From 99b77fef3c6c69bb7664f1ac97a69d5b17968dae Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Wed, 31 Oct 2018 12:20:28 +0200 Subject: net/mlx5: Fix XRC SRQ umem valid bits Adapt XRC SRQ to the latest HW specification with fixed definition around umem valid bits. The previous definition relied on a bit which was taken for other purposes in legacy FW. Fixes: bd37197554eb ("net/mlx5: Update mlx5_ifc with DEVX UID bits") Signed-off-by: Yishai Hadas Reviewed-by: Artemy Kovalyov Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index dbff9ff28f2c..34e17e6f8942 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -2473,14 +2473,15 @@ struct mlx5_ifc_xrc_srqc_bits { u8 wq_signature[0x1]; u8 cont_srq[0x1]; - u8 dbr_umem_valid[0x1]; + u8 reserved_at_22[0x1]; u8 rlky[0x1]; u8 basic_cyclic_rcv_wqe[0x1]; u8 log_rq_stride[0x3]; u8 xrcd[0x18]; u8 page_offset[0x6]; - u8 reserved_at_46[0x2]; + u8 reserved_at_46[0x1]; + u8 dbr_umem_valid[0x1]; u8 cqn[0x18]; u8 reserved_at_60[0x20]; @@ -6689,9 +6690,12 @@ struct mlx5_ifc_create_xrc_srq_in_bits { struct mlx5_ifc_xrc_srqc_bits xrc_srq_context_entry; - u8 reserved_at_280[0x40]; + u8 reserved_at_280[0x60]; + u8 xrc_srq_umem_valid[0x1]; - u8 reserved_at_2c1[0x5bf]; + u8 reserved_at_2e1[0x1f]; + + u8 reserved_at_300[0x580]; u8 pas[0][0x40]; }; -- cgit v1.2.3 From d19f9130b814d33c03118493c17454f7d90075d1 Mon Sep 17 00:00:00 2001 From: Elvira Khabirova Date: Sat, 10 Nov 2018 04:22:09 +0100 Subject: x86/ptrace: Fix documentation for tracehook_report_syscall_entry() tracehook_report_syscall_entry() is called not only if %TIF_SYSCALL_TRACE is set, but also if %TIF_SYSCALL_EMU is set, as appears from x86's entry code. Signed-off-by: Elvira Khabirova Cc: Borislav Petkov Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: ldv@altlinux.org Cc: oleg@redhat.com Cc: rostedt@goodmis.org Link: http://lkml.kernel.org/r/20181110042209.26333972@akathisia Signed-off-by: Ingo Molnar --- include/linux/tracehook.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 40b0b4c1bf7b..df20f8bdbfa3 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -83,8 +83,8 @@ static inline int ptrace_report_syscall(struct pt_regs *regs) * tracehook_report_syscall_entry - task is about to attempt a system call * @regs: user register state of current task * - * This will be called if %TIF_SYSCALL_TRACE has been set, when the - * current task has just entered the kernel for a system call. + * This will be called if %TIF_SYSCALL_TRACE or %TIF_SYSCALL_EMU have been set, + * when the current task has just entered the kernel for a system call. * Full user register state is available here. Changing the values * in @regs can affect the system call number and arguments to be tried. * It is safe to block here, preventing the system call from beginning. -- cgit v1.2.3 From 0145b50566e7de5637e80ecba96c7f0e6fff1aad Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Wed, 31 Oct 2018 15:20:05 +0100 Subject: iio/hid-sensors: Fix IIO_CHAN_INFO_RAW returning wrong values for signed numbers Before this commit sensor_hub_input_attr_get_raw_value() failed to take the signedness of 16 and 8 bit values into account, returning e.g. 65436 instead of -100 for the z-axis reading of an accelerometer. This commit adds a new is_signed parameter to the function and makes all callers pass the appropriate value for this. While at it, this commit also fixes up some neighboring lines where statements were needlessly split over 2 lines to improve readability. Signed-off-by: Hans de Goede Acked-by: Srinivas Pandruvada Acked-by: Benjamin Tissoires Cc: Signed-off-by: Jonathan Cameron --- drivers/hid/hid-sensor-custom.c | 2 +- drivers/hid/hid-sensor-hub.c | 13 ++++++++++--- drivers/iio/accel/hid-sensor-accel-3d.c | 5 ++++- drivers/iio/gyro/hid-sensor-gyro-3d.c | 5 ++++- drivers/iio/humidity/hid-sensor-humidity.c | 3 ++- drivers/iio/light/hid-sensor-als.c | 8 +++++--- drivers/iio/light/hid-sensor-prox.c | 8 +++++--- drivers/iio/magnetometer/hid-sensor-magn-3d.c | 8 +++++--- drivers/iio/orientation/hid-sensor-incl-3d.c | 8 +++++--- drivers/iio/pressure/hid-sensor-press.c | 8 +++++--- drivers/iio/temperature/hid-sensor-temperature.c | 3 ++- drivers/rtc/rtc-hid-sensor-time.c | 2 +- include/linux/hid-sensor-hub.h | 4 +++- 13 files changed, 52 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/drivers/hid/hid-sensor-custom.c b/drivers/hid/hid-sensor-custom.c index e8a114157f87..bb012bc032e0 100644 --- a/drivers/hid/hid-sensor-custom.c +++ b/drivers/hid/hid-sensor-custom.c @@ -358,7 +358,7 @@ static ssize_t show_value(struct device *dev, struct device_attribute *attr, sensor_inst->hsdev, sensor_inst->hsdev->usage, usage, report_id, - SENSOR_HUB_SYNC); + SENSOR_HUB_SYNC, false); } else if (!strncmp(name, "units", strlen("units"))) value = sensor_inst->fields[field_index].attribute.units; else if (!strncmp(name, "unit-expo", strlen("unit-expo"))) diff --git a/drivers/hid/hid-sensor-hub.c b/drivers/hid/hid-sensor-hub.c index 2b63487057c2..4256fdc5cd6d 100644 --- a/drivers/hid/hid-sensor-hub.c +++ b/drivers/hid/hid-sensor-hub.c @@ -299,7 +299,8 @@ EXPORT_SYMBOL_GPL(sensor_hub_get_feature); int sensor_hub_input_attr_get_raw_value(struct hid_sensor_hub_device *hsdev, u32 usage_id, u32 attr_usage_id, u32 report_id, - enum sensor_hub_read_flags flag) + enum sensor_hub_read_flags flag, + bool is_signed) { struct sensor_hub_data *data = hid_get_drvdata(hsdev->hdev); unsigned long flags; @@ -331,10 +332,16 @@ int sensor_hub_input_attr_get_raw_value(struct hid_sensor_hub_device *hsdev, &hsdev->pending.ready, HZ*5); switch (hsdev->pending.raw_size) { case 1: - ret_val = *(u8 *)hsdev->pending.raw_data; + if (is_signed) + ret_val = *(s8 *)hsdev->pending.raw_data; + else + ret_val = *(u8 *)hsdev->pending.raw_data; break; case 2: - ret_val = *(u16 *)hsdev->pending.raw_data; + if (is_signed) + ret_val = *(s16 *)hsdev->pending.raw_data; + else + ret_val = *(u16 *)hsdev->pending.raw_data; break; case 4: ret_val = *(u32 *)hsdev->pending.raw_data; diff --git a/drivers/iio/accel/hid-sensor-accel-3d.c b/drivers/iio/accel/hid-sensor-accel-3d.c index 41d97faf5013..38ff374a3ca4 100644 --- a/drivers/iio/accel/hid-sensor-accel-3d.c +++ b/drivers/iio/accel/hid-sensor-accel-3d.c @@ -149,6 +149,7 @@ static int accel_3d_read_raw(struct iio_dev *indio_dev, int report_id = -1; u32 address; int ret_type; + s32 min; struct hid_sensor_hub_device *hsdev = accel_state->common_attributes.hsdev; @@ -158,12 +159,14 @@ static int accel_3d_read_raw(struct iio_dev *indio_dev, case IIO_CHAN_INFO_RAW: hid_sensor_power_state(&accel_state->common_attributes, true); report_id = accel_state->accel[chan->scan_index].report_id; + min = accel_state->accel[chan->scan_index].logical_minimum; address = accel_3d_addresses[chan->scan_index]; if (report_id >= 0) *val = sensor_hub_input_attr_get_raw_value( accel_state->common_attributes.hsdev, hsdev->usage, address, report_id, - SENSOR_HUB_SYNC); + SENSOR_HUB_SYNC, + min < 0); else { *val = 0; hid_sensor_power_state(&accel_state->common_attributes, diff --git a/drivers/iio/gyro/hid-sensor-gyro-3d.c b/drivers/iio/gyro/hid-sensor-gyro-3d.c index 36941e69f959..88e857c4baf4 100644 --- a/drivers/iio/gyro/hid-sensor-gyro-3d.c +++ b/drivers/iio/gyro/hid-sensor-gyro-3d.c @@ -111,6 +111,7 @@ static int gyro_3d_read_raw(struct iio_dev *indio_dev, int report_id = -1; u32 address; int ret_type; + s32 min; *val = 0; *val2 = 0; @@ -118,13 +119,15 @@ static int gyro_3d_read_raw(struct iio_dev *indio_dev, case IIO_CHAN_INFO_RAW: hid_sensor_power_state(&gyro_state->common_attributes, true); report_id = gyro_state->gyro[chan->scan_index].report_id; + min = gyro_state->gyro[chan->scan_index].logical_minimum; address = gyro_3d_addresses[chan->scan_index]; if (report_id >= 0) *val = sensor_hub_input_attr_get_raw_value( gyro_state->common_attributes.hsdev, HID_USAGE_SENSOR_GYRO_3D, address, report_id, - SENSOR_HUB_SYNC); + SENSOR_HUB_SYNC, + min < 0); else { *val = 0; hid_sensor_power_state(&gyro_state->common_attributes, diff --git a/drivers/iio/humidity/hid-sensor-humidity.c b/drivers/iio/humidity/hid-sensor-humidity.c index beab6d6fd6e1..4bc95f31c730 100644 --- a/drivers/iio/humidity/hid-sensor-humidity.c +++ b/drivers/iio/humidity/hid-sensor-humidity.c @@ -75,7 +75,8 @@ static int humidity_read_raw(struct iio_dev *indio_dev, HID_USAGE_SENSOR_HUMIDITY, HID_USAGE_SENSOR_ATMOSPHERIC_HUMIDITY, humid_st->humidity_attr.report_id, - SENSOR_HUB_SYNC); + SENSOR_HUB_SYNC, + humid_st->humidity_attr.logical_minimum < 0); hid_sensor_power_state(&humid_st->common_attributes, false); return IIO_VAL_INT; diff --git a/drivers/iio/light/hid-sensor-als.c b/drivers/iio/light/hid-sensor-als.c index 406caaee9a3c..94f33250ba5a 100644 --- a/drivers/iio/light/hid-sensor-als.c +++ b/drivers/iio/light/hid-sensor-als.c @@ -93,6 +93,7 @@ static int als_read_raw(struct iio_dev *indio_dev, int report_id = -1; u32 address; int ret_type; + s32 min; *val = 0; *val2 = 0; @@ -102,8 +103,8 @@ static int als_read_raw(struct iio_dev *indio_dev, case CHANNEL_SCAN_INDEX_INTENSITY: case CHANNEL_SCAN_INDEX_ILLUM: report_id = als_state->als_illum.report_id; - address = - HID_USAGE_SENSOR_LIGHT_ILLUM; + min = als_state->als_illum.logical_minimum; + address = HID_USAGE_SENSOR_LIGHT_ILLUM; break; default: report_id = -1; @@ -116,7 +117,8 @@ static int als_read_raw(struct iio_dev *indio_dev, als_state->common_attributes.hsdev, HID_USAGE_SENSOR_ALS, address, report_id, - SENSOR_HUB_SYNC); + SENSOR_HUB_SYNC, + min < 0); hid_sensor_power_state(&als_state->common_attributes, false); } else { diff --git a/drivers/iio/light/hid-sensor-prox.c b/drivers/iio/light/hid-sensor-prox.c index 45107f7537b5..cf5a0c242609 100644 --- a/drivers/iio/light/hid-sensor-prox.c +++ b/drivers/iio/light/hid-sensor-prox.c @@ -73,6 +73,7 @@ static int prox_read_raw(struct iio_dev *indio_dev, int report_id = -1; u32 address; int ret_type; + s32 min; *val = 0; *val2 = 0; @@ -81,8 +82,8 @@ static int prox_read_raw(struct iio_dev *indio_dev, switch (chan->scan_index) { case CHANNEL_SCAN_INDEX_PRESENCE: report_id = prox_state->prox_attr.report_id; - address = - HID_USAGE_SENSOR_HUMAN_PRESENCE; + min = prox_state->prox_attr.logical_minimum; + address = HID_USAGE_SENSOR_HUMAN_PRESENCE; break; default: report_id = -1; @@ -95,7 +96,8 @@ static int prox_read_raw(struct iio_dev *indio_dev, prox_state->common_attributes.hsdev, HID_USAGE_SENSOR_PROX, address, report_id, - SENSOR_HUB_SYNC); + SENSOR_HUB_SYNC, + min < 0); hid_sensor_power_state(&prox_state->common_attributes, false); } else { diff --git a/drivers/iio/magnetometer/hid-sensor-magn-3d.c b/drivers/iio/magnetometer/hid-sensor-magn-3d.c index d55c4885211a..f3c0d41e5a8c 100644 --- a/drivers/iio/magnetometer/hid-sensor-magn-3d.c +++ b/drivers/iio/magnetometer/hid-sensor-magn-3d.c @@ -163,21 +163,23 @@ static int magn_3d_read_raw(struct iio_dev *indio_dev, int report_id = -1; u32 address; int ret_type; + s32 min; *val = 0; *val2 = 0; switch (mask) { case IIO_CHAN_INFO_RAW: hid_sensor_power_state(&magn_state->magn_flux_attributes, true); - report_id = - magn_state->magn[chan->address].report_id; + report_id = magn_state->magn[chan->address].report_id; + min = magn_state->magn[chan->address].logical_minimum; address = magn_3d_addresses[chan->address]; if (report_id >= 0) *val = sensor_hub_input_attr_get_raw_value( magn_state->magn_flux_attributes.hsdev, HID_USAGE_SENSOR_COMPASS_3D, address, report_id, - SENSOR_HUB_SYNC); + SENSOR_HUB_SYNC, + min < 0); else { *val = 0; hid_sensor_power_state( diff --git a/drivers/iio/orientation/hid-sensor-incl-3d.c b/drivers/iio/orientation/hid-sensor-incl-3d.c index 1e5451d1ff88..bdc5e4554ee4 100644 --- a/drivers/iio/orientation/hid-sensor-incl-3d.c +++ b/drivers/iio/orientation/hid-sensor-incl-3d.c @@ -111,21 +111,23 @@ static int incl_3d_read_raw(struct iio_dev *indio_dev, int report_id = -1; u32 address; int ret_type; + s32 min; *val = 0; *val2 = 0; switch (mask) { case IIO_CHAN_INFO_RAW: hid_sensor_power_state(&incl_state->common_attributes, true); - report_id = - incl_state->incl[chan->scan_index].report_id; + report_id = incl_state->incl[chan->scan_index].report_id; + min = incl_state->incl[chan->scan_index].logical_minimum; address = incl_3d_addresses[chan->scan_index]; if (report_id >= 0) *val = sensor_hub_input_attr_get_raw_value( incl_state->common_attributes.hsdev, HID_USAGE_SENSOR_INCLINOMETER_3D, address, report_id, - SENSOR_HUB_SYNC); + SENSOR_HUB_SYNC, + min < 0); else { hid_sensor_power_state(&incl_state->common_attributes, false); diff --git a/drivers/iio/pressure/hid-sensor-press.c b/drivers/iio/pressure/hid-sensor-press.c index 4c437918f1d2..d7b1c00ceb4d 100644 --- a/drivers/iio/pressure/hid-sensor-press.c +++ b/drivers/iio/pressure/hid-sensor-press.c @@ -77,6 +77,7 @@ static int press_read_raw(struct iio_dev *indio_dev, int report_id = -1; u32 address; int ret_type; + s32 min; *val = 0; *val2 = 0; @@ -85,8 +86,8 @@ static int press_read_raw(struct iio_dev *indio_dev, switch (chan->scan_index) { case CHANNEL_SCAN_INDEX_PRESSURE: report_id = press_state->press_attr.report_id; - address = - HID_USAGE_SENSOR_ATMOSPHERIC_PRESSURE; + min = press_state->press_attr.logical_minimum; + address = HID_USAGE_SENSOR_ATMOSPHERIC_PRESSURE; break; default: report_id = -1; @@ -99,7 +100,8 @@ static int press_read_raw(struct