From 26e08a6da54c575c69a113ab0c41c2890c0d613d Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 4 Dec 2020 21:02:42 +0100 Subject: dma-buf: Fix kerneldoc formatting I wanted to look up something and noticed the hyperlink doesn't work. While fixing that also noticed a trivial kerneldoc comment typo in the same section, fix that too. Reviewed-by: Michael J. Ruhl Reviewed-by: Simon Ser Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20201204200242.2671481-1-daniel.vetter@ffwll.ch --- include/linux/dma-buf-map.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dma-buf-map.h b/include/linux/dma-buf-map.h index 583a3a1f9447..278d489e4bdd 100644 --- a/include/linux/dma-buf-map.h +++ b/include/linux/dma-buf-map.h @@ -122,7 +122,7 @@ struct dma_buf_map { /** * DMA_BUF_MAP_INIT_VADDR - Initializes struct dma_buf_map to an address in system memory - * @vaddr: A system-memory address + * @vaddr_: A system-memory address */ #define DMA_BUF_MAP_INIT_VADDR(vaddr_) \ { \ -- cgit v1.2.3 From de9114ece5dfcc422164a24a687785843ed92c47 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 11 Dec 2020 16:58:40 +0100 Subject: dma-buf: Remove kmap kerneldoc vestiges MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Also try to clarify a bit when dma_buf_begin/end_cpu_access should be called. Acked-by: Christian König Signed-off-by: Daniel Vetter Cc: Thomas Zimmermann Cc: Sumit Semwal Cc: "Christian König" Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Link: https://patchwork.freedesktop.org/patch/msgid/20201211155843.3348718-1-daniel.vetter@ffwll.ch --- include/linux/dma-buf.h | 25 +++++++++---------------- 1 file changed, 9 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index cf72699cb2bc..7eca37c8b10c 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -183,24 +183,19 @@ struct dma_buf_ops { * @begin_cpu_access: * * This is called from dma_buf_begin_cpu_access() and allows the - * exporter to ensure that the memory is actually available for cpu - * access - the exporter might need to allocate or swap-in and pin the - * backing storage. The exporter also needs to ensure that cpu access is - * coherent for the access direction. The direction can be used by the - * exporter to optimize the cache flushing, i.e. access with a different + * exporter to ensure that the memory is actually coherent for cpu + * access. The exporter also needs to ensure that cpu access is coherent + * for the access direction. The direction can be used by the exporter + * to optimize the cache flushing, i.e. access with a different * direction (read instead of write) might return stale or even bogus * data (e.g. when the exporter needs to copy the data to temporary * storage). * - * This callback is optional. + * Note that this is both called through the DMA_BUF_IOCTL_SYNC IOCTL + * command for userspace mappings established through @mmap, and also + * for kernel mappings established with @vmap. * - * FIXME: This is both called through the DMA_BUF_IOCTL_SYNC command - * from userspace (where storage shouldn't be pinned to avoid handing - * de-factor mlock rights to userspace) and for the kernel-internal - * users of the various kmap interfaces, where the backing storage must - * be pinned to guarantee that the atomic kmap calls can succeed. Since - * there's no in-kernel users of the kmap interfaces yet this isn't a - * real problem. + * This callback is optional. * * Returns: * @@ -216,9 +211,7 @@ struct dma_buf_ops { * * This is called from dma_buf_end_cpu_access() when the importer is * done accessing the CPU. The exporter can use this to flush caches and - * unpin any resources pinned in @begin_cpu_access. - * The result of any dma_buf kmap calls after end_cpu_access is - * undefined. + * undo anything else done in @begin_cpu_access. * * This callback is optional. * -- cgit v1.2.3 From 85804b70cca68d77bca419b493ab843bf710de68 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 11 Dec 2020 16:58:41 +0100 Subject: dma-buf: some kerneldoc formatting fixes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Noticed while reviewing the output. Adds a bunch more links and fixes the function interface quoting. Acked-by: Christian König Signed-off-by: Daniel Vetter Cc: Thomas Zimmermann Cc: Sumit Semwal Cc: "Christian König" Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Link: https://patchwork.freedesktop.org/patch/msgid/20201211155843.3348718-2-daniel.vetter@ffwll.ch --- include/linux/dma-buf.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 7eca37c8b10c..43802a31b25d 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -85,10 +85,10 @@ struct dma_buf_ops { /** * @pin: * - * This is called by dma_buf_pin and lets the exporter know that the + * This is called by dma_buf_pin() and lets the exporter know that the * DMA-buf can't be moved any more. * - * This is called with the dmabuf->resv object locked and is mutual + * This is called with the &dmabuf.resv object locked and is mutual * exclusive with @cache_sgt_mapping. * * This callback is optional and should only be used in limited use @@ -103,7 +103,7 @@ struct dma_buf_ops { /** * @unpin: * - * This is called by dma_buf_unpin and lets the exporter know that the + * This is called by dma_buf_unpin() and lets the exporter know that the * DMA-buf can be moved again. * * This is called with the dmabuf->resv object locked and is mutual -- cgit v1.2.3 From c545781e1c55ab680dcc49c37212d5327b9d6812 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 11 Dec 2020 16:58:43 +0100 Subject: dma-buf: doc polish for pin/unpin MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Motivated by a discussion with Christian and Thomas: Try to untangle a bit what's relevant for importers and what's relevant for exporters. Also add an assert that really only dynamic importers use the api function, anything else doesn't make sense. Acked-by: Christian König Signed-off-by: Daniel Vetter Cc: Thomas Zimmermann Cc: Sumit Semwal Cc: "Christian König" Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Link: https://patchwork.freedesktop.org/patch/msgid/20201211155843.3348718-4-daniel.vetter@ffwll.ch --- include/linux/dma-buf.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 43802a31b25d..628681bf6c99 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -86,13 +86,15 @@ struct dma_buf_ops { * @pin: * * This is called by dma_buf_pin() and lets the exporter know that the - * DMA-buf can't be moved any more. + * DMA-buf can't be moved any more. The exporter should pin the buffer + * into system memory to make sure it is generally accessible by other + * devices. * * This is called with the &dmabuf.resv object locked and is mutual * exclusive with @cache_sgt_mapping. * - * This callback is optional and should only be used in limited use - * cases like scanout and not for temporary pin operations. + * This is called automatically for non-dynamic importers from + * dma_buf_attach(). * * Returns: * -- cgit v1.2.3 From 2ee5f8f05949735fa2f4c463a5e13fcb3660c719 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Tue, 8 Dec 2020 17:41:42 +0100 Subject: units: Add Watt units As there are the temperature units, let's add the Watt macros definition. Signed-off-by: Daniel Lezcano Reviewed-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- include/linux/units.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/units.h b/include/linux/units.h index aaf716364ec3..92c234e71cab 100644 --- a/include/linux/units.h +++ b/include/linux/units.h @@ -4,6 +4,10 @@ #include +#define MILLIWATT_PER_WATT 1000L +#define MICROWATT_PER_MILLIWATT 1000L +#define MICROWATT_PER_WATT 1000000L + #define ABSOLUTE_ZERO_MILLICELSIUS -273150 static inline long milli_kelvin_to_millicelsius(long t) -- cgit v1.2.3 From a20d0ef97abf486a917aff066c457bdb930425af Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Tue, 8 Dec 2020 17:41:44 +0100 Subject: powercap/drivers/dtpm: Add API for dynamic thermal power management On the embedded world, the complexity of the SoC leads to an increasing number of hotspots which need to be monitored and mitigated as a whole in order to prevent the temperature to go above the normative and legally stated 'skin temperature'. Another aspect is to sustain the performance for a given power budget, for example virtual reality where the user can feel dizziness if the GPU performance is capped while a big CPU is processing something else. Or reduce the battery charging because the dissipated power is too high compared with the power consumed by other devices. The userspace is the most adequate place to dynamically act on the different devices by limiting their power given an application profile: it has the knowledge of the platform. These userspace daemons are in charge of the Dynamic Thermal Power Management (DTPM). Nowadays, the dtpm daemons are abusing the thermal framework as they act on the cooling device state to force a specific and arbitrary state without taking care of the governor decisions. Given the closed loop of some governors that can confuse the logic or directly enter in a decision conflict. As the number of cooling device support is limited today to the CPU and the GPU, the dtpm daemons have little control on the power dissipation of the system. The out of tree solutions are hacking around here and there in the drivers, in the frameworks to have control on the devices. The common solution is to declare them as cooling devices. There is no unification of the power limitation unit, opaque states are used. This patch provides a way to create a hierarchy of constraints using the powercap framework. The devices which are registered as power limit-able devices are represented in this hierarchy as a tree. They are linked together with intermediate nodes which are just there to propagate the constraint to the children. The leaves of the tree are the real devices, the intermediate nodes are virtual, aggregating the children constraints and power characteristics. Each node have a weight on a 2^10 basis, in order to reflect the percentage of power distribution of the children's node. This percentage is used to dispatch the power limit to the children. The weight is computed against the max power of the siblings. This simple approach allows to do a fair distribution of the power limit. Signed-off-by: Daniel Lezcano Reviewed-by: Lukasz Luba Tested-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- include/linux/dtpm.h | 75 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 75 insertions(+) create mode 100644 include/linux/dtpm.h (limited to 'include/linux') diff --git a/include/linux/dtpm.h b/include/linux/dtpm.h new file mode 100644 index 000000000000..7a1d0b50e334 --- /dev/null +++ b/include/linux/dtpm.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 Linaro Ltd + * + * Author: Daniel Lezcano + */ +#ifndef ___DTPM_H__ +#define ___DTPM_H__ + +#include + +#define MAX_DTPM_DESCR 8 +#define MAX_DTPM_CONSTRAINTS 1 + +struct dtpm { + struct powercap_zone zone; + struct dtpm *parent; + struct list_head sibling; + struct list_head children; + struct dtpm_ops *ops; + unsigned long flags; + u64 power_limit; + u64 power_max; + u64 power_min; + int weight; + void *private; +}; + +struct dtpm_ops { + u64 (*set_power_uw)(struct dtpm *, u64); + u64 (*get_power_uw)(struct dtpm *); + void (*release)(struct dtpm *); +}; + +struct dtpm_descr; + +typedef int (*dtpm_init_t)(struct dtpm_descr *); + +struct dtpm_descr { + struct dtpm *parent; + const char *name; + dtpm_init_t init; +}; + +/* Init section thermal table */ +extern struct dtpm_descr *__dtpm_table[]; +extern struct dtpm_descr *__dtpm_table_end[]; + +#define DTPM_TABLE_ENTRY(name) \ + static typeof(name) *__dtpm_table_entry_##name \ + __used __section("__dtpm_table") = &name + +#define DTPM_DECLARE(name) DTPM_TABLE_ENTRY(name) + +#define for_each_dtpm_table(__dtpm) \ + for (__dtpm = __dtpm_table; \ + __dtpm < __dtpm_table_end; \ + __dtpm++) + +static inline struct dtpm *to_dtpm(struct powercap_zone *zone) +{ + return container_of(zone, struct dtpm, zone); +} + +int dtpm_update_power(struct dtpm *dtpm, u64 power_min, u64 power_max); + +int dtpm_release_zone(struct powercap_zone *pcz); + +struct dtpm *dtpm_alloc(struct dtpm_ops *ops); + +void dtpm_unregister(struct dtpm *dtpm); + +int dtpm_register(const char *name, struct dtpm *dtpm, struct dtpm *parent); + +#endif -- cgit v1.2.3 From 0e8f68d7f04856a9e2ad4817b477fa35124888bd Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Tue, 8 Dec 2020 17:41:45 +0100 Subject: powercap/drivers/dtpm: Add CPU energy model based support With the powercap dtpm controller, we are able to plug devices with power limitation features in the tree. The following patch introduces the CPU power limitation based on the energy model and the performance states. The power limitation is done at the performance domain level. If some CPUs are unplugged, the corresponding power will be subtracted from the performance domain total power. It is up to the platform to initialize the dtpm tree and add the CPU. Here is an example to create a simple tree with one root node called "pkg" and the CPU's performance domains. static int dtpm_register_pkg(struct dtpm_descr *descr) { struct dtpm *pkg; int ret; pkg = dtpm_alloc(NULL); if (!pkg) return -ENOMEM; ret = dtpm_register(descr->name, pkg, descr->parent); if (ret) return ret; return dtpm_register_cpu(pkg); } static struct dtpm_descr descr = { .name = "pkg", .init = dtpm_register_pkg, }; DTPM_DECLARE(descr); Signed-off-by: Daniel Lezcano Reviewed-by: Lukasz Luba Tested-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- include/linux/cpuhotplug.h | 1 + include/linux/dtpm.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 0042ef362511..ee09a39627d6 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -193,6 +193,7 @@ enum cpuhp_state { CPUHP_AP_ONLINE_DYN_END = CPUHP_AP_ONLINE_DYN + 30, CPUHP_AP_X86_HPET_ONLINE, CPUHP_AP_X86_KVM_CLK_ONLINE, + CPUHP_AP_DTPM_CPU_ONLINE, CPUHP_AP_ACTIVE, CPUHP_ONLINE, }; diff --git a/include/linux/dtpm.h b/include/linux/dtpm.h index 7a1d0b50e334..e80a332e3d8a 100644 --- a/include/linux/dtpm.h +++ b/include/linux/dtpm.h @@ -72,4 +72,6 @@ void dtpm_unregister(struct dtpm *dtpm); int dtpm_register(const char *name, struct dtpm *dtpm, struct dtpm *parent); +int dtpm_register_cpu(struct dtpm *parent); + #endif -- cgit v1.2.3 From f7005142dacea1769fba0152c493aaa61b33205c Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Mon, 21 Dec 2020 17:29:34 +0200 Subject: spi: uapi: unify SPI modes into a single spi.h header This change moves all the SPI mode bits into a separate 'spi.h' header in uAPI. This is meant to re-use these definitions inside the kernel as well as export them to userspace (via uAPI). The SPI mode definitions have usually been duplicated between between 'include/linux/spi/spi.h' and 'include/uapi/linux/spi/spidev.h', so whenever adding a new entry, this would need to be put in both headers. They've been moved from 'include/linux/spi/spi.h', since that seems a bit more complete; the bits have descriptions and there is the SPI_MODE_X_MASK. This change also does a conversion of these bitfields to _BITUL() macro. Reviewed-by: Andy Shevchenko Signed-off-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20201221152936.53873-1-alexandru.ardelean@analog.com Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 23 ++--------------------- 1 file changed, 2 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index aa09fdc8042d..a08c3f37e202 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -15,6 +15,8 @@ #include #include +#include + struct dma_chan; struct property_entry; struct spi_controller; @@ -165,27 +167,6 @@ struct spi_device { u8 bits_per_word; bool rt; u32 mode; -#define SPI_CPHA 0x01 /* clock phase */ -#define SPI_CPOL 0x02 /* clock polarity */ -#define SPI_MODE_0 (0|0) /* (original MicroWire) */ -#define SPI_MODE_1 (0|SPI_CPHA) -#define SPI_MODE_2 (SPI_CPOL|0) -#define SPI_MODE_3 (SPI_CPOL|SPI_CPHA) -#define SPI_MODE_X_MASK (SPI_CPOL|SPI_CPHA) -#define SPI_CS_HIGH 0x04 /* chipselect active high? */ -#define SPI_LSB_FIRST 0x08 /* per-word bits-on-wire */ -#define SPI_3WIRE 0x10 /* SI/SO signals shared */ -#define SPI_LOOP 0x20 /* loopback mode */ -#define SPI_NO_CS 0x40 /* 1 dev/bus, no chipselect */ -#define SPI_READY 0x80 /* slave pulls low to pause */ -#define SPI_TX_DUAL 0x100 /* transmit with 2 wires */ -#define SPI_TX_QUAD 0x200 /* transmit with 4 wires */ -#define SPI_RX_DUAL 0x400 /* receive with 2 wires */ -#define SPI_RX_QUAD 0x800 /* receive with 4 wires */ -#define SPI_CS_WORD 0x1000 /* toggle cs after each word */ -#define SPI_TX_OCTAL 0x2000 /* transmit with 8 wires */ -#define SPI_RX_OCTAL 0x4000 /* receive with 8 wires */ -#define SPI_3WIRE_HIZ 0x8000 /* high impedance turnaround */ int irq; void *controller_state; void *controller_data; -- cgit v1.2.3 From d962608ce2188a1d46ec9d356d6fad5cd6fc0341 Mon Sep 17 00:00:00 2001 From: Dragos Bogdan Date: Mon, 21 Dec 2020 17:29:35 +0200 Subject: spi: Add SPI_NO_TX/RX support Transmit/receive only is a valid SPI mode. For example, the MOSI/TX line might be missing from an ADC while for a DAC the MISO/RX line may be optional. This patch adds these two new modes: SPI_NO_TX and SPI_NO_RX. This way, the drivers will be able to identify if any of these two lines is missing and to adjust the transfers accordingly. Signed-off-by: Dragos Bogdan Signed-off-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20201221152936.53873-2-alexandru.ardelean@analog.com Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index a08c3f37e202..9bfdfaf286eb 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -6,6 +6,7 @@ #ifndef __LINUX_SPI_H #define __LINUX_SPI_H +#include #include #include #include @@ -166,6 +167,18 @@ struct spi_device { u8 chip_select; u8 bits_per_word; bool rt; +#define SPI_NO_TX BIT(31) /* no transmit wire */ +#define SPI_NO_RX BIT(30) /* no receive wire */ + /* + * All bits defined above should be covered by SPI_MODE_KERNEL_MASK. + * The SPI_MODE_KERNEL_MASK has the SPI_MODE_USER_MASK counterpart, + * which is defined in 'include/uapi/linux/spi/spi.h'. + * The bits defined here are from bit 31 downwards, while in + * SPI_MODE_USER_MASK are from 0 upwards. + * These bits must not overlap. A static assert check should make sure of that. + * If adding extra bits, make sure to decrease the bit index below as well. + */ +#define SPI_MODE_KERNEL_MASK (~(BIT(30) - 1)) u32 mode; int irq; void *controller_state; @@ -189,6 +202,10 @@ struct spi_device { */ }; +/* Make sure that SPI_MODE_KERNEL_MASK & SPI_MODE_USER_MASK don't overlap */ +static_assert((SPI_MODE_KERNEL_MASK & SPI_MODE_USER_MASK) == 0, + "SPI_MODE_USER_MASK & SPI_MODE_KERNEL_MASK must not overlap"); + static inline struct spi_device *to_spi_device(struct device *dev) { return dev ? container_of(dev, struct spi_device, dev) : NULL; -- cgit v1.2.3 From 4ea3cd65e0d47c4d3fc0c86d2d93d97457dc86fb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 18 Dec 2020 11:42:44 +0100 Subject: tty: rename tty_kopen() and add new function tty_kopen_shared() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduce a new function tty_kopen_shared() that yields a struct tty_struct. The semantic difference to tty_kopen() is that the tty is expected to be used already. So rename tty_kopen() to tty_kopen_exclusive() for clearness, adapt the single user and put the common code in a new static helper function. tty_kopen_shared is to be used to implement an LED trigger for tty devices in one of the next patches. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20201218104246.591315-2-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index c873f475f0a7..df707a5abfac 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -416,7 +416,8 @@ extern struct tty_struct *get_current_tty(void); /* tty_io.c */ extern int __init tty_init(void); extern const char *tty_name(const struct tty_struct *tty); -extern struct tty_struct *tty_kopen(dev_t device); +extern struct tty_struct *tty_kopen_exclusive(dev_t device); +extern struct tty_struct *tty_kopen_shared(dev_t device); extern void tty_kclose(struct tty_struct *tty); extern int tty_dev_name_to_number(const char *name, dev_t *number); extern int tty_ldisc_lock(struct tty_struct *tty, unsigned long timeout); @@ -441,7 +442,7 @@ static inline int __init tty_init(void) { return 0; } static inline const char *tty_name(const struct tty_struct *tty) { return "(none)"; } -static inline struct tty_struct *tty_kopen(dev_t device) +static inline struct tty_struct *tty_kopen_exclusive(dev_t device) { return ERR_PTR(-ENODEV); } static inline void tty_kclose(struct tty_struct *tty) { } -- cgit v1.2.3 From d20c219c7317843cec7f03eba15bfeae54f29654 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 18 Dec 2020 11:42:45 +0100 Subject: tty: new helper function tty_get_icount() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit For a given struct tty_struct this yields the corresponding statistics about sent and received characters (and some more) which is needed to implement an LED trigger for tty devices. The new function is then used to simplify tty_tiocgicount(). Reviewed-by: Pavel Machek Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20201218104246.591315-3-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index df707a5abfac..12be8b16cdef 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -500,6 +500,8 @@ extern void tty_unthrottle(struct tty_struct *tty); extern int tty_throttle_safe(struct tty_struct *tty); extern int tty_unthrottle_safe(struct tty_struct *tty); extern int tty_do_resize(struct tty_struct *tty, struct winsize *ws); +extern int tty_get_icount(struct tty_struct *tty, + struct serial_icounter_struct *icount); extern int is_current_pgrp_orphaned(void); extern void tty_hangup(struct tty_struct *tty); extern void tty_vhangup(struct tty_struct *tty); -- cgit v1.2.3 From 916c0c05521a52f13283ad3600793fc79516ff31 Mon Sep 17 00:00:00 2001 From: Sai Prakash Ranjan Date: Mon, 30 Nov 2020 15:09:23 +0530 Subject: soc: qcom: llcc-qcom: Extract major hardware version The major hardware version of the LLCC IP is encoded in its LLCC_COMMON_HW_INFO register. Extract the version and cache it in the driver data so that it can be used to implement version specific functionality like enabling Write sub cache for given SCID. Signed-off-by: Sai Prakash Ranjan [mani: splitted the version extract as a single patch and few cleanups] Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20201130093924.45057-4-manivannan.sadhasivam@linaro.org Signed-off-by: Bjorn Andersson --- include/linux/soc/qcom/llcc-qcom.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h index 3db6797ba6ff..d17a3de80510 100644 --- a/include/linux/soc/qcom/llcc-qcom.h +++ b/include/linux/soc/qcom/llcc-qcom.h @@ -79,6 +79,7 @@ struct llcc_edac_reg_data { * @bitmap: Bit map to track the active slice ids * @offsets: Pointer to the bank offsets array * @ecc_irq: interrupt for llcc cache error detection and reporting + * @major_version: Indicates the LLCC major version */ struct llcc_drv_data { struct regmap *regmap; @@ -91,6 +92,7 @@ struct llcc_drv_data { unsigned long *bitmap; u32 *offsets; int ecc_irq; + u32 major_version; }; #if IS_ENABLED(CONFIG_QCOM_LLCC) -- cgit v1.2.3 From c4df37fe186de4df8895a7a4793f5221eda6e5ae Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Mon, 30 Nov 2020 15:09:24 +0530 Subject: soc: qcom: llcc-qcom: Add support for SM8250 SoC SM8250 SoC uses LLCC IP version 2. In this version, the WRSC_EN register needs to be written to enable the Write Sub Cache for each SCID. Hence, use a dedicated "write_scid_en" member with predefined values and write them for LLCC IP version 2. Reviewed-by: Sai Prakash Ranjan Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20201130093924.45057-5-manivannan.sadhasivam@linaro.org Signed-off-by: Bjorn Andersson --- include/linux/soc/qcom/llcc-qcom.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h index d17a3de80510..64fc582ae415 100644 --- a/include/linux/soc/qcom/llcc-qcom.h +++ b/include/linux/soc/qcom/llcc-qcom.h @@ -29,6 +29,7 @@ #define LLCC_AUDHW 22 #define LLCC_NPU 23 #define LLCC_WLHW 24 +#define LLCC_CVP 28 #define LLCC_MODPE 29 #define LLCC_APTCM 30 #define LLCC_WRCACHE 31 -- cgit v1.2.3 From a2ff95e018f1d2bc816f3078d5110a655e355f18 Mon Sep 17 00:00:00 2001 From: Mark Pearson Date: Tue, 29 Dec 2020 19:18:26 -0500 Subject: ACPI: platform: Add platform profile support This is the initial implementation of the platform-profile feature. It provides the details discussed and outlined in the sysfs-platform_profile document. Many modern systems have the ability to modify the operating profile to control aspects like fan speed, temperature and power levels. This module provides a common sysfs interface that platform modules can register against to control their individual profile options. Signed-off-by: Mark Pearson Reviewed-by: Hans de Goede [ rjw: Use full words in enum values names ] Signed-off-by: Rafael J. Wysocki --- include/linux/platform_profile.h | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) create mode 100644 include/linux/platform_profile.h (limited to 'include/linux') diff --git a/include/linux/platform_profile.h b/include/linux/platform_profile.h new file mode 100644 index 000000000000..3623d7108421 --- /dev/null +++ b/include/linux/platform_profile.h @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Platform profile sysfs interface + * + * See Documentation/ABI/testing/sysfs-platform_profile.rst for more + * information. + */ + +#ifndef _PLATFORM_PROFILE_H_ +#define _PLATFORM_PROFILE_H_ + +#include + +/* + * If more options are added please update profile_names + * array in platform-profile.c and sysfs-platform-profile.rst + * documentation. + */ + +enum platform_profile_option { + PLATFORM_PROFILE_LOW_POWER, + PLATFORM_PROFILE_COOL, + PLATFORM_PROFILE_QUIET, + PLATFORM_PROFILE_BALANCED, + PLATFORM_PROFILE_PERFORMANCE, + PLATFORM_PROFILE_LAST, /*must always be last */ +}; + +struct platform_profile_handler { + unsigned long choices[BITS_TO_LONGS(PLATFORM_PROFILE_LAST)]; + int (*profile_get)(enum platform_profile_option *profile); + int (*profile_set)(enum platform_profile_option profile); +}; + +int platform_profile_register(const struct platform_profile_handler *pprof); +int platform_profile_remove(void); +void platform_profile_notify(void); + +#endif /*_PLATFORM_PROFILE_H_*/ -- cgit v1.2.3 From 0eb76ba29d16df2951d37c54ca279c4e5630b071 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 11 Dec 2020 13:27:15 +0100 Subject: crypto: remove cipher routines from public crypto API The cipher routines in the crypto API are mostly intended for templates implementing skcipher modes generically in software, and shouldn't be used outside of the crypto subsystem. So move the prototypes and all related definitions to a new header file under include/crypto/internal. Also, let's use the new module namespace feature to move the symbol exports into a new namespace CRYPTO_INTERNAL. Signed-off-by: Ard Biesheuvel Acked-by: Eric Biggers Signed-off-by: Herbert Xu --- include/linux/crypto.h | 163 ------------------------------------------------- 1 file changed, 163 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index ef90e07c9635..9b55cd6b1f1b 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -636,10 +636,6 @@ struct crypto_tfm { void *__crt_ctx[] CRYPTO_MINALIGN_ATTR; }; -struct crypto_cipher { - struct crypto_tfm base; -}; - struct crypto_comp { struct crypto_tfm base; }; @@ -743,165 +739,6 @@ static inline unsigned int crypto_tfm_ctx_alignment(void) return __alignof__(tfm->__crt_ctx); } -/** - * DOC: Single Block Cipher API - * - * The single block cipher API is used with the ciphers of type - * CRYPTO_ALG_TYPE_CIPHER (listed as type "cipher" in /proc/crypto). - * - * Using the single block cipher API calls, operations with the basic cipher - * primitive can be implemented. These cipher primitives exclude any block - * chaining operations including IV handling. - * - * The purpose of this single block cipher API is to support the implementation - * of templates or other concepts that only need to perform the cipher operation - * on one block at a time. Templates invoke the underlying cipher primitive - * block-wise and process either the input or the output data of these cipher - * operations. - */ - -static inline struct crypto_cipher *__crypto_cipher_cast(struct crypto_tfm *tfm) -{ - return (struct crypto_cipher *)tfm; -} - -/** - * crypto_alloc_cipher() - allocate single block cipher handle - * @alg_name: is the cra_name / name or cra_driver_name / driver name of the - * single block cipher - * @type: specifies the type of the cipher - * @mask: specifies the mask for the cipher - * - * Allocate a cipher handle for a single block cipher. The returned struct - * crypto_cipher is the cipher handle that is required for any subsequent API - * invocation for that single block cipher. - * - * Return: allocated cipher handle in case of success; IS_ERR() is true in case - * of an error, PTR_ERR() returns the error code. - */ -static inline struct crypto_cipher *crypto_alloc_cipher(const char *alg_name, - u32 type, u32 mask) -{ - type &= ~CRYPTO_ALG_TYPE_MASK; - type |= CRYPTO_ALG_TYPE_CIPHER; - mask |= CRYPTO_ALG_TYPE_MASK; - - return __crypto_cipher_cast(crypto_alloc_base(alg_name, type, mask)); -} - -static inline struct crypto_tfm *crypto_cipher_tfm(struct crypto_cipher *tfm) -{ - return &tfm->base; -} - -/** - * crypto_free_cipher() - zeroize and free the single block cipher handle - * @tfm: cipher handle to be freed - */ -static inline void crypto_free_cipher(struct crypto_cipher *tfm) -{ - crypto_free_tfm(crypto_cipher_tfm(tfm)); -} - -/** - * crypto_has_cipher() - Search for the availability of a single block cipher - * @alg_name: is the cra_name / name or cra_driver_name / driver name of the - * single block cipher - * @type: specifies the type of the cipher - * @mask: specifies the mask for the cipher - * - * Return: true when the single block cipher is known to the kernel crypto API; - * false otherwise - */ -static inline int crypto_has_cipher(const char *alg_name, u32 type, u32 mask) -{ - type &= ~CRYPTO_ALG_TYPE_MASK; - type |= CRYPTO_ALG_TYPE_CIPHER; - mask |= CRYPTO_ALG_TYPE_MASK; - - return crypto_has_alg(alg_name, type, mask); -} - -/** - * crypto_cipher_blocksize() - obtain block size for cipher - * @tfm: cipher handle - * - * The block size for the single block cipher referenced with the cipher handle - * tfm is returned. The caller may use that information to allocate appropriate - * memory for the data returned by the encryption or decryption operation - * - * Return: block size of cipher - */ -static inline unsigned int crypto_cipher_blocksize(struct crypto_cipher *tfm) -{ - return crypto_tfm_alg_blocksize(crypto_cipher_tfm(tfm)); -} - -static inline unsigned int crypto_cipher_alignmask(struct crypto_cipher *tfm) -{ - return crypto_tfm_alg_alignmask(crypto_cipher_tfm(tfm)); -} - -static inline u32 crypto_cipher_get_flags(struct crypto_cipher *tfm) -{ - return crypto_tfm_get_flags(crypto_cipher_tfm(tfm)); -} - -static inline void crypto_cipher_set_flags(struct crypto_cipher *tfm, - u32 flags) -{ - crypto_tfm_set_flags(crypto_cipher_tfm(tfm), flags); -} - -static inline void crypto_cipher_clear_flags(struct crypto_cipher *tfm, - u32 flags) -{ - crypto_tfm_clear_flags(crypto_cipher_tfm(tfm), flags); -} - -/** - * crypto_cipher_setkey() - set key for cipher - * @tfm: cipher handle - * @key: buffer holding the key - * @keylen: length of the key in bytes - * - * The caller provided key is set for the single block cipher referenced by the - * cipher handle. - * - * Note, the key length determines the cipher type. Many block ciphers implement - * different cipher modes depending on the key size, such as AES-128 vs AES-192 - * vs. AES-256. When providing a 16 byte key for an AES cipher handle, AES-128 - * is performed. - * - * Return: 0 if the setting of the key was successful; < 0 if an error occurred - */ -int crypto_cipher_setkey(struct crypto_cipher *tfm, - const u8 *key, unsigned int keylen); - -/** - * crypto_cipher_encrypt_one() - encrypt one block of plaintext - * @tfm: cipher handle - * @dst: points to the buffer that will be filled with the ciphertext - * @src: buffer holding the plaintext to be encrypted - * - * Invoke the encryption operation of one block. The caller must ensure that - * the plaintext and ciphertext buffers are at least one block in size. - */ -void crypto_cipher_encrypt_one(struct crypto_cipher *tfm, - u8 *dst, const u8 *src); - -/** - * crypto_cipher_decrypt_one() - decrypt one block of ciphertext - * @tfm: cipher handle - * @dst: points to the buffer that will be filled with the plaintext - * @src: buffer holding the ciphertext to be decrypted - * - * Invoke the decryption operation of one block. The caller must ensure that - * the plaintext and ciphertext buffers are at least one block in size. - */ -void crypto_cipher_decrypt_one(struct crypto_cipher *tfm, - u8 *dst, const u8 *src); - static inline struct crypto_comp *__crypto_comp_cast(struct crypto_tfm *tfm) { return (struct crypto_comp *)tfm; -- cgit v1.2.3 From 8280de6ab07b4c63eb607662754f151e539031a1 Mon Sep 17 00:00:00 2001 From: Wesley Cheng Date: Tue, 29 Dec 2020 15:03:30 -0800 Subject: usb: gadget: composite: Split composite reset and disconnect Add a specific composite reset API to differentiate between disconnect and reset events. This is needed for adjusting the current draw accordingly based on the USB battery charging specification. The device is only allowed to draw the 500/900 mA (HS/SS) while in the CONFIGURED state, and only 100 mA in the connected and UNCONFIGURED state. Reviewed-by: Peter Chen Signed-off-by: Wesley Cheng Link: https://lore.kernel.org/r/1609283011-21997-3-git-send-email-wcheng@codeaurora.org Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/composite.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index a2d229ab63ba..5646dad886e6 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -525,6 +525,8 @@ extern struct usb_string *usb_gstrings_attach(struct usb_composite_dev *cdev, extern int usb_string_ids_n(struct usb_composite_dev *c, unsigned n); extern void composite_disconnect(struct usb_gadget *gadget); +extern void composite_reset(struct usb_gadget *gadget); + extern int composite_setup(struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl); extern void composite_suspend(struct usb_gadget *gadget); -- cgit v1.2.3 From b5a8d233a588b3acf2a7a3a8da30f8f68f376626 Mon Sep 17 00:00:00 2001 From: Loic Poulain Date: Mon, 4 Jan 2021 17:14:50 +0100 Subject: bus: mhi: core: Add device hardware reset support The MHI specification allows to perform a hard reset of the device when writing to the SOC_RESET register. It can be used to completely restart the device (e.g. in case of unrecoverable MHI error). This is up to the MHI controller driver to determine when this hard reset should be used, and in case of MHI errors, should be used as a reset of last resort (after standard MHI stack reset). This function is a stateless function, the MHI layer do nothing except triggering the reset by writing into the right register(s), this is up to the caller to ensure right mhi_controller state (e.g. unregister the controller if necessary). Signed-off-by: Loic Poulain Reviewed-by: Manivannan Sadhasivam Signed-off-by: Manivannan Sadhasivam --- include/linux/mhi.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 562862ff819c..54afcae1709a 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -347,6 +347,7 @@ struct mhi_controller_config { * @unmap_single: CB function to destroy TRE buffer * @read_reg: Read a MHI register via the physical link (required) * @write_reg: Write a MHI register via the physical link (required) + * @reset: Controller specific reset function (optional) * @buffer_len: Bounce buffer length * @index: Index of the MHI controller instance * @bounce_buf: Use of bounce buffer @@ -437,6 +438,7 @@ struct mhi_controller { u32 *out); void (*write_reg)(struct mhi_controller *mhi_cntrl, void __iomem *addr, u32 val); + void (*reset)(struct mhi_controller *mhi_cntrl); size_t buffer_len; int index; @@ -672,6 +674,13 @@ enum mhi_ee_type mhi_get_exec_env(struct mhi_controller *mhi_cntrl); */ enum mhi_state mhi_get_mhi_state(struct mhi_controller *mhi_cntrl); +/** + * mhi_soc_reset - Trigger a device reset. This can be used as a last resort + * to reset and recover a device. + * @mhi_cntrl: MHI controller + */ +void mhi_soc_reset(struct mhi_controller *mhi_cntrl); + /** * mhi_device_get - Disable device low power mode * @mhi_dev: Device associated with the channel -- cgit v1.2.3 From 6c6ec2b0a3e0381d886d531bd1471dfdb1509237 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 17 Dec 2020 09:19:09 -0700 Subject: fs: add support for LOOKUP_CACHED io_uring always punts opens to async context, since there's no control over whether the lookup blocks or not. Add LOOKUP_CACHED to support just doing the fast RCU based lookups, which we know will not block. If we can do a cached path resolution of the filename, then we don't have to always punt lookups for a worker. During path resolution, we always do LOOKUP_RCU first. If that fails and we terminate LOOKUP_RCU, then fail a LOOKUP_CACHED attempt as well. Cc: Al Viro Signed-off-by: Jens Axboe Signed-off-by: Al Viro --- include/linux/namei.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index a4bb992623c4..b9605b2b46e7 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -46,6 +46,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT}; #define LOOKUP_NO_XDEV 0x040000 /* No mountpoint crossing. */ #define LOOKUP_BENEATH 0x080000 /* No escaping from starting point. */ #define LOOKUP_IN_ROOT 0x100000 /* Treat dirfd as fs root. */ +#define LOOKUP_CACHED 0x200000 /* Only do cached lookup */ /* LOOKUP_* flags which do scope-related checks based on the dirfd. */ #define LOOKUP_IS_SCOPED (LOOKUP_BENEATH | LOOKUP_IN_ROOT) -- cgit v1.2.3 From 99668f618062816ca7ba639b007eb145b9d3d41e Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 17 Dec 2020 09:19:10 -0700 Subject: fs: expose LOOKUP_CACHED through openat2() RESOLVE_CACHED Now that we support non-blocking path resolution internally, expose it via openat2() in the struct open_how ->resolve flags. This allows applications using openat2() to limit path resolution to the extent that it is already cached. If the lookup cannot be satisfied in a non-blocking manner, openat2(2) will return -1/-EAGAIN. Cc: Al Viro Signed-off-by: Jens Axboe Signed-off-by: Al Viro --- include/linux/fcntl.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h index 921e750843e6..766fcd973beb 100644 --- a/include/linux/fcntl.h +++ b/include/linux/fcntl.h @@ -19,7 +19,7 @@ /* List of all valid flags for the how->resolve argument: */ #define VALID_RESOLVE_FLAGS \ (RESOLVE_NO_XDEV | RESOLVE_NO_MAGICLINKS | RESOLVE_NO_SYMLINKS | \ - RESOLVE_BENEATH | RESOLVE_IN_ROOT) + RESOLVE_BENEATH | RESOLVE_IN_ROOT | RESOLVE_CACHED) /* List of all open_how "versions". */ #define OPEN_HOW_SIZE_VER0 24 /* sizeof first published struct */ -- cgit v1.2.3 From 14e43bf435612639cab01541fce7cc41bf7e370b Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 22 Sep 2020 09:44:18 -0700 Subject: vfs: don't unnecessarily clone write access for writable fds There's no need for mnt_want_write_file() to increment mnt_writers when the file is already open for writing, provided that mnt_drop_write_file() is changed to conditionally decrement it. We seem to have ended up in the current situation because mnt_want_write_file() used to be paired with mnt_drop_write(), due to mnt_drop_write_file() not having been added yet. So originally mnt_want_write_file() had to always increment mnt_writers. But later mnt_drop_write_file() was added, and all callers of mnt_want_write_file() were paired with it. This makes the compatibility between mnt_want_write_file() and mnt_drop_write() no longer necessary. Therefore, make __mnt_want_write_file() and __mnt_drop_write_file() skip incrementing mnt_writers on files already open for writing. This removes the only caller of mnt_clone_write(), so remove that too. Signed-off-by: Eric Biggers Signed-off-by: Al Viro --- include/linux/mount.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mount.h b/include/linux/mount.h index aaf343b38671..b43191fe6af7 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -79,7 +79,6 @@ struct path; extern int mnt_want_write(struct vfsmount *mnt); extern int mnt_want_write_file(struct file *file); -extern int mnt_clone_write(struct vfsmount *mnt); extern void mnt_drop_write(struct vfsmount *mnt); extern void mnt_drop_write_file(struct file *file); extern void mntput(struct vfsmount *mnt); -- cgit v1.2.3 From 4704bd317108c94b6e2d8309f3dbb70d2015568a Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 16 Nov 2020 11:18:16 +0100 Subject: list: Fix a typo at the kernel-doc markup hlist_add_behing -> hlist_add_behind Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Paul E. McKenney --- include/linux/list.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/list.h b/include/linux/list.h index 89bdc92e75c3..f2af4b4aa4e9 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -901,7 +901,7 @@ static inline void hlist_add_before(struct hlist_node *n, } /** - * hlist_add_behing - add a new entry after the one specified + * hlist_add_behind - add a new entry after the one specified * @n: new entry to be added * @prev: hlist node to add it after, which must be non-NULL */ -- cgit v1.2.3 From 5130b8fd06901c1b3a4bd0d0f5c5ea99b2b0a6f0 Mon Sep 17 00:00:00 2001 From: "Uladzislau Rezki (Sony)" Date: Fri, 20 Nov 2020 12:49:16 +0100 Subject: rcu: Introduce kfree_rcu() single-argument macro There is a kvfree_rcu() single argument macro that handles pointers returned by kvmalloc(). Even though it also handles pointer returned by kmalloc(), readability suffers. This commit therefore updates the kfree_rcu() macro to explicitly pair with kmalloc(), thus improving readability. Signed-off-by: Uladzislau Rezki (Sony) Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index de0826411311..b95373ea3b02 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -851,8 +851,9 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) /** * kfree_rcu() - kfree an object after a grace period. - * @ptr: pointer to kfree - * @rhf: the name of the struct rcu_head within the type of @ptr. + * @ptr: pointer to kfree for both single- and double-argument invocations. + * @rhf: the name of the struct rcu_head within the type of @ptr, + * but only for double-argument invocations. * * Many rcu callbacks functions just call kfree() on the base structure. * These functions are trivial, but their size adds up, and furthermore @@ -875,13 +876,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) * The BUILD_BUG_ON check must not involve any function calls, hence the * checks are done in macros here. */ -#define kfree_rcu(ptr, rhf) \ -do { \ - typeof (ptr) ___p = (ptr); \ - \ - if (___p) \ - __kvfree_rcu(&((___p)->rhf), offsetof(typeof(*(ptr)), rhf)); \ -} while (0) +#define kfree_rcu kvfree_rcu /** * kvfree_rcu() - kvfree an object after a grace period. @@ -913,7 +908,14 @@ do { \ kvfree_rcu_arg_2, kvfree_rcu_arg_1)(__VA_ARGS__) #define KVFREE_GET_MACRO(_1, _2, NAME, ...) NAME -#define kvfree_rcu_arg_2(ptr, rhf) kfree_rcu(ptr, rhf) +#define kvfree_rcu_arg_2(ptr, rhf) \ +do { \ + typeof (ptr) ___p = (ptr); \ + \ + if (___p) \ + __kvfree_rcu(&((___p)->rhf), offsetof(typeof(*(ptr)), rhf)); \ +} while (0) + #define kvfree_rcu_arg_1(ptr) \ do { \ typeof(ptr) ___p = (ptr); \ -- cgit v1.2.3 From 5ea5d1ed572cb5ac173674fe770252253d2d9e27 Mon Sep 17 00:00:00 2001 From: "Uladzislau Rezki (Sony)" Date: Fri, 20 Nov 2020 12:49:17 +0100 Subject: rcu: Eliminate the __kvfree_rcu() macro This commit open-codes the __kvfree_rcu() macro, thus saving a few lines of code and improving readability. Signed-off-by: Uladzislau Rezki (Sony) Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index b95373ea3b02..f1576cde5951 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -840,15 +840,6 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) */ #define __is_kvfree_rcu_offset(offset) ((offset) < 4096) -/* - * Helper macro for kfree_rcu() to prevent argument-expansion eyestrain. - */ -#define __kvfree_rcu(head, offset) \ - do { \ - BUILD_BUG_ON(!__is_kvfree_rcu_offset(offset)); \ - kvfree_call_rcu(head, (rcu_callback_t)(unsigned long)(offset)); \ - } while (0) - /** * kfree_rcu() - kfree an object after a grace period. * @ptr: pointer to kfree for both single- and double-argument invocations. @@ -866,7 +857,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) * Because the functions are not allowed in the low-order 4096 bytes of * kernel virtual memory, offsets up to 4095 bytes can be accommodated. * If the offset is larger than 4095 bytes, a compile-time error will - * be generated in __kvfree_rcu(). If this error is triggered, you can + * be generated in kvfree_rcu_arg_2(). If this error is triggered, you can * either fall back to use of call_rcu() or rearrange the structure to * position the rcu_head structure into the first 4096 bytes. * @@ -912,8 +903,11 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) do { \ typeof (ptr) ___p = (ptr); \ \ - if (___p) \ - __kvfree_rcu(&((___p)->rhf), offsetof(typeof(*(ptr)), rhf)); \ + if (___p) { \ + BUILD_BUG_ON(!__is_kvfree_rcu_offset(offsetof(typeof(*(ptr)), rhf))); \ + kvfree_call_rcu(&((___p)->rhf), (rcu_callback_t)(unsigned long) \ + (offsetof(typeof(*(ptr)), rhf))); \ + } \ } while (0) #define kvfree_rcu_arg_1(ptr) \ -- cgit v1.2.3 From 74612a07b83fc46c2b2e6f71a541d55b024ebefc Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 12 Nov 2020 16:34:09 -0800 Subject: srcu: Make Tiny SRCU use multi-bit grace-period counter There is a need for a polling interface for SRCU grace periods. This polling needs to distinguish between an SRCU instance being idle on the one hand or in the middle of a grace period on the other. This commit therefore converts the Tiny SRCU srcu_struct structure's srcu_idx from a defacto boolean to a free-running counter, using the bottom bit to indicate that a grace period is in progress. The second-from-bottom bit is thus used as the index returned by srcu_read_lock(). Link: https://lore.kernel.org/rcu/20201112201547.GF3365678@moria.home.lan/ Reported-by: Kent Overstreet [ paulmck: Fix ->srcu_lock_nesting[] indexing per Neeraj Upadhyay. ] Reviewed-by: Neeraj Upadhyay Signed-off-by: Paul E. McKenney --- include/linux/srcutiny.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h index 5a5a1941ca15..b8b42d0a24f1 100644 --- a/include/linux/srcutiny.h +++ b/include/linux/srcutiny.h @@ -15,7 +15,7 @@ struct srcu_struct { short srcu_lock_nesting[2]; /* srcu_read_lock() nesting depth. */ - short srcu_idx; /* Current reader array element. */ + unsigned short srcu_idx; /* Current reader array element in bit 0x2. */ u8 srcu_gp_running; /* GP workqueue running? */ u8 srcu_gp_waiting; /* GP waiting for readers? */ struct swait_queue_head srcu_wq; @@ -59,7 +59,7 @@ static inline int __srcu_read_lock(struct srcu_struct *ssp) { int idx; - idx = READ_ONCE(ssp->srcu_idx); + idx = ((READ_ONCE(ssp->srcu_idx) + 1) & 0x2) >> 1; WRITE_ONCE(ssp->srcu_lock_nesting[idx], ssp->srcu_lock_nesting[idx] + 1); return idx; } @@ -80,7 +80,7 @@ static inline void srcu_torture_stats_print(struct srcu_struct *ssp, { int idx; - idx = READ_ONCE(ssp->srcu_idx) & 0x1; + idx = ((READ_ONCE(ssp->srcu_idx) + 1) & 0x2) >> 1; pr_alert("%s%s Tiny SRCU per-CPU(idx=%d): (%hd,%hd)\n", tt, tf, idx, READ_ONCE(ssp->srcu_lock_nesting[!idx]), -- cgit v1.2.3 From 8b5bd67cf6422b63ee100d76d8de8960ca2df7f0 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 13 Nov 2020 12:54:48 -0800 Subject: srcu: Provide polling interfaces for Tiny SRCU grace periods There is a need for a polling interface for SRCU grace periods, so this commit supplies get_state_synchronize_srcu(), start_poll_synchronize_srcu(), and poll_state_synchronize_srcu() for this purpose. The first can be used if future grace periods are inevitable (perhaps due to a later call_srcu() invocation), the second if future grace periods might not otherwise happen, and the third to check if a grace period has elapsed since the corresponding call to either of the first two. As with get_state_synchronize_rcu() and cond_synchronize_rcu(), the return value from either get_state_synchronize_srcu() or start_poll_synchronize_srcu() must be passed in to a later call to poll_state_synchronize_srcu(). Link: https://lore.kernel.org/rcu/20201112201547.GF3365678@moria.home.lan/ Reported-by: Kent Overstreet [ paulmck: Add EXPORT_SYMBOL_GPL() per kernel test robot feedback. ] [ paulmck: Apply feedback from Neeraj Upadhyay. ] Link: https://lore.kernel.org/lkml/20201117004017.GA7444@paulmck-ThinkPad-P72/ Reviewed-by: Neeraj Upadhyay Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 2 ++ include/linux/srcu.h | 3 +++ include/linux/srcutiny.h | 1 + 3 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index de0826411311..e09c0d87b3c3 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -33,6 +33,8 @@ #define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b)) #define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b)) #define ulong2long(a) (*(long *)(&(a))) +#define USHORT_CMP_GE(a, b) (USHRT_MAX / 2 >= (unsigned short)((a) - (b))) +#define USHORT_CMP_LT(a, b) (USHRT_MAX / 2 < (unsigned short)((a) - (b))) /* Exported common interfaces */ void call_rcu(struct rcu_head *head, rcu_callback_t func); diff --git a/include/linux/srcu.h b/include/linux/srcu.h index e432cc92c73d..a0895bbf71ce 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -60,6 +60,9 @@ void cleanup_srcu_struct(struct srcu_struct *ssp); int __srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp); void __srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp); void synchronize_srcu(struct srcu_struct *ssp); +unsigned long get_state_synchronize_srcu(struct srcu_struct *ssp); +unsigned long start_poll_synchronize_srcu(struct srcu_struct *ssp); +bool poll_state_synchronize_srcu(struct srcu_struct *ssp, unsigned long cookie); #ifdef CONFIG_DEBUG_LOCK_ALLOC diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h index b8b42d0a24f1..0e0cf4d6a72a 100644 --- a/include/linux/srcutiny.h +++ b/include/linux/srcutiny.h @@ -16,6 +16,7 @@ struct srcu_struct { short srcu_lock_nesting[2]; /* srcu_read_lock() nesting depth. */ unsigned short srcu_idx; /* Current reader array element in bit 0x2. */ + unsigned short srcu_idx_max; /* Furthest future srcu_idx request. */ u8 srcu_gp_running; /* GP workqueue running? */ u8 srcu_gp_waiting; /* GP waiting for readers? */ struct swait_queue_head srcu_wq; -- cgit v1.2.3 From ac7b79fd190b02e7151bc7d2b9da692f537657f3 Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Sat, 19 Dec 2020 20:46:08 -0800 Subject: inotify, memcg: account inotify instances to kmemcg Currently the fs sysctl inotify/max_user_instances is used to limit the number of inotify instances on the system. For systems running multiple workloads, the per-user namespace sysctl max_inotify_instances can be used to further partition inotify instances. However there is no easy way to set a sensible system level max limit on inotify instances and further partition it between the workloads. It is much easier to charge the underlying resource (i.e. memory) behind the inotify instances to the memcg of the workload and let their memory limits limit the number of inotify instances they can create. With inotify instances charged to memcg, the admin can simply set max_user_instances to INT_MAX and let the memcg limits of the jobs limit their inotify instances. Link: https://lore.kernel.org/r/20201220044608.1258123-1-shakeelb@google.com Reviewed-by: Amir Goldstein Signed-off-by: Shakeel Butt Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index a2e42d3cd87c..e5409b83e731 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -470,6 +470,7 @@ static inline void fsnotify_update_flags(struct dentry *dentry) /* create a new group */ extern struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops); +extern struct fsnotify_group *fsnotify_alloc_user_group(const struct fsnotify_ops *ops); /* get reference to a group */ extern void fsnotify_get_group(struct fsnotify_group *group); /* drop reference on a group from fsnotify_alloc_group */ -- cgit v1.2.3 From 281462e593483350d8072a118c6e072c550a80fa Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Mon, 28 Dec 2020 18:49:16 +0300 Subject: memory: tegra124-emc: Make driver modular Add modularization support to the Tegra124 EMC driver, which now can be compiled as a loadable kernel module. Note that EMC clock must be registered at clk-init time, otherwise PLLM will be disabled as unused clock at boot time if EMC driver is compiled as a module. Hence add a prepare/complete callbacks. similarly to what is done for the Tegra20/30 EMC drivers. Tested-by: Nicolas Chauvet Signed-off-by: Dmitry Osipenko Link: https://lore.kernel.org/r/20201228154920.18846-2-digetx@gmail.com Signed-off-by: Krzysztof Kozlowski --- include/linux/clk/tegra.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk/tegra.h b/include/linux/clk/tegra.h index 3f01d43f0598..eb016fc9cc0b 100644 --- a/include/linux/clk/tegra.h +++ b/include/linux/clk/tegra.h @@ -136,6 +136,7 @@ extern void tegra210_clk_emc_dll_update_setting(u32 emc_dll_src_value); extern void tegra210_clk_emc_update_setting(u32 emc_src_value); struct clk; +struct tegra_emc; typedef long (tegra20_clk_emc_round_cb)(unsigned long rate, unsigned long min_rate, @@ -146,6 +147,13 @@ void tegra20_clk_set_emc_round_callback(tegra20_clk_emc_round_cb *round_cb, void *cb_arg); int tegra20_clk_prepare_emc_mc_same_freq(struct clk *emc_clk, bool same); +typedef int (tegra124_emc_prepare_timing_change_cb)(struct tegra_emc *emc, + unsigned long rate); +typedef void (tegra124_emc_complete_timing_change_cb)(struct tegra_emc *emc, + unsigned long rate); +void tegra124_clk_set_emc_callbacks(tegra124_emc_prepare_timing_change_cb *prep_cb, + tegra124_emc_complete_timing_change_cb *complete_cb); + struct tegra210_clk_emc_config { unsigned long rate; bool same_freq; -- cgit v1.2.3 From 8553a979fcd03448a4096c7d431b7ee1a52bfca3 Mon Sep 17 00:00:00 2001 From: Utkarsh Patel Date: Wed, 9 Dec 2020 22:09:03 -0800 Subject: platform/chrome: cros_ec_typec: Send mux configuration acknowledgment to EC In some corner cases downgrade of the superspeed typec device(e.g. Dell typec Dock, apple dongle) was seen because before the SOC mux configuration finishes, EC starts configuring the next mux state. With this change, once the SOC mux is configured, kernel will send an acknowledgment to EC via Host command EC_CMD_USB_PD_MUX_ACK [1]. After sending the host event EC will wait for the acknowledgment from kernel before starting the PD negotiation for the next mux state. This helps to have a framework to build better error handling along with the synchronization of timing sensitive mux states. This change also brings in corresponding EC header updates from the EC code base [1]. [1]: https://chromium.googlesource.com/chromiumos/platform/ec/+/refs/heads/master/include/ec_commands.h Signed-off-by: Utkarsh Patel Reviewed-by: Prashant Malani Signed-off-by: Benson Leung Link: https://lore.kernel.org/r/20201210060903.2205-3-utkarsh.h.patel@intel.com --- include/linux/platform_data/cros_ec_commands.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index 86376779ab31..9787715540c7 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -1286,6 +1286,16 @@ enum ec_feature_code { EC_FEATURE_ISH = 40, /* New TCPMv2 TYPEC_ prefaced commands supported */ EC_FEATURE_TYPEC_CMD = 41, + /* + * The EC will wait for direction from the AP to enter Type-C alternate + * modes or USB4. + */ + EC_FEATURE_TYPEC_REQUIRE_AP_MODE_ENTRY = 42, + /* + * The EC will wait for an acknowledge from the AP after setting the + * mux. + */ + EC_FEATURE_TYPEC_MUX_REQUIRE_AP_ACK = 43, }; #define EC_FEATURE_MASK_0(event_code) BIT(event_code % 32) @@ -6054,6 +6064,13 @@ struct ec_params_charger_control { uint8_t allow_charging; } __ec_align_size1; +/* Get ACK from the USB-C SS muxes */ +#define EC_CMD_USB_PD_MUX_ACK 0x0603 + +struct ec_params_usb_pd_mux_ack { + uint8_t port; /* USB-C port number */ +} __ec_align1; + /*****************************************************************************/ /* * Reserve a range of host commands for board-specific, experimental, or -- cgit v1.2.3 From 8527efc59d45d7135460daac36054f2f213ac08a Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Tue, 5 Jan 2021 19:59:05 -0800 Subject: rpmsg: glink: Guard qcom_glink_ssr_notify() with correct config The qcom_glink_ssr_notify() function doesn't relate to the SMEM specific GLINK config, but the common RPMSG_QCOM_GLINK config. Update the guard to properly reflect this. Reviewed-by: Alex Elder Reported-by: kernel test robot Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20210106035905.4153692-1-bjorn.andersson@linaro.org Signed-off-by: Bjorn Andersson --- include/linux/rpmsg/qcom_glink.