_CPU(struct psi_group_cpu, system_group_pcpu); +static struct psi_group psi_system = { + .pcpu = &system_group_pcpu, +}; + +static void psi_update_work(struct work_struct *work); + +static void group_init(struct psi_group *group) +{ + int cpu; + + for_each_possible_cpu(cpu) + seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq); + group->next_update = sched_clock() + psi_period; + INIT_DELAYED_WORK(&group->clock_work, psi_update_work); + mutex_init(&group->stat_lock); +} + +void __init psi_init(void) +{ + if (psi_disabled) + return; + + psi_period = jiffies_to_nsecs(PSI_FREQ); + group_init(&psi_system); +} + +static bool test_state(unsigned int *tasks, enum psi_states state) +{ + switch (state) { + case PSI_IO_SOME: + return tasks[NR_IOWAIT]; + case PSI_IO_FULL: + return tasks[NR_IOWAIT] && !tasks[NR_RUNNING]; + case PSI_MEM_SOME: + return tasks[NR_MEMSTALL]; + case PSI_MEM_FULL: + return tasks[NR_MEMSTALL] && !tasks[NR_RUNNING]; + case PSI_CPU_SOME: + return tasks[NR_RUNNING] > 1; + case PSI_NONIDLE: + return tasks[NR_IOWAIT] || tasks[NR_MEMSTALL] || + tasks[NR_RUNNING]; + default: + return false; + } +} + +static void get_recent_times(struct psi_group *group, int cpu, u32 *times) +{ + struct psi_group_cpu *groupc = per_cpu_ptr(group->pcpu, cpu); + unsigned int tasks[NR_PSI_TASK_COUNTS]; + u64 now, state_start; + unsigned int seq; + int s; + + /* Snapshot a coherent view of the CPU state */ + do { + seq = read_seqcount_begin(&groupc->seq); + now = cpu_clock(cpu); + memcpy(times, groupc->times, sizeof(groupc->times)); + memcpy(tasks, groupc->tasks, sizeof(groupc->tasks)); + state_start = groupc->state_start; + } while (read_seqcount_retry(&groupc->seq, seq)); + + /* Calculate state time deltas against the previous snapshot */ + for (s = 0; s < NR_PSI_STATES; s++) { + u32 delta; + /* + * In addition to already concluded states, we also + * incorporate currently active states on the CPU, + * since states may last for many sampling periods. + * + * This way we keep our delta sampling buckets small + * (u32) and our reported pressure close to what's + * actually happening. + */ + if (test_state(tasks, s)) + times[s] += now - state_start; + + delta = times[s] - groupc->times_prev[s]; + groupc->times_prev[s] = times[s]; + + times[s] = delta; + } +} + +static void calc_avgs(unsigned long avg[3], int missed_periods, + u64 time, u64 period) +{ + unsigned long pct; + + /* Fill in zeroes for periods of no activity */ + if (missed_periods) { + avg[0] = calc_load_n(avg[0], EXP_10s, 0, missed_periods); + avg[1] = calc_load_n(avg[1], EXP_60s, 0, missed_periods); + avg[2] = calc_load_n(avg[2], EXP_300s, 0, missed_periods); + } + + /* Sample the most recent active period */ + pct = div_u64(time * 100, period); + pct *= FIXED_1; + avg[0] = calc_load(avg[0], EXP_10s, pct); + avg[1] = calc_load(avg[1], EXP_60s, pct); + avg[2] = calc_load(avg[2], EXP_300s, pct); +} + +static bool update_stats(struct psi_group *group) +{ + u64 deltas[NR_PSI_STATES - 1] = { 0, }; + unsigned long missed_periods = 0; + unsigned long nonidle_total = 0; + u64 now, expires, period; + int cpu; + int s; + + mutex_lock(&group->stat_lock); + + /* + * Collect the per-cpu time buckets and average them into a + * single time sample that is normalized to wallclock time. + * + * For averaging, each CPU is weighted by its non-idle time in + * the sampling period. This eliminates artifacts from uneven + * loading, or even entirely idle CPUs. + */ + for_each_possible_cpu(cpu) { + u32 times[NR_PSI_STATES]; + u32 nonidle; + + get_recent_times(group, cpu, times); + + nonidle = nsecs_to_jiffies(times[PSI_NONIDLE]); + nonidle_total += nonidle; + + for (s = 0; s < PSI_NONIDLE; s++) + deltas[s] += (u64)times[s] * nonidle; + } + + /* + * Integrate the sample into the running statistics that are + * reported to userspace: the cumulative stall times and the + * decaying averages. + * + * Pressure percentages are sampled at PSI_FREQ. We might be + * called more often when the user polls more frequently than + * that; we might be called less often when there is no task + * activity, thus no data, and clock ticks are sporadic. The + * below handles both. + */ + + /* total= */ + for (s = 0; s < NR_PSI_STATES - 1; s++) + group->total[s] += div_u64(deltas[s], max(nonidle_total, 1UL)); + + /* avgX= */ + now = sched_clock(); + expires = group->next_update; + if (now < expires) + goto out; + if (now - expires > psi_period) + missed_periods = div_u64(now - expires, psi_period); + + /* + * The periodic clock tick can get delayed for various + * reasons, especially on loaded systems. To avoid clock + * drift, we schedule the clock in fixed psi_period intervals. + * But the deltas we sample out of the per-cpu buckets above + * are based on the actual time elapsing between clock ticks. + */ + group->next_update = expires + ((1 + missed_periods) * psi_period); + period = now - (group->last_update + (missed_periods * psi_period)); + group->last_update = now; + + for (s = 0; s < NR_PSI_STATES - 1; s++) { + u32 sample; + + sample = group->total[s] - group->total_prev[s]; + /* + * Due to the lockless sampling of the time buckets, + * recorded time deltas can slip into the next period, + * which under full pressure can result in samples in + * excess of the period length. + * + * We don't want to report non-sensical pressures in + * excess of 100%, nor do we want to drop such events + * on the floor. Instead we punt any overage into the + * future until pressure subsides. By doing this we + * don't underreport the occurring pressure curve, we + * just report it delayed by one period length. + * + * The error isn't cumulative. As soon as another + * delta slips from a period P to P+1, by definition + * it frees up its time T in P. + */ + if (sample > period) + sample = period; + group->total_prev[s] += sample; + calc_avgs(group->avg[s], missed_periods, sample, period); + } +out: + mutex_unlock(&group->stat_lock); + return nonidle_total; +} + +static void psi_update_work(struct work_struct *work) +{ + struct delayed_work *dwork; + struct psi_group *group; + bool nonidle; + + dwork = to_delayed_work(work); + group = container_of(dwork, struct psi_group, clock_work); + + /* + * If there is task activity, periodically fold the per-cpu + * times and feed samples into the running averages. If things + * are idle and there is no data to process, stop the clock. + * Once restarted, we'll catch up the running averages in one + * go - see calc_avgs() and missed_periods. + */ + + nonidle = update_stats(group); + + if (nonidle) { + unsigned long delay = 0; + u64 now; + + now = sched_clock(); + if (group->next_update > now) + delay = nsecs_to_jiffies(group->next_update - now) + 1; + schedule_delayed_work(dwork, delay); + } +} + +static void record_times(struct psi_group_cpu *groupc, int cpu, + bool memstall_tick) +{ + u32 delta; + u64 now; + + now = cpu_clock(cpu); + delta = now - groupc->state_start; + groupc->state_start = now; + + if (test_state(groupc->tasks, PSI_IO_SOME)) { + groupc->times[PSI_IO_SOME] += delta; + if (test_state(groupc->tasks, PSI_IO_FULL)) + groupc->times[PSI_IO_FULL] += delta; + } + + if (test_state(groupc->tasks, PSI_MEM_SOME)) { + groupc->times[PSI_MEM_SOME] += delta; + if (test_state(groupc->tasks, PSI_MEM_FULL)) + groupc->times[PSI_MEM_FULL] += delta; + else if (memstall_tick) { + u32 sample; + /* + * Since we care about lost potential, a + * memstall is FULL when there are no other + * working tasks, but also when the CPU is + * actively reclaiming and nothing productive + * could run even if it were runnable. + * + * When the timer tick sees a reclaiming CPU, + * regardless of runnable tasks, sample a FULL + * tick (or less if it hasn't been a full tick + * since the last state change). + */ + sample = min(delta, (u32)jiffies_to_nsecs(1)); + groupc->times[PSI_MEM_FULL] += sample; + } + } + + if (test_state(groupc->tasks, PSI_CPU_SOME)) + groupc->times[PSI_CPU_SOME] += delta; + + if (test_state(groupc->tasks, PSI_NONIDLE)) + groupc->times[PSI_NONIDLE] += delta; +} + +static void psi_group_change(struct psi_group *group, int cpu, + unsigned int clear, unsigned int set) +{ + struct psi_group_cpu *groupc; + unsigned int t, m; + + groupc = per_cpu_ptr(group->pcpu, cpu); + + /* + * First we assess the aggregate resource states this CPU's + * tasks have been in since the last change, and account any + * SOME and FULL time these may have resulted in. + * + * Then we update the task counts according to the state + * change requested through the @clear and @set bits. + */ + write_seqcount_begin(&groupc->seq); + + record_times(groupc, cpu, false); + + for (t = 0, m = clear; m; m &= ~(1 << t), t++) { + if (!(m & (1 << t))) + continue; + if (groupc->tasks[t] == 0 && !psi_bug) { + printk_deferred(KERN_ERR "psi: task underflow! cpu=%d t=%d tasks=[%u %u %u] clear=%x set=%x\n", + cpu, t, groupc->tasks[0], + groupc->tasks[1], groupc->tasks[2], + clear, set); + psi_bug = 1; + } + groupc->tasks[t]--; + } + + for (t = 0; set; set &= ~(1 << t), t++) + if (set & (1 << t)) + groupc->tasks[t]++; + + write_seqcount_end(&groupc->seq); + + if (!delayed_work_pending(&group->clock_work)) + schedule_delayed_work(&group->clock_work, PSI_FREQ); +} + +void psi_task_change(struct task_struct *task, int clear, int set) +{ + int cpu = task_cpu(task); + + if (!task->pid) + return; + + if (((task->psi_flags & set) || + (task->psi_flags & clear) != clear) && + !psi_bug) { + printk_deferred(KERN_ERR "psi: inconsistent task state! task=%d:%s cpu=%d psi_flags=%x clear=%x set=%x\n", + task->pid, task->comm, cpu, + task->psi_flags, clear, set); + psi_bug = 1; + } + + task->psi_flags &= ~clear; + task->psi_flags |= set; + + psi_group_change(&psi_system, cpu, clear, set); +} + +void psi_memstall_tick(struct task_struct *task, int cpu) +{ + struct psi_group_cpu *groupc; + + groupc = per_cpu_ptr(psi_system.pcpu, cpu); + write_seqcount_begin(&groupc->seq); + record_times(groupc, cpu, true); + write_seqcount_end(&groupc->seq); +} + +/** + * psi_memstall_enter - mark the beginning of a memory stall section + * @flags: flags to handle nested sections + * + * Marks the calling task as being stalled due to a lack of memory, + * such as waiting for a refault or performing reclaim. + */ +void psi_memstall_enter(unsigned long *flags) +{ + struct rq_flags rf; + struct rq *rq; + + if (psi_disabled) + return; + + *flags = current->flags & PF_MEMSTALL; + if (*flags) + return; + /* + * PF_MEMSTALL setting & accounting needs to be atomic wrt + * changes to the task's scheduling state, otherwise we can + * race with CPU migration. + */ + rq = this_rq_lock_irq(&rf); + + current->flags |= PF_MEMSTALL; + psi_task_change(current, 0, TSK_MEMSTALL); + + rq_unlock_irq(rq, &rf); +} + +/** + * psi_memstall_leave - mark the end of an memory stall section + * @flags: flags to handle nested memdelay sections + * + * Marks the calling task as no longer stalled due to lack of memory. + */ +void psi_memstall_leave(unsigned long *flags) +{ + struct rq_flags rf; + struct rq *rq; + + if (psi_disabled) + return; + + if (*flags) + return; + /* + * PF_MEMSTALL clearing & accounting needs to be atomic wrt + * changes to the task's scheduling state, otherwise we could + * race with CPU migration. + */ + rq = this_rq_lock_irq(&rf); + + current->flags &= ~PF_MEMSTALL; + psi_task_change(current, TSK_MEMSTALL, 0); + + rq_unlock_irq(rq, &rf); +} + +static int psi_show(struct seq_file *m, struct psi_group *group, + enum psi_res res) +{ + int full; + + if (psi_disabled) + return -EOPNOTSUPP; + + update_stats(group); + + for (full = 0; full < 2 - (res == PSI_CPU); full++) { + unsigned long avg[3]; + u64 total; + int w; + + for (w = 0; w < 3; w++) + avg[w] = group->avg[res * 2 + full][w]; + total = div_u64(group->total[res * 2 + full], NSEC_PER_USEC); + + seq_printf(m, "%s avg10=%lu.