iio_dev *indio_dev, press_state->common_attributes.hsdev, HID_USAGE_SENSOR_PRESSURE, address, report_id, - SENSOR_HUB_SYNC); + SENSOR_HUB_SYNC, + min < 0); hid_sensor_power_state(&press_state->common_attributes, false); } else { diff --git a/drivers/iio/temperature/hid-sensor-temperature.c b/drivers/iio/temperature/hid-sensor-temperature.c index beaf6fd3e337..b592fc4f007e 100644 --- a/drivers/iio/temperature/hid-sensor-temperature.c +++ b/drivers/iio/temperature/hid-sensor-temperature.c @@ -76,7 +76,8 @@ static int temperature_read_raw(struct iio_dev *indio_dev, HID_USAGE_SENSOR_TEMPERATURE, HID_USAGE_SENSOR_DATA_ENVIRONMENTAL_TEMPERATURE, temp_st->temperature_attr.report_id, - SENSOR_HUB_SYNC); + SENSOR_HUB_SYNC, + temp_st->temperature_attr.logical_minimum < 0); hid_sensor_power_state( &temp_st->common_attributes, false); diff --git a/drivers/rtc/rtc-hid-sensor-time.c b/drivers/rtc/rtc-hid-sensor-time.c index 2751dba850c6..3e1abb455472 100644 --- a/drivers/rtc/rtc-hid-sensor-time.c +++ b/drivers/rtc/rtc-hid-sensor-time.c @@ -213,7 +213,7 @@ static int hid_rtc_read_time(struct device *dev, struct rtc_time *tm) /* get a report with all values through requesting one value */ sensor_hub_input_attr_get_raw_value(time_state->common_attributes.hsdev, HID_USAGE_SENSOR_TIME, hid_time_addresses[0], - time_state->info[0].report_id, SENSOR_HUB_SYNC); + time_state->info[0].report_id, SENSOR_HUB_SYNC, false); /* wait for all values (event) */ ret = wait_for_completion_killable_timeout( &time_state->comp_last_time, HZ*6); diff --git a/include/linux/hid-sensor-hub.h b/include/linux/hid-sensor-hub.h index 331dc377c275..dc12f5c4b076 100644 --- a/include/linux/hid-sensor-hub.h +++ b/include/linux/hid-sensor-hub.h @@ -177,6 +177,7 @@ int sensor_hub_input_get_attribute_info(struct hid_sensor_hub_device *hsdev, * @attr_usage_id: Attribute usage id as per spec * @report_id: Report id to look for * @flag: Synchronous or asynchronous read +* @is_signed: If true then fields < 32 bits will be sign-extended * * Issues a synchronous or asynchronous read request for an input attribute. * Returns data upto 32 bits. @@ -190,7 +191,8 @@ enum sensor_hub_read_flags { int sensor_hub_input_attr_get_raw_value(struct hid_sensor_hub_device *hsdev, u32 usage_id, u32 attr_usage_id, u32 report_id, - enum sensor_hub_read_flags flag + enum sensor_hub_read_flags flag, + bool is_signed ); /** -- cgit v1.2.3 From 786a9ab1330169f2602238822b4df5d5c4c98f6c Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Wed, 21 Nov 2018 10:35:17 +0100 Subject: gpio: davinci: restore a way to manually specify the GPIO base Commit 587f7a694f01 ("gpio: davinci: Use dev name for label and automatic base selection") broke the network support in legacy boot mode for da850-evm since we can no longer request the MDIO clock GPIO. Other boards may be broken too, which I haven't tested. The problem is in the fact that most board files still use the legacy GPIO API where lines are requested by numbers rather than descriptors. While this should be fixed eventually, in order to unbreak the board for now - provide a way to manually specify the GPIO base in platform data. Fixes: 587f7a694f01 ("gpio: davinci: Use dev name for label and automatic base selection") Cc: stable@vger.kernel.org Signed-off-by: Bartosz Golaszewski Acked-by: Linus Walleij Signed-off-by: Sekhar Nori --- drivers/gpio/gpio-davinci.c | 2 +- include/linux/platform_data/gpio-davinci.h | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/gpio/gpio-davinci.c b/drivers/gpio/gpio-davinci.c index 5c1564fcc24e..bdb29e51b417 100644 --- a/drivers/gpio/gpio-davinci.c +++ b/drivers/gpio/gpio-davinci.c @@ -258,7 +258,7 @@ static int davinci_gpio_probe(struct platform_device *pdev) chips->chip.set = davinci_gpio_set; chips->chip.ngpio = ngpio; - chips->chip.base = -1; + chips->chip.base = pdata->no_auto_base ? pdata->base : -1; #ifdef CONFIG_OF_GPIO chips->chip.of_gpio_n_cells = 2; diff --git a/include/linux/platform_data/gpio-davinci.h b/include/linux/platform_data/gpio-davinci.h index f92a47e18034..a93841bfb9f7 100644 --- a/include/linux/platform_data/gpio-davinci.h +++ b/include/linux/platform_data/gpio-davinci.h @@ -17,6 +17,8 @@ #define __DAVINCI_GPIO_PLATFORM_H struct davinci_gpio_platform_data { + bool no_auto_base; + u32 base; u32 ngpio; u32 gpio_unbanked; }; -- cgit v1.2.3 From 8114865ff82e200b383e46821c25cb0625b842b5 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Sun, 18 Nov 2018 17:10:15 -0500 Subject: function_graph: Create function_graph_enter() to consolidate architecture code Currently all the architectures do basically the same thing in preparing the function graph tracer on entry to a function. This code can be pulled into a generic location and then this will allow the function graph tracer to be fixed, as well as extended. Create a new function graph helper function_graph_enter() that will call the hook function (ftrace_graph_entry) and the shadow stack operation (ftrace_push_return_trace), and remove the need of the architecture code to manage the shadow stack. This is needed to prepare for a fix of a design bug on how the curr_ret_stack is used. Cc: stable@kernel.org Fixes: 03274a3ffb449 ("tracing/fgraph: Adjust fgraph depth before calling trace return callback") Reviewed-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 3 +++ kernel/trace/trace_functions_graph.c | 16 ++++++++++++++++ 2 files changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index a397907e8d72..5717e8f81c59 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -779,6 +779,9 @@ extern void return_to_handler(void); extern int ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, unsigned long frame_pointer, unsigned long *retp); +extern int +function_graph_enter(unsigned long ret, unsigned long func, + unsigned long frame_pointer, unsigned long *retp); unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx, unsigned long ret, unsigned long *retp); diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 169b3c44ee97..28f2602435d0 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -182,6 +182,22 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, return 0; } +int function_graph_enter(unsigned long ret, unsigned long func, + unsigned long frame_pointer, unsigned long *retp) +{ + struct ftrace_graph_ent trace; + + trace.func = func; + trace.depth = current->curr_ret_stack + 1; + + /* Only trace if the calling function expects to */ + if (!ftrace_graph_entry(&trace)) + return -EBUSY; + + return ftrace_push_return_trace(ret, func, &trace.depth, + frame_pointer, retp); +} + /* Retrieve a function return address to the trace stack on thread info.*/ static void ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret, -- cgit v1.2.3 From d125f3f866df88da5a85df00291f88f0baa89f7c Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Mon, 19 Nov 2018 07:40:39 -0500 Subject: function_graph: Make ftrace_push_return_trace() static As all architectures now call function_graph_enter() to do the entry work, no architecture should ever call ftrace_push_return_trace(). Make it static. This is needed to prepare for a fix of a design bug on how the curr_ret_stack is used. Cc: stable@kernel.org Fixes: 03274a3ffb449 ("tracing/fgraph: Adjust fgraph depth before calling trace return callback") Reviewed-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 3 --- kernel/trace/trace_functions_graph.c | 2 +- 2 files changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 5717e8f81c59..dd16e8218db3 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -776,9 +776,6 @@ struct ftrace_ret_stack { */ extern void return_to_handler(void); -extern int -ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, - unsigned long frame_pointer, unsigned long *retp); extern int function_graph_enter(unsigned long ret, unsigned long func, unsigned long frame_pointer, unsigned long *retp); diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 28f2602435d0..88ca787a1cdc 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -118,7 +118,7 @@ print_graph_duration(struct trace_array *tr, unsigned long long duration, struct trace_seq *s, u32 flags); /* Add a function return address to the trace stack on thread info.*/ -int +static int ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, unsigned long frame_pointer, unsigned long *retp) { -- cgit v1.2.3 From 39eb456dacb543de90d3bc6a8e0ac5cf51ac475e Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Mon, 19 Nov 2018 08:07:12 -0500 Subject: function_graph: Use new curr_ret_depth to manage depth instead of curr_ret_stack Currently, the depth of the ret_stack is determined by curr_ret_stack index. The issue is that there's a race between setting of the curr_ret_stack and calling of the callback attached to the return of the function. Commit 03274a3ffb44 ("tracing/fgraph: Adjust fgraph depth before calling trace return callback") moved the calling of the callback to after the setting of the curr_ret_stack, even stating that it was safe to do so, when in fact, it was the reason there was a barrier() there (yes, I should have commented that barrier()). Not only does the curr_ret_stack keep track of the current call graph depth, it also keeps the ret_stack content from being overwritten by new data. The function profiler, uses the "subtime" variable of ret_stack structure and by moving the curr_ret_stack, it allows for interrupts to use the same structure it was using, corrupting the data, and breaking the profiler. To fix this, there needs to be two variables to handle the call stack depth and the pointer to where the ret_stack is being used, as they need to change at two different locations. Cc: stable@kernel.org Fixes: 03274a3ffb449 ("tracing/fgraph: Adjust fgraph depth before calling trace return callback") Reviewed-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/sched.h | 1 + kernel/trace/ftrace.c | 3 +++ kernel/trace/trace_functions_graph.c | 21 +++++++++++++-------- 3 files changed, 17 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index a51c13c2b1a0..d6183a55e8eb 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1116,6 +1116,7 @@ struct task_struct { #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* Index of current stored address in ret_stack: */ int curr_ret_stack; + int curr_ret_depth; /* Stack of return addresses for return function tracing: */ struct ftrace_ret_stack *ret_stack; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index f536f601bd46..48513954713c 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -6814,6 +6814,7 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list) atomic_set(&t->tracing_graph_pause, 0); atomic_set(&t->trace_overrun, 0); t->curr_ret_stack = -1; + t->curr_ret_depth = -1; /* Make sure the tasks see the -1 first: */ smp_wmb(); t->ret_stack = ret_stack_list[start++]; @@ -7038,6 +7039,7 @@ graph_init_task(struct task_struct *t, struct ftrace_ret_stack *ret_stack) void ftrace_graph_init_idle_task(struct task_struct *t, int cpu) { t->curr_ret_stack = -1; + t->curr_ret_depth = -1; /* * The idle task has no parent, it either has its own * stack or no stack at all. @@ -7068,6 +7070,7 @@ void ftrace_graph_init_task(struct task_struct *t) /* Make sure we do not use the parent ret_stack */ t->ret_stack = NULL; t->curr_ret_stack = -1; + t->curr_ret_depth = -1; if (ftrace_graph_active) { struct ftrace_ret_stack *ret_stack; diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 88ca787a1cdc..02d4081a7f5a 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -119,7 +119,7 @@ print_graph_duration(struct trace_array *tr, unsigned long long duration, /* Add a function return address to the trace stack on thread info.*/ static int -ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, +ftrace_push_return_trace(unsigned long ret, unsigned long func, unsigned long frame_pointer, unsigned long *retp) { unsigned long long calltime; @@ -177,8 +177,6 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, #ifdef HAVE_FUNCTION_GRAPH_RET_ADDR_PTR current->ret_stack[index].retp = retp; #endif - *depth = current->curr_ret_stack; - return 0; } @@ -188,14 +186,20 @@ int function_graph_enter(unsigned long ret, unsigned long func, struct ftrace_graph_ent trace; trace.func = func; - trace.depth = current->curr_ret_stack + 1; + trace.depth = ++current->curr_ret_depth; /* Only trace if the calling function expects to */ if (!ftrace_graph_entry(&trace)) - return -EBUSY; + goto out; - return ftrace_push_return_trace(ret, func, &trace.depth, - frame_pointer, retp); + if (ftrace_push_return_trace(ret, func, + frame_pointer, retp)) + goto out; + + return 0; + out: + current->curr_ret_depth--; + return -EBUSY; } /* Retrieve a function return address to the trace stack on thread info.