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rpmsg/qcom_glink.h b/include/linux/rpmsg/qcom_glink.h index daded9fddf36..22fc3a69b683 100644 --- a/include/linux/rpmsg/qcom_glink.h +++ b/include/linux/rpmsg/qcom_glink.h @@ -7,12 +7,17 @@ struct qcom_glink; +#if IS_ENABLED(CONFIG_RPMSG_QCOM_GLINK) +void qcom_glink_ssr_notify(const char *ssr_name); +#else +static inline void qcom_glink_ssr_notify(const char *ssr_name) {} +#endif + #if IS_ENABLED(CONFIG_RPMSG_QCOM_GLINK_SMEM) struct qcom_glink *qcom_glink_smem_register(struct device *parent, struct device_node *node); void qcom_glink_smem_unregister(struct qcom_glink *glink); -void qcom_glink_ssr_notify(const char *ssr_name); #else @@ -24,7 +29,6 @@ qcom_glink_smem_register(struct device *parent, } static inline void qcom_glink_smem_unregister(struct qcom_glink *glink) {} -static inline void qcom_glink_ssr_notify(const char *ssr_name) {} #endif #endif -- cgit v1.2.3 From 98621ed011c57ba6e52e01a5982b221c9943b6d9 Mon Sep 17 00:00:00 2001 From: Sowjanya Komatineni Date: Mon, 21 Dec 2020 13:17:35 -0800 Subject: spi: spi-mem: Mark dummy transfers by setting dummy_data bit This patch marks dummy transfer by setting dummy_data bit to 1. Controllers supporting dummy transfer by hardware use this bit field to skip software transfer of dummy bytes and use hardware dummy bytes transfer. Signed-off-by: Sowjanya Komatineni Link: https://lore.kernel.org/r/1608585459-17250-6-git-send-email-skomatineni@nvidia.com Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 9bfdfaf286eb..797ef28fa7d5 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -825,6 +825,7 @@ extern void spi_res_release(struct spi_controller *ctlr, * transfer. If 0 the default (from @spi_device) is used. * @bits_per_word: select a bits_per_word other than the device default * for this transfer. If 0 the default (from @spi_device) is used. + * @dummy_data: indicates transfer is dummy bytes transfer. * @cs_change: affects chipselect after this transfer completes * @cs_change_delay: delay between cs deassert and assert when * @cs_change is set and @spi_transfer is not the last in @spi_message @@ -937,6 +938,7 @@ struct spi_transfer { struct sg_table tx_sg; struct sg_table rx_sg; + unsigned dummy_data:1; unsigned cs_change:1; unsigned tx_nbits:3; unsigned rx_nbits:3; -- cgit v1.2.3 From f2485a2dc9f0f30fbdd013ad5772975100c71360 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 13 Jun 2020 00:08:44 -0400 Subject: elf_prstatus: collect the common part (everything before pr_reg) into a struct Preparations to doing i386 compat elf_prstatus sanely - rather than duplicating the beginning of compat_elf_prstatus, take these fields into a separate structure (compat_elf_prstatus_common), so that it could be reused. Due to the incestous relationship between binfmt_elf.c and compat_binfmt_elf.c we need the same shape change done to native struct elf_prstatus, gathering the fields prior to pr_reg into a new structure (struct elf_prstatus_common). Fortunately, offset of pr_reg is always a multiple of 16 with no padding right before it, so it's possible to turn all the stuff prior to it into a single member without disturbing the layout. [build fix from Geert Uytterhoeven folded in] Signed-off-by: Al Viro --- include/linux/elfcore-compat.h | 7 ++++++- include/linux/elfcore.h | 7 ++++++- 2 files changed, 12 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/elfcore-compat.h b/include/linux/elfcore-compat.h index 10485f0c9740..4aeda5f1f038 100644 --- a/include/linux/elfcore-compat.h +++ b/include/linux/elfcore-compat.h @@ -17,7 +17,7 @@ struct compat_elf_siginfo compat_int_t si_errno; }; -struct compat_elf_prstatus +struct compat_elf_prstatus_common { struct compat_elf_siginfo pr_info; short pr_cursig; @@ -31,6 +31,11 @@ struct compat_elf_prstatus struct old_timeval32 pr_stime; struct old_timeval32 pr_cutime; struct old_timeval32 pr_cstime; +}; + +struct compat_elf_prstatus +{ + struct compat_elf_prstatus_common common; compat_elf_gregset_t pr_reg; compat_int_t pr_fpvalid; }; diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h index de51c1bef27d..2aaa15779d50 100644 --- a/include/linux/elfcore.h +++ b/include/linux/elfcore.h @@ -29,7 +29,7 @@ struct elf_siginfo * the SVR4 structure, but more Linuxy, with things that Linux does * not support and which gdb doesn't really use excluded. */ -struct elf_prstatus +struct elf_prstatus_common { struct elf_siginfo pr_info; /* Info associated with signal */ short pr_cursig; /* Current signal */ @@ -43,6 +43,11 @@ struct elf_prstatus struct __kernel_old_timeval pr_stime; /* System time */ struct __kernel_old_timeval pr_cutime; /* Cumulative user time */ struct __kernel_old_timeval pr_cstime; /* Cumulative system time */ +}; + +struct elf_prstatus +{ + struct elf_prstatus_common common; elf_gregset_t pr_reg; /* GP registers */ int pr_fpvalid; /* True if math co-processor being used. */ }; -- cgit v1.2.3 From 7facdc426f86c67e579e49e100943cbccc43e1c6 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 13 Jun 2020 23:03:25 -0400 Subject: [amd64] clean PRSTATUS_SIZE/SET_PR_FPVALID up properly To get rid of hardcoded size/offset in those macros we need to have a definition of i386 variant of struct elf_prstatus. However, we can't do that in asm/compat.h - the types needed for that are not there and adding an include of asm/user32.h into asm/compat.h would cause a lot of mess. That could be conveniently done in elfcore-compat.h, but currently there is nowhere to put arch-dependent parts of it - no asm/elfcore-compat.h. So we introduce a new file (asm/elfcore-compat.h, present on architectures that have CONFIG_ARCH_HAS_ELFCORE_COMPAT set, currently only on x86), have it pulled by linux/elfcore-compat.h and move the definitions there. As a side benefit, we don't need to worry about accidental inclusion of that file into binfmt_elf.c itself, so we don't need the dance with COMPAT_PRSTATUS_SIZE, etc. - only fs/compat_binfmt_elf.c will see that header. Signed-off-by: Al Viro --- include/linux/elfcore-compat.h | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/elfcore-compat.h b/include/linux/elfcore-compat.h index 4aeda5f1f038..e272c3d452ce 100644 --- a/include/linux/elfcore-compat.h +++ b/include/linux/elfcore-compat.h @@ -33,13 +33,6 @@ struct compat_elf_prstatus_common struct old_timeval32 pr_cstime; }; -struct compat_elf_prstatus -{ - struct compat_elf_prstatus_common common; - compat_elf_gregset_t pr_reg; - compat_int_t pr_fpvalid; -}; - struct compat_elf_prpsinfo { char pr_state; @@ -54,4 +47,15 @@ struct compat_elf_prpsinfo char pr_psargs[ELF_PRARGSZ]; }; +#ifdef CONFIG_ARCH_HAS_ELFCORE_COMPAT +#include +#endif + +struct compat_elf_prstatus +{ + struct compat_elf_prstatus_common common; + compat_elf_gregset_t pr_reg; + compat_int_t pr_fpvalid; +}; + #endif /* _LINUX_ELFCORE_COMPAT_H */ -- cgit v1.2.3 From c167b9c7e3d6131b4a4865c112a3dbc86d2e997d Mon Sep 17 00:00:00 2001 From: Maximilian Luz Date: Mon, 21 Dec 2020 19:39:51 +0100 Subject: platform/surface: Add Surface Aggregator subsystem Add Surface System Aggregator Module core and Surface Serial Hub driver, required for the embedded controller found on Microsoft Surface devices. The Surface System Aggregator Module (SSAM, SAM or Surface Aggregator) is an embedded controller (EC) found on 4th and later generation Microsoft Surface devices, with the exception of the Surface Go series. This EC provides various functionality, depending on the device in question. This can include battery status and thermal reporting (5th and later generations), but also HID keyboard (6th+) and touchpad input (7th+) on Surface Laptop and Surface Book 3 series devices. This patch provides the basic necessities for communication with the SAM EC on 5th and later generation devices. On these devices, the EC provides an interface that acts as serial device, called the Surface Serial Hub (SSH). 4th generation devices, on which the EC interface is provided via an HID-over-I2C device, are not supported by this patch. Specifically, this patch adds a driver for the SSH device (device HID MSHW0084 in ACPI), as well as a controller structure and associated API. This represents the functional core of the Surface Aggregator kernel subsystem, introduced with this patch, and will be expanded upon in subsequent commits. The SSH driver acts as the main attachment point for this subsystem and sets-up and manages the controller structure. The controller in turn provides a basic communication interface, allowing to send requests from host to EC and receiving the corresponding responses, as well as managing and receiving events, sent from EC to host. It is structured into multiple layers, with the top layer presenting the API used by other kernel drivers and the lower layers modeled after the serial protocol used for communication. Said other drivers are then responsible for providing the (Surface model specific) functionality accessible through the EC (e.g. battery status reporting, thermal information, ...) via said controller structure and API, and will be added in future commits. Signed-off-by: Maximilian Luz Link: https://lore.kernel.org/r/20201221183959.1186143-2-luzmaximilian@gmail.com Signed-off-by: Hans de Goede --- include/linux/surface_aggregator/controller.h | 824 ++++++++++++++++++++++++++ include/linux/surface_aggregator/serial_hub.h | 672 +++++++++++++++++++++ 2 files changed, 1496 insertions(+) create mode 100644 include/linux/surface_aggregator/controller.h create mode 100644 include/linux/surface_aggregator/serial_hub.h (limited to 'include/linux') diff --git a/include/linux/surface_aggregator/controller.h b/include/linux/surface_aggregator/controller.h new file mode 100644 index 000000000000..f4b1ba887384 --- /dev/null +++ b/include/linux/surface_aggregator/controller.h @@ -0,0 +1,824 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Surface System Aggregator Module (SSAM) controller interface. + * + * Main communication interface for the SSAM EC. Provides a controller + * managing access and communication to and from the SSAM EC, as well as main + * communication structures and definitions. + * + * Copyright (C) 2019-2020 Maximilian Luz + */ + +#ifndef _LINUX_SURFACE_AGGREGATOR_CONTROLLER_H +#define _LINUX_SURFACE_AGGREGATOR_CONTROLLER_H + +#include +#include +#include + +#include + + +/* -- Main data types and definitions --------------------------------------- */ + +/** + * enum ssam_event_flags - Flags for enabling/disabling SAM events + * @SSAM_EVENT_SEQUENCED: The event will be sent via a sequenced data frame. + */ +enum ssam_event_flags { + SSAM_EVENT_SEQUENCED = BIT(0), +}; + +/** + * struct ssam_event - SAM event sent from the EC to the host. + * @target_category: Target category of the event source. See &enum ssam_ssh_tc. + * @target_id: Target ID of the event source. + * @command_id: Command ID of the event. + * @instance_id: Instance ID of the event source. + * @length: Length of the event payload in bytes. + * @data: Event payload data. + */ +struct ssam_event { + u8 target_category; + u8 target_id; + u8 command_id; + u8 instance_id; + u16 length; + u8 data[]; +}; + +/** + * enum ssam_request_flags - Flags for SAM requests. + * + * @SSAM_REQUEST_HAS_RESPONSE: + * Specifies that the request expects a response. If not set, the request + * will be directly completed after its underlying packet has been + * transmitted. If set, the request transport system waits for a response + * of the request. + * + * @SSAM_REQUEST_UNSEQUENCED: + * Specifies that the request should be transmitted via an unsequenced + * packet. If set, the request must not have a response, meaning that this + * flag and the %SSAM_REQUEST_HAS_RESPONSE flag are mutually exclusive. + */ +enum ssam_request_flags { + SSAM_REQUEST_HAS_RESPONSE = BIT(0), + SSAM_REQUEST_UNSEQUENCED = BIT(1), +}; + +/** + * struct ssam_request - SAM request description. + * @target_category: Category of the request's target. See &enum ssam_ssh_tc. + * @target_id: ID of the request's target. + * @command_id: Command ID of the request. + * @instance_id: Instance ID of the request's target. + * @flags: Flags for the request. See &enum ssam_request_flags. + * @length: Length of the request payload in bytes. + * @payload: Request payload data. + * + * This struct fully describes a SAM request with payload. It is intended to + * help set up the actual transport struct, e.g. &struct ssam_request_sync, + * and specifically its raw message data via ssam_request_write_data(). + */ +struct ssam_request { + u8 target_category; + u8 target_id; + u8 command_id; + u8 instance_id; + u16 flags; + u16 length; + const u8 *payload; +}; + +/** + * struct ssam_response - Response buffer for SAM request. + * @capacity: Capacity of the buffer, in bytes. + * @length: Length of the actual data stored in the memory pointed to by + * @pointer, in bytes. Set by the transport system. + * @pointer: Pointer to the buffer's memory, storing the response payload data. + */ +struct ssam_response { + size_t capacity; + size_t length; + u8 *pointer; +}; + +struct ssam_controller; + +struct ssam_controller *ssam_get_controller(void); +struct ssam_controller *ssam_client_bind(struct device *client); +int ssam_client_link(struct ssam_controller *ctrl, struct device *client); + +struct device *ssam_controller_device(struct ssam_controller *c); + +struct ssam_controller *ssam_controller_get(struct ssam_controller *c); +void ssam_controller_put(struct ssam_controller *c); + +void ssam_controller_statelock(struct ssam_controller *c); +void ssam_controller_stateunlock(struct ssam_controller *c); + +ssize_t ssam_request_write_data(struct ssam_span *buf, + struct ssam_controller *ctrl, + const struct ssam_request *spec); + + +/* -- Synchronous request interface. ---------------------------------------- */ + +/** + * struct ssam_request_sync - Synchronous SAM request struct. + * @base: Underlying SSH request. + * @comp: Completion used to signal full completion of the request. After the + * request has been submitted, this struct may only be modified or + * deallocated after the completion has been signaled. + * request has been submitted, + * @resp: Buffer to store the response. + * @status: Status of the request, set after the base request has been + * completed or has failed. + */ +struct ssam_request_sync { + struct ssh_request base; + struct completion comp; + struct ssam_response *resp; + int status; +}; + +int ssam_request_sync_alloc(size_t payload_len, gfp_t flags, + struct ssam_request_sync **rqst, + struct ssam_span *buffer); + +void ssam_request_sync_free(struct ssam_request_sync *rqst); + +int ssam_request_sync_init(struct ssam_request_sync *rqst, + enum ssam_request_flags flags); + +/** + * ssam_request_sync_set_data - Set message data of a synchronous request. + * @rqst: The request. + * @ptr: Pointer to the request message data. + * @len: Length of the request message data. + * + * Set the request message data of a synchronous request. The provided buffer + * needs to live until the request has been completed. + */ +static inline void ssam_request_sync_set_data(struct ssam_request_sync *rqst, + u8 *ptr, size_t len) +{ + ssh_request_set_data(&rqst->base, ptr, len); +} + +/** + * ssam_request_sync_set_resp - Set response buffer of a synchronous request. + * @rqst: The request. + * @resp: The response buffer. + * + * Sets the response buffer of a synchronous request. This buffer will store + * the response of the request after it has been completed. May be %NULL if no + * response is expected. + */ +static inline void ssam_request_sync_set_resp(struct ssam_request_sync *rqst, + struct ssam_response *resp) +{ + rqst->resp = resp; +} + +int ssam_request_sync_submit(struct ssam_controller *ctrl, + struct ssam_request_sync *rqst); + +/** + * ssam_request_sync_wait - Wait for completion of a synchronous request. + * @rqst: The request to wait for. + * + * Wait for completion and release of a synchronous request. After this + * function terminates, the request is guaranteed to have left the transport + * system. After successful submission of a request, this function must be + * called before accessing the response of the request, freeing the request, + * or freeing any of the buffers associated with the request. + * + * This function must not be called if the request has not been submitted yet + * and may lead to a deadlock/infinite wait if a subsequent request submission + * fails in that case, due to the completion never triggering. + * + * Return: Returns the status of the given request, which is set on completion + * of the packet. This value is zero on success and negative on failure. + */ +static inline int ssam_request_sync_wait(struct ssam_request_sync *rqst) +{ + wait_for_completion(&rqst->comp); + return rqst->status; +} + +int ssam_request_sync(struct ssam_controller *ctrl, + const struct ssam_request *spec, + struct ssam_response *rsp); + +int ssam_request_sync_with_buffer(struct ssam_controller *ctrl, + const struct ssam_request *spec, + struct ssam_response *rsp, + struct ssam_span *buf); + +/** + * ssam_request_sync_onstack - Execute a synchronous request on the stack. + * @ctrl: The controller via which the request is submitted. + * @rqst: The request specification. + * @rsp: The response buffer. + * @payload_len: The (maximum) request payload length. + * + * Allocates a synchronous request with specified payload length on the stack, + * fully initializes it via the provided request specification, submits it, + * and finally waits for its completion before returning its status. This + * helper macro essentially allocates the request message buffer on the stack + * and then calls ssam_request_sync_with_buffer(). + * + * Note: The @payload_len parameter specifies the maximum payload length, used + * for buffer allocation. The actual payload length may be smaller. + * + * Return: Returns the status of the request or any failure during setup, i.e. + * zero on success and a negative value on failure. + */ +#define ssam_request_sync_onstack(ctrl, rqst, rsp, payload_len) \ + ({ \ + u8 __data[SSH_COMMAND_MESSAGE_LENGTH(payload_len)]; \ + struct ssam_span __buf = { &__data[0], ARRAY_SIZE(__data) }; \ + \ + ssam_request_sync_with_buffer(ctrl, rqst, rsp, &__buf); \ + }) + +/** + * __ssam_retry - Retry request in case of I/O errors or timeouts. + * @request: The request function to execute. Must return an integer. + * @n: Number of tries. + * @args: Arguments for the request function. + * + * Executes the given request function, i.e. calls @request. In case the + * request returns %-EREMOTEIO (indicates I/O error) or %-ETIMEDOUT (request + * or underlying packet timed out), @request will be re-executed again, up to + * @n times in total. + * + * Return: Returns the return value of the last execution of @request. + */ +#define __ssam_retry(request, n, args...) \ + ({ \ + int __i, __s = 0; \ + \ + for (__i = (n); __i > 0; __i--) { \ + __s = request(args); \ + if (__s != -ETIMEDOUT && __s != -EREMOTEIO) \ + break; \ + } \ + __s; \ + }) + +/** + * ssam_retry - Retry request in case of I/O errors or timeouts up to three + * times in total. + * @request: The request function to execute. Must return an integer. + * @args: Arguments for the request function. + * + * Executes the given request function, i.e. calls @request. In case the + * request returns %-EREMOTEIO (indicates I/O error) or -%ETIMEDOUT (request + * or underlying packet timed out), @request will be re-executed again, up to + * three times in total. + * + * See __ssam_retry() for a more generic macro for this purpose. + * + * Return: Returns the return value of the last execution of @request. + */ +#define ssam_retry(request, args...) \ + __ssam_retry(request, 3, args) + +/** + * struct ssam_request_spec - Blue-print specification of SAM request. + * @target_category: Category of the request's target. See &enum ssam_ssh_tc. + * @target_id: ID of the request's target. + * @command_id: Command ID of the request. + * @instance_id: Instance ID of the request's target. + * @flags: Flags for the request. See &enum ssam_request_flags. + * + * Blue-print specification for a SAM request. This struct describes the + * unique static parameters of a request (i.e. type) without specifying any of + * its instance-specific data (e.g. payload). It is intended to be used as base + * for defining simple request functions via the + * ``SSAM_DEFINE_SYNC_REQUEST_x()`` family of macros. + */ +struct ssam_request_spec { + u8 target_category; + u8 target_id; + u8 command_id; + u8 instance_id; + u8 flags; +}; + +/** + * struct ssam_request_spec_md - Blue-print specification for multi-device SAM + * request. + * @target_category: Category of the request's target. See &enum ssam_ssh_tc. + * @command_id: Command ID of the request. + * @flags: Flags for the request. See &enum ssam_request_flags. + * + * Blue-print specification for a multi-device SAM request, i.e. a request + * that is applicable to multiple device instances, described by their + * individual target and instance IDs. This struct describes the unique static + * parameters of a request (i.e. type) without specifying any of its + * instance-specific data (e.g. payload) and without specifying any of its + * device specific IDs (i.e. target and instance ID). It is intended to be + * used as base for defining simple multi-device request functions via the + * ``SSAM_DEFINE_SYNC_REQUEST_MD_x()`` and ``SSAM_DEFINE_SYNC_REQUEST_CL_x()`` + * families of macros. + */ +struct ssam_request_spec_md { + u8 target_category; + u8 command_id; + u8 flags; +}; + +/** + * SSAM_DEFINE_SYNC_REQUEST_N() - Define synchronous SAM request function + * with neither argument nor return value. + * @name: Name of the generated function. + * @spec: Specification (&struct ssam_request_spec) defining the request. + * + * Defines a function executing the synchronous SAM request specified by + * @spec, with the request having neither argument nor return value. The + * generated function takes care of setting up the request struct and buffer + * allocation, as well as execution of the request itself, returning once the + * request has been fully completed. The required transport buffer will be + * allocated on the stack. + * + * The generated function is defined as ``int name(struct ssam_controller + * *ctrl)``, returning the status of the request, which is zero on success and + * negative on failure. The ``ctrl`` parameter is the controller via which the + * request is being sent. + * + * Refer to ssam_request_sync_onstack() for more details on the behavior of + * the generated function. + */ +#define SSAM_DEFINE_SYNC_REQUEST_N(name, spec...) \ + int name(struct ssam_controller *ctrl) \ + { \ + struct ssam_request_spec s = (struct ssam_request_spec)spec; \ + struct ssam_request rqst; \ + \ + rqst.target_category = s.target_category; \ + rqst.target_id = s.target_id; \ + rqst.command_id = s.command_id; \ + rqst.instance_id = s.instance_id; \ + rqst.flags = s.flags; \ + rqst.length = 0; \ + rqst.payload = NULL; \ + \ + return ssam_request_sync_onstack(ctrl, &rqst, NULL, 0); \ + } + +/** + * SSAM_DEFINE_SYNC_REQUEST_W() - Define synchronous SAM request function with + * argument. + * @name: Name of the generated function. + * @atype: Type of the request's argument. + * @spec: Specification (&struct ssam_request_spec) defining the request. + * + * Defines a function executing the synchronous SAM request specified by + * @spec, with the request taking an argument of type @atype and having no + * return value. The generated function takes care of setting up the request + * struct, buffer allocation, as well as execution of the request itself, + * returning once the request has been fully completed. The required transport + * buffer will be allocated on the stack. + * + * The generated function is defined as ``int name(struct ssam_controller + * *ctrl, const atype *arg)``, returning the status of the request, which is + * zero on success and negative on failure. The ``ctrl`` parameter is the + * controller via which the request is sent. The request argument is specified + * via the ``arg`` pointer. + * + * Refer to ssam_request_sync_onstack() for more details on the behavior of + * the generated function. + */ +#define SSAM_DEFINE_SYNC_REQUEST_W(name, atype, spec...) \ + int name(struct ssam_controller *ctrl, const atype *arg) \ + { \ + struct ssam_request_spec s = (struct ssam_request_spec)spec; \ + struct ssam_request rqst; \ + \ + rqst.target_category = s.target_category; \ + rqst.target_id = s.target_id; \ + rqst.command_id = s.command_id; \ + rqst.instance_id = s.instance_id; \ + rqst.flags = s.flags; \ + rqst.length = sizeof(atype); \ + rqst.payload = (u8 *)arg; \ + \ + return ssam_request_sync_onstack(ctrl, &rqst, NULL, \ + sizeof(atype)); \ + } + +/** + * SSAM_DEFINE_SYNC_REQUEST_R() - Define synchronous SAM request function with + * return value. + * @name: Name of the generated function. + * @rtype: Type of the request's return value. + * @spec: Specification (&struct ssam_request_spec) defining the request. + * + * Defines a function executing the synchronous SAM request specified by + * @spec, with the request taking no argument but having a return value of + * type @rtype. The generated function takes care of setting up the request + * and response structs, buffer allocation, as well as execution of the + * request itself, returning once the request has been fully completed. The + * required transport buffer will be allocated on the stack. + * + * The generated function is defined as ``int name(struct ssam_controller + * *ctrl, rtype *ret)``, returning the status of the request, which is zero on + * success and negative on failure. The ``ctrl`` parameter is the controller + * via which the request is sent. The request's return value is written to the + * memory pointed to by the ``ret`` parameter. + * + * Refer to ssam_request_sync_onstack() for more details on the behavior of + * the generated function. + */ +#define SSAM_DEFINE_SYNC_REQUEST_R(name, rtype, spec...) \ + int name(struct ssam_controller *ctrl, rtype *ret) \ + { \ + struct ssam_request_spec s = (struct ssam_request_spec)spec; \ + struct ssam_request rqst; \ + struct ssam_response rsp; \ + int status; \ + \ + rqst.target_category = s.target_category; \ + rqst.target_id = s.target_id; \ + rqst.command_id = s.command_id; \ + rqst.instance_id = s.instance_id; \ + rqst.flags = s.flags | SSAM_REQUEST_HAS_RESPONSE; \ + rqst.length = 0; \ + rqst.payload = NULL; \ + \ + rsp.capacity = sizeof(rtype); \ + rsp.length = 0; \ + rsp.pointer = (u8 *)ret; \ + \ + status = ssam_request_sync_onstack(ctrl, &rqst, &rsp, 0); \ + if (status) \ + return status; \ + \ + if (rsp.length != sizeof(rtype)) { \ + struct device *dev = ssam_controller_device(ctrl); \ + dev_err(dev, \ + "rqst: invalid response length, expected %zu, got %zu (tc: %#04x, cid: %#04x)", \ + sizeof(rtype), rsp.length, rqst.target_category,\ + rqst.command_id); \ + return -EIO; \ + } \ + \ + return 0; \ + } + +/** + * SSAM_DEFINE_SYNC_REQUEST_MD_N() - Define synchronous multi-device SAM + * request function with neither argument nor return value. + * @name: Name of the generated function. + * @spec: Specification (&struct ssam_request_spec_md) defining the request. + * + * Defines a function executing the synchronous SAM request specified by + * @spec, with the request having neither argument nor return value. Device + * specifying parameters are not hard-coded, but instead must be provided to + * the function. The generated function takes care of setting up the request + * struct, buffer allocation, as well as execution of the request itself, + * returning once the request has been fully completed. The required transport + * buffer will be allocated on the stack. + * + * The generated function is defined as ``int name(struct ssam_controller + * *ctrl, u8 tid, u8 iid)``, returning the status of the request, which is + * zero on success and negative on failure. The ``ctrl`` parameter is the + * controller via which the request is sent, ``tid`` the target ID for the + * request, and ``iid`` the instance ID. + * + * Refer to ssam_request_sync_onstack() for more details on the behavior of + * the generated function. + */ +#define SSAM_DEFINE_SYNC_REQUEST_MD_N(name, spec...) \ + int name(struct ssam_controller *ctrl, u8 tid, u8 iid) \ + { \ + struct ssam_request_spec_md s = (struct ssam_request_spec_md)spec; \ + struct ssam_request rqst; \ + \ + rqst.target_category = s.target_category; \ + rqst.target_id = tid; \ + rqst.command_id = s.command_id; \ + rqst.instance_id = iid; \ + rqst.flags = s.flags; \ + rqst.length = 0; \ + rqst.payload = NULL; \ + \ + return ssam_request_sync_onstack(ctrl, &rqst, NULL, 0); \ + } + +/** + * SSAM_DEFINE_SYNC_REQUEST_MD_W() - Define synchronous multi-device SAM + * request function with argument. + * @name: Name of the generated function. + * @atype: Type of the request's argument. + * @spec: Specification (&struct ssam_request_spec_md) defining the request. + * + * Defines a function executing the synchronous SAM request specified by + * @spec, with the request taking an argument of type @atype and having no + * return value. Device specifying parameters are not hard-coded, but instead + * must be provided to the function. The generated function takes care of + * setting up the request struct, buffer allocation, as well as execution of + * the request itself, returning once the request has been fully completed. + * The required transport buffer will be allocated on the stack. + * + * The generated function is defined as ``int name(struct ssam_controller + * *ctrl, u8 tid, u8 iid, const atype *arg)``, returning the status of the + * request, which is zero on success and negative on failure. The ``ctrl`` + * parameter is the controller via which the request is sent, ``tid`` the + * target ID for the request, and ``iid`` the instance ID. The request argument + * is specified via the ``arg`` pointer. + * + * Refer to ssam_request_sync_onstack() for more details on the behavior of + * the generated function. + */ +#define SSAM_DEFINE_SYNC_REQUEST_MD_W(name, atype, spec...) \ + int name(struct ssam_controller *ctrl, u8 tid, u8 iid, const atype *arg)\ + { \ + struct ssam_request_spec_md s = (struct ssam_request_spec_md)spec; \ + struct ssam_request rqst; \ + \ + rqst.target_category = s.target_category; \ + rqst.target_id = tid; \ + rqst.command_id = s.command_id; \ + rqst.instance_id = iid; \ + rqst.flags = s.flags; \ + rqst.length = sizeof(atype); \ + rqst.payload = (u8 *)arg; \ + \ + return ssam_request_sync_onstack(ctrl, &rqst, NULL, \ + sizeof(atype)); \ + } + +/** + * SSAM_DEFINE_SYNC_REQUEST_MD_R() - Define synchronous multi-device SAM + * request function with return value. + * @name: Name of the generated function. + * @rtype: Type of the request's return value. + * @spec: Specification (&struct ssam_request_spec_md) defining the request. + * + * Defines a function executing the synchronous SAM request specified by + * @spec, with the request taking no argument but having a return value of + * type @rtype. Device specifying parameters are not hard-coded, but instead + * must be provided to the function. The generated function takes care of + * setting up the request and response structs, buffer allocation, as well as + * execution of the request itself, returning once the request has been fully + * completed. The required transport buffer will be allocated on the stack. + * + * The generated function is defined as ``int name(struct ssam_controller + * *ctrl, u8 tid, u8 iid, rtype *ret)``, returning the status of the request, + * which is zero on success and negative on failure. The ``ctrl`` parameter is + * the controller via which the request is sent, ``tid`` the target ID for the + * request, and ``iid`` the instance ID. The request's return value is written + * to the memory pointed to by the ``ret`` parameter. + * + * Refer to ssam_request_sync_onstack() for more details on the behavior of + * the generated function. + */ +#define SSAM_DEFINE_SYNC_REQUEST_MD_R(name, rtype, spec...) \ + int name(struct ssam_controller *ctrl, u8 tid, u8 iid, rtype *ret) \ + { \ + struct ssam_request_spec_md s = (struct ssam_request_spec_md)spec; \ + struct ssam_request rqst; \ + struct ssam_response rsp; \ + int status; \ + \ + rqst.target_category = s.target_category; \ + rqst.target_id = tid; \ + rqst.command_id = s.command_id; \ + rqst.instance_id = iid; \ + rqst.flags = s.flags | SSAM_REQUEST_HAS_RESPONSE; \ + rqst.length = 0; \ + rqst.payload = NULL; \ + \ + rsp.capacity = sizeof(rtype); \ + rsp.length = 0; \ + rsp.pointer = (u8 *)ret; \ + \ + status = ssam_request_sync_onstack(ctrl, &rqst, &rsp, 0); \ + if (status) \ + return status; \ + \ + if (rsp.length != sizeof(rtype)) { \ + struct device *dev = ssam_controller_device(ctrl); \ + dev_err(dev, \ + "rqst: invalid response length, expected %zu, got %zu (tc: %#04x, cid: %#04x)", \ + sizeof(rtype), rsp.length, rqst.target_category,\ + rqst.command_id); \ + return -EIO; \ + } \ + \ + return 0; \ + } + + +/* -- Event notifier/callbacks. --------------------------------------------- */ + +#define SSAM_NOTIF_STATE_SHIFT 2 +#define SSAM_NOTIF_STATE_MASK ((1 << SSAM_NOTIF_STATE_SHIFT) - 1) + +/** + * enum ssam_notif_flags - Flags used in return values from SSAM notifier + * callback functions. + * + * @SSAM_NOTIF_HANDLED: + * Indicates that the notification has been handled. This flag should be + * set by the handler if the handler can act/has acted upon the event + * provided to it. This flag should not be set if the handler is not a + * primary handler intended for the provided event. + * + * If this flag has not been set by any handler after the notifier chain + * has been traversed, a warning will be emitted, stating that the event + * has not been handled. + * + * @SSAM_NOTIF_STOP: + * Indicates that the notifier traversal should stop. If this flag is + * returned from a notifier callback, notifier chain traversal will + * immediately stop and any remaining notifiers will not be called. This + * flag is automatically set when ssam_notifier_from_errno() is called + * with a negative error value. + */ +enum ssam_notif_flags { + SSAM_NOTIF_HANDLED = BIT(0), + SSAM_NOTIF_STOP = BIT(1), +}; + +struct ssam_event_notifier; + +typedef u32 (*ssam_notifier_fn_t)(struct ssam_event_notifier *nf, + const struct ssam_event *event); + +/** + * struct ssam_notifier_block - Base notifier block for SSAM event + * notifications. + * @node: The node for the list of notifiers. + * @fn: The callback function of this notifier. This function takes the + * respective notifier block and event as input and should return + * a notifier value, which can either be obtained from the flags + * provided in &enum ssam_notif_flags, converted from a standard + * error value via ssam_notifier_from_errno(), or a combination of + * both (e.g. ``ssam_notifier_from_errno(e) | SSAM_NOTIF_HANDLED``). + * @priority: Priority value determining the order in which notifier callbacks + * will be called. A higher value means higher priority, i.e. the + * associated callback will be executed earlier than other (lower + * priority) callbacks. + */ +struct ssam_notifier_block { + struct list_head node; + ssam_notifier_fn_t fn; + int priority; +}; + +/** + * ssam_notifier_from_errno() - Convert standard error value to notifier + * return code. + * @err: The error code to convert, must be negative (in case of failure) or + * zero (in case of success). + * + * Return: Returns the notifier return value obtained by converting the + * specified @err value. In case @err is negative, the %SSAM_NOTIF_STOP flag + * will be set, causing notifier call chain traversal to abort. + */ +static inline u32 ssam_notifier_from_errno(int err) +{ + if (WARN_ON(err > 0) || err == 0) + return 0; + else + return ((-err) << SSAM_NOTIF_STATE_SHIFT) | SSAM_NOTIF_STOP; +} + +/** + * ssam_notifier_to_errno() - Convert notifier return code to standard error + * value. + * @ret: The notifier return value to convert. + * + * Return: Returns the negative error value encoded in @ret or zero if @ret + * indicates success. + */ +static inline int ssam_notifier_to_errno(u32 ret) +{ + return -(ret >> SSAM_NOTIF_STATE_SHIFT); +} + + +/* -- Event/notification registry. ------------------------------------------ */ + +/** + * struct ssam_event_registry - Registry specification used for enabling events. + * @target_category: Target category for the event registry requests. + * @target_id: Target ID for the event registry requests. + * @cid_enable: Command ID for the event-enable request. + * @cid_disable: Command ID for the event-disable request. + * + * This struct describes a SAM event registry via the minimal collection of + * SAM IDs specifying the requests to use for enabling and disabling an event. + * The individual event to be enabled/disabled itself is specified via &struct + * ssam_event_id. + */ +struct ssam_event_registry { + u8 target_category; + u8 target_id; + u8 cid_enable; + u8 cid_disable; +}; + +/** + * struct ssam_event_id - Unique event ID used for enabling events. + * @target_category: Target category of the event source. + * @instance: Instance ID of the event source. + * + * This struct specifies the event to be enabled/disabled via an externally + * provided registry. It does not specify the registry to be used itself, this + * is done via &struct ssam_event_registry. + */ +struct ssam_event_id { + u8 target_category; + u8 instance; +}; + +/** + * enum ssam_event_mask - Flags specifying how events are matched to notifiers. + * + * @SSAM_EVENT_MASK_NONE: + * Run the callback for any event with matching target category. Do not + * do any additional filtering. + * + * @SSAM_EVENT_MASK_TARGET: + * In addition to filtering by target category, only execute the notifier + * callback for events with a target ID matching to the one of the + * registry used for enabling/disabling the event. + * + * @SSAM_EVENT_MASK_INSTANCE: + * In addition to filtering by target category, only execute the notifier + * callback for events with an instance ID matching to the instance ID + * used when enabling the event. + * + * @SSAM_EVENT_MASK_STRICT: + * Do all the filtering above. + */ +enum ssam_event_mask { + SSAM_EVENT_MASK_TARGET = BIT(0), + SSAM_EVENT_MASK_INSTANCE = BIT(1), + + SSAM_EVENT_MASK_NONE = 0, + SSAM_EVENT_MASK_STRICT = + SSAM_EVENT_MASK_TARGET + | SSAM_EVENT_MASK_INSTANCE, +}; + +/** + * SSAM_EVENT_REGISTRY() - Define a new event registry. + * @tc: Target category for the event registry requests. + * @tid: Target ID for the event registry requests. + * @cid_en: Command ID for the event-enable request. + * @cid_dis: Command ID for the event-disable request. + * + * Return: Returns the &struct ssam_event_registry specified by the given + * parameters. + */ +#define SSAM_EVENT_REGISTRY(tc, tid, cid_en, cid_dis) \ + ((struct ssam_event_registry) { \ + .target_category = (tc), \ + .target_id = (tid), \ + .cid_enable = (cid_en), \ + .cid_disable = (cid_dis), \ + }) + +#define SSAM_EVENT_REGISTRY_SAM \ + SSAM_EVENT_REGISTRY(SSAM_SSH_TC_SAM, 0x01, 0x0b, 0x0c) + +#define SSAM_EVENT_REGISTRY_KIP \ + SSAM_EVENT_REGISTRY(SSAM_SSH_TC_KIP, 0x02, 0x27, 0x28) + +#define SSAM_EVENT_REGISTRY_REG \ + SSAM_EVENT_REGISTRY(SSAM_SSH_TC_REG, 0x02, 0x01, 0x02) + +/** + * struct ssam_event_notifier - Notifier block for SSAM events. + * @base: The base notifier block with callback function and priority. + * @event: The event for which this block will receive notifications. + * @event.reg: Registry via which the event will be enabled/disabled. + * @event.id: ID specifying the event. + * @event.mask: Flags determining how events are matched to the notifier. + * @event.flags: Flags used for enabling the event. + */ +struct ssam_event_notifier { + struct ssam_notifier_block base; + + struct { + struct ssam_event_registry reg; + struct ssam_event_id id; + enum ssam_event_mask mask; + u8 flags; + } event; +}; + +int ssam_notifier_register(struct ssam_controller *ctrl, + struct ssam_event_notifier *n); + +int ssam_notifier_unregister(struct ssam_controller *ctrl, + struct ssam_event_notifier *n); + +#endif /* _LINUX_SURFACE_AGGREGATOR_CONTROLLER_H */ diff --git a/include/linux/surface_aggregator/serial_hub.h b/include/linux/surface_aggregator/serial_hub.h new file mode 100644 index 000000000000..64276fbfa1d5 --- /dev/null +++ b/include/linux/surface_aggregator/serial_hub.h @@ -0,0 +1,672 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Surface Serial Hub (SSH) protocol and communication interface. + * + * Lower-level communication layers and SSH protocol definitions for the + * Surface System Aggregator Module (SSAM). Provides the interface for basic + * packet- and request-based communication with the SSAM EC via SSH. + * + * Copyright (C) 2019-2020 Maximilian Luz + */ + +#ifndef _LINUX_SURFACE_AGGREGATOR_SERIAL_HUB_H +#define _LINUX_SURFACE_AGGREGATOR_SERIAL_HUB_H + +#include +#include +#include +#include +#include + + +/* -- Data structures for SAM-over-SSH communication. ----------------------- */ + +/** + * enum ssh_frame_type - Frame types for SSH frames. + * + * @SSH_FRAME_TYPE_DATA_SEQ: + * Indicates a data frame, followed by a payload with the length specified + * in the ``struct ssh_frame.len`` field. This frame is sequenced, meaning + * that an ACK is required. + * + * @SSH_FRAME_TYPE_DATA_NSQ: + * Same as %SSH_FRAME_TYPE_DATA_SEQ, but unsequenced, meaning that the + * message does not have to be ACKed. + * + * @SSH_FRAME_TYPE_ACK: + * Indicates an ACK message. + * + * @SSH_FRAME_TYPE_NAK: + * Indicates an error response for previously sent frame. In general, this + * means that the frame and/or payload is malformed, e.g. a CRC is wrong. + * For command-type payloads, this can also mean that the command is + * invalid. + */ +enum ssh_frame_type { + SSH_FRAME_TYPE_DATA_SEQ = 0x80, + SSH_FRAME_TYPE_DATA_NSQ = 0x00, + SSH_FRAME_TYPE_ACK = 0x40, + SSH_FRAME_TYPE_NAK = 0x04, +}; + +/** + * struct ssh_frame - SSH communication frame. + * @type: The type of the frame. See &enum ssh_frame_type. + * @len: The length of the frame payload directly following the CRC for this + * frame. Does not include the final CRC for that payload. + * @seq: The sequence number for this message/exchange. + */ +struct ssh_frame { + u8 type; + __le16 len; + u8 seq; +} __packed; + +static_assert(sizeof(struct ssh_frame) == 4); + +/* + * SSH_FRAME_MAX_PAYLOAD_SIZE - Maximum SSH frame payload length in bytes. + * + * This is the physical maximum length of the protocol. Implementations may + * set a more constrained limit. + */ +#define SSH_FRAME_MAX_PAYLOAD_SIZE U16_MAX + +/** + * enum ssh_payload_type - Type indicator for the SSH payload. + * @SSH_PLD_TYPE_CMD: The payload is a command structure with optional command + * payload. + */ +enum ssh_payload_type { + SSH_PLD_TYPE_CMD = 0x80, +}; + +/** + * struct ssh_command - Payload of a command-type frame. + * @type: The type of the payload. See &enum ssh_payload_type. Should be + * SSH_PLD_TYPE_CMD for this struct. + * @tc: Command target category. + * @tid_out: Output target ID. Should be zero if this an incoming (EC to host) + * message. + * @tid_in: Input target ID. Should be zero if this is an outgoing (host to + * EC) message. + * @iid: Instance ID. + * @rqid: Request ID. Used to match requests with responses and differentiate + * between responses and events. + * @cid: Command ID. + */ +struct ssh_command { + u8 type; + u8 tc; + u8 tid_out; + u8 tid_in; + u8 iid; + __le16 rqid; + u8 cid; +} __packed; + +static_assert(sizeof(struct ssh_command) == 8); + +/* + * SSH_COMMAND_MAX_PAYLOAD_SIZE - Maximum SSH command payload length in bytes. + * + * This is the physical maximum length of the protocol. Implementations may + * set a more constrained limit. + */ +#define SSH_COMMAND_MAX_PAYLOAD_SIZE \ + (SSH_FRAME_MAX_PAYLOAD_SIZE - sizeof(struct ssh_command)) + +/* + * SSH_MSG_LEN_BASE - Base-length of a SSH message. + * + * This is the minimum number of bytes required to form a message. The actual + * message length is SSH_MSG_LEN_BASE plus the length of the frame payload. + */ +#define SSH_MSG_LEN_BASE (sizeof(struct ssh_frame) + 3ull * sizeof(u16)) + +/* + * SSH_MSG_LEN_CTRL - Length of a SSH control message. + * + * This is the length of a SSH control message, which is equal to a SSH + * message without any payload. + */ +#define SSH_MSG_LEN_CTRL SSH_MSG_LEN_BASE + +/** + * SSH_MESSAGE_LENGTH() - Compute length of SSH message. + * @payload_size: Length of the payload inside the SSH frame. + * + * Return: Returns the length of a SSH message with payload of specified size. + */ +#define SSH_MESSAGE_LENGTH(payload_size) (SSH_MSG_LEN_BASE + (payload_size)) + +/** + * SSH_COMMAND_MESSAGE_LENGTH() - Compute length of SSH command message. + * @payload_size: Length of the command payload. + * + * Return: Returns the length of a SSH command message with command payload of + * specified size. + */ +#define SSH_COMMAND_MESSAGE_LENGTH(payload_size) \ + SSH_MESSAGE_LENGTH(sizeof(struct ssh_command) + (payload_size)) + +/** + * SSH_MSGOFFSET_FRAME() - Compute offset in SSH message to specified field in + * frame. + * @field: The field for which the offset should be computed. + * + * Return: Returns the offset of the specified &struct ssh_frame field in the + * raw SSH message data as. Takes SYN bytes (u16) preceding the frame into + * account. + */ +#define SSH_MSGOFFSET_FRAME(field) \ + (sizeof(u16) + offsetof(struct ssh_frame, field)) + +/** + * SSH_MSGOFFSET_COMMAND() - Compute offset in SSH message to specified field + * in command. + * @field: The field for which the offset should be computed. + * + * Return: Returns the offset of the specified &struct ssh_command field in + * the raw SSH message data. Takes SYN bytes (u16) preceding the frame and the + * frame CRC (u16) between frame and command into account. + */ +#define SSH_MSGOFFSET_COMMAND(field) \ + (2ull * sizeof(u16) + sizeof(struct ssh_frame) \ + + offsetof(struct ssh_command, field)) + +/* + * SSH_MSG_SYN - SSH message synchronization (SYN) bytes as u16. + */ +#define SSH_MSG_SYN ((u16)0x55aa) + +/** + * ssh_crc() - Compute CRC for SSH messages. + * @buf: The pointer pointing to the data for which the CRC should be computed. + * @len: The length of the data for which the CRC should be computed. + * + * Return: Returns the CRC computed on the provided data, as used for SSH + * messages. + */ +static inline u16 ssh_crc(const u8 *buf, size_t len) +{ + return crc_ccitt_false(0xffff, buf, len); +} + +/* + * SSH_NUM_EVENTS - The number of reserved event IDs. + * + * The number of reserved event IDs, used for registering an SSH event + * handler. Valid event IDs are numbers below or equal to this value, with + * exception of zero, which is not an event ID. Thus, this is also the + * absolute maximum number of event handlers that can be registered. + */ +#define SSH_NUM_EVENTS 34 + +/* + * SSH_NUM_TARGETS - The number of communication targets used in the protocol. + */ +#define SSH_NUM_TARGETS 2 + +/** + * ssh_rqid_next_valid() - Return the next valid request ID. + * @rqid: The current request ID. + * + * Return: Returns the next valid request ID, following the current request ID + * provided to this function. This function skips any request IDs reserved for + * events. + */ +static inline u16 ssh_rqid_next_valid(u16 rqid) +{ + return rqid > 0 ? rqid + 1u : rqid + SSH_NUM_EVENTS + 1u; +} + +/** + * ssh_rqid_to_event() - Convert request ID to its corresponding event ID. + * @rqid: The request ID to convert. + */ +static inline u16 ssh_rqid_to_event(u16 rqid) +{ + return rqid - 1u; +} + +/** + * ssh_rqid_is_event() - Check if given request ID is a valid event ID. + * @rqid: The request ID to check. + */ +static inline bool ssh_rqid_is_event(u16 rqid) +{ + return ssh_rqid_to_event(rqid) < SSH_NUM_EVENTS; +} + +/** + * ssh_tc_to_rqid() - Convert target category to its corresponding request ID. + * @tc: The target category to convert. + */ +static inline u16 ssh_tc_to_rqid(u8 tc) +{ + return tc; +} + +/** + * ssh_tid_to_index() - Convert target ID to its corresponding target index. + * @tid: The target ID to convert. + */ +static inline u8 ssh_tid_to_index(u8 tid) +{ + return tid - 1u; +} + +/** + * ssh_tid_is_valid() - Check if target ID is valid/supported. + * @tid: The target ID to check. + */ +static inline bool ssh_tid_is_valid(u8 tid) +{ + return ssh_tid_to_index(tid) < SSH_NUM_TARGETS; +} + +/** + * struct ssam_span - Reference to a buffer region. + * @ptr: Pointer to the buffer region. + * @len: Length of the buffer region. + * + * A reference to a (non-owned) buffer segment, consisting of pointer and + * length. Use of this struct indicates non-owned data, i.e. data of which the + * life-time is managed (i.e. it is allocated/freed) via another pointer. + */ +struct ssam_span { + u8 *ptr; + size_t len; +}; + +/* + * Known SSH/EC target categories. + * + * List of currently known target category values; "Known" as in we know they + * exist and are valid on at least some device/model. Detailed functionality + * or the full category name is only known for some of these categories and + * is detailed in the respective comment below. + * + * These values and abbreviations have been extracted from strings inside the + * Windows driver. + */ +enum ssam_ssh_tc { + /* Category 0x00 is invalid for EC use. */ + SSAM_SSH_TC_SAM = 0x01, /* Generic system functionality, real-time clock. */ + SSAM_SSH_TC_BAT = 0x02, /* Battery/power subsystem. */ + SSAM_SSH_TC_TMP = 0x03, /* Thermal subsystem. */ + SSAM_SSH_TC_PMC = 0x04, + SSAM_SSH_TC_FAN = 0x05, + SSAM_SSH_TC_PoM = 0x06, + SSAM_SSH_TC_DBG = 0x07, + SSAM_SSH_TC_KBD = 0x08, /* Legacy keyboard (Laptop 1/2). */ + SSAM_SSH_TC_FWU = 0x09, + SSAM_SSH_TC_UNI = 0x0a, + SSAM_SSH_TC_LPC = 0x0b, + SSAM_SSH_TC_TCL = 0x0c, + SSAM_SSH_TC_SFL = 0x0d, + SSAM_SSH_TC_KIP = 0x0e, + SSAM_SSH_TC_EXT = 0x0f, + SSAM_SSH_TC_BLD = 0x10, + SSAM_SSH_TC_BAS = 0x11, /* Detachment system (Surface Book 2/3). */ + SSAM_SSH_TC_SEN = 0x12, + SSAM_SSH_TC_SRQ = 0x13, + SSAM_SSH_TC_MCU = 0x14, + SSAM_SSH_TC_HID = 0x15, /* Generic HID input subsystem. */ + SSAM_SSH_TC_TCH = 0x16, + SSAM_SSH_TC_BKL = 0x17, + SSAM_SSH_TC_TAM = 0x18, + SSAM_SSH_TC_ACC = 0x19, + SSAM_SSH_TC_UFI = 0x1a, + SSAM_SSH_TC_USC = 0x1b, + SSAM_SSH_TC_PEN = 0x1c, + SSAM_SSH_TC_VID = 0x1d, + SSAM_SSH_TC_AUD = 0x1e, + SSAM_SSH_TC_SMC = 0x1f, + SSAM_SSH_TC_KPD = 0x20, + SSAM_SSH_TC_REG = 0x21, /* Extended event registry. */ +}; + + +/* -- Packet transport layer (ptl). ----------------------------------------- */ + +/** + * enum ssh_packet_base_priority - Base priorities for &struct ssh_packet. + * @SSH_PACKET_PRIORITY_FLUSH: Base priority for flush packets. + * @SSH_PACKET_PRIORITY_DATA: Base priority for normal data packets. + * @SSH_PACKET_PRIORITY_NAK: Base priority for NAK packets. + * @SSH_PACKET_PRIORITY_ACK: Base priority for ACK packets. + */ +enum ssh_packet_base_priority { + SSH_PACKET_PRIORITY_FLUSH = 0, /* same as DATA to sequence flush */ + SSH_PACKET_PRIORITY_DATA = 0, + SSH_PACKET_PRIORITY_NAK = 1, + SSH_PACKET_PRIORITY_ACK = 2, +}; + +/* + * Same as SSH_PACKET_PRIORITY() below, only with actual values. + */ +#define __SSH_PACKET_PRIORITY(base, try) \ + (((base) << 4) | ((try) & 0x0f)) + +/** + * SSH_PACKET_PRIORITY() - Compute packet priority from base priority and + * number of tries. + * @base: The base priority as suffix of &enum ssh_packet_base_priority, e.g. + * ``FLUSH``, ``DATA``, ``ACK``, or ``NAK``. + * @try: The number of tries (must be less than 16). + * + * Compute the combined packet priority. The combined priority is dominated by + * the base priority, whereas the number of (re-)tries decides the precedence + * of packets with the same base priority, giving higher priority to packets + * that already have more tries. + * + * Return: Returns the computed priority as value fitting inside a &u8. A + * higher number means a higher priority. + */ +#define SSH_PACKET_PRIORITY(base, try) \ + __SSH_PACKET_PRIORITY(SSH_PACKET_PRIORITY_##base, (try)) + +/** + * ssh_packet_priority_get_try() - Get number of tries from packet priority. + * @priority: The packet priority. + * + * Return: Returns the number of tries encoded in the specified packet + * priority. + */ +static inline u8 ssh_packet_priority_get_try(u8 priority) +{ + return priority & 0x0f; +} + +/** + * ssh_packet_priority_get_base - Get base priority from packet priority. + * @priority: The packet priority. + * + * Return: Returns the base priority encoded in the given packet priority. + */ +static inline u8 ssh_packet_priority_get_base(u8 priority) +{ + return (priority & 0xf0) >> 4; +} + +enum ssh_packet_flags { + /* state flags */ + SSH_PACKET_SF_LOCKED_BIT, + SSH_PACKET_SF_QUEUED_BIT, + SSH_PACKET_SF_PENDING_BIT, + SSH_PACKET_SF_TRANSMITTING_BIT, + SSH_PACKET_SF_TRANSMITTED_BIT, + SSH_PACKET_SF_ACKED_BIT, + SSH_PACKET_SF_CANCELED_BIT, + SSH_PACKET_SF_COMPLETED_BIT, + + /* type flags */ + SSH_PACKET_TY_FLUSH_BIT, + SSH_PACKET_TY_SEQUENCED_BIT, + SSH_PACKET_TY_BLOCKING_BIT, + + /* mask for state flags */ + SSH_PACKET_FLAGS_SF_MASK = + BIT(SSH_PACKET_SF_LOCKED_BIT) + | BIT(SSH_PACKET_SF_QUEUED_BIT) + | BIT(SSH_PACKET_SF_PENDING_BIT) + | BIT(SSH_PACKET_SF_TRANSMITTING_BIT) + | BIT(SSH_PACKET_SF_TRANSMITTED_BIT) + | BIT(SSH_PACKET_SF_ACKED_BIT) + | BIT(SSH_PACKET_SF_CANCELED_BIT) + | BIT(SSH_PACKET_SF_COMPLETED_BIT), + + /* mask for type flags */ + SSH_PACKET_FLAGS_TY_MASK = + BIT(SSH_PACKET_TY_FLUSH_BIT) + | BIT(SSH_PACKET_TY_SEQUENCED_BIT) + | BIT(SSH_PACKET_TY_BLOCKING_BIT), +}; + +struct ssh_ptl; +struct ssh_packet; + +/** + * struct ssh_packet_ops - Callback operations for a SSH packet. + * @release: Function called when the packet reference count reaches zero. + * This callback must be relied upon to ensure that the packet has + * left the transport system(s). + * @complete: Function called when the packet is completed, either with + * success or failure. In case of failure, the reason for the + * failure is indicated by the value of the provided status code + * argument. This value will be zero in case of success. Note that + * a call to this callback does not guarantee that the packet is + * not in use by the transport system any more. + */ +struct ssh_packet_ops { + void (*release)(struct ssh_packet *p); + void (*complete)(struct ssh_packet *p, int status); +}; + +/** + * struct ssh_packet - SSH transport packet. + * @ptl: Pointer to the packet transport layer. May be %NULL if the packet + * (or enclosing request) has not been submitted yet. + * @refcnt: Reference count of the packet. + * @priority: Priority of the packet. Must be computed via + * SSH_PACKET_PRIORITY(). Must only be accessed while holding the + * queue lock after first submission. + * @data: Raw message data. + * @data.len: Length of the raw message data. + * @data.ptr: Pointer to the raw message data buffer. + * @state: State and type flags describing current packet state (dynamic) + * and type (static). See &enum ssh_packet_flags for possible + * options. + * @timestamp: Timestamp specifying when the latest transmission of a + * currently pending packet has been started. May be %KTIME_MAX + * before or in-between transmission attempts. Used for the packet + * timeout implementation. Must only be accessed while holding the + * pending lock after first submission. + * @queue_node: The list node for the packet queue. + * @pending_node: The list node for the set of pending packets. + * @ops: Packet operations. + */ +struct ssh_packet { + struct ssh_ptl *ptl; + struct kref refcnt; + + u8 priority; + + struct { + size_t len; + u8 *ptr; + } data; + + unsigned long state; + ktime_t timestamp; + + struct list_head queue_node; + struct list_head pending_node; + + const struct ssh_packet_ops *ops; +}; + +struct ssh_packet *ssh_packet_get(struct ssh_packet *p); +void ssh_packet_put(struct ssh_packet *p); + +/** + * ssh_packet_set_data() - Set raw message data of packet. + * @p: The packet for which the message data should be set. + * @ptr: Pointer to the memory holding the message data. + * @len: Length of the message data. + * + * Sets the raw message data buffer of the packet to the provided memory. The + * memory is not copied. Instead, the caller is responsible for management + * (i.e. allocation and deallocation) of the memory. The caller must ensure + * that the provided memory is valid and contains a valid SSH message, + * starting from the time of submission of the packet until the ``release`` + * callback has been called. During this time, the memory may not be altered + * in any way. + */ +static inline void ssh_packet_set_data(struct ssh_packet *p, u8 *ptr, size_t len) +{ + p->data.ptr = ptr; + p->data.len = len; +} + + +/* -- Request transport layer (rtl). ---------------------------------------- */ + +enum ssh_request_flags { + /* state flags */ + SSH_REQUEST_SF_LOCKED_BIT, + SSH_REQUEST_SF_QUEUED_BIT, + SSH_REQUEST_SF_PENDING_BIT, + SSH_REQUEST_SF_TRANSMITTING_BIT, + SSH_REQUEST_SF_TRANSMITTED_BIT, + SSH_REQUEST_SF_RSPRCVD_BIT, + SSH_REQUEST_SF_CANCELED_BIT, + SSH_REQUEST_SF_COMPLETED_BIT, + + /* type flags */ + SSH_REQUEST_TY_FLUSH_BIT, + SSH_REQUEST_TY_HAS_RESPONSE_BIT, + + /* mask for state flags */ + SSH_REQUEST_FLAGS_SF_MASK = + BIT(SSH_REQUEST_SF_LOCKED_BIT) + | BIT(SSH_REQUEST_SF_QUEUED_BIT) + | BIT(SSH_REQUEST_SF_PENDING_BIT) + | BIT(SSH_REQUEST_SF_TRANSMITTING_BIT) + | BIT(SSH_REQUEST_SF_TRANSMITTED_BIT) + | BIT(SSH_REQUEST_SF_RSPRCVD_BIT) + | BIT(SSH_REQUEST_SF_CANCELED_BIT) + | BIT(SSH_REQUEST_SF_COMPLETED_BIT), + + /* mask