%02lu avg60=%lu.%02lu avg300=%lu.%02lu total=%llu\n", + full ? "full" : "some", + LOAD_INT(avg[0]), LOAD_FRAC(avg[0]), + LOAD_INT(avg[1]), LOAD_FRAC(avg[1]), + LOAD_INT(avg[2]), LOAD_FRAC(avg[2]), + total); + } + + return 0; +} + +static int psi_io_show(struct seq_file *m, void *v) +{ + return psi_show(m, &psi_system, PSI_IO); +} + +static int psi_memory_show(struct seq_file *m, void *v) +{ + return psi_show(m, &psi_system, PSI_MEM); +} + +static int psi_cpu_show(struct seq_file *m, void *v) +{ + return psi_show(m, &psi_system, PSI_CPU); +} + +static int psi_io_open(struct inode *inode, struct file *file) +{ + return single_open(file, psi_io_show, NULL); +} + +static int psi_memory_open(struct inode *inode, struct file *file) +{ + return single_open(file, psi_memory_show, NULL); +} + +static int psi_cpu_open(struct inode *inode, struct file *file) +{ + return single_open(file, psi_cpu_show, NULL); +} + +static const struct file_operations psi_io_fops = { + .open = psi_io_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static const struct file_operations psi_memory_fops = { + .open = psi_memory_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static const struct file_operations psi_cpu_fops = { + .open = psi_cpu_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init psi_proc_init(void) +{ + proc_mkdir("pressure", NULL); + proc_create("pressure/io", 0, NULL, &psi_io_fops); + proc_create("pressure/memory", 0, NULL, &psi_memory_fops); + proc_create("pressure/cpu", 0, NULL, &psi_cpu_fops); + return 0; +} +module_init(psi_proc_init); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 1de189bb9209..618577fc9aa8 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -54,6 +54,7 @@ #include #include #include +#include #include #include #include @@ -319,6 +320,7 @@ extern bool dl_cpu_busy(unsigned int cpu); #ifdef CONFIG_CGROUP_SCHED #include +#include struct cfs_rq; struct rt_rq; diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index 8aea199a39b4..4904c4677000 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -55,6 +55,92 @@ static inline void rq_sched_info_depart (struct rq *rq, unsigned long long delt # define schedstat_val_or_zero(var) 0 #endif /* CONFIG_SCHEDSTATS */ +#ifdef CONFIG_PSI +/* + * PSI tracks state that persists across sleeps, such as iowaits and + * memory stalls. As a result, it has to distinguish between sleeps, + * where a task's runnable state changes, and requeues, where a task + * and its state are being moved between CPUs and runqueues. + */ +static inline void psi_enqueue(struct task_struct *p, bool wakeup) +{ + int clear = 0, set = TSK_RUNNING; + + if (psi_disabled) + return; + + if (!wakeup || p->sched_psi_wake_requeue) { + if (p->flags & PF_MEMSTALL) + set |= TSK_MEMSTALL; + if (p->sched_psi_wake_requeue) + p->sched_psi_wake_requeue = 0; + } else { + if (p->in_iowait) + clear |= TSK_IOWAIT; + } + + psi_task_change(p, clear, set); +} + +static inline void psi_dequeue(struct task_struct *p, bool sleep) +{ + int clear = TSK_RUNNING, set = 0; + + if (psi_disabled) + return; + + if (!sleep) { + if (p->flags & PF_MEMSTALL) + clear |= TSK_MEMSTALL; + } else { + if (p->in_iowait) + set |= TSK_IOWAIT; + } + + psi_task_change(p, clear, set); +} + +static inline void psi_ttwu_dequeue(struct task_struct *p) +{ + if (psi_disabled) + return; + /* + * Is the task being migrated during a wakeup? Make sure to + * deregister its sleep-persistent psi states from the old + * queue, and let psi_enqueue() know it has to requeue. + */ + if (unlikely(p->in_iowait || (p->flags & PF_MEMSTALL))) { + struct rq_flags rf; + struct rq *rq; + int clear = 0; + + if (p->in_iowait) + clear |= TSK_IOWAIT; + if (p->flags & PF_MEMSTALL) + clear |= TSK_MEMSTALL; + + rq = __task_rq_lock(p, &rf); + psi_task_change(p, clear, 0); + p->sched_psi_wake_requeue = 1; + __task_rq_unlock(rq, &rf); + } +} + +static inline void psi_task_tick(struct rq *rq) +{ + if (psi_disabled) + return; + + if (unlikely(rq->curr->flags & PF_MEMSTALL)) + psi_memstall_tick(rq->curr, cpu_of(rq)); +} +#else /* CONFIG_PSI */ +static inline void psi_enqueue(struct task_struct *p, bool wakeup) {} +static inline void psi_dequeue(struct task_struct *p, bool sleep) {} +static inline void psi_ttwu_dequeue(struct task_struct *p) {} +static inline void psi_task_tick(struct rq *rq) {} +#endif /* CONFIG_PSI */ + #ifdef CONFIG_SCHED_INFO static inline void sched_info_reset_dequeued(struct task_struct *t) { diff --git a/mm/compaction.c b/mm/compaction.c index faca45ebe62d..7c607479de4a 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -22,6 +22,7 @@ #include #include #include +#include #include "internal.h" #ifdef CONFIG_COMPACTION @@ -2068,11 +2069,15 @@ static int kcompactd(void *p) pgdat->kcompactd_classzone_idx = pgdat->nr_zones - 1; while (!kthread_should_stop()) { + unsigned long pflags; + trace_mm_compaction_kcompactd_sleep(pgdat->node_id); wait_event_freezable(pgdat->kcompactd_wait, kcompactd_work_requested(pgdat)); + psi_memstall_enter(&pflags); kcompactd_do_work(pgdat); + psi_memstall_leave(&pflags); } return 0; diff --git a/mm/filemap.c b/mm/filemap.c index 01a841f17bf4..41586009fa42 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -37,6 +37,7 @@ #include #include #include +#include #include "internal.h" #define CREATE_TRACE_POINTS @@ -1075,11 +1076,14 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q, struct wait_page_queue wait_page; wait_queue_entry_t *wait = &wait_page.wait; bool thrashing = false; + unsigned long pflags; int ret = 0; - if (bit_nr == PG_locked && !PageSwapBacked(page) && + if (bit_nr == PG_locked && !PageUptodate(page) && PageWorkingset(page)) { - delayacct_thrashing_start(); + if (!PageSwapBacked(page)) + delayacct_thrashing_start(); + psi_memstall_enter(&pflags); thrashing = true; } @@ -1121,8 +1125,11 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q, finish_wait(q, wait); - if (thrashing) - delayacct_thrashing_end(); + if (thrashing) { + if (!PageSwapBacked(page)) + delayacct_thrashing_end(); + psi_memstall_leave(&pflags); + } /* * A signal could leave PageWaiters set. Clearing it here if diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 20f25d06c00c..f97b5a1700a4 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -66,6 +66,7 @@ #include #include #include +#include #include #include @@ -3549,15 +3550,20 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, enum compact_priority prio, enum compact_result *compact_result) { struct page *page; + unsigned long pflags; unsigned int noreclaim_flag; if (!order) return NULL; + psi_memstall_enter(&pflags); noreclaim_flag = memalloc_noreclaim_save(); + *compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac, prio); + memalloc_noreclaim_restore(noreclaim_flag); + psi_memstall_leave(&pflags); if (*compact_result <= COMPACT_INACTIVE) return NULL; @@ -3756,11 +3762,13 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order, struct reclaim_state reclaim_state; int progress; unsigned int noreclaim_flag; + unsigned long pflags; cond_resched(); /* We now go into synchronous reclaim */ cpuset_memory_pressure_bump(); + psi_memstall_enter(&pflags); fs_reclaim_acquire(gfp_mask); noreclaim_flag = memalloc_noreclaim_save(); reclaim_state.reclaimed_slab = 0; @@ -3772,6 +3780,7 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order, current->reclaim_state = NULL; memalloc_noreclaim_restore(noreclaim_flag); fs_reclaim_release(gfp_mask); + psi_memstall_leave(&pflags); cond_resched(); diff --git a/mm/vmscan.c b/mm/vmscan.c index 87e9fef341d2..8ea87586925e 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -49,6 +49,7 @@ #include #include #include +#include #include #include @@ -3305,6 +3306,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, { struct zonelist *zonelist; unsigned long nr_reclaimed; + unsigned long pflags; int nid; unsigned int noreclaim_flag; struct scan_control sc = { @@ -3333,9 +3335,13 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, sc.gfp_mask, sc.reclaim_idx); + psi_memstall_enter(&pflags); noreclaim_flag = memalloc_noreclaim_save(); + nr_reclaimed = do_try_to_free_pages(zonelist, &sc); + memalloc_noreclaim_restore(noreclaim_flag); + psi_memstall_leave(&pflags); trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed); @@ -3500,6 +3506,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) int i; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; + unsigned long pflags; struct zone *zone; struct scan_control sc = { .gfp_mask = GFP_KERNEL, @@ -3510,6 +3517,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) .may_swap = 1, }; + psi_memstall_enter(&pflags); __fs_reclaim_acquire(); count_vm_event(PAGEOUTRUN); @@ -3611,6 +3619,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) out: snapshot_refaults(NULL, pgdat); __fs_reclaim_release(); + psi_memstall_leave(&pflags); /* * Return the order kswapd stopped reclaiming at as * prepare_kswapd_sleep() takes it into account. If another caller -- cgit v1.2.3 From 2ce7135adc9ad081aa3c49744144376ac74fea60 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:31 -0700 Subject: psi: cgroup support On a system that executes multiple cgrouped jobs and independent workloads, we don't just care about the health of the overall system, but also that of individual jobs, so that we can ensure individual job health, fairness between jobs, or prioritize some jobs over others. This patch implements pressure stall tracking for cgroups. In kernels with CONFIG_PSI=y, cgroup2 groups will have cpu.pressure, memory.pressure, and io.pressure files that track aggregate pressure stall times for only the tasks inside the cgroup. Link: http://lkml.kernel.org/r/20180828172258.3185-10-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Tejun Heo Acked-by: Peter Zijlstra (Intel) Tested-by: Daniel Drake Tested-by: Suren Baghdasaryan Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/accounting/psi.txt | 9 +++ Documentation/admin-guide/cgroup-v2.rst | 18 +++++ include/linux/cgroup-defs.h | 4 ++ include/linux/cgroup.h | 15 ++++ include/linux/psi.h | 25 +++++++ init/Kconfig | 4 ++ kernel/cgroup/cgroup.c | 45 +++++++++++- kernel/sched/psi.c | 118 +++++++++++++++++++++++++++++--- 8 files changed, 228 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/Documentation/accounting/psi.txt b/Documentation/accounting/psi.txt index 3753a82f1cf5..b8ca28b60215 100644 --- a/Documentation/accounting/psi.txt +++ b/Documentation/accounting/psi.txt @@ -62,3 +62,12 @@ well as medium and long term trends. The total absolute stall time is tracked and exported as well, to allow detection of latency spikes which wouldn't necessarily make a dent in the time averages, or to average trends over custom time frames. + +Cgroup2 interface +================= + +In a system with a CONFIG_CGROUP=y kernel and the cgroup2 filesystem +mounted, pressure stall information is also tracked for tasks grouped +into cgroups. Each subdirectory in the cgroupfs mountpoint contains +cpu.pressure, memory.pressure, and io.pressure files; the format is +the same as the /proc/pressure/ files. diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index caf36105a1c7..8389d6f72a77 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -966,6 +966,12 @@ All time durations are in microseconds. $PERIOD duration. "max" for $MAX indicates no limit. If only one number is written, $MAX is updated. + cpu.pressure + A read-only nested-key file which exists on non-root cgroups. + + Shows pressure stall information for CPU. See + Documentation/accounting/psi.txt for details. + Memory ------ @@ -1271,6 +1277,12 @@ PAGE_SIZE multiple when read back. higher than the limit for an extended period of time. This reduces the impact on the workload and memory management. + memory.pressure + A read-only nested-key file which exists on non-root cgroups. + + Shows pressure stall information for memory. See + Documentation/accounting/psi.txt for details. + Usage Guidelines ~~~~~~~~~~~~~~~~ @@ -1408,6 +1420,12 @@ IO Interface Files 8:16 rbps=2097152 wbps=max riops=max wiops=max + io.pressure + A read-only nested-key file which exists on non-root cgroups. + + Shows pressure stall information for IO. See + Documentation/accounting/psi.txt for details. + Writeback ~~~~~~~~~ diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 22254c1fe1c5..5e1694fe035b 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -20,6 +20,7 @@ #include #include #include +#include #ifdef CONFIG_CGROUPS @@ -436,6 +437,9 @@ struct cgroup { /* used to schedule release agent */ struct work_struct release_agent_work; + /* used to track pressure stalls */ + struct psi_group psi; + /* used to store eBPF programs */ struct cgroup_bpf bpf; diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b622d6608605..9968332cceed 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -650,6 +650,11 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp) pr_cont_kernfs_path(cgrp->kn); } +static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) +{ + return &cgrp->psi; +} + static inline void cgroup_init_kthreadd(void) { /* @@ -703,6 +708,16 @@ static inline union kernfs_node_id *cgroup_get_kernfs_id(struct cgroup *cgrp) return NULL; } +static inline struct cgroup *cgroup_parent(struct cgroup *cgrp) +{ + return NULL; +} + +static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) +{ + return NULL; +} + static inline bool task_under_cgroup_hierarchy(struct task_struct *task, struct cgroup *ancestor) { diff --git a/include/linux/psi.h b/include/linux/psi.h index b0daf050de58..8e0725aac0aa 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -4,6 +4,9 @@ #include #include +struct seq_file; +struct css_set; + #ifdef CONFIG_PSI extern bool psi_disabled; @@ -16,6 +19,14 @@ void psi_memstall_tick(struct task_struct *task, int cpu); void psi_memstall_enter(unsigned long *flags); void psi_memstall_leave(unsigned long *flags); +int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res); + +#ifdef CONFIG_CGROUPS +int psi_cgroup_alloc(struct cgroup *cgrp); +void psi_cgroup_free(struct cgroup *cgrp); +void cgroup_move_task(struct task_struct *p, struct css_set *to); +#endif + #else /* CONFIG_PSI */ static inline void psi_init(void) {} @@ -23,6 +34,20 @@ static inline void psi_init(void) {} static inline void psi_memstall_enter(unsigned long *flags) {} static inline void psi_memstall_leave(unsigned long *flags) {} +#ifdef CONFIG_CGROUPS +static inline int psi_cgroup_alloc(struct cgroup *cgrp) +{ + return 0; +} +static inline void psi_cgroup_free(struct cgroup *cgrp) +{ +} +static inline void cgroup_move_task(struct task_struct *p, struct css_set *to) +{ + rcu_assign_pointer(p->cgroups, to); +} +#endif + #endif /* CONFIG_PSI */ #endif /* _LINUX_PSI_H */ diff --git a/init/Kconfig b/init/Kconfig index 26e639df5517..a4112e95724a 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -501,6 +501,10 @@ config PSI the share of walltime in which some or all tasks in the system are delayed due to contention of the respective resource. + In kernels with cgroup support, cgroups (cgroup2 only) will + have cpu.pressure, memory.pressure, and io.pressure files, + which aggregate pressure stalls for the grouped tasks only. + For more details see Documentation/accounting/psi.txt. Say N if unsure. diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 4c1cf0969a80..8b79318810ad 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -55,6 +55,7 @@ #include #include #include +#include #include #define CREATE_TRACE_POINTS @@ -862,7 +863,7 @@ static void css_set_move_task(struct task_struct *task, */ WARN_ON_ONCE(task->flags & PF_EXITING); - rcu_assign_pointer(task->cgroups, to_cset); + cgroup_move_task(task, to_cset); list_add_tail(&task->cg_list, use_mg_tasks ? &to_cset->mg_tasks : &to_cset->tasks); } @@ -3446,6 +3447,21 @@ static int cpu_stat_show(struct seq_file *seq, void *v) return ret; } +#ifdef CONFIG_PSI +static int cgroup_io_pressure_show(struct seq_file *seq, void *v) +{ + return psi_show(seq, &seq_css(seq)->cgroup->psi, PSI_IO); +} +static int cgroup_memory_pressure_show(struct seq_file *seq, void *v) +{ + return psi_show(seq, &seq_css(seq)->cgroup->psi, PSI_MEM); +} +static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v) +{ + return psi_show(seq, &seq_css(seq)->cgroup->psi, PSI_CPU); +} +#endif + static int cgroup_file_open(struct kernfs_open_file *of) { struct cftype *cft = of->kn->priv; @@ -4576,6 +4592,23 @@ static struct cftype cgroup_base_files[] = { .flags = CFTYPE_NOT_ON_ROOT, .seq_show = cpu_stat_show, }, +#ifdef CONFIG_PSI + { + .name = "io.pressure", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = cgroup_io_pressure_show, + }, + { + .name = "memory.pressure", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = cgroup_memory_pressure_show, + }, + { + .name = "cpu.pressure", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = cgroup_cpu_pressure_show, + }, +#endif { } /* terminate */ }; @@ -4636,6 +4669,7 @@ static void css_free_rwork_fn(struct work_struct *work) */ cgroup_put(cgroup_parent(cgrp)); kernfs_put(cgrp->kn); + psi_cgroup_free(cgrp); if (cgroup_on_dfl(cgrp)) cgroup_rstat_exit(cgrp); kfree(cgrp); @@ -4892,10 +4926,15 @@ static struct cgroup *cgroup_create(struct cgroup *parent) cgrp->self.parent = &parent->self; cgrp->root = root; cgrp->level = level; - ret = cgroup_bpf_inherit(cgrp); + + ret = psi_cgroup_alloc(cgrp); if (ret) goto out_idr_free; + ret = cgroup_bpf_inherit(cgrp); + if (ret) + goto out_psi_free; + for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) { cgrp->ancestor_ids[tcgrp->level] = tcgrp->id; @@ -4933,6 +4972,8 @@ static struct cgroup *cgroup_create(struct cgroup *parent) return cgrp; +out_psi_free: + psi_cgroup_free(cgrp); out_idr_free: cgroup_idr_remove(&root->cgroup_idr, cgrp->id); out_stat_exit: diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 595414599b98..7cdecfc010af 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -473,9 +473,35 @@ static void psi_group_change(struct psi_group *group, int cpu, schedule_delayed_work(&group->clock_work, PSI_FREQ); } +static struct psi_group *iterate_groups(struct task_struct *task, void **iter) +{ +#ifdef CONFIG_CGROUPS + struct cgroup *cgroup = NULL; + + if (!*iter) + cgroup = task->cgroups->dfl_cgrp; + else if (*iter == &psi_system) + return NULL; + else + cgroup = cgroup_parent(*iter); + + if (cgroup && cgroup_parent(cgroup)) { + *iter = cgroup; + return cgroup_psi(cgroup); + } +#else + if (*iter) + return NULL; +#endif + *iter = &psi_system; + return &psi_system; +} + void psi_task_change(struct task_struct *task, int clear, int set) { int cpu = task_cpu(task); + struct psi_group *group; + void *iter = NULL; if (!task->pid) return; @@ -492,17 +518,23 @@ void psi_task_change(struct task_struct *task, int clear, int set) task->psi_flags &= ~clear; task->psi_flags |= set; - psi_group_change(&psi_system, cpu, clear, set); + while ((group = iterate_groups(task, &iter))) + psi_group_change(group, cpu, clear, set); } void psi_memstall_tick(struct task_struct *task, int cpu) { - struct psi_group_cpu *groupc; + struct psi_group *group; + void *iter = NULL; - groupc = per_cpu_ptr(psi_system.pcpu, cpu); - write_seqcount_begin(&groupc->seq); - record_times(groupc, cpu, true); - write_seqcount_end(&groupc->seq); + while ((group = iterate_groups(task, &iter))) { + struct psi_group_cpu *groupc; + + groupc = per_cpu_ptr(group->pcpu, cpu); + write_seqcount_begin(&groupc->seq); + record_times(groupc, cpu, true); + write_seqcount_end(&groupc->seq); + } } /** @@ -565,8 +597,78 @@ void psi_memstall_leave(unsigned long *flags) rq_unlock_irq(rq, &rf); } -static int psi_show(struct seq_file *m, struct psi_group *group, - enum psi_res res) +#ifdef CONFIG_CGROUPS +int psi_cgroup_alloc(struct cgroup *cgroup) +{ + if (psi_disabled) + return 0; + + cgroup->psi.pcpu = alloc_percpu(struct psi_group_cpu); + if (!cgroup->psi.pcpu) + return -ENOMEM; + group_init(&cgroup->psi); + return 0; +} + +void psi_cgroup_free(struct cgroup *cgroup) +{ + if (psi_disabled) + return; + + cancel_delayed_work_sync(&cgroup->psi.clock_work); + free_percpu(cgroup->psi.pcpu); +} + +/** + * cgroup_move_task - move task to a different cgroup + * @task: the task + * @to: the target css_set + * + * Move task to a new cgroup and safely migrate its associated stall + * state between the different groups. + * + * This function acquires the task's rq lock to lock out concurrent + * changes to the task's scheduling state and - in case the task is + * running - concurrent changes to its stall state. + */ +void cgroup_move_task(struct task_struct *task, struct css_set *to) +{ + bool move_psi = !psi_disabled; + unsigned int task_flags = 0; + struct rq_flags rf; + struct rq *rq; + + if (move_psi) { + rq = task_rq_lock(task, &rf); + + if (task_on_rq_queued(task)) + task_flags = TSK_RUNNING; + else if (task->in_iowait) + task_flags = TSK_IOWAIT; + + if (task->flags & PF_MEMSTALL) + task_flags |= TSK_MEMSTALL; + + if (task_flags) + psi_task_change(task, task_flags, 0); + } + + /* + * Lame to do this here, but the scheduler cannot be locked + * from the outside, so we move cgroups from inside sched/. + */ + rcu_assign_pointer(task->cgroups, to); + + if (move_psi) { + if (task_flags) + psi_task_change(task, 0, task_flags); + + task_rq_unlock(rq, task, &rf); + } +} +#endif /* CONFIG_CGROUPS */ + +int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) { int full; -- cgit v1.2.3 From 68d48e6a2df575b935edd420396c3cb8b6aa6ad3 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:39 -0700 Subject: mm: workingset: add vmstat counter for shadow nodes Make it easier to catch bugs in the shadow node shrinker by adding a counter for the shadow nodes in circulation. [akpm@linux-foundation.org: assert that irqs are disabled, for __inc_lruvec_page_state()] [akpm@linux-foundation.org: s/WARN_ON_ONCE/VM_WARN_ON_ONCE/, per Johannes] Link: http://lkml.kernel.org/r/20181009184732.762-4-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Reviewed-by: Andrew Morton Acked-by: Peter Zijlstra (Intel) Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 + mm/vmstat.c | 1 + mm/workingset.c | 14 ++++++++++++-- 3 files changed, 14 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index ba51d5bf7af1..9f0caccd5833 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -161,6 +161,7 @@ enum node_stat_item { NR_SLAB_UNRECLAIMABLE, NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */ NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ + WORKINGSET_NODES, WORKINGSET_REFAULT, WORKINGSET_ACTIVATE, WORKINGSET_RESTORE, diff --git a/mm/vmstat.c b/mm/vmstat.c index d918f6192d15..dab53430f63c 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1143,6 +1143,7 @@ const char * const vmstat_text[] = { "nr_slab_unreclaimable", "nr_isolated_anon", "nr_isolated_file", + "workingset_nodes", "workingset_refault", "workingset_activate", "workingset_restore", diff --git a/mm/workingset.c b/mm/workingset.c index 5a72c9d5e195..7e6ef312cea5 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -377,12 +377,20 @@ void workingset_update_node(struct radix_tree_node *node) * already where they should be. The list_empty() test is safe * as node->private_list is protected by the i_pages lock. */ + VM_WARN_ON_ONCE(!irqs_disabled()); /* For __inc_lruvec_page_state */ + if (node->count && node->count == node->exceptional) { - if (list_empty(&node->private_list)) + if (list_empty(&node->private_list)) { list_lru_add(&shadow_nodes, &node->private_list); + __inc_lruvec_page_state(virt_to_page(node), + WORKINGSET_NODES); + } } else { - if (!list_empty(&node->private_list)) + if (!list_empty(&node->private_list)) { list_lru_del(&shadow_nodes, &node->private_list); + __dec_lruvec_page_state(virt_to_page(node), + WORKINGSET_NODES); + } } } @@ -473,6 +481,8 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, } list_lru_isolate(lru, item); + __dec_lruvec_page_state(virt_to_page(node), WORKINGSET_NODES); + spin_unlock(lru_lock); /* -- cgit v1.2.3 From 85cfb245060e45640fa3447f8b0bad5e8bd3bdaf Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Fri, 26 Oct 2018 15:07:41 -0700 Subject: memcg: remove memcg_kmem_skip_account The flag memcg_kmem_skip_account was added during the era of opt-out kmem accounting. There is no need for such flag in the opt-in world as there aren't any __GFP_ACCOUNT allocations within memcg_create_cache_enqueue(). Link: http://lkml.kernel.org/r/20180919004501.178023-1-shakeelb@google.com Signed-off-by: Shakeel Butt Acked-by: Johannes Weiner Cc: Michal Hocko Cc: Vladimir Davydov Cc: Greg Thelen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 3 --- mm/memcontrol.c | 24 +----------------------- 2 files changed, 1 insertion(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index b8fcc6b3080c..8f8a5418b627 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -724,9 +724,6 @@ struct task_struct { #endif #ifdef CONFIG_MEMCG unsigned in_user_fault:1; -#ifdef CONFIG_MEMCG_KMEM - unsigned memcg_kmem_skip_account:1; -#endif #endif #ifdef CONFIG_COMPAT_BRK unsigned brk_randomized:1; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 0e9ede617b89..645ede7ad1b2 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2460,7 +2460,7 @@ static void memcg_kmem_cache_create_func(struct work_struct *w) /* * Enqueue the creation of a per-memcg kmem_cache. */ -static void __memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg, +static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg, struct kmem_cache *cachep) { struct memcg_kmem_cache_create_work *cw; @@ -2478,25 +2478,6 @@ static void __memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg, queue_work(memcg_kmem_cache_wq, &cw->work); } -static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg, - struct kmem_cache *cachep) -{ - /* - * We need to stop accounting when we kmalloc, because if the - * corresponding kmalloc cache is not yet created, the first allocation - * in __memcg_schedule_kmem_cache_create will recurse. - * - * However, it is better to enclose the whole function. Depending on - * the debugging options enabled, INIT_WORK(), for instance, can - * trigger an allocation. This too, will make us recurse. Because at - * this point we can't allow ourselves back into memcg_kmem_get_cache, - * the safest choice is to do it like this, wrapping the whole function. - */ - current->memcg_kmem_skip_account = 1; - __memcg_schedule_kmem_cache_create(memcg, cachep); - current->memcg_kmem_skip_account = 0; -} - static inline bool memcg_kmem_bypass(void) { if (in_interrupt() || !current->mm || (current->flags & PF_KTHREAD)) @@ -2531,9 +2512,6 @@ struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep) if (memcg_kmem_bypass()) return cachep; - if (current->memcg_kmem_skip_account) - return cachep; - memcg = get_mem_cgroup_from_current(); kmemcg_id = READ_ONCE(memcg->kmemcg_id); if (kmemcg_id < 0) -- cgit v1.2.3 From f682a97a00591def7cefbb5003dc04045028e405 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 26 Oct 2018 15:07:45 -0700 Subject: mm: provide kernel parameter to allow disabling page init poisoning Patch series "Address issues slowing persistent memory initialization", v5. The main thing this patch set achieves is that it allows us to initialize each node worth of persistent memory independently. As a result we reduce page init time by about 2 minutes because instead of taking 30 to 40 seconds per node and going through each node one at a time, we process all 4 nodes in parallel in the case of a 12TB persistent memory setup spread evenly over 4 nodes. This patch (of 3): On systems with a large amount of memory it can take a significant amount of time to initialize all of the page structs with the PAGE_POISON_PATTERN value. I have seen it take over 2 minutes to initialize a system with over 12TB of RAM. In order to work around the issue I had to disable CONFIG_DEBUG_VM and then the boot time returned to something much more reasonable as the arch_add_memory call completed in milliseconds versus seconds. However in doing that I had to disable all of the other VM debugging on the system. In order to work around a kernel that might have CONFIG_DEBUG_VM enabled on a system that has a large amount of memory I have added a new kernel parameter named "vm_debug" that can be set to "-" in order to disable it. Link: http://lkml.kernel.org/r/20180925201921.3576.84239.stgit@localhost.localdomain Reviewed-by: Pavel Tatashin Signed-off-by: Alexander Duyck Cc: Dave Hansen Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/kernel-parameters.txt | 12 +++++++ include/linux/page-flags.h | 8 +++++ mm/debug.c | 46 +++++++++++++++++++++++++ mm/memblock.c | 5 ++- mm/sparse.c | 4 +-- 5 files changed, 69 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 8022d902e770..dcd082576e79 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -4839,6 +4839,18 @@ This is actually a boot loader parameter; the value is passed to the kernel using a special protocol. + vm_debug[=options] [KNL] Available with CONFIG_DEBUG_VM=y. + May slow down system boot speed, especially when + enabled on systems with a large amount of memory. + All options are enabled by default, and this + interface is meant to allow for selectively + enabling or disabling specific virtual memory + debugging features. + + Available options are: + P Enable page structure init time poisoning + - Disable all of the above options + vmalloc=nn[KMG] [KNL,BOOT] Forces the vmalloc area to have an exact size of . This can be used to increase the minimum size (128MB on x86). It can also be used to diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 4d99504f6496..934f91ef3f54 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -163,6 +163,14 @@ static inline int PagePoisoned(const struct page *page) return page->flags == PAGE_POISON_PATTERN; } +#ifdef CONFIG_DEBUG_VM +void page_init_poison(struct page *page, size_t size); +#else +static inline void page_init_poison(struct page *page, size_t size) +{ +} +#endif + /* * Page flags policies wrt compound pages * diff --git a/mm/debug.c b/mm/debug.c index bd10aad8539a..cdacba12e09a 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -13,6 +13,7 @@ #include #include #include +#include #include "internal.h" @@ -175,4 +176,49 @@ void dump_mm(const struct mm_struct *mm) ); } +static bool page_init_poisoning __read_mostly = true; + +static int __init setup_vm_debug(char *str) +{ + bool __page_init_poisoning = true; + + /* + * Calling vm_debug with no arguments is equivalent to requesting + * to enable all debugging options we can control. + */ + if (*str++ != '=' || !*str) + goto out; + + __page_init_poisoning = false; + if (*str == '-') + goto out; + + while (*str) { + switch (tolower(*str)) { + case'p': + __page_init_poisoning = true; + break; + default: + pr_err("vm_debug option '%c' unknown. skipped\n", + *str); + } + + str++; + } +out: + if (page_init_poisoning && !