*/ @@ -257,7 +261,7 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret, trace->func = current->ret_stack[index].func; trace->calltime = current->ret_stack[index].calltime; trace->overrun = atomic_read(¤t->trace_overrun); - trace->depth = index; + trace->depth = current->curr_ret_depth; } /* @@ -273,6 +277,7 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer) trace.rettime = trace_clock_local(); barrier(); current->curr_ret_stack--; + current->curr_ret_depth--; /* * The curr_ret_stack can be less than -1 only if it was * filtered out and it's about to return from the function. -- cgit v1.2.3 From 321a874a7ef85655e93b3206d0f36b4a6097f948 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 25 Nov 2018 19:33:38 +0100 Subject: sched/smt: Expose sched_smt_present static key Make the scheduler's 'sched_smt_present' static key globaly available, so it can be used in the x86 speculation control code. Provide a query function and a stub for the CONFIG_SMP=n case. Signed-off-by: Thomas Gleixner Reviewed-by: Ingo Molnar Cc: Peter Zijlstra Cc: Andy Lutomirski Cc: Linus Torvalds Cc: Jiri Kosina Cc: Tom Lendacky Cc: Josh Poimboeuf Cc: Andrea Arcangeli Cc: David Woodhouse Cc: Tim Chen Cc: Andi Kleen Cc: Dave Hansen Cc: Casey Schaufler Cc: Asit Mallick Cc: Arjan van de Ven Cc: Jon Masters Cc: Waiman Long Cc: Greg KH Cc: Dave Stewart Cc: Kees Cook Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20181125185004.430168326@linutronix.de --- include/linux/sched/smt.h | 18 ++++++++++++++++++ kernel/sched/sched.h | 4 +--- 2 files changed, 19 insertions(+), 3 deletions(-) create mode 100644 include/linux/sched/smt.h (limited to 'include/linux') diff --git a/include/linux/sched/smt.h b/include/linux/sched/smt.h new file mode 100644 index 000000000000..c9e0be514110 --- /dev/null +++ b/include/linux/sched/smt.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_SCHED_SMT_H +#define _LINUX_SCHED_SMT_H + +#include + +#ifdef CONFIG_SCHED_SMT +extern struct static_key_false sched_smt_present; + +static __always_inline bool sched_smt_active(void) +{ + return static_branch_likely(&sched_smt_present); +} +#else +static inline bool sched_smt_active(void) { return false; } +#endif + +#endif diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 618577fc9aa8..4e524ab589c9 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -23,6 +23,7 @@ #include #include #include +#include #include #include #include @@ -936,9 +937,6 @@ static inline int cpu_of(struct rq *rq) #ifdef CONFIG_SCHED_SMT - -extern struct static_key_false sched_smt_present; - extern void __update_idle_core(struct rq *rq); static inline void update_idle_core(struct rq *rq) -- cgit v1.2.3 From a74cfffb03b73d41e08f84c2e5c87dec0ce3db9f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 25 Nov 2018 19:33:39 +0100 Subject: x86/speculation: Rework SMT state change arch_smt_update() is only called when the sysfs SMT control knob is changed. This means that when SMT is enabled in the sysfs control knob the system is considered to have SMT active even if all siblings are offline. To allow finegrained control of the speculation mitigations, the actual SMT state is more interesting than the fact that siblings could be enabled. Rework the code, so arch_smt_update() is invoked from each individual CPU hotplug function, and simplify the update function while at it. Signed-off-by: Thomas Gleixner Reviewed-by: Ingo Molnar Cc: Peter Zijlstra Cc: Andy Lutomirski Cc: Linus Torvalds Cc: Jiri Kosina Cc: Tom Lendacky Cc: Josh Poimboeuf Cc: Andrea Arcangeli Cc: David Woodhouse Cc: Tim Chen Cc: Andi Kleen Cc: Dave Hansen Cc: Casey Schaufler Cc: Asit Mallick Cc: Arjan van de Ven Cc: Jon Masters Cc: Waiman Long Cc: Greg KH Cc: Dave Stewart Cc: Kees Cook Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20181125185004.521974984@linutronix.de --- arch/x86/kernel/cpu/bugs.c | 11 +++++------ include/linux/sched/smt.h | 2 ++ kernel/cpu.c | 15 +++++++++------ 3 files changed, 16 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index a723af0c4400..5625b323ff32 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -344,16 +345,14 @@ void arch_smt_update(void) return; mutex_lock(&spec_ctrl_mutex); - mask = x86_spec_ctrl_base; - if (cpu_smt_control == CPU_SMT_ENABLED) + + mask = x86_spec_ctrl_base & ~SPEC_CTRL_STIBP; + if (sched_smt_active()) mask |= SPEC_CTRL_STIBP; - else - mask &= ~SPEC_CTRL_STIBP; if (mask != x86_spec_ctrl_base) { pr_info("Spectre v2 cross-process SMT mitigation: %s STIBP\n", - cpu_smt_control == CPU_SMT_ENABLED ? - "Enabling" : "Disabling"); + mask & SPEC_CTRL_STIBP ? "Enabling" : "Disabling"); x86_spec_ctrl_base = mask; on_each_cpu(update_stibp_msr, NULL, 1); } diff --git a/include/linux/sched/smt.h b/include/linux/sched/smt.h index c9e0be514110..59d3736c454c 100644 --- a/include/linux/sched/smt.h +++ b/include/linux/sched/smt.h @@ -15,4 +15,6 @@ static __always_inline bool sched_smt_active(void) static inline bool sched_smt_active(void) { return false; } #endif +void arch_smt_update(void); + #endif diff --git a/kernel/cpu.c b/kernel/cpu.c index 3c7f3b4c453c..91d5c38eb7e5 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -367,6 +368,12 @@ static void lockdep_release_cpus_lock(void) #endif /* CONFIG_HOTPLUG_CPU */ +/* + * Architectures that need SMT-specific errata handling during SMT hotplug + * should override this. + */ +void __weak arch_smt_update(void) { } + #ifdef CONFIG_HOTPLUG_SMT enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED; EXPORT_SYMBOL_GPL(cpu_smt_control); @@ -1011,6 +1018,7 @@ out: * concurrent CPU hotplug via cpu_add_remove_lock. */ lockup_detector_cleanup(); + arch_smt_update(); return ret; } @@ -1139,6 +1147,7 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) ret = cpuhp_up_callbacks(cpu, st, target); out: cpus_write_unlock(); + arch_smt_update(); return ret; } @@ -2055,12 +2064,6 @@ static void cpuhp_online_cpu_device(unsigned int cpu) kobject_uevent(&dev->kobj, KOBJ_ONLINE); } -/* - * Architectures that need SMT-specific errata handling during SMT hotplug - * should override this. - */ -void __weak arch_smt_update(void) { }; - static int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) { int cpu, ret = 0; -- cgit v1.2.3 From 46f7ecb1e7359f183f5bbd1e08b90e10e52164f9 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 25 Nov 2018 19:33:50 +0100 Subject: ptrace: Remove unused ptrace_may_access_sched() and MODE_IBRS The IBPB control code in x86 removed the usage. Remove the functionality which was introduced for this. Signed-off-by: Thomas Gleixner Reviewed-by: Ingo Molnar Cc: Peter Zijlstra Cc: Andy Lutomirski Cc: Linus Torvalds Cc: Jiri Kosina Cc: Tom Lendacky Cc: Josh Poimboeuf Cc: Andrea Arcangeli Cc: David Woodhouse Cc: Tim Chen Cc: Andi Kleen Cc: Dave Hansen Cc: Casey Schaufler Cc: Asit Mallick Cc: Arjan van de Ven Cc: Jon Masters Cc: Waiman Long Cc: Greg KH Cc: Dave Stewart Cc: Kees Cook Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20181125185005.559149393@linutronix.de --- include/linux/ptrace.h | 17 ----------------- kernel/ptrace.c | 10 ---------- 2 files changed, 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 6c2ffed907f5..de20ede2c5c8 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -64,15 +64,12 @@ extern void exit_ptrace(struct task_struct *tracer, struct list_head *dead); #define PTRACE_MODE_NOAUDIT 0x04 #define PTRACE_MODE_FSCREDS 0x08 #define PTRACE_MODE_REALCREDS 0x10 -#define PTRACE_MODE_SCHED 0x20 -#define PTRACE_MODE_IBPB 0x40 /* shorthands for READ/ATTACH and FSCREDS/REALCREDS combinations */ #define PTRACE_MODE_READ_FSCREDS (PTRACE_MODE_READ | PTRACE_MODE_FSCREDS) #define PTRACE_MODE_READ_REALCREDS (PTRACE_MODE_READ | PTRACE_MODE_REALCREDS) #define PTRACE_MODE_ATTACH_FSCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_FSCREDS) #define PTRACE_MODE_ATTACH_REALCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_REALCREDS) -#define PTRACE_MODE_SPEC_IBPB (PTRACE_MODE_ATTACH_REALCREDS | PTRACE_MODE_IBPB) /** * ptrace_may_access - check whether the caller is permitted to access @@ -90,20 +87,6 @@ extern void exit_ptrace(struct task_struct *tracer, struct list_head *dead); */ extern bool ptrace_may_access(struct task_struct *task, unsigned int mode); -/** - * ptrace_may_access - check whether the caller is permitted to access - * a target task. - * @task: target task - * @mode: selects type of access and caller credentials - * - * Returns true on success, false on denial. - * - * Similar to ptrace_may_access(). Only to be called from context switch - * code. Does not call into audit and the regular LSM hooks due to locking - * constraints. - */ -extern bool ptrace_may_access_sched(struct task_struct *task, unsigned int mode); - static inline int ptrace_reparented(struct task_struct *child) { return !same_thread_group(child->real_parent, child->parent); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 80b34dffdfb9..c2cee9db5204 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -261,9 +261,6 @@ static int ptrace_check_attach(struct task_struct *child, bool ignore_state) static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode) { - if (mode & PTRACE_MODE_SCHED) - return false; - if (mode & PTRACE_MODE_NOAUDIT) return has_ns_capability_noaudit(current, ns, CAP_SYS_PTRACE); else @@ -331,16 +328,9 @@ ok: !ptrace_has_cap(mm->user_ns, mode))) return -EPERM; - if (mode & PTRACE_MODE_SCHED) - return 0; return security_ptrace_access_check(task, mode); } -bool ptrace_may_access_sched(struct task_struct *task, unsigned int mode) -{ - return __ptrace_may_access(task, mode | PTRACE_MODE_SCHED); -} - bool ptrace_may_access(struct task_struct *task, unsigned int mode) { int err; -- cgit v1.2.3 From 9137bb27e60e554dab694eafa4cca241fa3a694f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 25 Nov 2018 19:33:53 +0100 Subject: x86/speculation: Add prctl() control for indirect branch speculation Add the PR_SPEC_INDIRECT_BRANCH option for the PR_GET_SPECULATION_CTRL and PR_SET_SPECULATION_CTRL prctls to allow fine grained per task control of indirect branch speculation via STIBP and IBPB. Invocations: Check indirect branch speculation status with - prctl(PR_GET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, 0, 0, 0); Enable indirect branch speculation with - prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_ENABLE, 0, 0); Disable indirect branch speculation with - prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_DISABLE, 0, 0); Force disable indirect branch speculation with - prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_FORCE_DISABLE, 0, 0); See Documentation/userspace-api/spec_ctrl.rst. Signed-off-by: Tim Chen Signed-off-by: Thomas Gleixner Reviewed-by: Ingo Molnar Cc: Peter Zijlstra Cc: Andy Lutomirski Cc: Linus Torvalds Cc: Jiri Kosina Cc: Tom Lendacky Cc: Josh Poimboeuf Cc: Andrea Arcangeli Cc: David Woodhouse Cc: Andi Kleen Cc: Dave Hansen Cc: Casey Schaufler Cc: Asit Mallick Cc: Arjan van de Ven Cc: Jon Masters Cc: Waiman Long Cc: Greg KH Cc: Dave Stewart Cc: Kees Cook Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20181125185005.866780996@linutronix.de --- Documentation/userspace-api/spec_ctrl.rst | 9 +++++ arch/x86/include/asm/nospec-branch.h | 1 + arch/x86/kernel/cpu/bugs.c | 67 +++++++++++++++++++++++++++++++ arch/x86/kernel/process.c | 5 +++ include/linux/sched.h | 9 +++++ include/uapi/linux/prctl.h | 1 + tools/include/uapi/linux/prctl.h | 1 + 7 files changed, 93 insertions(+) (limited to 'include/linux') diff --git a/Documentation/userspace-api/spec_ctrl.rst b/Documentation/userspace-api/spec_ctrl.rst index 32f3d55c54b7..c4dbe6f7cdae 100644 --- a/Documentation/userspace-api/spec_ctrl.rst +++ b/Documentation/userspace-api/spec_ctrl.rst @@ -92,3 +92,12 @@ Speculation misfeature controls * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_ENABLE, 0, 0); * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_DISABLE, 0, 0); * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_FORCE_DISABLE, 0, 0); + +- PR_SPEC_INDIR_BRANCH: Indirect Branch Speculation in User Processes + (Mitigate Spectre V2 style attacks against user processes) + + Invocations: + * prctl(PR_GET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, 0, 0, 0); + * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_ENABLE, 0, 0); + * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_DISABLE, 0, 0); + * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_FORCE_DISABLE, 0, 0); diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index d4d35baf0430..2adbe7b047fa 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -232,6 +232,7 @@ enum spectre_v2_mitigation { enum spectre_v2_user_mitigation { SPECTRE_V2_USER_NONE, SPECTRE_V2_USER_STRICT, + SPECTRE_V2_USER_PRCTL, }; /* The Speculative Store Bypass disable variants */ diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 9cab538e10f1..74359fff87fd 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -566,6 +566,8 @@ void arch_smt_update(void) case SPECTRE_V2_USER_STRICT: update_stibp_strict(); break; + case SPECTRE_V2_USER_PRCTL: + break; } mutex_unlock(&spec_ctrl_mutex); @@ -752,12 +754,50 @@ static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl) return 0; } +static int ib_prctl_set(struct task_struct *task, unsigned long ctrl) +{ + switch (ctrl) { + case PR_SPEC_ENABLE: + if (spectre_v2_user == SPECTRE_V2_USER_NONE) + return 0; + /* + * Indirect branch speculation is always disabled in strict + * mode. + */ + if (spectre_v2_user == SPECTRE_V2_USER_STRICT) + return -EPERM; + task_clear_spec_ib_disable(task); + task_update_spec_tif(task); + break; + case PR_SPEC_DISABLE: + case PR_SPEC_FORCE_DISABLE: + /* + * Indirect branch speculation is always allowed when + * mitigation is force disabled. + */ + if (spectre_v2_user == SPECTRE_V2_USER_NONE) + return -EPERM; + if (spectre_v2_user == SPECTRE_V2_USER_STRICT) + return 