for type flags */ + SSH_REQUEST_FLAGS_TY_MASK = + BIT(SSH_REQUEST_TY_FLUSH_BIT) + | BIT(SSH_REQUEST_TY_HAS_RESPONSE_BIT), +}; + +struct ssh_rtl; +struct ssh_request; + +/** + * struct ssh_request_ops - Callback operations for a SSH request. + * @release: Function called when the request's reference count reaches zero. + * This callback must be relied upon to ensure that the request has + * left the transport systems (both, packet an request systems). + * @complete: Function called when the request is completed, either with + * success or failure. The command data for the request response + * is provided via the &struct ssh_command parameter (``cmd``), + * the command payload of the request response via the &struct + * ssh_span parameter (``data``). + * + * If the request does not have any response or has not been + * completed with success, both ``cmd`` and ``data`` parameters will + * be NULL. If the request response does not have any command + * payload, the ``data`` span will be an empty (zero-length) span. + * + * In case of failure, the reason for the failure is indicated by + * the value of the provided status code argument (``status``). This + * value will be zero in case of success and a regular errno + * otherwise. + * + * Note that a call to this callback does not guarantee that the + * request is not in use by the transport systems any more. + */ +struct ssh_request_ops { + void (*release)(struct ssh_request *rqst); + void (*complete)(struct ssh_request *rqst, + const struct ssh_command *cmd, + const struct ssam_span *data, int status); +}; + +/** + * struct ssh_request - SSH transport request. + * @packet: The underlying SSH transport packet. + * @node: List node for the request queue and pending set. + * @state: State and type flags describing current request state (dynamic) + * and type (static). See &enum ssh_request_flags for possible + * options. + * @timestamp: Timestamp specifying when we start waiting on the response of + * the request. This is set once the underlying packet has been + * completed and may be %KTIME_MAX before that, or when the request + * does not expect a response. Used for the request timeout + * implementation. + * @ops: Request Operations. + */ +struct ssh_request { + struct ssh_packet packet; + struct list_head node; + + unsigned long state; + ktime_t timestamp; + + const struct ssh_request_ops *ops; +}; + +/** + * to_ssh_request() - Cast a SSH packet to its enclosing SSH request. + * @p: The packet to cast. + * + * Casts the given &struct ssh_packet to its enclosing &struct ssh_request. + * The caller is responsible for making sure that the packet is actually + * wrapped in a &struct ssh_request. + * + * Return: Returns the &struct ssh_request wrapping the provided packet. + */ +static inline struct ssh_request *to_ssh_request(struct ssh_packet *p) +{ + return container_of(p, struct ssh_request, packet); +} + +/** + * ssh_request_get() - Increment reference count of request. + * @r: The request to increment the reference count of. + * + * Increments the reference count of the given request by incrementing the + * reference count of the underlying &struct ssh_packet, enclosed in it. + * + * See also ssh_request_put(), ssh_packet_get(). + * + * Return: Returns the request provided as input. + */ +static inline struct ssh_request *ssh_request_get(struct ssh_request *r) +{ + return r ? to_ssh_request(ssh_packet_get(&r->packet)) : NULL; +} + +/** + * ssh_request_put() - Decrement reference count of request. + * @r: The request to decrement the reference count of. + * + * Decrements the reference count of the given request by decrementing the + * reference count of the underlying &struct ssh_packet, enclosed in it. If + * the reference count reaches zero, the ``release`` callback specified in the + * request's &struct ssh_request_ops, i.e. ``r->ops->release``, will be + * called. + * + * See also ssh_request_get(), ssh_packet_put(). + */ +static inline void ssh_request_put(struct ssh_request *r) +{ + if (r) + ssh_packet_put(&r->packet); +} + +/** + * ssh_request_set_data() - Set raw message data of request. + * @r: The request for which the message data should be set. + * @ptr: Pointer to the memory holding the message data. + * @len: Length of the message data. + * + * Sets the raw message data buffer of the underlying packet to the specified + * buffer. Does not copy the actual message data, just sets the buffer pointer + * and length. Refer to ssh_packet_set_data() for more details. + */ +static inline void ssh_request_set_data(struct ssh_request *r, u8 *ptr, size_t len) +{ + ssh_packet_set_data(&r->packet, ptr, len); +} + +#endif /* _LINUX_SURFACE_AGGREGATOR_SERIAL_HUB_H */ -- cgit v1.2.3 From eb0e90a82098d4a48308abb87d2087578a83987f Mon Sep 17 00:00:00 2001 From: Maximilian Luz Date: Mon, 21 Dec 2020 19:39:56 +0100 Subject: platform/surface: aggregator: Add dedicated bus and device type The Surface Aggregator EC provides varying functionality, depending on the Surface device. To manage this functionality, we use dedicated client devices for each subsystem or virtual device of the EC. While some of these clients are described as standard devices in ACPI and the corresponding client drivers can be implemented as platform drivers in the kernel (making use of the controller API already present), many devices, especially on newer Surface models, cannot be found there. To simplify management of these devices, we introduce a new bus and client device type for the Surface Aggregator subsystem. The new device type takes care of managing the controller reference, essentially guaranteeing its validity for as long as the client device exists, thus alleviating the need to manually establish device links for that purpose in the client driver (as has to be done with the platform devices). Signed-off-by: Maximilian Luz Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20201221183959.1186143-7-luzmaximilian@gmail.com Signed-off-by: Hans de Goede --- include/linux/mod_devicetable.h | 18 ++ include/linux/surface_aggregator/device.h | 423 ++++++++++++++++++++++++++++++ 2 files changed, 441 insertions(+) create mode 100644 include/linux/surface_aggregator/device.h (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index c425290b21e2..935060955152 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -846,4 +846,22 @@ struct auxiliary_device_id { kernel_ulong_t driver_data; }; +/* Surface System Aggregator Module */ + +#define SSAM_MATCH_TARGET 0x1 +#define SSAM_MATCH_INSTANCE 0x2 +#define SSAM_MATCH_FUNCTION 0x4 + +struct ssam_device_id { + __u8 match_flags; + + __u8 domain; + __u8 category; + __u8 target; + __u8 instance; + __u8 function; + + kernel_ulong_t driver_data; +}; + #endif /* LINUX_MOD_DEVICETABLE_H */ diff --git a/include/linux/surface_aggregator/device.h b/include/linux/surface_aggregator/device.h new file mode 100644 index 000000000000..02f3e06c0a60 --- /dev/null +++ b/include/linux/surface_aggregator/device.h @@ -0,0 +1,423 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Surface System Aggregator Module (SSAM) bus and client-device subsystem. + * + * Main interface for the surface-aggregator bus, surface-aggregator client + * devices, and respective drivers building on top of the SSAM controller. + * Provides support for non-platform/non-ACPI SSAM clients via dedicated + * subsystem. + * + * Copyright (C) 2019-2020 Maximilian Luz + */ + +#ifndef _LINUX_SURFACE_AGGREGATOR_DEVICE_H +#define _LINUX_SURFACE_AGGREGATOR_DEVICE_H + +#include +#include +#include + +#include + + +/* -- Surface System Aggregator Module bus. --------------------------------- */ + +/** + * enum ssam_device_domain - SAM device domain. + * @SSAM_DOMAIN_VIRTUAL: Virtual device. + * @SSAM_DOMAIN_SERIALHUB: Physical device connected via Surface Serial Hub. + */ +enum ssam_device_domain { + SSAM_DOMAIN_VIRTUAL = 0x00, + SSAM_DOMAIN_SERIALHUB = 0x01, +}; + +/** + * enum ssam_virtual_tc - Target categories for the virtual SAM domain. + * @SSAM_VIRTUAL_TC_HUB: Device hub category. + */ +enum ssam_virtual_tc { + SSAM_VIRTUAL_TC_HUB = 0x00, +}; + +/** + * struct ssam_device_uid - Unique identifier for SSAM device. + * @domain: Domain of the device. + * @category: Target category of the device. + * @target: Target ID of the device. + * @instance: Instance ID of the device. + * @function: Sub-function of the device. This field can be used to split a + * single SAM device into multiple virtual subdevices to separate + * different functionality of that device and allow one driver per + * such functionality. + */ +struct ssam_device_uid { + u8 domain; + u8 category; + u8 target; + u8 instance; + u8 function; +}; + +/* + * Special values for device matching. + * + * These values are intended to be used with SSAM_DEVICE(), SSAM_VDEV(), and + * SSAM_SDEV() exclusively. Specifically, they are used to initialize the + * match_flags member of the device ID structure. Do not use them directly + * with struct ssam_device_id or struct ssam_device_uid. + */ +#define SSAM_ANY_TID 0xffff +#define SSAM_ANY_IID 0xffff +#define SSAM_ANY_FUN 0xffff + +/** + * SSAM_DEVICE() - Initialize a &struct ssam_device_id with the given + * parameters. + * @d: Domain of the device. + * @cat: Target category of the device. + * @tid: Target ID of the device. + * @iid: Instance ID of the device. + * @fun: Sub-function of the device. + * + * Initializes a &struct ssam_device_id with the given parameters. See &struct + * ssam_device_uid for details regarding the parameters. The special values + * %SSAM_ANY_TID, %SSAM_ANY_IID, and %SSAM_ANY_FUN can be used to specify that + * matching should ignore target ID, instance ID, and/or sub-function, + * respectively. This macro initializes the ``match_flags`` field based on the + * given parameters. + * + * Note: The parameters @d and @cat must be valid &u8 values, the parameters + * @tid, @iid, and @fun must be either valid &u8 values or %SSAM_ANY_TID, + * %SSAM_ANY_IID, or %SSAM_ANY_FUN, respectively. Other non-&u8 values are not + * allowed. + */ +#define SSAM_DEVICE(d, cat, tid, iid, fun) \ + .match_flags = (((tid) != SSAM_ANY_TID) ? SSAM_MATCH_TARGET : 0) \ + | (((iid) != SSAM_ANY_IID) ? SSAM_MATCH_INSTANCE : 0) \ + | (((fun) != SSAM_ANY_FUN) ? SSAM_MATCH_FUNCTION : 0), \ + .domain = d, \ + .category = cat, \ + .target = ((tid) != SSAM_ANY_TID) ? (tid) : 0, \ + .instance = ((iid) != SSAM_ANY_IID) ? (iid) : 0, \ + .function = ((fun) != SSAM_ANY_FUN) ? (fun) : 0 \ + +/** + * SSAM_VDEV() - Initialize a &struct ssam_device_id as virtual device with + * the given parameters. + * @cat: Target category of the device. + * @tid: Target ID of the device. + * @iid: Instance ID of the device. + * @fun: Sub-function of the device. + * + * Initializes a &struct ssam_device_id with the given parameters in the + * virtual domain. See &struct ssam_device_uid for details regarding the + * parameters. The special values %SSAM_ANY_TID, %SSAM_ANY_IID, and + * %SSAM_ANY_FUN can be used to specify that matching should ignore target ID, + * instance ID, and/or sub-function, respectively. This macro initializes the + * ``match_flags`` field based on the given parameters. + * + * Note: The parameter @cat must be a valid &u8 value, the parameters @tid, + * @iid, and @fun must be either valid &u8 values or %SSAM_ANY_TID, + * %SSAM_ANY_IID, or %SSAM_ANY_FUN, respectively. Other non-&u8 values are not + * allowed. + */ +#define SSAM_VDEV(cat, tid, iid, fun) \ + SSAM_DEVICE(SSAM_DOMAIN_VIRTUAL, SSAM_VIRTUAL_TC_##cat, tid, iid, fun) + +/** + * SSAM_SDEV() - Initialize a &struct ssam_device_id as physical SSH device + * with the given parameters. + * @cat: Target category of the device. + * @tid: Target ID of the device. + * @iid: Instance ID of the device. + * @fun: Sub-function of the device. + * + * Initializes a &struct ssam_device_id with the given parameters in the SSH + * domain. See &struct ssam_device_uid for details regarding the parameters. + * The special values %SSAM_ANY_TID, %SSAM_ANY_IID, and %SSAM_ANY_FUN can be + * used to specify that matching should ignore target ID, instance ID, and/or + * sub-function, respectively. This macro initializes the ``match_flags`` + * field based on the given parameters. + * + * Note: The parameter @cat must be a valid &u8 value, the parameters @tid, + * @iid, and @fun must be either valid &u8 values or %SSAM_ANY_TID, + * %SSAM_ANY_IID, or %SSAM_ANY_FUN, respectively. Other non-&u8 values are not + * allowed. + */ +#define SSAM_SDEV(cat, tid, iid, fun) \ + SSAM_DEVICE(SSAM_DOMAIN_SERIALHUB, SSAM_SSH_TC_##cat, tid, iid, fun) + +/** + * struct ssam_device - SSAM client device. + * @dev: Driver model representation of the device. + * @ctrl: SSAM controller managing this device. + * @uid: UID identifying the device. + */ +struct ssam_device { + struct device dev; + struct ssam_controller *ctrl; + + struct ssam_device_uid uid; +}; + +/** + * struct ssam_device_driver - SSAM client device driver. + * @driver: Base driver model structure. + * @match_table: Match table specifying which devices the driver should bind to. + * @probe: Called when the driver is being bound to a device. + * @remove: Called when the driver is being unbound from the device. + */ +struct ssam_device_driver { + struct device_driver driver; + + const struct ssam_device_id *match_table; + + int (*probe)(struct ssam_device *sdev); + void (*remove)(struct ssam_device *sdev); +}; + +extern struct bus_type ssam_bus_type; +extern const struct device_type ssam_device_type; + +/** + * is_ssam_device() - Check if the given device is a SSAM client device. + * @d: The device to test the type of. + * + * Return: Returns %true if the specified device is of type &struct + * ssam_device, i.e. the device type points to %ssam_device_type, and %false + * otherwise. + */ +static inline bool is_ssam_device(struct device *d) +{ + return d->type == &ssam_device_type; +} + +/** + * to_ssam_device() - Casts the given device to a SSAM client device. + * @d: The device to cast. + * + * Casts the given &struct device to a &struct ssam_device. The caller has to + * ensure that the given device is actually enclosed in a &struct ssam_device, + * e.g. by calling is_ssam_device(). + * + * Return: Returns a pointer to the &struct ssam_device wrapping the given + * device @d. + */ +static inline struct ssam_device *to_ssam_device(struct device *d) +{ + return container_of(d, struct ssam_device, dev); +} + +/** + * to_ssam_device_driver() - Casts the given device driver to a SSAM client + * device driver. + * @d: The driver to cast. + * + * Casts the given &struct device_driver to a &struct ssam_device_driver. The + * caller has to ensure that the given driver is actually enclosed in a + * &struct ssam_device_driver. + * + * Return: Returns the pointer to the &struct ssam_device_driver wrapping the + * given device driver @d. + */ +static inline +struct ssam_device_driver *to_ssam_device_driver(struct device_driver *d) +{ + return container_of(d, struct ssam_device_driver, driver); +} + +const struct ssam_device_id *ssam_device_id_match(const struct ssam_device_id *table, + const struct ssam_device_uid uid); + +const struct ssam_device_id *ssam_device_get_match(const struct ssam_device *dev); + +const void *ssam_device_get_match_data(const struct ssam_device *dev); + +struct ssam_device *ssam_device_alloc(struct ssam_controller *ctrl, + struct ssam_device_uid uid); + +int ssam_device_add(struct ssam_device *sdev); +void ssam_device_remove(struct ssam_device *sdev); + +/** + * ssam_device_get() - Increment reference count of SSAM client device. + * @sdev: The device to increment the reference count of. + * + * Increments the reference count of the given SSAM client device by + * incrementing the reference count of the enclosed &struct device via + * get_device(). + * + * See ssam_device_put() for the counter-part of this function. + * + * Return: Returns the device provided as input. + */ +static inline struct ssam_device *ssam_device_get(struct ssam_device *sdev) +{ + return sdev ? to_ssam_device(get_device(&sdev->dev)) : NULL; +} + +/** + * ssam_device_put() - Decrement reference count of SSAM client device. + * @sdev: The device to decrement the reference count of. + * + * Decrements the reference count of the given SSAM client device by + * decrementing the reference count of the enclosed &struct device via + * put_device(). + * + * See ssam_device_get() for the counter-part of this function. + */ +static inline void ssam_device_put(struct ssam_device *sdev) +{ + if (sdev) + put_device(&sdev->dev); +} + +/** + * ssam_device_get_drvdata() - Get driver-data of SSAM client device. + * @sdev: The device to get the driver-data from. + * + * Return: Returns the driver-data of the given device, previously set via + * ssam_device_set_drvdata(). + */ +static inline void *ssam_device_get_drvdata(struct ssam_device *sdev) +{ + return dev_get_drvdata(&sdev->dev); +} + +/** + * ssam_device_set_drvdata() - Set driver-data of SSAM client device. + * @sdev: The device to set the driver-data of. + * @data: The data to set the device's driver-data pointer to. + */ +static inline void ssam_device_set_drvdata(struct ssam_device *sdev, void *data) +{ + dev_set_drvdata(&sdev->dev, data); +} + +int __ssam_device_driver_register(struct ssam_device_driver *d, struct module *o); +void ssam_device_driver_unregister(struct ssam_device_driver *d); + +/** + * ssam_device_driver_register() - Register a SSAM client device driver. + * @drv: The driver to register. + */ +#define ssam_device_driver_register(drv) \ + __ssam_device_driver_register(drv, THIS_MODULE) + +/** + * module_ssam_device_driver() - Helper macro for SSAM device driver + * registration. + * @drv: The driver managed by this module. + * + * Helper macro to register a SSAM device driver via module_init() and + * module_exit(). This macro may only be used once per module and replaces the + * aforementioned definitions. + */ +#define module_ssam_device_driver(drv) \ + module_driver(drv, ssam_device_driver_register, \ + ssam_device_driver_unregister) + + +/* -- Helpers for client-device requests. ----------------------------------- */ + +/** + * SSAM_DEFINE_SYNC_REQUEST_CL_N() - Define synchronous client-device SAM + * request function with neither argument nor return value. + * @name: Name of the generated function. + * @spec: Specification (&struct ssam_request_spec_md) defining the request. + * + * Defines a function executing the synchronous SAM request specified by + * @spec, with the request having neither argument nor return value. Device + * specifying parameters are not hard-coded, but instead are provided via the + * client device, specifically its UID, supplied when calling this function. + * The generated function takes care of setting up the request struct, buffer + * allocation, as well as execution of the request itself, returning once the + * request has been fully completed. The required transport buffer will be + * allocated on the stack. + * + * The generated function is defined as ``int name(struct ssam_device *sdev)``, + * returning the status of the request, which is zero on success and negative + * on failure. The ``sdev`` parameter specifies both the target device of the + * request and by association the controller via which the request is sent. + * + * Refer to ssam_request_sync_onstack() for more details on the behavior of + * the generated function. + */ +#define SSAM_DEFINE_SYNC_REQUEST_CL_N(name, spec...) \ + SSAM_DEFINE_SYNC_REQUEST_MD_N(__raw_##name, spec) \ + int name(struct ssam_device *sdev) \ + { \ + return __raw_##name(sdev->ctrl, sdev->uid.target, \ + sdev->uid.instance); \ + } + +/** + * SSAM_DEFINE_SYNC_REQUEST_CL_W() - Define synchronous client-device SAM + * request function with argument. + * @name: Name of the generated function. + * @atype: Type of the request's argument. + * @spec: Specification (&struct ssam_request_spec_md) defining the request. + * + * Defines a function executing the synchronous SAM request specified by + * @spec, with the request taking an argument of type @atype and having no + * return value. Device specifying parameters are not hard-coded, but instead + * are provided via the client device, specifically its UID, supplied when + * calling this function. The generated function takes care of setting up the + * request struct, buffer allocation, as well as execution of the request + * itself, returning once the request has been fully completed. The required + * transport buffer will be allocated on the stack. + * + * The generated function is defined as ``int name(struct ssam_device *sdev, + * const atype *arg)``, returning the status of the request, which is zero on + * success and negative on failure. The ``sdev`` parameter specifies both the + * target device of the request and by association the controller via which + * the request is sent. The request's argument is specified via the ``arg`` + * pointer. + * + * Refer to ssam_request_sync_onstack() for more details on the behavior of + * the generated function. + */ +#define SSAM_DEFINE_SYNC_REQUEST_CL_W(name, atype, spec...) \ + SSAM_DEFINE_SYNC_REQUEST_MD_W(__raw_##name, atype, spec) \ + int name(struct ssam_device *sdev, const atype *arg) \ + { \ + return __raw_##name(sdev->ctrl, sdev->uid.target, \ + sdev->uid.instance, arg); \ + } + +/** + * SSAM_DEFINE_SYNC_REQUEST_CL_R() - Define synchronous client-device SAM + * request function with return value. + * @name: Name of the generated function. + * @rtype: Type of the request's return value. + * @spec: Specification (&struct ssam_request_spec_md) defining the request. + * + * Defines a function executing the synchronous SAM request specified by + * @spec, with the request taking no argument but having a return value of + * type @rtype. Device specifying parameters are not hard-coded, but instead + * are provided via the client device, specifically its UID, supplied when + * calling this function. The generated function takes care of setting up the + * request struct, buffer allocation, as well as execution of the request + * itself, returning once the request has been fully completed. The required + * transport buffer will be allocated on the stack. + * + * The generated function is defined as ``int name(struct ssam_device *sdev, + * rtype *ret)``, returning the status of the request, which is zero on + * success and negative on failure. The ``sdev`` parameter specifies both the + * target device of the request and by association the controller via which + * the request is sent. The request's return value is written to the memory + * pointed to by the ``ret`` parameter. + * + * Refer to ssam_request_sync_onstack() for more details on the behavior of + * the generated function. + */ +#define SSAM_DEFINE_SYNC_REQUEST_CL_R(name, rtype, spec...) \ + SSAM_DEFINE_SYNC_REQUEST_MD_R(__raw_##name, rtype, spec) \ + int name(struct ssam_device *sdev, rtype *ret) \ + { \ + return __raw_##name(sdev->ctrl, sdev->uid.target, \ + sdev->uid.instance, ret); \ + } + +#endif /* _LINUX_SURFACE_AGGREGATOR_DEVICE_H */ -- cgit v1.2.3 From fc00bc8ac1dada4085f9308f85f2d6359da0faa8 Mon Sep 17 00:00:00 2001 From: Maximilian Luz Date: Mon, 21 Dec 2020 19:39:59 +0100 Subject: platform/surface: Add Surface ACPI Notify driver The Surface ACPI Notify (SAN) device provides an ACPI interface to the Surface Aggregator EC, specifically the Surface Serial Hub interface. This interface allows EC requests to be made from ACPI code and can convert a subset of EC events back to ACPI notifications. Specifically, this interface provides a GenericSerialBus operation region ACPI code can execute a request by writing the request command data and payload to this operation region and reading back the corresponding response via a write-then-read operation. Furthermore, this interface provides a _DSM method to be called when certain events from the EC have been received, essentially turning them into ACPI notifications. The driver provided in this commit essentially takes care of translating the request data written to the operation region, executing the request, waiting for it to finish, and finally writing and translating back the response (if the request has one). Furthermore, this driver takes care of enabling the events handled via ACPI _DSM calls. Lastly, this driver also exposes an interface providing discrete GPU (dGPU) power-on notifications on the Surface Book 2, which are also received via the operation region interface (but not handled by the SAN driver directly), making them accessible to other drivers (such as a dGPU hot-plug driver that may be added later on). On 5th and 6th generation Surface devices (Surface Pro 5/2017, Pro 6, Book 2, Laptop 1 and 2), the SAN interface provides full battery and thermal subsystem access, as well as other EC based functionality. On those models, battery and thermal sensor devices are implemented as standard ACPI devices of that type, however, forward ACPI calls to the corresponding Surface Aggregator EC request via the SAN interface and receive corresponding notifications (e.g. battery information change) from it. This interface is therefore required to provide said functionality on those devices. Signed-off-by: Maximilian Luz Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20201221183959.1186143-10-luzmaximilian@gmail.com Signed-off-by: Hans de Goede --- include/linux/surface_acpi_notify.h | 39 +++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) create mode 100644 include/linux/surface_acpi_notify.h (limited to 'include/linux') diff --git a/include/linux/surface_acpi_notify.h b/include/linux/surface_acpi_notify.h new file mode 100644 index 000000000000..8e3e86c7d78c --- /dev/null +++ b/include/linux/surface_acpi_notify.h @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Interface for Surface ACPI Notify (SAN) driver. + * + * Provides access to discrete GPU notifications sent from ACPI via the SAN + * driver, which are not handled by this driver directly. + * + * Copyright (C) 2019-2020 Maximilian Luz + */ + +#ifndef _LINUX_SURFACE_ACPI_NOTIFY_H +#define _LINUX_SURFACE_ACPI_NOTIFY_H + +#include +#include + +/** + * struct san_dgpu_event - Discrete GPU ACPI event. + * @category: Category of the event. + * @target: Target ID of the event source. + * @command: Command ID of the event. + * @instance: Instance ID of the event source. + * @length: Length of the event's payload data (in bytes). + * @payload: Pointer to the event's payload data. + */ +struct san_dgpu_event { + u8 category; + u8 target; + u8 command; + u8 instance; + u16 length; + u8 *payload; +}; + +int san_client_link(struct device *client); +int san_dgpu_notifier_register(struct notifier_block *nb); +int san_dgpu_notifier_unregister(struct notifier_block *nb); + +#endif /* _LINUX_SURFACE_ACPI_NOTIFY_H */ -- cgit v1.2.3 From ae5c2341ed3987bd434ed495bd4f3d8b2bc3e623 Mon Sep 17 00:00:00 2001 From: "Joel Fernandes (Google)" Date: Wed, 23 Sep 2020 11:22:09 -0400 Subject: rcu/segcblist: Add counters to segcblist datastructure Add counting of segment lengths of segmented callback list. This will be useful for a number of things such as knowing how big the ready-to-execute segment have gotten. The immediate benefit is ability to trace how the callbacks in the segmented callback list change. Also this patch remove hacks related to using donecbs's ->len field as a temporary variable to save the segmented callback list's length. This cannot be done anymore and is not needed. Also fix SRCU: The negative counting of the unsegmented list cannot be used to adjust the segmented one. To fix this, sample the unsegmented length in advance, and use it after CB execution to adjust the segmented list's length. Reviewed-by: Frederic Weisbecker Signed-off-by: Joel Fernandes (Google) Signed-off-by: Paul E. McKenney --- include/linux/rcu_segcblist.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/rcu_segcblist.h b/include/linux/rcu_segcblist.h index b36afe7b22c9..6c01f09a6456 100644 --- a/include/linux/rcu_segcblist.h +++ b/include/linux/rcu_segcblist.h @@ -72,6 +72,7 @@ struct rcu_segcblist { #else long len; #endif + long seglen[RCU_CBLIST_NSEGS]; u8 enabled; u8 offloaded; }; -- cgit v1.2.3 From 65e560327fe68153a9ad7452d5fd3171a1927d33 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 13 Nov 2020 13:13:16 +0100 Subject: rcu/nocb: Turn enabled/offload states into a common flag This commit gathers the rcu_segcblist ->enabled and ->offloaded property field into a single ->flags bitmask to avoid further proliferation of individual u8 fields in the structure. This change prepares for the state formerly known as ->offloaded state to be modified at runtime. Cc: Josh Triplett Cc: Steven Rostedt Cc: Mathieu Desnoyers Cc: Lai Jiangshan Cc: Joel Fernandes Cc: Neeraj Upadhyay Cc: Thomas Gleixner Inspired-by: Paul E. McKenney Tested-by: Boqun Feng Signed-off-by: Frederic Weisbecker Signed-off-by: Paul E. McKenney --- include/linux/rcu_segcblist.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcu_segcblist.h b/include/linux/rcu_segcblist.h index 6c01f09a6456..4714b0263c76 100644 --- a/include/linux/rcu_segcblist.h +++ b/include/linux/rcu_segcblist.h @@ -63,6 +63,9 @@ struct rcu_cblist { #define RCU_NEXT_TAIL 3 #define RCU_CBLIST_NSEGS 4 +#define SEGCBLIST_ENABLED BIT(0) +#define SEGCBLIST_OFFLOADED BIT(1) + struct rcu_segcblist { struct rcu_head *head; struct rcu_head **tails[RCU_CBLIST_NSEGS]; @@ -73,8 +76,7 @@ struct rcu_segcblist { long len; #endif long seglen[RCU_CBLIST_NSEGS]; - u8 enabled; - u8 offloaded; + u8 flags; }; #define RCU_SEGCBLIST_INITIALIZER(n) \ -- cgit v1.2.3 From 8d346d438f93b5344e99d429727ec9c2f392d4ec Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 13 Nov 2020 13:13:17 +0100 Subject: rcu/nocb: Provide basic callback offloading state machine bits Offloading and de-offloading RCU callback processes must be done carefully. There must never be a time at which callback processing is disabled because the task driving the offloading or de-offloading might be preempted or otherwise stalled at that point in time, which would result in OOM due to calbacks piling up indefinitely. This implies that there will be times during which a given CPU's callbacks might be concurrently invoked by both that CPU's RCU_SOFTIRQ handler (or, equivalently, that CPU's rcuc kthread) and by that CPU's rcuo kthread. This situation could fatally confuse both rcu_barrier() and the CPU-hotplug offlining process, so these must be excluded during any concurrent-callback-invocation period. In addition, during times of concurrent callback invocation, changes to ->cblist must be protected both as needed for RCU_SOFTIRQ and as needed for the rcuo kthread. This commit therefore defines and documents the states for a state machine that coordinates offloading and deoffloading. Cc: Josh Triplett Cc: Steven Rostedt Cc: Mathieu Desnoyers Cc: Lai Jiangshan Cc: Joel Fernandes Cc: Neeraj Upadhyay Cc: Thomas Gleixner Inspired-by: Paul E. McKenney Tested-by: Boqun Feng Signed-off-by: Frederic Weisbecker Signed-off-by: Paul E. McKenney --- include/linux/rcu_segcblist.h | 115 +++++++++++++++++++++++++++++++++++++++++- 1 file changed, 114 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rcu_segcblist.h b/include/linux/rcu_segcblist.h index 4714b0263c76..8afe886e85f1 100644 --- a/include/linux/rcu_segcblist.h +++ b/include/linux/rcu_segcblist.h @@ -63,8 +63,121 @@ struct rcu_cblist { #define RCU_NEXT_TAIL 3 #define RCU_CBLIST_NSEGS 4 + +/* + * ==NOCB Offloading state machine== + * + * + * ---------------------------------------------------------------------------- + * | SEGCBLIST_SOFTIRQ_ONLY | + * | | + * | Callbacks processed by rcu_core() from softirqs or local | + * | rcuc kthread, without holding nocb_lock. | + * ---------------------------------------------------------------------------- + * | + * v + * ---------------------------------------------------------------------------- + * | SEGCBLIST_OFFLOADED | + * | | + * | Callbacks processed by rcu_core() from softirqs or local | + * | rcuc kthread, while holding nocb_lock. Waking up CB and GP kthreads, | + * | allowing nocb_timer to be armed. | + * ---------------------------------------------------------------------------- + * | + * v + * ----------------------------------- + * | | + * v v + * --------------------------------------- ----------------------------------| + * | SEGCBLIST_OFFLOADED | | | SEGCBLIST_OFFLOADED | | + * | SEGCBLIST_KTHREAD_CB | | SEGCBLIST_KTHREAD_GP | + * | | | | + * | | | | + * | CB kthread woke up and | | GP kthread woke up and | + * | acknowledged SEGCBLIST_OFFLOADED. | | acknowledged SEGCBLIST_OFFLOADED| + * | Processes callbacks concurrently | | | + * | with rcu_core(), holding | | | + * | nocb_lock. | | | + * --------------------------------------- ----------------------------------- + * | | + * ----------------------------------- + * | + * v + * |--------------------------------------------------------------------------| + * | SEGCBLIST_OFFLOADED | | + * | SEGCBLIST_KTHREAD_CB | | + * | SEGCBLIST_KTHREAD_GP | + * | | + * | Kthreads handle callbacks holding nocb_lock, local rcu_core() stops | + * | handling callbacks. | + * ---------------------------------------------------------------------------- + */ + + + +/* + * ==NOCB De-Offloading state machine== + * + * + * |--------------------------------------------------------------------------| + * | SEGCBLIST_OFFLOADED | | + * | SEGCBLIST_KTHREAD_CB | | + * | SEGCBLIST_KTHREAD_GP | + * | | + * | CB/GP kthreads handle callbacks holding nocb_lock, local rcu_core() | + * | ignores callbacks. | + * ---------------------------------------------------------------------------- + * | + * v + * |--------------------------------------------------------------------------| + * | SEGCBLIST_KTHREAD_CB | | + * | SEGCBLIST_KTHREAD_GP | + * | | + * | CB/GP kthreads and local rcu_core() handle callbacks concurrently | + * | holding nocb_lock. Wake up CB and GP kthreads if necessary. | + * ---------------------------------------------------------------------------- + * | + * v + * ----------------------------------- + * | | + * v v + * ---------------------------------------------------------------------------| + * | | + * | SEGCBLIST_KTHREAD_CB | SEGCBLIST_KTHREAD_GP | + * | | | + * | GP kthread woke up and | CB kthread woke up and | + * | acknowledged the fact that | acknowledged the fact that | + * | SEGCBLIST_OFFLOADED got cleared. | SEGCBLIST_OFFLOADED got cleared. | + * | | The CB kthread goes to sleep | + * | The callbacks from the target CPU | until it ever gets re-offloaded. | + * | will be ignored from the GP kthread | | + * | loop. | | + * ---------------------------------------------------------------------------- + * | | + * ----------------------------------- + * | + * v + * ---------------------------------------------------------------------------- + * | 0 | + * | | + * | Callbacks processed by rcu_core() from softirqs or local | + * | rcuc kthread, while holding nocb_lock. Forbid nocb_timer to be armed. | + * | Flush pending nocb_timer. Flush nocb bypass callbacks. | + * ---------------------------------------------------------------------------- + * | + * v + * ---------------------------------------------------------------------------- + * | SEGCBLIST_SOFTIRQ_ONLY | + * | | + * | Callbacks processed by rcu_core() from softirqs or local | + * | rcuc kthread, without holding nocb_lock. | + * ---------------------------------------------------------------------------- + */ #define SEGCBLIST_ENABLED BIT(0) -#define SEGCBLIST_OFFLOADED BIT(1) +#define SEGCBLIST_SOFTIRQ_ONLY BIT(1) +#define SEGCBLIST_KTHREAD_CB BIT(2) +#define SEGCBLIST_KTHREAD_GP BIT(3) +#define SEGCBLIST_OFFLOADED BIT(4) struct rcu_segcblist { struct rcu_head *head; -- cgit v1.2.3 From d97b078182406c0bd0aacd36fc0a693e118e608f Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 13 Nov 2020 13:13:19 +0100 Subject: rcu/nocb: De-offloading CB kthread To de-offload callback processing back onto a CPU, it is necessary to clear SEGCBLIST_OFFLOAD and notify the nocb CB kthread, which will then clear its own bit flag and go to sleep to stop handling callbacks. This commit makes that change. It will also be necessary to notify the nocb GP kthread in this same way, which is the subject of a follow-on commit. Cc: Josh Triplett Cc: Steven Rostedt Cc: Mathieu Desnoyers Cc: Lai Jiangshan Cc: Joel Fernandes Cc: Neeraj Upadhyay Cc: Thomas Gleixner Inspired-by: Paul E. McKenney Tested-by: Boqun Feng Signed-off-by: Frederic Weisbecker [ paulmck: Add export per kernel test robot feedback. ] Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index de0826411311..40266eb418b6 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -104,8 +104,10 @@ static inline void rcu_user_exit(void) { } #ifdef CONFIG_RCU_NOCB_CPU void rcu_init_nohz(void); +int rcu_nocb_cpu_deoffload(int cpu); #else /* #ifdef CONFIG_RCU_NOCB_CPU */ static inline void rcu_init_nohz(void) { } +static inline int rcu_nocb_cpu_deoffload(int cpu) { return 0; } #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ /** -- cgit v1.2.3 From 254e11efde66ca0a0ce0c99a62c377314b5984ff Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 13 Nov 2020 13:13:22 +0100 Subject: rcu/nocb: Re-offload support To re-offload the callback processing off of a CPU, it is necessary to clear SEGCBLIST_SOFTIRQ_ONLY, set SEGCBLIST_OFFLOADED, and then notify both the CB and GP kthreads so that they both set their own bit flag and start processing the callbacks remotely. The re-offloading worker is then notified that it can stop the RCU_SOFTIRQ handler (or rcuc kthread, as the case may be) from processing the callbacks locally. Ordering must be carefully enforced so that the callbacks that used to be processed locally without locking will have the same ordering properties when they are invoked by the nocb CB and GP kthreads. This commit makes this change. Cc: Josh Triplett Cc: Steven Rostedt Cc: Mathieu Desnoyers Cc: Lai Jiangshan Cc: Joel Fernandes Cc: Neeraj Upadhyay Cc: Thomas Gleixner Inspired-by: Paul E. McKenney Tested-by: Boqun Feng Signed-off-by: Frederic Weisbecker [ paulmck: Export rcu_nocb_cpu_offload(). ] Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 40266eb418b6..e0ee52e2756d 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -104,9 +104,11 @@ static inline void rcu_user_exit(void) { } #ifdef CONFIG_RCU_NOCB_CPU void rcu_init_nohz(void); +int rcu_nocb_cpu_offload(int cpu); int rcu_nocb_cpu_deoffload(int cpu); #else /* #ifdef CONFIG_RCU_NOCB_CPU */ static inline void rcu_init_nohz(void) { } +static inline int rcu_nocb_cpu_offload(int cpu) { return -EINVAL; } static inline int rcu_nocb_cpu_deoffload(int cpu) { return 0; } #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ -- cgit v1.2.3 From 43759fe5a137389e94ed6d4680c3c63c17273158 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 11 Nov 2020 23:53:13 +0100 Subject: cpu/hotplug: Add lockdep_is_cpus_held() This commit adds a lockdep_is_cpus_held() function to verify that the proper locks are held and that various operations are running in the correct context. Signed-off-by: Frederic Weisbecker Cc: Paul E. McKenney Cc: Josh Triplett Cc: Steven Rostedt Cc: Mathieu Desnoyers Cc: Lai Jiangshan Cc: Joel Fernandes Cc: Neeraj Upadhyay Cc: Thomas Gleixner Cc: Boqun Feng Signed-off-by: Paul E. McKenney --- include/linux/cpu.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index d6428aaf67e7..3aaa0687e8df 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -111,6 +111,8 @@ static inline void cpu_maps_update_done(void) #endif /* CONFIG_SMP */ extern struct bus_type cpu_subsys; +extern int lockdep_is_cpus_held(void); + #ifdef CONFIG_HOTPLUG_CPU extern void cpus_write_lock(void); extern void cpus_write_unlock(void); -- cgit v1.2.3 From dcd42591ebb8a25895b551a5297ea9c24414ba54 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 13 Nov 2020 13:13:33 +0100 Subject: timer: Add timer_curr_running() This commit adds a timer_curr_running() function that verifies that the current code is running in the context of the specified timer's handler. Cc: Josh Triplett Cc: Steven Rostedt Cc: Mathieu Desnoyers Cc: Lai Jiangshan Cc: Joel Fernandes Cc: Neeraj Upadhyay Cc: Thomas Gleixner Tested-by: Boqun Feng Signed-off-by: Frederic Weisbecker Signed-off-by: Paul E. McKenney --- include/linux/timer.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/timer.h b/include/linux/timer.h index fda13c9d1256..4118a97e62fb 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -192,6 +192,8 @@ extern int try_to_del_timer_sync(struct timer_list *timer); #define del_singleshot_timer_sync(t) del_timer_sync(t) +extern bool timer_curr_running(struct timer_list *timer); + extern void init_timers(void); struct hrtimer; extern enum hrtimer_restart it_real_fn(struct hrtimer *); -- cgit v1.2.3 From ae19aaafae95a5487469433e9cae4c208f8d15cd Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 17 Nov 2020 11:30:18 -0800 Subject: torture: Add fuzzed hrtimer-based sleep functions This commit adds torture_hrtimeout_ns(), torture_hrtimeout_us(), torture_hrtimeout_ms(), torture_hrtimeout_jiffies(), and torture_hrtimeout_s(), each of which uses hrtimers to block for a fuzzed time interval. These functions are intended to be used by the various torture tests to decouple wakeups from the timer wheel, thus providing more opportunity for Murphy to insert destructive race conditions. Signed-off-by: Paul E. McKenney --- include/linux/torture.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/torture.h b/include/linux/torture.h index 7f65bd1dd307..32941f8106b2 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -61,6 +61,13 @@ static inline void torture_random_init(struct torture_random_state *trsp) trsp->trs_count = 0; } +/* Definitions for high-resolution-timer sleeps. */ +int torture_hrtimeout_ns(ktime_t baset_ns, u32 fuzzt_ns, struct torture_random_state *trsp); +int torture_hrtimeout_us(u32 baset_us, u32 fuzzt_ns, struct torture_random_state *trsp); +int torture_hrtimeout_ms(u32 baset_ms, u32 fuzzt_us, struct torture_random_state *trsp); +int torture_hrtimeout_jiffies(u32 baset_j, struct torture_random_state *trsp); +int torture_hrtimeout_s(u32 baset_s, u32 fuzzt_ms, struct torture_random_state *trsp); + /* Task shuffler, which causes CPUs to occasionally go idle. */ void torture_shuffle_task_register(struct task_struct *tp); int torture_shuffle_init(long shuffint); -- cgit v1.2.3 From 8a67a20bf257ca378d6e5588fbe4382966395ac8 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 25 Nov 2020 13:00:04 -0800 Subject: torture: Throttle VERBOSE_TOROUT_*() output This commit adds kernel boot parameters torture.verbose_sleep_frequency and torture.verbose_sleep_duration, which allow VERBOSE_TOROUT_*() output to be throttled with periodic sleeps on large systems. Signed-off-by: Paul E. McKenney --- include/linux/torture.h | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/torture.h b/include/linux/torture.h index 32941f8106b2..d62d13c8c69a 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -32,9 +32,20 @@ #define TOROUT_STRING(s) \ pr_alert("%s" TORTURE_FLAG " %s\n", torture_type, s) #define VERBOSE_TOROUT_STRING(s) \ - do { if (verbose) pr_alert("%s" TORTURE_FLAG " %s\n", torture_type, s); } while (0) +do { \ + if (verbose) { \ + verbose_torout_sleep(); \ + pr_alert("%s" TORTURE_FLAG " %s\n", torture_type, s); \ + } \ +} while (0) #define VERBOSE_TOROUT_ERRSTRING(s) \ - do { if (verbose) pr_alert("%s" TORTURE_FLAG "!!! %s\n", torture_type, s); } while (0) +do { \ + if (verbose) { \ + verbose_torout_sleep(); \ + pr_alert("%s" TORTURE_FLAG "!!! %s\n", torture_type, s); \ + } \ +} while (0) +void verbose_torout_sleep(void); /* Definitions for online/offline exerciser. */ typedef void torture_ofl_func(void); -- cgit v1.2.3 From 1afb95fee0342b8d9e05b0433e8e44a6dfd7c4a3 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sat, 19 Dec 2020 07:34:35 -0800 Subject: torture: Maintain torture-specific set of CPUs-online books The TREE01 rcutorture scenario intentionally creates confusion as to the number of available CPUs by specifying the "maxcpus=8 nr_cpus=43" kernel boot parameters. This can disable rcutorture's load shedding, which currently uses num_online_cpus(), which would count the extra 35 CPUs. However, the rcutorture guest OS will be provisioned with only 8 CPUs, which means that rcutorture will present full load even when all but one of the original 8 CPUs are offline. This can result in spurious errors due to extreme overloading of that single remaining CPU. This commit therefore keeps a separate set of books on the number of usable online CPUs, so that torture_num_online_cpus() is used for load shedding instead of num_online_cpus(). Note that initial sizing must use num_online_cpus() because torture_num_online_cpus() will return NR_CPUS until shortly after torture_onoff_init() is invoked. Reported-by: Frederic Weisbecker [ paulmck: Apply feedback from kernel test robot. ] Signed-off-by: Paul E. McKenney --- include/linux/torture.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/torture.h b/include/linux/torture.h index d62d13c8c69a..0910c5803f35 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -48,6 +48,11 @@ do { \ void verbose_torout_sleep(void); /* Definitions for online/offline exerciser. */ +#ifdef CONFIG_HOTPLUG_CPU +int torture_num_online_cpus(void); +#else /* #ifdef CONFIG_HOTPLUG_CPU */ +static inline int torture_num_online_cpus(void) { return 1; } +#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */ typedef void torture_ofl_func(void); bool torture_offline(int cpu, long *n_onl_attempts, long *n_onl_successes, unsigned long *sum_offl, int *min_onl, int *max_onl); -- cgit v1.2.3 From 9326eecd9365a5b82220a4011592f7c0209566fc Mon Sep 17 00:00:00 2001 From: Xu Yilun Date: Wed, 6 Jan 2021 20:37:10 -0800 Subject: fpga: dfl: move dfl_device_id to mod_devicetable.h In order to support MODULE_DEVICE_TABLE() for dfl device driver, this patch moves struct dfl_device_id to mod_devicetable.h Some brief description for DFL (Device Feature List) is added to make the DFL known to the whole kernel. Reviewed-by: Tom Rix Acked-by: Wu Hao Signed-off-by: Xu Yilun Signed-off-by: Wu Hao Signed-off-by: Matthew Gerlach Signed-off-by: Russ Weight Signed-off-by: Moritz Fischer Link: https://lore.kernel.org/r/20210107043714.991646-5-mdf@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mod_devicetable.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index c425290b21e2..b8dae34eca10 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -846,4 +846,28 @@ struct auxiliary_device_id { kernel_ulong_t driver_data; }; +/* + * DFL (Device Feature List) + * + * DFL defines a linked list of feature headers within the device MMIO space to + * provide an extensible way of adding features. Software can walk through these + * predefined data structures to enumerate features. It is now used in the FPGA. + * See Documentation/fpga/dfl.rst for more information. + * + * The dfl bus type is introduced to match the individual feature devices (dfl + * devices) for specific dfl drivers. + */ + +/** + * struct dfl_device_id - dfl device identifier + * @type: DFL FIU type of the device. See enum dfl_id_type. + * @feature_id: feature identifier local to its DFL FIU type. + * @driver_data: driver specific data. + */ +struct dfl_device_id { + __u16 type; + __u16 feature_id; + kernel_ulong_t driver_data; +}; + #endif /* LINUX_MOD_DEVICETABLE_H */ -- cgit v1.2.3 From ecc1641aca658ed4140751748f84985ffb6cce28 Mon Sep 17 00:00:00 2001 From: Xu Yilun Date: Wed, 6 Jan 2021 20:37:12 -0800 Subject: fpga: dfl: move dfl bus related APIs to include/linux/dfl.h Now the dfl drivers could be made as independent modules and put in different folders according to their functionalities. In order for scattered dfl device drivers to include dfl bus APIs, move the dfl bus APIs to a new header file in the public folder. [mdf@kernel.org: Fixed up header guards to match filename] Reviewed-by: Tom Rix Acked-by: Wu Hao Signed-off-by: Xu Yilun Signed-off-by: Moritz Fischer Link: https://lore.kernel.org/r/20210107043714.991646-7-mdf@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/dfl.h | 86 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 86 insertions(+) create mode 100644 include/linux/dfl.h (limited to 'include/linux') diff --git a/include/linux/dfl.h b/include/linux/dfl.h new file mode 100644 index 000000000000..6cc10982351a --- /dev/null +++ b/include/linux/dfl.h @@ -0,0 +1,86 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Header file for DFL driver and device API + * + * Copyright (C) 2020 Intel Corporation, Inc. + */ + +#ifndef __LINUX_DFL_H +#define __LINUX_DFL_H + +#include +#include + +/** + * enum dfl_id_type - define the DFL FIU types + */ +enum dfl_id_type { + FME_ID = 0, + PORT_ID = 1, + DFL_ID_MAX, +}; + +/** + * struct dfl_device - represent an dfl device on dfl bus + * + * @dev: generic device interface. + * @id: id of the dfl device. + * @type: type of DFL FIU of the device. See enum dfl_id_type. + * @feature_id: feature identifier local to its DFL FIU type. + * @mmio_res: mmio resource of this dfl device. + * @irqs: list of Linux IRQ numbers of this dfl device. + * @num_irqs: number of IRQs supported by this dfl device. + * @cdev: pointer to DFL FPGA container device this dfl device belongs to. + * @id_entry: matched id entry in dfl driver's id table. + */ +struct dfl_device { + struct device dev; + int id; + u16 type; + u16 feature_id; + struct resource mmio_res; + int *irqs; + unsigned int num_irqs; + struct dfl_fpga_cdev *cdev; + const struct dfl_device_id *id_entry; +}; + +/** + * struct dfl_driver - represent an dfl device driver + * + * @drv: driver model structure. + * @id_table: pointer to table of device IDs the driver is interested in. + * { } member terminated. + * @probe: mandatory callback for device binding. + * @remove: callback for device unbinding. + */ +struct dfl_driver { + struct device_driver drv; + const struct dfl_device_id *id_table; + + int (*probe)(struct dfl_device *dfl_dev); + void (*remove)(struct dfl_device *dfl_dev); +}; + +#define to_dfl_dev(d) container_of(d, struct dfl_device, dev) +#define to_dfl_drv(d) container_of(d, struct dfl_driver, drv) + +/* + * use a macro to avoid include chaining to get THIS_MODULE. + */ +#define dfl_driver_register(drv) \ + __dfl_driver_register(drv, THIS_MODULE) +int __dfl_driver_register(struct dfl_driver *dfl_drv, struct module *owner); +void dfl_driver_unregister(struct dfl_driver *dfl_drv); + +/* + * module_dfl_driver() - Helper macro for drivers that don't do + * anything special in module init/exit. This eliminates a lot of + * boilerplate. Each module may only use this macro once, and + * calling it replaces module_init() and module_exit(). + */ +#define module_dfl_driver(__dfl_driver) \ + module_driver(__dfl_driver, dfl_driver_register, \ + dfl_driver_unregister) + +#endif /* __LINUX_DFL_H */ -- cgit v1.2.3 From 63f24a7fafd44899f001b8467b38fac5a534f63e Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Tue, 5 Jan 2021 13:02:28 +0100 Subject: vt: move set_leds to keyboard.c set_leds and compute_shiftstate are called from a single place in vt.c. Let's combine these two into vt_set_leds_compute_shiftstate. This allows for making keyboard_tasklet local in the next patch. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20210105120239.28031-1-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/kbd_kern.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kbd_kern.h b/include/linux/kbd_kern.h index 82f29aa35062..adf98004624b 100644 --- a/include/linux/kbd_kern.h +++ b/include/linux/kbd_kern.h @@ -71,12 +71,6 @@ extern void (*kbd_ledfunc)(unsigned int led); extern int set_console(int nr); extern void schedule_console_callback(void); -/* FIXME: review locking for vt.c callers */ -static inline void set_leds(void) -{ - tasklet_schedule(&keyboard_tasklet); -} - static inline int vc_kbd_mode(struct kbd_struct * kbd, int flag) { return ((kbd->modeflags >> flag) & 1); @@ -135,7 +129,7 @@ static inline void chg_vc_kbd_led(struct kbd_struct * kbd, int flag) struct console; -void compute_shiftstate(void); +void vt_set_leds_compute_shiftstate(void); /* defkeymap.c */ -- cgit v1.2.3 From a18a9da82c57804ce5977ea0e01b72ee3f40a51b Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Tue, 5 Jan 2021 13:02:29 +0100 Subject: vt: keyboard, make keyboard_tasklet local Now that the last extern user of the tasklet (set_leds) is in keyboard.c, we can make keyboard_tasklet local to this unit too. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20210105120239.28031-2-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/kbd_kern.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kbd_kern.h b/include/linux/kbd_kern.h index adf98004624b..c40811d79769 100644 --- a/include/linux/kbd_kern.h +++ b/include/linux/kbd_kern.h @@ -6,8 +6,6 @@ #include #include -extern struct tasklet_struct keyboard_tasklet; - extern char *func_table[MAX_NR_FUNC]; /* -- cgit v1.2.3 From ff2047fb755d4415ec3c70ac799889371151796d Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Tue, 5 Jan 2021 13:02:35 +0100 Subject: vt: drop old FONT ioctls Drop support for these ioctls: * PIO_FONT, PIO_FONTX * GIO_FONT, GIO_FONTX * PIO_FONTRESET As was demonstrated by commit 90bfdeef83f1 (tty: make FONTX ioctl use the tty pointer they were actually passed), these ioctls are not used from userspace, as: 1) they used to be broken (set up font on current console, not the open one) and racy (before the commit above) 2) KDFONTOP ioctl is used for years instead Note that PIO_FONTRESET is defunct on most systems as VGA_CONSOLE is set on them for ages. That turns on BROKEN_GRAPHICS_PROGRAMS which makes PIO_FONTRESET just return an error. We are removing KD_FONT_FLAG_OLD here as it was used only by these removed ioctls. kd.h header exists both in kernel and uapi headers, so we can remove the kernel one completely. Everyone includeing kd.h will now automatically get the uapi one. There are now unused definitions of the ioctl numbers and "struct consolefontdesc" in kd.h, but as it is a uapi header, I am not touching these. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20210105120239.28031-8-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/kd.h | 8 -------- 1 file changed, 8 deletions(-) delete mode 100644 include/linux/kd.h (limited to 'include/linux') diff --git a/include/linux/kd.h b/include/linux/kd.h deleted file mode 100644 index b130a18f860f..000000000000 --- a/include/linux/kd.h +++ /dev/null @@ -1,8 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_KD_H -#define _LINUX_KD_H - -#include - -#define KD_FONT_FLAG_OLD 0x80000000 /* Invoked via old interface [compat] */ -#endif /* _LINUX_KD_H */ -- cgit v1.2.3 From cac8a63063e33606c4b8419ef34ef7644d7c2fc4 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Tue, 5 Jan 2021 13:02:36 +0100 Subject: vgacon: drop BROKEN_GRAPHICS_PROGRAMS BROKEN_GRAPHICS_PROGRAMS is defined when CONFIG_VGA_CONSOLE=y. And vgacon.c is built exclusively in that case too. So the check for BROKEN_GRAPHICS_PROGRAMS is pointless in vgacon.c as it is always true. So remove the test and BROKEN_GRAPHICS_PROGRAMS completely. This also eliminates the need for vga_font_is_default global as it is only set and never read. Cc: dri-devel@lists.freedesktop.org Cc: linux-fbdev@vger.kernel.org Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20210105120239.28031-9-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/vt_kern.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h index 349e39c3ab60..94e7a315479c 100644 --- a/include/linux/vt_kern.h +++ b/include/linux/vt_kern.h @@ -16,18 +16,6 @@ #include #include -/* - * Presently, a lot of graphics programs do not restore the contents of - * the higher font pages. Defining this flag will avoid use of them, but - * will lose support for PIO_FONTRESET. Note that many font operations are - * not likely to work with these programs anyway; they need to be - * fixed. The linux/Documentation directory includes a code snippet - * to save and restore the text font. - */ -#ifdef CONFIG_VGA_CONSOLE -#define BROKEN_GRAPHICS_PROGRAMS 1 -#endif - void kd_mksound(unsigned int hz, unsigned int ticks); int kbd_rate(struct kbd_repeat *rep); -- cgit v1.2.3 From 0bc1bd092af3c7c0b025ece93c3a86916f89f3ca Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Tue, 5 Jan 2021 13:02:38 +0100 Subject: tty_port: drop last traces of low_latency The main purpose of tty_port::low_latency was removed in commit a9c3f68f3cd8 (tty: Fix low_latency BUG) back in 2014. It was left in place for drivers as an optional tune knob. But only one driver has been using it until the previous commit. So remove this misconcept completely, given there are no users. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20210105120239.28031-11-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 12be8b16cdef..b57f6812b3ba 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -240,8 +240,7 @@ struct tty_port { wait_queue_head_t delta_msr_wait; /* Modem status change */ unsigned long flags; /* User TTY flags ASYNC_ */ unsigned long iflags; /* Internal flags TTY_PORT_ */ - unsigned char console:1, /* port is a console */ - low_latency:1; /* optional: tune for latency */ + unsigned char console:1; /* port is a console */ struct mutex mutex; /* Locking */ struct mutex buf_mutex; /* Buffer alloc lock */ unsigned char *xmit_buf; /* Optional buffer */ -- cgit v1.2.3 From f446776ebffb9d3fb145b8d84f7f358f64cb54d6 Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Mon, 23 Nov 2020 18:49:01 -0600 Subject: tty: Export redirect release This will be required by the pty code when it removes tty_vhangup() on master close. Signed-off-by: Corey Minyard Link: https://lore.kernel.org/r/20201124004902.1398477-2-minyard@acm.org Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index b57f6812b3ba..dd6ded6138f7 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -421,6 +421,7 @@ extern void tty_kclose(struct tty_struct *tty); extern int tty_dev_name_to_number(const char *name, dev_t *number); extern int tty_ldisc_lock(struct tty_struct *tty, unsigned long timeout); extern void tty_ldisc_unlock(struct tty_struct *tty); +extern struct file *tty_release_redirect(struct tty_struct *tty); #else static inline void tty_kref_put(struct tty_struct *tty) { } -- cgit v1.2.3 From 04f111130e9afa41c10d7bcec14e00e3be8b6977 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Thu, 10 Dec 2020 13:15:14 +0100 Subject: thermal/core: Remove notify ops With the removal of the notifys user in a previous patches, the ops is no longer needed, remove it. Signed-off-by: Daniel Lezcano Reviewed-by: Lukasz Luba Link: https://lore.kernel.org/r/20201210121514.25760-5-daniel.lezcano@linaro.org --- include/linux/thermal.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 31b84404f047..c80032322158 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -77,8 +77,6 @@ struct thermal_zone_device_ops { int (*set_emul_temp) (struct thermal_zone_device *, int); int (*get_trend) (struct thermal_zone_device *, int, enum thermal_trend *); - int (*notify) (struct thermal_zone_device *, int, - enum thermal_trip_type); void (*hot)(struct thermal_zone_device *); void (*critical)(struct thermal_zone_device *); }; -- cgit v1.2.3 From 4b9bbb29baf6c948d24eaeff892815b8a403b64c Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Thu, 17 Dec 2020 19:17:00 -0800 Subject: driver core: Add device link support for INFERRED flag This flag can never be added to a device link that already exists and doesn't have the flag set. It can only be added when a device link is created for the first time or it can be maintained if the device link already has the it set. This flag will be used for marking device links created ONLY by inferring dependencies from data and NOT from explicit action by device drivers/frameworks. This will be useful in the future when we need to deal with cycles in dependencies inferred from firmware. Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20201218031703.3053753-3-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 89bb8b84173e..cb5eb2e58c25 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -323,6 +323,7 @@ enum device_link_state { * AUTOPROBE_CONSUMER: Probe consumer driver automatically after supplier binds. * MANAGED: The core tracks presence of supplier/consumer drivers (internal). * SYNC_STATE_ONLY: Link only affects sync_state() behavior. + * INFERRED: Inferred from data (eg: firmware) and not from driver actions. */ #define DL_FLAG_STATELESS BIT(0) #define DL_FLAG_AUTOREMOVE_CONSUMER BIT(1) @@ -332,6 +333,7 @@ enum device_link_state { #define DL_FLAG_AUTOPROBE_CONSUMER BIT(5) #define DL_FLAG_MANAGED BIT(6) #define DL_FLAG_SYNC_STATE_ONLY BIT(7) +#define DL_FLAG_INFERRED BIT(8) /** * enum dl_dev_state - Device driver presence tracking information. -- cgit v1.2.3 From 30bfce109420912f201d4f295f9130ff44f04b41 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 6 Jan 2021 13:06:36 -0800 Subject: net: remove ndo_udp_tunnel_* callbacks All UDP tunnel port management is now routed via udp_tunnel_nic infra directly. Remove the old callbacks. Reviewed-by: Alexander Duyck Reviewed-by: Jacob Keller Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 259be67644e3..1ec3ac5d5bbf 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1213,19 +1213,6 @@ struct netdev_net_notifier { * struct netdev_phys_item_id *ppid) * Called to get the parent ID of the physical port of this device. * - * void (*ndo_udp_tunnel_add)(struct net_device *dev, - * struct udp_tunnel_info *ti); - * Called by UDP tunnel to notify a driver about the UDP port and socket - * address family that a UDP tunnel is listnening to. It is called only - * when a new port starts listening. The operation is protected by the - * RTNL. - * - * void (*ndo_udp_tunnel_del)(struct net_device *dev, - * struct udp_tunnel_info *ti); - * Called by UDP tunnel to notify the driver about a UDP port and socket - * address family that the UDP tunnel is not listening to anymore. The - * operation is protected by the RTNL. - * * void* (*ndo_dfwd_add_station)(struct net_device *pdev, * struct net_device *dev) * Called by upper layer devices to accelerate switching or other @@ -1464,10 +1451,6 @@ struct net_device_ops { struct netdev_phys_item_id *ppid); int (*ndo_get_phys_port_name)(struct net_device *dev, char *name, size_t len); - void (*ndo_udp_tunnel_add)(struct net_device *dev, - struct udp_tunnel_info *ti); - void (*ndo_udp_tunnel_del)(struct net_device *dev, - struct udp_tunnel_info *ti); void* (*ndo_dfwd_add_station)(struct net_device *pdev, struct net_device *dev); void (*ndo_dfwd_del_station)(struct net_device *pdev, -- cgit v1.2.3 From 8b86850bf9ef259e194ce49c776aded3b8c281fb Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Wed, 6 Jan 2021 09:09:44 -0800 Subject: net: phy: bcm7xxx: Add an entry for BCM72116 BCM72116 features a 28nm integrated EPHY, add an entry to match this PHY OUI. Signed-off-by: Florian Fainelli Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/20210106170944.1253046-1-f.fainelli@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/brcmphy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index d0bd226d6bd9..de9430d55c90 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -31,6 +31,7 @@ #define PHY_ID_BCM89610 0x03625cd0 #define PHY_ID_BCM72113 0x35905310 +#define PHY_ID_BCM72116 0x35905350 #define PHY_ID_BCM7250 0xae025280 #define PHY_ID_BCM7255 0xae025120 #define PHY_ID_BCM7260 0xae025190 -- cgit v1.2.3 From f46b9b8ee89b52f6ee1f4da49d392e609746ab10 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 7 Jan 2021 03:24:00 +0200 Subject: net: dsa: move the Broadcom tag information in a separate header file It is a bit strange to see something as specific as Broadcom SYSTEMPORT bits in the main DSA include file. Move these away into a separate header, and have the tagger and the SYSTEMPORT driver include them. Signed-off-by: Vladimir Oltean Acked-by: Florian Fainelli Signed-off-by: Jakub Kicinski --- include/linux/dsa/brcm.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) create mode 100644 include/linux/dsa/brcm.h (limited to 'include/linux') diff --git a/include/linux/dsa/brcm.h b/include/linux/dsa/brcm.h new file mode 100644 index 000000000000..47545a948784 --- /dev/null +++ b/include/linux/dsa/brcm.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0-only + * Copyright (C) 2014 Broadcom Corporation + */ + +/* Included by drivers/net/ethernet/broadcom/bcmsysport.c and + * net/dsa/tag_brcm.c + */ +#ifndef _NET_DSA_BRCM_H +#define _NET_DSA_BRCM_H + +/* Broadcom tag specific helpers to insert and extract queue/port number */ +#define BRCM_TAG_SET_PORT_QUEUE(p, q) ((p) << 8 | q) +#define BRCM_TAG_GET_PORT(v) ((v) >> 8) +#define BRCM_TAG_GET_QUEUE(v) ((v) & 0xff) + +#endif -- cgit v1.2.3 From 424f481f06dc7f1528447cc3224f5fd3c5e11f65 Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Wed, 6 Jan 2021 14:18:29 -0800 Subject: skbuff: remove unused skb_zcopy_abort function skb_zcopy_abort() has no in-tree consumers, remove it. Signed-off-by: Jonathan Lemon Acked-by: Willem de Bruijn Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 333bcdc39635..3ca8d7c7b30c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1490,17 +1490,6 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy) } } -/* Abort a zerocopy operation and revert zckey on error in send syscall */ -static inline void skb_zcopy_abort(struct sk_buff *skb) -{ - struct ubuf_info *uarg = skb_zcopy(skb); - - if (uarg) { - sock_zerocopy_put_abort(uarg, false); - skb_shinfo(skb)->tx_flags &= ~SKBTX_ZEROCOPY_FRAG; - } -} - static inline void skb_mark_not_on_list(struct sk_buff *skb) { skb->next = NULL; -- cgit v1.2.3 From 75518851a2a0c047def521aaf87db401de098352 Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Wed, 6 Jan 2021 14:18:31 -0800 Subject: skbuff: Push status and refcounts into sock_zerocopy_callback Before this change, the caller of sock_zerocopy_callback would need to save the zerocopy status, decrement and check the refcount, and then call the callback function - the callback was only invoked when the refcount reached zero. Now, the caller just passes the status into the callback function, which saves the status and handles its own refcounts. This makes the behavior of the sock_zerocopy_callback identical to the tpacket and vhost callbacks. Signed-off-by: Jonathan Lemon Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 3ca8d7c7b30c..52e96c35f5af 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1479,9 +1479,6 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy) if (uarg) { if (skb_zcopy_is_nouarg(skb)) { /* no notification callback */ - } else if (uarg->callback == sock_zerocopy_callback) { - uarg->zerocopy = uarg->zerocopy && zerocopy; - sock_zerocopy_put(uarg); } else { uarg->callback(uarg, zerocopy); } -- cgit v1.2.3 From 59776362b14b81dc45c6bbd4e7cb3871f390fc1b Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Wed, 6 Jan 2021 14:18:32 -0800 Subject: skbuff: replace sock_zerocopy_put() with skb_zcopy_put() Replace sock_zerocopy_put with the generic skb_zcopy_put() function. Pass 'true' as the success argument, as this is identical to no change. Signed-off-by: Jonathan Lemon Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 52e96c35f5af..a6c86839035b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -496,7 +496,6 @@ static inline void sock_zerocopy_get(struct ubuf_info *uarg) refcount_inc(&uarg->refcnt); } -void sock_zerocopy_put(struct ubuf_info *uarg); void sock_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); void sock_zerocopy_callback(struct ubuf_info *uarg, bool success); @@ -1471,6 +1470,12 @@ static inline void *skb_zcopy_get_nouarg(struct sk_buff *skb) return (void *)((uintptr_t) skb_shinfo(skb)->destructor_arg & ~0x1UL); } +static inline void skb_zcopy_put(struct ubuf_info *uarg) +{ + if (uarg) + uarg->callback(uarg, true); +} + /* Release a reference on a zerocopy structure */ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy) { -- cgit v1.2.3 From e76d46cfff8d2335f363f58bd7387de4059d871d Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Wed, 6 Jan 2021 14:18:33 -0800 Subject: skbuff: replace sock_zerocopy_get with skb_zcopy_get Rename the get routines for consistency. Signed-off-by: Jonathan Lemon Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a6c86839035b..5b8a53ab51fd 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -491,11 +491,6 @@ struct ubuf_info *sock_zerocopy_alloc(struct sock *sk, size_t size); struct ubuf_info *sock_zerocopy_realloc(struct sock *sk, size_t size, struct ubuf_info *uarg); -static inline void sock_zerocopy_get(struct ubuf_info *uarg) -{ - refcount_inc(&uarg->refcnt); -} - void sock_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); void sock_zerocopy_callback(struct ubuf_info *uarg, bool success); @@ -1441,6 +1436,11 @@ static inline struct ubuf_info *skb_zcopy(struct sk_buff *skb) return is_zcopy ? skb_uarg(skb) : NULL; } +static inline void skb_zcopy_get(struct ubuf_info *uarg) +{ + refcount_inc(&uarg->refcnt); +} + static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg, bool *have_ref) { @@ -1448,7 +1448,7 @@ static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg, if (unlikely(have_ref && *have_ref)) *have_ref = false; else - sock_zerocopy_get(uarg); + skb_zcopy_get(uarg); skb_shinfo(skb)->destructor_arg = uarg; skb_shinfo(skb)->tx_flags |= SKBTX_ZEROCOPY_FRAG; } -- cgit v1.2.3 From 36177832f42d9c7b222ab039678398a9d4070fff Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Wed, 6 Jan 2021 14:18:34 -0800 Subject: skbuff: Add skb parameter to the ubuf zerocopy callback Add an optional skb parameter to the zerocopy callback parameter, which is passed down from skb_zcopy_clear(). This gives access to the original skb, which is needed for upcoming RX zero-copy error handling. Signed-off-by: Jonathan Lemon Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 5b8a53ab51fd..b23c3b4b3209 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -461,7 +461,8 @@ enum { * The desc field is used to track userspace buffer index. */ struct ubuf_info { - void (*callback)(struct ubuf_info *, bool zerocopy_success); + void (*callback)(struct sk_buff *, struct ubuf_info *, + bool zerocopy_success); union { struct { unsigned long desc; @@ -493,7 +494,8 @@ struct ubuf_info *sock_zerocopy_realloc(struct sock *sk, size_t size, void sock_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); -void sock_zerocopy_callback(struct ubuf_info *uarg, bool success); +void sock_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg, + bool success); int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len); int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, @@ -1473,20 +1475,17 @@ static inline void *skb_zcopy_get_nouarg(struct sk_buff *skb) static inline void skb_zcopy_put(struct ubuf_info *uarg) { if (uarg) - uarg->callback(uarg, true); + uarg->callback(NULL, uarg, true); } /* Release a reference on a zerocopy structure */ -static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy) +static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy_success) { struct ubuf_info *uarg = skb_zcopy(skb); if (uarg) { - if (skb_zcopy_is_nouarg(skb)) { - /* no notification callback */ - } else { - uarg->callback(uarg, zerocopy); - } + if (!skb_zcopy_is_nouarg(skb)) + uarg->callback(skb, uarg, zerocopy_success); skb_shinfo(skb)->tx_flags &= ~SKBTX_ZEROCOPY_FRAG; } -- cgit v1.2.3 From 236a6b1cd585a408139550201343f3f16f9324b9 Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Wed, 6 Jan 2021 14:18:35 -0800 Subject: skbuff: Call sock_zerocopy_put_abort from skb_zcopy_put_abort The sock_zerocopy_put_abort function contains logic which is specific to the current zerocopy implementation. Add a wrapper which checks the callback and dispatches apppropriately. Signed-off-by: Jonathan Lemon Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b23c3b4b3209..9f7393167f0a 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1478,6 +1478,16 @@ static inline void skb_zcopy_put(struct ubuf_info *uarg) uarg->callback(NULL, uarg, true); } +static inline void skb_zcopy_put_abort(struct ubuf_info *uarg, bool have_uref) +{ + if (uarg) { + if (uarg->callback == sock_zerocopy_callback) + sock_zerocopy_put_abort(uarg, have_uref); + else if (have_uref) + skb_zcopy_put(uarg); + } +} + /* Release a reference on a zerocopy structure */ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy_success) { -- cgit v1.2.3 From 8c793822c5803e01d03f71c431f59316f0b278b7 Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Wed, 6 Jan 2021 14:18:37 -0800 Subject: skbuff: rename sock_zerocopy_* to msg_zerocopy_* At Willem's suggestion, rename the sock_zerocopy_* functions so that they match the MSG_ZEROCOPY flag, which makes it clear they are specific to this zerocopy implementation. Signed-off-by: Jonathan Lemon Acked-by: Willem de Bruijn Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9f7393167f0a..f6a3cee5c967 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -488,14 +488,14 @@ struct ubuf_info { int mm_account_pinned_pages(struct mmpin *mmp, size_t size); void mm_unaccount_pinned_pages(struct mmpin *mmp); -struct ubuf_info *sock_zerocopy_alloc(struct sock *sk, size_t size); -struct ubuf_info *sock_zerocopy_realloc(struct sock *sk, size_t size, - struct ubuf_info *uarg); +struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size); +struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, + struct ubuf_info *uarg); -void sock_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); +void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); -void sock_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg, - bool success); +void msg_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg, + bool success); int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len); int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, @@ -1481,8 +1481,8 @@ static inline void skb_zcopy_put(struct ubuf_info *uarg) static inline void skb_zcopy_put_abort(struct ubuf_info *uarg, bool have_uref) { if (uarg) { - if (uarg->callback == sock_zerocopy_callback) - sock_zerocopy_put_abort(uarg, have_uref); + if (uarg->callback == msg_zerocopy_callback) + msg_zerocopy_put_abort(uarg, have_uref); else if (have_uref) skb_zcopy_put(uarg); } @@ -2776,7 +2776,7 @@ static inline int skb_orphan_frags(struct sk_buff *skb, gfp_t gfp_mask) if (likely(!skb_zcopy(skb))) return 0; if (!skb_zcopy_is_nouarg(skb) && - skb_uarg(skb)->callback == sock_zerocopy_callback) + skb_uarg(skb)->callback == msg_zerocopy_callback) return 0; return skb_copy_ubufs(skb, gfp_mask); } -- cgit v1.2.3 From 06b4feb37e64e543714c971a4162a75e2e4024d4 Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Wed, 6 Jan 2021 14:18:38 -0800 Subject: net: group skb_shinfo zerocopy related bits together. In preparation for expanded zerocopy (TX and RX), move the zerocopy related bits out of tx_flags into their own flag word. Signed-off-by: Jonathan Lemon Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 38 +++++++++++++++++++++----------------- 1 file changed, 21 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f6a3cee5c967..7b5adc511ac6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -430,28 +430,32 @@ enum { /* device driver is going to provide hardware time stamp */ SKBTX_IN_PROGRESS = 1 << 2, - /* device driver supports TX zero-copy buffers */ - SKBTX_DEV_ZEROCOPY = 1 << 3, - /* generate wifi status information (where possible) */ SKBTX_WIFI_STATUS = 1 << 4, - /* This indicates at least one fragment might be overwritten - * (as in vmsplice(), sendfile() ...) - * If we need to compute a TX checksum, we'll need to copy - * all frags to avoid possible bad checksum - */ - SKBTX_SHARED_FRAG = 1 << 5, - /* generate software time stamp when entering packet scheduling */ SKBTX_SCHED_TSTAMP = 1 << 6, }; -#define SKBTX_ZEROCOPY_FRAG (SKBTX_DEV_ZEROCOPY | SKBTX_SHARED_FRAG) #define SKBTX_ANY_SW_TSTAMP (SKBTX_SW_TSTAMP | \ SKBTX_SCHED_TSTAMP) #define SKBTX_ANY_TSTAMP (SKBTX_HW_TSTAMP | SKBTX_ANY_SW_TSTAMP) +/* Definitions for flags in struct skb_shared_info */ +enum { + /* use zcopy routines */ + SKBFL_ZEROCOPY_ENABLE = BIT(0), + + /* This indicates at least one fragment might be overwritten + * (as in vmsplice(), sendfile() ...) + * If we need to compute a TX checksum, we'll need to copy + * all frags to avoid possible bad checksum + */ + SKBFL_SHARED_FRAG = BIT(1), +}; + +#define SKBFL_ZEROCOPY_FRAG (SKBFL_ZEROCOPY_ENABLE | SKBFL_SHARED_FRAG) + /* * The callback notifies userspace to release buffers when skb DMA is done in * lower device, the skb last reference should be 0 when calling this. @@ -506,7 +510,7 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, * the end of the header data, ie. at skb->end. */ struct skb_shared_info { - __u8 __unused; + __u8 flags; __u8 meta_len; __u8 nr_frags; __u8 tx_flags; @@ -1433,7 +1437,7 @@ static inline struct skb_shared_hwtstamps *skb_hwtstamps(struct sk_buff *skb) static inline struct ubuf_info *skb_zcopy(struct sk_buff *skb) { - bool is_zcopy = skb && skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY; + bool is_zcopy = skb && skb_shinfo(skb)->flags & SKBFL_ZEROCOPY_ENABLE; return is_zcopy ? skb_uarg(skb) : NULL; } @@ -1452,14 +1456,14 @@ static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg, else skb_zcopy_get(uarg); skb_shinfo(skb)->destructor_arg = uarg; - skb_shinfo(skb)->tx_flags |= SKBTX_ZEROCOPY_FRAG; + skb_shinfo(skb)->flags |= SKBFL_ZEROCOPY_FRAG; } } static inline void skb_zcopy_set_nouarg(struct sk_buff *skb, void *val) { skb_shinfo(skb)->destructor_arg = (void *)((uintptr_t) val | 0x1UL); - skb_shinfo(skb)->tx_flags |= SKBTX_ZEROCOPY_FRAG; + skb_shinfo(skb)->flags |= SKBFL_ZEROCOPY_FRAG; } static inline bool skb_zcopy_is_nouarg(struct sk_buff *skb) @@ -1497,7 +1501,7 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy_success) if (!skb_zcopy_is_nouarg(skb)) uarg->callback(skb, uarg, zerocopy_success); - skb_shinfo(skb)->tx_flags &= ~SKBTX_ZEROCOPY_FRAG; + skb_shinfo(skb)->flags &= ~SKBFL_ZEROCOPY_FRAG; } } @@ -3323,7 +3327,7 @@ static inline int skb_linearize(struct sk_buff *skb) static inline bool skb_has_shared_frag(const struct sk_buff *skb) { return skb_is_nonlinear(skb) && - skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG; + skb_shinfo(skb)->flags & SKBFL_SHARED_FRAG; } /** -- cgit v1.2.3 From 04c2d33eabdc76df730e1e356f6b2c656381d7d5 Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Wed, 6 Jan 2021 14:18:39 -0800 Subject: skbuff: add flags to ubuf_info for ubuf setup Currently, when an ubuf is attached to a new skb, the shared flags word is initialized to a fixed value. Instead of doing this, set the default flags in the ubuf, and have new skbs inherit from this default. This is needed when setting up different zerocopy types. Signed-off-by: Jonathan Lemon Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7b5adc511ac6..a7bc71d2debb 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -480,6 +480,7 @@ struct ubuf_info { }; }; refcount_t refcnt; + u8 flags; struct mmpin { struct user_struct *user; @@ -1456,7 +1457,7 @@ static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg, else skb_zcopy_get(uarg); skb_shinfo(skb)->destructor_arg = uarg; - skb_shinfo(skb)->flags |= SKBFL_ZEROCOPY_FRAG; + skb_shinfo(skb)->flags |= uarg->flags; } } -- cgit v1.2.3 From 9ee5e5ade033875191a2d2e470033e9cdde44a6a Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Wed, 6 Jan 2021 14:18:40 -0800 Subject: tap/tun: add skb_zcopy_init() helper for initialization. Replace direct assignments with skb_zcopy_init() for zerocopy cases where a new skb is initialized, without changing the reference counts. Signed-off-by: Jonathan Lemon Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a7bc71d2debb..68ad45a98810 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1448,6 +1448,12 @@ static inline void skb_zcopy_get(struct ubuf_info *uarg) refcount_inc(&uarg->refcnt); } +static inline void skb_zcopy_init(struct sk_buff *skb, struct ubuf_info *uarg) +{ + skb_shinfo(skb)->destructor_arg = uarg; + skb_shinfo(skb)->flags |= uarg->flags; +} + static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg, bool *have_ref) { @@ -1456,8 +1462,7 @@ static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg, *have_ref = false; else skb_zcopy_get(uarg); - skb_shinfo(skb)->destructor_arg = uarg; - skb_shinfo(skb)->flags |= uarg->flags; + skb_zcopy_init(skb, uarg); } } -- cgit v1.2.3 From 8e0449172497a915e79da66b222255dc9b4a5f31 Mon Sep 17 00:00:00 2001 From: Jonathan Lemon Date: Wed, 6 Jan 2021 14:18:41 -0800 Subject: skbuff: Rename skb_zcopy_{get|put} to net_zcopy_{get|put} Unlike the rest of the skb_zcopy_ functions, these routines operate on a 'struct ubuf', not a skb. Remove the 'skb_' prefix from the naming to make things clearer. Suggested-by: Willem de Bruijn Signed-off-by: Jonathan Lemon Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 68ad45a98810..7a057b1f1eb8 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1443,7 +1443,7 @@ static inline struct ubuf_info *skb_zcopy(struct sk_buff *skb) return is_zcopy ? skb_uarg(skb) : NULL; } -static inline void skb_zcopy_get(struct ubuf_info *uarg) +static inline void net_zcopy_get(struct ubuf_info *uarg) { refcount_inc(&uarg->refcnt); } @@ -1461,7 +1461,7 @@ static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg, if (unlikely(have_ref && *have_ref)) *have_ref = false; else - skb_zcopy_get(uarg); + net_zcopy_get(uarg); skb_zcopy_init(skb, uarg); } } @@ -1482,19 +1482,19 @@ static inline void *skb_zcopy_get_nouarg(struct sk_buff *skb) return (void *)((uintptr_t) skb_shinfo(skb)->destructor_arg & ~0x1UL); } -static inline void skb_zcopy_put(struct ubuf_info *uarg) +static inline void net_zcopy_put(struct ubuf_info *uarg) { if (uarg) uarg->callback(NULL, uarg, true); } -static inline void skb_zcopy_put_abort(struct ubuf_info *uarg, bool have_uref) +static inline void net_zcopy_put_abort(struct ubuf_info *uarg, bool have_uref) { if (uarg) { if (uarg->callback == msg_zerocopy_callback) msg_zerocopy_put_abort(uarg, have_uref); else if (have_uref) - skb_zcopy_put(uarg); + net_zcopy_put(uarg); } } -- cgit v1.2.3 From 33cb6d1ed311af2c1dfd107fa334cfb51113ef35 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Mon, 28 Dec 2020 21:30:21 +0100 Subject: dmaengine: at_hdmac: remove platform data header linux/platform_data/dma-atmel.h is only used by the at_hdmac driver. Move the CFG bits definitions back in at_hdmac_regs.h and the remaining definitions in the driver. Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20201228203022.2674133-1-alexandre.belloni@bootlin.com Signed-off-by: Vinod Koul --- include/linux/platform_data/dma-atmel.h | 61 --------------------------------- 1 file changed, 61 deletions(-) delete mode 100644 include/linux/platform_data/dma-atmel.h (limited to 'include/linux') diff --git a/include/linux/platform_data/dma-atmel.h b/include/linux/platform_data/dma-atmel.h deleted file mode 100644 index 069637e6004f..000000000000 --- a/include/linux/platform_data/dma-atmel.h +++ /dev/null @@ -1,61 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Header file for the Atmel AHB DMA Controller driver - * - * Copyright (C) 2008 Atmel Corporation - */ -#ifndef AT_HDMAC_H -#define AT_HDMAC_H - -#include - -/** - * struct at_dma_platform_data - Controller configuration parameters - * @nr_channels: Number of channels supported by hardware (max 8) - * @cap_mask: dma_capability flags supported by the platform - */ -struct at_dma_platform_data { - unsigned int nr_channels; - dma_cap_mask_t cap_mask; -}; - -/** - * struct at_dma_slave - Controller-specific information about a slave - * @dma_dev: required DMA master device - * @cfg: Platform-specific initializer for the CFG register - */ -struct at_dma_slave { - struct device *dma_dev; - u32 cfg; -}; - - -/* Platform-configurable bits in CFG */ -#define ATC_PER_MSB(h) ((0x30U & (h)) >> 4) /* Extract most significant bits of a handshaking identifier */ - -#define ATC_SRC_PER(h) (0xFU & (h)) /* Channel src rq associated with periph handshaking ifc h */ -#define ATC_DST_PER(h) ((0xFU & (h)) << 4) /* Channel dst rq associated with periph handshaking ifc h */ -#define ATC_SRC_REP (0x1 << 8) /* Source Replay Mod */ -#define ATC_SRC_H2SEL (0x1 << 9) /* Source Handshaking Mod */ -#define ATC_SRC_H2SEL_SW (0x0 << 9) -#define ATC_SRC_H2SEL_HW (0x1 << 9) -#define ATC_SRC_PER_MSB(h) (ATC_PER_MSB(h) << 10) /* Channel src rq (most significant bits) */ -#define ATC_DST_REP (0x1 << 12) /* Destination Replay Mod */ -#define ATC_DST_H2SEL (0x1 << 13) /* Destination Handshaking Mod */ -#define ATC_DST_H2SEL_SW (0x0 << 13) -#define ATC_DST_H2SEL_HW (0x1 << 13) -#define ATC_DST_PER_MSB(h) (ATC_PER_MSB(h) << 14) /* Channel dst rq (most significant bits) */ -#define ATC_SOD (0x1 << 16) /* Stop On Done */ -#define ATC_LOCK_IF (0x1 << 20) /* Interface Lock */ -#define ATC_LOCK_B (0x1 << 21) /* AHB Bus Lock */ -#define ATC_LOCK_IF_L (0x1 << 22) /* Master Interface Arbiter Lock */ -#define ATC_LOCK_IF_L_CHUNK (0x0 << 22) -#define ATC_LOCK_IF_L_BUFFER (0x1 << 22) -#define ATC_AHB_PROT_MASK (0x7 << 24) /* AHB Protection */ -#define ATC_FIFOCFG_MASK (0x3 << 28) /* FIFO Request Configuration */ -#define ATC_FIFOCFG_LARGESTBURST (0x0 << 28) -#define ATC_FIFOCFG_HALFFIFO (0x1 << 28) -#define ATC_FIFOCFG_ENOUGHSPACE (0x2 << 28) - - -#endif /* AT_HDMAC_H */ -- cgit v1.2.3 From 994122211665301080cd232c06ae219b681dcb57 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 7 Jan 2021 17:34:01 -0600 Subject: remoteproc: qcom: expose types for COMPILE_TEST Stub functions are defined for SSR notifier registration in case QCOM_RPROC_COMMON is not configured. As a result, code that uses these functions can link successfully even if the common remoteproc code is not built. Code that registers an SSR notifier function likely needs the types defined in "qcom_rproc.h", but those are only exposed if QCOM_RPROC_COMMON is enabled. Rearrange the conditional definition so the qcom_ssr_notify_data structure and qcom_ssr_notify_type enumerated type are defined whether or not QCOM_RPROC_COMMON is enabled. Reviewed-by: Bjorn Andersson Signed-off-by: Alex Elder Signed-off-by: Jakub Kicinski --- include/linux/remoteproc/qcom_rproc.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/remoteproc/qcom_rproc.h b/include/linux/remoteproc/qcom_rproc.h index 647051662174..82b211518136 100644 --- a/include/linux/remoteproc/qcom_rproc.h +++ b/include/linux/remoteproc/qcom_rproc.h @@ -3,8 +3,6 @@ struct notifier_block; -#if IS_ENABLED(CONFIG_QCOM_RPROC_COMMON) - /** * enum qcom_ssr_notify_type - Startup/Shutdown events related to a remoteproc * processor. @@ -26,6 +24,8 @@ struct qcom_ssr_notify_data { bool crashed; }; +#if IS_ENABLED(CONFIG_QCOM_RPROC_COMMON) + void *qcom_register_ssr_notifier(const char *name, struct notifier_block *nb); int qcom_unregister_ssr_notifier(void *notify, struct notifier_block *nb); -- cgit v1.2.3 From ce2ceb9b1cff777c7d8beb368eddc3b8e45381f6 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Thu, 7 Jan 2021 17:34:02 -0600 Subject: soc: qcom: mdt_loader: define stubs for COMPILE_TEST Define stub functions for the exposed MDT functions in case QCOM_MDT_LOADER is not configured. This allows users of these functions to link correctly for COMPILE_TEST builds without QCOM_SCM enabled. Reviewed-by: Bjorn Andersson Signed-off-by: Alex Elder Signed-off-by: Jakub Kicinski --- include/linux/soc/qcom/mdt_loader.h | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/qcom/mdt_loader.h b/include/linux/soc/qcom/mdt_loader.h index e600baec6825..afd47217996b 100644 --- a/include/linux/soc/qcom/mdt_loader.h +++ b/include/linux/soc/qcom/mdt_loader.h @@ -11,6 +11,8 @@ struct device; struct firmware; +#if IS_ENABLED(CONFIG_QCOM_MDT_LOADER) + ssize_t qcom_mdt_get_size(const struct firmware *fw); int qcom_mdt_load(struct device *dev, const struct firmware *fw, const char *fw_name, int pas_id, void *mem_region, @@ -23,4 +25,37 @@ int qcom_mdt_load_no_init(struct device *dev, const struct firmware *fw, phys_addr_t *reloc_base); void *qcom_mdt_read_metadata(const struct firmware *fw, size_t *data_len); +#else /* !IS_ENABLED(CONFIG_QCOM_MDT_LOADER) */ + +static inline ssize_t qcom_mdt_get_size(const struct firmware *fw) +{ + return -ENODEV; +} + +static inline int qcom_mdt_load(struct device *dev, const struct firmware *fw, + const char *fw_name, int pas_id, + void *mem_region, phys_addr_t mem_phys, + size_t mem_size, phys_addr_t *reloc_base) +{ + return -ENODEV; +} + +static inline int qcom_mdt_load_no_init(struct device *dev, + const struct firmware *fw, + const char *fw_name, int pas_id, + void *mem_region, phys_addr_t mem_phys, + size_t mem_size, + phys_addr_t *reloc_base) +{ + return -ENODEV; +} + +static inline void *qcom_mdt_read_metadata(const struct firmware *fw, + size_t *data_len) +{ + return ERR_PTR(-ENODEV); +} + +#endif /* !IS_ENABLED(CONFIG_QCOM_MDT_LOADER) */ + #endif -- cgit v1.2.3 From 1d11fa696733ffb9ac24771716b1b1b9953e5a48 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 8 Jan 2021 03:39:03 -0800 Subject: net-gro: remove GRO_DROP GRO_DROP can only be returned from napi_gro_frags() if the skb has not been allocated by a prior napi_get_frags() Since drivers must use napi_get_frags() and test its result before populating the skb with metadata, we can safely remove GRO_DROP since it offers no practical use. Signed-off-by: Eric Dumazet Cc: Jesse Brandeburg Acked-by: Edward Cree Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1ec3ac5d5bbf..5b949076ed23 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -376,7 +376,6 @@ enum gro_result { GRO_MERGED_FREE, GRO_HELD, GRO_NORMAL, - GRO_DROP, GRO_CONSUMED, }; typedef enum gro_result gro_result_t; -- cgit v1.2.3 From 8fbdbb66f8c10bb359ad20fff95628e5deac88f4 Mon Sep 17 00:00:00 2001 From: Darren Salt Date: Tue, 5 Jan 2021 14:44:01 +0100 Subject: PCI: Export pci_rebar_get_possible_sizes() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Export pci_rebar_get_possible_sizes() for use by modular drivers. Signed-off-by: Darren Salt Signed-off-by: Nirmoy Das Signed-off-by: Christian König Acked-by: Bjorn Helgaas Link: https://patchwork.kernel.org/project/dri-devel/patch/20210107175017.15893-2-nirmoy.das@amd.com --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index b32126d26997..5f25a0ec48c1 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1232,6 +1232,7 @@ void pci_update_resource(struct pci_dev *dev, int resno); int __must_check pci_assign_resource(struct pci_dev *dev, int i); int __must_check pci_reassign_resource(struct pci_dev *dev, int i, resource_size_t add_size, resource_size_t align); void pci_release_resource(struct pci_dev *dev, int resno); +u32 pci_rebar_get_possible_sizes(struct pci_dev *pdev, int bar); int __must_check pci_resize_resource(struct pci_dev *dev, int i, int size); int pci_select_bars(struct pci_dev *dev, unsigned long flags); bool pci_device_is_present(struct pci_dev *pdev); -- cgit v1.2.3 From 192f1bf7559e895d51f81c3976c5892c8b1e0601 Mon Sep 17 00:00:00 2001 From: Nirmoy Das Date: Thu, 7 Jan 2021 14:30:34 +0100 Subject: PCI: Add pci_rebar_bytes_to_size() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Users of pci_resize_resource() need a way to calculate BAR size from desired bytes. Add a helper function and export it so that modular drivers can use it. Signed-off-by: Darren Salt Signed-off-by: Christian König Signed-off-by: Nirmoy Das Acked-by: Bjorn Helgaas Link: https://patchwork.kernel.org/project/dri-devel/patch/20210107175017.15893-3-nirmoy.das@amd.com --- include/linux/pci.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 5f25a0ec48c1..53f4904ee83d 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1232,6 +1232,14 @@ void pci_update_resource(struct pci_dev *dev, int resno); int __must_check pci_assign_resource(struct pci_dev *dev, int i); int __must_check pci_reassign_resource(struct pci_dev *dev, int i, resource_size_t add_size, resource_size_t align); void pci_release_resource(struct pci_dev *dev, int resno); +static inline int pci_rebar_bytes_to_size(u64 bytes) +{ + bytes = roundup_pow_of_two(bytes); + + /* Return BAR size as defined in the resizable BAR specification */ + return max(ilog2(bytes), 20) - 20; +} + u32 pci_rebar_get_possible_sizes(struct pci_dev *pdev, int bar); int __must_check pci_resize_resource(struct pci_dev *dev, int i, int size); int pci_select_bars(struct pci_dev *dev, unsigned long flags); -- cgit v1.2.3 From 398cb92495cc1972014ffa81ff9cea1e5167b8df Mon Sep 17 00:00:00 2001 From: Guo Ren Date: Fri, 13 Nov 2020 09:48:27 +0000 Subject: csky: Fixup perf probe failed Current perf init will failed with: [ 1.452433] csky-pmu: probe of soc:pmu failed with error -16 This patch fix it up with adding CPUHP_AP_PERF_CSKY_ONLINE in cpuhotplug.h. Signed-off-by: Guo Ren Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Arnaldo Carvalho de Melo --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 0042ef362511..d3e26dc81494 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -185,6 +185,7 @@ enum cpuhp_state { CPUHP_AP_PERF_POWERPC_TRACE_IMC_ONLINE, CPUHP_AP_PERF_POWERPC_HV_24x7_ONLINE, CPUHP_AP_PERF_POWERPC_HV_GPCI_ONLINE, + CPUHP_AP_PERF_CSKY_ONLINE, CPUHP_AP_WATCHDOG_ONLINE, CPUHP_AP_WORKQUEUE_ONLINE, CPUHP_AP_RCUTREE_ONLINE, -- cgit v1.2.3 From 04769cb1c45a919cd94b931e6494d2a9afc32914 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 27 Nov 2020 17:41:19 +0100 Subject: mm/frame-vector: Use FOLL_LONGTERM MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This is used by media/videbuf2 for persistent dma mappings, not just for a single dma operation and then freed again, so needs FOLL_LONGTERM. Unfortunately current pup_locked doesn't support FOLL_LONGTERM due to locking issues. Rework the code to pull the pup path out from the mmap_sem critical section as suggested by Jason. By relying entirely on the vma checks in pin_user_pages and follow_pfn (for vm_flags and vma_is_fsdax) we can also streamline the code a lot. Note that pin_user_pages_fast is a safe replacement despite the seeming lack of checking for vma->vm_flasg & (VM_IO | VM_PFNMAP). Such ptes are marked with pte_mkspecial (which pup_fast rejects in the fastpath), and only architectures supporting that support the pin_user_pages_fast fastpath. Signed-off-by: Daniel Vetter Cc: Christoph Hellwig Cc: Jason Gunthorpe Cc: Pawel Osciak Cc: Marek Szyprowski Cc: Kyungmin Park Cc: Tomasz Figa Cc: Mauro Carvalho Chehab Cc: Andrew Morton Cc: John Hubbard Cc: Jérôme Glisse Cc: Jan Kara Cc: Dan Williams Cc: linux-mm@kvack.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-samsung-soc@vger.kernel.org Cc: linux-media@vger.kernel.org Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20201127164131.2244124-6-daniel.vetter@ffwll.ch --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index ecdf8a8cd6ae..2e7b1d048df9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1768,7 +1768,7 @@ struct frame_vector { struct frame_vector *frame_vector_create(unsigned int nr_frames); void frame_vector_destroy(struct frame_vector *vec); int get_vaddr_frames(unsigned long start, unsigned int nr_pfns, - unsigned int gup_flags, struct frame_vector *vec); + struct frame_vector *vec); void put_vaddr_frames(struct frame_vector *vec); int frame_vector_to_pages(struct frame_vector *vec); void frame_vector_to_pfns(struct frame_vector *vec); -- cgit v1.2.3 From eb83b8e3e6478845f8130622a2048ed4ec3b3be3 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 27 Nov 2020 17:41:20 +0100 Subject: media: videobuf2: Move frame_vector into media subsystem MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It's the only user. This also garbage collects the CONFIG_FRAME_VECTOR symbol from all over the tree (well just one place, somehow omap media driver still had this in its Kconfig, despite not using it). Reviewed-by: John Hubbard Acked-by: Hans Verkuil Acked-by: Mauro Carvalho Chehab Acked-by: Tomasz Figa Signed-off-by: Daniel Vetter Cc: Jason Gunthorpe Cc: Pawel Osciak Cc: Marek Szyprowski Cc: Kyungmin Park Cc: Tomasz Figa Cc: Mauro Carvalho Chehab Cc: Andrew Morton Cc: John Hubbard Cc: Jérôme Glisse Cc: Jan Kara Cc: Dan Williams Cc: linux-mm@kvack.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-samsung-soc@vger.kernel.org Cc: linux-media@vger.kernel.org Cc: Daniel Vetter Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20201127164131.2244124-7-daniel.vetter@ffwll.ch --- include/linux/mm.h | 42 ------------------------------------------ 1 file changed, 42 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 2e7b1d048df9..049439b65553 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1754,48 +1754,6 @@ int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc); int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc, struct task_struct *task, bool bypass_rlim); -/* Container for pinned pfns / pages */ -struct frame_vector { - unsigned int nr_allocated; /* Number of frames we have space for */ - unsigned int nr_frames; /* Number of frames stored in ptrs array */ - bool got_ref; /* Did we pin pages by getting page ref? */ - bool is_pfns; /* Does array contain pages or pfns? */ - void *ptrs[]; /* Array of pinned pfns / pages. Use - * pfns_vector_pages() or pfns_vector_pfns() - * for access */ -}; - -struct frame_vector *frame_vector_create(unsigned int nr_frames); -void frame_vector_destroy(struct frame_vector *vec); -int get_vaddr_frames(unsigned long start, unsigned int nr_pfns, - struct frame_vector *vec); -void put_vaddr_frames(struct frame_vector *vec); -int frame_vector_to_pages(struct frame_vector *vec); -void frame_vector_to_pfns(struct frame_vector *vec); - -static inline unsigned int frame_vector_count(struct frame_vector *vec) -{ - return vec->nr_frames; -} - -static inline struct page **frame_vector_pages(struct frame_vector *vec) -{ - if (vec->is_pfns) { - int err = frame_vector_to_pages(vec); - - if (err) - return ERR_PTR(err); - } - return (struct page **)(vec->ptrs); -} - -static inline unsigned long *frame_vector_pfns(struct frame_vector *vec) -{ - if (!vec->is_pfns) - frame_vector_to_pfns(vec); - return (unsigned long *)(vec->ptrs); -} - struct kvec; int get_kernel_pages(const struct kvec *iov, int nr_pages, int write, struct page **pages); -- cgit v1.2.3 From 96667f8a4382db9ed042332ca6ee165ae9b91307 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 27 Nov 2020 17:41:21 +0100 Subject: mm: Close race in generic_access_phys MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Way back it was a reasonable assumptions that iomem mappings never change the pfn range they point at. But this has changed: - gpu drivers dynamically manage their memory nowadays, invalidating ptes with unmap_mapping_range when buffers get moved - contiguous dma allocations have moved from dedicated carvetouts to cma regions. This means if we miss the unmap the pfn might contain pagecache or anon memory (well anything allocated with GFP_MOVEABLE) - even /dev/mem now invalidates mappings when the kernel requests that iomem region when CONFIG_IO_STRICT_DEVMEM is set, see 3234ac664a87 ("/dev/mem: Revoke mappings when a driver claims the region") Accessing pfns obtained from ptes without holding all the locks is therefore no longer a good idea. Fix this. Since ioremap might need to manipulate pagetables too we need to drop the pt lock and have a retry loop if we raced. While at it, also add kerneldoc and improve the comment for the vma_ops->access function. It's for accessing, not for moving the memory from iomem to system memory, as the old comment seemed to suggest. References: 28b2ee20c7cb ("access_process_vm device memory infrastructure") Signed-off-by: Daniel Vetter Cc: Jason Gunthorpe Cc: Dan Williams Cc: Kees Cook Cc: Benjamin Herrensmidt Cc: Dave Airlie Cc: Andrew Morton Cc: John Hubbard Cc: Jérôme Glisse Cc: Jan Kara Cc: Dan Williams Cc: linux-mm@kvack.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-samsung-soc@vger.kernel.org Cc: linux-media@vger.kernel.org Cc: Chris Wilson Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20201127164131.2244124-8-daniel.vetter@ffwll.ch --- include/linux/mm.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 049439b65553..c9900aedc195 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -590,7 +590,8 @@ struct vm_operations_struct { vm_fault_t (*pfn_mkwrite)(struct vm_fault *vmf); /* called by access_process_vm when get_user_pages() fails, typically - * for use by special VMAs that can switch between memory and hardware + * for use by special VMAs. See also generic_access_phys() for a generic + * implementation useful for any iomem mapping. */ int (*access)(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write); -- cgit v1.2.3 From 71a1d8ed900f8cf53151beff17e3e2ff8e9283a1 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 27 Nov 2020 17:41:24 +0100 Subject: resource: Move devmem revoke code to resource framework MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We want all iomem mmaps to consistently revoke ptes when the kernel takes over and CONFIG_IO_STRICT_DEVMEM is enabled. This includes the pci bar mmaps available through procfs and sysfs, which currently do not revoke mappings. To prepare for this, move the code from the /dev/kmem driver to kernel/resource.c. During review Jason spotted that barriers are used somewhat inconsistently. Fix that up while we shuffle this code, since it doesn't have an actual impact at runtime. Otherwise no semantic and behavioural changes intended, just code extraction and adjusting comments and names. Reviewed-by: Greg Kroah-Hartman Signed-off-by: Daniel Vetter Cc: Jason Gunthorpe Cc: Kees Cook Cc: Dan Williams Cc: Andrew Morton Cc: John Hubbard Cc: Jérôme Glisse Cc: Jan Kara Cc: Dan Williams Cc: linux-mm@kvack.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-samsung-soc@vger.kernel.org Cc: linux-media@vger.kernel.org Cc: Arnd Bergmann Cc: Greg Kroah-Hartman Cc: Daniel Vetter Cc: David Hildenbrand Cc: "Rafael J. Wysocki" Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20201127164131.2244124-11-daniel.vetter@ffwll.ch --- include/linux/ioport.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index fe48b7840665..55de385c839c 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -334,11 +334,7 @@ static inline void irqresource_disabled(struct resource *res, u32 irq) res->flags = IORESOURCE_IRQ | IORESOURCE_DISABLED | IORESOURCE_UNSET; } -#ifdef CONFIG_IO_STRICT_DEVMEM -void revoke_devmem(struct resource *res); -#else -static inline void revoke_devmem(struct resource *res) { }; -#endif +extern struct address_space *iomem_get_mapping(void); #endif /* __ASSEMBLY__ */ #endif /* _LINUX_IOPORT_H */ -- cgit v1.2.3 From 74b30195395c406c787280a77ae55aed82dbbfc7 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 27 Nov 2020 17:41:25 +0100 Subject: sysfs: Support zapping of binary attr mmaps MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We want to be able to revoke pci mmaps so that the same access rules applies as for /dev/kmem. Revoke support for devmem was added in 3234ac664a87 ("/dev/mem: Revoke mappings when a driver claims the region"). The simplest way to achieve this is by having the same filp->f_mapping for all mappings, so that unmap_mapping_range can find them all, no matter through which file they've been created. Since this must be set at open time we need sysfs support for this. Add an optional mapping parameter bin_attr, which is only consulted when there's also an mmap callback, since without mmap support allowing to adjust the ->f_mapping makes no sense. Reviewed-by: Greg Kroah-Hartman Signed-off-by: Daniel Vetter Cc: Jason Gunthorpe Cc: Kees Cook Cc: Dan Williams Cc: Andrew Morton Cc: John Hubbard Cc: Jérôme Glisse Cc: Jan Kara Cc: Dan Williams Cc: linux-mm@kvack.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-samsung-soc@vger.kernel.org Cc: linux-media@vger.kernel.org Cc: Bjorn Helgaas Cc: linux-pci@vger.kernel.org Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Cc: Christian Brauner Cc: "David S. Miller" Cc: Michael Ellerman Cc: Sourabh Jain Cc: Daniel Vetter Cc: Mauro Carvalho Chehab Cc: Nayna Jain Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20201127164131.2244124-12-daniel.vetter@ffwll.ch --- include/linux/sysfs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 2caa34c1ca1a..d76a1ddf83a3 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -164,11 +164,13 @@ __ATTRIBUTE_GROUPS(_name) struct file; struct vm_area_struct; +struct address_space; struct bin_attribute { struct attribute attr; size_t size; void *private; + struct address_space *mapping; ssize_t (*read)(struct file *, struct kobject *, struct bin_attribute *, char *, loff_t, size_t); ssize_t (*write)(struct file *, struct kobject *, struct bin_attribute *, -- cgit v1.2.3 From b90f3726ea3811421f56757e866f01f6e2bb37d6 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 6 Jan 2021 18:33:04 -0800 Subject: linux/clk.h: use correct kernel-doc notation for 2 functions Fix kernel-doc notation for 2 functions so that the generated html is correct. Currently it skips all text between the ':' and the '-', so "[un]register a clock rate" is missing. Fixes: 86bcfa2e87c4 ("clk: add pr_debug & kerneldoc around clk notifiers") Signed-off-by: Randy Dunlap Cc: Mike Turquette Cc: Russell King Cc: linux-clk@vger.kernel.org Link: https://lore.kernel.org/r/20210107023304.24442-1-rdunlap@infradead.org Signed-off-by: Stephen Boyd --- include/linux/clk.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk.h b/include/linux/clk.h index 31ff1bf1b79f..45e698b74178 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -92,7 +92,7 @@ struct clk_bulk_data { #ifdef CONFIG_COMMON_CLK /** - * clk_notifier_register: register a clock rate-change notifier callback + * clk_notifier_register - register a clock rate-change notifier callback * @clk: clock whose rate we are interested in * @nb: notifier block with callback function pointer * @@ -103,7 +103,7 @@ struct clk_bulk_data { int clk_notifier_register(struct clk *clk, struct notifier_block *nb); /** - * clk_notifier_unregister: unregister a clock rate-change notifier callback + * clk_notifier_unregister - unregister a clock rate-change notifier callback * @clk: clock whose rate we are no longer interested in * @nb: notifier block which will be unregistered */ -- cgit v1.2.3 From 3188677d4901fbfb7a363ab2558e0a4bc76deecb Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sun, 10 Jan 2021 15:01:59 +0100 Subject: power: supply: max8903: Absorb pdata header The platform data header is not included by any other file in the kernel but the driver itself. Decomission the stand-alone header and absorb it into the driver itself. Cc: Chris Lapa Cc: MyungJoo Ham Signed-off-by: Linus Walleij Signed-off-by: Sebastian Reichel --- include/linux/power/max8903_charger.h | 43 ----------------------------------- 1 file changed, 43 deletions(-) delete mode 100644 include/linux/power/max8903_charger.h (limited to 'include/linux') diff --git a/include/linux/power/max8903_charger.h b/include/linux/power/max8903_charger.h deleted file mode 100644 index 02f94a1b323b..000000000000 --- a/include/linux/power/max8903_charger.h +++ /dev/null @@ -1,43 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * max8903_charger.h - Maxim 8903 USB/Adapter Charger Driver - * - * Copyright (C) 2011 Samsung Electronics - * MyungJoo Ham - */ - -#ifndef __MAX8903_CHARGER_H__ -#define __MAX8903_CHARGER_H__ - -struct max8903_pdata { - /* - * GPIOs - * cen, chg, flt, dcm and usus are optional. - * dok and uok are not optional depending on the status of - * dc_valid and usb_valid. - */ - int cen; /* Charger Enable input */ - int dok; /* DC(Adapter) Power OK output */ - int uok; /* USB Power OK output */ - int chg; /* Charger status output */ - int flt; /* Fault output */ - int dcm; /* Current-Limit Mode input (1: DC, 2: USB) */ - int usus; /* USB Suspend Input (1: suspended) */ - - /* - * DC(Adapter/TA) is wired - * When dc_valid is true, - * dok should be valid. - * - * At least one of dc_valid or usb_valid should be true. - */ - bool dc_valid; - /* - * USB is wired - * When usb_valid is true, - * uok should be valid. - */ - bool usb_valid; -}; - -#endif /* __MAX8903_CHARGER_H__ */ -- cgit v1.2.3 From a643bff752dcf72a07e1b2ab2f8587e4f51118be Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 11 Jan 2021 23:55:14 -0800 Subject: bpf: Add bpf_patch_call_args prototype to include/linux/bpf.h Add bpf_patch_call_args() prototype. This function is called from BPF verifier and only if CONFIG_BPF_JIT_ALWAYS_ON is not defined. This fixes compiler warning about missing prototype in some kernel configurations. Fixes: 1ea47e01ad6e ("bpf: add support for bpf_call to interpreter") Reported-by: kernel test robot Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210112075520.4103414-2-andrii@kernel.org --- include/linux/bpf.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 07cb5d15e743..ef9309604b3e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1403,7 +1403,10 @@ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size) /* verify correctness of eBPF program */ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, union bpf_attr __user *uattr); + +#ifndef CONFIG_BPF_JIT_ALWAYS_ON void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth); +#endif struct btf *bpf_get_btf_vmlinux(void); -- cgit v1.2.3 From 6943c2b05bf09fd5c5729f7d7d803bf3f126cb9a Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 11 Jan 2021 23:55:15 -0800 Subject: bpf: Avoid warning when re-casting __bpf_call_base into __bpf_call_base_args BPF interpreter uses extra input argument, so re-casts __bpf_call_base into __bpf_call_base_args. Avoid compiler warning about incompatible function prototypes by casting to void * first. Fixes: 1ea47e01ad6e ("bpf: add support for bpf_call to interpreter") Reported-by: kernel test robot Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210112075520.4103414-3-andrii@kernel.org --- include/linux/filter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 29c27656165b..5edf2b660881 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -886,7 +886,7 @@ void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp); u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); #define __bpf_call_base_args \ ((u64 (*)(u64, u64, u64, u64, u64, const struct bpf_insn *)) \ - __bpf_call_base) + (void *)__bpf_call_base) struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog); void bpf_jit_compile(struct bpf_prog *prog); -- cgit v1.2.3 From 936f8946bdb48239f4292812d4d2e26c6d328c95 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 11 Jan 2021 23:55:16 -0800 Subject: bpf: Declare __bpf_free_used_maps() unconditionally __bpf_free_used_maps() is always defined in kernel/bpf/core.c, while include/linux/bpf.h is guarding it behind CONFIG_BPF_SYSCALL. Move it out of that guard region and fix compiler warning. Fixes: a2ea07465c8d ("bpf: Fix missing prog untrack in release_maps") Reported-by: kernel test robot Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210112075520.4103414-4-andrii@kernel.org --- include/linux/bpf.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index ef9309604b3e..6e585dbc10df 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1206,8 +1206,6 @@ void bpf_prog_sub(struct bpf_prog *prog, int i); void bpf_prog_inc(struct bpf_prog *prog); struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog); void bpf_prog_put(struct bpf_prog *prog); -void __bpf_free_used_maps(struct bpf_prog_aux *aux, - struct bpf_map **used_maps, u32 len); void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock); void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock); @@ -1676,6 +1674,9 @@ static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, return bpf_prog_get_type_dev(ufd, type, false); } +void __bpf_free_used_maps(struct bpf_prog_aux *aux, + struct bpf_map **used_maps, u32 len); + bool bpf_prog_get_ok(struct bpf_prog *, enum bpf_prog_type *, bool); int bpf_prog_offload_compile(struct bpf_prog *prog); -- cgit v1.2.3 From 541c3bad8dc51b253ba8686d0cd7628e6b9b5f4c Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 11 Jan 2021 23:55:18 -0800 Subject: bpf: Support BPF ksym variables in kernel modules Add support for directly accessing kernel module variables from BPF programs using special ldimm64 instructions. This functionality builds upon vmlinux ksym support, but extends ldimm64 with src_reg=BPF_PSEUDO_BTF_ID to allow specifying kernel module BTF's FD in insn[1].imm field. During BPF program load time, verifier will resolve FD to BTF object and will take reference on BTF object itself and, for module BTFs, corresponding module as well, to make sure it won't be unloaded from under running BPF program. The mechanism used is similar to how bpf_prog keeps track of used bpf_maps. One interesting change is also in how per-CPU variable is determined. The logic is to find .data..percpu data section in provided BTF, but both vmlinux and module each have their own .data..percpu entries in BTF. So for module's case, the search for DATASEC record needs to look at only module's added BTF types. This is implemented with custom search function. Signed-off-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Acked-by: Hao Luo Link: https://lore.kernel.org/bpf/20210112075520.4103414-6-andrii@kernel.org --- include/linux/bpf.h | 10 ++++++++++ include/linux/bpf_verifier.h | 3 +++ include/linux/btf.h | 3 +++ 3 files changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 6e585dbc10df..1aac2af12fed 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -761,9 +761,15 @@ struct bpf_ctx_arg_aux { u32 btf_id; }; +struct btf_mod_pair { + struct btf *btf; + struct module *module; +}; + struct bpf_prog_aux { atomic64_t refcnt; u32 used_map_cnt; + u32 used_btf_cnt; u32 max_ctx_offset; u32 max_pkt_offset; u32 max_tp_access; @@ -802,6 +808,7 @@ struct bpf_prog_aux { const struct bpf_prog_ops *ops; struct bpf_map **used_maps; struct mutex used_maps_mutex; /* mutex for used_maps and used_map_cnt */ + struct btf_mod_pair *used_btfs; struct bpf_prog *prog; struct user_struct *user; u64 load_time; /* ns since boottime */ @@ -1668,6 +1675,9 @@ bpf_base_func_proto(enum bpf_func_id func_id) } #endif /* CONFIG_BPF_SYSCALL */ +void __bpf_free_used_btfs(struct bpf_prog_aux *aux, + struct btf_mod_pair *used_btfs, u32 len); + static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type) { diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index e941fe1484e5..dfe6f85d97dd 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -340,6 +340,7 @@ struct bpf_insn_aux_data { }; #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */ +#define MAX_USED_BTFS 64 /* max number of BTFs accessed by one BPF program */ #define BPF_VERIFIER_TMP_LOG_SIZE 1024 @@ -398,7 +399,9 @@ struct bpf_verifier_env { struct bpf_verifier_state_list **explored_states; /* search pruning optimization */ struct bpf_verifier_state_list *free_list; struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */ + struct btf_mod_pair used_btfs[MAX_USED_BTFS]; /* array of BTF's used by BPF program */ u32 used_map_cnt; /* number of used maps */ + u32 used_btf_cnt; /* number of used BTF objects */ u32 id_gen; /* used to generate unique reg IDs */ bool allow_ptr_leaks; bool allow_ptr_to_map_access; diff --git a/include/linux/btf.h b/include/linux/btf.h index 4c200f5d242b..7fabf1428093 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -91,6 +91,9 @@ int btf_type_snprintf_show(const struct btf *btf, u32 type_id, void *obj, int btf_get_fd_by_id(u32 id); u32 btf_obj_id(const struct btf *btf); bool btf_is_kernel(const struct btf *btf); +bool btf_is_module(const struct btf *btf); +struct module *btf_try_get_module(const struct btf *btf); +u32 btf_nr_types(const struct btf *btf); bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, const struct btf_member *m, u32 expected_offset, u32 expected_size); -- cgit v1.2.3 From 5a9d5ecd69ed65fc2d49cdecfc1c1ab1e4d7af34 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Mon, 11 Jan 2021 15:19:18 +0100 Subject: can: dev: move bittiming related code into seperate file This patch moves the bittiming related code of the CAN device infrastructure into a separate file. Reviewed-by: Vincent Mailhol Link: https://lore.kernel.org/r/20210111141930.693847-4-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- include/linux/can/bittiming.h | 44 +++++++++++++++++++++++++++++++++++++++++++ include/linux/can/dev.h | 16 +--------------- 2 files changed, 45 insertions(+), 15 deletions(-) create mode 100644 include/linux/can/bittiming.h (limited to 'include/linux') diff --git a/include/linux/can/bittiming.h b/include/linux/can/bittiming.h new file mode 100644 index 000000000000..707575c668f4 --- /dev/null +++ b/include/linux/can/bittiming.