__page_init_poisoning) + pr_warn("Page struct poisoning disabled by kernel command line option 'vm_debug'\n"); + + page_init_poisoning = __page_init_poisoning; + + return 1; +} +__setup("vm_debug", setup_vm_debug); + +void page_init_poison(struct page *page, size_t size) +{ + if (page_init_poisoning) + memset(page, PAGE_POISON_PATTERN, size); +} +EXPORT_SYMBOL_GPL(page_init_poison); #endif /* CONFIG_DEBUG_VM */ diff --git a/mm/memblock.c b/mm/memblock.c index 237944479d25..a85315083b5a 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1444,10 +1444,9 @@ void * __init memblock_virt_alloc_try_nid_raw( ptr = memblock_virt_alloc_internal(size, align, min_addr, max_addr, nid); -#ifdef CONFIG_DEBUG_VM if (ptr && size > 0) - memset(ptr, PAGE_POISON_PATTERN, size); -#endif + page_init_poison(ptr, size); + return ptr; } diff --git a/mm/sparse.c b/mm/sparse.c index 10b07eea9a6e..67ad061f7fb8 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -696,13 +696,11 @@ int __meminit sparse_add_one_section(struct pglist_data *pgdat, goto out; } -#ifdef CONFIG_DEBUG_VM /* * Poison uninitialized struct pages in order to catch invalid flags * combinations. */ - memset(memmap, PAGE_POISON_PATTERN, sizeof(struct page) * PAGES_PER_SECTION); -#endif + page_init_poison(memmap, sizeof(struct page) * PAGES_PER_SECTION); section_mark_present(ms); sparse_init_one_section(ms, section_nr, memmap, usemap); -- cgit v1.2.3 From d483da5bc78b86fe4200d2947f193a745f711713 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 26 Oct 2018 15:07:48 -0700 Subject: mm: create non-atomic version of SetPageReserved for init use It doesn't make much sense to use the atomic SetPageReserved at init time when we are using memset to clear the memory and manipulating the page flags via simple "&=" and "|=" operations in __init_single_page. This patch adds a non-atomic version __SetPageReserved that can be used during page init and shows about a 10% improvement in initialization times on the systems I have available for testing. On those systems I saw initialization times drop from around 35 seconds to around 32 seconds to initialize a 3TB block of persistent memory. I believe the main advantage of this is that it allows for more compiler optimization as the __set_bit operation can be reordered whereas the atomic version cannot. I tried adding a bit of documentation based on f1dd2cd13c4 ("mm, memory_hotplug: do not associate hotadded memory to zones until online"). Ideally the reserved flag should be set earlier since there is a brief window where the page is initialization via __init_single_page and we have not set the PG_Reserved flag. I'm leaving that for a future patch set as that will require a more significant refactor. Link: http://lkml.kernel.org/r/20180925202018.3576.11607.stgit@localhost.localdomain Signed-off-by: Alexander Duyck Reviewed-by: Pavel Tatashin Acked-by: Michal Hocko Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 1 + mm/page_alloc.c | 9 +++++++-- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 934f91ef3f54..50ce1bddaf56 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -303,6 +303,7 @@ PAGEFLAG(Foreign, foreign, PF_NO_COMPOUND); PAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) __CLEARPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) + __SETPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) PAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) __CLEARPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) __SETPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index eb6c50cc8880..cee1abf85d72 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1232,7 +1232,12 @@ void __meminit reserve_bootmem_region(phys_addr_t start, phys_addr_t end) /* Avoid false-positive PageTail() */ INIT_LIST_HEAD(&page->lru); - SetPageReserved(page); + /* + * no need for atomic set_bit because the struct + * page is not visible yet so nobody should + * access it yet. + */ + __SetPageReserved(page); } } } @@ -5508,7 +5513,7 @@ not_early: page = pfn_to_page(pfn); __init_single_page(page, pfn, zone, nid); if (context == MEMMAP_HOTPLUG) - SetPageReserved(page); + __SetPageReserved(page); /* * Mark the block movable so that blocks are reserved for -- cgit v1.2.3 From 966cf44f637e6aeea7e3d01ba004bf8b5beac78f Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 26 Oct 2018 15:07:52 -0700 Subject: mm: defer ZONE_DEVICE page initialization to the point where we init pgmap The ZONE_DEVICE pages were being initialized in two locations. One was with the memory_hotplug lock held and another was outside of that lock. The problem with this is that it was nearly doubling the memory initialization time. Instead of doing this twice, once while holding a global lock and once without, I am opting to defer the initialization to the one outside of the lock. This allows us to avoid serializing the overhead for memory init and we can instead focus on per-node init times. One issue I encountered is that devm_memremap_pages and hmm_devmmem_pages_create were initializing only the pgmap field the same way. One wasn't initializing hmm_data, and the other was initializing it to a poison value. Since this is something that is exposed to the driver in the case of hmm I am opting for a third option and just initializing hmm_data to 0 since this is going to be exposed to unknown third party drivers. [alexander.h.duyck@linux.intel.com: fix reference count for pgmap in devm_memremap_pages] Link: http://lkml.kernel.org/r/20181008233404.1909.37302.stgit@localhost.localdomain Link: http://lkml.kernel.org/r/20180925202053.3576.66039.stgit@localhost.localdomain Signed-off-by: Alexander Duyck Reviewed-by: Pavel Tatashin Tested-by: Dan Williams Cc: Dave Hansen Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ kernel/memremap.c | 25 ++++++--------- mm/hmm.c | 12 ++++--- mm/page_alloc.c | 92 ++++++++++++++++++++++++++++++++++++++++++++++++++++-- 4 files changed, 108 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 737279bb479c..33228a49d7d2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -848,6 +848,8 @@ static inline bool is_zone_device_page(const struct page *page) { return page_zonenum(page) == ZONE_DEVICE; } +extern void memmap_init_zone_device(struct zone *, unsigned long, + unsigned long, struct dev_pagemap *); #else static inline bool is_zone_device_page(const struct page *page) { diff --git a/kernel/memremap.c b/kernel/memremap.c index 5b8600d39931..620fc4d2559a 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -175,10 +175,10 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) struct vmem_altmap *altmap = pgmap->altmap_valid ? &pgmap->altmap : NULL; struct resource *res = &pgmap->res; - unsigned long pfn, pgoff, order; + struct dev_pagemap *conflict_pgmap; pgprot_t pgprot = PAGE_KERNEL; + unsigned long pgoff, order; int error, nid, is_ram; - struct dev_pagemap *conflict_pgmap; align_start = res->start & ~(SECTION_SIZE - 1); align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE) @@ -256,19 +256,14 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) if (error) goto err_add_memory; - for_each_device_pfn(pfn, pgmap) { - struct page *page = pfn_to_page(pfn); - - /* - * ZONE_DEVICE pages union ->lru with a ->pgmap back - * pointer. It is a bug if a ZONE_DEVICE page is ever - * freed or placed on a driver-private list. Seed the - * storage with LIST_POISON* values. - */ - list_del(&page->lru); - page->pgmap = pgmap; - percpu_ref_get(pgmap->ref); - } + /* + * Initialization of the pages has been deferred until now in order + * to allow us to do the work while not holding the hotplug lock. + */ + memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE], + align_start >> PAGE_SHIFT, + align_size >> PAGE_SHIFT, pgmap); + percpu_ref_get_many(pgmap->ref, pfn_end(pgmap) - pfn_first(pgmap)); devm_add_action(dev, devm_memremap_pages_release, pgmap); diff --git a/mm/hmm.c b/mm/hmm.c index c968e49f7a0c..774d684fa2b4 100644 --- a/mm/hmm.c +++ b/mm/hmm.c @@ -1024,7 +1024,6 @@ static int hmm_devmem_pages_create(struct hmm_devmem *devmem) resource_size_t key, align_start, align_size, align_end; struct device *device = devmem->device; int ret, nid, is_ram; - unsigned long pfn; align_start = devmem->resource->start & ~(PA_SECTION_SIZE - 1); align_size = ALIGN(devmem->resource->start + @@ -1109,11 +1108,14 @@ static int hmm_devmem_pages_create(struct hmm_devmem *devmem) align_size >> PAGE_SHIFT, NULL); mem_hotplug_done(); - for (pfn = devmem->pfn_first; pfn < devmem->pfn_last; pfn++) { - struct page *page = pfn_to_page(pfn); + /* + * Initialization of the pages has been deferred until now in order + * to allow us to do the work while not holding the hotplug lock. + */ + memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE], + align_start >> PAGE_SHIFT, + align_size >> PAGE_SHIFT, &devmem->pagemap); - page->pgmap = &devmem->pagemap; - } return 0; error_add_memory: diff --git a/mm/page_alloc.c b/mm/page_alloc.c index cee1abf85d72..d73ff2188d72 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5465,12 +5465,23 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, if (highest_memmap_pfn < end_pfn - 1) highest_memmap_pfn = end_pfn - 1; +#ifdef CONFIG_ZONE_DEVICE /* * Honor reservation requested by the driver for this ZONE_DEVICE - * memory + * memory. We limit the total number of pages to initialize to just + * those that might contain the memory mapping. We will defer the + * ZONE_DEVICE page initialization until after we have released + * the hotplug lock. */ - if (altmap && start_pfn == altmap->base_pfn) - start_pfn += altmap->reserve; + if (zone == ZONE_DEVICE) { + if (!altmap) + return; + + if (start_pfn == altmap->base_pfn) + start_pfn += altmap->reserve; + end_pfn = altmap->base_pfn + vmem_altmap_offset(altmap); + } +#endif for (pfn = start_pfn; pfn < end_pfn; pfn++) { /* @@ -5537,6 +5548,81 @@ not_early: } } +#ifdef CONFIG_ZONE_DEVICE +void __ref memmap_init_zone_device(struct zone *zone, + unsigned long start_pfn, + unsigned long size, + struct dev_pagemap *pgmap) +{ + unsigned long pfn, end_pfn = start_pfn + size; + struct pglist_data *pgdat = zone->zone_pgdat; + unsigned long zone_idx = zone_idx(zone); + unsigned long start = jiffies; + int nid = pgdat->node_id; + + if (WARN_ON_ONCE(!pgmap || !is_dev_zone(zone))) + return; + + /* + * The call to memmap_init_zone should have already taken care + * of the pages reserved for the memmap, so we can just jump to + * the end of that region and start processing the device pages. + */ + if (pgmap->altmap_valid) { + struct vmem_altmap *altmap = &pgmap->altmap; + + start_pfn = altmap->base_pfn + vmem_altmap_offset(altmap); + size = end_pfn - start_pfn; + } + + for (pfn = start_pfn; pfn < end_pfn; pfn++) { + struct page *page = pfn_to_page(pfn); + + __init_single_page(page, pfn, zone_idx, nid); + + /* + * Mark page reserved as it will need to wait for onlining + * phase for it to be fully associated with a zone. + * + * We can use the non-atomic __set_bit operation for setting + * the flag as we are still initializing the pages. + */ + __SetPageReserved(page); + + /* + * ZONE_DEVICE pages union ->lru with a ->pgmap back + * pointer and hmm_data. It is a bug if a ZONE_DEVICE + * page is ever freed or placed on a driver-private list. + */ + page->pgmap = pgmap; + page->hmm_data = 0; + + /* + * Mark the block movable so that blocks are reserved for + * movable at startup. This will force kernel allocations + * to reserve their blocks rather than leaking throughout + * the address space during boot when many long-lived + * kernel allocations are made. + * + * bitmap is created for zone's valid pfn range. but memmap + * can be created for invalid pages (for alignment) + * check here not to call set_pageblock_migratetype() against + * pfn out of zone. + * + * Please note that MEMMAP_HOTPLUG path doesn't clear memmap + * because this is done early in sparse_add_one_section + */ + if (!