0; + task_set_spec_ib_disable(task); + if (ctrl == PR_SPEC_FORCE_DISABLE) + task_set_spec_ib_force_disable(task); + task_update_spec_tif(task); + break; + default: + return -ERANGE; + } + return 0; +} + int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which, unsigned long ctrl) { switch (which) { case PR_SPEC_STORE_BYPASS: return ssb_prctl_set(task, ctrl); + case PR_SPEC_INDIRECT_BRANCH: + return ib_prctl_set(task, ctrl); default: return -ENODEV; } @@ -790,11 +830,34 @@ static int ssb_prctl_get(struct task_struct *task) } } +static int ib_prctl_get(struct task_struct *task) +{ + if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) + return PR_SPEC_NOT_AFFECTED; + + switch (spectre_v2_user) { + case SPECTRE_V2_USER_NONE: + return PR_SPEC_ENABLE; + case SPECTRE_V2_USER_PRCTL: + if (task_spec_ib_force_disable(task)) + return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE; + if (task_spec_ib_disable(task)) + return PR_SPEC_PRCTL | PR_SPEC_DISABLE; + return PR_SPEC_PRCTL | PR_SPEC_ENABLE; + case SPECTRE_V2_USER_STRICT: + return PR_SPEC_DISABLE; + default: + return PR_SPEC_NOT_AFFECTED; + } +} + int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which) { switch (which) { case PR_SPEC_STORE_BYPASS: return ssb_prctl_get(task); + case PR_SPEC_INDIRECT_BRANCH: + return ib_prctl_get(task); default: return -ENODEV; } @@ -974,6 +1037,8 @@ static char *stibp_state(void) return ", STIBP: disabled"; case SPECTRE_V2_USER_STRICT: return ", STIBP: forced"; + case SPECTRE_V2_USER_PRCTL: + return ""; } return ""; } @@ -986,6 +1051,8 @@ static char *ibpb_state(void) return ", IBPB: disabled"; case SPECTRE_V2_USER_STRICT: return ", IBPB: always-on"; + case SPECTRE_V2_USER_PRCTL: + return ""; } } return ""; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index afbe2eb4a1c6..7d31192296a8 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -450,6 +450,11 @@ static unsigned long speculation_ctrl_update_tif(struct task_struct *tsk) set_tsk_thread_flag(tsk, TIF_SSBD); else clear_tsk_thread_flag(tsk, TIF_SSBD); + + if (task_spec_ib_disable(tsk)) + set_tsk_thread_flag(tsk, TIF_SPEC_IB); + else + clear_tsk_thread_flag(tsk, TIF_SPEC_IB); } /* Return the updated threadinfo flags*/ return task_thread_info(tsk)->flags; diff --git a/include/linux/sched.h b/include/linux/sched.h index a51c13c2b1a0..d607db5fcc6a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1453,6 +1453,8 @@ static inline bool is_percpu_thread(void) #define PFA_SPREAD_SLAB 2 /* Spread some slab caches over cpuset */ #define PFA_SPEC_SSB_DISABLE 3 /* Speculative Store Bypass disabled */ #define PFA_SPEC_SSB_FORCE_DISABLE 4 /* Speculative Store Bypass force disabled*/ +#define PFA_SPEC_IB_DISABLE 5 /* Indirect branch speculation restricted */ +#define PFA_SPEC_IB_FORCE_DISABLE 6 /* Indirect branch speculation permanently restricted */ #define TASK_PFA_TEST(name, func) \ static inline bool task_##func(struct task_struct *p) \ @@ -1484,6 +1486,13 @@ TASK_PFA_CLEAR(SPEC_SSB_DISABLE, spec_ssb_disable) TASK_PFA_TEST(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) TASK_PFA_SET(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) +TASK_PFA_TEST(SPEC_IB_DISABLE, spec_ib_disable) +TASK_PFA_SET(SPEC_IB_DISABLE, spec_ib_disable) +TASK_PFA_CLEAR(SPEC_IB_DISABLE, spec_ib_disable) + +TASK_PFA_TEST(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable) +TASK_PFA_SET(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable) + static inline void current_restore_flags(unsigned long orig_flags, unsigned long flags) { diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index c0d7ea0bf5b6..b17201edfa09 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -212,6 +212,7 @@ struct prctl_mm_map { #define PR_SET_SPECULATION_CTRL 53 /* Speculation control variants */ # define PR_SPEC_STORE_BYPASS 0 +# define PR_SPEC_INDIRECT_BRANCH 1 /* Return and control values for PR_SET/GET_SPECULATION_CTRL */ # define PR_SPEC_NOT_AFFECTED 0 # define PR_SPEC_PRCTL (1UL << 0) diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index c0d7ea0bf5b6..b17201edfa09 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -212,6 +212,7 @@ struct prctl_mm_map { #define PR_SET_SPECULATION_CTRL 53 /* Speculation control variants */ # define PR_SPEC_STORE_BYPASS 0 +# define PR_SPEC_INDIRECT_BRANCH 1 /* Return and control values for PR_SET/GET_SPECULATION_CTRL */ # define PR_SPEC_NOT_AFFECTED 0 # define PR_SPEC_PRCTL (1UL << 0) -- cgit v1.2.3 From 3f2b7b9035107d6096ea438ea3d97dcf0481b6d2 Mon Sep 17 00:00:00 2001 From: "kiran.modukuri" Date: Mon, 26 Nov 2018 15:41:48 +0000 Subject: fscache: Fix race in fscache_op_complete() due to split atomic_sub & read The code in fscache_retrieval_complete is using atomic_sub followed by an atomic_read: atomic_sub(n_pages, &op->n_pages); if (atomic_read(&op->n_pages) <= 0) fscache_op_complete(&op->op, true); This causes two threads doing a decrement of n_pages to race with each other seeing the op->refcount 0 at same time - and they end up calling fscache_op_complete() in both the threads leading to an assertion failure. Fix this by using atomic_sub_return_relaxed() instead of two calls. Note that I'm using 'relaxed' rather than, say, 'release' as there aren't multiple variables that appear to need ordering across the release. The oops looks something like: FS-Cache: Assertion failed FS-Cache: 0 > 0 is false ... kernel BUG at /usr/src/linux-4.4.0/fs/fscache/operation.c:449! ... Workqueue: fscache_operation fscache_op_work_func [fscache] ... RIP: 0010:[] fscache_op_complete+0x10d/0x180 [fscache] ... Call Trace: [] cachefiles_read_copier+0x3a9/0x410 [cachefiles] [] fscache_op_work_func+0x22/0x50 [fscache] [] process_one_work+0x150/0x3f0 [] worker_thread+0x11a/0x470 [] ? __schedule+0x359/0x980 [] ? rescuer_thread+0x310/0x310 [] kthread+0xd6/0xf0 [] ? kthread_park+0x60/0x60 [] ret_from_fork+0x3f/0x70 [] ? kthread_park+0x60/0x60 This seen this in 4.4.x kernels and the same bug affects fscache in latest upstreams kernels. Fixes: 1bb4b7f98f36 ("FS-Cache: The retrieval remaining-pages counter needs to be atomic_t") Signed-off-by: Kiran Kumar Modukuri Signed-off-by: David Howells --- include/linux/fscache-cache.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 34cf0fdd7dc7..610815e3f1aa 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -196,8 +196,7 @@ static inline void fscache_enqueue_retrieval(struct fscache_retrieval *op) static inline void fscache_retrieval_complete(struct fscache_retrieval *op, int n_pages) { - atomic_sub(n_pages, &op->n_pages); - if (atomic_read(&op->n_pages) <= 0) + if (atomic_sub_return_relaxed(n_pages, &op->n_pages) <= 0) fscache_op_complete(&op->op, false); } -- cgit v1.2.3 From 90230968f102acbe103fbf7c03d41addfef5f153 Mon Sep 17 00:00:00 2001 From: Baruch Siach Date: Thu, 29 Nov 2018 12:00:05 +0200 Subject: net: phy: sfp: correct location of SFP standards SFP standards are now available from the SNIA (Storage Networking Industry Association) website. Cc: Andrew Lunn Cc: Florian Fainelli Signed-off-by: Baruch Siach Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/sfp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sfp.h b/include/linux/sfp.h index d37518e89db2..d9d9de3fcf8e 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -224,7 +224,7 @@ struct sfp_eeprom_ext { * * See the SFF-8472 specification and related documents for the definition * of these structure members. This can be obtained from - * ftp://ftp.seagate.com/sff + * https://www.snia.org/technology-communities/sff/specifications */ struct sfp_eeprom_id { struct sfp_eeprom_base base; -- cgit v1.2.3 From 89d328f637b9904b6d4c9af73c8a608b8dd4d6f8 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 1 Nov 2018 16:17:22 -0700 Subject: pstore/ram: Correctly calculate usable PRZ bytes The actual number of bytes stored in a PRZ is smaller than the bytes requested by platform data, since there is a header on each PRZ. Additionally, if ECC is enabled, there are trailing bytes used as well. Normally this mismatch doesn't matter since PRZs are circular buffers and the leading "overflow" bytes are just thrown away. However, in the case of a compressed record, this rather badly corrupts the results. This corruption was visible with "ramoops.mem_size=204800 ramoops.ecc=1". Any stored crashes would not be uncompressable (producing a pstorefs "dmesg-*.enc.z" file), and triggering errors at boot: [ 2.790759] pstore: crypto_comp_decompress failed, ret = -22! Backporting this depends on commit 70ad35db3321 ("pstore: Convert console write to use ->write_buf") Reported-by: Joel Fernandes Fixes: b0aad7a99c1d ("pstore: Add compression support to pstore") Signed-off-by: Kees Cook Reviewed-by: Joel Fernandes (Google) --- fs/pstore/ram.c | 15 ++++++--------- include/linux/pstore.h | 5 ++++- 2 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index 712960e117fe..8646fe6e916f 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -816,17 +816,14 @@ static int ramoops_probe(struct platform_device *pdev) cxt->pstore.data = cxt; /* - * Console can handle any buffer size, so prefer LOG_LINE_MAX. If we - * have to handle dumps, we must have at least record_size buffer. And - * for ftrace, bufsize is irrelevant (if bufsize is 0, buf will be - * ZERO_SIZE_PTR). + * Since bufsize is only used for dmesg crash dumps, it + * must match the size of the dprz record (after PRZ header + * and ECC bytes have been accounted for). */ - if (cxt->console_size) - cxt->pstore.bufsize = 1024; /* LOG_LINE_MAX */ - cxt->pstore.bufsize = max(cxt->record_size, cxt->pstore.bufsize); - cxt->pstore.buf = kmalloc(cxt->pstore.bufsize, GFP_KERNEL); + cxt->pstore.bufsize = cxt->dprzs[0]->buffer_size; + cxt->pstore.buf = kzalloc(cxt->pstore.bufsize, GFP_KERNEL); if (!cxt->pstore.buf) { - pr_err("cannot allocate pstore buffer\n"); + pr_err("cannot allocate pstore crash dump buffer\n"); err = -ENOMEM; goto fail_clear; } diff --git a/include/linux/pstore.h b/include/linux/pstore.h index a15bc4d48752..30fcec375a3a 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -90,7 +90,10 @@ struct pstore_record { * * @buf_lock: spinlock to serialize access to @buf * @buf: preallocated crash dump buffer - * @bufsize: size of @buf available for crash dump writes + * @bufsize: size of @buf available for crash dump bytes (must match + * smallest number of bytes available for writing to a + * backend entry, since compressed bytes don't take kindly + * to being truncated) * * @read_mutex: serializes @open, @read, @close, and @erase callbacks * @flags: bitfield of frontends the backend can accept writes for -- cgit v1.2.3 From 0c7a52e4d4b5c4d35b31f3c3ad32af814f1bf491 Mon Sep 17 00:00:00 2001 From: Zenghui Yu Date: Wed, 28 Nov 2018 03:35:23 +0000 Subject: tracepoint: Use __idx instead of idx in DO_TRACE macro to make it unique After enabling KVM event tracing, almost all of trace_kvm_exit()'s printk shows "kvm_exit: IRQ: ..." even if the actual exception_type is NOT IRQ. More specifically, trace_kvm_exit() is defined in virt/kvm/arm/trace.h by TRACE_EVENT. This slight problem may have existed after commit e6753f23d961 ("tracepoint: Make rcuidle tracepoint callers use SRCU"). There are two variables in trace_kvm_exit() and __DO_TRACE() which have the same name, *idx*. Thus the actual value of *idx* will be overwritten when tracing. Fix it by adding a simple prefix. Cc: Joel Fernandes Cc: Wang Haibin Cc: linux-trace-devel@vger.kernel.org Cc: stable@vger.kernel.org Fixes: e6753f23d961 ("tracepoint: Make rcuidle tracepoint callers use SRCU") Reviewed-by: Joel Fernandes (Google) Signed-off-by: Zenghui Yu Signed-off-by: Steven Rostedt (VMware) --- include/linux/tracepoint.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 538ba1a58f5b..e9de8ad0bad7 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -166,7 +166,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) struct tracepoint_func *it_func_ptr; \ void *it_func; \ void *__data; \ - int __maybe_unused idx = 0; \ + int __maybe_unused __idx = 0; \ \ if (!(cond)) \ return; \ @@ -182,7 +182,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) * doesn't work from the idle path. \ */ \ if (rcuidle) { \ - idx = srcu_read_lock_notrace(&tracepoint_srcu); \ + __idx = srcu_read_lock_notrace(&tracepoint_srcu);\ rcu_irq_enter_irqson(); \ } \ \ @@ -198,7 +198,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) \ if (rcuidle) { \ rcu_irq_exit_irqson(); \ - srcu_read_unlock_notrace(&tracepoint_srcu, idx);\ + srcu_read_unlock_notrace(&tracepoint_srcu, __idx);\ } \ \ preempt_enable_notrace(); \ -- cgit v1.2.3 From e0c274472d5d27f277af722e017525e0b33784cd Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 30 Nov 2018 14:09:58 -0800 Subject: psi: make disabling/enabling easier for vendor kernels Mel Gorman reports a hackbench regression with psi that would prohibit shipping the suse kernel with it default-enabled, but he'd still like users to be able to opt in at little to no cost to others. With the current combination of CONFIG_PSI and the psi_disabled bool set from the commandline, this is a challenge. Do the following things to make it easier: 1. Add a config option CONFIG_PSI_DEFAULT_DISABLED that allows distros to enable CONFIG_PSI in their kernel but leave the feature disabled unless a user requests it at boot-time. To avoid double negatives, rename psi_disabled= to psi=. 