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (c) 2020 Pengutronix, Marc Kleine-Budde + */ + +#ifndef _CAN_BITTIMING_H +#define _CAN_BITTIMING_H + +#include +#include + +#define CAN_SYNC_SEG 1 + +#ifdef CONFIG_CAN_CALC_BITTIMING +int can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt, + const struct can_bittiming_const *btc); +#else /* !CONFIG_CAN_CALC_BITTIMING */ +static inline int +can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt, + const struct can_bittiming_const *btc) +{ + netdev_err(dev, "bit-timing calculation not available\n"); + return -EINVAL; +} +#endif /* CONFIG_CAN_CALC_BITTIMING */ + +int can_get_bittiming(struct net_device *dev, struct can_bittiming *bt, + const struct can_bittiming_const *btc, + const u32 *bitrate_const, + const unsigned int bitrate_const_cnt); + +/* + * can_bit_time() - Duration of one bit + * + * Please refer to ISO 11898-1:2015, section 11.3.1.1 "Bit time" for + * additional information. + * + * Return: the number of time quanta in one bit. + */ +static inline unsigned int can_bit_time(const struct can_bittiming *bt) +{ + return CAN_SYNC_SEG + bt->prop_seg + bt->phase_seg1 + bt->phase_seg2; +} + +#endif /* !_CAN_BITTIMING_H */ diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 197a79535cc2..054c3bed190b 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -15,6 +15,7 @@ #define _CAN_DEV_H #include +#include #include #include #include @@ -82,21 +83,6 @@ struct can_priv { #endif }; -#define CAN_SYNC_SEG 1 - -/* - * can_bit_time() - Duration of one bit - * - * Please refer to ISO 11898-1:2015, section 11.3.1.1 "Bit time" for - * additional information. - * - * Return: the number of time quanta in one bit. - */ -static inline unsigned int can_bit_time(const struct can_bittiming *bt) -{ - return CAN_SYNC_SEG + bt->prop_seg + bt->phase_seg1 + bt->phase_seg2; -} - /* * can_cc_dlc2len(value) - convert a given data length code (dlc) of a * Classical CAN frame into a valid data length of max. 8 bytes. -- cgit v1.2.3 From bdd2e413192dd5f2153d166cd907b048cce872e8 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Mon, 11 Jan 2021 15:19:19 +0100 Subject: can: dev: move length related code into seperate file This patch moves all CAN frame length related code of the CAN device infrastructure into a separate file. Reviewed-by: Vincent Mailhol Link: https://lore.kernel.org/r/20210111141930.693847-5-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- include/linux/can/dev.h | 41 +-------------------------------------- include/linux/can/length.h | 48 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 49 insertions(+), 40 deletions(-) create mode 100644 include/linux/can/length.h (limited to 'include/linux') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 054c3bed190b..d75fba1d030a 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -83,15 +84,6 @@ struct can_priv { #endif }; -/* - * can_cc_dlc2len(value) - convert a given data length code (dlc) of a - * Classical CAN frame into a valid data length of max. 8 bytes. - * - * To be used in the CAN netdriver receive path to ensure conformance with - * ISO 11898-1 Chapter 8.4.2.3 (DLC field) - */ -#define can_cc_dlc2len(dlc) (min_t(u8, (dlc), CAN_MAX_DLEN)) - /* Check for outgoing skbs that have not been created by the CAN subsystem */ static inline bool can_skb_headroom_valid(struct net_device *dev, struct sk_buff *skb) @@ -156,31 +148,6 @@ static inline bool can_is_canfd_skb(const struct sk_buff *skb) return skb->len == CANFD_MTU; } -/* helper to get the data length code (DLC) for Classical CAN raw DLC access */ -static inline u8 can_get_cc_dlc(const struct can_frame *cf, const u32 ctrlmode) -{ - /* return len8_dlc as dlc value only if all conditions apply */ - if ((ctrlmode & CAN_CTRLMODE_CC_LEN8_DLC) && - (cf->len == CAN_MAX_DLEN) && - (cf->len8_dlc > CAN_MAX_DLEN && cf->len8_dlc <= CAN_MAX_RAW_DLC)) - return cf->len8_dlc; - - /* return the payload length as dlc value */ - return cf->len; -} - -/* helper to set len and len8_dlc value for Classical CAN raw DLC access */ -static inline void can_frame_set_cc_len(struct can_frame *cf, const u8 dlc, - const u32 ctrlmode) -{ - /* the caller already ensured that dlc is a value from 0 .. 15 */ - if (ctrlmode & CAN_CTRLMODE_CC_LEN8_DLC && dlc > CAN_MAX_DLEN) - cf->len8_dlc = dlc; - - /* limit the payload length 'len' to CAN_MAX_DLEN */ - cf->len = can_cc_dlc2len(dlc); -} - /* helper to define static CAN controller features at device creation time */ static inline void can_set_static_ctrlmode(struct net_device *dev, u32 static_mode) @@ -196,12 +163,6 @@ static inline void can_set_static_ctrlmode(struct net_device *dev, dev->mtu = CANFD_MTU; } -/* get data length from raw data length code (DLC) */ -u8 can_fd_dlc2len(u8 dlc); - -/* map the sanitized data length to an appropriate data length code */ -u8 can_fd_len2dlc(u8 len); - struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max, unsigned int txqs, unsigned int rxqs); #define alloc_candev(sizeof_priv, echo_skb_max) \ diff --git a/include/linux/can/length.h b/include/linux/can/length.h new file mode 100644 index 000000000000..156b9d17969a --- /dev/null +++ b/include/linux/can/length.h @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2020 Oliver Hartkopp + */ + +#ifndef _CAN_LENGTH_H +#define _CAN_LENGTH_H + +/* + * can_cc_dlc2len(value) - convert a given data length code (dlc) of a + * Classical CAN frame into a valid data length of max. 8 bytes. + * + * To be used in the CAN netdriver receive path to ensure conformance with + * ISO 11898-1 Chapter 8.4.2.3 (DLC field) + */ +#define can_cc_dlc2len(dlc) (min_t(u8, (dlc), CAN_MAX_DLEN)) + +/* helper to get the data length code (DLC) for Classical CAN raw DLC access */ +static inline u8 can_get_cc_dlc(const struct can_frame *cf, const u32 ctrlmode) +{ + /* return len8_dlc as dlc value only if all conditions apply */ + if ((ctrlmode & CAN_CTRLMODE_CC_LEN8_DLC) && + (cf->len == CAN_MAX_DLEN) && + (cf->len8_dlc > CAN_MAX_DLEN && cf->len8_dlc <= CAN_MAX_RAW_DLC)) + return cf->len8_dlc; + + /* return the payload length as dlc value */ + return cf->len; +} + +/* helper to set len and len8_dlc value for Classical CAN raw DLC access */ +static inline void can_frame_set_cc_len(struct can_frame *cf, const u8 dlc, + const u32 ctrlmode) +{ + /* the caller already ensured that dlc is a value from 0 .. 15 */ + if (ctrlmode & CAN_CTRLMODE_CC_LEN8_DLC && dlc > CAN_MAX_DLEN) + cf->len8_dlc = dlc; + + /* limit the payload length 'len' to CAN_MAX_DLEN */ + cf->len = can_cc_dlc2len(dlc); +} + +/* get data length from raw data length code (DLC) */ +u8 can_fd_dlc2len(u8 dlc); + +/* map the sanitized data length to an appropriate data length code */ +u8 can_fd_len2dlc(u8 len); + +#endif /* !_CAN_LENGTH_H */ -- cgit v1.2.3 From 18f2dbfd2232212f53af9d249682f13a8335d54f Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Mon, 11 Jan 2021 15:19:20 +0100 Subject: can: dev: move skb related into seperate file This patch moves the skb related code of the CAN device infrastructure into a separate file. Reviewed-by: Vincent Mailhol Link: https://lore.kernel.org/r/20210111141930.693847-6-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- include/linux/can/dev.h | 76 ------------------------------------------------ include/linux/can/skb.h | 77 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 77 insertions(+), 76 deletions(-) (limited to 'include/linux') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index d75fba1d030a..4a26e128af7f 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -84,69 +84,6 @@ struct can_priv { #endif }; -/* Check for outgoing skbs that have not been created by the CAN subsystem */ -static inline bool can_skb_headroom_valid(struct net_device *dev, - struct sk_buff *skb) -{ - /* af_packet creates a headroom of HH_DATA_MOD bytes which is fine */ - if (WARN_ON_ONCE(skb_headroom(skb) < sizeof(struct can_skb_priv))) - return false; - - /* af_packet does not apply CAN skb specific settings */ - if (skb->ip_summed == CHECKSUM_NONE) { - /* init headroom */ - can_skb_prv(skb)->ifindex = dev->ifindex; - can_skb_prv(skb)->skbcnt = 0; - - skb->ip_summed = CHECKSUM_UNNECESSARY; - - /* perform proper loopback on capable devices */ - if (dev->flags & IFF_ECHO) - skb->pkt_type = PACKET_LOOPBACK; - else - skb->pkt_type = PACKET_HOST; - - skb_reset_mac_header(skb); - skb_reset_network_header(skb); - skb_reset_transport_header(skb); - } - - return true; -} - -/* Drop a given socketbuffer if it does not contain a valid CAN frame. */ -static inline bool can_dropped_invalid_skb(struct net_device *dev, - struct sk_buff *skb) -{ - const struct canfd_frame *cfd = (struct canfd_frame *)skb->data; - - if (skb->protocol == htons(ETH_P_CAN)) { - if (unlikely(skb->len != CAN_MTU || - cfd->len > CAN_MAX_DLEN)) - goto inval_skb; - } else if (skb->protocol == htons(ETH_P_CANFD)) { - if (unlikely(skb->len != CANFD_MTU || - cfd->len > CANFD_MAX_DLEN)) - goto inval_skb; - } else - goto inval_skb; - - if (!can_skb_headroom_valid(dev, skb)) - goto inval_skb; - - return false; - -inval_skb: - kfree_skb(skb); - dev->stats.tx_dropped++; - return true; -} - -static inline bool can_is_canfd_skb(const struct sk_buff *skb) -{ - /* the CAN specific type of skb is identified by its data length */ - return skb->len == CANFD_MTU; -} /* helper to define static CAN controller features at device creation time */ static inline void can_set_static_ctrlmode(struct net_device *dev, @@ -187,23 +124,10 @@ void can_bus_off(struct net_device *dev); void can_change_state(struct net_device *dev, struct can_frame *cf, enum can_state tx_state, enum can_state rx_state); -int can_put_echo_skb(struct sk_buff *skb, struct net_device *dev, - unsigned int idx); -struct sk_buff *__can_get_echo_skb(struct net_device *dev, unsigned int idx, - u8 *len_ptr); -unsigned int can_get_echo_skb(struct net_device *dev, unsigned int idx); -void can_free_echo_skb(struct net_device *dev, unsigned int idx); - #ifdef CONFIG_OF void of_can_transceiver(struct net_device *dev); #else static inline void of_can_transceiver(struct net_device *dev) { } #endif -struct sk_buff *alloc_can_skb(struct net_device *dev, struct can_frame **cf); -struct sk_buff *alloc_canfd_skb(struct net_device *dev, - struct canfd_frame **cfd); -struct sk_buff *alloc_can_err_skb(struct net_device *dev, - struct can_frame **cf); - #endif /* !_CAN_DEV_H */ diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h index fc61cf4eff1c..c90ebbd3008c 100644 --- a/include/linux/can/skb.h +++ b/include/linux/can/skb.h @@ -16,6 +16,19 @@ #include #include +void can_flush_echo_skb(struct net_device *dev); +int can_put_echo_skb(struct sk_buff *skb, struct net_device *dev, + unsigned int idx); +struct sk_buff *__can_get_echo_skb(struct net_device *dev, unsigned int idx, + u8 *len_ptr); +unsigned int can_get_echo_skb(struct net_device *dev, unsigned int idx); +void can_free_echo_skb(struct net_device *dev, unsigned int idx); +struct sk_buff *alloc_can_skb(struct net_device *dev, struct can_frame **cf); +struct sk_buff *alloc_canfd_skb(struct net_device *dev, + struct canfd_frame **cfd); +struct sk_buff *alloc_can_err_skb(struct net_device *dev, + struct can_frame **cf); + /* * The struct can_skb_priv is used to transport additional information along * with the stored struct can(fd)_frame that can not be contained in existing @@ -74,4 +87,68 @@ static inline struct sk_buff *can_create_echo_skb(struct sk_buff *skb) return nskb; } +/* Check for outgoing skbs that have not been created by the CAN subsystem */ +static inline bool can_skb_headroom_valid(struct net_device *dev, + struct sk_buff *skb) +{ + /* af_packet creates a headroom of HH_DATA_MOD bytes which is fine */ + if (WARN_ON_ONCE(skb_headroom(skb) < sizeof(struct can_skb_priv))) + return false; + + /* af_packet does not apply CAN skb specific settings */ + if (skb->ip_summed == CHECKSUM_NONE) { + /* init headroom */ + can_skb_prv(skb)->ifindex = dev->ifindex; + can_skb_prv(skb)->skbcnt = 0; + + skb->ip_summed = CHECKSUM_UNNECESSARY; + + /* perform proper loopback on capable devices */ + if (dev->flags & IFF_ECHO) + skb->pkt_type = PACKET_LOOPBACK; + else + skb->pkt_type = PACKET_HOST; + + skb_reset_mac_header(skb); + skb_reset_network_header(skb); + skb_reset_transport_header(skb); + } + + return true; +} + +/* Drop a given socketbuffer if it does not contain a valid CAN frame. */ +static inline bool can_dropped_invalid_skb(struct net_device *dev, + struct sk_buff *skb) +{ + const struct canfd_frame *cfd = (struct canfd_frame *)skb->data; + + if (skb->protocol == htons(ETH_P_CAN)) { + if (unlikely(skb->len != CAN_MTU || + cfd->len > CAN_MAX_DLEN)) + goto inval_skb; + } else if (skb->protocol == htons(ETH_P_CANFD)) { + if (unlikely(skb->len != CANFD_MTU || + cfd->len > CANFD_MAX_DLEN)) + goto inval_skb; + } else + goto inval_skb; + + if (!can_skb_headroom_valid(dev, skb)) + goto inval_skb; + + return false; + +inval_skb: + kfree_skb(skb); + dev->stats.tx_dropped++; + return true; +} + +static inline bool can_is_canfd_skb(const struct sk_buff *skb) +{ + /* the CAN specific type of skb is identified by its data length */ + return skb->len == CANFD_MTU; +} + #endif /* !_CAN_SKB_H */ -- cgit v1.2.3 From 0a042c6ec991e4d33062ee52e9e23f615bc659f9 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Mon, 11 Jan 2021 15:19:21 +0100 Subject: can: dev: move netlink related code into seperate file This patch moves the netlink related code of the CAN device infrastructure into a separate file. Reviewed-by: Vincent Mailhol Link: https://lore.kernel.org/r/20210111141930.693847-7-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- include/linux/can/dev.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 4a26e128af7f..7faf6a37d5b2 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -100,6 +100,8 @@ static inline void can_set_static_ctrlmode(struct net_device *dev, dev->mtu = CANFD_MTU; } +void can_setup(struct net_device *dev); + struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max, unsigned int txqs, unsigned int rxqs); #define alloc_candev(sizeof_priv, echo_skb_max) \ @@ -130,4 +132,8 @@ void of_can_transceiver(struct net_device *dev); static inline void of_can_transceiver(struct net_device *dev) { } #endif +extern struct rtnl_link_ops can_link_ops; +int can_netlink_register(void); +void can_netlink_unregister(void); + #endif /* !_CAN_DEV_H */ -- cgit v1.2.3 From 35192007d28d528aae74ddf5b26eaebf8e9a720c Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Fri, 18 Dec 2020 15:02:39 +0300 Subject: usb: phy: tegra: Support waking up from a low power mode Support programming of waking up from a low power mode by implementing the generic set_wakeup() callback of the USB PHY API. Tested-by: Matt Merhar Tested-by: Nicolas Chauvet Tested-by: Peter Geis Tested-by: Ion Agorria Acked-by: Thierry Reding Acked-by: Peter Chen Signed-off-by: Dmitry Osipenko Link: https://lore.kernel.org/r/20201218120246.7759-3-digetx@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/tegra_usb_phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index c29d1b4c9381..fd1c9f6a4e37 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -79,6 +79,8 @@ struct tegra_usb_phy { bool is_ulpi_phy; struct gpio_desc *reset_gpio; struct reset_control *pad_rst; + bool wakeup_enabled; + bool pad_wakeup; bool powered_on; }; -- cgit v1.2.3 From fc53d5279094e38e6363506339772a7021da2df8 Mon Sep 17 00:00:00 2001 From: Peter Geis Date: Fri, 18 Dec 2020 15:02:42 +0300 Subject: usb: chipidea: tegra: Support host mode Add USB host mode to the Tegra HDRC driver. This allows us to benefit from support provided by the generic ChipIdea driver instead of duplicating the effort in a separate ehci-tegra driver. Tested-by: Matt Merhar Tested-by: Nicolas Chauvet Tested-by: Ion Agorria Acked-by: Thierry Reding Acked-by: Peter Chen Signed-off-by: Peter Geis Signed-off-by: Dmitry Osipenko Link: https://lore.kernel.org/r/20201218120246.7759-6-digetx@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/chipidea.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/chipidea.h b/include/linux/usb/chipidea.h index 025b41687ce9..edf3342507f1 100644 --- a/include/linux/usb/chipidea.h +++ b/include/linux/usb/chipidea.h @@ -88,6 +88,12 @@ struct ci_hdrc_platform_data { struct pinctrl_state *pins_default; struct pinctrl_state *pins_host; struct pinctrl_state *pins_device; + + /* platform-specific hooks */ + int (*hub_control)(struct ci_hdrc *ci, u16 typeReq, u16 wValue, + u16 wIndex, char *buf, u16 wLength, + bool *done, unsigned long *flags); + void (*enter_lpm)(struct ci_hdrc *ci, bool enable); }; /* Default offset of capability registers */ -- cgit v1.2.3 From c512150b266b5d173c5ba841e9c09e4830ea4eca Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sat, 5 Dec 2020 01:40:56 +0100 Subject: regulator: ab8500: Remove unused platform data The struct ab8500_regulator_platform_data was a leftover since the days before we probed all regulators from the device tree. The ab8500-ext regulator was the only used, defining platform data and register intialization that was never used for anything, a copy of a boardfile no longer in use. Delete the ab8500_regulator_platform_data and make the ab8500-ext regulator reference the regulator init data in the local file directly. We are 100% device tree these days. Cc: Lee Jones Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20201205004057.1712753-1-linus.walleij@linaro.org Signed-off-by: Mark Brown --- include/linux/mfd/abx500/ab8500.h | 3 --- include/linux/regulator/ab8500.h | 10 ---------- 2 files changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/abx500/ab8500.h b/include/linux/mfd/abx500/ab8500.h index 524a7e4702c2..302a330c5c84 100644 --- a/include/linux/mfd/abx500/ab8500.h +++ b/include/linux/mfd/abx500/ab8500.h @@ -368,7 +368,6 @@ struct ab8500 { int it_latchhier_num; }; -struct ab8500_regulator_platform_data; struct ab8500_codec_platform_data; struct ab8500_sysctrl_platform_data; @@ -376,11 +375,9 @@ struct ab8500_sysctrl_platform_data; * struct ab8500_platform_data - AB8500 platform data * @irq_base: start of AB8500 IRQs, AB8500_NR_IRQS will be used * @init: board-specific initialization after detection of ab8500 - * @regulator: machine-specific constraints for regulators */ struct ab8500_platform_data { void (*init) (struct ab8500 *); - struct ab8500_regulator_platform_data *regulator; struct ab8500_codec_platform_data *codec; struct ab8500_sysctrl_platform_data *sysctrl; }; diff --git a/include/linux/regulator/ab8500.h b/include/linux/regulator/ab8500.h index 3ab1ddf151a2..ecf7b4713df9 100644 --- a/include/linux/regulator/ab8500.h +++ b/include/linux/regulator/ab8500.h @@ -153,14 +153,4 @@ enum ab8500_ext_regulator_id { AB8500_NUM_EXT_REGULATORS, }; -/* AB8500 regulator platform data */ -struct ab8500_regulator_platform_data { - int num_reg_init; - struct ab8500_regulator_reg_init *reg_init; - int num_regulator; - struct regulator_init_data *regulator; - int num_ext_regulator; - struct regulator_init_data *ext_regulator; -}; - #endif -- cgit v1.2.3 From 3acb64c07e95a75dc0af0bc958f2d09a44a9fd0d Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sat, 5 Dec 2020 01:40:57 +0100 Subject: regulator: ab8500: Decomission platform data header The platform data header was only used to pass platform data from board files. We now populate the regulators exclusively from device tree, so the header contents can be moved into the regulator drivers. Cc: Lee Jones Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20201205004057.1712753-2-linus.walleij@linaro.org Signed-off-by: Mark Brown --- include/linux/regulator/ab8500.h | 156 --------------------------------------- 1 file changed, 156 deletions(-) delete mode 100644 include/linux/regulator/ab8500.h (limited to 'include/linux') diff --git a/include/linux/regulator/ab8500.h b/include/linux/regulator/ab8500.h deleted file mode 100644 index ecf7b4713df9..000000000000 --- a/include/linux/regulator/ab8500.h +++ /dev/null @@ -1,156 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) ST-Ericsson SA 2010 - * - * Authors: Sundar Iyer for ST-Ericsson - * Bengt Jonsson for ST-Ericsson - * Daniel Willerud for ST-Ericsson - */ - -#ifndef __LINUX_MFD_AB8500_REGULATOR_H -#define __LINUX_MFD_AB8500_REGULATOR_H - -#include - -/* AB8500 regulators */ -enum ab8500_regulator_id { - AB8500_LDO_AUX1, - AB8500_LDO_AUX2, - AB8500_LDO_AUX3, - AB8500_LDO_INTCORE, - AB8500_LDO_TVOUT, - AB8500_LDO_AUDIO, - AB8500_LDO_ANAMIC1, - AB8500_LDO_ANAMIC2, - AB8500_LDO_DMIC, - AB8500_LDO_ANA, - AB8500_NUM_REGULATORS, -}; - -/* AB8505 regulators */ -enum ab8505_regulator_id { - AB8505_LDO_AUX1, - AB8505_LDO_AUX2, - AB8505_LDO_AUX3, - AB8505_LDO_AUX4, - AB8505_LDO_AUX5, - AB8505_LDO_AUX6, - AB8505_LDO_INTCORE, - AB8505_LDO_ADC, - AB8505_LDO_AUDIO, - AB8505_LDO_ANAMIC1, - AB8505_LDO_ANAMIC2, - AB8505_LDO_AUX8, - AB8505_LDO_ANA, - AB8505_NUM_REGULATORS, -}; - -/* AB8500 and AB8505 register initialization */ -struct ab8500_regulator_reg_init { - int id; - u8 mask; - u8 value; -}; - -#define INIT_REGULATOR_REGISTER(_id, _mask, _value) \ - { \ - .id = _id, \ - .mask = _mask, \ - .value = _value, \ - } - -/* AB8500 registers */ -enum ab8500_regulator_reg { - AB8500_REGUREQUESTCTRL2, - AB8500_REGUREQUESTCTRL3, - AB8500_REGUREQUESTCTRL4, - AB8500_REGUSYSCLKREQ1HPVALID1, - AB8500_REGUSYSCLKREQ1HPVALID2, - AB8500_REGUHWHPREQ1VALID1, - AB8500_REGUHWHPREQ1VALID2, - AB8500_REGUHWHPREQ2VALID1, - AB8500_REGUHWHPREQ2VALID2, - AB8500_REGUSWHPREQVALID1, - AB8500_REGUSWHPREQVALID2, - AB8500_REGUSYSCLKREQVALID1, - AB8500_REGUSYSCLKREQVALID2, - AB8500_REGUMISC1, - AB8500_VAUDIOSUPPLY, - AB8500_REGUCTRL1VAMIC, - AB8500_VPLLVANAREGU, - AB8500_VREFDDR, - AB8500_EXTSUPPLYREGU, - AB8500_VAUX12REGU, - AB8500_VRF1VAUX3REGU, - AB8500_VAUX1SEL, - AB8500_VAUX2SEL, - AB8500_VRF1VAUX3SEL, - AB8500_REGUCTRL2SPARE, - AB8500_REGUCTRLDISCH, - AB8500_REGUCTRLDISCH2, - AB8500_NUM_REGULATOR_REGISTERS, -}; - -/* AB8505 registers */ -enum ab8505_regulator_reg { - AB8505_REGUREQUESTCTRL1, - AB8505_REGUREQUESTCTRL2, - AB8505_REGUREQUESTCTRL3, - AB8505_REGUREQUESTCTRL4, - AB8505_REGUSYSCLKREQ1HPVALID1, - AB8505_REGUSYSCLKREQ1HPVALID2, - AB8505_REGUHWHPREQ1VALID1, - AB8505_REGUHWHPREQ1VALID2, - AB8505_REGUHWHPREQ2VALID1, - AB8505_REGUHWHPREQ2VALID2, - AB8505_REGUSWHPREQVALID1, - AB8505_REGUSWHPREQVALID2, - AB8505_REGUSYSCLKREQVALID1, - AB8505_REGUSYSCLKREQVALID2, - AB8505_REGUVAUX4REQVALID, - AB8505_REGUMISC1, - AB8505_VAUDIOSUPPLY, - AB8505_REGUCTRL1VAMIC, - AB8505_VSMPSAREGU, - AB8505_VSMPSBREGU, - AB8505_VSAFEREGU, /* NOTE! PRCMU register */ - AB8505_VPLLVANAREGU, - AB8505_EXTSUPPLYREGU, - AB8505_VAUX12REGU, - AB8505_VRF1VAUX3REGU, - AB8505_VSMPSASEL1, - AB8505_VSMPSASEL2, - AB8505_VSMPSASEL3, - AB8505_VSMPSBSEL1, - AB8505_VSMPSBSEL2, - AB8505_VSMPSBSEL3, - AB8505_VSAFESEL1, /* NOTE! PRCMU register */ - AB8505_VSAFESEL2, /* NOTE! PRCMU register */ - AB8505_VSAFESEL3, /* NOTE! PRCMU register */ - AB8505_VAUX1SEL, - AB8505_VAUX2SEL, - AB8505_VRF1VAUX3SEL, - AB8505_VAUX4REQCTRL, - AB8505_VAUX4REGU, - AB8505_VAUX4SEL, - AB8505_REGUCTRLDISCH, - AB8505_REGUCTRLDISCH2, - AB8505_REGUCTRLDISCH3, - AB8505_CTRLVAUX5, - AB8505_CTRLVAUX6, - AB8505_NUM_REGULATOR_REGISTERS, -}; - -/* AB8500 external regulators */ -struct ab8500_ext_regulator_cfg { - bool hwreq; /* requires hw mode or high power mode */ -}; - -enum ab8500_ext_regulator_id { - AB8500_EXT_SUPPLY1, - AB8500_EXT_SUPPLY2, - AB8500_EXT_SUPPLY3, - AB8500_NUM_EXT_REGULATORS, -}; - -#endif -- cgit v1.2.3 From 1e9d63331f8fa556f31e1406ab12f2a1e5cdb495 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 12 Jan 2021 11:02:44 -0800 Subject: fs: correctly document the inode dirty flags The documentation for I_DIRTY_SYNC and I_DIRTY_DATASYNC is a bit misleading, and I_DIRTY_TIME isn't documented at all. Fix this. Link: https://lore.kernel.org/r/20210112190253.64307-3-ebiggers@kernel.org Reviewed-by: Christoph Hellwig Reviewed-by: Jan Kara Signed-off-by: Eric Biggers Signed-off-by: Jan Kara --- include/linux/fs.h | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index fd47deea7c17..45a0303b2aeb 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2084,8 +2084,8 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, /* * Inode state bits. Protected by inode->i_lock * - * Three bits determine the dirty state of the inode, I_DIRTY_SYNC, - * I_DIRTY_DATASYNC and I_DIRTY_PAGES. + * Four bits determine the dirty state of the inode: I_DIRTY_SYNC, + * I_DIRTY_DATASYNC, I_DIRTY_PAGES, and I_DIRTY_TIME. * * Four bits define the lifetime of an inode. Initially, inodes are I_NEW, * until that flag is cleared. I_WILL_FREE, I_FREEING and I_CLEAR are set at @@ -2094,12 +2094,20 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, * Two bits are used for locking and completion notification, I_NEW and I_SYNC. * * I_DIRTY_SYNC Inode is dirty, but doesn't have to be written on - * fdatasync(). i_atime is the usual cause. - * I_DIRTY_DATASYNC Data-related inode changes pending. We keep track of + * fdatasync() (unless I_DIRTY_DATASYNC is also set). + * Timestamp updates are the usual cause. + * I_DIRTY_DATASYNC Data-related inode changes pending. We keep track of * these changes separately from I_DIRTY_SYNC so that we * don't have to write inode on fdatasync() when only - * mtime has changed in it. + * e.g. the timestamps have changed. * I_DIRTY_PAGES Inode has dirty pages. Inode itself may be clean. + * I_DIRTY_TIME The inode itself only has dirty timestamps, and the + * lazytime mount option is enabled. We keep track of this + * separately from I_DIRTY_SYNC in order to implement + * lazytime. This gets cleared if I_DIRTY_INODE + * (I_DIRTY_SYNC and/or I_DIRTY_DATASYNC) gets set. I.e. + * either I_DIRTY_TIME *or* I_DIRTY_INODE can be set in + * i_state, but not both. I_DIRTY_PAGES may still be set. * I_NEW Serves as both a mutex and completion notification. * New inodes set I_NEW. If two processes both create * the same inode, one of them will release its inode and -- cgit v1.2.3 From ed296c6c05b0ac52d7c6bf13a90f02b8b8222169 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 12 Jan 2021 11:02:53 -0800 Subject: ext4: simplify i_state checks in __ext4_update_other_inode_time() Since I_DIRTY_TIME and I_DIRTY_INODE are mutually exclusive in i_state, there's no need to check for I_DIRTY_TIME && !I_DIRTY_INODE. Just check for I_DIRTY_TIME. Also introduce a helper function in include/linux/fs.h to do this check. Link: https://lore.kernel.org/r/20210112190253.64307-12-ebiggers@kernel.org Reviewed-by: Christoph Hellwig Reviewed-by: Jan Kara Signed-off-by: Eric Biggers Signed-off-by: Jan Kara --- include/linux/fs.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 45a0303b2aeb..de0c789104c2 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2194,6 +2194,21 @@ static inline void mark_inode_dirty_sync(struct inode *inode) __mark_inode_dirty(inode, I_DIRTY_SYNC); } +/* + * Returns true if the given inode itself only has dirty timestamps (its pages + * may still be dirty) and isn't currently being allocated or freed. + * Filesystems should call this if when writing an inode when lazytime is + * enabled, they want to opportunistically write the timestamps of other inodes + * located very nearby on-disk, e.g. in the same inode block. This returns true + * if the given inode is in need of such an opportunistic update. Requires + * i_lock, or at least later re-checking under i_lock. + */ +static inline bool inode_is_dirtytime_only(struct inode *inode) +{ + return (inode->i_state & (I_DIRTY_TIME | I_NEW | + I_FREEING | I_WILL_FREE)) == I_DIRTY_TIME; +} + extern void inc_nlink(struct inode *inode); extern void drop_nlink(struct inode *inode); extern void clear_nlink(struct inode *inode); -- cgit v1.2.3 From 660343d063f7b7151a8c679d91ebe13cf40ad866 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Wed, 13 Jan 2021 13:49:21 +0200 Subject: dmaengine: Extend the dmaengine_alignment for 128 and 256 bytes Some DMA device can benefit with higher order of alignment than the maximum of 64 bytes currently defined. Define 128 and 256 bytes alignment for these devices. Signed-off-by: Peter Ujfalusi Signed-off-by: Peter Ujfalusi Tested-by: Kishon Vijay Abraham I Link: https://lore.kernel.org/r/20210113114923.9231-2-peter.ujfalusi@gmail.com Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 68130f5f599e..004736b6a9c8 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -745,6 +745,8 @@ enum dmaengine_alignment { DMAENGINE_ALIGN_16_BYTES = 4, DMAENGINE_ALIGN_32_BYTES = 5, DMAENGINE_ALIGN_64_BYTES = 6, + DMAENGINE_ALIGN_128_BYTES = 7, + DMAENGINE_ALIGN_256_BYTES = 8, }; /** -- cgit v1.2.3 From a3b4388ea19b055ec482114e227c58d0184edfa5 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sun, 10 Jan 2021 15:49:05 +0100 Subject: power: supply: z2_battery: Convert to GPIO descriptors This converts the Palm Z2 battery driver to use GPIO descriptors. Cc: Haojian Zhuang Cc: Robert Jarzmik Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Linus Walleij Reviewed-by: Daniel Mack Signed-off-by: Sebastian Reichel --- include/linux/z2_battery.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/z2_battery.h b/include/linux/z2_battery.h index eaba53ff387c..9e8be7a7cd25 100644 --- a/include/linux/z2_battery.h +++ b/include/linux/z2_battery.h @@ -6,7 +6,6 @@ struct z2_battery_info { int batt_I2C_bus; int batt_I2C_addr; int batt_I2C_reg; - int charge_gpio; int min_voltage; int max_voltage; int batt_div; -- cgit v1.2.3 From cb6d6918c56ffd98e88164d5471f692d33dabf2b Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 11 Jan 2021 00:45:08 +0100 Subject: power: supply: wm97xx_battery: Convert to GPIO descriptor This converts the WM97xx driver to use a GPIO descriptor instead of passing a GPIO number thru platform data. Like everything else in the driver, use a simple local variable for the descriptor, it can only ever appear in one instance anyway so it should not hurt. After converting the driver I noticed that none of the boardfiles actually define a meaningful GPIO line for this, but hey, it is converted. Cc: Haojian Zhuang Cc: Robert Jarzmik Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Linus Walleij Reviewed-by: Daniel Mack Signed-off-by: Sebastian Reichel --- include/linux/wm97xx.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/wm97xx.h b/include/linux/wm97xx.h index 58e082dadc68..462854f4f286 100644 --- a/include/linux/wm97xx.h +++ b/include/linux/wm97xx.h @@ -294,7 +294,6 @@ struct wm97xx { struct wm97xx_batt_pdata { int batt_aux; int temp_aux; - int charge_gpio; int min_voltage; int max_voltage; int batt_div; -- cgit v1.2.3 From 838b00a2260ab6ec104a2a5696e619c19e8cd9be Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Mon, 11 Jan 2021 23:05:24 -0800 Subject: net/mlx5: Add HW definition of reg_c_preserve Add capability bit to test whether reg_c value is preserved on recirculation. Signed-off-by: Paul Blakey Signed-off-by: Maor Dickman Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed Signed-off-by: Jakub Kicinski --- include/linux/mlx5/mlx5_ifc.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 442c0160caab..823411e288c0 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1278,7 +1278,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_a0[0x3]; u8 ece_support[0x1]; - u8 reserved_at_a4[0x7]; + u8 reserved_at_a4[0x5]; + u8 reg_c_preserve[0x1]; + u8 reserved_at_aa[0x1]; u8 log_max_srq[0x5]; u8 reserved_at_b0[0x1]; u8 uplink_follow[0x1]; -- cgit v1.2.3 From 9d93a9e8aab3f82b6742dd034a6a81d4025cd82e Mon Sep 17 00:00:00 2001 From: Gabriel Somlo Date: Tue, 12 Jan 2021 12:31:40 -0500 Subject: drivers/soc/litex: move generic accessors to litex.h Move generic LiteX CSR (MMIO) register accessors to litex.h and declare them as "static inline", in preparation for supporting 32-bit CSR subregisters and 64-bit CPUs. NOTE: this is a non-functional change. Signed-off-by: Gabriel Somlo Signed-off-by: Stafford Horne --- include/linux/litex.h | 74 +++++++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 69 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/litex.h b/include/linux/litex.h index 40f5be503593..67c1a18a7425 100644 --- a/include/linux/litex.h +++ b/include/linux/litex.h @@ -3,9 +3,6 @@ * Common LiteX header providing * helper functions for accessing CSRs. * - * Implementation of the functions is provided by - * the LiteX SoC Controller driver. - * * Copyright (C) 2019-2020 Antmicro */ @@ -33,9 +30,76 @@ #define READ_LITEX_SUBREGISTER(base_offset, subreg_id) \ le32_to_cpu((__le32 __force)readl(base_offset + (LITEX_REG_SIZE * subreg_id))) -void litex_set_reg(void __iomem *reg, unsigned long reg_sz, unsigned long val); +/* + * LiteX SoC Generator, depending on the configuration, can split a single + * logical CSR (Control&Status Register) into a series of consecutive physical + * registers. + * + * For example, in the configuration with 8-bit CSR Bus, 32-bit aligned (the + * default one for 32-bit CPUs) a 32-bit logical CSR will be generated as four + * 32-bit physical registers, each one containing one byte of meaningful data. + * + * For details see: https://github.com/enjoy-digital/litex/wiki/CSR-Bus + * + * The purpose of `litex_set_reg`/`litex_get_reg` is to implement the logic + * of writing to/reading from the LiteX CSR in a single place that can be + * then reused by all LiteX drivers. + */ + +/** + * litex_set_reg() - Writes the value to the LiteX CSR (Control&Status Register) + * @reg: Address of the CSR + * @reg_size: The width of the CSR expressed in the number of bytes + * @val: Value to be written to the CSR + * + * In the currently supported LiteX configuration (8-bit CSR Bus, 32-bit aligned), + * a 32-bit LiteX CSR is generated as 4 consecutive 32-bit physical registers, + * each one containing one byte of meaningful data. + * + * This function splits a single possibly multi-byte write into a series of + * single-byte writes with a proper offset. + */ +static inline void litex_set_reg(void __iomem *reg, ulong reg_size, ulong val) +{ + ulong shifted_data, shift, i; + + for (i = 0; i < reg_size; ++i) { + shift = ((reg_size - i - 1) * LITEX_SUBREG_SIZE_BIT); + shifted_data = val >> shift; + + WRITE_LITEX_SUBREGISTER(shifted_data, reg, i); + } +} + +/** + * litex_get_reg() - Reads the value of the LiteX CSR (Control&Status Register) + * @reg: Address of the CSR + * @reg_size: The width of the CSR expressed in the number of bytes + * + * Return: Value read from the CSR + * + * In the currently supported LiteX configuration (8-bit CSR Bus, 32-bit aligned), + * a 32-bit LiteX CSR is generated as 4 consecutive 32-bit physical registers, + * each one containing one byte of meaningful data. + * + * This function generates a series of single-byte reads with a proper offset + * and joins their results into a single multi-byte value. + */ +static inline ulong litex_get_reg(void __iomem *reg, ulong reg_size) +{ + ulong shifted_data, shift, i; + ulong result = 0; + + for (i = 0; i < reg_size; ++i) { + shifted_data = READ_LITEX_SUBREGISTER(reg, i); + + shift = ((reg_size - i - 1) * LITEX_SUBREG_SIZE_BIT); + result |= (shifted_data << shift); + } + + return result; +} -unsigned long litex_get_reg(void __iomem *reg, unsigned long reg_sz); static inline void litex_write8(void __iomem *reg, u8 val) { -- cgit v1.2.3 From b5d3061ea2e691ab1fa6465fce3c59d9d10357de Mon Sep 17 00:00:00 2001 From: Gabriel Somlo Date: Tue, 12 Jan 2021 12:31:41 -0500 Subject: drivers/soc/litex: separate MMIO from subregister offset calculation Separate MMIO (read/write) access into _[read|write]_litex_subregister() static inline functions, leaving existing "READ|WRITE" macros to handle calculation of the subregister offset only. NOTE: this is a non-functional change. Signed-off-by: Gabriel Somlo Signed-off-by: Stafford Horne --- include/linux/litex.h | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/litex.h b/include/linux/litex.h index 67c1a18a7425..918bab45243c 100644 --- a/include/linux/litex.h +++ b/include/linux/litex.h @@ -24,11 +24,23 @@ #define LITEX_SUBREG_SIZE 0x1 #define LITEX_SUBREG_SIZE_BIT (LITEX_SUBREG_SIZE * 8) +static inline void _write_litex_subregister(u32 val, void __iomem *addr) +{ + writel((u32 __force)cpu_to_le32(val), addr); +} + +static inline u32 _read_litex_subregister(void __iomem *addr) +{ + return le32_to_cpu((__le32 __force)readl(addr)); +} + #define WRITE_LITEX_SUBREGISTER(val, base_offset, subreg_id) \ - writel((u32 __force)cpu_to_le32(val), base_offset + (LITEX_REG_SIZE * subreg_id)) + _write_litex_subregister(val, (base_offset) + \ + LITEX_REG_SIZE * (subreg_id)) #define READ_LITEX_SUBREGISTER(base_offset, subreg_id) \ - le32_to_cpu((__le32 __force)readl(base_offset + (LITEX_REG_SIZE * subreg_id))) + _read_litex_subregister((base_offset) + \ + LITEX_REG_SIZE * (subreg_id)) /* * LiteX SoC Generator, depending on the configuration, can split a single -- cgit v1.2.3 From ffa4ebc48971abffed722b75887ac1d8c9256b41 Mon Sep 17 00:00:00 2001 From: Gabriel Somlo Date: Tue, 12 Jan 2021 12:31:42 -0500 Subject: drivers/soc/litex: s/LITEX_REG_SIZE/LITEX_SUBREG_ALIGN/g The constant LITEX_REG_SIZE is renamed to the more descriptive LITEX_SUBREG_ALIGN (LiteX CSR subregisters are located at 32-bit aligned MMIO addresses). NOTE: this is a non-functional change. Signed-off-by: Gabriel Somlo Signed-off-by: Stafford Horne --- include/linux/litex.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/litex.h b/include/linux/litex.h index 918bab45243c..c63a7e1a337c 100644 --- a/include/linux/litex.h +++ b/include/linux/litex.h @@ -20,10 +20,12 @@ * Supporting other configurations will require extending the logic in this * header and in the LiteX SoC controller driver. */ -#define LITEX_REG_SIZE 0x4 #define LITEX_SUBREG_SIZE 0x1 #define LITEX_SUBREG_SIZE_BIT (LITEX_SUBREG_SIZE * 8) +/* LiteX subregisters of any width are always aligned on a 4-byte boundary */ +#define LITEX_SUBREG_ALIGN 0x4 + static inline void _write_litex_subregister(u32 val, void __iomem *addr) { writel((u32 __force)cpu_to_le32(val), addr); @@ -36,11 +38,11 @@ static inline u32 _read_litex_subregister(void __iomem *addr) #define WRITE_LITEX_SUBREGISTER(val, base_offset, subreg_id) \ _write_litex_subregister(val, (base_offset) + \ - LITEX_REG_SIZE * (subreg_id)) + LITEX_SUBREG_ALIGN * (subreg_id)) #define READ_LITEX_SUBREGISTER(base_offset, subreg_id) \ _read_litex_subregister((base_offset) + \ - LITEX_REG_SIZE * (subreg_id)) + LITEX_SUBREG_ALIGN * (subreg_id)) /* * LiteX SoC Generator, depending on the configuration, can split a single -- cgit v1.2.3 From 51f109228308a87c7f2583360e54acfc567203da Mon Sep 17 00:00:00 2001 From: Gabriel Somlo Date: Tue, 12 Jan 2021 12:31:43 -0500 Subject: drivers/soc/litex: support 32-bit subregisters, 64-bit CPUs Upstream LiteX now defaults to using 32-bit CSR subregisters (see https://github.com/enjoy-digital/litex/commit/a2b71fde). This patch expands on commit 22447a99c97e ("drivers/soc/litex: add LiteX SoC Controller driver"), adding support for handling both 8- and 32-bit LiteX CSR (MMIO) subregisters, as determined by the LITEX_SUBREG_SIZE Kconfig option. NOTE that while LITEX_SUBREG_SIZE could theoretically be a device tree property, defining it as a compile-time constant allows for much better optimization of the resulting code. This is further supported by the low expected usefulness of deploying the same kernel across LiteX SoCs built with different CSR-Bus data widths. Finally, the litex_[read|write][8|16|32|64]() accessors are redefined in terms of litex_[get|set]_reg(), which, after compiler optimization, will result in code as efficient as hardcoded shifts, but with the added benefit of automatically matching the appropriate LITEX_SUBREG_SIZE. NOTE that litex_[get|set]_reg() nominally operate on 64-bit data, but that will also be optimized by the compiler in situations where narrower data is used from a call site. Signed-off-by: Gabriel Somlo Signed-off-by: Stafford Horne --- include/linux/litex.h | 137 ++++++++++++++++++++------------------------------ 1 file changed, 54 insertions(+), 83 deletions(-) (limited to 'include/linux') diff --git a/include/linux/litex.h b/include/linux/litex.h index c63a7e1a337c..3456d527f644 100644 --- a/include/linux/litex.h +++ b/include/linux/litex.h @@ -10,17 +10,14 @@ #define _LINUX_LITEX_H #include -#include -#include -/* - * The parameters below are true for LiteX SoCs configured for 8-bit CSR Bus, - * 32-bit aligned. - * - * Supporting other configurations will require extending the logic in this - * header and in the LiteX SoC controller driver. - */ -#define LITEX_SUBREG_SIZE 0x1 +/* LiteX SoCs support 8- or 32-bit CSR Bus data width (i.e., subreg. size) */ +#if defined(CONFIG_LITEX_SUBREG_SIZE) && \ + (CONFIG_LITEX_SUBREG_SIZE == 1 || CONFIG_LITEX_SUBREG_SIZE == 4) +#define LITEX_SUBREG_SIZE CONFIG_LITEX_SUBREG_SIZE +#else +#error LiteX subregister size (LITEX_SUBREG_SIZE) must be 4 or 1! +#endif #define LITEX_SUBREG_SIZE_BIT (LITEX_SUBREG_SIZE * 8) /* LiteX subregisters of any width are always aligned on a 4-byte boundary */ @@ -36,25 +33,32 @@ static inline u32 _read_litex_subregister(void __iomem *addr) return le32_to_cpu((__le32 __force)readl(addr)); } -#define WRITE_LITEX_SUBREGISTER(val, base_offset, subreg_id) \ - _write_litex_subregister(val, (base_offset) + \ - LITEX_SUBREG_ALIGN * (subreg_id)) - -#define READ_LITEX_SUBREGISTER(base_offset, subreg_id) \ - _read_litex_subregister((base_offset) + \ - LITEX_SUBREG_ALIGN * (subreg_id)) - /* * LiteX SoC Generator, depending on the configuration, can split a single * logical CSR (Control&Status Register) into a series of consecutive physical * registers. * - * For example, in the configuration with 8-bit CSR Bus, 32-bit aligned (the - * default one for 32-bit CPUs) a 32-bit logical CSR will be generated as four - * 32-bit physical registers, each one containing one byte of meaningful data. + * For example, in the configuration with 8-bit CSR Bus, a 32-bit aligned, + * 32-bit wide logical CSR will be laid out as four 32-bit physical + * subregisters, each one containing one byte of meaningful data. * * For details see: https://github.com/enjoy-digital/litex/wiki/CSR-Bus - * + */ + +/* number of LiteX subregisters needed to store a register of given reg_size */ +#define _litex_num_subregs(reg_size) \ + (((reg_size) - 1) / LITEX_SUBREG_SIZE + 1) + +/* + * since the number of 4-byte aligned subregisters required to store a single + * LiteX CSR (MMIO) register varies with LITEX_SUBREG_SIZE, the offset of the + * next adjacent LiteX CSR register w.r.t. the offset of the current one also + * depends on how many subregisters the latter is spread across + */ +#define _next_reg_off(off, size) \ + ((off) + _litex_num_subregs(size) * LITEX_SUBREG_ALIGN) + +/* * The purpose of `litex_set_reg`/`litex_get_reg` is to implement the logic * of writing to/reading from the LiteX CSR in a single place that can be * then reused by all LiteX drivers. @@ -66,22 +70,17 @@ static inline u32 _read_litex_subregister(void __iomem *addr) * @reg_size: The width of the CSR expressed in the number of bytes * @val: Value to be written to the CSR * - * In the currently supported LiteX configuration (8-bit CSR Bus, 32-bit aligned), - * a 32-bit LiteX CSR is generated as 4 consecutive 32-bit physical registers, - * each one containing one byte of meaningful data. - * - * This function splits a single possibly multi-byte write into a series of - * single-byte writes with a proper offset. + * This function splits a single (possibly multi-byte) LiteX CSR write into + * a series of subregister writes with a proper offset. */ -static inline void litex_set_reg(void __iomem *reg, ulong reg_size, ulong val) +static inline void litex_set_reg(void __iomem *reg, size_t reg_size, u64 val) { - ulong shifted_data, shift, i; - - for (i = 0; i < reg_size; ++i) { - shift = ((reg_size - i - 1) * LITEX_SUBREG_SIZE_BIT); - shifted_data = val >> shift; + u8 shift = _litex_num_subregs(reg_size) * LITEX_SUBREG_SIZE_BIT; - WRITE_LITEX_SUBREGISTER(shifted_data, reg, i); + while (shift > 0) { + shift -= LITEX_SUBREG_SIZE_BIT; + _write_litex_subregister(val >> shift, reg); + reg += LITEX_SUBREG_ALIGN; } } @@ -92,89 +91,61 @@ static inline void litex_set_reg(void __iomem *reg, ulong reg_size, ulong val) * * Return: Value read from the CSR * - * In the currently supported LiteX configuration (8-bit CSR Bus, 32-bit aligned), - * a 32-bit LiteX CSR is generated as 4 consecutive 32-bit physical registers, - * each one containing one byte of meaningful data. - * - * This function generates a series of single-byte reads with a proper offset - * and joins their results into a single multi-byte value. + * This function generates a series of subregister reads with a proper offset + * and joins their results into a single (possibly multi-byte) LiteX CSR value. */ -static inline ulong litex_get_reg(void __iomem *reg, ulong reg_size) +static inline u64 litex_get_reg(void __iomem *reg, size_t reg_size) { - ulong shifted_data, shift, i; - ulong result = 0; - - for (i = 0; i < reg_size; ++i) { - shifted_data = READ_LITEX_SUBREGISTER(reg, i); - - shift = ((reg_size - i - 1) * LITEX_SUBREG_SIZE_BIT); - result |= (shifted_data << shift); + u64 r; + u8 i; + + r = _read_litex_subregister(reg); + for (i = 1; i < _litex_num_subregs(reg_size); i++) { + r <<= LITEX_SUBREG_SIZE_BIT; + reg += LITEX_SUBREG_ALIGN; + r |= _read_litex_subregister(reg); } - - return result; + return r; } - static inline void litex_write8(void __iomem *reg, u8 val) { - WRITE_LITEX_SUBREGISTER(val, reg, 0); + litex_set_reg(reg, sizeof(u8), val); } static inline void litex_write16(void __iomem *reg, u16 val) { - WRITE_LITEX_SUBREGISTER(val >> 8, reg, 0); - WRITE_LITEX_SUBREGISTER(val, reg, 1); + litex_set_reg(reg, sizeof(u16), val); } static inline void litex_write32(void __iomem *reg, u32 val) { - WRITE_LITEX_SUBREGISTER(val >> 24, reg, 0); - WRITE_LITEX_SUBREGISTER(val >> 16, reg, 1); - WRITE_LITEX_SUBREGISTER(val >> 8, reg, 2); - WRITE_LITEX_SUBREGISTER(val, reg, 3); + litex_set_reg(reg, sizeof(u32), val); } static inline void litex_write64(void __iomem *reg, u64 val) { - WRITE_LITEX_SUBREGISTER(val >> 56, reg, 0); - WRITE_LITEX_SUBREGISTER(val >> 48, reg, 1); - WRITE_LITEX_SUBREGISTER(val >> 40, reg, 2); - WRITE_LITEX_SUBREGISTER(val >> 32, reg, 3); - WRITE_LITEX_SUBREGISTER(val >> 24, reg, 4); - WRITE_LITEX_SUBREGISTER(val >> 16, reg, 5); - WRITE_LITEX_SUBREGISTER(val >> 8, reg, 6); - WRITE_LITEX_SUBREGISTER(val, reg, 7); + litex_set_reg(reg, sizeof(u64), val); } static inline u8 litex_read8(void __iomem *reg) { - return READ_LITEX_SUBREGISTER(reg, 0); + return litex_get_reg(reg, sizeof(u8)); } static inline u16 litex_read16(void __iomem *reg) { - return (READ_LITEX_SUBREGISTER(reg, 0) << 8) - | (READ_LITEX_SUBREGISTER(reg, 1)); + return litex_get_reg(reg, sizeof(u16)); } static inline u32 litex_read32(void __iomem *reg) { - return (READ_LITEX_SUBREGISTER(reg, 0) << 24) - | (READ_LITEX_SUBREGISTER(reg, 1) << 16) - | (READ_LITEX_SUBREGISTER(reg, 2) << 8) - | (READ_LITEX_SUBREGISTER(reg, 3)); + return litex_get_reg(reg, sizeof(u32)); } static inline u64 litex_read64(void __iomem *reg) { - return ((u64)READ_LITEX_SUBREGISTER(reg, 0) << 56) - | ((u64)READ_LITEX_SUBREGISTER(reg, 1) << 48) - | ((u64)READ_LITEX_SUBREGISTER(reg, 2) << 40) - | ((u64)READ_LITEX_SUBREGISTER(reg, 3) << 32) - | ((u64)READ_LITEX_SUBREGISTER(reg, 4) << 24) - | ((u64)READ_LITEX_SUBREGISTER(reg, 5) << 16) - | ((u64)READ_LITEX_SUBREGISTER(reg, 6) << 8) - | ((u64)READ_LITEX_SUBREGISTER(reg, 7)); + return litex_get_reg(reg, sizeof(u64)); } #endif /* _LINUX_LITEX_H */ -- cgit v1.2.3 From 4f70d150294b3ddfbe4be7130ca53898cd5b91be Mon Sep 17 00:00:00 2001 From: Gabriel Somlo Date: Tue, 12 Jan 2021 12:31:44 -0500 Subject: drivers/soc/litex: make 'litex_[set|get]_reg()' methods private The 'litex_[set|get]_reg()' methods use the 'reg_size' parameter to specify the width of the LiteX CSR (MMIO) register being accessed. Since 'u64' is the widest data being supported, the value of 'reg_size' MUST be between 1 and sizeof(u64), which SHOULD be checked at runtime if these methods are publicly available for use by other LiteX device drivers. At the same time, none of the existing (or foreseeable) LiteX device drivers have a need to access registers whose size is unknown during compilation. As such, all LiteX device drivers should use fixed-width accessor methods such as 'litex_[write|read][8|16|32|64]()'. This patch renames 'litex_[set|get]_reg()' to '_litex_[set|get]_reg()', indicating that they should NOT be directly called from outside of the 'include/linux/litex.h' header file. Signed-off-by: Gabriel Somlo Signed-off-by: Stafford Horne --- include/linux/litex.h | 35 ++++++++++++++++++++--------------- 1 file changed, 20 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/litex.h b/include/linux/litex.h index 3456d527f644..5ea9ccf5cce4 100644 --- a/include/linux/litex.h +++ b/include/linux/litex.h @@ -59,21 +59,25 @@ static inline u32 _read_litex_subregister(void __iomem *addr) ((off) + _litex_num_subregs(size) * LITEX_SUBREG_ALIGN) /* - * The purpose of `litex_set_reg`/`litex_get_reg` is to implement the logic - * of writing to/reading from the LiteX CSR in a single place that can be - * then reused by all LiteX drivers. + * The purpose of `_litex_[set|get]_reg()` is to implement the logic of + * writing to/reading from the LiteX CSR in a single place that can be then + * reused by all LiteX drivers via the `litex_[write|read][8|16|32|64]()` + * accessors for the appropriate data width. + * NOTE: direct use of `_litex_[set|get]_reg()` by LiteX drivers is strongly + * discouraged, as they perform no error checking on the requested data width! */ /** - * litex_set_reg() - Writes the value to the LiteX CSR (Control&Status Register) + * _litex_set_reg() - Writes a value to the LiteX CSR (Control&Status Register) * @reg: Address of the CSR * @reg_size: The width of the CSR expressed in the number of bytes * @val: Value to be written to the CSR * * This function splits a single (possibly multi-byte) LiteX CSR write into * a series of subregister writes with a proper offset. + * NOTE: caller is responsible for ensuring (0 < reg_size <= sizeof(u64)). */ -static inline void litex_set_reg(void __iomem *reg, size_t reg_size, u64 val) +static inline void _litex_set_reg(void __iomem *reg, size_t reg_size, u64 val) { u8 shift = _litex_num_subregs(reg_size) * LITEX_SUBREG_SIZE_BIT; @@ -85,7 +89,7 @@ static inline void litex_set_reg(void __iomem *reg, size_t reg_size, u64 val) } /** - * litex_get_reg() - Reads the value of the LiteX CSR (Control&Status Register) + * _litex_get_reg() - Reads a value of the LiteX CSR (Control&Status Register) * @reg: Address of the CSR * @reg_size: The width of the CSR expressed in the number of bytes * @@ -93,8 +97,9 @@ static inline void litex_set_reg(void __iomem *reg, size_t reg_size, u64 val) * * This function generates a series of subregister reads with a proper offset * and joins their results into a single (possibly multi-byte) LiteX CSR value. + * NOTE: caller is responsible for ensuring (0 < reg_size <= sizeof(u64)). */ -static inline u64 litex_get_reg(void __iomem *reg, size_t reg_size) +static inline u64 _litex_get_reg(void __iomem *reg, size_t reg_size) { u64 r; u8 i; @@ -110,42 +115,42 @@ static inline u64 litex_get_reg(void __iomem *reg, size_t reg_size) static inline void litex_write8(void __iomem *reg, u8 val) { - litex_set_reg(reg, sizeof(u8), val); + _litex_set_reg(reg, sizeof(u8), val); } static inline void litex_write16(void __iomem *reg, u16 val) { - litex_set_reg(reg, sizeof(u16), val); + _litex_set_reg(reg, sizeof(u16), val); } static inline void litex_write32(void __iomem *reg, u32 val) { - litex_set_reg(reg, sizeof(u32), val); + _litex_set_reg(reg, sizeof(u32), val); } static inline void litex_write64(void __iomem *reg, u64 val) { - litex_set_reg(reg, sizeof(u64), val); + _litex_set_reg(reg, sizeof(u64), val); } static inline u8 litex_read8(void __iomem *reg) { - return litex_get_reg(reg, sizeof(u8)); + return _litex_get_reg(reg, sizeof(u8)); } static inline u16 litex_read16(void __iomem *reg) { - return litex_get_reg(reg, sizeof(u16)); + return _litex_get_reg(reg, sizeof(u16)); } static inline u32 litex_read32(void __iomem *reg) { - return litex_get_reg(reg, sizeof(u32)); + return _litex_get_reg(reg, sizeof(u32)); } static inline u64 litex_read64(void __iomem *reg) { - return litex_get_reg(reg, sizeof(u64)); + return _litex_get_reg(reg, sizeof(u64)); } #endif /* _LINUX_LITEX_H */ -- cgit v1.2.3 From 99b7beb0431a4b9728023e9169ed15af678d2c7f Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Mon, 11 Jan 2021 15:19:24 +0100 Subject: can: length: canfd_sanitize_len(): add function to sanitize CAN-FD data length The data field in CAN-FD frames have specifig frame length (0, 1, 2, 3, 4, 5, 6, 7, 8, 12, 16, 20, 24, 32, 48, 64). This function "rounds" up a given length to the next valid CAN-FD frame length. Reviewed-by: Vincent Mailhol Link: https://lore.kernel.org/r/20210111141930.693847-10-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- include/linux/can/length.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/can/length.h b/include/linux/can/length.h index 156b9d17969a..b2313b2a0b02 100644 --- a/include/linux/can/length.h +++ b/include/linux/can/length.h @@ -45,4 +45,10 @@ u8 can_fd_dlc2len(u8 dlc); /* map the sanitized data length to an appropriate data length code */ u8 can_fd_len2dlc(u8 len); +/* map the data length to an appropriate data link layer length */ +static inline u8 canfd_sanitize_len(u8 len) +{ + return can_fd_dlc2len(can_fd_len2dlc(len)); +} + #endif /* !