(pfn & (pageblock_nr_pages - 1))) { + set_pageblock_migratetype(page, MIGRATE_MOVABLE); + cond_resched(); + } + } + + pr_info("%s initialised, %lu pages in %ums\n", dev_name(pgmap->dev), + size, jiffies_to_msecs(jiffies - start)); +} + +#endif static void __meminit zone_init_free_lists(struct zone *zone) { unsigned int order, t; -- cgit v1.2.3 From 85a06835f6f1ba79f0f00838ccd5ad840dd1eafb Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Fri, 26 Oct 2018 15:08:50 -0700 Subject: mm: mremap: downgrade mmap_sem to read when shrinking Other than munmap, mremap might be used to shrink memory mapping too. So, it may hold write mmap_sem for long time when shrinking large mapping, as what commit ("mm: mmap: zap pages with read mmap_sem in munmap") described. The mremap() will not manipulate vmas anymore after __do_munmap() call for the mapping shrink use case, so it is safe to downgrade to read mmap_sem. So, the same optimization, which downgrades mmap_sem to read for zapping pages, is also feasible and reasonable to this case. The period of holding exclusive mmap_sem for shrinking large mapping would be reduced significantly with this optimization. MREMAP_FIXED and MREMAP_MAYMOVE are more complicated to adopt this optimization since they need manipulate vmas after do_munmap(), downgrading mmap_sem may create race window. Simple mapping shrink is the low hanging fruit, and it may cover the most cases of unmap with munmap together. [akpm@linux-foundation.org: tweak comment] [yang.shi@linux.alibaba.com: fix unsigned compare against 0 issue] Link: http://lkml.kernel.org/r/1538687672-17795-2-git-send-email-yang.shi@linux.alibaba.com Link: http://lkml.kernel.org/r/1538067582-60038-1-git-send-email-yang.shi@linux.alibaba.com Signed-off-by: Yang Shi Acked-by: Vlastimil Babka Acked-by: Kirill A. Shutemov Cc: Michal Hocko Cc: Matthew Wilcox Cc: Laurent Dufour Cc: Colin Ian King Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ mm/mmap.c | 4 ++-- mm/mremap.c | 20 ++++++++++++++++---- 3 files changed, 20 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 33228a49d7d2..a023c5ce71fa 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2306,6 +2306,8 @@ extern unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate, struct list_head *uf); +extern int __do_munmap(struct mm_struct *, unsigned long, size_t, + struct list_head *uf, bool downgrade); extern int do_munmap(struct mm_struct *, unsigned long, size_t, struct list_head *uf); diff --git a/mm/mmap.c b/mm/mmap.c index 58e323c92c8e..1bfd12032664 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2687,8 +2687,8 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma, * work. This now handles partial unmappings. * Jeremy Fitzhardinge */ -static int __do_munmap(struct mm_struct *mm, unsigned long start, size_t len, - struct list_head *uf, bool downgrade) +int __do_munmap(struct mm_struct *mm, unsigned long start, size_t len, + struct list_head *uf, bool downgrade) { unsigned long end; struct vm_area_struct *vma, *prev, *last; diff --git a/mm/mremap.c b/mm/mremap.c index a9617e72e6b7..7f9f9180e401 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -521,6 +521,7 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, unsigned long ret = -EINVAL; unsigned long charged = 0; bool locked = false; + bool downgraded = false; struct vm_userfaultfd_ctx uf = NULL_VM_UFFD_CTX; LIST_HEAD(uf_unmap_early); LIST_HEAD(uf_unmap); @@ -557,12 +558,20 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, /* * Always allow a shrinking remap: that just unmaps * the unnecessary pages.. - * do_munmap does all the needed commit accounting + * __do_munmap does all the needed commit accounting, and + * downgrades mmap_sem to read if so directed. */ if (old_len >= new_len) { - ret = do_munmap(mm, addr+new_len, old_len - new_len, &uf_unmap); - if (ret && old_len != new_len) + int retval; + + retval = __do_munmap(mm, addr+new_len, old_len - new_len, + &uf_unmap, true); + if (retval < 0 && old_len != new_len) { + ret = retval; goto out; + /* Returning 1 indicates mmap_sem is downgraded to read. */ + } else if (retval == 1) + downgraded = true; ret = addr; goto out; } @@ -627,7 +636,10 @@ out: vm_unacct_memory(charged); locked = 0; } - up_write(¤t->mm->mmap_sem); + if (downgraded) + up_read(¤t->mm->mmap_sem); + else + up_write(¤t->mm->mmap_sem); if (locked && new_len > old_len) mm_populate(new_addr + old_len, new_len - old_len); userfaultfd_unmap_complete(mm, &uf_unmap_early); -- cgit v1.2.3 From cc4b8c794f476076c9ce19f43eb4d98dc4b5e155 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Fri, 26 Oct 2018 15:08:57 -0700 Subject: mm: dax: add comment for PFN_SPECIAL The comment for PFN_SPECIAL is missed in pfn_t.h. Add comment to get consistent with other pfn flags. Link: http://lkml.kernel.org/r/1538086549-100536-1-git-send-email-yang.shi@linux.alibaba.com Signed-off-by: Yang Shi Suggested-by: Dan Williams Reviewed-by: Dan Williams Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pfn_t.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h index 673546ba7342..7bb77850c65a 100644 --- a/include/linux/pfn_t.h +++ b/include/linux/pfn_t.h @@ -9,6 +9,8 @@ * PFN_SG_LAST - pfn references a page and is the last scatterlist entry * PFN_DEV - pfn is not covered by system memmap by default * PFN_MAP - pfn has a dynamic page mapping established by a device driver + * PFN_SPECIAL - for CONFIG_FS_DAX_LIMITED builds to allow XIP, but not + * get_user_pages */ #define PFN_FLAGS_MASK (((u64) (~PAGE_MASK)) << (BITS_PER_LONG_LONG - PAGE_SHIFT)) #define PFN_SG_CHAIN (1ULL << (BITS_PER_LONG_LONG - 1)) -- cgit v1.2.3 From 1c2d479a119b84feacbe4de782016f1bf1ad16dc Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Fri, 26 Oct 2018 15:09:28 -0700 Subject: mm/memcontrol.c: convert mem_cgroup_id::ref to refcount_t type This will allow to use generic refcount_t interfaces to check counters overflow instead of currently existing VM_BUG_ON(). The only difference after the patch is VM_BUG_ON() may cause BUG(), while refcount_t fires with WARN(). But this seems not to be significant here, since such the problems are usually caught by syzbot with panic-on-warn enabled. Link: http://lkml.kernel.org/r/153910718919.7006.13400779039257185427.stgit@localhost.localdomain Signed-off-by: Kirill Tkhai Reviewed-by: Andrew Morton Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Vladimir Davydov Cc: Andrea Parri Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 2 +- mm/memcontrol.c | 10 ++++------ 2 files changed, 5 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 4399cc3f00e4..7ab2120155a4 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -78,7 +78,7 @@ struct mem_cgroup_reclaim_cookie { struct mem_cgroup_id { int id; - atomic_t ref; + refcount_t ref; }; /* diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 645ede7ad1b2..92d38c88250f 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4299,14 +4299,12 @@ static void mem_cgroup_id_remove(struct mem_cgroup *memcg) static void mem_cgroup_id_get_many(struct mem_cgroup *memcg, unsigned int n) { - VM_BUG_ON(atomic_read(&memcg->id.ref) <= 0); - atomic_add(n, &memcg->id.ref); + refcount_add(n, &memcg->id.ref); } static void mem_cgroup_id_put_many(struct mem_cgroup *memcg, unsigned int n) { - VM_BUG_ON(atomic_read(&memcg->id.ref) < n); - if (atomic_sub_and_test(n, &memcg->id.ref)) { + if (refcount_sub_and_test(n, &memcg->id.ref)) { mem_cgroup_id_remove(memcg); /* Memcg ID pins CSS */ @@ -4523,7 +4521,7 @@ static int mem_cgroup_css_online(struct cgroup_subsys_state *css) } /* Online state pins memcg ID, memcg ID pins CSS */ - atomic_set(&memcg->id.ref, 1); + refcount_set(&memcg->id.ref, 1); css_get(css); return 0; } @@ -6357,7 +6355,7 @@ subsys_initcall(mem_cgroup_init); #ifdef CONFIG_MEMCG_SWAP static struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg) { - while (!atomic_inc_not_zero(&memcg->id.ref)) { + while (!refcount_inc_not_zero(&memcg->id.ref)) { /* * The root cgroup cannot be destroyed, so it's refcount must * always be >= 1. -- cgit v1.2.3 From 907ec5fca3dc38d37737de826f06f25b063aa08e Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Fri, 26 Oct 2018 15:10:15 -0700 Subject: mm: zero remaining unavailable struct pages Patch series "mm: Fix for movable_node boot option", v3. This patch series contains a fix for the movable_node boot option issue which was introduced by commit 124049decbb1 ("x86/e820: put !E820_TYPE_RAM regions into memblock.reserved"). The commit breaks the option because it changed the memory gap range to reserved memblock. So, the node is marked as Normal zone even if the SRAT has Hot pluggable affinity. First and second patch fix the original issue which the commit tried to fix, then revert the commit. This patch (of 3): There is a kernel panic that is triggered when reading /proc/kpageflags on the kernel booted with kernel parameter 'memmap=nn[KMG]!ss[KMG]': BUG: unable to handle kernel paging request at fffffffffffffffe PGD 9b20e067 P4D 9b20e067 PUD 9b210067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 2 PID: 1728 Comm: page-types Not tainted 4.17.0-rc6-mm1-v4.17-rc6-180605-0816-00236-g2dfb086ef02c+ #160 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.11.0-2.fc28 04/01/2014 RIP: 0010:stable_page_flags+0x27/0x3c0 Code: 00 00 00 0f 1f 44 00 00 48 85 ff 0f 84 a0 03 00 00 41 54 55 49 89 fc 53 48 8b 57 08 48 8b 2f 48 8d 42 ff 83 e2 01 48 0f 44 c7 <48> 8b 00 f6 c4 01 0f 84 10 03 00 00 31 db 49 8b 54 24 08 4c 89 e7 RSP: 0018:ffffbbd44111fde0 EFLAGS: 00010202 RAX: fffffffffffffffe RBX: 00007fffffffeff9 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000202 RDI: ffffed1182fff5c0 RBP: ffffffffffffffff R08: 0000000000000001 R09: 0000000000000001 R10: ffffbbd44111fed8 R11: 0000000000000000 R12: ffffed1182fff5c0 R13: 00000000000bffd7 R14: 0000000002fff5c0 R15: ffffbbd44111ff10 FS: 00007efc4335a500(0000) GS:ffff93a5bfc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: fffffffffffffffe CR3: 00000000b2a58000 CR4: 00000000001406e0 Call Trace: kpageflags_read+0xc7/0x120 proc_reg_read+0x3c/0x60 __vfs_read+0x36/0x170 vfs_read+0x89/0x130 ksys_pread64+0x71/0x90 do_syscall_64+0x5b/0x160 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7efc42e75e23 Code: 09 00 ba 9f 01 00 00 e8 ab 81 f4 ff 66 2e 0f 1f 84 00 00 00 00 00 90 83 3d 29 0a 2d 00 00 75 13 49 89 ca b8 11 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 34 c3 48 83 ec 08 e8 db d3 01 00 48 89 04 24 According to kernel bisection, this problem became visible due to commit f7f99100d8d9 which changes how struct pages are initialized. Memblock layout affects the pfn ranges covered by node/zone. Consider that we have a VM with 2 NUMA nodes and each node has 4GB memory, and the default (no memmap= given) memblock layout is like below: MEMBLOCK configuration: memory size = 0x00000001fff75c00 reserved size = 0x000000000300c000 memory.cnt = 0x4 memory[0x0] [0x0000000000001000-0x000000000009efff], 