2. Make psi_disabled a static branch to eliminate any branch costs when the feature is disabled. In terms of numbers before and after this patch, Mel says: : The following is a comparision using CONFIG_PSI=n as a baseline against : your patch and a vanilla kernel : : 4.20.0-rc4 4.20.0-rc4 4.20.0-rc4 : kconfigdisable-v1r1 vanilla psidisable-v1r1 : Amean 1 1.3100 ( 0.00%) 1.3923 ( -6.28%) 1.3427 ( -2.49%) : Amean 3 3.8860 ( 0.00%) 4.1230 * -6.10%* 3.8860 ( -0.00%) : Amean 5 6.8847 ( 0.00%) 8.0390 * -16.77%* 6.7727 ( 1.63%) : Amean 7 9.9310 ( 0.00%) 10.8367 * -9.12%* 9.9910 ( -0.60%) : Amean 12 16.6577 ( 0.00%) 18.2363 * -9.48%* 17.1083 ( -2.71%) : Amean 18 26.5133 ( 0.00%) 27.8833 * -5.17%* 25.7663 ( 2.82%) : Amean 24 34.3003 ( 0.00%) 34.6830 ( -1.12%) 32.0450 ( 6.58%) : Amean 30 40.0063 ( 0.00%) 40.5800 ( -1.43%) 41.5087 ( -3.76%) : Amean 32 40.1407 ( 0.00%) 41.2273 ( -2.71%) 39.9417 ( 0.50%) : : It's showing that the vanilla kernel takes a hit (as the bisection : indicated it would) and that disabling PSI by default is reasonably : close in terms of performance for this particular workload on this : particular machine so; Link: http://lkml.kernel.org/r/20181127165329.GA29728@cmpxchg.org Signed-off-by: Johannes Weiner Tested-by: Mel Gorman Reported-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/kernel-parameters.txt | 4 ++++ include/linux/psi.h | 3 ++- init/Kconfig | 9 ++++++++ kernel/sched/psi.c | 30 +++++++++++++++++-------- kernel/sched/stats.h | 8 +++---- 5 files changed, 40 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 675170c36078..5d6ba930d4f4 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3505,6 +3505,10 @@ before loading. See Documentation/blockdev/ramdisk.txt. + psi= [KNL] Enable or disable pressure stall information + tracking. + Format: + psmouse.proto= [HW,MOUSE] Highest PS2 mouse protocol extension to probe for; one of (bare|imps|exps|lifebook|any). psmouse.rate= [HW,MOUSE] Set desired mouse report rate, in reports diff --git a/include/linux/psi.h b/include/linux/psi.h index 8e0725aac0aa..7006008d5b72 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -1,6 +1,7 @@ #ifndef _LINUX_PSI_H #define _LINUX_PSI_H +#include #include #include @@ -9,7 +10,7 @@ struct css_set; #ifdef CONFIG_PSI -extern bool psi_disabled; +extern struct static_key_false psi_disabled; void psi_init(void); diff --git a/init/Kconfig b/init/Kconfig index a4112e95724a..cf5b5a0dcbc2 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -509,6 +509,15 @@ config PSI Say N if unsure. +config PSI_DEFAULT_DISABLED + bool "Require boot parameter to enable pressure stall information tracking" + default n + depends on PSI + help + If set, pressure stall information tracking will be disabled + per default but can be enabled through passing psi_enable=1 + on the kernel commandline during boot. + endmenu # "CPU/Task time and stats accounting" config CPU_ISOLATION diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 3d7355d7c3e3..fe24de3fbc93 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -136,8 +136,18 @@ static int psi_bug __read_mostly; -bool psi_disabled __read_mostly; -core_param(psi_disabled, psi_disabled, bool, 0644); +DEFINE_STATIC_KEY_FALSE(psi_disabled); + +#ifdef CONFIG_PSI_DEFAULT_DISABLED +bool psi_enable; +#else +bool psi_enable = true; +#endif +static int __init setup_psi(char *str) +{ + return kstrtobool(str, &psi_enable) == 0; +} +__setup("psi=", setup_psi); /* Running averages - we need to be higher-res than loadavg */ #define PSI_FREQ (2*HZ+1) /* 2 sec intervals */ @@ -169,8 +179,10 @@ static void group_init(struct psi_group *group) void __init psi_init(void) { - if (psi_disabled) + if (!psi_enable) { + static_branch_enable(&psi_disabled); return; + } psi_period = jiffies_to_nsecs(PSI_FREQ); group_init(&psi_system); @@ -549,7 +561,7 @@ void psi_memstall_enter(unsigned long *flags) struct rq_flags rf; struct rq *rq; - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; *flags = current->flags & PF_MEMSTALL; @@ -579,7 +591,7 @@ void psi_memstall_leave(unsigned long *flags) struct rq_flags rf; struct rq *rq; - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; if (*flags) @@ -600,7 +612,7 @@ void psi_memstall_leave(unsigned long *flags) #ifdef CONFIG_CGROUPS int psi_cgroup_alloc(struct cgroup *cgroup) { - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return 0; cgroup->psi.pcpu = alloc_percpu(struct psi_group_cpu); @@ -612,7 +624,7 @@ int psi_cgroup_alloc(struct cgroup *cgroup) void psi_cgroup_free(struct cgroup *cgroup) { - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; cancel_delayed_work_sync(&cgroup->psi.clock_work); @@ -637,7 +649,7 @@ void cgroup_move_task(struct task_struct *task, struct css_set *to) struct rq_flags rf; struct rq *rq; - if (psi_disabled) { + if (static_branch_likely(&psi_disabled)) { /* * Lame to do this here, but the scheduler cannot be locked * from the outside, so we move cgroups from inside sched/. @@ -673,7 +685,7 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) { int full; - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return -EOPNOTSUPP; update_stats(group); diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index 4904c4677000..aa0de240fb41 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -66,7 +66,7 @@ static inline void psi_enqueue(struct task_struct *p, bool wakeup) { int clear = 0, set = TSK_RUNNING; - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; if (!wakeup || p->sched_psi_wake_requeue) { @@ -86,7 +86,7 @@ static inline void psi_dequeue(struct task_struct *p, bool sleep) { int clear = TSK_RUNNING, set = 0; - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; if (!sleep) { @@ -102,7 +102,7 @@ static inline void psi_dequeue(struct task_struct *p, bool sleep) static inline void psi_ttwu_dequeue(struct task_struct *p) { - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; /* * Is the task being migrated during a wakeup? Make sure to @@ -128,7 +128,7 @@ static inline void psi_ttwu_dequeue(struct task_struct *p) static inline void psi_task_tick(struct rq *rq) { - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; if (unlikely(rq->curr->flags & PF_MEMSTALL)) -- cgit v1.2.3 From b7df9ada9a7700dbcca1ba53d217c01e3d48179c Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 1 Dec 2018 01:18:53 +0100 Subject: bpf: fix pointer offsets in context for 32 bit Currently, pointer offsets in three BPF context structures are broken in two scenarios: i) 32 bit compiled applications running on 64 bit kernels, and ii) LLVM compiled BPF programs running on 32 bit kernels. The latter is due to BPF target machine being strictly 64 bit. So in each of the cases the offsets will mismatch in verifier when checking / rewriting context access. Fix this by providing a helper macro __bpf_md_ptr() that will enforce padding up to 64 bit and proper alignment, and for context access a macro bpf_ctx_range_ptr() which will cover full 64 bit member range on 32 bit archs. For flow_keys, we additionally need to force the size check to sizeof(__u64) as with other pointer types. Fixes: d58e468b1112 ("flow_dissector: implements flow dissector BPF hook") Fixes: 4f738adba30a ("bpf: create tcp_bpf_ulp allowing BPF to monitor socket TX/RX data") Fixes: 2dbb9b9e6df6 ("bpf: Introduce BPF_PROG_TYPE_SK_REUSEPORT") Reported-by: David S. Miller Signed-off-by: Daniel Borkmann Acked-by: David S. Miller Tested-by: David S. Miller Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 7 +++++++ include/uapi/linux/bpf.h | 17 ++++++++++++----- net/core/filter.c | 16 ++++++++-------- tools/include/uapi/linux/bpf.h | 17 ++++++++++++----- 4 files changed, 39 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 448dcc448f1f..795ff0b869bb 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -449,6 +449,13 @@ struct sock_reuseport; offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1 #define bpf_ctx_range_till(TYPE, MEMBER1, MEMBER2) \ offsetof(TYPE, MEMBER1) ... offsetofend(TYPE, MEMBER2) - 1 +#if BITS_PER_LONG == 64 +# define bpf_ctx_range_ptr(TYPE, MEMBER) \ + offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1 +#else +# define bpf_ctx_range_ptr(TYPE, MEMBER) \ + offsetof(TYPE, MEMBER) ... offsetof(TYPE, MEMBER) + 8 - 1 +#endif /* BITS_PER_LONG == 64 */ #define bpf_target_off(TYPE, MEMBER, SIZE, PTR_SIZE) \ ({ \ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 852dc17ab47a..426b5c8a245b 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2422,6 +2422,12 @@ enum bpf_lwt_encap_mode { BPF_LWT_ENCAP_SEG6_INLINE }; +#define __bpf_md_ptr(type, name) \ +union { \ + type name; \ + __u64 :64; \ +} __attribute__((aligned(8))) + /* user accessible mirror of in-kernel sk_buff. * new fields can only be added to the end of this structure */ @@ -2456,7 +2462,7 @@ struct __sk_buff { /* ... here. */ __u32 data_meta; - struct bpf_flow_keys *flow_keys; + __bpf_md_ptr(struct bpf_flow_keys *, flow_keys); }; struct bpf_tunnel_key { @@ -2572,8 +2578,8 @@ enum sk_action { * be added to the end of this structure */ struct sk_msg_md { - void *data; - void *data_end; + __bpf_md_ptr(void *, data); + __bpf_md_ptr(void *, data_end); __u32 family; __u32 remote_ip4; /* Stored in network byte order */ @@ -2589,8 +2595,9 @@ struct sk_reuseport_md { * Start of directly accessible data. It begins from * the tcp/udp header. */ - void *data; - void *data_end; /* End of directly accessible data */ + __bpf_md_ptr(void *, data); + /* End of directly accessible data */ + __bpf_md_ptr(void *, data_end); /* * Total length of packet (starting from the tcp/udp header). * Note that the directly accessible bytes (data_end - data) diff --git a/net/core/filter.c b/net/core/filter.c index 9a1327eb25fa..6ee605da990f 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5435,8 +5435,8 @@ 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 *)) + case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): + if (size != sizeof(__u64)) return false; break; default: @@ -5464,7 +5464,7 @@ 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_ptr(struct __sk_buff, flow_keys): case bpf_ctx_range_till(struct __sk_buff, family, local_port): return false; } @@ -5489,7 +5489,7 @@ static bool cg_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): + case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): return false; case bpf_ctx_range(struct __sk_buff, data): case bpf_ctx_range(struct __sk_buff, data_end): @@ -5530,7 +5530,7 @@ 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): + case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): return false; } @@ -5756,7 +5756,7 @@ 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_ptr(struct __sk_buff, flow_keys): case bpf_ctx_range_till(struct __sk_buff, family, local_port): return false; } @@ -5958,7 +5958,7 @@ 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): + case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): return false; } @@ -6039,7 +6039,7 @@ static bool flow_dissector_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_ptr(struct __sk_buff, flow_keys): info->reg_type = PTR_TO_FLOW_KEYS; break; case bpf_ctx_range(struct __sk_buff, tc_classid): diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 852dc17ab47a..426b5c8a245b 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2422,6 +2422,12 @@ enum bpf_lwt_encap_mode { BPF_LWT_ENCAP_SEG6_INLINE }; +#define __bpf_md_ptr(type, name) \ +union { \ + type name; \ + __u64 :64; \ +} __attribute__((aligned(8))) + /* user accessible mirror of in-kernel sk_buff. * new fields can only be added to the end of this structure */ @@ -2456,7 +2462,7 @@ struct __sk_buff { /* ... here. */ __u32 data_meta; - struct bpf_flow_keys *flow_keys; + __bpf_md_ptr(struct bpf_flow_keys *, flow_keys); }; struct bpf_tunnel_key { @@ -2572,8 +2578,8 @@ enum sk_action { * be added to the end of this structure */ struct sk_msg_md { - void *data; - void *data_end; + __bpf_md_ptr(void *, data); + __bpf_md_ptr(void *, data_end); __u32 family; __u32 remote_ip4; /* Stored in network byte order */ @@ -2589,8 +2595,9 @@ struct sk_reuseport_md { * Start of directly accessible data. It begins from * the tcp/udp header. */ - void *data; - void *data_end; /* End of directly accessible data */ + __bpf_md_ptr(void *, data); + /* End of directly accessible data */ + __bpf_md_ptr(void *, data_end); /* * Total length of packet (starting from the tcp/udp header). * Note that the directly accessible bytes (data_end - data) -- cgit v1.2.3 From 71700bb96047f68a0aae3932466fc7c9ad5ce6c0 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 30 Nov 2018 16:11:15 -0500 Subject: SUNRPC: Fix a memory leak in call_encode() If we retransmit an RPC request, we currently end up clobbering the value of req->rq_rcv_buf.bvec that was allocated by the initial call to xprt_request_prepare(req). Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xdr.h | 1 - net/sunrpc/clnt.c | 1 + net/sunrpc/xprt.c | 2 ++ 3 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 43106ffa6788..2ec128060239 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -72,7 +72,6 @@ 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; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index e35d642558e7..c6782aa47525 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -2309,6 +2309,7 @@ out_retry: task->tk_status = 0; /* Note: rpc_verify_header() may have freed the RPC slot */ if (task->tk_rqstp == req) { + xdr_free_bvec(&req->rq_rcv_buf); req->rq_reply_bytes_recvd = req->rq_rcv_buf.len = 0; if (task->tk_client->cl_discrtry) xprt_conditional_disconnect(req->rq_xprt, diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 86bea4520c4d..122c91c28e7c 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1623,6 +1623,8 @@ xprt_request_init(struct rpc_task *task) req->rq_snd_buf.buflen = 0; req->rq_rcv_buf.len = 0; req->rq_rcv_buf.buflen = 0; + req->rq_snd_buf.bvec = NULL; + req->rq_rcv_buf.bvec = NULL; req->rq_release_snd_buf = NULL; xprt_reset_majortimeo(req); dprintk("RPC: %5u reserved req %p xid %08x\n", task->tk_pid, -- cgit v1.2.3 From 37c2578c0c40e286bc0d30bdc05290b2058cf66e Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Mon, 3 Dec 2018 00:54:35 +0000 Subject: Drivers: hv: vmbus: Offload the handling of channels to two workqueues vmbus_process_offer() mustn't call channel->sc_creation_callback() directly for sub-channels, because sc_creation_callback() -> vmbus_open() may never get the host's response to the OPEN_CHANNEL message (the host may rescind a channel at any time, e.g. in the case of hot removing a NIC), and vmbus_onoffer_rescind() may not wake up the vmbus_open() as it's blocked due to a non-zero vmbus_connection.offer_in_progress, and finally we have a deadlock. The above is also true for primary channels, if the related device drivers use sync probing mode by default. And, usually the handling of primary channels and sub-channels can depend on each other, so we should offload them to different workqueues to avoid possible deadlock, e.g. in sync-probing mode, NIC1's netvsc_subchan_work() can race with NIC2's netvsc_probe() -> rtnl_lock(), and causes deadlock: the former gets the rtnl_lock and waits for all the sub-channels to appear, but the latter can't get the rtnl_lock and this blocks the handling of sub-channels. The patch can fix the multiple-NIC deadlock described above for v3.x kernels (e.g. RHEL 7.x) which don't support async-probing of devices, and v4.4, v4.9, v4.14 and v4.18 which support async-probing but don't enable async-probing for Hyper-V drivers (yet). The patch can also fix the hang issue in sub-channel's handling described above for all versions of kernels, including v4.19 and v4.20-rc4. So actually the patch should be applied to all the existing kernels, not only the kernels that have 8195b1396ec8. Fixes: 8195b1396ec8 ("hv_netvsc: fix deadlock on hotplug") Cc: stable@vger.kernel.org Cc: Stephen Hemminger Cc: K. Y. Srinivasan Cc: Haiyang Zhang Signed-off-by: Dexuan Cui Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- drivers/hv/channel_mgmt.c | 189 ++++++++++++++++++++++++++++++---------------- drivers/hv/connection.c | 24 +++++- drivers/hv/hyperv_vmbus.h | 7 ++ include/linux/hyperv.h | 7 ++ 4 files changed, 161 insertions(+), 66 deletions(-) (limited to 'include/linux') diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index 6277597d3d58..edd34c167a9b 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -435,61 +435,16 @@ void vmbus_free_channels(void) } } -/* - * vmbus_process_offer - Process the offer by creating a channel/device - * associated with this offer - */ -static void vmbus_process_offer(struct vmbus_channel *newchannel) +/* Note: the function can run concurrently for primary/sub channels. */ +static void vmbus_add_channel_work(struct work_struct *work) { - struct vmbus_channel *channel; - bool fnew = true; + struct vmbus_channel *newchannel = + container_of(work, struct vmbus_channel, add_channel_work); + struct vmbus_channel *primary_channel = newchannel->primary_channel; unsigned long flags; u16 dev_type; int ret; - /* Make sure this is a new offer */ - mutex_lock(&vmbus_connection.channel_mutex); - - /* - * Now that we have acquired the channel_mutex, - * we can release the potentially racing rescind thread. - */ - atomic_dec(&vmbus_connection.offer_in_progress); - - list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) { - if (!uuid_le_cmp(channel->offermsg.offer.if_type, - newchannel->offermsg.offer.if_type) && - !uuid_le_cmp(channel->offermsg.offer.if_instance, - newchannel->offermsg.offer.if_instance)) { - fnew = false; - break; - } - } - - if (fnew) - list_add_tail(&newchannel->listentry, - &vmbus_connection.chn_list); - - mutex_unlock(&vmbus_connection.channel_mutex); - - if (!fnew) { - /* - * Check to see if this is a sub-channel. - */ - if (newchannel->offermsg.offer.sub_channel_index != 0) { - /* - * Process the sub-channel. - */ - newchannel->primary_channel = channel; - spin_lock_irqsave(&channel->lock, flags); - list_add_tail(&newchannel->sc_list, &channel->sc_list); - channel->num_sc++; - spin_unlock_irqrestore(&channel->lock, flags); - } else { - goto err_free_chan; - } - } - dev_type = hv_get_dev_type(newchannel); init_vp_index(newchannel, dev_type); @@ -507,27 +462,26 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel) /* * This state is used to indicate a successful open * so that when we do close the channel normally, we - * can cleanup properly + * can cleanup properly. */ newchannel->state = CHANNEL_OPEN_STATE; - if (!fnew) { - struct hv_device *dev - = newchannel->primary_channel->device_obj; + if (primary_channel != NULL) { + /* newchannel is a sub-channel. */ + struct hv_device *dev = primary_channel->device_obj; if (vmbus_add_channel_kobj(dev, newchannel)) - goto err_free_chan; + goto err_deq_chan; + + if (primary_channel->sc_creation_callback != NULL) + primary_channel->sc_creation_callback(newchannel); - if (channel->sc_creation_callback != NULL) - channel->sc_creation_callback(newchannel); newchannel->probe_done = true; return; } /* - * Start the process of binding this offer to the driver - * We need to set the DeviceObject field before calling - * vmbus_child_dev_add() + * Start the process of binding the primary channel to the driver */ newchannel->device_obj = vmbus_device_create( &newchannel->offermsg.offer.if_type, @@ -556,13 +510,28 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel) err_deq_chan: mutex_lock(&vmbus_connection.channel_mutex); - list_del(&newchannel->listentry); + + /* + * We need to set the flag, otherwise + * vmbus_onoffer_rescind() can be blocked. + */ + newchannel->probe_done = true; + + if (primary_channel == NULL) { + list_del(&newchannel->listentry); + } else { + spin_lock_irqsave(&primary_channel->lock, flags); + list_del(&newchannel->sc_list); + spin_unlock_irqrestore(&primary_channel->lock, flags); + } + mutex_unlock(&vmbus_connection.channel_mutex); if (newchannel->target_cpu != get_cpu()) { put_cpu(); smp_call_function_single(newchannel->target_cpu, - percpu_channel_deq, newchannel, true); + percpu_channel_deq, + newchannel, true); } else { percpu_channel_deq(newchannel); put_cpu(); @@ -570,14 +539,104 @@ err_deq_chan: vmbus_release_relid(newchannel->offermsg.child_relid); -err_free_chan: free_channel(newchannel); } +/* + * vmbus_process_offer - Process the offer by creating a channel/device + * associated with this offer + */ +static void vmbus_process_offer(struct vmbus_channel *newchannel) +{ + struct vmbus_channel *channel; + struct workqueue_struct *wq; + unsigned long flags; + bool fnew = true; + + mutex_lock(&vmbus_connection.channel_mutex); + + /* + * Now that we have acquired the channel_mutex, + * we can release the potentially racing rescind thread. + */ + atomic_dec(&vmbus_connection.offer_in_progress); + + list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) { + if (!uuid_le_cmp(channel->offermsg.offer.if_type, + newchannel->offermsg.offer.if_type) && + !uuid_le_cmp(channel->offermsg.offer.if_instance, + newchannel->offermsg.offer.if_instance)) { + fnew = false; + break; + } + } + + if (fnew) + list_add_tail(&newchannel->listentry, + &vmbus_connection.chn_list); + else { + /* + * Check to see if this is a valid sub-channel. + */ + if (newchannel->offermsg.offer.sub_channel_index == 0) { + mutex_unlock(&vmbus_connection.channel_mutex); + /* + * Don't call free_channel(), because newchannel->kobj + * is not initialized yet. + */ + kfree(newchannel); + WARN_ON_ONCE(1); + return; + } + /* + * Process the sub-channel. + */ + newchannel->primary_channel = channel; + spin_lock_irqsave(&channel->lock, flags); + list_add_tail(&newchannel->sc_list, &channel->sc_list); + spin_unlock_irqrestore(&channel->lock, flags); + } + + mutex_unlock(&vmbus_connection.channel_mutex); + + /* + * vmbus_process_offer() mustn't call channel->sc_creation_callback() + * directly for sub-channels, because sc_creation_callback() -> + * vmbus_open() may never get the host's response to the + * OPEN_CHANNEL message (the host may rescind a channel at any time, + * e.g. in the case of hot removing a NIC), and vmbus_onoffer_rescind() + * may not wake up the vmbus_open() as it's blocked due to a non-zero + * vmbus_connection.offer_in_progress, and finally we have a deadlock. + * + * The above is also true for primary channels, if the related device + * drivers use sync probing mode by default. + * + * And, usually the handling of primary channels and sub-channels can + * depend on each other, so we should offload them to different + * workqueues to avoid possible deadlock, e.g. in sync-probing mode, + * NIC1's netvsc_subchan_work() can race with NIC2's netvsc_probe() -> + * rtnl_lock(), and causes deadlock: the former gets the rtnl_lock + * and waits for all the sub-channels to appear, but the latter + * can't get the rtnl_lock and this blocks the handling of + * sub-channels. + */ + INIT_WORK(&newchannel->add_channel_work, vmbus_add_channel_work); + wq = fnew ? vmbus_connection.handle_primary_chan_wq : + vmbus_connection.handle_sub_chan_wq; + queue_work(wq, &newchannel->add_channel_work); +} + /* * We use this state to statically distribute the channel interrupt load. */ static int next_numa_node_id; +/* + * init_vp_index() accesses global variables like next_numa_node_id, and + * it can run concurrently for primary channels and sub-channels: see + * vmbus_process_offer(), so we need the lock to protect the global + * variables. + */ +static DEFINE_SPINLOCK(bind_channel_to_cpu_lock); /* * Starting with Win8, we can statically distribute the incoming @@ -613,6 +672,8 @@ static void init_vp_index(struct vmbus_channel *channel, u16 dev_type) return; } + spin_lock(&bind_channel_to_cpu_lock); + /* * Based on the channel affinity policy, we will assign the NUMA * nodes. @@ -695,6 +756,8 @@ static void init_vp_index(struct vmbus_channel *channel, u16 dev_type) channel->target_cpu = cur_cpu; channel->target_vp = hv_cpu_number_to_vp_number(cur_cpu); + spin_unlock(&bind_channel_to_cpu_lock); + free_cpumask_var(available_mask); } diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c index f4d08c8ac7f8..4fe117b761ce 100644 --- a/drivers/hv/connection.c +++ b/drivers/hv/connection.c @@ -190,6 +190,20 @@ int vmbus_connect(void) goto cleanup; } + vmbus_connection.handle_primary_chan_wq = + create_workqueue("hv_pri_chan"); + if (!vmbus_connection.handle_primary_chan_wq) { + ret = -ENOMEM; + goto cleanup; + } + + vmbus_connection.handle_sub_chan_wq = + create_workqueue("hv_sub_chan"); + if (!vmbus_connection.handle_sub_chan_wq) { + ret = -ENOMEM; + goto cleanup; + } + INIT_LIST_HEAD(&vmbus_connection.chn_msg_list); spin_lock_init(&vmbus_connection.channelmsg_lock); @@ -280,10 +294,14 @@ void vmbus_disconnect(void) */ vmbus_initiate_unload(false); - if (vmbus_connection.work_queue) { - drain_workqueue(vmbus_connection.work_queue); + if (vmbus_connection.handle_sub_chan_wq) + destroy_workqueue(vmbus_connection.handle_sub_chan_wq); + + if (vmbus_connection.handle_primary_chan_wq) + destroy_workqueue(vmbus_connection.handle_primary_chan_wq); + + if (vmbus_connection.work_queue) destroy_workqueue(vmbus_connection.work_queue); - } if (vmbus_connection.int_page) { free_pages((unsigned long)vmbus_connection.int_page, 0); diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index 72eaba3d50fc..87d3d7da78f8 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -335,7 +335,14 @@ struct vmbus_connection { struct list_head chn_list; struct mutex channel_mutex; + /* + * An offer message is handled first on the work_queue, and then + * is further handled on handle_primary_chan_wq or + * handle_sub_chan_wq. + */ struct workqueue_struct *work_queue; + struct workqueue_struct *handle_primary_chan_wq; + struct workqueue_struct *handle_sub_chan_wq; }; diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index b3e24368930a..14131b6fae68 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -905,6 +905,13 @@ struct vmbus_channel { bool probe_done; + /* + * We must offload the handling of the primary/sub channels + * from the single-threaded vmbus_connection.work_queue to + * two different workqueue, otherwise we can block + * vmbus_connection.work_queue and hang: see vmbus_process_offer(). + */ + struct work_struct add_channel_work; }; static inline bool is_hvsock_channel(const struct vmbus_channel *c) -- cgit v1.2.3 From 27359fd6e5f3c5db8fe544b63238b6170e8806d8 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 30 Nov 2018 11:05:06 -0500 Subject: dax: Fix unlock mismatch with updated API Internal to dax_unlock_mapping_entry(), dax_unlock_entry() is