_CAN_LENGTH_H */ -- cgit v1.2.3 From 85d99c3e2a13d542445342a1383a686dadeaac3d Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Mon, 11 Jan 2021 15:19:25 +0100 Subject: can: length: can_skb_get_frame_len(): introduce function to get data length of frame in data link layer This patch adds the function can_skb_get_frame_len() which returns the length of a CAN frame on the data link layer, including Start-of-frame, Identifier, various other bits, the actual data, the CRC, the End-of-frame, the Inter frame spacing. Co-developed-by: Arunachalam Santhanam Signed-off-by: Arunachalam Santhanam Co-developed-by: Vincent Mailhol Signed-off-by: Vincent Mailhol Acked-by: Vincent Mailhol Reviewed-by: Vincent Mailhol Co-developed-by: Marc Kleine-Budde Link: https://lore.kernel.org/r/20210111141930.693847-11-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- include/linux/can/length.h | 120 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 120 insertions(+) (limited to 'include/linux') diff --git a/include/linux/can/length.h b/include/linux/can/length.h index b2313b2a0b02..6995092b774e 100644 --- a/include/linux/can/length.h +++ b/include/linux/can/length.h @@ -1,10 +1,127 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (C) 2020 Oliver Hartkopp + * Copyright (C) 2020 Marc Kleine-Budde */ #ifndef _CAN_LENGTH_H #define _CAN_LENGTH_H +/* + * Size of a Classical CAN Standard Frame + * + * Name of Field Bits + * --------------------------------------------------------- + * Start-of-frame 1 + * Identifier 11 + * Remote transmission request (RTR) 1 + * Identifier extension bit (IDE) 1 + * Reserved bit (r0) 1 + * Data length code (DLC) 4 + * Data field 0...64 + * CRC 15 + * CRC delimiter 1 + * ACK slot 1 + * ACK delimiter 1 + * End-of-frame (EOF) 7 + * Inter frame spacing 3 + * + * rounded up and ignoring bitstuffing + */ +#define CAN_FRAME_OVERHEAD_SFF DIV_ROUND_UP(47, 8) + +/* + * Size of a Classical CAN Extended Frame + * + * Name of Field Bits + * --------------------------------------------------------- + * Start-of-frame 1 + * Identifier A 11 + * Substitute remote request (SRR) 1 + * Identifier extension bit (IDE) 1 + * Identifier B 18 + * Remote transmission request (RTR) 1 + * Reserved bits (r1, r0) 2 + * Data length code (DLC) 4 + * Data field 0...64 + * CRC 15 + * CRC delimiter 1 + * ACK slot 1 + * ACK delimiter 1 + * End-of-frame (EOF) 7 + * Inter frame spacing 3 + * + * rounded up and ignoring bitstuffing + */ +#define CAN_FRAME_OVERHEAD_EFF DIV_ROUND_UP(67, 8) + +/* + * Size of a CAN-FD Standard Frame + * + * Name of Field Bits + * --------------------------------------------------------- + * Start-of-frame 1 + * Identifier 11 + * Reserved bit (r1) 1 + * Identifier extension bit (IDE) 1 + * Flexible data rate format (FDF) 1 + * Reserved bit (r0) 1 + * Bit Rate Switch (BRS) 1 + * Error Status Indicator (ESI) 1 + * Data length code (DLC) 4 + * Data field 0...512 + * Stuff Bit Count (SBC) 0...16: 4 20...64:5 + * CRC 0...16: 17 20...64:21 + * CRC delimiter (CD) 1 + * ACK slot (AS) 1 + * ACK delimiter (AD) 1 + * End-of-frame (EOF) 7 + * Inter frame spacing 3 + * + * assuming CRC21, rounded up and ignoring bitstuffing + */ +#define CANFD_FRAME_OVERHEAD_SFF DIV_ROUND_UP(61, 8) + +/* + * Size of a CAN-FD Extended Frame + * + * Name of Field Bits + * --------------------------------------------------------- + * Start-of-frame 1 + * Identifier A 11 + * Substitute remote request (SRR) 1 + * Identifier extension bit (IDE) 1 + * Identifier B 18 + * Reserved bit (r1) 1 + * Flexible data rate format (FDF) 1 + * Reserved bit (r0) 1 + * Bit Rate Switch (BRS) 1 + * Error Status Indicator (ESI) 1 + * Data length code (DLC) 4 + * Data field 0...512 + * Stuff Bit Count (SBC) 0...16: 4 20...64:5 + * CRC 0...16: 17 20...64:21 + * CRC delimiter (CD) 1 + * ACK slot (AS) 1 + * ACK delimiter (AD) 1 + * End-of-frame (EOF) 7 + * Inter frame spacing 3 + * + * assuming CRC21, rounded up and ignoring bitstuffing + */ +#define CANFD_FRAME_OVERHEAD_EFF DIV_ROUND_UP(80, 8) + +/* + * Maximum size of a Classical CAN frame + * (rounded up and ignoring bitstuffing) + */ +#define CAN_FRAME_LEN_MAX (CAN_FRAME_OVERHEAD_EFF + CAN_MAX_DLEN) + +/* + * Maximum size of a CAN-FD frame + * (rounded up and ignoring bitstuffing) + */ +#define CANFD_FRAME_LEN_MAX (CANFD_FRAME_OVERHEAD_EFF + CANFD_MAX_DLEN) + /* * can_cc_dlc2len(value) - convert a given data length code (dlc) of a * Classical CAN frame into a valid data length of max. 8 bytes. @@ -45,6 +162,9 @@ u8 can_fd_dlc2len(u8 dlc); /* map the sanitized data length to an appropriate data length code */ u8 can_fd_len2dlc(u8 len); +/* calculate the CAN Frame length in bytes of a given skb */ +unsigned int can_skb_get_frame_len(const struct sk_buff *skb); + /* map the data length to an appropriate data link layer length */ static inline u8 canfd_sanitize_len(u8 len) { -- cgit v1.2.3 From f0ef72febc9a6a569d92cdf6c7996015dfa8e8bb Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Mon, 11 Jan 2021 15:19:26 +0100 Subject: can: dev: extend struct can_skb_priv to hold CAN frame length In order to implement byte queue limits (bql) in CAN drivers, the length of the CAN frame needs to be passed into the networking stack after queueing and after transmission completion. To avoid to calculate this length twice, extend the struct can_skb_priv to hold the length of the CAN frame and extend __can_get_echo_skb() to return that value. Reviewed-by: Vincent Mailhol Link: https://lore.kernel.org/r/20210111141930.693847-12-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- include/linux/can/skb.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h index c90ebbd3008c..5db9da30843c 100644 --- a/include/linux/can/skb.h +++ b/include/linux/can/skb.h @@ -20,7 +20,7 @@ void can_flush_echo_skb(struct net_device *dev); int can_put_echo_skb(struct sk_buff *skb, struct net_device *dev, unsigned int idx); struct sk_buff *__can_get_echo_skb(struct net_device *dev, unsigned int idx, - u8 *len_ptr); + u8 *len_ptr, unsigned int *frame_len_ptr); unsigned int can_get_echo_skb(struct net_device *dev, unsigned int idx); void can_free_echo_skb(struct net_device *dev, unsigned int idx); struct sk_buff *alloc_can_skb(struct net_device *dev, struct can_frame **cf); @@ -42,11 +42,13 @@ struct sk_buff *alloc_can_err_skb(struct net_device *dev, * struct can_skb_priv - private additional data inside CAN sk_buffs * @ifindex: ifindex of the first interface the CAN frame appeared on * @skbcnt: atomic counter to have an unique id together with skb pointer + * @frame_len: length of CAN frame in data link layer * @cf: align to the following CAN frame at skb->data */ struct can_skb_priv { int ifindex; int skbcnt; + unsigned int frame_len; struct can_frame cf[]; }; -- cgit v1.2.3 From 1dcb6e57db833419483d0df2d956b1cc2a802683 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Mon, 11 Jan 2021 15:19:27 +0100 Subject: can: dev: can_put_echo_skb(): extend to handle frame_len Add a frame_len argument to can_put_echo_skb() which is used to save length of the CAN frame into field frame_len of struct can_skb_priv so that it can be later used after transmission completion. Convert all users of this function, too. Drivers which implement BQL call can_put_echo_skb() with the output of can_skb_get_frame_len(skb) and drivers which do not simply pass zero as an input (in the same way that NULL would be given to can_get_echo_skb()). This way, we have a nice symmetry between the two echo functions. Link: https://lore.kernel.org/r/20210111061335.39983-1-mailhol.vincent@wanadoo.fr Signed-off-by: Marc Kleine-Budde Reviewed-by: Vincent Mailhol Link: https://lore.kernel.org/r/20210111141930.693847-13-mkl@pengutronix.de Signed-off-by: Vincent Mailhol --- include/linux/can/skb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h index 5db9da30843c..eaac4a637ae0 100644 --- a/include/linux/can/skb.h +++ b/include/linux/can/skb.h @@ -18,7 +18,7 @@ void can_flush_echo_skb(struct net_device *dev); int can_put_echo_skb(struct sk_buff *skb, struct net_device *dev, - unsigned int idx); + unsigned int idx, unsigned int frame_len); struct sk_buff *__can_get_echo_skb(struct net_device *dev, unsigned int idx, u8 *len_ptr, unsigned int *frame_len_ptr); unsigned int can_get_echo_skb(struct net_device *dev, unsigned int idx); -- cgit v1.2.3 From 9420e1d495e2a3b5f673148b7e3ebc861b1441f7 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Mon, 11 Jan 2021 15:19:28 +0100 Subject: can: dev: can_get_echo_skb(): extend to return can frame length In order to implement byte queue limits (bql) in CAN drivers, the length of the CAN frame needs to be passed into the networking stack after queueing and after transmission completion. To avoid to calculate this length twice, extend can_get_echo_skb() to return that value. Convert all users of this function, too. Reviewed-by: Vincent Mailhol Link: https://lore.kernel.org/r/20210111141930.693847-14-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- include/linux/can/skb.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h index eaac4a637ae0..685f34cfba20 100644 --- a/include/linux/can/skb.h +++ b/include/linux/can/skb.h @@ -21,7 +21,8 @@ int can_put_echo_skb(struct sk_buff *skb, struct net_device *dev, unsigned int idx, unsigned int frame_len); struct sk_buff *__can_get_echo_skb(struct net_device *dev, unsigned int idx, u8 *len_ptr, unsigned int *frame_len_ptr); -unsigned int can_get_echo_skb(struct net_device *dev, unsigned int idx); +unsigned int can_get_echo_skb(struct net_device *dev, unsigned int idx, + unsigned int *frame_len_ptr); void can_free_echo_skb(struct net_device *dev, unsigned int idx); struct sk_buff *alloc_can_skb(struct net_device *dev, struct can_frame **cf); struct sk_buff *alloc_canfd_skb(struct net_device *dev, -- cgit v1.2.3 From 99842c9685ab00fa8689e8bd12bde62b706b6198 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Mon, 11 Jan 2021 15:19:29 +0100 Subject: can: dev: can_rx_offload_get_echo_skb(): extend to return can frame length In order to implement byte queue limits (bql) in CAN drivers, the length of the CAN frame needs to be passed into the networking stack after queueing and after transmission completion. To avoid to calculate this length twice, extend can_rx_offload_get_echo_skb() to return that value. Convert all users of this function, too. Reviewed-by: Vincent Mailhol Link: https://lore.kernel.org/r/20210111141930.693847-15-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- include/linux/can/rx-offload.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/can/rx-offload.h b/include/linux/can/rx-offload.h index f1b38088b765..40882df7105e 100644 --- a/include/linux/can/rx-offload.h +++ b/include/linux/can/rx-offload.h @@ -44,7 +44,8 @@ int can_rx_offload_irq_offload_fifo(struct can_rx_offload *offload); int can_rx_offload_queue_sorted(struct can_rx_offload *offload, struct sk_buff *skb, u32 timestamp); unsigned int can_rx_offload_get_echo_skb(struct can_rx_offload *offload, - unsigned int idx, u32 timestamp); + unsigned int idx, u32 timestamp, + unsigned int *frame_len_ptr); int can_rx_offload_queue_tail(struct can_rx_offload *offload, struct sk_buff *skb); void can_rx_offload_del(struct can_rx_offload *offload); -- cgit v1.2.3 From a5418be9dffe70ccbb0b4bd5ea3881c81927e965 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 8 Dec 2020 09:46:56 +0530 Subject: sched/core: Rename schedutil_cpu_util() and allow rest of the kernel to use it There is nothing schedutil specific in schedutil_cpu_util(), rename it to effective_cpu_util(). Also create and expose another wrapper sched_cpu_util() which can be used by other parts of the kernel, like thermal core (that will be done in a later commit). Signed-off-by: Viresh Kumar Signed-off-by: Peter Zijlstra (Intel) Acked-by: Rafael J. Wysocki Link: https://lkml.kernel.org/r/db011961fb3bb8bef1c0eda5cd64564637d3ef31.1607400596.git.viresh.kumar@linaro.org --- include/linux/sched.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 6e3a5eeec509..31169e70476a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1968,6 +1968,11 @@ extern long sched_getaffinity(pid_t pid, struct cpumask *mask); #define TASK_SIZE_OF(tsk) TASK_SIZE #endif +#ifdef CONFIG_SMP +/* Returns effective CPU energy utilization, as seen by the scheduler */ +unsigned long sched_cpu_util(int cpu, unsigned long max); +#endif /* CONFIG_SMP */ + #ifdef CONFIG_RSEQ /* -- cgit v1.2.3 From dfd5e3f5fe27bda91d5cc028c86ffbb7a0614489 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 9 Dec 2020 16:06:21 +0100 Subject: locking/lockdep: Mark local_lock_t The local_lock_t's are special, because they cannot form IRQ inversions, make sure we can tell them apart from the rest of the locks. Signed-off-by: Peter Zijlstra (Intel) --- include/linux/local_lock_internal.h | 5 ++++- include/linux/lockdep.h | 15 ++++++++++++--- include/linux/lockdep_types.h | 18 ++++++++++++++---- 3 files changed, 30 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h index 4a8795b21d77..ded90b097e6e 100644 --- a/include/linux/local_lock_internal.h +++ b/include/linux/local_lock_internal.h @@ -18,6 +18,7 @@ typedef struct { .dep_map = { \ .name = #lockname, \ .wait_type_inner = LD_WAIT_CONFIG, \ + .lock_type = LD_LOCK_PERCPU, \ } #else # define LL_DEP_MAP_INIT(lockname) @@ -30,7 +31,9 @@ do { \ static struct lock_class_key __key; \ \ debug_check_no_locks_freed((void *)lock, sizeof(*lock));\ - lockdep_init_map_wait(&(lock)->dep_map, #lock, &__key, 0, LD_WAIT_CONFIG);\ + lockdep_init_map_type(&(lock)->dep_map, #lock, &__key, 0, \ + LD_WAIT_CONFIG, LD_WAIT_INV, \ + LD_LOCK_PERCPU); \ } while (0) #ifdef CONFIG_DEBUG_LOCK_ALLOC diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index b9e9adec73e8..7b7ebf2e28ec 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -185,12 +185,19 @@ extern void lockdep_unregister_key(struct lock_class_key *key); * to lockdep: */ -extern void lockdep_init_map_waits(struct lockdep_map *lock, const char *name, - struct lock_class_key *key, int subclass, short inner, short outer); +extern void lockdep_init_map_type(struct lockdep_map *lock, const char *name, + struct lock_class_key *key, int subclass, u8 inner, u8 outer, u8 lock_type); + +static inline void +lockdep_init_map_waits(struct lockdep_map *lock, const char *name, + struct lock_class_key *key, int subclass, u8 inner, u8 outer) +{ + lockdep_init_map_type(lock, name, key, subclass, inner, LD_WAIT_INV, LD_LOCK_NORMAL); +} static inline void lockdep_init_map_wait(struct lockdep_map *lock, const char *name, - struct lock_class_key *key, int subclass, short inner) + struct lock_class_key *key, int subclass, u8 inner) { lockdep_init_map_waits(lock, name, key, subclass, inner, LD_WAIT_INV); } @@ -340,6 +347,8 @@ static inline void lockdep_set_selftest_task(struct task_struct *task) # define lock_set_class(l, n, k, s, i) do { } while (0) # define lock_set_subclass(l, s, i) do { } while (0) # define lockdep_init() do { } while (0) +# define lockdep_init_map_type(lock, name, key, sub, inner, outer, type) \ + do { (void)(name); (void)(key); } while (0) # define lockdep_init_map_waits(lock, name, key, sub, inner, outer) \ do { (void)(name); (void)(key); } while (0) # define lockdep_init_map_wait(lock, name, key, sub, inner) \ diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h index 9a1fd49df17f..2ec9ff5a7fff 100644 --- a/include/linux/lockdep_types.h +++ b/include/linux/lockdep_types.h @@ -30,6 +30,12 @@ enum lockdep_wait_type { LD_WAIT_MAX, /* must be last */ }; +enum lockdep_lock_type { + LD_LOCK_NORMAL = 0, /* normal, catch all */ + LD_LOCK_PERCPU, /* percpu */ + LD_LOCK_MAX, +}; + #ifdef CONFIG_LOCKDEP /* @@ -119,8 +125,10 @@ struct lock_class { int name_version; const char *name; - short wait_type_inner; - short wait_type_outer; + u8 wait_type_inner; + u8 wait_type_outer; + u8 lock_type; + /* u8 hole; */ #ifdef CONFIG_LOCK_STAT unsigned long contention_point[LOCKSTAT_POINTS]; @@ -169,8 +177,10 @@ struct lockdep_map { struct lock_class_key *key; struct lock_class *class_cache[NR_LOCKDEP_CACHING_CLASSES]; const char *name; - short wait_type_outer; /* can be taken in this context */ - short wait_type_inner; /* presents this context */ + u8 wait_type_outer; /* can be taken in this context */ + u8 wait_type_inner; /* presents this context */ + u8 lock_type; + /* u8 hole; */ #ifdef CONFIG_LOCK_STAT int cpu; unsigned long ip; -- cgit v1.2.3 From b0f87e8ac263e3b82ec314542cb7fb07a47fc8b7 Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Tue, 12 Jan 2021 18:00:58 +0900 Subject: mfd: rohm-generic: Add BD9571 and BD9574 Add chip IDs for BD9571MWV and BD9574MWF. Signed-off-by: Yoshihiro Shimoda Reviewed-by: Matti Vaittinen Acked-for-MFD-by: Lee Jones Signed-off-by: Lee Jones --- include/linux/mfd/rohm-generic.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/rohm-generic.h b/include/linux/mfd/rohm-generic.h index 4283b5b33e04..affacf8c6e91 100644 --- a/include/linux/mfd/rohm-generic.h +++ b/include/linux/mfd/rohm-generic.h @@ -12,6 +12,8 @@ enum rohm_chip_type { ROHM_CHIP_TYPE_BD71847, ROHM_CHIP_TYPE_BD70528, ROHM_CHIP_TYPE_BD71828, + ROHM_CHIP_TYPE_BD9571, + ROHM_CHIP_TYPE_BD9574, ROHM_CHIP_TYPE_AMOUNT }; -- cgit v1.2.3 From bfb26be7fe90186e5d9fe704cc124ab77bb7d127 Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Tue, 12 Jan 2021 18:01:04 +0900 Subject: mfd: bd9571mwv: Use the SPDX license identifier Use the SPDX license identifier instead of a local description. Signed-off-by: Yoshihiro Shimoda Reviewed-by: Geert Uytterhoeven Acked-for-MFD-by: Lee Jones Signed-off-by: Lee Jones --- include/linux/mfd/bd9571mwv.h | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/bd9571mwv.h b/include/linux/mfd/bd9571mwv.h index eb05569f752b..bcc709293b24 100644 --- a/include/linux/mfd/bd9571mwv.h +++ b/include/linux/mfd/bd9571mwv.h @@ -1,17 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * ROHM BD9571MWV-M driver * * Copyright (C) 2017 Marek Vasut * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any - * kind, whether expressed or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License version 2 for more details. - * * Based on the TPS65086 driver */ -- cgit v1.2.3 From f16e1fd197f85a943b5880009f4aefe05a17df0d Mon Sep 17 00:00:00 2001 From: Khiem Nguyen Date: Tue, 12 Jan 2021 18:01:06 +0900 Subject: mfd: bd9571mwv: Make the driver more generic Since the driver supports BD9571MWV PMIC only, this patch makes the functions and data structure become more generic so that it can support other PMIC variants as well. Also remove printing part name which Lee Jones suggested. Signed-off-by: Khiem Nguyen Co-developed-by: Yoshihiro Shimoda Signed-off-by: Yoshihiro Shimoda Reviewed-by: Matti Vaittinen Acked-for-MFD-by: Lee Jones Signed-off-by: Lee Jones --- include/linux/mfd/bd9571mwv.h | 18 ++---------------- 1 file changed, 2 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/bd9571mwv.h b/include/linux/mfd/bd9571mwv.h index bcc709293b24..e1716eca6bb5 100644 --- a/include/linux/mfd/bd9571mwv.h +++ b/include/linux/mfd/bd9571mwv.h @@ -3,6 +3,7 @@ * ROHM BD9571MWV-M driver * * Copyright (C) 2017 Marek Vasut + * Copyright (C) 2020 Renesas Electronics Corporation * * Based on the TPS65086 driver */ @@ -17,7 +18,7 @@ #define BD9571MWV_VENDOR_CODE 0x00 #define BD9571MWV_VENDOR_CODE_VAL 0xdb #define BD9571MWV_PRODUCT_CODE 0x01 -#define BD9571MWV_PRODUCT_CODE_VAL 0x60 +#define BD9571MWV_PRODUCT_CODE_BD9571MWV 0x60 #define BD9571MWV_PRODUCT_REVISION 0x02 #define BD9571MWV_I2C_FUSA_MODE 0x10 @@ -94,19 +95,4 @@ enum bd9571mwv_irqs { BD9571MWV_IRQ_WDT_OF, BD9571MWV_IRQ_BKUP_TRG, }; - -/** - * struct bd9571mwv - state holder for the bd9571mwv driver - * - * Device data may be used to access the BD9571MWV chip - */ -struct bd9571mwv { - struct device *dev; - struct regmap *regmap; - - /* IRQ Data */ - int irq; - struct regmap_irq_chip_data *irq_data; -}; - #endif /* __LINUX_MFD_BD9571MWV_H */ -- cgit v1.2.3 From b2548da647bb04737196ffd945505d47a166239b Mon Sep 17 00:00:00 2001 From: Khiem Nguyen Date: Tue, 12 Jan 2021 18:01:07 +0900 Subject: mfd: bd9571mwv: Add support for BD9574MWF The new PMIC BD9574MWF inherits features from BD9571MWV. Add the support of new PMIC to existing bd9571mwv driver. Signed-off-by: Khiem Nguyen Co-developed-by: Yoshihiro Shimoda Signed-off-by: Yoshihiro Shimoda Reviewed-by: Matti Vaittinen Acked-for-MFD-by: Lee Jones Signed-off-by: Lee Jones --- include/linux/mfd/bd9571mwv.h | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/bd9571mwv.h b/include/linux/mfd/bd9571mwv.h index e1716eca6bb5..8efd99d07c9e 100644 --- a/include/linux/mfd/bd9571mwv.h +++ b/include/linux/mfd/bd9571mwv.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * ROHM BD9571MWV-M driver + * ROHM BD9571MWV-M and BD9574MWF-M driver * * Copyright (C) 2017 Marek Vasut * Copyright (C) 2020 Renesas Electronics Corporation @@ -14,11 +14,12 @@ #include #include -/* List of registers for BD9571MWV */ +/* List of registers for BD9571MWV and BD9574MWF */ #define BD9571MWV_VENDOR_CODE 0x00 #define BD9571MWV_VENDOR_CODE_VAL 0xdb #define BD9571MWV_PRODUCT_CODE 0x01 #define BD9571MWV_PRODUCT_CODE_BD9571MWV 0x60 +#define BD9571MWV_PRODUCT_CODE_BD9574MWF 0x74 #define BD9571MWV_PRODUCT_REVISION 0x02 #define BD9571MWV_I2C_FUSA_MODE 0x10 @@ -48,6 +49,7 @@ #define BD9571MWV_VD33_VID 0x44 #define BD9571MWV_DVFS_VINIT 0x50 +#define BD9574MWF_VD09_VINIT 0x51 #define BD9571MWV_DVFS_SETVMAX 0x52 #define BD9571MWV_DVFS_BOOSTVID 0x53 #define BD9571MWV_DVFS_SETVID 0x54 @@ -61,6 +63,7 @@ #define BD9571MWV_GPIO_INT_SET 0x64 #define BD9571MWV_GPIO_INT 0x65 #define BD9571MWV_GPIO_INTMASK 0x66 +#define BD9574MWF_GPIO_MUX 0x67 #define BD9571MWV_REG_KEEP(n) (0x70 + (n)) @@ -70,6 +73,8 @@ #define BD9571MWV_PROT_ERROR_STATUS2 0x83 #define BD9571MWV_PROT_ERROR_STATUS3 0x84 #define BD9571MWV_PROT_ERROR_STATUS4 0x85 +#define BD9574MWF_PROT_ERROR_STATUS5 0x86 +#define BD9574MWF_SYSTEM_ERROR_STATUS 0x87 #define BD9571MWV_INT_INTREQ 0x90 #define BD9571MWV_INT_INTREQ_MD1_INT BIT(0) @@ -82,6 +87,12 @@ #define BD9571MWV_INT_INTREQ_BKUP_TRG_INT BIT(7) #define BD9571MWV_INT_INTMASK 0x91 +#define BD9574MWF_SSCG_CNT 0xA0 +#define BD9574MWF_POFFB_MRB 0xA1 +#define BD9574MWF_SMRB_WR_PROT 0xA2 +#define BD9574MWF_SMRB_ASSERT 0xA3 +#define BD9574MWF_SMRB_STATUS 0xA4 + #define BD9571MWV_ACCESS_KEY 0xff /* Define the BD9571MWV IRQ numbers */ @@ -91,7 +102,7 @@ enum bd9571mwv_irqs { BD9571MWV_IRQ_MD2_E2, BD9571MWV_IRQ_PROT_ERR, BD9571MWV_IRQ_GP, - BD9571MWV_IRQ_128H_OF, + BD9571MWV_IRQ_128H_OF, /* BKUP_HOLD on BD9574MWF */ BD9571MWV_IRQ_WDT_OF, BD9571MWV_IRQ_BKUP_TRG, }; -- cgit v1.2.3 From 097d43d8570457c1af9b09fab15412697b177f35 Mon Sep 17 00:00:00 2001 From: Daeseok Youn Date: Thu, 14 Jan 2021 16:08:17 +0900 Subject: mm: memblock: remove return value of memblock_free_all() No one checks the return value of memblock_free_all(). Make the return value void. memblock_free_all() is used on mem_init() for each architecture, and the total count of freed pages will be added to _totalram_pages variable by calling totalram_pages_add(). so do not need to return total count of freed pages. Signed-off-by: Daeseok Youn Reviewed-by: David Hildenbrand Signed-off-by: Mike Rapoport --- include/linux/memblock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index b93c44b9121e..acf1e6a85066 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -117,7 +117,7 @@ int memblock_mark_mirror(phys_addr_t base, phys_addr_t size); int memblock_mark_nomap(phys_addr_t base, phys_addr_t size); int memblock_clear_nomap(phys_addr_t base, phys_addr_t size); -unsigned long memblock_free_all(void); +void memblock_free_all(void); void reset_node_managed_pages(pg_data_t *pgdat); void reset_all_zones_managed_pages(void); -- cgit v1.2.3 From a8cccdd954732a558d481407ab7c3106b89c34ae Mon Sep 17 00:00:00 2001 From: Sami Tolvanen Date: Fri, 11 Dec 2020 10:46:24 -0800 Subject: init: lto: ensure initcall ordering With LTO, the compiler doesn't necessarily obey the link order for initcalls, and initcall variables need globally unique names to avoid collisions at link time. This change exports __KBUILD_MODNAME and adds the initcall_id() macro, which uses it together with __COUNTER__ and __LINE__ to help ensure these variables have unique names, and moves each variable to its own section when LTO is enabled, so the correct order can be specified using a linker script. The generate_initcall_ordering.pl script uses nm to find initcalls from the object files passed to the linker, and generates a linker script that specifies the same order for initcalls that we would have without LTO. With LTO enabled, the script is called in link-vmlinux.sh through jobserver-exec to limit the number of jobs spawned. Signed-off-by: Sami Tolvanen Reviewed-by: Kees Cook Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20201211184633.3213045-8-samitolvanen@google.com --- include/linux/init.h | 52 +++++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 45 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init.h b/include/linux/init.h index e668832ef66a..a57bf0dfd75f 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -184,19 +184,57 @@ extern bool initcall_debug; * as KEEP() in the linker script. */ +/* Format: ____ */ +#define __initcall_id(fn) \ + __PASTE(__KBUILD_MODNAME, \ + __PASTE(__, \ + __PASTE(__COUNTER__, \ + __PASTE(_, \ + __PASTE(__LINE__, \ + __PASTE(_, fn)))))) + +/* Format: ____ */ +#define __initcall_name(prefix, __iid, id) \ + __PASTE(__, \ + __PASTE(prefix, \ + __PASTE(__, \ + __PASTE(__iid, id)))) + +#ifdef CONFIG_LTO_CLANG +/* + * With LTO, the compiler doesn't necessarily obey link order for + * initcalls. In order to preserve the correct order, we add each + * variable into its own section and generate a linker script (in + * scripts/link-vmlinux.sh) to specify the order of the sections. + */ +#define __initcall_section(__sec, __iid) \ + #__sec ".init.." #__iid +#else +#define __initcall_section(__sec, __iid) \ + #__sec ".init" +#endif + #ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS -#define ___define_initcall(fn, id, __sec) \ +#define ____define_initcall(fn, __name, __sec) \ __ADDRESSABLE(fn) \ - asm(".section \"" #__sec ".init\", \"a\" \n" \ - "__initcall_" #fn #id ": \n" \ + asm(".section \"" __sec "\", \"a\" \n" \ + __stringify(__name) ": \n" \ ".long " #fn " - . \n" \ ".previous \n"); #else -#define ___define_initcall(fn, id, __sec) \ - static initcall_t __initcall_##fn##id __used \ - __attribute__((__section__(#__sec ".init"))) = fn; +#define ____define_initcall(fn, __name, __sec) \ + static initcall_t __name __used \ + __attribute__((__section__(__sec))) = fn; #endif +#define __unique_initcall(fn, id, __sec, __iid) \ + ____define_initcall(fn, \ + __initcall_name(initcall, __iid, id), \ + __initcall_section(__sec, __iid)) + +#define ___define_initcall(fn, id, __sec) \ + __unique_initcall(fn, id, __sec, __initcall_id(fn)) + #define __define_initcall(fn, id) ___define_initcall(fn, id, .initcall##id) /* @@ -236,7 +274,7 @@ extern bool initcall_debug; #define __exitcall(fn) \ static exitcall_t __exitcall_##fn __exit_call = fn -#define console_initcall(fn) ___define_initcall(fn,, .con_initcall) +#define console_initcall(fn) ___define_initcall(fn, con, .con_initcall) struct obs_kernel_param { const char *str; -- cgit v1.2.3 From 3578ad11f3fba07e64c26d8db68cfd3dde28c59e Mon Sep 17 00:00:00 2001 From: Sami Tolvanen Date: Fri, 11 Dec 2020 10:46:25 -0800 Subject: init: lto: fix PREL32 relocations With LTO, the compiler can rename static functions to avoid global naming collisions. As initcall functions are typically static, renaming can break references to them in inline assembly. This change adds a global stub with a stable name for each initcall to fix the issue when PREL32 relocations are used. Signed-off-by: Sami Tolvanen Reviewed-by: Kees Cook Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20201211184633.3213045-9-samitolvanen@google.com --- include/linux/init.h | 31 +++++++++++++++++++++++++++---- 1 file changed, 27 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init.h b/include/linux/init.h index a57bf0dfd75f..a01f01c1a5c5 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -209,26 +209,49 @@ extern bool initcall_debug; */ #define __initcall_section(__sec, __iid) \ #__sec ".init.." #__iid + +/* + * With LTO, the compiler can rename static functions to avoid + * global naming collisions. We use a global stub function for + * initcalls to create a stable symbol name whose address can be + * taken in inline assembly when PREL32 relocations are used. + */ +#define __initcall_stub(fn, __iid, id) \ + __initcall_name(initstub, __iid, id) + +#define __define_initcall_stub(__stub, fn) \ + int __init __stub(void); \ + int __init __stub(void) \ + { \ + return fn(); \ + } \ + __ADDRESSABLE(__stub) #else #define __initcall_section(__sec, __iid) \ #__sec ".init" + +#define __initcall_stub(fn, __iid, id) fn + +#define __define_initcall_stub(__stub, fn) \ + __ADDRESSABLE(fn) #endif #ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS -#define ____define_initcall(fn, __name, __sec) \ - __ADDRESSABLE(fn) \ +#define ____define_initcall(fn, __stub, __name, __sec) \ + __define_initcall_stub(__stub, fn) \ asm(".section \"" __sec "\", \"a\" \n" \ __stringify(__name) ": \n" \ - ".long " #fn " - . \n" \ + ".long " __stringify(__stub) " - . \n" \ ".previous \n"); #else -#define ____define_initcall(fn, __name, __sec) \ +#define ____define_initcall(fn, __unused, __name, __sec) \ static initcall_t __name __used \ __attribute__((__section__(__sec))) = fn; #endif #define __unique_initcall(fn, id, __sec, __iid) \ ____define_initcall(fn, \ + __initcall_stub(fn, __iid, id), \ __initcall_name(initcall, __iid, id), \ __initcall_section(__sec, __iid)) -- cgit v1.2.3 From 09a4e4d9c52a3c5e39e4f409b2c083ab13c6afc2 Mon Sep 17 00:00:00 2001 From: Sami Tolvanen Date: Fri, 11 Dec 2020 10:46:26 -0800 Subject: PCI: Fix PREL32 relocations for LTO With Clang's Link Time Optimization (LTO), the compiler can rename static functions to avoid global naming collisions. As PCI fixup functions are typically static, renaming can break references to them in inline assembly. This change adds a global stub to DECLARE_PCI_FIXUP_SECTION to fix the issue when PREL32 relocations are used. Signed-off-by: Sami Tolvanen Acked-by: Bjorn Helgaas Reviewed-by: Kees Cook Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20201211184633.3213045-10-samitolvanen@google.com --- include/linux/pci.h | 27 +++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index b32126d26997..2276e5d00192 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1917,7 +1917,7 @@ enum pci_fixup_pass { }; #ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS -#define __DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class, \ +#define ___DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class, \ class_shift, hook) \ __ADDRESSABLE(hook) \ asm(".section " #sec ", \"a\" \n" \ @@ -1926,10 +1926,33 @@ enum pci_fixup_pass { ".long " #class ", " #class_shift " \n" \ ".long " #hook " - . \n" \ ".previous \n"); + +/* + * Clang's LTO may rename static functions in C, but has no way to + * handle such renamings when referenced from inline asm. To work + * around this, create global C stubs for these cases. + */ +#ifdef CONFIG_LTO_CLANG +#define __DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class, \ + class_shift, hook, stub) \ + void stub(struct pci_dev *dev); \ + void stub(struct pci_dev *dev) \ + { \ + hook(dev); \ + } \ + ___DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class, \ + class_shift, stub) +#else +#define __DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class, \ + class_shift, hook, stub) \ + ___DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class, \ + class_shift, hook) +#endif + #define DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class, \ class_shift, hook) \ __DECLARE_PCI_FIXUP_SECTION(sec, name, vendor, device, class, \ - class_shift, hook) + class_shift, hook, __UNIQUE_ID(hook)) #else /* Anonymous variables would be nice... */ #define DECLARE_PCI_FIXUP_SECTION(section, name, vendor, device, class, \ -- cgit v1.2.3 From 215b674b84dd052098fe6389e32a5afaff8b4d56 Mon Sep 17 00:00:00 2001 From: Lokesh Gidra Date: Fri, 8 Jan 2021 14:22:20 -0800 Subject: security: add inode_init_security_anon() LSM hook This change adds a new LSM hook, inode_init_security_anon(), that will be used while creating secure anonymous inodes. The hook allows/denies its creation and assigns a security context to the inode. The new hook accepts an optional context_inode parameter that callers can use to provide additional contextual information to security modules for granting/denying permission to create an anon-inode of the same type. This context_inode's security_context can also be used to initialize the newly created anon-inode's security_context. Signed-off-by: Lokesh Gidra Reviewed-by: Eric Biggers Signed-off-by: Paul Moore --- include/linux/lsm_hook_defs.h | 2 ++ include/linux/lsm_hooks.h | 9 +++++++++ include/linux/security.h | 10 ++++++++++ 3 files changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 7aaa753b8608..dfd261dcbcb0 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -113,6 +113,8 @@ LSM_HOOK(void, LSM_RET_VOID, inode_free_security, struct inode *inode) LSM_HOOK(int, 0, inode_init_security, struct inode *inode, struct inode *dir, const struct qstr *qstr, const char **name, void **value, size_t *len) +LSM_HOOK(int, 0, inode_init_security_anon, struct inode *inode, + const struct qstr *name, const struct inode *context_inode) LSM_HOOK(int, 0, inode_create, struct inode *dir, struct dentry *dentry, umode_t mode) LSM_HOOK(int, 0, inode_link, struct dentry *old_dentry, struct inode *dir, diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index a19adef1f088..bdfc8a76a4f7 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -233,6 +233,15 @@ * Returns 0 if @name and @value have been successfully set, * -EOPNOTSUPP if no security attribute is needed, or * -ENOMEM on memory allocation failure. + * @inode_init_security_anon: + * Set up the incore security field for the new anonymous inode + * and return whether the inode creation is permitted by the security + * module or not. + * @inode contains the inode structure + * @name name of the anonymous inode class + * @context_inode optional related inode + * Returns 0 on success, -EACCES if the security module denies the + * creation of this inode, or another -errno upon other errors. * @inode_create: * Check permission to create a regular file. * @dir contains inode structure of the parent of the new file. diff --git a/include/linux/security.h b/include/linux/security.h index c35ea0ffccd9..b0d14f04b16d 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -324,6 +324,9 @@ void security_inode_free(struct inode *inode); int security_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, initxattrs initxattrs, void *fs_data); +int security_inode_init_security_anon(struct inode *inode, + const struct qstr *name, + const struct inode *context_inode); int security_old_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, const char **name, void **value, size_t *len); @@ -738,6 +741,13 @@ static inline int security_inode_init_security(struct inode *inode, return 0; } +static inline int security_inode_init_security_anon(struct inode *inode, + const struct qstr *name, + const struct inode *context_inode) +{ + return 0; +} + static inline int security_old_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, -- cgit v1.2.3 From e7e832ce6fa769f800cd7eaebdb0459ad31e0416 Mon Sep 17 00:00:00 2001 From: Daniel Colascione Date: Fri, 8 Jan 2021 14:22:21 -0800 Subject: fs: add LSM-supporting anon-inode interface This change adds a new function, anon_inode_getfd_secure, that creates anonymous-node file with individual non-S_PRIVATE inode to which security modules can apply policy. Existing callers continue using the original singleton-inode kind of anonymous-inode file. We can transition anonymous inode users to the new kind of anonymous inode in individual patches for the sake of bisection and review. The new function accepts an optional context_inode parameter that callers can use to provide additional contextual information to security modules. For example, in case of userfaultfd, the created inode is a 'logical child' of the context_inode (userfaultfd inode of the parent process) in the sense that it provides the security context required during creation of the child process' userfaultfd inode. Signed-off-by: Daniel Colascione [LG: Delete obsolete comments to alloc_anon_inode()] [LG: Add context_inode description in comments to anon_inode_getfd_secure()] [LG: Remove definition of anon_inode_getfile_secure() as there are no callers] [LG: Make __anon_inode_getfile() static] [LG: Use correct error cast in __anon_inode_getfile()] [LG: Fix error handling in __anon_inode_getfile()] Signed-off-by: Lokesh Gidra Reviewed-by: Eric Biggers Signed-off-by: Paul Moore --- include/linux/anon_inodes.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/anon_inodes.h b/include/linux/anon_inodes.h index d0d7d96261ad..71881a2b6f78 100644 --- a/include/linux/anon_inodes.h +++ b/include/linux/anon_inodes.h @@ -10,12 +10,17 @@ #define _LINUX_ANON_INODES_H struct file_operations; +struct inode; struct file *anon_inode_getfile(const char *name, const struct file_operations *fops, void *priv, int flags); int anon_inode_getfd(const char *name, const struct file_operations *fops, void *priv, int flags); +int anon_inode_getfd_secure(const char *name, + const struct file_operations *fops, + void *priv, int flags, + const struct inode *context_inode); #endif /* _LINUX_ANON_INODES_H */ -- cgit v1.2.3 From b1ae3587d16a8c8fc9453e147c8708d6f006ffbb Mon Sep 17 00:00:00 2001 From: Bjarni Jonasson Date: Wed, 13 Jan 2021 12:56:25 +0100 Subject: net: phy: Add 100 base-x mode Sparx-5 supports this mode and it is missing in the PHY core. Signed-off-by: Bjarni Jonasson Reviewed-by: Russell King Signed-off-by: Jakub Kicinski --- include/linux/phy.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 9effb511acde..24fcc6456a9e 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -104,6 +104,7 @@ extern const int phy_10gbit_features_array[1]; * @PHY_INTERFACE_MODE_MOCA: Multimedia over Coax * @PHY_INTERFACE_MODE_QSGMII: Quad SGMII * @PHY_INTERFACE_MODE_TRGMII: Turbo RGMII + * @PHY_INTERFACE_MODE_100BASEX: 100 BaseX * @PHY_INTERFACE_MODE_1000BASEX: 1000 BaseX * @PHY_INTERFACE_MODE_2500BASEX: 2500 BaseX * @PHY_INTERFACE_MODE_RXAUI: Reduced XAUI @@ -135,6 +136,7 @@ typedef enum { PHY_INTERFACE_MODE_MOCA, PHY_INTERFACE_MODE_QSGMII, PHY_INTERFACE_MODE_TRGMII, + PHY_INTERFACE_MODE_100BASEX, PHY_INTERFACE_MODE_1000BASEX, PHY_INTERFACE_MODE_2500BASEX, PHY_INTERFACE_MODE_RXAUI, @@ -217,6 +219,8 @@ static inline const char *phy_modes(phy_interface_t interface) return "usxgmii"; case PHY_INTERFACE_MODE_10GKR: return "10gbase-kr"; + case PHY_INTERFACE_MODE_100BASEX: + return "100base-x"; default: return "unknown"; } -- cgit v1.2.3 From 91c960b0056672e74627776655c926388350fa30 Mon Sep 17 00:00:00 2001 From: Brendan Jackman Date: Thu, 14 Jan 2021 18:17:44 +0000 Subject: bpf: Rename BPF_XADD and prepare to encode other atomics in .imm MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A subsequent patch will add additional atomic operations. These new operations will use the same opcode field as the existing XADD, with the immediate discriminating different operations. In preparation, rename the instruction mode BPF_ATOMIC and start calling the zero immediate BPF_ADD. This is possible (doesn't break existing valid BPF progs) because the immediate field is currently reserved MBZ and BPF_ADD is zero. All uses are removed from the tree but the BPF_XADD definition is kept around to avoid breaking builds for people including kernel headers. Signed-off-by: Brendan Jackman Signed-off-by: Alexei Starovoitov Acked-by: Björn Töpel Link: https://lore.kernel.org/bpf/20210114181751.768687-5-jackmanb@google.com --- include/linux/filter.h | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 5edf2b660881..392e94b79668 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -259,15 +259,23 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) .off = OFF, \ .imm = 0 }) -/* Atomic memory add, *(uint *)(dst_reg + off16) += src_reg */ -#define BPF_STX_XADD(SIZE, DST, SRC, OFF) \ +/* + * Atomic operations: + * + * BPF_ADD *(uint *) (dst_reg + off16) += src_reg + */ + +#define BPF_ATOMIC_OP(SIZE, OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ - .code = BPF_STX | BPF_SIZE(SIZE) | BPF_XADD, \ + .code = BPF_STX | BPF_SIZE(SIZE) | BPF_ATOMIC, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ - .imm = 0 }) + .imm = OP }) + +/* Legacy alias */ +#define BPF_STX_XADD(SIZE, DST, SRC, OFF) BPF_ATOMIC_OP(SIZE, BPF_ADD, DST, SRC, OFF) /* Memory store, *(uint *) (dst_reg + off16) = imm32 */ -- cgit v1.2.3 From 5ca419f2864a2c60940dcf4bbaeb69546200e36f Mon Sep 17 00:00:00 2001 From: Brendan Jackman Date: Thu, 14 Jan 2021 18:17:46 +0000 Subject: bpf: Add BPF_FETCH field / create atomic_fetch_add instruction The BPF_FETCH field can be set in bpf_insn.imm, for BPF_ATOMIC instructions, in order to have the previous value of the atomically-modified memory location loaded into the src register after an atomic op is carried out. Suggested-by: Yonghong Song Signed-off-by: Brendan Jackman Signed-off-by: Alexei Starovoitov Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20210114181751.768687-7-jackmanb@google.com --- include/linux/filter.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 392e94b79668..23fca41b8540 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -264,6 +264,7 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) * Atomic operations: * * BPF_ADD *(uint *) (dst_reg + off16) += src_reg + * BPF_ADD | BPF_FETCH src_reg = atomic_fetch_add(dst_reg + off16, src_reg); */ #define BPF_ATOMIC_OP(SIZE, OP, DST, SRC, OFF) \ -- cgit v1.2.3 From 5ffa25502b5ab3d639829a2d1e316cff7f59a41e Mon Sep 17 00:00:00 2001 From: Brendan Jackman Date: Thu, 14 Jan 2021 18:17:47 +0000 Subject: bpf: Add instructions for atomic_[cmp]xchg This adds two atomic opcodes, both of which include the BPF_FETCH flag. XCHG without the BPF_FETCH flag would naturally encode atomic_set. This is not supported because it would be of limited value to userspace (it doesn't imply any barriers). CMPXCHG without BPF_FETCH woulud be an atomic compare-and-write. We don't have such an operation in the kernel so it isn't provided to BPF either. There are two significant design decisions made for the CMPXCHG instruction: - To solve the issue that this operation fundamentally has 3 operands, but we only have two register fields. Therefore the operand we compare against (the kernel's API calls it 'old') is hard-coded to be R0. x86 has similar design (and A64 doesn't have this problem). A potential alternative might be to encode the other operand's register number in the immediate field. - The kernel's atomic_cmpxchg returns the old value, while the C11 userspace APIs return a boolean indicating the comparison result. Which should BPF do? A64 returns the old value. x86 returns the old value in the hard-coded register (and also sets a flag). That means return-old-value is easier to JIT, so that's what we use. Signed-off-by: Brendan Jackman Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210114181751.768687-8-jackmanb@google.com --- include/linux/filter.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 23fca41b8540..d563820f197d 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -265,6 +265,8 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) * * BPF_ADD *(uint *) (dst_reg + off16) += src_reg * BPF_ADD | BPF_FETCH src_reg = atomic_fetch_add(dst_reg + off16, src_reg); + * BPF_XCHG src_reg = atomic_xchg(dst_reg + off16, src_reg) + * BPF_CMPXCHG r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg) */ #define BPF_ATOMIC_OP(SIZE, OP, DST, SRC, OFF) \ -- cgit v1.2.3 From 981f94c3e92146705baf97fb417a5ed1ab1a79a5 Mon Sep 17 00:00:00 2001 From: Brendan Jackman Date: Thu, 14 Jan 2021 18:17:49 +0000 Subject: bpf: Add bitwise atomic instructions This adds instructions for atomic[64]_[fetch_]and atomic[64]_[fetch_]or atomic[64]_[fetch_]xor All these operations are isomorphic enough to implement with the same verifier, interpreter, and x86 JIT code, hence being a single commit. The main interesting thing here is that x86 doesn't directly support the fetch_ version these operations, so we need to generate a CMPXCHG loop in the JIT. This requires the use of two temporary registers, IIUC it's safe to use BPF_REG_AX and x86's AUX_REG for this purpose. Signed-off-by: Brendan Jackman Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210114181751.768687-10-jackmanb@google.com --- include/linux/filter.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index d563820f197d..7fdce5407214 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -264,7 +264,13 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) * Atomic operations: * * BPF_ADD *(uint *) (dst_reg + off16) += src_reg + * BPF_AND *(uint *) (dst_reg + off16) &= src_reg + * BPF_OR *(uint *) (dst_reg + off16) |= src_reg + * BPF_XOR *(uint *) (dst_reg + off16) ^= src_reg * BPF_ADD | BPF_FETCH src_reg = atomic_fetch_add(dst_reg + off16, src_reg); + * BPF_AND | BPF_FETCH src_reg = atomic_fetch_and(dst_reg + off16, src_reg); + * BPF_OR | BPF_FETCH src_reg = atomic_fetch_or(dst_reg + off16, src_reg); + * BPF_XOR | BPF_FETCH src_reg = atomic_fetch_xor(dst_reg + off16, src_reg); * BPF_XCHG src_reg = atomic_xchg(dst_reg + off16, src_reg) * BPF_CMPXCHG r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg) */ -- cgit v1.2.3 From bd7525dacd7e204f8cae061941fb9001c89d6988 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 14 Jan 2021 14:40:42 +0100 Subject: bpf: Move stack_map_get_build_id into lib Moving stack_map_get_build_id into lib with declaration in linux/buildid.h header: int build_id_parse(struct vm_area_struct *vma, unsigned char *build_id); This function returns build id for given struct vm_area_struct. There is no functional change to stack_map_get_build_id function. Signed-off-by: Jiri Olsa Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20210114134044.1418404-2-jolsa@kernel.org --- include/linux/buildid.h | 11 +++++++++++ 1 file changed, 11 insertions(+) create mode 100644 include/linux/buildid.h (limited to 'include/linux') diff --git a/include/linux/buildid.h b/include/linux/buildid.h new file mode 100644 index 000000000000..08028a212589 --- /dev/null +++ b/include/linux/buildid.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_BUILDID_H +#define _LINUX_BUILDID_H + +#include + +#define BUILD_ID_SIZE_MAX 20 + +int build_id_parse(struct vm_area_struct *vma, unsigned char *build_id); + +#endif -- cgit v1.2.3 From 921f88fc891922b325b3668cd026a386571ed602 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 14 Jan 2021 14:40:43 +0100 Subject: bpf: Add size arg to build_id_parse function It's possible to have other build id types (other than default SHA1). Currently there's also ld support for MD5 build id. Adding size argument to build_id_parse function, that returns (if defined) size of the parsed build id, so we can recognize the build id type. Signed-off-by: Jiri Olsa Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20210114134044.1418404-3-jolsa@kernel.org --- include/linux/buildid.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/buildid.h b/include/linux/buildid.h index 08028a212589..40232f90db6e 100644 --- a/include/linux/buildid.h +++ b/include/linux/buildid.h @@ -6,6 +6,7 @@ #define BUILD_ID_SIZE_MAX 20 -int build_id_parse(struct vm_area_struct *vma, unsigned char *build_id); +int build_id_parse(struct vm_area_struct *vma, unsigned char *build_id, + __u32 *size); #endif -- cgit v1.2.3 From d6e645012d97164609260ac567b304681734c5e2 Mon Sep 17 00:00:00 2001 From: Tushar Sugandhi Date: Thu, 7 Jan 2021 20:07:03 -0800 Subject: IMA: define a hook to measure kernel integrity critical data IMA provides capabilities to measure file and buffer data. However, various data structures, policies, and states stored in kernel memory also impact the integrity of the system. Several kernel subsystems contain such integrity critical data. These kernel subsystems help protect the integrity of the system. Currently, IMA does not provide a generic function for measuring kernel integrity critical data. Define ima_measure_critical_data, a new IMA hook, to measure kernel integrity critical data. Signed-off-by: Tushar Sugandhi Reviewed-by: Tyler Hicks Signed-off-by: Mimi Zohar --- include/linux/ima.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ima.h b/include/linux/ima.h index 7db9cca1af34..59bd90ac3c35 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -31,6 +31,9 @@ extern void ima_post_path_mknod(struct dentry *dentry); extern int ima_file_hash(struct file *file, char *buf, size_t buf_size); extern int ima_inode_hash(struct inode *inode, char *buf, size_t buf_size); extern void ima_kexec_cmdline(int kernel_fd, const void *buf, int size); +extern void ima_measure_critical_data(const char *event_name, + const void *buf, size_t buf_len, + bool hash); #ifdef CONFIG_IMA_APPRAISE_BOOTPARAM extern void ima_appraise_parse_cmdline(void); @@ -128,6 +131,10 @@ static inline int ima_inode_hash(struct inode *inode, char *buf, size_t buf_size } static inline void ima_kexec_cmdline(int kernel_fd, const void *buf, int size) {} + +static inline void ima_measure_critical_data(const char *event_name, + const void *buf, size_t buf_len, + bool hash) {} #endif /* CONFIG_IMA */ #ifndef CONFIG_IMA_KEXEC -- cgit v1.2.3 From 9f5d7d23cc5ec61a92076b73665fcb9aaa5bb5a0 Mon Sep 17 00:00:00 2001 From: Tushar Sugandhi Date: Thu, 7 Jan 2021 20:07:06 -0800 Subject: IMA: extend critical data hook to limit the measurement based on a label The IMA hook ima_measure_critical_data() does not support a way to specify the source of the critical data provider. Thus, the data measurement cannot be constrained based on the data source label in the IMA policy. Extend the IMA hook ima_measure_critical_data() to support passing the data source label as an input parameter, so that the policy rule can be used to limit the measurements based on the label. Signed-off-by: Tushar Sugandhi Reviewed-by: Tyler Hicks Signed-off-by: Mimi Zohar --- include/linux/ima.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ima.h b/include/linux/ima.h index 59bd90ac3c35..2ac834badbbe 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -31,7 +31,8 @@ extern void ima_post_path_mknod(struct dentry *dentry); extern int ima_file_hash(struct file *file, char *buf, size_t buf_size); extern int ima_inode_hash(struct inode *inode, char *buf, size_t buf_size); extern void ima_kexec_cmdline(int kernel_fd, const void *buf, int size); -extern void ima_measure_critical_data(const char *event_name, +extern void ima_measure_critical_data(const char *event_label, + const char *event_name, const void *buf, size_t buf_len, bool hash); @@ -132,9 +133,11 @@ static inline int ima_inode_hash(struct inode *inode, char *buf, size_t buf_size static inline void ima_kexec_cmdline(int kernel_fd, const void *buf, int size) {} -static inline void ima_measure_critical_data(const char *event_name, +static inline void ima_measure_critical_data(const char *event_label, + const char *event_name, const void *buf, size_t buf_len, bool hash) {} + #endif /* CONFIG_IMA */ #ifndef CONFIG_IMA_KEXEC -- cgit v1.2.3 From 3c15e00e7b58bc2b37e53d2612f0a0163281be77 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Thu, 26 Nov 2020 11:41:42 +0100 Subject: mfd/bus: sunxi-rsb: Make .remove() callback return void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver core ignores the return value of struct device_driver::remove because there is only little that can be done. To simplify the quest to make this function return void, let struct sunxi_rsb_driver::remove return void, too. All users already unconditionally return 0, this commit makes this obvious and ensures future users don't behave differently. To simplify even further, make axp20x_device_remove() return void instead of returning 0 unconditionally, too. Signed-off-by: Uwe Kleine-König Reviewed-by: Chen-Yu Tsai Signed-off-by: Lee Jones --- include/linux/mfd/axp20x.h | 2 +- include/linux/sunxi-rsb.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/axp20x.h b/include/linux/mfd/axp20x.h index fd5957c042da..9ab0e2fca7ea 100644 --- a/include/linux/mfd/axp20x.h +++ b/include/linux/mfd/axp20x.h @@ -696,6 +696,6 @@ int axp20x_device_probe(struct axp20x_dev *axp20x); * * This tells the axp20x core to remove the associated mfd devices */ -int axp20x_device_remove(struct axp20x_dev *axp20x); +void axp20x_device_remove(struct axp20x_dev *axp20x); #endif /* __LINUX_MFD_AXP20X_H */ diff --git a/include/linux/sunxi-rsb.h b/include/linux/sunxi-rsb.h index 7e75bb0346d0..bf0d365f471c 100644 --- a/include/linux/sunxi-rsb.h +++ b/include/linux/sunxi-rsb.h @@ -59,7 +59,7 @@ static inline void sunxi_rsb_device_set_drvdata(struct sunxi_rsb_device *rdev, struct sunxi_rsb_driver { struct device_driver driver; int (*probe)(struct sunxi_rsb_device *rdev); - int (*remove)(struct sunxi_rsb_device *rdev); + void (*remove)(struct sunxi_rsb_device *rdev); }; static inline struct sunxi_rsb_driver *to_sunxi_rsb_driver(struct device_driver *d) -- cgit v1.2.3 From e68d0119e3284334de5650a1ac42ef4e179f895e Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Fri, 15 Jan 2021 12:49:11 +0300 Subject: software node: Introduce device_add_software_node() This helper will register a software node and then assign it to device at the same time. The function will also make sure that the device can't have more than one software node. Acked-by: Felipe Balbi Signed-off-by: Heikki Krogerus Link: https://lore.kernel.org/r/20210115094914.88401-2-heikki.krogerus@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/property.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index 0a9001fe7aea..b0e413dc5927 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -488,4 +488,7 @@ fwnode_create_software_node(const struct property_entry *properties, const struct fwnode_handle *parent); void fwnode_remove_software_node(struct fwnode_handle *fwnode); +int device_add_software_node(struct device *dev, const struct software_node *swnode); +void device_remove_software_node(struct device *dev); + #endif /* _LINUX_PROPERTY_H_ */ -- cgit v1.2.3 From 429b29aef7f841086949c7359f9c3ccb051e7ea3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 15 Jan 2021 16:51:29 +0100 Subject: tty: serial: Drop unused efm32 serial driver MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Support for this machine was just removed, so drop the now unused UART driver, too. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20210115155130.185010-7-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- include/linux/platform_data/efm32-uart.h | 19 ------------------- 1 file changed, 19 deletions(-) delete mode 100644 include/linux/platform_data/efm32-uart.h (limited to 'include/linux') diff --git a/include/linux/platform_data/efm32-uart.h b/include/linux/platform_data/efm32-uart.h deleted file mode 100644 index ccbb8f11db75..000000000000 --- a/include/linux/platform_data/efm32-uart.h +++ /dev/null @@ -1,19 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * - * - */ -#ifndef __LINUX_PLATFORM_DATA_EFM32_UART_H__ -#define __LINUX_PLATFORM_DATA_EFM32_UART_H__ - -#include - -/** - * struct efm32_uart_pdata - * @location: pinmux location for the I/O pins (to be written to the ROUTE - * register) - */ -struct efm32_uart_pdata { - u8 location; -}; -#endif /* ifndef __LINUX_PLATFORM_DATA_EFM32_UART_H__ */ -- cgit v1.2.3 From 0ba882ae2818193487b70ad39622973538711d9a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Thu, 14 Jan 2021 16:16:27 +0100 Subject: spi: Drop unused efm32 bus driver MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Support for this machine was just removed, so drop the now unused spi bus driver, too. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20210114151630.128830-5-u.kleine-koenig@pengutronix.de Signed-off-by: Mark Brown --- include/linux/platform_data/efm32-spi.h | 15 --------------- 1 file changed, 15 deletions(-) delete mode 100644 include/linux/platform_data/efm32-spi.h (limited to 'include/linux') diff --git a/include/linux/platform_data/efm32-spi.h b/include/linux/platform_data/efm32-spi.h deleted file mode 100644 index a2c56fcd0534..000000000000 --- a/include/linux/platform_data/efm32-spi.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __LINUX_PLATFORM_DATA_EFM32_SPI_H__ -#define __LINUX_PLATFORM_DATA_EFM32_SPI_H__ - -#include - -/** - * struct efm32_spi_pdata - * @location: pinmux location for the I/O pins (to be written to the ROUTE - * register) - */ -struct efm32_spi_pdata { - u8 location; -}; -#endif /* ifndef __LINUX_PLATFORM_DATA_EFM32_SPI_H__ */ -- cgit v1.2.3 From 8d502ef682fdbe0ddf2274dae903b07baf1140e0 Mon Sep 17 00:00:00 2001 From: Craig Tatlor Date: Fri, 4 Dec 2020 05:54:56 +0300 Subject: fixp-arith: add a linear interpolation function Adds a function to interpolate against two points, this is carried arount as a helper function by tons of drivers. Signed-off-by: Craig Tatlor Signed-off-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20201204025509.1075506-3-dmitry.baryshkov@linaro.org Signed-off-by: Jonathan Cameron --- include/linux/fixp-arith.