0x000000000009e000 bytes on node 0 flags: 0x0 memory[0x1] [0x0000000000100000-0x00000000bffd6fff], 0x00000000bfed7000 bytes on node 0 flags: 0x0 memory[0x2] [0x0000000100000000-0x000000013fffffff], 0x0000000040000000 bytes on node 0 flags: 0x0 memory[0x3] [0x0000000140000000-0x000000023fffffff], 0x0000000100000000 bytes on node 1 flags: 0x0 ... If you give memmap=1G!4G (so it just covers memory[0x2]), the range [0x100000000-0x13fffffff] is gone: MEMBLOCK configuration: memory size = 0x00000001bff75c00 reserved size = 0x000000000300c000 memory.cnt = 0x3 memory[0x0] [0x0000000000001000-0x000000000009efff], 0x000000000009e000 bytes on node 0 flags: 0x0 memory[0x1] [0x0000000000100000-0x00000000bffd6fff], 0x00000000bfed7000 bytes on node 0 flags: 0x0 memory[0x2] [0x0000000140000000-0x000000023fffffff], 0x0000000100000000 bytes on node 1 flags: 0x0 ... This causes shrinking node 0's pfn range because it is calculated by the address range of memblock.memory. So some of struct pages in the gap range are left uninitialized. We have a function zero_resv_unavail() which does zeroing the struct pages outside memblock.memory, but currently it covers only the reserved unavailable range (i.e. memblock.memory && !memblock.reserved). This patch extends it to cover all unavailable range, which fixes the reported issue. Link: http://lkml.kernel.org/r/20181002143821.5112-2-msys.mizuma@gmail.com Fixes: f7f99100d8d9 ("mm: stop zeroing memory during allocation in vmemmap") Signed-off-by: Naoya Horiguchi Signed-off-by-by: Masayoshi Mizuma Tested-by: Oscar Salvador Tested-by: Masayoshi Mizuma Reviewed-by: Pavel Tatashin Cc: Ingo Molnar Cc: Michal Hocko Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 15 --------------- mm/page_alloc.c | 36 +++++++++++++++++++++++++----------- 2 files changed, 25 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 516920549378..2acdd046df2d 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -265,21 +265,6 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, for_each_mem_range_rev(i, &memblock.memory, &memblock.reserved, \ nid, flags, p_start, p_end, p_nid) -/** - * for_each_resv_unavail_range - iterate through reserved and unavailable memory - * @i: u64 used as loop variable - * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL - * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL - * - * Walks over unavailable but reserved (reserved && !memory) areas of memblock. - * Available as soon as memblock is initialized. - * Note: because this memory does not belong to any physical node, flags and - * nid arguments do not make sense and thus not exported as arguments. - */ -#define for_each_resv_unavail_range(i, p_start, p_end) \ - for_each_mem_range(i, &memblock.reserved, &memblock.memory, \ - NUMA_NO_NODE, MEMBLOCK_NONE, p_start, p_end, NULL) - static inline void memblock_set_region_flags(struct memblock_region *r, enum memblock_flags flags) { diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c26d3152f9ba..6d863c5afa08 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6515,29 +6515,42 @@ void __init free_area_init_node(int nid, unsigned long *zones_size, * struct pages which are reserved in memblock allocator and their fields * may be accessed (for example page_to_pfn() on some configuration accesses * flags). We must explicitly zero those struct pages. + * + * This function also addresses a similar issue where struct pages are left + * uninitialized because the physical address range is not covered by + * memblock.memory or memblock.reserved. That could happen when memblock + * layout is manually configured via memmap=. */ void __init zero_resv_unavail(void) { phys_addr_t start, end; unsigned long pfn; u64 i, pgcnt; + phys_addr_t next = 0; /* - * Loop through ranges that are reserved, but do not have reported - * physical memory backing. + * Loop through unavailable ranges not covered by memblock.memory. */ pgcnt = 0; - for_each_resv_unavail_range(i, &start, &end) { - for (pfn = PFN_DOWN(start); pfn < PFN_UP(end); pfn++) { - if (!pfn_valid(ALIGN_DOWN(pfn, pageblock_nr_pages))) { - pfn = ALIGN_DOWN(pfn, pageblock_nr_pages) - + pageblock_nr_pages - 1; - continue; + for_each_mem_range(i, &memblock.memory, NULL, + NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, NULL) { + if (next < start) { + for (pfn = PFN_DOWN(next); pfn < PFN_UP(start); pfn++) { + if (!pfn_valid(ALIGN_DOWN(pfn, pageblock_nr_pages))) + continue; + mm_zero_struct_page(pfn_to_page(pfn)); + pgcnt++; } - mm_zero_struct_page(pfn_to_page(pfn)); - pgcnt++; } + next = end; } + for (pfn = PFN_DOWN(next); pfn < max_pfn; pfn++) { + if (!pfn_valid(ALIGN_DOWN(pfn, pageblock_nr_pages))) + continue; + mm_zero_struct_page(pfn_to_page(pfn)); + pgcnt++; + } + /* * Struct pages that do not have backing memory. This could be because @@ -6547,7 +6560,8 @@ void __init zero_resv_unavail(void) * this code can be removed. */ if (pgcnt) - pr_info("Reserved but unavailable: %lld pages", pgcnt); + pr_info("Zeroed struct page in unavailable ranges: %lld pages", pgcnt); + } #endif /* CONFIG_HAVE_MEMBLOCK && !CONFIG_FLAT_NODE_MEM_MAP */ -- cgit v1.2.3 From df06b37ffe5a442503b7095b77b0a970df515459 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Fri, 26 Oct 2018 15:10:28 -0700 Subject: mm/gup: cache dev_pagemap while pinning pages Getting pages from ZONE_DEVICE memory needs to check the backing device's live-ness, which is tracked in the device's dev_pagemap metadata. This metadata is stored in a radix tree and looking it up adds measurable software overhead. This patch avoids repeating this relatively costly operation when dev_pagemap is used by caching the last dev_pagemap while getting user pages. The gup_benchmark kernel self test reports this reduces time to get user pages to as low as 1/3 of the previous time. Link: http://lkml.kernel.org/r/20181012173040.15669-1-keith.busch@intel.com Signed-off-by: Keith Busch Reviewed-by: Dan Williams Acked-by: Kirill A. Shutemov Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 8 ++-- include/linux/mm.h | 12 +----- mm/gup.c | 110 ++++++++++++++++++++++++++++-------------------- mm/huge_memory.c | 16 +++---- mm/nommu.c | 6 +-- 5 files changed, 79 insertions(+), 73 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index fdcb45999b26..4663ee96cf59 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -213,9 +213,9 @@ static inline int hpage_nr_pages(struct page *page) } struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, - pmd_t *pmd, int flags); + pmd_t *pmd, int flags, struct dev_pagemap **pgmap); struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, - pud_t *pud, int flags); + pud_t *pud, int flags, struct dev_pagemap **pgmap); extern vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd); @@ -344,13 +344,13 @@ static inline void mm_put_huge_zero_page(struct mm_struct *mm) } static inline struct page *follow_devmap_pmd(struct vm_area_struct *vma, - unsigned long addr, pmd_t *pmd, int flags) + unsigned long addr, pmd_t *pmd, int flags, struct dev_pagemap **pgmap) { return NULL; } static inline struct page *follow_devmap_pud(struct vm_area_struct *vma, - unsigned long addr, pud_t *pud, int flags) + unsigned long addr, pud_t *pud, int flags, struct dev_pagemap **pgmap) { return NULL; } diff --git a/include/linux/mm.h b/include/linux/mm.h index a023c5ce71fa..1e52b8fd1685 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2536,16 +2536,8 @@ static inline vm_fault_t vmf_error(int err) return VM_FAULT_SIGBUS; } -struct page *follow_page_mask(struct vm_area_struct *vma, - unsigned long address, unsigned int foll_flags, - unsigned int *page_mask); - -static inline struct page *follow_page(struct vm_area_struct *vma, - unsigned long address, unsigned int foll_flags) -{ - unsigned int unused_page_mask; - return follow_page_mask(vma, address, foll_flags, &unused_page_mask); -} +struct page *follow_page(struct vm_area_struct *vma, unsigned long address, + unsigned int foll_flags); #define FOLL_WRITE 0x01 /* check pte is writable */ #define FOLL_TOUCH 0x02 /* mark page accessed */ diff --git a/mm/gup.c b/mm/gup.c index 08eb350e0f35..841d7ef53591 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -20,6 +20,11 @@ #include "internal.h" +struct follow_page_context { + struct dev_pagemap *pgmap; + unsigned int page_mask; +}; + static struct page *no_page_table(struct vm_area_struct *vma, unsigned int flags) { @@ -71,10 +76,10 @@ static inline bool can_follow_write_pte(pte_t pte, unsigned int flags) } static struct page *follow_page_pte(struct vm_area_struct *vma, - unsigned long address, pmd_t *pmd, unsigned int flags) + unsigned long address, pmd_t *pmd, unsigned int flags, + struct dev_pagemap **pgmap) { struct mm_struct *mm = vma->vm_mm; - struct dev_pagemap *pgmap = NULL; struct page *page; spinlock_t *ptl; pte_t *ptep, pte; @@ -116,8 +121,8 @@ retry: * Only return device mapping pages in the FOLL_GET case since * they are only valid while holding the pgmap reference. */ - pgmap = get_dev_pagemap(pte_pfn(pte), NULL); - if (pgmap) + *pgmap = get_dev_pagemap(pte_pfn(pte), *pgmap); + if (*pgmap) page = pte_page(pte); else goto no_page; @@ -152,15 +157,8 @@ retry: goto retry; } - if (flags & FOLL_GET) { + if (flags & FOLL_GET) get_page(page); - - /* drop the pgmap reference now that we hold the page */ - if (pgmap) { - put_dev_pagemap(pgmap); - pgmap = NULL; - } - } if (flags & FOLL_TOUCH) { if ((flags & FOLL_WRITE) && !pte_dirty(pte) && !PageDirty(page)) @@ -210,7 +208,8 @@ no_page: static struct page *follow_pmd_mask(struct vm_area_struct *vma, unsigned long address, pud_t *pudp, - unsigned int flags, unsigned int *page_mask) + unsigned int flags, + struct follow_page_context *ctx) { pmd_t *pmd, pmdval; spinlock_t *ptl; @@ -258,13 +257,13 @@ retry: } if (pmd_devmap(pmdval)) { ptl = pmd_lock(mm, pmd); - page = follow_devmap_pmd(vma, address, pmd, flags); + page = follow_devmap_pmd(vma, address, pmd, flags, &ctx->pgmap); spin_unlock(ptl); if (page) return page; } if (likely(!pmd_trans_huge(pmdval))) - return follow_page_pte(vma, address, pmd, flags); + return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); if ((flags & FOLL_NUMA) && pmd_protnone(pmdval)) return no_page_table(vma, flags); @@ -284,7 +283,7 @@ retry_locked: } if (unlikely(!pmd_trans_huge(*pmd))) { spin_unlock(ptl); - return follow_page_pte(vma, address, pmd, flags); + return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); } if (flags & FOLL_SPLIT) { int ret; @@ -307,18 +306,18 @@ retry_locked: } return ret ? ERR_PTR(ret) : - follow_page_pte(vma, address, pmd, flags); + follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); } page = follow_trans_huge_pmd(vma, address, pmd, flags); spin_unlock(ptl); - *page_mask = HPAGE_PMD_NR - 1; + ctx->page_mask = HPAGE_PMD_NR - 1; return page; } - static struct page *follow_pud_mask(struct vm_area_struct *vma, unsigned long address, p4d_t *p4dp, - unsigned int flags, unsigned