used to store a replacement entry in the Xarray at the given xas-index with the DAX_LOCKED bit clear. When called, dax_unlock_entry() expects the unlocked value of the entry relative to the current Xarray state to be specified. In most contexts dax_unlock_entry() is operating in the same scope as the matched dax_lock_entry(). However, in the dax_unlock_mapping_entry() case the implementation needs to recall the original entry. In the case where the original entry is a 'pmd' entry it is possible that the pfn performed to do the lookup is misaligned to the value retrieved in the Xarray. Change the api to return the unlock cookie from dax_lock_page() and pass it to dax_unlock_page(). This fixes a bug where dax_unlock_page() was assuming that the page was PMD-aligned if the entry was a PMD entry with signatures like: WARNING: CPU: 38 PID: 1396 at fs/dax.c:340 dax_insert_entry+0x2b2/0x2d0 RIP: 0010:dax_insert_entry+0x2b2/0x2d0 [..] Call Trace: dax_iomap_pte_fault.isra.41+0x791/0xde0 ext4_dax_huge_fault+0x16f/0x1f0 ? up_read+0x1c/0xa0 __do_fault+0x1f/0x160 __handle_mm_fault+0x1033/0x1490 handle_mm_fault+0x18b/0x3d0 Link: https://lkml.kernel.org/r/20181130154902.GL10377@bombadil.infradead.org Fixes: 9f32d221301c ("dax: Convert dax_lock_mapping_entry to XArray") Reported-by: Dan Williams Signed-off-by: Matthew Wilcox Tested-by: Dan Williams Reviewed-by: Jan Kara Signed-off-by: Dan Williams --- fs/dax.c | 21 ++++++++------------- include/linux/dax.h | 14 ++++++++------ mm/memory-failure.c | 6 ++++-- 3 files changed, 20 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/fs/dax.c b/fs/dax.c index 3f592dc18d67..48132eca3761 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -379,20 +379,20 @@ static struct page *dax_busy_page(void *entry) * @page: The page whose entry we want to lock * * Context: Process context. - * Return: %true if the entry was locked or does not need to be locked. + * Return: A cookie to pass to dax_unlock_page() or 0 if the entry could + * not be locked. */ -bool dax_lock_mapping_entry(struct page *page) +dax_entry_t dax_lock_page(struct page *page) { XA_STATE(xas, NULL, 0); void *entry; - bool locked; /* Ensure page->mapping isn't freed while we look at it */ rcu_read_lock(); for (;;) { struct address_space *mapping = READ_ONCE(page->mapping); - locked = false; + entry = NULL; if (!mapping || !dax_mapping(mapping)) break; @@ -403,7 +403,7 @@ bool dax_lock_mapping_entry(struct page *page) * otherwise we would not have a valid pfn_to_page() * translation. */ - locked = true; + entry = (void *)~0UL; if (S_ISCHR(mapping->host->i_mode)) break; @@ -426,23 +426,18 @@ bool dax_lock_mapping_entry(struct page *page) break; } rcu_read_unlock(); - return locked; + return (dax_entry_t)entry; } -void dax_unlock_mapping_entry(struct page *page) +void dax_unlock_page(struct page *page, dax_entry_t cookie) { struct address_space *mapping = page->mapping; XA_STATE(xas, &mapping->i_pages, page->index); - void *entry; if (S_ISCHR(mapping->host->i_mode)) return; - rcu_read_lock(); - entry = xas_load(&xas); - rcu_read_unlock(); - entry = dax_make_entry(page_to_pfn_t(page), dax_is_pmd_entry(entry)); - dax_unlock_entry(&xas, entry); + dax_unlock_entry(&xas, (void *)cookie); } /* diff --git a/include/linux/dax.h b/include/linux/dax.h index 450b28db9533..0dd316a74a29 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -7,6 +7,8 @@ #include #include +typedef unsigned long dax_entry_t; + struct iomap_ops; struct dax_device; struct dax_operations { @@ -88,8 +90,8 @@ int dax_writeback_mapping_range(struct address_space *mapping, struct block_device *bdev, struct writeback_control *wbc); struct page *dax_layout_busy_page(struct address_space *mapping); -bool dax_lock_mapping_entry(struct page *page); -void dax_unlock_mapping_entry(struct page *page); +dax_entry_t dax_lock_page(struct page *page); +void dax_unlock_page(struct page *page, dax_entry_t cookie); #else static inline bool bdev_dax_supported(struct block_device *bdev, int blocksize) @@ -122,14 +124,14 @@ static inline int dax_writeback_mapping_range(struct address_space *mapping, return -EOPNOTSUPP; } -static inline bool dax_lock_mapping_entry(struct page *page) +static inline dax_entry_t dax_lock_page(struct page *page) { if (IS_DAX(page->mapping->host)) - return true; - return false; + return ~0UL; + return 0; } -static inline void dax_unlock_mapping_entry(struct page *page) +static inline void dax_unlock_page(struct page *page, dax_entry_t cookie) { } #endif diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 0cd3de3550f0..7c72f2a95785 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1161,6 +1161,7 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags, LIST_HEAD(tokill); int rc = -EBUSY; loff_t start; + dax_entry_t cookie; /* * Prevent the inode from being freed while we are interrogating @@ -1169,7 +1170,8 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags, * also prevents changes to the mapping of this pfn until * poison signaling is complete. */ - if (!dax_lock_mapping_entry(page)) + cookie = dax_lock_page(page); + if (!cookie) goto out; if (hwpoison_filter(page)) { @@ -1220,7 +1222,7 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags, kill_procs(&tokill, flags & MF_MUST_KILL, !unmap_success, pfn, flags); rc = 0; unlock: - dax_unlock_mapping_entry(page); + dax_unlock_page(page, cookie); out: /* drop pgmap ref acquired in caller */ put_dev_pagemap(pgmap); -- cgit v1.2.3 From f51ccf46217c28758b1f3b5bc0ccfc00eca658b2 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 4 Dec 2018 17:00:36 +0100 Subject: USB: serial: console: fix reported terminal settings The USB-serial console implementation has never reported the actual terminal settings used. Despite storing the corresponding cflags in its struct console, these were never honoured on later tty open() where the tty termios would be left initialised to the driver defaults. Unlike the serial console implementation, the USB-serial code calls subdriver open() already at console setup. While calling set_termios() and write() before open() looks like it could work for some USB-serial drivers, others definitely do not expect this, so modelling this after serial core is going to be intrusive, if at all possible. Instead, use a (renamed) tty helper to save the termios data used at console setup so that the tty termios reflects the actual terminal settings after a subsequent tty open(). Note that the calls to tty_init_termios() (tty_driver_install()) and tty_save_termios() are serialised using the disconnect mutex. This specifically fixes a regression that was triggered by a recent change adding software flow control to the pl2303 driver: a getty trying to disable flow control while leaving the baud rate unchanged would now also set the baud rate to the driver default (prior to the flow-control change this had been a noop). Fixes: 7041d9c3f01b ("USB: serial: pl2303: add support for tx xon/xoff flow control") Cc: stable # 4.18 Cc: Florian Zumbiehl Reported-by: Jarkko Nikula Tested-by: Jarkko Nikula Acked-by: Greg Kroah-Hartman Signed-off-by: Johan Hovold --- drivers/tty/tty_io.c | 11 +++++++++-- drivers/usb/serial/console.c | 2 +- include/linux/tty.h | 1 + 3 files changed, 11 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index ee80dfbd5442..687250ec8032 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -1373,7 +1373,13 @@ err_release_lock: return ERR_PTR(retval); } -static void tty_free_termios(struct tty_struct *tty) +/** + * tty_save_termios() - save tty termios data in driver table + * @tty: tty whose termios data to save + * + * Locking: Caller guarantees serialisation with tty_init_termios(). + */ +void tty_save_termios(struct tty_struct *tty) { struct ktermios *tp; int idx = tty->index; @@ -1392,6 +1398,7 @@ static void tty_free_termios(struct tty_struct *tty) } *tp = tty->termios; } +EXPORT_SYMBOL_GPL(tty_save_termios); /** * tty_flush_works - flush all works of a tty/pty pair @@ -1491,7 +1498,7 @@ static void release_tty(struct tty_struct *tty, int idx) WARN_ON(!mutex_is_locked(&tty_mutex)); if (tty->ops->shutdown) tty->ops->shutdown(tty); - tty_free_termios(tty); + tty_save_termios(tty); tty_driver_remove_tty(tty->driver, tty); tty->port->itty = NULL; if (tty->link) diff --git a/drivers/usb/serial/console.c b/drivers/usb/serial/console.c index 17940589c647..7d289302ff6c 100644 --- a/drivers/usb/serial/console.c +++ b/drivers/usb/serial/console.c @@ -101,7 +101,6 @@ static int usb_console_setup(struct console *co, char *options) cflag |= PARENB; break; } - co->cflag = cflag; /* * no need to check the index here: if the index is wrong, console @@ -164,6 +163,7 @@ static int usb_console_setup(struct console *co, char *options) serial->type->set_termios(tty, port, &dummy); tty_port_tty_set(&port->port, NULL); + tty_save_termios(tty); tty_kref_put(tty); } tty_port_set_initialized(&port->port, 1); diff --git a/include/linux/tty.h b/include/linux/tty.h index 414db2bce715..392138fe59b6 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -556,6 +556,7 @@ extern struct tty_struct *tty_init_dev(struct tty_driver *driver, int idx); extern void tty_release_struct(struct tty_struct *tty, int idx); extern int tty_release(struct inode *inode, struct file *filp); extern void tty_init_termios(struct tty_struct *tty); +extern void tty_save_termios(struct tty_struct *tty); extern int tty_standard_install(struct tty_driver *driver, struct tty_struct *tty); -- cgit v1.2.3 From 704620afc70cf47abb9d6a1a57f3825d2bca49cf Mon Sep 17 00:00:00 2001 From: Mathias Payer Date: Wed, 5 Dec 2018 21:19:59 +0100 Subject: USB: check usb_get_extra_descriptor for proper size When reading an extra descriptor, we need to properly check the minimum and maximum size allowed, to prevent from invalid data being sent by a device. Reported-by: Hui Peng Reported-by: Mathias Payer Co-developed-by: Linus Torvalds Signed-off-by: Hui Peng Signed-off-by: Mathias Payer Signed-off-by: Linus Torvalds Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/hub.c | 2 +- drivers/usb/core/usb.c | 6 +++--- drivers/usb/host/hwa-hc.c | 2 +- include/linux/usb.h | 4 ++-- 4 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 528664059a12..f76b2e0aba9d 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -2251,7 +2251,7 @@ static int usb_enumerate_device_otg(struct usb_device *udev) /* descriptor may appear anywhere in config */ err = __usb_get_extra_descriptor(udev->rawdescriptors[0], le16_to_cpu(udev->config[0].desc.wTotalLength), - USB_DT_OTG, (void **) &desc); + USB_DT_OTG, (void **) &desc, sizeof(*desc)); if (err || !(desc->bmAttributes & USB_OTG_HNP)) return 0; diff --git a/drivers/usb/core/usb.c b/drivers/usb/core/usb.c index 79d8bd7a612e..4ebfbd737905 100644 --- a/drivers/usb/core/usb.c +++ b/drivers/usb/core/usb.c @@ -832,14 +832,14 @@ EXPORT_SYMBOL_GPL(usb_get_current_frame_number); */ int __usb_get_extra_descriptor(char *buffer, unsigned size, - unsigned char type, void **ptr) + unsigned char type, void **ptr, size_t minsize) { struct usb_descriptor_header *header; while (size >= sizeof(struct usb_descriptor_header)) { header = (struct usb_descriptor_header *)buffer; - if (header->bLength < 2) { + if (header->bLength < 2 || header->bLength > size) { printk(KERN_ERR "%s: bogus descriptor, type %d length %d\n", usbcore_name, @@ -848,7 +848,7 @@ int __usb_get_extra_descriptor(char *buffer, unsigned size, return -1; } - if (header->bDescriptorType == type) { + if (header->bDescriptorType == type && header->bLength >= minsize) { *ptr = header; return 0; } diff --git a/drivers/usb/host/hwa-hc.c b/drivers/usb/host/hwa-hc.c index 684d6f074c3a..09a8ebd95588 100644 --- a/drivers/usb/host/hwa-hc.c +++ b/drivers/usb/host/hwa-hc.c @@ -640,7 +640,7 @@ static int hwahc_security_create(struct hwahc *hwahc) top = itr + itr_size; result = __usb_get_extra_descriptor(usb_dev->rawdescriptors[index], le16_to_cpu(usb_dev->actconfig->desc.wTotalLength), - USB_DT_SECURITY, (void **) &secd); + USB_DT_SECURITY, (void **) &secd, sizeof(*secd)); if (result == -1) { dev_warn(dev, "BUG? WUSB host has no security descriptors\n"); return 0; diff --git a/include/linux/usb.h b/include/linux/usb.h index 4cdd515a4385..5e49e82c4368 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -407,11 +407,11 @@ struct usb_host_bos { }; int __usb_get_extra_descriptor(char *buffer, unsigned size, - unsigned char type, void **ptr); + unsigned char type, void **ptr, size_t min); #define usb_get_extra_descriptor(ifpoint, type, ptr) \ __usb_get_extra_descriptor((ifpoint)->extra, \ (ifpoint)->extralen, \ - type, (void **)ptr) + type, (void **)ptr, sizeof(**(ptr))) /* ----------------------------------------------------------------------- */ -- cgit v1.2.3 From 2f0799a0ffc033bf3cc82d5032acc3ec633464c2 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Wed, 5 Dec 2018 15:45:54 -0800 Subject: mm, thp: restore node-local hugepage allocations This is a full revert of ac5b2c18911f ("mm: thp: relax __GFP_THISNODE for MADV_HUGEPAGE mappings") and a partial revert of 89c83fb539f9 ("mm, thp: consolidate THP gfp handling into alloc_hugepage_direct_gfpmask"). By not setting __GFP_THISNODE, applications can allocate remote hugepages when the local node is fragmented or low on memory when either the thp defrag setting