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fixp-arith.h b/include/linux/fixp-arith.h index 8396013785ef..281cb4f83dbe 100644 --- a/include/linux/fixp-arith.h +++ b/include/linux/fixp-arith.h @@ -141,4 +141,23 @@ static inline s32 fixp_sin32_rad(u32 radians, u32 twopi) #define fixp_cos32_rad(rad, twopi) \ fixp_sin32_rad(rad + twopi / 4, twopi) +/** + * fixp_linear_interpolate() - interpolates a value from two known points + * + * @x0: x value of point 0 + * @y0: y value of point 0 + * @x1: x value of point 1 + * @y1: y value of point 1 + * @x: the linear interpolant + */ +static inline int fixp_linear_interpolate(int x0, int y0, int x1, int y1, int x) +{ + if (y0 == y1 || x == x0) + return y0; + if (x1 == x0 || x == x1) + return y1; + + return y0 + ((y1 - y0) * (x - x0) / (x1 - x0)); +} + #endif -- cgit v1.2.3 From ec82edb258bbf0233306cc45f65d4b6092243ee9 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Fri, 4 Dec 2020 05:54:59 +0300 Subject: iio: adc: move qcom-vadc-common.h to include dir qcom-vadc-common module will be used by ADC thermal monitoring driver, so move it to global include dir. Signed-off-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20201204025509.1075506-6-dmitry.baryshkov@linaro.org Signed-off-by: Jonathan Cameron --- include/linux/iio/adc/qcom-vadc-common.h | 187 +++++++++++++++++++++++++++++++ 1 file changed, 187 insertions(+) create mode 100644 include/linux/iio/adc/qcom-vadc-common.h (limited to 'include/linux') diff --git a/include/linux/iio/adc/qcom-vadc-common.h b/include/linux/iio/adc/qcom-vadc-common.h new file mode 100644 index 000000000000..03a9119edc71 --- /dev/null +++ b/include/linux/iio/adc/qcom-vadc-common.h @@ -0,0 +1,187 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Code shared between the different Qualcomm PMIC voltage ADCs + */ + +#ifndef QCOM_VADC_COMMON_H +#define QCOM_VADC_COMMON_H + +#include + +#define VADC_CONV_TIME_MIN_US 2000 +#define VADC_CONV_TIME_MAX_US 2100 + +/* Min ADC code represents 0V */ +#define VADC_MIN_ADC_CODE 0x6000 +/* Max ADC code represents full-scale range of 1.8V */ +#define VADC_MAX_ADC_CODE 0xa800 + +#define VADC_ABSOLUTE_RANGE_UV 625000 +#define VADC_RATIOMETRIC_RANGE 1800 + +#define VADC_DEF_PRESCALING 0 /* 1:1 */ +#define VADC_DEF_DECIMATION 0 /* 512 */ +#define VADC_DEF_HW_SETTLE_TIME 0 /* 0 us */ +#define VADC_DEF_AVG_SAMPLES 0 /* 1 sample */ +#define VADC_DEF_CALIB_TYPE VADC_CALIB_ABSOLUTE + +#define VADC_DECIMATION_MIN 512 +#define VADC_DECIMATION_MAX 4096 +#define ADC5_DEF_VBAT_PRESCALING 1 /* 1:3 */ +#define ADC5_DECIMATION_SHORT 250 +#define ADC5_DECIMATION_MEDIUM 420 +#define ADC5_DECIMATION_LONG 840 +/* Default decimation - 1024 for rev2, 840 for pmic5 */ +#define ADC5_DECIMATION_DEFAULT 2 +#define ADC5_DECIMATION_SAMPLES_MAX 3 + +#define VADC_HW_SETTLE_DELAY_MAX 10000 +#define VADC_HW_SETTLE_SAMPLES_MAX 16 +#define VADC_AVG_SAMPLES_MAX 512 +#define ADC5_AVG_SAMPLES_MAX 16 + +#define PMIC5_CHG_TEMP_SCALE_FACTOR 377500 +#define PMIC5_SMB_TEMP_CONSTANT 419400 +#define PMIC5_SMB_TEMP_SCALE_FACTOR 356 + +#define PMI_CHG_SCALE_1 -138890 +#define PMI_CHG_SCALE_2 391750000000LL + +#define VADC5_MAX_CODE 0x7fff +#define ADC5_FULL_SCALE_CODE 0x70e4 +#define ADC5_USR_DATA_CHECK 0x8000 + +#define R_PU_100K 100000 +#define RATIO_MAX_ADC7 BIT(14) + +#define DIE_TEMP_ADC7_SCALE_1 -60000 +#define DIE_TEMP_ADC7_SCALE_2 20000 +#define DIE_TEMP_ADC7_SCALE_FACTOR 1000 +#define DIE_TEMP_ADC7_MAX 160000 + +/** + * struct vadc_map_pt - Map the graph representation for ADC channel + * @x: Represent the ADC digitized code. + * @y: Represent the physical data which can be temperature, voltage, + * resistance. + */ +struct vadc_map_pt { + s32 x; + s32 y; +}; + +/* + * VADC_CALIB_ABSOLUTE: uses the 625mV and 1.25V as reference channels. + * VADC_CALIB_RATIOMETRIC: uses the reference voltage (1.8V) and GND for + * calibration. + */ +enum vadc_calibration { + VADC_CALIB_ABSOLUTE = 0, + VADC_CALIB_RATIOMETRIC +}; + +/** + * struct vadc_linear_graph - Represent ADC characteristics. + * @dy: numerator slope to calculate the gain. + * @dx: denominator slope to calculate the gain. + * @gnd: A/D word of the ground reference used for the channel. + * + * Each ADC device has different offset and gain parameters which are + * computed to calibrate the device. + */ +struct vadc_linear_graph { + s32 dy; + s32 dx; + s32 gnd; +}; + +/** + * struct vadc_prescale_ratio - Represent scaling ratio for ADC input. + * @num: the inverse numerator of the gain applied to the input channel. + * @den: the inverse denominator of the gain applied to the input channel. + */ +struct vadc_prescale_ratio { + u32 num; + u32 den; +}; + +/** + * enum vadc_scale_fn_type - Scaling function to convert ADC code to + * physical scaled units for the channel. + * SCALE_DEFAULT: Default scaling to convert raw adc code to voltage (uV). + * SCALE_THERM_100K_PULLUP: Returns temperature in millidegC. + * Uses a mapping table with 100K pullup. + * SCALE_PMIC_THERM: Returns result in milli degree's Centigrade. + * SCALE_XOTHERM: Returns XO thermistor voltage in millidegC. + * SCALE_PMI_CHG_TEMP: Conversion for PMI CHG temp + * SCALE_HW_CALIB_DEFAULT: Default scaling to convert raw adc code to + * voltage (uV) with hardware applied offset/slope values to adc code. + * SCALE_HW_CALIB_THERM_100K_PULLUP: Returns temperature in millidegC using + * lookup table. The hardware applies offset/slope to adc code. + * SCALE_HW_CALIB_XOTHERM: Returns XO thermistor voltage in millidegC using + * 100k pullup. The hardware applies offset/slope to adc code. + * SCALE_HW_CALIB_THERM_100K_PU_PM7: Returns temperature in millidegC using + * lookup table for PMIC7. The hardware applies offset/slope to adc code. + * SCALE_HW_CALIB_PMIC_THERM: Returns result in milli degree's Centigrade. + * The hardware applies offset/slope to adc code. + * SCALE_HW_CALIB_PMIC_THERM: Returns result in milli degree's Centigrade. + * The hardware applies offset/slope to adc code. This is for PMIC7. + * SCALE_HW_CALIB_PM5_CHG_TEMP: Returns result in millidegrees for PMIC5 + * charger temperature. + * SCALE_HW_CALIB_PM5_SMB_TEMP: Returns result in millidegrees for PMIC5 + * SMB1390 temperature. + */ +enum vadc_scale_fn_type { + SCALE_DEFAULT = 0, + SCALE_THERM_100K_PULLUP, + SCALE_PMIC_THERM, + SCALE_XOTHERM, + SCALE_PMI_CHG_TEMP, + SCALE_HW_CALIB_DEFAULT, + SCALE_HW_CALIB_THERM_100K_PULLUP, + SCALE_HW_CALIB_XOTHERM, + SCALE_HW_CALIB_THERM_100K_PU_PM7, + SCALE_HW_CALIB_PMIC_THERM, + SCALE_HW_CALIB_PMIC_THERM_PM7, + SCALE_HW_CALIB_PM5_CHG_TEMP, + SCALE_HW_CALIB_PM5_SMB_TEMP, + SCALE_HW_CALIB_INVALID, +}; + +struct adc5_data { + const u32 full_scale_code_volt; + const u32 full_scale_code_cur; + const struct adc5_channels *adc_chans; + const struct iio_info *info; + unsigned int *decimation; + unsigned int *hw_settle_1; + unsigned int *hw_settle_2; +}; + +int qcom_vadc_scale(enum vadc_scale_fn_type scaletype, + const struct vadc_linear_graph *calib_graph, + const struct vadc_prescale_ratio *prescale, + bool absolute, + u16 adc_code, int *result_mdec); + +struct qcom_adc5_scale_type { + int (*scale_fn)(const struct vadc_prescale_ratio *prescale, + const struct adc5_data *data, u16 adc_code, int *result); +}; + +int qcom_adc5_hw_scale(enum vadc_scale_fn_type scaletype, + unsigned int prescale_ratio, + const struct adc5_data *data, + u16 adc_code, int *result_mdec); + +int qcom_adc5_prescaling_from_dt(u32 num, u32 den); + +int qcom_adc5_hw_settle_time_from_dt(u32 value, const unsigned int *hw_settle); + +int qcom_adc5_avg_samples_from_dt(u32 value); + +int qcom_adc5_decimation_from_dt(u32 value, const unsigned int *decimation); + +int qcom_vadc_decimation_from_dt(u32 value); + +#endif /* QCOM_VADC_COMMON_H */ -- cgit v1.2.3 From 6e39b145cef7577cd6b550e633155e5fc1e5838e Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Fri, 4 Dec 2020 05:55:01 +0300 Subject: iio: provide of_iio_channel_get_by_name() and devm_ version it There might be cases when the IIO channel is attached to the device subnode instead of being attached to the main device node. Allow drivers to query IIO channels by using device tree nodes. Signed-off-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20201204025509.1075506-8-dmitry.baryshkov@linaro.org Signed-off-by: Jonathan Cameron --- include/linux/iio/consumer.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/consumer.h b/include/linux/iio/consumer.h index c4118dcb8e05..0a90ba8fa1bb 100644 --- a/include/linux/iio/consumer.h +++ b/include/linux/iio/consumer.h @@ -13,6 +13,7 @@ struct iio_dev; struct iio_chan_spec; struct device; +struct device_node; /** * struct iio_channel - everything needed for a consumer to use a channel @@ -97,6 +98,41 @@ void iio_channel_release_all(struct iio_channel *chan); */ struct iio_channel *devm_iio_channel_get_all(struct device *dev); +/** + * of_iio_channel_get_by_name() - get description of all that is needed to access channel. + * @np: Pointer to consumer device tree node + * @consumer_channel: Unique name to identify the channel on the consumer + * side. This typically describes the channels use within + * the consumer. E.g. 'battery_voltage' + */ +#ifdef CONFIG_OF +struct iio_channel *of_iio_channel_get_by_name(struct device_node *np, const char *name); +#else +static inline struct iio_channel * +of_iio_channel_get_by_name(struct device_node *np, const char *name) +{ + return NULL; +} +#endif + +/** + * devm_of_iio_channel_get_by_name() - Resource managed version of of_iio_channel_get_by_name(). + * @dev: Pointer to consumer device. + * @np: Pointer to consumer device tree node + * @consumer_channel: Unique name to identify the channel on the consumer + * side. This typically describes the channels use within + * the consumer. E.g. 'battery_voltage' + * + * Returns a pointer to negative errno if it is not able to get the iio channel + * otherwise returns valid pointer for iio channel. + * + * The allocated iio channel is automatically released when the device is + * unbound. + */ +struct iio_channel *devm_of_iio_channel_get_by_name(struct device *dev, + struct device_node *np, + const char *consumer_channel); + struct iio_cb_buffer; /** * iio_channel_get_all_cb() - register callback for triggered capture -- cgit v1.2.3 From bb01e263743293d37148f1fa00e3ea04dca416a5 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Fri, 4 Dec 2020 05:55:02 +0300 Subject: iio: adc: move vadc_map_pt from header to the source file struct vadc_map_pt is not used outside of qcom-vadc-common.c, so move it there from the global header file. Signed-off-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20201204025509.1075506-9-dmitry.baryshkov@linaro.org Signed-off-by: Jonathan Cameron --- include/linux/iio/adc/qcom-vadc-common.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/adc/qcom-vadc-common.h b/include/linux/iio/adc/qcom-vadc-common.h index 03a9119edc71..1d337dd9e3dc 100644 --- a/include/linux/iio/adc/qcom-vadc-common.h +++ b/include/linux/iio/adc/qcom-vadc-common.h @@ -59,17 +59,6 @@ #define DIE_TEMP_ADC7_SCALE_FACTOR 1000 #define DIE_TEMP_ADC7_MAX 160000 -/** - * struct vadc_map_pt - Map the graph representation for ADC channel - * @x: Represent the ADC digitized code. - * @y: Represent the physical data which can be temperature, voltage, - * resistance. - */ -struct vadc_map_pt { - s32 x; - s32 y; -}; - /* * VADC_CALIB_ABSOLUTE: uses the 625mV and 1.25V as reference channels. * VADC_CALIB_RATIOMETRIC: uses the reference voltage (1.8V) and GND for -- cgit v1.2.3 From 3bd0ceb566f700adc5d164f431d1da039374aa97 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Fri, 4 Dec 2020 05:55:03 +0300 Subject: iio: adc: qcom-vadc-common: rewrite vadc7 die temp calculation qcom_vadc7_scale_hw_calib_die_temp() uses a table format different from the rest of volt/temp conversion functions in this file. Also the conversion functions results in non-monothonic values conversion, which seems wrong. Rewrite qcom_vadc7_scale_hw_calib_die_temp() to use qcom_vadc_map_voltage_temp() directly, like the rest of conversion functions do. Signed-off-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20201204025509.1075506-10-dmitry.baryshkov@linaro.org Signed-off-by: Jonathan Cameron --- include/linux/iio/adc/qcom-vadc-common.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/adc/qcom-vadc-common.h b/include/linux/iio/adc/qcom-vadc-common.h index 1d337dd9e3dc..58216124d89d 100644 --- a/include/linux/iio/adc/qcom-vadc-common.h +++ b/include/linux/iio/adc/qcom-vadc-common.h @@ -54,11 +54,6 @@ #define R_PU_100K 100000 #define RATIO_MAX_ADC7 BIT(14) -#define DIE_TEMP_ADC7_SCALE_1 -60000 -#define DIE_TEMP_ADC7_SCALE_2 20000 -#define DIE_TEMP_ADC7_SCALE_FACTOR 1000 -#define DIE_TEMP_ADC7_MAX 160000 - /* * VADC_CALIB_ABSOLUTE: uses the 625mV and 1.25V as reference channels. * VADC_CALIB_RATIOMETRIC: uses the reference voltage (1.8V) and GND for -- cgit v1.2.3 From bca585d24a1719d9314d5438b0d2804a33d9bbb6 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 5 Jan 2021 14:13:52 -0500 Subject: new helper: d_find_alias_rcu() similar to d_find_alias(inode), except that * the caller must be holding rcu_read_lock() * inode must not be freed until matching rcu_read_unlock() * result is *NOT* pinned and can only be dereferenced until the matching rcu_read_unlock(). Signed-off-by: Al Viro --- include/linux/dcache.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index d7b369fc15d3..c1e48014106f 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -262,6 +262,8 @@ extern void d_tmpfile(struct dentry *, struct inode *); extern struct dentry *d_find_alias(struct inode *); extern void d_prune_aliases(struct inode *); +extern struct dentry *d_find_alias_rcu(struct inode *); + /* test whether we have any submounts in a subdir tree */ extern int path_has_submounts(const struct path *); -- cgit v1.2.3 From 7ae41220ef5831674f446baef19bfe1b31358260 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Mon, 11 Jan 2021 00:17:36 +0100 Subject: rtc: introduce features bitfield Introduce a bitfield to allow the drivers to announce the available features for an RTC. The main use case would be to better handle alarms, that could be present or not or have a minute resolution or may need a correct week day to be set. Use the newly introduced RTC_FEATURE_ALARM bit to then test whether alarms are available instead of relying on the presence of ops->set_alarm. Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20210110231752.1418816-2-alexandre.belloni@bootlin.com --- include/linux/rtc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 568909449c13..bd611e26291d 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -141,6 +141,8 @@ struct rtc_device { */ unsigned long set_offset_nsec; + unsigned long features[BITS_TO_LONGS(RTC_FEATURE_CNT)]; + time64_t range_min; timeu64_t range_max; time64_t start_secs; -- cgit v1.2.3 From 61712a5f8271ebdbb9d34d28279b77a452db9d5c Mon Sep 17 00:00:00 2001 From: Yue Zou Date: Mon, 18 Jan 2021 01:03:55 +0000 Subject: vgaarb: Remove unneeded semicolons Remove superfluous semicolons after function definitions. Signed-off-by: Yue Zou Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210118010356.214491-1-zouyue3@huawei.com --- include/linux/vgaarb.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vgaarb.h b/include/linux/vgaarb.h index 977caf96c8d2..fc6dfeba04a5 100644 --- a/include/linux/vgaarb.h +++ b/include/linux/vgaarb.h @@ -121,9 +121,9 @@ extern struct pci_dev *vga_default_device(void); extern void vga_set_default_device(struct pci_dev *pdev); extern int vga_remove_vgacon(struct pci_dev *pdev); #else -static inline struct pci_dev *vga_default_device(void) { return NULL; }; -static inline void vga_set_default_device(struct pci_dev *pdev) { }; -static inline int vga_remove_vgacon(struct pci_dev *pdev) { return 0; }; +static inline struct pci_dev *vga_default_device(void) { return NULL; } +static inline void vga_set_default_device(struct pci_dev *pdev) { } +static inline int vga_remove_vgacon(struct pci_dev *pdev) { return 0; } #endif /* -- cgit v1.2.3 From 8ff059b8531f3b98e14f0461859fc7cdd95823e4 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Mon, 18 Jan 2021 13:38:42 +0100 Subject: efi: ia64: move IA64-only declarations to new asm/efi.h header Move some EFI related declarations that are only referenced on IA64 to a new asm/efi.h arch header. Cc: Tony Luck Cc: Fenghua Yu Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 763b816ba19c..0c31af36697c 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -167,8 +167,6 @@ struct capsule_info { int __efi_capsule_setup_info(struct capsule_info *cap_info); -typedef int (*efi_freemem_callback_t) (u64 start, u64 end, void *arg); - /* * Types and defines for Time Services */ @@ -605,10 +603,6 @@ efi_guid_to_str(efi_guid_t *guid, char *out) } extern void efi_init (void); -extern void *efi_get_pal_addr (void); -extern void efi_map_pal_code (void); -extern void efi_memmap_walk (efi_freemem_callback_t callback, void *arg); -extern void efi_gettimeofday (struct timespec64 *ts); #ifdef CONFIG_EFI extern void efi_enter_virtual_mode (void); /* switch EFI to virtual mode, if possible */ #else -- cgit v1.2.3 From 84335675f2223cbd25d0de7d38ecc7d40b95bd4a Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 15 Jan 2021 17:47:39 +0100 Subject: dma-buf: Add debug option MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We have too many people abusing the struct page they can get at but really shouldn't in importers. Aside from that the backing page might simply not exist (for dynamic p2p mappings) looking at it and using it e.g. for mmap can also wreak the page handling of the exporter completely. Importers really must go through the proper interface like dma_buf_mmap for everything. I'm semi-tempted to enforce this for dynamic importers since those really have no excuse at all to break the rules. Unfortuantely we can't store the right pointers somewhere safe to make sure we oops on something recognizable, so best is to just wrangle them a bit by flipping all the bits. At least on x86 kernel addresses have all their high bits sets and the struct page array is fairly low in the kernel mapping, so flipping all the bits gives us a very high pointer in userspace and hence excellent chances for an invalid dereference. v2: Add a note to the @map_dma_buf hook that exporters shouldn't do fancy caching tricks, which would blow up with this address scrambling trick here (Chris) Enable by default when CONFIG_DMA_API_DEBUG is enabled. v3: Only one copy of the mangle/unmangle code (Christian) v4: #ifdef, not #if (0day) v5: sg_table can also be an ERR_PTR (Chris, Christian) Reviewed-by: Chris Wilson Reviewed-by: Christian König Signed-off-by: Daniel Vetter Cc: Chris Wilson Cc: Sumit Semwal Cc: "Christian König" Cc: David Stevens Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Link: https://patchwork.freedesktop.org/patch/msgid/20210115164739.3958206-1-daniel.vetter@ffwll.ch --- include/linux/dma-buf.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 628681bf6c99..efdc56b9d95f 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -154,6 +154,12 @@ struct dma_buf_ops { * On failure, returns a negative error value wrapped into a pointer. * May also return -EINTR when a signal was received while being * blocked. + * + * Note that exporters should not try to cache the scatter list, or + * return the same one for multiple calls. Caching is done either by the + * DMA-BUF code (for non-dynamic importers) or the importer. Ownership + * of the scatter list is transferred to the caller, and returned by + * @unmap_dma_buf. */ struct sg_table * (*map_dma_buf)(struct dma_buf_attachment *, enum dma_data_direction); -- cgit v1.2.3 From 1b399bb04837183cecdc1b32ef1cfc7fcfa75d32 Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Sun, 13 Dec 2020 23:54:46 +0000 Subject: kconfig.h: Add IF_ENABLED() macro IF_ENABLED(CONFIG_FOO, ptr) evaluates to (ptr) if CONFIG_FOO is set to 'y' or 'm', NULL otherwise. The (ptr) argument must be a pointer. The IF_ENABLED() macro can be very useful to help GCC drop dead code. For instance, consider the following: #ifdef CONFIG_FOO_SUSPEND static int foo_suspend(struct device *dev) { ... } #endif static struct pm_ops foo_ops = { #ifdef CONFIG_FOO_SUSPEND .suspend = foo_suspend, #endif }; While this works, the foo_suspend() macro is compiled conditionally, only when CONFIG_FOO_SUSPEND is set. This is problematic, as there could be a build bug in this function, we wouldn't have a way to know unless the config option is set. An alternative is to declare foo_suspend() always, but mark it as maybe unused: static int __maybe_unused foo_suspend(struct device *dev) { ... } static struct pm_ops foo_ops = { #ifdef CONFIG_FOO_SUSPEND .suspend = foo_suspend, #endif }; Again, this works, but the __maybe_unused attribute is required to instruct the compiler that the function may not be referenced anywhere, and is safe to remove without making a fuss about it. This makes the programmer responsible for tagging the functions that can be garbage-collected. With this patch, it is now possible to write the following: static int foo_suspend(struct device *dev) { ... } static struct pm_ops foo_ops = { .suspend = IF_ENABLED(CONFIG_FOO_SUSPEND, foo_suspend), }; The foo_suspend() function will now be automatically dropped by the compiler, and it does not require any specific attribute. Signed-off-by: Paul Cercueil Acked-by: Arnd Bergmann Link: https://lore.kernel.org/r/20201213235447.138271-1-paul@crapouillou.net Signed-off-by: Linus Walleij --- include/linux/kconfig.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kconfig.h b/include/linux/kconfig.h index 9d12c970f18f..e78e17a76dc9 100644 --- a/include/linux/kconfig.h +++ b/include/linux/kconfig.h @@ -72,4 +72,10 @@ */ #define IS_ENABLED(option) __or(IS_BUILTIN(option), IS_MODULE(option)) +/* + * IF_ENABLED(CONFIG_FOO, ptr) evaluates to (ptr) if CONFIG_FOO is set to 'y' + * or 'm', NULL otherwise. + */ +#define IF_ENABLED(option, ptr) (IS_ENABLED(option) ? (ptr) : NULL) + #endif /* __LINUX_KCONFIG_H */ -- cgit v1.2.3 From b33752c300232d7f95dd9a4353947d0c9e6a0e52 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Fri, 15 Jan 2021 09:06:37 -0800 Subject: HID: i2c-hid: Reorganize so ACPI and OF are separate modules This patch rejiggers the i2c-hid code so that the OF (Open Firmware aka Device Tree) and ACPI support is separated out a bit. The OF and ACPI drivers are now separate modules that wrap the core module. Essentially, what we're doing here: * Make "power up" and "power down" a function that can be (optionally) implemented by a given user of the i2c-hid core. * The OF and ACPI modules are drivers on their own, so they implement probe / remove / suspend / resume / shutdown. The core code provides implementations that OF and ACPI can call into. We'll organize this so that we now have 3 modules: the old i2c-hid module becomes the "core" module and two new modules will depend on it, handling probing the specific device. As part of this work, we'll remove the i2c-hid "platform data" concept since it's not needed. Signed-off-by: Douglas Anderson Reviewed-by: Hans de Goede Signed-off-by: Benjamin Tissoires --- include/linux/platform_data/i2c-hid.h | 41 ----------------------------------- 1 file changed, 41 deletions(-) delete mode 100644 include/linux/platform_data/i2c-hid.h (limited to 'include/linux') diff --git a/include/linux/platform_data/i2c-hid.h b/include/linux/platform_data/i2c-hid.h deleted file mode 100644 index c628bb5e1061..000000000000 --- a/include/linux/platform_data/i2c-hid.h +++ /dev/null @@ -1,41 +0,0 @@ -/* - * HID over I2C protocol implementation - * - * Copyright (c) 2012 Benjamin Tissoires - * Copyright (c) 2012 Ecole Nationale de l'Aviation Civile, France - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file COPYING in the main directory of this archive for - * more details. - */ - -#ifndef __LINUX_I2C_HID_H -#define __LINUX_I2C_HID_H - -#include -#include - -/** - * struct i2chid_platform_data - used by hid over i2c implementation. - * @hid_descriptor_address: i2c register where the HID descriptor is stored. - * @supplies: regulators for powering on the device. - * @post_power_delay_ms: delay after powering on before device is usable. - * - * Note that it is the responsibility of the platform driver (or the acpi 5.0 - * driver, or the flattened device tree) to setup the irq related to the gpio in - * the struct i2c_board_info. - * The platform driver should also setup the gpio according to the device: - * - * A typical example is the following: - * irq = gpio_to_irq(intr_gpio); - * hkdk4412_i2c_devs5[0].irq = irq; // store the irq in i2c_board_info - * gpio_request(intr_gpio, "elan-irq"); - * s3c_gpio_setpull(intr_gpio, S3C_GPIO_PULL_UP); - */ -struct i2c_hid_platform_data { - u16 hid_descriptor_address; - struct regulator_bulk_data supplies[2]; - int post_power_delay_ms; -}; - -#endif /* __LINUX_I2C_HID_H */ -- cgit v1.2.3 From f2fc9ff28d1c9bef7760516feadd38164044caae Mon Sep 17 00:00:00 2001 From: Thinh Nguyen Date: Wed, 13 Jan 2021 18:52:46 -0800 Subject: usb: ch9: Add USB 3.2 SSP attributes In preparation for USB 3.2 dual-lane support, add sublink speed attribute macros and enum usb_ssp_rate. A USB device that operates in SuperSpeed Plus may operate at different speed and lane count. These additional macros and enum values help specifying that. Signed-off-by: Thinh Nguyen Link: https://lore.kernel.org/r/ae9293ebd63a29f2a2035054753534d9eb123d74.1610592135.git.Thinh.Nguyen@synopsys.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/ch9.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/ch9.h b/include/linux/usb/ch9.h index 604c6c514a50..86c50907634e 100644 --- a/include/linux/usb/ch9.h +++ b/include/linux/usb/ch9.h @@ -36,6 +36,15 @@ #include #include +/* USB 3.2 SuperSpeed Plus phy signaling rate generation and lane count */ + +enum usb_ssp_rate { + USB_SSP_GEN_UNKNOWN = 0, + USB_SSP_GEN_2x1, + USB_SSP_GEN_1x2, + USB_SSP_GEN_2x2, +}; + /** * usb_ep_type_string() - Returns human readable-name of the endpoint type. * @ep_type: The endpoint type to return human-readable name for. If it's not -- cgit v1.2.3 From db615c6264cffcd8f117c5628db1794afbd0f254 Mon Sep 17 00:00:00 2001 From: Thinh Nguyen Date: Wed, 13 Jan 2021 18:53:00 -0800 Subject: usb: gadget: Introduce SSP rates and lanes A USB device controller operating in SuperSpeed Plus may support gen2x1, gen1x2, and/or gen2x2. Introduce SuperSpeed Plus signaling rate generation and lane count to usb_gadget with the fields ssp_rate and max_ssp_rate. The gadget driver can use these to setup the device BOS descriptor and select the desire operating speed and number of lanes. Signed-off-by: Thinh Nguyen Link: https://lore.kernel.org/r/b6d2196dcc3c73747f91abf9a082b20bbe276cc4.1610592135.git.Thinh.Nguyen@synopsys.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/gadget.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index e7351d64f11f..02483c862444 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -339,6 +339,10 @@ struct usb_gadget_ops { * @speed: Speed of current connection to USB host. * @max_speed: Maximal speed the UDC can handle. UDC must support this * and all slower speeds. + * @ssp_rate: Current connected SuperSpeed Plus signaling rate and lane count. + * @max_ssp_rate: Maximum SuperSpeed Plus signaling rate and lane count the UDC + * can handle. The UDC must support this and all slower speeds and lower + * number of lanes. * @state: the state we are now (attached, suspended, configured, etc) * @name: Identifies the controller hardware type. Used in diagnostics * and sometimes configuration. @@ -406,6 +410,11 @@ struct usb_gadget { struct list_head ep_list; /* of usb_ep */ enum usb_device_speed speed; enum usb_device_speed max_speed; + + /* USB SuperSpeed Plus only */ + enum usb_ssp_rate ssp_rate; + enum usb_ssp_rate max_ssp_rate; + enum usb_device_state state; const char *name; struct device dev; -- cgit v1.2.3 From ead4c124852e66b6aa033e34cf9c4f08d40aeffc Mon Sep 17 00:00:00 2001 From: Thinh Nguyen Date: Wed, 13 Jan 2021 18:53:07 -0800 Subject: usb: gadget: Introduce udc_set_ssp_rate() for SSP A SuperSpeed Plus device may operate at different speed and lane count (i.e. gen2x2, gen1x2, or gen2x1). Introduce gadget ops udc_set_ssp_rate() to set the desire corresponding usb_ssp_rate for SuperSpeed Plus capable devices. If the USB device supports different speeds at SuperSpeed Plus, set the device to operate with the maximum number of lanes and speed. Signed-off-by: Thinh Nguyen Link: https://lore.kernel.org/r/9b85357cdadc02e3f0d653fd05f89eb46af836e1.1610592135.git.Thinh.Nguyen@synopsys.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/gadget.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 02483c862444..ee04ef214ce8 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -323,6 +323,8 @@ struct usb_gadget_ops { struct usb_gadget_driver *); int (*udc_stop)(struct usb_gadget *); void (*udc_set_speed)(struct usb_gadget *, enum usb_device_speed); + void (*udc_set_ssp_rate)(struct usb_gadget *gadget, + enum usb_ssp_rate rate); struct usb_ep *(*match_ep)(struct usb_gadget *, struct usb_endpoint_descriptor *, struct usb_ss_ep_comp_descriptor *); -- cgit v1.2.3 From 0627cc334d408953c0ff9ef8731325c2d02572ed Mon Sep 17 00:00:00 2001 From: Yue Zou Date: Mon, 18 Jan 2021 01:01:37 +0000 Subject: sony-laptop: Remove unneeded semicolon Remove a superfluous semicolon after function definition. Signed-off-by: Yue Zou Link: https://lore.kernel.org/r/20210118010137.214378-1-zouyue3@huawei.com Signed-off-by: Hans de Goede --- include/linux/sony-laptop.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sony-laptop.h b/include/linux/sony-laptop.h index 374d0fdb0743..1e3c92feea6e 100644 --- a/include/linux/sony-laptop.h +++ b/include/linux/sony-laptop.h @@ -31,7 +31,7 @@ #if IS_ENABLED(CONFIG_SONY_LAPTOP) int sony_pic_camera_command(int command, u8 value); #else -static inline int sony_pic_camera_command(int command, u8 value) { return 0; }; +static inline int sony_pic_camera_command(int command, u8 value) { return 0; } #endif #endif /* __KERNEL__ */ -- cgit v1.2.3 From 719a402cf60311b1cdff3f6320abaecdcc5e46b7 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Sun, 17 Jan 2021 16:59:42 +0200 Subject: net: netdevice: Add operation ndo_sk_get_lower_dev ndo_sk_get_lower_dev returns the lower netdev that corresponds to a given socket. Additionally, we implement a helper netdev_sk_get_lowest_dev() to get the lowest one in chain. Signed-off-by: Tariq Toukan Reviewed-by: Boris Pismenny Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5b949076ed23..02dcef4d66e2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1398,6 +1398,8 @@ struct net_device_ops { struct net_device* (*ndo_get_xmit_slave)(struct net_device *dev, struct sk_buff *skb, bool all_slaves); + struct net_device* (*ndo_sk_get_lower_dev)(struct net_device *dev, + struct sock *sk); netdev_features_t (*ndo_fix_features)(struct net_device *dev, netdev_features_t features); int (*ndo_set_features)(struct net_device *dev, @@ -2858,6 +2860,8 @@ int init_dummy_netdev(struct net_device *dev); struct net_device *netdev_get_xmit_slave(struct net_device *dev, struct sk_buff *skb, bool all_slaves); +struct net_device *netdev_sk_get_lowest_dev(struct net_device *dev, + struct sock *sk); struct net_device *dev_get_by_index(struct net *net, int ifindex); struct net_device *__dev_get_by_index(struct net *net, int ifindex); struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); -- cgit v1.2.3 From ab0da5a57188b80d16d3222236c4e184953a5bb4 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Wed, 30 Dec 2020 15:01:20 +0200 Subject: net/mlx5: Expose ifc bits for query modify header Expose ifc bits for query_modify_header_context_in to be used by DEVX. Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 442c0160caab..cf692fc17f41 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -5904,6 +5904,18 @@ struct mlx5_ifc_dealloc_modify_header_context_in_bits { u8 reserved_at_60[0x20]; }; +struct mlx5_ifc_query_modify_header_context_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 modify_header_id[0x20]; + + u8 reserved_at_60[0xa0]; +}; + struct mlx5_ifc_query_dct_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; -- cgit v1.2.3 From f4d3bd8be4f2bc43e4b13490cbc9969d15c2f058 Mon Sep 17 00:00:00 2001 From: Yu-Hsuan Hsu Date: Fri, 15 Jan 2021 15:53:00 +0800 Subject: cros_ec_commands: Add EC_CODEC_I2S_RX_RESET Add the new command EC_CODEC_I2S_RX_RESET in ec_codec_i2s_rx_subcmd, which is used for resetting the EC codec. Signed-off-by: Yu-Hsuan Hsu Acked-by: Enric Balletbo i Serra Link: https://lore.kernel.org/r/20210115075301.47995-1-yuhsuan@chromium.org Signed-off-by: Mark Brown --- include/linux/platform_data/cros_ec_commands.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index 86376779ab31..95889ada83a3 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -4600,6 +4600,7 @@ enum ec_codec_i2s_rx_subcmd { EC_CODEC_I2S_RX_SET_SAMPLE_DEPTH = 0x2, EC_CODEC_I2S_RX_SET_DAIFMT = 0x3, EC_CODEC_I2S_RX_SET_BCLK = 0x4, + EC_CODEC_I2S_RX_RESET = 0x5, EC_CODEC_I2S_RX_SUBCMD_COUNT, }; -- cgit v1.2.3 From 93e86295f5e9238779096fa599c3804a08e25bd1 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Mon, 18 Jan 2021 00:04:55 -0800 Subject: workqueue: fix annotation for WQ_SYSFS 'wq_sysfs_register()' in annotation for 'WQ_SYSFS' is unavailable, change it to 'workqueue_sysfs_register()'. Signed-off-by: Menglong Dong Reviewed-by: Lai Jiangshan Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 26de0cae2a0a..d15a7730ee18 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -311,7 +311,7 @@ enum { WQ_MEM_RECLAIM = 1 << 3, /* may be used for memory reclaim */ WQ_HIGHPRI = 1 << 4, /* high priority */ WQ_CPU_INTENSIVE = 1 << 5, /* cpu intensive workqueue */ - WQ_SYSFS = 1 << 6, /* visible in sysfs, see wq_sysfs_register() */ + WQ_SYSFS = 1 << 6, /* visible in sysfs, see workqueue_sysfs_register() */ /* * Per-cpu workqueues are generally preferred because they tend to -- cgit v1.2.3 From 2f196059864fb0fe8f60c14a2cb214055b283e08 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Mon, 2 Nov 2020 17:11:49 +0100 Subject: efi/libstub: whitespace cleanup Trivial whitespace cleanup. Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 0c31af36697c..2537a246c2d6 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -29,10 +29,10 @@ #include #define EFI_SUCCESS 0 -#define EFI_LOAD_ERROR ( 1 | (1UL << (BITS_PER_LONG-1))) +#define EFI_LOAD_ERROR ( 1 | (1UL << (BITS_PER_LONG-1))) #define EFI_INVALID_PARAMETER ( 2 | (1UL << (BITS_PER_LONG-1))) #define EFI_UNSUPPORTED ( 3 | (1UL << (BITS_PER_LONG-1))) -#define EFI_BAD_BUFFER_SIZE ( 4 | (1UL << (BITS_PER_LONG-1))) +#define EFI_BAD_BUFFER_SIZE ( 4 | (1UL << (BITS_PER_LONG-1))) #define EFI_BUFFER_TOO_SMALL ( 5 | (1UL << (BITS_PER_LONG-1))) #define EFI_NOT_READY ( 6 | (1UL << (BITS_PER_LONG-1))) #define EFI_DEVICE_ERROR ( 7 | (1UL << (BITS_PER_LONG-1))) -- cgit v1.2.3 From 3820749ddcee694abfd5ae6cabc18aaab11eab34 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Mon, 2 Nov 2020 11:51:10 +0100 Subject: efi/libstub: move TPM related prototypes into efistub.h Move TPM related definitions that are only used in the EFI stub into efistub.h, which is a local header. Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 2537a246c2d6..8710f5710c1d 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1104,13 +1104,6 @@ enum efi_secureboot_mode efi_get_secureboot_mode(efi_get_variable_t *get_var) return efi_secureboot_mode_enabled; } -#ifdef CONFIG_RESET_ATTACK_MITIGATION -void efi_enable_reset_attack_mitigation(void); -#else -static inline void -efi_enable_reset_attack_mitigation(void) { } -#endif - #ifdef CONFIG_EFI_EMBEDDED_FIRMWARE void efi_check_for_embedded_firmwares(void); #else @@ -1119,8 +1112,6 @@ static inline void efi_check_for_embedded_firmwares(void) { } efi_status_t efi_random_get_seed(void); -void efi_retrieve_tpm2_eventlog(void); - /* * Arch code can implement the following three template macros, avoiding * reptition for the void/non-void return cases of {__,}efi_call_virt(): -- cgit v1.2.3 From 7eab14de73a8028f770e703962c5437a2b0dda82 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Sat, 16 Jan 2021 16:13:22 +0000 Subject: mdio, phy: fix -Wshadow warnings triggered by nested container_of() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit container_of() macro hides a local variable '__mptr' inside. This becomes a problem when several container_of() are nested in each other within single line or plain macros. As C preprocessor doesn't support generating random variable names, the sole solution is to avoid defining macros that consist only of container_of() calls, or they will self-shadow '__mptr' each time: In file included from ./include/linux/bitmap.h:10, from drivers/net/phy/phy_device.c:12: drivers/net/phy/phy_device.c: In function ‘phy_device_release’: ./include/linux/kernel.h:693:8: warning: declaration of ‘__mptr’ shadows a previous local [-Wshadow] 693 | void *__mptr = (void *)(ptr); \ | ^~~~~~ ./include/linux/phy.h:647:26: note: in expansion of macro ‘container_of’ 647 | #define to_phy_device(d) container_of(to_mdio_device(d), \ | ^~~~~~~~~~~~ ./include/linux/mdio.h:52:27: note: in expansion of macro ‘container_of’ 52 | #define to_mdio_device(d) container_of(d, struct mdio_device, dev) | ^~~~~~~~~~~~ ./include/linux/phy.h:647:39: note: in expansion of macro ‘to_mdio_device’ 647 | #define to_phy_device(d) container_of(to_mdio_device(d), \ | ^~~~~~~~~~~~~~ drivers/net/phy/phy_device.c:217:8: note: in expansion of macro ‘to_phy_device’ 217 | kfree(to_phy_device(dev)); | ^~~~~~~~~~~~~ ./include/linux/kernel.h:693:8: note: shadowed declaration is here 693 | void *__mptr = (void *)(ptr); \ | ^~~~~~ ./include/linux/phy.h:647:26: note: in expansion of macro ‘container_of’ 647 | #define to_phy_device(d) container_of(to_mdio_device(d), \ | ^~~~~~~~~~~~ drivers/net/phy/phy_device.c:217:8: note: in expansion of macro ‘to_phy_device’ 217 | kfree(to_phy_device(dev)); | ^~~~~~~~~~~~~ As they are declared in header files, these warnings are highly repetitive and very annoying (along with the one from linux/pci.h). Convert the related macros from linux/{mdio,phy}.h to static inlines to avoid self-shadowing and potentially improve bug-catching. No functional changes implied. Signed-off-by: Alexander Lobakin Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/20210116161246.67075-1-alobakin@pm.me Signed-off-by: Jakub Kicinski --- include/linux/mdio.h | 23 ++++++++++++++++++----- include/linux/phy.h | 7 +++++-- 2 files changed, 23 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mdio.h b/include/linux/mdio.h index dbd69b3d170b..ffb787d5ebde 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -49,7 +49,11 @@ struct mdio_device { unsigned int reset_assert_delay; unsigned int reset_deassert_delay; }; -#define to_mdio_device(d) container_of(d, struct mdio_device, dev) + +static inline struct mdio_device *to_mdio_device(const struct device *dev) +{ + return container_of(dev, struct mdio_device, dev); +} /* struct mdio_driver_common: Common to all MDIO drivers */ struct mdio_driver_common { @@ -57,8 +61,12 @@ struct mdio_driver_common { int flags; }; #define MDIO_DEVICE_FLAG_PHY 1 -#define to_mdio_common_driver(d) \ - container_of(d, struct mdio_driver_common, driver) + +static inline struct mdio_driver_common * +to_mdio_common_driver(const struct device_driver *driver) +{ + return container_of(driver, struct mdio_driver_common, driver); +} /* struct mdio_driver: Generic MDIO driver */ struct mdio_driver { @@ -73,8 +81,13 @@ struct mdio_driver { /* Clears up any memory if needed */ void (*remove)(struct mdio_device *mdiodev); }; -#define to_mdio_driver(d) \ - container_of(to_mdio_common_driver(d), struct mdio_driver, mdiodrv) + +static inline struct mdio_driver * +to_mdio_driver(const struct device_driver *driver) +{ + return container_of(to_mdio_common_driver(driver), struct mdio_driver, + mdiodrv); +} /* device driver data */ static inline void mdiodev_set_drvdata(struct mdio_device *mdio, void *data) diff --git a/include/linux/phy.h b/include/linux/phy.h index 24fcc6456a9e..bc323fbdd21e 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -648,8 +648,11 @@ struct phy_device { const struct macsec_ops *macsec_ops; #endif }; -#define to_phy_device(d) container_of(to_mdio_device(d), \ - struct phy_device, mdio) + +static inline struct phy_device *to_phy_device(const struct device *dev) +{ + return container_of(to_mdio_device(dev), struct phy_device, mdio); +} /** * struct phy_tdr_config - Configuration of a TDR raw test -- cgit v1.2.3 From a7d6ba14efb778fc8c65c627a057d5dd29debd04 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Tue, 15 Dec 2020 00:38:04 +0100 Subject: thermal/core: Remove the 'forced_passive' option The code was reorganized in 2012 with the commit 0c01ebbfd3caf1. The main change is a loop on the trip points array and a unconditional call to the throttle() ops of the governors for each of them even if the trip temperature is not reached yet. With this change, the 'forced_passive' is no longer checked in the thermal_zone_device_update() function but in the step wise governor's throttle() callback. As the force_passive does no belong to the trip point array, the thermal_zone_device_update() can not compare with the specified passive temperature, thus does not detect the passive limit has been crossed. Consequently, throttle() is never called and the 'forced_passive' branch is unreached. In addition, the default processor cooling device is not automatically bound to the thermal zone if there is not passive trip point, thus the 'forced_passive' can not operate. If there is an active trip point, then the throttle function will be called to mitigate at this temperature and the 'forced_passive' will override the mitigation of the active trip point in this case but with the default cooling device bound to the thermal zone, so usually a fan, and that is not a passive cooling effect. Given the regression exists since more than 8 years, nobody complained and at the best of my knowledge there is no bug open in https://bugzilla.kernel.org, it is reasonable to say it is unused. Remove the 'forced_passive' related code. Signed-off-by: Daniel Lezcano Reviewed-by: Thara Gopinath Link: https://lore.kernel.org/r/20201214233811.485669-1-daniel.lezcano@linaro.org --- include/linux/thermal.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index c80032322158..a57232a9a6f9 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -131,9 +131,6 @@ struct thermal_cooling_device { trip point. * @prev_high_trip: the above current temperature if you've crossed a passive trip point. - * @forced_passive: If > 0, temperature at which to switch on all ACPI - * processor cooling devices. Currently only used by the - * step-wise governor. * @need_update: if equals 1, thermal_zone_device_update needs to be invoked. * @ops: operations this &thermal_zone_device supports * @tzp: thermal zone parameters @@ -167,7 +164,6 @@ struct thermal_zone_device { int passive; int prev_low_trip; int prev_high_trip; - unsigned int forced_passive; atomic_t need_update; struct thermal_zone_device_ops *ops; struct thermal_zone_params *tzp; -- cgit v1.2.3 From 2121496fdc5f2d93eda9743c4b487469f0042e3c Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Tue, 15 Dec 2020 00:38:09 +0100 Subject: thermal/core: Remove unused macro THERMAL_TRIPS_NONE The macro THERMAL_TRIPS_NONE is no longer used, remove it. Signed-off-by: Daniel Lezcano Reviewed-by: Thara Gopinath Link: https://lore.kernel.org/r/20201214233811.485669-6-daniel.lezcano@linaro.org --- include/linux/thermal.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index a57232a9a6f9..060a2160add4 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -17,7 +17,6 @@ #include #include -#define THERMAL_TRIPS_NONE -1 #define THERMAL_MAX_TRIPS 12 /* invalid cooling state */ -- cgit v1.2.3 From 17d399cd9c8936909bc8936a5837b6da9af9c29e Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 16 Dec 2020 23:03:35 +0100 Subject: thermal/core: Precompute the delays from msecs to jiffies The delays are stored in ms units and when the polling function is called this delay is converted into jiffies at each call. Instead of doing the conversion again and again, compute the jiffies at init time and use the value directly when setting the polling. Cc: Thara Gopinath Signed-off-by: Daniel Lezcano Reviewed-by: Lukasz Luba Reviewed-by: Thara Gopinath Link: https://lore.kernel.org/r/20201216220337.839878-1-daniel.lezcano@linaro.org --- include/linux/thermal.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 060a2160add4..d1b82c70de69 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -117,9 +117,14 @@ struct thermal_cooling_device { * @trips_disabled; bitmap for disabled trips * @passive_delay: number of milliseconds to wait between polls when * performing passive cooling. + * @passive_delay_jiffies: number of jiffies to wait between polls when + * performing passive cooling. * @polling_delay: number of milliseconds to wait between polls when * checking whether trip points have been crossed (0 for * interrupt driven systems) + * @polling_delay_jiffies: number of jiffies to wait between polls when + * checking whether trip points have been crossed (0 for + * interrupt driven systems) * @temperature: current temperature. This is only for core code, * drivers should use thermal_zone_get_temp() to get the * current temperature @@ -155,6 +160,8 @@ struct thermal_zone_device { void *devdata; int trips; unsigned long trips_disabled; /* bitmap for disabled trips */ + unsigned long passive_delay_jiffies; + unsigned long polling_delay_jiffies; int passive_delay; int polling_delay; int temperature; -- cgit v1.2.3 From b39d2dd5b5ed08d15711aefd5afd72bd87387c64 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 16 Dec 2020 23:03:37 +0100 Subject: thermal/core: Remove ms based delay fields MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The code does no longer use the ms unit based fields to set the delays as they are replaced by the jiffies. Remove them and replace their user to use the jiffies version instead. Cc: Thara Gopinath Signed-off-by: Daniel Lezcano Reviewed-by: Lukasz Luba Reviewed-by: Peter Kästle Acked-by: Hans de Goede Link: https://lore.kernel.org/r/20201216220337.839878-3-daniel.lezcano@linaro.org --- include/linux/thermal.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index d1b82c70de69..1e686404951b 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -115,13 +115,8 @@ struct thermal_cooling_device { * @devdata: private pointer for device private data * @trips: number of trip points the thermal zone supports * @trips_disabled; bitmap for disabled trips - * @passive_delay: number of milliseconds to wait between polls when - * performing passive cooling. * @passive_delay_jiffies: number of jiffies to wait between polls when * performing passive cooling. - * @polling_delay: number of milliseconds to wait between polls when - * checking whether trip points have been crossed (0 for - * interrupt driven systems) * @polling_delay_jiffies: number of jiffies to wait between polls when * checking whether trip points have been crossed (0 for * interrupt driven systems) @@ -162,8 +157,6 @@ struct thermal_zone_device { unsigned long trips_disabled; /* bitmap for disabled trips */ unsigned long passive_delay_jiffies; unsigned long polling_delay_jiffies; - int passive_delay; - int polling_delay; int temperature; int last_temperature; int emul_temperature; -- cgit v1.2.3 From 23ff8529ee207c634ce2e170c353938db7aa98a9 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Mon, 18 Jan 2021 18:38:24 +0100 Subject: thermal/core: Make cooling device state change private The change of the cooling device state should be used by the governor or at least by the core code, not by the drivers themselves. Remove the API usage and move the function declaration to the internal headers. Signed-off-by: Daniel Lezcano Acked-by: Guenter Roeck Acked-by: Zhang Rui Link: https://lore.kernel.org/r/20210118173824.9970-1-daniel.lezcano@linaro.org --- include/linux/thermal.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 1e686404951b..6ac7bb1d2b1f 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -390,7 +390,6 @@ int thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp); int thermal_zone_get_slope(struct thermal_zone_device *tz); int thermal_zone_get_offset(struct thermal_zone_device *tz); -void thermal_cdev_update(struct thermal_cooling_device *); void thermal_notify_framework(struct thermal_zone_device *, int); int thermal_zone_device_enable(struct thermal_zone_device *tz); int thermal_zone_device_disable(struct thermal_zone_device *tz); @@ -437,8 +436,6 @@ static inline int thermal_zone_get_offset( struct thermal_zone_device *tz) { return -ENODEV; } -static inline void thermal_cdev_update(struct thermal_cooling_device *cdev) -{ } static inline void thermal_notify_framework(struct thermal_zone_device *tz, int trip) { } -- cgit v1.2.3 From fa82117010430aff2ce86400f7328f55a31b48a6 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sat, 16 Jan 2021 14:13:37 +0800 Subject: net: add inline function skb_csum_is_sctp This patch is to define a inline function skb_csum_is_sctp(), and also replace all places where it checks if it's a SCTP CSUM skb. This function would be used later in many networking drivers in the following patches. Suggested-by: Alexander Duyck Signed-off-by: Xin Long Reviewed-by: Alexander Duyck Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index c9568cf60c2a..46f901adf1a8 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4621,6 +4621,11 @@ static inline void skb_reset_redirect(struct sk_buff *skb) #endif } +static inline bool skb_csum_is_sctp(struct sk_buff *skb) +{ + return skb->csum_not_inet; +} + static inline void skb_set_kcov_handle(struct sk_buff *skb, const u64 kcov_handle) { -- cgit v1.2.3 From 7b8fc0103bb51d1d3e1fb5fd67958612e709f883 Mon Sep 17 00:00:00 2001 From: Jarod Wilson Date: Mon, 18 Jan 2021 20:09:27 -0500 Subject: bonding: add a vlan+srcmac tx hashing option This comes from an end-user request, where they're running multiple VMs on hosts with bonded interfaces connected to some interest switch topologies, where 802.3ad isn't an option. They're currently running a proprietary solution that effectively achieves load-balancing of VMs and bandwidth utilization improvements with a similar form of transmission algorithm. Basically, each VM has it's own vlan, so it always sends its traffic out the same interface, unless that interface fails. Traffic gets split between the interfaces, maintaining a consistent path, with failover still available if an interface goes down. Unlike bond_eth_hash(), this hash function is using the full source MAC address instead of just the last byte, as there are so few components to the hash, and in the no-vlan case, we would be returning just the last byte of the source MAC as the hash value. It's entirely possible to have two NICs in a bond with the same last byte of their MAC, but not the same MAC, so this adjustment should guarantee distinct hashes in all cases. This has been rudimetarily tested to provide similar results to the proprietary solution it is aiming to replace. A patch for iproute2 is also posted, to properly support the new mode there as well. Cc: Jay Vosburgh Cc: Veaceslav Falico Cc: Andy Gospodarek Cc: Thomas Davis Signed-off-by: Jarod Wilson Link: https://lore.kernel.org/r/20210119010927.1191922-1-jarod@redhat.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 02dcef4d66e2..ef517254367d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2617,6 +2617,7 @@ enum netdev_lag_hash { NETDEV_LAG_HASH_L23, NETDEV_LAG_HASH_E23, NETDEV_LAG_HASH_E34, + NETDEV_LAG_HASH_VLAN_SRCMAC, NETDEV_LAG_HASH_UNKNOWN, }; -- cgit v1.2.3 From 67c6bb56b649590a3f59c2a92331aa4e83d4534c Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 6 Jan 2021 10:34:49 +0000 Subject: firmware: smccc: Add SMCCC TRNG function call IDs The ARM architected TRNG firmware interface, described in ARM spec DEN0098, define an ARM SMCCC based interface to a true random number generator, provided by firmware. Add the definitions of the SMCCC functions as defined by the spec. Signed-off-by: Ard Biesheuvel Signed-off-by: Andre Przywara Reviewed-by: Linus Walleij Reviewed-by: Sudeep Holla Link: https://lore.kernel.org/r/20210106103453.152275-2-andre.przywara@arm.com Signed-off-by: Will Deacon --- include/linux/arm-smccc.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index f860645f6512..62c54234576c 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -102,6 +102,37 @@ ARM_SMCCC_OWNER_STANDARD_HYP, \ 0x21) +/* TRNG entropy source calls (defined by ARM DEN0098) */ +#define ARM_SMCCC_TRNG_VERSION \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + ARM_SMCCC_OWNER_STANDARD, \ + 0x50) + +#define ARM_SMCCC_TRNG_FEATURES \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + ARM_SMCCC_OWNER_STANDARD, \ + 0x51) + +#define ARM_SMCCC_TRNG_GET_UUID \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + ARM_SMCCC_OWNER_STANDARD, \ + 0x52) + +#define ARM_SMCCC_TRNG_RND32 \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + ARM_SMCCC_OWNER_STANDARD, \ + 0x53) + +#define ARM_SMCCC_TRNG_RND64 \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_64, \ + ARM_SMCCC_OWNER_STANDARD, \ + 0x53) + /* * Return codes defined in ARM DEN 0070A * ARM DEN 0070A is now merged/consolidated into ARM DEN 0028 C -- cgit v1.2.3 From 93cc26fa8f37fbd320f36525bfedd4b3e2b3e2ba Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 18 Jan 2021 14:23:22 +0100 Subject: backlight: lms283gf05: Convert to GPIO descriptors This converts the lms283gf05 backlight driver to use GPIO descriptors and switches the single PXA Palm Z2 device over to defining these. Since the platform data was only used to convey GPIO information we can delete the platform data header. Notice that we define the proper active low semantics in the board file GPIO descriptor table (active low) and assert the reset line by bringing it to "1" (asserted). Cc: Marek Vasut Cc: Haojian Zhuang Cc: Robert Jarzmik Signed-off-by: Linus Walleij Reviewed-by: Daniel Mack Acked-by: Mark Brown Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones --- include/linux/spi/lms283gf05.h | 16 ---------------- 1 file changed, 16 deletions(-) delete mode 100644 include/linux/spi/lms283gf05.h (limited to 'include/linux') diff --git a/include/linux/spi/lms283gf05.h b/include/linux/spi/lms283gf05.h deleted file mode 100644 index f237b2d062e9..000000000000 --- a/include/linux/spi/lms283gf05.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * lms283gf05.h - Platform glue for Samsung LMS283GF05 LCD - * - * Copyright (C) 2009 Marek Vasut -*/ - -#ifndef _INCLUDE_LINUX_SPI_LMS283GF05_H_ -#define _INCLUDE_LINUX_SPI_LMS283GF05_H_ - -struct lms283gf05_pdata { - unsigned long reset_gpio; - bool reset_inverted; -}; - -#endif /* _INCLUDE_LINUX_SPI_LMS283GF05_H_ */ -- cgit v1.2.3 From f9ce0be71d1fbb038ada15ced83474b0e63f264d Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Sat, 19 Dec 2020 15:19:23 +0300 Subject: mm: Cleanup faultaround and finish_fault() codepaths alloc_set_pte() has two users with different requirements: in the faultaround code, it called from an atomic context and PTE page table has to be preallocated. finish_fault() can sleep and allocate page table as needed. PTL locking rules are also strange, hard to follow and overkill for finish_fault(). Let's untangle the mess. alloc_set_pte() has gone now. All locking is explicit. The price is some code duplication to handle huge pages in faultaround path, but it should be fine, having overall improvement in readability. Link: https://lore.kernel.org/r/20201229132819.najtavneutnf7ajp@box Signed-off-by: Kirill A. Shutemov [will: s/from from/from/ in comment; spotted by willy] Signed-off-by: Will Deacon --- include/linux/mm.h | 12 +++++++----- include/linux/pgtable.h | 11 +++++++++++ 2 files changed, 18 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index ecdf8a8cd6ae..4572a9bc5862 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -542,8 +542,8 @@ struct vm_fault { * is not NULL, otherwise pmd. */ pgtable_t prealloc_pte; /* Pre-allocated pte page table. - * vm_ops->map_pages() calls - * alloc_set_pte() from atomic context. + * vm_ops->map_pages() sets up a page + * table from atomic context. * do_fault_around() pre-allocates * page table to avoid allocation from * atomic context. @@ -578,7 +578,7 @@ struct vm_operations_struct { vm_fault_t (*fault)(struct vm_fault *vmf); vm_fault_t (*huge_fault)(struct vm_fault *vmf, enum page_entry_size pe_size); - void (*map_pages)(struct vm_fault *vmf, + vm_fault_t (*map_pages)(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); unsigned long (*pagesize)(struct vm_area_struct * area); @@ -988,7 +988,9 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) return pte; } -vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *page); +vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page); +void do_set_pte(struct vm_fault *vmf, struct page *page); + vm_fault_t finish_fault(struct vm_fault *vmf); vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf); #endif @@ -2622,7 +2624,7 @@ extern void truncate_inode_pages_final(struct address_space *); /* generic vm_area_ops exported for stackable file systems */ extern vm_fault_t filemap_fault(struct vm_fault *vmf); -extern void filemap_map_pages(struct vm_fault *vmf, +extern vm_fault_t filemap_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); extern vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf); diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 8fcdfa52eb4b..36eb748f3c97 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1314,6 +1314,17 @@ static inline int pmd_trans_unstable(pmd_t *pmd) #endif } +/* + * the ordering of these checks is important for pmds with _page_devmap set. + * if we check pmd_trans_unstable() first we will trip the bad_pmd() check + * inside of pmd_none_or_trans_huge_or_clear_bad(). this will end up correctly + * returning 1 but not before it spams dmesg with the pmd_clear_bad() output. + */ +static inline int pmd_devmap_trans_unstable(pmd_t *pmd) +{ + return pmd_devmap(*pmd) || pmd_trans_unstable(pmd); +} + #ifndef CONFIG_NUMA_BALANCING /* * Technically a PTE can be PROTNONE even when not doing NUMA balancing but -- cgit v1.2.3 From 46bdb4277f98e70d0c91f4289897ade533fe9e80 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 24 Nov 2020 18:48:26 +0000 Subject: mm: Allow architectures to request 'old' entries when prefaulting Commit 5c0a85fad949 ("mm: make faultaround produce old ptes") changed the "faultaround" behaviour to initialise prefaulted PTEs as 'old', since this avoids vmscan wrongly assuming that they are hot, despite having never been explicitly accessed by userspace. The change has been shown to benefit numerous arm64 micro-architectures (with hardware access flag) running Android, where both application launch latency and direct reclaim time are significantly reduced (by 10%+ and ~80% respectively). Unfortunately, commit 315d09bf30c2 ("Revert "mm: make faultaround produce old ptes"") reverted the change due to it being identified as the cause of a ~6% regression in unixbench on x86. Experiments on a variety of recent arm64 micro-architectures indicate that unixbench is not affected by the original commit, which appears to yield a 0-1% performance improvement. Since one size does not fit all for the initial state of prefaulted PTEs, introduce arch_wants_old_prefaulted_pte(), which allows an architecture to opt-in to 'old' prefaulted PTEs at runtime based on whatever criteria it may have. Cc: Jan Kara Cc: Minchan Kim Cc: Andrew Morton Cc: Kirill A. Shutemov Cc: Linus Torvalds Reported-by: Vinayak Menon Signed-off-by: Will Deacon --- include/linux/mm.