int *page_mask) + unsigned int flags, + struct follow_page_context *ctx) { pud_t *pud; spinlock_t *ptl; @@ -344,7 +343,7 @@ static struct page *follow_pud_mask(struct vm_area_struct *vma, } if (pud_devmap(*pud)) { ptl = pud_lock(mm, pud); - page = follow_devmap_pud(vma, address, pud, flags); + page = follow_devmap_pud(vma, address, pud, flags, &ctx->pgmap); spin_unlock(ptl); if (page) return page; @@ -352,13 +351,13 @@ static struct page *follow_pud_mask(struct vm_area_struct *vma, if (unlikely(pud_bad(*pud))) return no_page_table(vma, flags); - return follow_pmd_mask(vma, address, pud, flags, page_mask); + return follow_pmd_mask(vma, address, pud, flags, ctx); } - static struct page *follow_p4d_mask(struct vm_area_struct *vma, unsigned long address, pgd_t *pgdp, - unsigned int flags, unsigned int *page_mask) + unsigned int flags, + struct follow_page_context *ctx) { p4d_t *p4d; struct page *page; @@ -378,7 +377,7 @@ static struct page *follow_p4d_mask(struct vm_area_struct *vma, return page; return no_page_table(vma, flags); } - return follow_pud_mask(vma, address, p4d, flags, page_mask); + return follow_pud_mask(vma, address, p4d, flags, ctx); } /** @@ -396,13 +395,13 @@ static struct page *follow_p4d_mask(struct vm_area_struct *vma, */ struct page *follow_page_mask(struct vm_area_struct *vma, unsigned long address, unsigned int flags, - unsigned int *page_mask) + struct follow_page_context *ctx) { pgd_t *pgd; struct page *page; struct mm_struct *mm = vma->vm_mm; - *page_mask = 0; + ctx->page_mask = 0; /* make this handle hugepd */ page = follow_huge_addr(mm, address, flags & FOLL_WRITE); @@ -431,7 +430,19 @@ struct page *follow_page_mask(struct vm_area_struct *vma, return no_page_table(vma, flags); } - return follow_p4d_mask(vma, address, pgd, flags, page_mask); + return follow_p4d_mask(vma, address, pgd, flags, ctx); +} + +struct page *follow_page(struct vm_area_struct *vma, unsigned long address, + unsigned int foll_flags) +{ + struct follow_page_context ctx = { NULL }; + struct page *page; + + page = follow_page_mask(vma, address, foll_flags, &ctx); + if (ctx.pgmap) + put_dev_pagemap(ctx.pgmap); + return page; } static int get_gate_page(struct mm_struct *mm, unsigned long address, @@ -659,9 +670,9 @@ static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas, int *nonblocking) { - long i = 0; - unsigned int page_mask; + long ret = 0, i = 0; struct vm_area_struct *vma = NULL; + struct follow_page_context ctx = { NULL }; if (!nr_pages) return 0; @@ -691,12 +702,14 @@ static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, pages ? &pages[i] : NULL); if (ret) return i ? : ret; - page_mask = 0; + ctx.page_mask = 0; goto next_page; } - if (!vma || check_vma_flags(vma, gup_flags)) - return i ? : -EFAULT; + if (!vma || check_vma_flags(vma, gup_flags)) { + ret = -EFAULT; + goto out; + } if (is_vm_hugetlb_page(vma)) { i = follow_hugetlb_page(mm, vma, pages, vmas, &start, &nr_pages, i, @@ -709,23 +722,26 @@ retry: * If we have a pending SIGKILL, don't keep faulting pages and * potentially allocating memory. */ - if (unlikely(fatal_signal_pending(current))) - return i ? i : -ERESTARTSYS; + if (unlikely(fatal_signal_pending(current))) { + ret = -ERESTARTSYS; + goto out; + } cond_resched(); - page = follow_page_mask(vma, start, foll_flags, &page_mask); + + page = follow_page_mask(vma, start, foll_flags, &ctx); if (!page) { - int ret; ret = faultin_page(tsk, vma, start, &foll_flags, nonblocking); switch (ret) { case 0: goto retry; + case -EBUSY: + ret = 0; + /* FALLTHRU */ case -EFAULT: case -ENOMEM: case -EHWPOISON: - return i ? i : ret; - case -EBUSY: - return i; + goto out; case -ENOENT: goto next_page; } @@ -737,27 +753,31 @@ retry: */ goto next_page; } else if (IS_ERR(page)) { - return i ? i : PTR_ERR(page); + ret = PTR_ERR(page); + goto out; } if (pages) { pages[i] = page; flush_anon_page(vma, page, start); flush_dcache_page(page); - page_mask = 0; + ctx.page_mask = 0; } next_page: if (vmas) { vmas[i] = vma; - page_mask = 0; + ctx.page_mask = 0; } - page_increm = 1 + (~(start >> PAGE_SHIFT) & page_mask); + page_increm = 1 + (~(start >> PAGE_SHIFT) & ctx.page_mask); if (page_increm > nr_pages) page_increm = nr_pages; i += page_increm; start += page_increm * PAGE_SIZE; nr_pages -= page_increm; } while (nr_pages); - return i; +out: + if (ctx.pgmap) + put_dev_pagemap(ctx.pgmap); + return i ? i : ret; } static bool vma_permits_fault(struct vm_area_struct *vma, diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 8ea1b36bd452..25c7d7509cf4 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -852,11 +852,10 @@ static void touch_pmd(struct vm_area_struct *vma, unsigned long addr, } struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, - pmd_t *pmd, int flags) + pmd_t *pmd, int flags, struct dev_pagemap **pgmap) { unsigned long pfn = pmd_pfn(*pmd); struct mm_struct *mm = vma->vm_mm; - struct dev_pagemap *pgmap; struct page *page; assert_spin_locked(pmd_lockptr(mm, pmd)); @@ -886,12 +885,11 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, return ERR_PTR(-EEXIST); pfn += (addr & ~PMD_MASK) >> PAGE_SHIFT; - pgmap = get_dev_pagemap(pfn, NULL); - if (!pgmap) + *pgmap = get_dev_pagemap(pfn, *pgmap); + if (!*pgmap) return ERR_PTR(-EFAULT); page = pfn_to_page(pfn); get_page(page); - put_dev_pagemap(pgmap); return page; } @@ -1000,11 +998,10 @@ static void touch_pud(struct vm_area_struct *vma, unsigned long addr, } struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, - pud_t *pud, int flags) + pud_t *pud, int flags, struct dev_pagemap **pgmap) { unsigned long pfn = pud_pfn(*pud); struct mm_struct *mm = vma->vm_mm; - struct dev_pagemap *pgmap; struct page *page; assert_spin_locked(pud_lockptr(mm, pud)); @@ -1028,12 +1025,11 @@ struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, return ERR_PTR(-EEXIST); pfn += (addr & ~PUD_MASK) >> PAGE_SHIFT; - pgmap = get_dev_pagemap(pfn, NULL); - if (!pgmap) + *pgmap = get_dev_pagemap(pfn, *pgmap); + if (!*pgmap) return ERR_PTR(-EFAULT); page = pfn_to_page(pfn); get_page(page); - put_dev_pagemap(pgmap); return page; } diff --git a/mm/nommu.c b/mm/nommu.c index e4aac33216ae..749276beb109 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1709,11 +1709,9 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, return ret; } -struct page *follow_page_mask(struct vm_area_struct *vma, - unsigned long address, unsigned int flags, - unsigned int *page_mask) +struct page *follow_page(struct vm_area_struct *vma, unsigned long address, + unsigned int foll_flags) { - *page_mask = 0; return NULL; } -- cgit v1.2.3 From bc4ae27d817a4e92071ef67cb6368120cfabe7ec Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Fri, 26 Oct 2018 15:10:51 -0700 Subject: mm: split SWP_FILE into SWP_ACTIVATED and SWP_FS The SWP_FILE flag serves two purposes: to make swap_{read,write}page() go through the filesystem, and to make swapoff() call ->swap_deactivate(). For Btrfs, we want the latter but not the former, so split this flag into two. This makes us always call ->swap_deactivate() if ->swap_activate() succeeded, not just if it didn't add any swap extents itself. This also resolves the issue of the very misleading name of SWP_FILE, which is only used for swap files over NFS. Link: http://lkml.kernel.org/r/6d63d8668c4287a4f6d203d65696e96f80abdfc7.1536704650.git.osandov@fb.com Signed-off-by: Omar Sandoval Reviewed-by: Nikolay Borisov Reviewed-by: Andrew Morton Cc: Johannes Weiner Cc: David Sterba Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 13 +++++++------ mm/page_io.c | 6 +++--- mm/swapfile.c | 13 ++++++++----- 3 files changed, 18 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index b93740d72e78..38195f5c96b1 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -167,13 +167,14 @@ enum { SWP_SOLIDSTATE = (1 << 4), /* blkdev seeks are cheap */ SWP_CONTINUED = (1 << 5), /* swap_map has count continuation */ SWP_BLKDEV = (1 << 6), /* its a block device */ - SWP_FILE = (1 << 7), /* set after swap_activate success */ - SWP_AREA_DISCARD = (1 << 8), /* single-time swap area discards */ - SWP_PAGE_DISCARD = (1 << 9), /* freed swap page-cluster discards */ - SWP_STABLE_WRITES = (1 << 10), /* no overwrite PG_writeback pages */ - SWP_SYNCHRONOUS_IO = (1 << 11), /* synchronous IO is efficient */ + SWP_ACTIVATED = (1 << 7), /* set after swap_activate success */ + SWP_FS = (1 << 8), /* swap file goes through fs */ + SWP_AREA_DISCARD = (1 << 9), /* single-time swap area discards */ + SWP_PAGE_DISCARD = (1 << 10), /* freed swap page-cluster discards */ + SWP_STABLE_WRITES = (1 << 11), /* no overwrite PG_writeback pages */ + SWP_SYNCHRONOUS_IO = (1 << 12), /* synchronous IO is efficient */ /* add others here before... */ - SWP_SCANNING = (1 << 12), /* refcount in scan_swap_map */ + SWP_SCANNING = (1 << 13), /* refcount in scan_swap_map */ }; #define SWAP_CLUSTER_MAX 32UL diff --git a/mm/page_io.c b/mm/page_io.c index 573d3663d846..a451ffa9491c 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -283,7 +283,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc, struct swap_info_struct *sis = page_swap_info(page); VM_BUG_ON_PAGE(!PageSwapCache(page), page); - if (sis->flags & SWP_FILE) { + if (sis->flags & SWP_FS) { struct kiocb kiocb; struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; @@ -365,7 +365,7 @@ int swap_readpage(struct page *page, bool synchronous) goto out; } - if (sis->flags & SWP_FILE) { + if (sis->flags & SWP_FS) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; @@ -423,7 +423,7 @@ int swap_set_page_dirty(struct page *page) { struct swap_info_struct *sis = page_swap_info(page); - if (sis->flags & SWP_FILE) { + if (sis->flags & SWP_FS) { struct address_space *mapping = sis->swap_file->f_mapping; VM_BUG_ON_PAGE(!PageSwapCache(page), page); diff --git a/mm/swapfile.c b/mm/swapfile.c index 2681e50592c5..f0c7e4c11bab 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1003,7 +1003,7 @@ start_over: goto nextsi; } if (size == SWAPFILE_CLUSTER) { - if (!(si->flags & SWP_FILE)) + if (!(si->flags & SWP_FS)) n_ret = swap_alloc_cluster(si, swp_entries); } else n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE, @@ -2299,12 +2299,13 @@ static void destroy_swap_extents(struct swap_info_struct *sis) kfree(se); } - if (sis->flags & SWP_FILE) { + if (sis->flags & SWP_ACTIVATED) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; - sis->flags &= ~SWP_FILE; - mapping->a_ops->swap_deactivate(swap_file); + sis->flags &= ~SWP_ACTIVATED; + if (mapping->a_ops->swap_deactivate) + mapping->a_ops->swap_deactivate(swap_file); } } @@ -2400,8 +2401,10 @@ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span) if (mapping->a_ops->swap_activate) { ret = mapping->a_ops->swap_activate(sis, swap_file, span); + if (ret >= 0) + sis->flags |= SWP_ACTIVATED; if (!ret) { - sis->flags |= SWP_FILE; + sis->flags |= SWP_FS; ret = add_swap_extent(sis, 0, sis->max, 0); *span = sis->pages; } -- cgit v1.2.3