is "always" or the vma has been madvised with MADV_HUGEPAGE. Remote access to hugepages often has much higher latency than local pages of the native page size. On Haswell, ac5b2c18911f was shown to have a 13.9% access regression after this commit for binaries that remap their text segment to be backed by transparent hugepages. The intent of ac5b2c18911f is to address an issue where a local node is low on memory or fragmented such that a hugepage cannot be allocated. In every scenario where this was described as a fix, there is abundant and unfragmented remote memory available to allocate from, even with a greater access latency. If remote memory is also low or fragmented, not setting __GFP_THISNODE was also measured on Haswell to have a 40% regression in allocation latency. Restore __GFP_THISNODE for thp allocations. Fixes: ac5b2c18911f ("mm: thp: relax __GFP_THISNODE for MADV_HUGEPAGE mappings") Fixes: 89c83fb539f9 ("mm, thp: consolidate THP gfp handling into alloc_hugepage_direct_gfpmask") Cc: Andrea Arcangeli Cc: Mel Gorman Cc: Vlastimil Babka Cc: Michal Hocko Cc: Andrew Morton Signed-off-by: David Rientjes Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 2 -- mm/huge_memory.c | 42 ++++++++++++++++-------------------------- mm/mempolicy.c | 2 +- 3 files changed, 17 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index bac395f1d00a..5228c62af416 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -139,8 +139,6 @@ struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, struct mempolicy *get_task_policy(struct task_struct *p); struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, unsigned long addr); -struct mempolicy *get_vma_policy(struct vm_area_struct *vma, - unsigned long addr); bool vma_policy_mof(struct vm_area_struct *vma); extern void numa_default_policy(void); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 622cced74fd9..f2d19e4fe854 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -632,37 +632,27 @@ release: static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma, unsigned long addr) { const bool vma_madvised = !!(vma->vm_flags & VM_HUGEPAGE); - gfp_t this_node = 0; - -#ifdef CONFIG_NUMA - struct mempolicy *pol; - /* - * __GFP_THISNODE is used only when __GFP_DIRECT_RECLAIM is not - * specified, to express a general desire to stay on the current - * node for optimistic allocation attempts. If the defrag mode - * and/or madvise hint requires the direct reclaim then we prefer - * to fallback to other node rather than node reclaim because that - * can lead to excessive reclaim even though there is free memory - * on other nodes. We expect that NUMA preferences are specified - * by memory policies. - */ - pol = get_vma_policy(vma, addr); - if (pol->mode != MPOL_BIND) - this_node = __GFP_THISNODE; - mpol_cond_put(pol); -#endif + const gfp_t gfp_mask = GFP_TRANSHUGE_LIGHT | __GFP_THISNODE; + /* Always do synchronous compaction */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags)) - return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY); + return GFP_TRANSHUGE | __GFP_THISNODE | + (vma_madvised ? 0 : __GFP_NORETRY); + + /* Kick kcompactd and fail quickly */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags)) - return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM | this_node; + return gfp_mask | __GFP_KSWAPD_RECLAIM; + + /* Synchronous compaction if madvised, otherwise kick kcompactd */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags)) - return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM : - __GFP_KSWAPD_RECLAIM | this_node); + return gfp_mask | (vma_madvised ? __GFP_DIRECT_RECLAIM : + __GFP_KSWAPD_RECLAIM); + + /* Only do synchronous compaction if madvised */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags)) - return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM : - this_node); - return GFP_TRANSHUGE_LIGHT | this_node; + return gfp_mask | (vma_madvised ? __GFP_DIRECT_RECLAIM : 0); + + return gfp_mask; } /* Caller must hold page table lock. */ diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 5837a067124d..69e278b469ef 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1662,7 +1662,7 @@ struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, * freeing by another task. It is the caller's responsibility to free the * extra reference for shared policies. */ -struct mempolicy *get_vma_policy(struct vm_area_struct *vma, +static struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr) { struct mempolicy *pol = __get_vma_policy(vma, addr); -- cgit v1.2.3 From 356ff8a9a78fb35d6482584d260c3754dcbdf669 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Fri, 7 Dec 2018 14:50:16 -0800 Subject: Revert "mm, thp: consolidate THP gfp handling into alloc_hugepage_direct_gfpmask" This reverts commit 89c83fb539f95491be80cdd5158e6f0ce329e317. This should have been done as part of 2f0799a0ffc0 ("mm, thp: restore node-local hugepage allocations"). The movement of the thp allocation policy from alloc_pages_vma() to alloc_hugepage_direct_gfpmask() was intended to only set __GFP_THISNODE for mempolicies that are not MPOL_BIND whereas the revert could set this regardless of mempolicy. While the check for MPOL_BIND between alloc_hugepage_direct_gfpmask() and alloc_pages_vma() was racy, that has since been removed since the revert. What is left is the possibility to use __GFP_THISNODE in policy_node() when it is unexpected because the special handling for hugepages in alloc_pages_vma() was removed as part of the consolidation. Secondly, prior to 89c83fb539f9, alloc_pages_vma() implemented a somewhat different policy for hugepage allocations, which were allocated through alloc_hugepage_vma(). For hugepage allocations, if the allocating process's node is in the set of allowed nodes, allocate with __GFP_THISNODE for that node (for MPOL_PREFERRED, use that node with __GFP_THISNODE instead). This was changed for shmem_alloc_hugepage() to allow fallback to other nodes in 89c83fb539f9 as it did for new_page() in mm/mempolicy.c which is functionally different behavior and removes the requirement to only allocate hugepages locally. So this commit does a full revert of 89c83fb539f9 instead of the partial revert that was done in 2f0799a0ffc0. The result is the same thp allocation policy for 4.20 that was in 4.19. Fixes: 89c83fb539f9 ("mm, thp: consolidate THP gfp handling into alloc_hugepage_direct_gfpmask") Fixes: 2f0799a0ffc0 ("mm, thp: restore node-local hugepage allocations") Signed-off-by: David Rientjes Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Mel Gorman Cc: Michal Hocko Cc: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 12 ++++++++---- mm/huge_memory.c | 27 +++++++++++++-------------- mm/mempolicy.c | 32 +++++++++++++++++++++++++++++--- mm/shmem.c | 2 +- 4 files changed, 51 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 76f8db0b0e71..0705164f928c 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -510,18 +510,22 @@ alloc_pages(gfp_t gfp_mask, unsigned int order) } extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr, - int node); + int node, bool hugepage); +#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ + alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true) #else #define alloc_pages(gfp_mask, order) \ alloc_pages_node(numa_node_id(), gfp_mask, order) -#define alloc_pages_vma(gfp_mask, order, vma, addr, node)\ +#define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\ + alloc_pages(gfp_mask, order) +#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ alloc_pages(gfp_mask, order) #endif #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) #define alloc_page_vma(gfp_mask, vma, addr) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id()) + alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false) #define alloc_page_vma_node(gfp_mask, vma, addr, node) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, node) + alloc_pages_vma(gfp_mask, 0, vma, addr, node, false) extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); extern unsigned long get_zeroed_page(gfp_t gfp_mask); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index f2d19e4fe854..5da55b38b1b7 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -629,30 +629,30 @@ release: * available * never: never stall for any thp allocation */ -static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma, unsigned long addr) +static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma) { const bool vma_madvised = !!(vma->vm_flags & VM_HUGEPAGE); - const gfp_t gfp_mask = GFP_TRANSHUGE_LIGHT | __GFP_THISNODE; /* Always do synchronous compaction */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags)) - return GFP_TRANSHUGE | __GFP_THISNODE | - (vma_madvised ? 0 : __GFP_NORETRY); + return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY); /* Kick kcompactd and fail quickly */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags)) - return gfp_mask | __GFP_KSWAPD_RECLAIM; + return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM; /* Synchronous compaction if madvised, otherwise kick kcompactd */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags)) - return gfp_mask | (vma_madvised ? __GFP_DIRECT_RECLAIM : - __GFP_KSWAPD_RECLAIM); + return GFP_TRANSHUGE_LIGHT | + (vma_madvised ? __GFP_DIRECT_RECLAIM : + __GFP_KSWAPD_RECLAIM); /* Only do synchronous compaction if madvised */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags)) - return gfp_mask | (vma_madvised ? __GFP_DIRECT_RECLAIM : 0); + return GFP_TRANSHUGE_LIGHT | + (vma_madvised ? __GFP_DIRECT_RECLAIM : 0); - return gfp_mask; + return GFP_TRANSHUGE_LIGHT; } /* Caller must hold page table lock. */ @@ -724,8 +724,8 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) pte_free(vma->vm_mm, pgtable); return ret; } - gfp = alloc_hugepage_direct_gfpmask(vma, haddr); - page = alloc_pages_vma(gfp, HPAGE_PMD_ORDER, vma, haddr, numa_node_id()); + gfp = alloc_hugepage_direct_gfpmask(vma); + page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER); if (unlikely(!page)) { count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; @@ -1295,9 +1295,8 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd) alloc: if (transparent_hugepage_enabled(vma) && !transparent_hugepage_debug_cow()) { - huge_gfp = alloc_hugepage_direct_gfpmask(vma, haddr); - new_page = alloc_pages_vma(huge_gfp, HPAGE_PMD_ORDER, vma, - haddr, numa_node_id()); + huge_gfp = alloc_hugepage_direct_gfpmask(vma); + new_page = alloc_hugepage_vma(huge_gfp, vma, haddr, HPAGE_PMD_ORDER); } else new_page = NULL; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 69e278b469ef..d4496d9d34f5 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1116,8 +1116,8 @@ static struct page *new_page(struct page *page, unsigned long start) } else if (PageTransHuge(page)) { struct page *thp; - thp = alloc_pages_vma(GFP_TRANSHUGE, HPAGE_PMD_ORDER, vma, - address, numa_node_id()); + thp = alloc_hugepage_vma(GFP_TRANSHUGE, vma, address, + HPAGE_PMD_ORDER); if (!thp) return NULL; prep_transhuge_page(thp); @@ -2011,6 +2011,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, * @vma: Pointer to VMA or NULL if not available. * @addr: Virtual Address of the allocation. Must be inside the VMA. * @node: Which node to prefer for allocation (modulo policy). + * @hugepage: for hugepages try only the preferred node if possible * * This function allocates a page from the kernel page pool and applies * a NUMA policy associated with the VMA or the current process. @@ -2021,7 +2022,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, */ struct page * alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, - unsigned long addr, int node) + unsigned long addr, int node, bool hugepage) { struct mempolicy *pol; struct page *page; @@ -2039,6 +2040,31 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, goto out; } + if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hugepage)) { + int hpage_node = node; + + /* + * For hugepage allocation and non-interleave policy which + * allows the current node (or other explicitly preferred + * node) we only try to allocate from the current/preferred + * node and don't fall back to other nodes, as the cost of + * remote accesses would likely offset THP benefits. + * + * If the policy is interleave, or does not allow the current + * node in its nodemask, we allocate the standard way. + */ + if (pol->mode == MPOL_PREFERRED && !(pol->flags & MPOL_F_LOCAL)) + hpage_node = pol->v.preferred_node; + + nmask = policy_nodemask(gfp, pol); + if (!nmask || node_isset(hpage_node, *nmask)) { + mpol_cond_put(pol); + page = __alloc_pages_node(hpage_node, + gfp | __GFP_THISNODE, order); + goto out; + } + } + nmask = policy_nodemask(gfp, pol); preferred_nid = policy_node(gfp, pol, node); page = __alloc_pages_nodemask(gfp, order, preferred_nid, nmask); diff --git a/mm/shmem.c b/mm/shmem.c index cddc72ac44d8..921f80488bb3 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1439,7 +1439,7 @@ static struct page *shmem_alloc_hugepage(gfp_t gfp, shmem_pseudo_vma_init(&pvma, info, hindex); page = alloc_pages_vma(gfp | __GFP_COMP | __GFP_NORETRY | __GFP_NOWARN, - HPAGE_PMD_ORDER, &pvma, 0, numa_node_id()); + HPAGE_PMD_ORDER, &pvma, 0, numa_node_id(), true); shmem_pseudo_vma_destroy(&pvma); if (page) prep_transhuge_page(page); -- cgit v1.2.3