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 4572a9bc5862..251a2339befb 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -434,6 +434,7 @@ extern pgprot_t protection_map[16]; * @FAULT_FLAG_REMOTE: The fault is not for current task/mm. * @FAULT_FLAG_INSTRUCTION: The fault was during an instruction fetch. * @FAULT_FLAG_INTERRUPTIBLE: The fault can be interrupted by non-fatal signals. + * @FAULT_FLAG_PREFAULT: Fault was a prefault. * * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify * whether we would allow page faults to retry by specifying these two @@ -464,6 +465,7 @@ extern pgprot_t protection_map[16]; #define FAULT_FLAG_REMOTE 0x80 #define FAULT_FLAG_INSTRUCTION 0x100 #define FAULT_FLAG_INTERRUPTIBLE 0x200 +#define FAULT_FLAG_PREFAULT 0x400 /* * The default fault flags that should be used by most of the @@ -501,7 +503,8 @@ static inline bool fault_flag_allow_retry_first(unsigned int flags) { FAULT_FLAG_USER, "USER" }, \ { FAULT_FLAG_REMOTE, "REMOTE" }, \ { FAULT_FLAG_INSTRUCTION, "INSTRUCTION" }, \ - { FAULT_FLAG_INTERRUPTIBLE, "INTERRUPTIBLE" } + { FAULT_FLAG_INTERRUPTIBLE, "INTERRUPTIBLE" }, \ + { FAULT_FLAG_PREFAULT, "PREFAULT" } /* * vm_fault is filled by the pagefault handler and passed to the vma's -- cgit v1.2.3 From 9f77c58d65ff216d71f5ab829b6f39afefbde10c Mon Sep 17 00:00:00 2001 From: Pi-Hsun Shih Date: Mon, 21 Dec 2020 12:12:23 +0800 Subject: platform/chrome: cros_ec_commands: Add host command to keep AP off after EC reset. Add command to EC_CMD_REBOOT_EC to reset EC but don't boot AP. Signed-off-by: Pi-Hsun Shih Signed-off-by: Enric Balletbo i Serra Link: https://lore.kernel.org/r/20201221041231.14516-1-pihsun@chromium.org --- include/linux/platform_data/cros_ec_commands.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index 9787715540c7..d3c40220b281 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -4741,6 +4741,7 @@ enum ec_reboot_cmd { EC_REBOOT_DISABLE_JUMP = 5, /* Disable jump until next reboot */ EC_REBOOT_HIBERNATE = 6, /* Hibernate EC */ EC_REBOOT_HIBERNATE_CLEAR_AP_OFF = 7, /* and clears AP_OFF flag */ + EC_REBOOT_COLD_AP_OFF = 8, /* Cold-reboot and don't boot AP */ }; /* Flags for ec_params_reboot_ec.reboot_flags */ -- cgit v1.2.3 From f6f1f8e6e3eea25f539105d48166e91f0ab46dd1 Mon Sep 17 00:00:00 2001 From: Aswath Govindraju Date: Tue, 5 Jan 2021 16:28:12 +0530 Subject: misc: eeprom_93xx46: Add quirk to support Microchip 93LC46B eeprom A dummy zero bit is sent preceding the data during a read transfer by the Microchip 93LC46B eeprom (section 2.7 of[1]). This results in right shift of data during a read. In order to ignore this bit a quirk can be added to send an extra zero bit after the read address. Add a quirk to ignore the zero bit sent before data by adding a zero bit after the read address. [1] - https://www.mouser.com/datasheet/2/268/20001749K-277859.pdf Signed-off-by: Aswath Govindraju Link: https://lore.kernel.org/r/20210105105817.17644-3-a-govindraju@ti.com Signed-off-by: Greg Kroah-Hartman --- include/linux/eeprom_93xx46.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/eeprom_93xx46.h b/include/linux/eeprom_93xx46.h index eec7928ff8fe..99580c22f91a 100644 --- a/include/linux/eeprom_93xx46.h +++ b/include/linux/eeprom_93xx46.h @@ -16,6 +16,8 @@ struct eeprom_93xx46_platform_data { #define EEPROM_93XX46_QUIRK_SINGLE_WORD_READ (1 << 0) /* Instructions such as EWEN are (addrlen + 2) in length. */ #define EEPROM_93XX46_QUIRK_INSTRUCTION_LENGTH (1 << 1) +/* Add extra cycle after address during a read */ +#define EEPROM_93XX46_QUIRK_EXTRA_READ_CYCLE BIT(2) /* * optional hooks to control additional logic -- cgit v1.2.3 From 149ae80b1d50e7db5ac7df1cdf0820017b70e716 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Thu, 14 Jan 2021 11:53:18 +0100 Subject: soc: bcm: brcmstb: add stubs for getting platform IDs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some brcmstb drivers may be shared with other SoC families. E.g. the same USB PHY block is shared by brcmstb and BCM4908. To avoid building brcmstb common code on non-brcmstb platforms we need stubs for: 1. brcmstb_get_family_id() 2. brcmstb_get_product_id() (to avoid "undefined reference to" errors). With this change PHY_BRCM_USB will not have to unconditionally select SOC_BRCMSTB anymore. Signed-off-by: Rafał Miłecki Signed-off-by: Florian Fainelli --- include/linux/soc/brcmstb/brcmstb.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/brcmstb/brcmstb.h b/include/linux/soc/brcmstb/brcmstb.h index 8e884e0dda0a..f2b768852777 100644 --- a/include/linux/soc/brcmstb/brcmstb.h +++ b/include/linux/soc/brcmstb/brcmstb.h @@ -2,6 +2,8 @@ #ifndef __BRCMSTB_SOC_H #define __BRCMSTB_SOC_H +#include + static inline u32 BRCM_ID(u32 reg) { return reg >> 28 ? reg >> 16 : reg >> 8; @@ -12,6 +14,8 @@ static inline u32 BRCM_REV(u32 reg) return reg & 0xff; } +#if IS_ENABLED(CONFIG_SOC_BRCMSTB) + /* * Helper functions for getting family or product id from the * SoC driver. @@ -19,4 +23,16 @@ static inline u32 BRCM_REV(u32 reg) u32 brcmstb_get_family_id(void); u32 brcmstb_get_product_id(void); +#else +static inline u32 brcmstb_get_family_id(void) +{ + return 0; +} + +static inline u32 brcmstb_get_product_id(void) +{ + return 0; +} +#endif + #endif /* __BRCMSTB_SOC_H */ -- cgit v1.2.3 From 9cacf81f8161111db25f98e78a7a0e32ae142b3f Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Fri, 15 Jan 2021 08:34:59 -0800 Subject: bpf: Remove extra lock_sock for TCP_ZEROCOPY_RECEIVE Add custom implementation of getsockopt hook for TCP_ZEROCOPY_RECEIVE. We skip generic hooks for TCP_ZEROCOPY_RECEIVE and have a custom call in do_tcp_getsockopt using the on-stack data. This removes 3% overhead for locking/unlocking the socket. Without this patch: 3.38% 0.07% tcp_mmap [kernel.kallsyms] [k] __cgroup_bpf_run_filter_getsockopt | --3.30%--__cgroup_bpf_run_filter_getsockopt | --0.81%--__kmalloc With the patch applied: 0.52% 0.12% tcp_mmap [kernel.kallsyms] [k] __cgroup_bpf_run_filter_getsockopt_kern Note, exporting uapi/tcp.h requires removing netinet/tcp.h from test_progs.h because those headers have confliciting definitions. Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20210115163501.805133-2-sdf@google.com --- include/linux/bpf-cgroup.h | 27 +++++++++++++++++++++++---- include/linux/indirect_call_wrapper.h | 6 ++++++ 2 files changed, 29 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 72e69a0e1e8c..bcb2915e6124 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -147,6 +147,10 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, int __user *optlen, int max_optlen, int retval); +int __cgroup_bpf_run_filter_getsockopt_kern(struct sock *sk, int level, + int optname, void *optval, + int *optlen, int retval); + static inline enum bpf_cgroup_storage_type cgroup_storage_type( struct bpf_map *map) { @@ -364,10 +368,23 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, ({ \ int __ret = retval; \ if (cgroup_bpf_enabled) \ - __ret = __cgroup_bpf_run_filter_getsockopt(sock, level, \ - optname, optval, \ - optlen, max_optlen, \ - retval); \ + if (!(sock)->sk_prot->bpf_bypass_getsockopt || \ + !INDIRECT_CALL_INET_1((sock)->sk_prot->bpf_bypass_getsockopt, \ + tcp_bpf_bypass_getsockopt, \ + level, optname)) \ + __ret = __cgroup_bpf_run_filter_getsockopt( \ + sock, level, optname, optval, optlen, \ + max_optlen, retval); \ + __ret; \ +}) + +#define BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sock, level, optname, optval, \ + optlen, retval) \ +({ \ + int __ret = retval; \ + if (cgroup_bpf_enabled) \ + __ret = __cgroup_bpf_run_filter_getsockopt_kern( \ + sock, level, optname, optval, optlen, retval); \ __ret; \ }) @@ -452,6 +469,8 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, #define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, \ optlen, max_optlen, retval) ({ retval; }) +#define BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sock, level, optname, optval, \ + optlen, retval) ({ retval; }) #define BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock, level, optname, optval, optlen, \ kernel_optval) ({ 0; }) diff --git a/include/linux/indirect_call_wrapper.h b/include/linux/indirect_call_wrapper.h index 54c02c84906a..cfcfef37b2f1 100644 --- a/include/linux/indirect_call_wrapper.h +++ b/include/linux/indirect_call_wrapper.h @@ -60,4 +60,10 @@ #define INDIRECT_CALL_INET(f, f2, f1, ...) f(__VA_ARGS__) #endif +#if IS_ENABLED(CONFIG_INET) +#define INDIRECT_CALL_INET_1(f, f1, ...) INDIRECT_CALL_1(f, f1, __VA_ARGS__) +#else +#define INDIRECT_CALL_INET_1(f, f1, ...) f(__VA_ARGS__) +#endif + #endif -- cgit v1.2.3 From 20f2505fb436cfa674cf1f46aaa624f44d3d1d03 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Fri, 15 Jan 2021 08:35:00 -0800 Subject: bpf: Try to avoid kzalloc in cgroup/{s,g}etsockopt When we attach a bpf program to cgroup/getsockopt any other getsockopt() syscall starts incurring kzalloc/kfree cost. Let add a small buffer on the stack and use it for small (majority) {s,g}etsockopt values. The buffer is small enough to fit into the cache line and cover the majority of simple options (most of them are 4 byte ints). It seems natural to do the same for setsockopt, but it's a bit more involved when the BPF program modifies the data (where we have to kmalloc). The assumption is that for the majority of setsockopt calls (which are doing pure BPF options or apply policy) this will bring some benefit as well. Without this patch (we remove about 1% __kmalloc): 3.38% 0.07% tcp_mmap [kernel.kallsyms] [k] __cgroup_bpf_run_filter_getsockopt | --3.30%--__cgroup_bpf_run_filter_getsockopt | --0.81%--__kmalloc Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20210115163501.805133-3-sdf@google.com --- include/linux/filter.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 7fdce5407214..5b3137d7b690 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1298,6 +1298,11 @@ struct bpf_sysctl_kern { u64 tmp_reg; }; +#define BPF_SOCKOPT_KERN_BUF_SIZE 32 +struct bpf_sockopt_buf { + u8 data[BPF_SOCKOPT_KERN_BUF_SIZE]; +}; + struct bpf_sockopt_kern { struct sock *sk; u8 *optval; -- cgit v1.2.3 From a9ed15dae0755a0368735e0556a462d8519bdb05 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Fri, 15 Jan 2021 08:35:01 -0800 Subject: bpf: Split cgroup_bpf_enabled per attach type When we attach any cgroup hook, the rest (even if unused/unattached) start to contribute small overhead. In particular, the one we want to avoid is __cgroup_bpf_run_filter_skb which does two redirections to get to the cgroup and pushes/pulls skb. Let's split cgroup_bpf_enabled to be per-attach to make sure only used attach types trigger. I've dropped some existing high-level cgroup_bpf_enabled in some places because BPF_PROG_CGROUP_XXX_RUN macros usually have another cgroup_bpf_enabled check. I also had to copy-paste BPF_CGROUP_RUN_SA_PROG_LOCK for GETPEERNAME/GETSOCKNAME because type for cgroup_bpf_enabled[type] has to be constant and known at compile time. Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20210115163501.805133-4-sdf@google.com --- include/linux/bpf-cgroup.h | 38 ++++++++++++++++++++------------------ 1 file changed, 20 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index bcb2915e6124..0748fd87969e 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -23,8 +23,8 @@ struct ctl_table_header; #ifdef CONFIG_CGROUP_BPF -extern struct static_key_false cgroup_bpf_enabled_key; -#define cgroup_bpf_enabled static_branch_unlikely(&cgroup_bpf_enabled_key) +extern struct static_key_false cgroup_bpf_enabled_key[MAX_BPF_ATTACH_TYPE]; +#define cgroup_bpf_enabled(type) static_branch_unlikely(&cgroup_bpf_enabled_key[type]) DECLARE_PER_CPU(struct bpf_cgroup_storage*, bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); @@ -189,7 +189,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled) \ + if (cgroup_bpf_enabled(BPF_CGROUP_INET_INGRESS)) \ __ret = __cgroup_bpf_run_filter_skb(sk, skb, \ BPF_CGROUP_INET_INGRESS); \ \ @@ -199,7 +199,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled && sk && sk == skb->sk) { \ + if (cgroup_bpf_enabled(BPF_CGROUP_INET_EGRESS) && sk && sk == skb->sk) { \ typeof(sk) __sk = sk_to_full_sk(sk); \ if (sk_fullsock(__sk)) \ __ret = __cgroup_bpf_run_filter_skb(__sk, skb, \ @@ -211,7 +211,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_SK_PROG(sk, type) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled) { \ + if (cgroup_bpf_enabled(type)) { \ __ret = __cgroup_bpf_run_filter_sk(sk, type); \ } \ __ret; \ @@ -232,7 +232,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, type) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled) \ + if (cgroup_bpf_enabled(type)) \ __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \ NULL); \ __ret; \ @@ -241,7 +241,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, type, t_ctx) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled) { \ + if (cgroup_bpf_enabled(type)) { \ lock_sock(sk); \ __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \ t_ctx); \ @@ -256,8 +256,10 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_INET6_BIND_LOCK(sk, uaddr) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET6_BIND, NULL) -#define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (cgroup_bpf_enabled && \ - sk->sk_prot->pre_connect) +#define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) \ + ((cgroup_bpf_enabled(BPF_CGROUP_INET4_CONNECT) || \ + cgroup_bpf_enabled(BPF_CGROUP_INET6_CONNECT)) && \ + (sk)->sk_prot->pre_connect) #define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr) \ BPF_CGROUP_RUN_SA_PROG(sk, uaddr, BPF_CGROUP_INET4_CONNECT) @@ -301,7 +303,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(sock_ops, sk) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled) \ + if (cgroup_bpf_enabled(BPF_CGROUP_SOCK_OPS)) \ __ret = __cgroup_bpf_run_filter_sock_ops(sk, \ sock_ops, \ BPF_CGROUP_SOCK_OPS); \ @@ -311,7 +313,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled && (sock_ops)->sk) { \ + if (cgroup_bpf_enabled(BPF_CGROUP_SOCK_OPS) && (sock_ops)->sk) { \ typeof(sk) __sk = sk_to_full_sk((sock_ops)->sk); \ if (__sk && sk_fullsock(__sk)) \ __ret = __cgroup_bpf_run_filter_sock_ops(__sk, \ @@ -324,7 +326,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type, major, minor, access) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled) \ + if (cgroup_bpf_enabled(BPF_CGROUP_DEVICE)) \ __ret = __cgroup_bpf_check_dev_permission(type, major, minor, \ access, \ BPF_CGROUP_DEVICE); \ @@ -336,7 +338,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, count, pos) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled) \ + if (cgroup_bpf_enabled(BPF_CGROUP_SYSCTL)) \ __ret = __cgroup_bpf_run_filter_sysctl(head, table, write, \ buf, count, pos, \ BPF_CGROUP_SYSCTL); \ @@ -347,7 +349,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, kernel_optval) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled) \ + if (cgroup_bpf_enabled(BPF_CGROUP_SETSOCKOPT)) \ __ret = __cgroup_bpf_run_filter_setsockopt(sock, level, \ optname, optval, \ optlen, \ @@ -358,7 +360,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled) \ + if (cgroup_bpf_enabled(BPF_CGROUP_GETSOCKOPT)) \ get_user(__ret, optlen); \ __ret; \ }) @@ -367,7 +369,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, max_optlen, retval) \ ({ \ int __ret = retval; \ - if (cgroup_bpf_enabled) \ + if (cgroup_bpf_enabled(BPF_CGROUP_GETSOCKOPT)) \ if (!(sock)->sk_prot->bpf_bypass_getsockopt || \ !INDIRECT_CALL_INET_1((sock)->sk_prot->bpf_bypass_getsockopt, \ tcp_bpf_bypass_getsockopt, \ @@ -382,7 +384,7 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, optlen, retval) \ ({ \ int __ret = retval; \ - if (cgroup_bpf_enabled) \ + if (cgroup_bpf_enabled(BPF_CGROUP_GETSOCKOPT)) \ __ret = __cgroup_bpf_run_filter_getsockopt_kern( \ sock, level, optname, optval, optlen, retval); \ __ret; \ @@ -444,7 +446,7 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, return 0; } -#define cgroup_bpf_enabled (0) +#define cgroup_bpf_enabled(type) (0) #define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, type, t_ctx) ({ 0; }) #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0) #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; }) -- cgit v1.2.3 From 3b830a9c34d5897be07176ce4e6f2d75e2c8cfd7 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 18 Jan 2021 13:31:30 -0800 Subject: tty: convert tty_ldisc_ops 'read()' function to take a kernel pointer The tty line discipline .read() function was passed the final user pointer destination as an argument, which doesn't match the 'write()' function, and makes it very inconvenient to do a splice method for ttys. This is a conversion to use a kernel buffer instead. NOTE! It does this by passing the tty line discipline ->read() function an additional "cookie" to fill in, and an offset into the cookie data. The line discipline can fill in the cookie data with its own private information, and then the reader will repeat the read until either the cookie is cleared or it runs out of data. The only real user of this is N_HDLC, which can use this to handle big packets, even if the kernel buffer is smaller than the whole packet. Cc: Christoph Hellwig Cc: Greg Kroah-Hartman Cc: Al Viro Signed-off-by: Linus Torvalds --- include/linux/tty_ldisc.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h index b1e6043e9917..572a07976116 100644 --- a/include/linux/tty_ldisc.h +++ b/include/linux/tty_ldisc.h @@ -185,7 +185,8 @@ struct tty_ldisc_ops { void (*close)(struct tty_struct *); void (*flush_buffer)(struct tty_struct *tty); ssize_t (*read)(struct tty_struct *tty, struct file *file, - unsigned char __user *buf, size_t nr); + unsigned char *buf, size_t nr, + void **cookie, unsigned long offset); ssize_t (*write)(struct tty_struct *tty, struct file *file, const unsigned char *buf, size_t nr); int (*ioctl)(struct tty_struct *tty, struct file *file, -- cgit v1.2.3 From 7baf2429a1a965369b0ce44efb6315cdd515aa9c Mon Sep 17 00:00:00 2001 From: wenxu Date: Tue, 19 Jan 2021 16:31:50 +0800 Subject: net/sched: cls_flower add CT_FLAGS_INVALID flag support This patch add the TCA_FLOWER_KEY_CT_FLAGS_INVALID flag to match the ct_state with invalid for conntrack. Signed-off-by: wenxu Acked-by: Marcelo Ricardo Leitner Link: https://lore.kernel.org/r/1611045110-682-1-git-send-email-wenxu@ucloud.cn Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 46f901adf1a8..186dad231e30 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1353,8 +1353,8 @@ void skb_flow_dissect_ct(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, - u16 *ctinfo_map, - size_t mapsize); + u16 *ctinfo_map, size_t mapsize, + bool post_ct); void skb_flow_dissect_tunnel_info(const struct sk_buff *skb, struct flow_dissector *flow_dissector, -- cgit v1.2.3 From fcba4b2047a31a55e1cef73849363a3cf7c2736d Mon Sep 17 00:00:00 2001 From: Loic Poulain Date: Tue, 5 Jan 2021 17:44:35 +0100 Subject: mhi: unconstify mhi_event_config Some parameters may have to be determined at runtime. It is the case for the event ring MSI vector. Signed-off-by: Loic Poulain Reviewed-by: Manivannan Sadhasivam Signed-off-by: Manivannan Sadhasivam --- include/linux/mhi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 54afcae1709a..48f5c9168ae0 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -279,7 +279,7 @@ struct mhi_controller_config { u32 num_channels; const struct mhi_channel_config *ch_cfg; u32 num_events; - const struct mhi_event_config *event_cfg; + struct mhi_event_config *event_cfg; bool use_bounce_buf; bool m2_no_db; }; -- cgit v1.2.3 From 6ffcc18d9c0b4522c95aab71ff3ff5a56e699945 Mon Sep 17 00:00:00 2001 From: Carl Huang Date: Mon, 4 Jan 2021 18:11:28 +0800 Subject: mhi: use irq_flags if controller driver configures it If controller driver has specified the irq_flags, mhi uses this specified irq_flags. Otherwise, mhi uses default irq_flags. The purpose of this change is to support one MSI vector for QCA6390. MHI will use one same MSI vector too in this scenario. In case of one MSI vector, IRQ_NO_BALANCING is needed when irq handler is requested. The reason is if irq migration happens, the msi_data may change too. However, the msi_data is already programmed to QCA6390 hardware during initialization phase. This msi_data inconsistence will result in crash in kernel. Another issue is in case of one MSI vector, IRQF_NO_SUSPEND will trigger WARNINGS because QCA6390 wants to disable the IRQ during the suspend. To avoid above two issues, QCA6390 driver specifies the irq_flags in case of one MSI vector when mhi_register_controller is called. Signed-off-by: Carl Huang Reviewed-by: Manivannan Sadhasivam Signed-off-by: Manivannan Sadhasivam --- include/linux/mhi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 562862ff819c..b7138127664f 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -353,6 +353,7 @@ struct mhi_controller_config { * @fbc_download: MHI host needs to do complete image transfer (optional) * @pre_init: MHI host needs to do pre-initialization before power up * @wake_set: Device wakeup set flag + * @irq_flags: irq flags passed to request_irq (optional) * * Fields marked as (required) need to be populated by the controller driver * before calling mhi_register_controller(). For the fields marked as (optional) @@ -444,6 +445,7 @@ struct mhi_controller { bool fbc_download; bool pre_init; bool wake_set; + unsigned long irq_flags; }; /** -- cgit v1.2.3 From 0908c5aca31eb5e0c72d7a5dba422629b88e877d Mon Sep 17 00:00:00 2001 From: Kyle Tso Date: Thu, 14 Jan 2021 22:50:51 +0800 Subject: usb: typec: tcpm: AMS and Collision Avoidance This patch provides the implementation of Collision Avoidance introduced in PD3.0. The start of each Atomic Message Sequence (AMS) initiated by the port will be denied if the current AMS is not interruptible. The Source port will set the CC to SinkTxNG if it is going to initiate an AMS, and SinkTxOk otherwise. Meanwhile, any AMS initiated by a Sink port will be denied in TCPM if the port partner (Source) sets SinkTxNG except for HARD_RESET and SOFT_RESET. Tested-by: Hans de Goede Reviewed-by: Heikki Krogerus Signed-off-by: Kyle Tso Link: https://lore.kernel.org/r/20210114145053.1952756-2-kyletso@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/pd.h | 1 + include/linux/usb/tcpm.h | 4 ++++ 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/pd.h b/include/linux/usb/pd.h index bb9a782e1411..79599b90ba55 100644 --- a/include/linux/usb/pd.h +++ b/include/linux/usb/pd.h @@ -479,6 +479,7 @@ static inline unsigned int rdo_max_power(u32 rdo) #define PD_T_NEWSRC 250 /* Maximum of 275ms */ #define PD_T_SWAP_SRC_START 20 /* Minimum of 20ms */ #define PD_T_BIST_CONT_MODE 50 /* 30 - 60 ms */ +#define PD_T_SINK_TX 16 /* 16 - 20 ms */ #define PD_T_DRP_TRY 100 /* 75 - 150 ms */ #define PD_T_DRP_TRYWAIT 600 /* 400 - 800 ms */ diff --git a/include/linux/usb/tcpm.h b/include/linux/usb/tcpm.h index f4a18427f5c4..3af99f85e8b9 100644 --- a/include/linux/usb/tcpm.h +++ b/include/linux/usb/tcpm.h @@ -19,6 +19,10 @@ enum typec_cc_status { TYPEC_CC_RP_3_0, }; +/* Collision Avoidance */ +#define SINK_TX_NG TYPEC_CC_RP_1_5 +#define SINK_TX_OK TYPEC_CC_RP_3_0 + enum typec_cc_polarity { TYPEC_POLARITY_CC1, TYPEC_POLARITY_CC2, -- cgit v1.2.3 From 8dea75e11380fc59656fe965766ac192a831455f Mon Sep 17 00:00:00 2001 From: Kyle Tso Date: Thu, 14 Jan 2021 22:50:52 +0800 Subject: usb: typec: tcpm: Protocol Error handling PD3.0 Spec 6.8.1 describes how to handle Protocol Error. There are general rules defined in Table 6-61 which regulate incoming Message handling. If the incoming Message is unexpected, unsupported, or unrecognized, Protocol Error occurs. Follow the rules to handle these situations. Also consider PD2.0 connection (PD2.0 Spec Table 6-36) for backward compatibilities. To know the types of AMS in all the recipient's states, identify those AMS who are initiated by the port partner but not yet recorded in the current code. Besides, introduce a new state CHUNK_NOT_SUPP to delay the NOT_SUPPORTED message after receiving a chunked message. Tested-by: Hans de Goede Reviewed-by: Heikki Krogerus Signed-off-by: Kyle Tso Link: https://lore.kernel.org/r/20210114145053.1952756-3-kyletso@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/pd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/pd.h b/include/linux/usb/pd.h index 79599b90ba55..272454f9cd67 100644 --- a/include/linux/usb/pd.h +++ b/include/linux/usb/pd.h @@ -480,6 +480,7 @@ static inline unsigned int rdo_max_power(u32 rdo) #define PD_T_SWAP_SRC_START 20 /* Minimum of 20ms */ #define PD_T_BIST_CONT_MODE 50 /* 30 - 60 ms */ #define PD_T_SINK_TX 16 /* 16 - 20 ms */ +#define PD_T_CHUNK_NOT_SUPP 42 /* 40 - 50 ms */ #define PD_T_DRP_TRY 100 /* 75 - 150 ms */ #define PD_T_DRP_TRYWAIT 600 /* 400 - 800 ms */ -- cgit v1.2.3 From 742d33729a0df11c9d8d4625dbf21dd20cdefd44 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Wed, 20 Jan 2021 14:34:23 +0000 Subject: mm: Move immutable fields of 'struct vm_fault' into anonymous struct 'struct vm_fault' contains both information about the fault being serviced alongside mutable fields contributing to the state of the fault-handling logic. Unfortunately, the distinction between the two is not clear-cut, and a number of callers end up manipulating the structure temporarily before restoring it when returning. Try to clean this up by moving the immutable fault information into an anonymous struct, which will later be marked as 'const'. Ideally, the 'flags' field would be part of the new structure too, but it seems as though the ->page_mkwrite() path is not ready for this yet. Cc: Kirill A. Shutemov Suggested-by: Linus Torvalds Link: https://lore.kernel.org/r/CAHk-=whYs9XsO88iqJzN6NC=D-dp2m0oYXuOoZ=eWnvv=5OA+w@mail.gmail.com Signed-off-by: Will Deacon --- include/linux/mm.h | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 251a2339befb..b4a5cb9bff7d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -517,11 +517,14 @@ static inline bool fault_flag_allow_retry_first(unsigned int flags) * pgoff should be used in favour of virtual_address, if possible. */ struct vm_fault { - struct vm_area_struct *vma; /* Target VMA */ - unsigned int flags; /* FAULT_FLAG_xxx flags */ - gfp_t gfp_mask; /* gfp mask to be used for allocations */ - pgoff_t pgoff; /* Logical page offset based on vma */ - unsigned long address; /* Faulting virtual address */ + struct { + struct vm_area_struct *vma; /* Target VMA */ + gfp_t gfp_mask; /* gfp mask to be used for allocations */ + pgoff_t pgoff; /* Logical page offset based on vma */ + unsigned long address; /* Faulting virtual address */ + }; + unsigned int flags; /* FAULT_FLAG_xxx flags + * XXX: should really be 'const' */ pmd_t *pmd; /* Pointer to pmd entry matching * the 'address' */ pud_t *pud; /* Pointer to pud entry matching -- cgit v1.2.3 From 9d3af4b448a119ac81378d3bc775f1c4a2a7ff36 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 14 Jan 2021 15:24:19 +0000 Subject: mm: Pass 'address' to map to do_set_pte() and drop FAULT_FLAG_PREFAULT Rather than modifying the 'address' field of the 'struct vm_fault' passed to do_set_pte(), leave that to identify the real faulting address and pass in the virtual address to be mapped by the new pte as a separate argument. This makes FAULT_FLAG_PREFAULT redundant, as a prefault entry can be identified simply by comparing the new address parameter with the faulting address, so remove the redundant flag at the same time. Cc: Kirill A. Shutemov Cc: Linus Torvalds Signed-off-by: Will Deacon --- include/linux/mm.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index b4a5cb9bff7d..e0f056753bef 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -434,7 +434,6 @@ extern pgprot_t protection_map[16]; * @FAULT_FLAG_REMOTE: The fault is not for current task/mm. * @FAULT_FLAG_INSTRUCTION: The fault was during an instruction fetch. * @FAULT_FLAG_INTERRUPTIBLE: The fault can be interrupted by non-fatal signals. - * @FAULT_FLAG_PREFAULT: Fault was a prefault. * * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify * whether we would allow page faults to retry by specifying these two @@ -465,7 +464,6 @@ extern pgprot_t protection_map[16]; #define FAULT_FLAG_REMOTE 0x80 #define FAULT_FLAG_INSTRUCTION 0x100 #define FAULT_FLAG_INTERRUPTIBLE 0x200 -#define FAULT_FLAG_PREFAULT 0x400 /* * The default fault flags that should be used by most of the @@ -503,8 +501,7 @@ static inline bool fault_flag_allow_retry_first(unsigned int flags) { FAULT_FLAG_USER, "USER" }, \ { FAULT_FLAG_REMOTE, "REMOTE" }, \ { FAULT_FLAG_INSTRUCTION, "INSTRUCTION" }, \ - { FAULT_FLAG_INTERRUPTIBLE, "INTERRUPTIBLE" }, \ - { FAULT_FLAG_PREFAULT, "PREFAULT" } + { FAULT_FLAG_INTERRUPTIBLE, "INTERRUPTIBLE" } /* * vm_fault is filled by the pagefault handler and passed to the vma's @@ -995,7 +992,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) } vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page); -void do_set_pte(struct vm_fault *vmf, struct page *page); +void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr); vm_fault_t finish_fault(struct vm_fault *vmf); vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf); -- cgit v1.2.3 From 5857c9209ce58f8e262889539ccdf63e73ad7a93 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 14 Jan 2021 15:44:09 +0000 Subject: mm: Mark anonymous struct field of 'struct vm_fault' as 'const' The fields of this struct are only ever read after being initialised, so mark it 'const' before somebody tries to modify it again. GCC will then complain (with an error) about modification of these fields after they have been initialised, although LLVM currently allows them without even a warning: https://bugs.llvm.org/show_bug.cgi?id=48755 Hopefully, future versions of LLVM will emit a warning. Cc: Kirill A. Shutemov Cc: Linus Torvalds Signed-off-by: Will Deacon --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index e0f056753bef..7ff3d9817d38 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -514,7 +514,7 @@ static inline bool fault_flag_allow_retry_first(unsigned int flags) * pgoff should be used in favour of virtual_address, if possible. */ struct vm_fault { - struct { + const struct { struct vm_area_struct *vma; /* Target VMA */ gfp_t gfp_mask; /* gfp mask to be used for allocations */ pgoff_t pgoff; /* Logical page offset based on vma */ -- cgit v1.2.3 From 464e96aeb16ab4e071d353f69ebbddfa08c8d731 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Fri, 27 Nov 2020 11:15:43 -0800 Subject: keys: remove trailing semicolon in macro definition The macro use will already have a semicolon. Signed-off-by: Tom Rix Signed-off-by: David Howells Acked-by: Jarkko Sakkinen Reviewed-by: Ben Boeckel --- include/linux/key.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/key.h b/include/linux/key.h index 0f2e24f13c2b..1b0837c975b9 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -360,7 +360,7 @@ static inline struct key *request_key(struct key_type *type, * completion of keys undergoing construction with a non-interruptible wait. */ #define request_key_net(type, description, net, callout_info) \ - request_key_tag(type, description, net->key_domain, callout_info); + request_key_tag(type, description, net->key_domain, callout_info) /** * request_key_net_rcu - Request a key for a net namespace under RCU conditions @@ -372,7 +372,7 @@ static inline struct key *request_key(struct key_type *type, * network namespace are used. */ #define request_key_net_rcu(type, description, net) \ - request_key_rcu(type, description, net->key_domain); + request_key_rcu(type, description, net->key_domain) #endif /* CONFIG_NET */ extern int wait_for_key_construction(struct key *key, bool intr); -- cgit v1.2.3 From f14602caf4faef18999985bc87a414b552844ad2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micka=C3=ABl=20Sala=C3=BCn?= Date: Fri, 20 Nov 2020 19:04:22 +0100 Subject: PKCS#7: Fix missing include MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add missing linux/types.h for size_t. [DH: Changed from stddef.h] Signed-off-by: Mickaël Salaün Signed-off-by: David Howells Reviewed-by: Ben Boeckel --- include/linux/verification.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/verification.h b/include/linux/verification.h index 911ab7c2b1ab..a655923335ae 100644 --- a/include/linux/verification.h +++ b/include/linux/verification.h @@ -8,6 +8,8 @@ #ifndef _LINUX_VERIFICATION_H #define _LINUX_VERIFICATION_H +#include + /* * Indicate that both builtin trusted keys and secondary trusted keys * should be used. -- cgit v1.2.3 From 4993e1f9479a4161fd7d93e2b8b30b438f00cb0f Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 20 Nov 2020 19:04:23 +0100 Subject: certs: Fix blacklist flag type confusion MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit KEY_FLAG_KEEP is not meant to be passed to keyring_alloc() or key_alloc(), as these only take KEY_ALLOC_* flags. KEY_FLAG_KEEP has the same value as KEY_ALLOC_BYPASS_RESTRICTION, but fortunately only key_create_or_update() uses it. LSMs using the key_alloc hook don't check that flag. KEY_FLAG_KEEP is then ignored but fortunately (again) the root user cannot write to the blacklist keyring, so it is not possible to remove a key/hash from it. Fix this by adding a KEY_ALLOC_SET_KEEP flag that tells key_alloc() to set KEY_FLAG_KEEP on the new key. blacklist_init() can then, correctly, pass this to keyring_alloc(). We can also use this in ima_mok_init() rather than setting the flag manually. Note that this doesn't fix an observable bug with the current implementation but it is required to allow addition of new hashes to the blacklist in the future without making it possible for them to be removed. Fixes: 734114f8782f ("KEYS: Add a system blacklist keyring") Reported-by: Mickaël Salaün Signed-off-by: David Howells cc: Mickaël Salaün cc: Mimi Zohar Cc: David Woodhouse --- include/linux/key.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/key.h b/include/linux/key.h index 1b0837c975b9..7febc4881363 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -289,6 +289,7 @@ extern struct key *key_alloc(struct key_type *type, #define KEY_ALLOC_BUILT_IN 0x0004 /* Key is built into kernel */ #define KEY_ALLOC_BYPASS_RESTRICTION 0x0008 /* Override the check on restricted keyrings */ #define KEY_ALLOC_UID_KEYRING 0x0010 /* allocating a user or user session keyring */ +#define KEY_ALLOC_SET_KEEP 0x0020 /* Set the KEEP flag on the key/keyring */ extern void key_revoke(struct key *key); extern void key_invalidate(struct key *key); -- cgit v1.2.3 From 4c9a3a6c9c5478ce6b4b9db6c964244474676bcb Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 14 Jan 2021 09:04:37 +0100 Subject: parport: fix a kernel-doc markup The kernel-doc markup inside share.c is actually for __parport_register_driver. The actual goal seems to be to document parport_register_driver(). So, fix the existing markup and add a new one. Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/dc0778af8c466cc667409ead05876a5cfd3cbece.1610610937.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/parport.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/parport.h b/include/linux/parport.h index 1fb508c19e83..f981f794c850 100644 --- a/include/linux/parport.h +++ b/include/linux/parport.h @@ -297,6 +297,37 @@ int __must_check __parport_register_driver(struct parport_driver *, * parport_register_driver must be a macro so that KBUILD_MODNAME can * be expanded */ + +/** + * parport_register_driver - register a parallel port device driver + * @driver: structure describing the driver + * + * This can be called by a parallel port device driver in order + * to receive notifications about ports being found in the + * system, as well as ports no longer available. + * + * If devmodel is true then the new device model is used + * for registration. + * + * The @driver structure is allocated by the caller and must not be + * deallocated until after calling parport_unregister_driver(). + * + * If using the non device model: + * The driver's attach() function may block. The port that + * attach() is given will be valid for the duration of the + * callback, but if the driver wants to take a copy of the + * pointer it must call parport_get_port() to do so. Calling + * parport_register_device() on that port will do this for you. + * + * The driver's detach() function may block. The port that + * detach() is given will be valid for the duration of the + * callback, but if the driver wants to take a copy of the + * pointer it must call parport_get_port() to do so. + * + * + * Returns 0 on success. The non device model will always succeeds. + * but the new device model can fail and will return the error code. + **/ #define parport_register_driver(driver) \ __parport_register_driver(driver, THIS_MODULE, KBUILD_MODNAME) -- cgit v1.2.3 From e23bd83368af41ce420bd0eacb32817ccf7d3ca2 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 14 Jan 2021 09:04:41 +0100 Subject: firmware: stratix10-svc: fix kernel-doc markups There are some common comments marked, instead, with kernel-doc notation, which won't work. While here, rename an identifier, in order to match the function prototype below kernel-doc markup. Acked-by: Richard Gong Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/02a1eb47767e01e875d8840805b8b2d4f3c6bdee.1610610937.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/firmware/intel/stratix10-svc-client.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firmware/intel/stratix10-svc-client.h b/include/linux/firmware/intel/stratix10-svc-client.h index a93d85932eb9..ebc295647581 100644 --- a/include/linux/firmware/intel/stratix10-svc-client.h +++ b/include/linux/firmware/intel/stratix10-svc-client.h @@ -6,7 +6,7 @@ #ifndef __STRATIX10_SVC_CLIENT_H #define __STRATIX10_SVC_CLIENT_H -/** +/* * Service layer driver supports client names * * fpga: for FPGA configuration @@ -15,7 +15,7 @@ #define SVC_CLIENT_FPGA "fpga" #define SVC_CLIENT_RSU "rsu" -/** +/* * Status of the sent command, in bit number * * SVC_STATUS_OK: @@ -50,7 +50,7 @@ #define SVC_STATUS_ERROR 5 #define SVC_STATUS_NO_SUPPORT 6 -/** +/* * Flag bit for COMMAND_RECONFIG * * COMMAND_RECONFIG_FLAG_PARTIAL: @@ -58,7 +58,7 @@ */ #define COMMAND_RECONFIG_FLAG_PARTIAL 1 -/** +/* * Timeout settings for service clients: * timeout value used in Stratix10 FPGA manager driver. * timeout value used in RSU driver @@ -218,7 +218,7 @@ void stratix10_svc_free_memory(struct stratix10_svc_chan *chan, void *kaddr); int stratix10_svc_send(struct stratix10_svc_chan *chan, void *msg); /** - * intel_svc_done() - complete service request + * stratix10_svc_done() - complete service request * @chan: service channel assigned to the client * * This function is used by service client to inform service layer that -- cgit v1.2.3 From 3aa1141f9916af3258e2bc69e294e2cc07d2ddf1 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 14 Jan 2021 09:04:42 +0100 Subject: connector: fix a kernel-doc markup A function has a different name between their prototype and its kernel-doc markup. Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/889cfb141a98ae06d5bc79b744786ec2e8f92d93.1610610937.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/connector.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/connector.h b/include/linux/connector.h index 8ea860efea37..487350bb19c3 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -99,7 +99,7 @@ void cn_del_callback(const struct cb_id *id); int cn_netlink_send_mult(struct cn_msg *msg, u16 len, u32 portid, u32 group, gfp_t gfp_mask); /** - * cn_netlink_send_mult - Sends message to the specified groups. + * cn_netlink_send - Sends message to the specified groups. * * @msg: message header(with attached data). * @portid: destination port. -- cgit v1.2.3 From 909782ad0a36e4e5f875a431e280cba7b9b046fa Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 14 Jan 2021 09:04:44 +0100 Subject: memblock: fix kernel-doc markups Some identifiers have different names between their prototypes and the kernel-doc markup. Acked-by: Mike Rapoport Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/f3c65f61367993a607f9daf9dc1a3bdab1f0a040.1610610937.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/memblock.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index b93c44b9121e..9cc6da7b513e 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -272,7 +272,7 @@ void __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone, unsigned long *out_spfn, unsigned long *out_epfn); /** - * for_each_free_mem_range_in_zone - iterate through zone specific free + * for_each_free_mem_pfn_range_in_zone - iterate through zone specific free * memblock areas * @i: u64 used as loop variable * @zone: zone in which all of the memory blocks reside @@ -292,7 +292,7 @@ void __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone, __next_mem_pfn_range_in_zone(&i, zone, p_start, p_end)) /** - * for_each_free_mem_range_in_zone_from - iterate through zone specific + * for_each_free_mem_pfn_range_in_zone_from - iterate through zone specific * free memblock areas from a given point * @i: u64 used as loop variable * @zone: zone in which all of the memory blocks reside -- cgit v1.2.3 From 484cac791015e786f857c1cd98b7696aaf1e8a7a Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 14 Jan 2021 09:04:45 +0100 Subject: w1: fix a kernel-doc markup A function has a different name between their prototype and its kernel-doc markup. Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/2dc136ff6290d7c8919599d21bee244f31647c8c.1610610937.git.mchehab+huawei@kernel.org Signed-off-by: Jonathan Corbet --- include/linux/w1.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/w1.h b/include/linux/w1.h index 949d3b10e531..9a2a0ef39018 100644 --- a/include/linux/w1.h +++ b/include/linux/w1.h @@ -280,7 +280,7 @@ int w1_register_family(struct w1_family *family); void w1_unregister_family(struct w1_family *family); /** - * module_w1_driver() - Helper macro for registering a 1-Wire families + * module_w1_family() - Helper macro for registering a 1-Wire families * @__w1_family: w1_family struct * * Helper macro for 1-Wire families which do not do anything special in module -- cgit v1.2.3 From 660d2062190db131d2feaf19914e90f868fe285c Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 13 Jan 2021 10:11:35 +0100 Subject: crypto - shash: reduce minimum alignment of shash_desc structure Unlike many other structure types defined in the crypto API, the 'shash_desc' structure is permitted to live on the stack, which implies its contents may not be accessed by DMA masters. (This is due to the fact that the stack may be located in the vmalloc area, which requires a different virtual-to-physical translation than the one implemented by the DMA subsystem) Our definition of CRYPTO_MINALIGN_ATTR is based on ARCH_KMALLOC_MINALIGN, which may take DMA constraints into account on architectures that support non-cache coherent DMA such as ARM and arm64. In this case, the value is chosen to reflect the largest cacheline size in the system, in order to ensure that explicit cache maintenance as required by non-coherent DMA masters does not affect adjacent, unrelated slab allocations. On arm64, this value is currently set at 128 bytes. This means that applying CRYPTO_MINALIGN_ATTR to struct shash_desc is both unnecessary (as it is never used for DMA), and undesirable, given that it wastes stack space (on arm64, performing the alignment costs 112 bytes in the worst case, and the hole between the 'tfm' and '__ctx' members takes up another 120 bytes, resulting in an increased stack footprint of up to 232 bytes.) So instead, let's switch to the minimum SLAB alignment, which does not take DMA constraints into account. Note that this is a no-op for x86. Signed-off-by: Ard Biesheuvel Signed-off-by: Herbert Xu --- include/linux/crypto.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 9b55cd6b1f1b..da5e0d74bb2f 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -151,9 +151,12 @@ * The macro CRYPTO_MINALIGN_ATTR (along with the void * type in the actual * declaration) is used to ensure that the crypto_tfm context structure is * aligned correctly for the given architecture so that there are no alignment - * faults for C data types. In particular, this is required on platforms such - * as arm where pointers are 32-bit aligned but there are data types such as - * u64 which require 64-bit alignment. + * faults for C data types. On architectures that support non-cache coherent + * DMA, such as ARM or arm64, it also takes into account the minimal alignment + * that is required to ensure that the context struct member does not share any + * cachelines with the rest of the struct. This is needed to ensure that cache + * maintenance for non-coherent DMA (cache invalidation in particular) does not + * affect data that may be accessed by the CPU concurrently. */ #define CRYPTO_MINALIGN ARCH_KMALLOC_MINALIGN -- cgit v1.2.3 From 239319670e2a7c405eeb4b3e7721cf8bf8eef840 Mon Sep 17 00:00:00 2001 From: Ye Xiang Date: Tue, 15 Dec 2020 13:44:42 +0800 Subject: HID: hid-sensor-custom: Add custom sensor iio support Currently custom sensors properties are not decoded and it is up to user space to interpret. Some manufacturers already standardized the meaning of some custom sensors. They can be presented as a proper IIO sensor. We can identify these sensors based on manufacturer and serial number property in the report. This change is identifying hinge sensor when the manufacturer is "INTEL". This creates a platform device so that a sensor driver can be loaded to process these sensors. Signed-off-by: Ye Xiang Acked-by: Jiri Kosina Link: https://lore.kernel.org/r/20201215054444.9324-2-xiang.ye@intel.com Signed-off-by: Jonathan Cameron --- include/linux/hid-sensor-ids.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid-sensor-ids.h b/include/linux/hid-sensor-ids.h index d82a97e311d3..3bbdbccc5805 100644 --- a/include/linux/hid-sensor-ids.h +++ b/include/linux/hid-sensor-ids.h @@ -128,6 +128,10 @@ #define HID_USAGE_SENSOR_UNITS_DEGREES_PER_SECOND 0x15 /* Common selectors */ +#define HID_USAGE_SENSOR_PROP_DESC 0x200300 +#define HID_USAGE_SENSOR_PROP_FRIENDLY_NAME 0x200301 +#define HID_USAGE_SENSOR_PROP_SERIAL_NUM 0x200307 +#define HID_USAGE_SENSOR_PROP_MANUFACTURER 0x200305 #define HID_USAGE_SENSOR_PROP_REPORT_INTERVAL 0x20030E #define HID_USAGE_SENSOR_PROP_SENSITIVITY_ABS 0x20030F #define HID_USAGE_SENSOR_PROP_SENSITIVITY_RANGE_PCT 0x200310 @@ -158,4 +162,14 @@ #define HID_USAGE_SENSOR_PROP_REPORTING_STATE_NO_EVENTS_ENUM 0x200840 #define HID_USAGE_SENSOR_PROP_REPORTING_STATE_ALL_EVENTS_ENUM 0x200841 +/* Custom Sensor (2000e1) */ +#define HID_USAGE_SENSOR_HINGE 0x20020B +#define HID_USAGE_SENSOR_DATA_FIELD_LOCATION 0x200400 +#define HID_USAGE_SENSOR_DATA_FIELE_TIME_SINCE_SYS_BOOT 0x20052B +#define HID_USAGE_SENSOR_DATA_FIELD_CUSTOM_USAGE 0x200541 +#define HID_USAGE_SENSOR_DATA_FIELD_CUSTOM_VALUE_BASE 0x200543 +/* Custom Sensor data 28=>x>=0 */ +#define HID_USAGE_SENSOR_DATA_FIELD_CUSTOM_VALUE(x) \ + (HID_USAGE_SENSOR_DATA_FIELD_CUSTOM_VALUE_BASE + (x)) + #endif -- cgit v1.2.3 From 2f0df49c89acaa58571d509830bc481250699885 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Fri, 11 Dec 2020 16:37:54 -0500 Subject: jump_label: Do not profile branch annotations While running my branch profiler that checks for incorrect "likely" and "unlikely"s around the kernel, there's a large number of them that are incorrect due to being "static_branches". As static_branches are rather special, as they are likely or unlikely for other reasons than normal annotations are used for, there's no reason to have them be profiled. Expose the "unlikely_notrace" and "likely_notrace" so that the static_branch can use them, and have them be ignored by the branch profilers. Signed-off-by: Steven Rostedt (VMware) Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20201211163754.585174b9@gandalf.local.home --- include/linux/compiler.h | 2 ++ include/linux/jump_label.h | 12 ++++++------ 2 files changed, 8 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index b8fe0c23cfff..df5b405e6305 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -76,6 +76,8 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #else # define likely(x) __builtin_expect(!!(x), 1) # define unlikely(x) __builtin_expect(!!(x), 0) +# define likely_notrace(x) likely(x) +# define unlikely_notrace(x) unlikely(x) #endif /* Optimization barrier */ diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 32809624d422..d92691262f51 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -261,14 +261,14 @@ static __always_inline void jump_label_init(void) static __always_inline bool static_key_false(struct static_key *key) { - if (unlikely(static_key_count(key) > 0)) + if (unlikely_notrace(static_key_count(key) > 0)) return true; return false; } static __always_inline bool static_key_true(struct static_key *key) { - if (likely(static_key_count(key) > 0)) + if (likely_notrace(static_key_count(key) > 0)) return true; return false; } @@ -460,7 +460,7 @@ extern bool ____wrong_branch_error(void); branch = !arch_static_branch_jump(&(x)->key, true); \ else \ branch = ____wrong_branch_error(); \ - likely(branch); \ + likely_notrace(branch); \ }) #define static_branch_unlikely(x) \ @@ -472,13 +472,13 @@ extern bool ____wrong_branch_error(void); branch = arch_static_branch(&(x)->key, false); \ else \ branch = ____wrong_branch_error(); \ - unlikely(branch); \ + unlikely_notrace(branch); \ }) #else /* !CONFIG_JUMP_LABEL */ -#define static_branch_likely(x) likely(static_key_enabled(&(x)->key)) -#define static_branch_unlikely(x) unlikely(static_key_enabled(&(x)->key)) +#define static_branch_likely(x) likely_notrace(static_key_enabled(&(x)->key)) +#define static_branch_unlikely(x) unlikely_notrace(static_key_enabled(&(x)->key)) #endif /* CONFIG_JUMP_LABEL */ -- cgit v1.2.3 From 997acaf6b4b59c6a9c259740312a69ea549cc684 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 11 Jan 2021 15:37:07 +0000 Subject: lockdep: report broken irq restoration We generally expect local_irq_save() and local_irq_restore() to be paired and sanely nested, and so local_irq_restore() expects to be called with irqs disabled. Thus, within local_irq_restore() we only trace irq flag changes when unmasking irqs. This means that a sequence such as: | local_irq_disable(); | local_irq_save(flags); | local_irq_enable(); | local_irq_restore(flags); ... is liable to break things, as the local_irq_restore() would mask irqs without tracing this change. Similar problems may exist for architectures whose arch_irq_restore() function depends on being called with irqs disabled. We don't consider such sequences to be a good idea, so let's define those as forbidden, and add tooling to detect such broken cases. This patch adds debug code to WARN() when raw_local_irq_restore() is called with irqs enabled. As raw_local_irq_restore() is expected to pair with raw_local_irq_save(), it should never be called with irqs enabled. To avoid the possibility of circular header dependencies between irqflags.h and bug.h, the warning is handled in a separate C file. The new code is all conditional on a new CONFIG_DEBUG_IRQFLAGS symbol which is independent of CONFIG_TRACE_IRQFLAGS. As noted above such cases will confuse lockdep, so CONFIG_DEBUG_LOCKDEP now selects CONFIG_DEBUG_IRQFLAGS. Signed-off-by: Mark Rutland Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20210111153707.10071-1-mark.rutland@arm.com --- include/linux/irqflags.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 8de0e1373de7..600c10da321a 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -149,6 +149,17 @@ do { \ # define start_critical_timings() do { } while (0) #endif +#ifdef CONFIG_DEBUG_IRQFLAGS +extern void warn_bogus_irq_restore(void); +#define raw_check_bogus_irq_restore() \ + do { \ + if (unlikely(!arch_irqs_disabled())) \ + warn_bogus_irq_restore(); \ + } while (0) +#else +#define raw_check_bogus_irq_restore() do { } while (0) +#endif + /* * Wrap the arch provided IRQ routines to provide appropriate checks. */ @@ -162,6 +173,7 @@ do { \ #define raw_local_irq_restore(flags) \ do { \ typecheck(unsigned long, flags); \ + raw_check_bogus_irq_restore(); \ arch_local_irq_restore(flags); \ } while (0) #define raw_local_save_flags(flags) \ -- cgit v1.2.3 From 67e3242ee28052daa90e1fa193efc601939fde58 Mon Sep 17 00:00:00 2001 From: Lina Iyer Date: Wed, 20 Jan 2021 08:50:41 -0700 Subject: PM: domains: inform PM domain of a device's next wakeup Some devices may have a predictable interrupt pattern while executing usecases. An example would be the VSYNC interrupt associated with display devices. A 60 Hz display could cause a interrupt every 16 ms. If the device were in a PM domain, the domain would need to be powered up for device to resume and handle the interrupt. Entering a domain idle state saves power, only if the residency of the idle state is met. Without knowing the idle duration of the domain, the governor would just choose the deepest idle state that matches the QoS requirements. The domain might be powered off just as the device is expecting to wake up. If devices could inform PM frameworks of their next event, the parent PM domain's idle duration can be determined. So let's add the dev_pm_genpd_set_next_wakeup() API for the device to inform PM domains of the impending wakeup. This information will be the domain governor to determine the best idle state given the wakeup. Signed-off-by: Lina Iyer Reviewed-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 2ca919ae8d36..735583c0bc6d 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -9,6 +9,7 @@ #define _LINUX_PM_DOMAIN_H #include +#include #include #include #include @@ -191,6 +192,7 @@ struct generic_pm_domain_data { struct notifier_block *power_nb; int cpu; unsigned int performance_state; + ktime_t next_wakeup; void *data; }; @@ -217,6 +219,7 @@ int pm_genpd_remove(struct generic_pm_domain *genpd); int dev_pm_genpd_set_performance_state(struct device *dev, unsigned int state); int dev_pm_genpd_add_notifier(struct device *dev, struct notifier_block *nb); int dev_pm_genpd_remove_notifier(struct device *dev); +void dev_pm_genpd_set_next_wakeup(struct device *dev, ktime_t next); extern struct dev_power_governor simple_qos_governor; extern struct dev_power_governor pm_domain_always_on_gov; @@ -275,6 +278,9 @@ static inline int dev_pm_genpd_remove_notifier(struct device *dev) return -EOPNOTSUPP; } +static inline void dev_pm_genpd_set_next_wakeup(struct device *dev, ktime_t next) +{ } + #define simple_qos_governor (*(struct dev_power_governor *)(NULL)) #define pm_domain_always_on_gov (*(struct dev_power_governor *)(NULL)) #endif -- cgit v1.2.3 From c79aa080fb0f60a0e24c87014dc9c2f373e1379b Mon Sep 17 00:00:00 2001 From: Lina Iyer Date: Wed, 20 Jan 2021 08:50:42 -0700 Subject: PM: domains: use device's next wakeup to determine domain idle state Currently, a PM domain's idle state is determined based on whether the QoS requirements are met. However, even entering an idle state may waste power if the minimum residency requirements aren't fulfilled. CPU PM domains use the next timer wakeup for the CPUs in the domain to determine the sleep duration of the domain. This is compared with the idle state residencies to determine the optimal idle state. For other PM domains, determining the sleep length is not that straight forward. But if the device's next_event is available, we can use that to determine the sleep duration of the PM domain. Let's update the domain governor logic to check for idle state residency based on the next wakeup of devices as well as QoS constraints. But since, not all domains may contain devices capable of specifying the next wakeup, let's enable this additional check only if specified by the domain's flags when initializing the domain. Signed-off-by: Lina Iyer Reviewed-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 735583c0bc6d..dfcfbcecc34b 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -56,6 +56,10 @@ * * GENPD_FLAG_RPM_ALWAYS_ON: Instructs genpd to always keep the PM domain * powered on except for system suspend. + * + * GENPD_FLAG_MIN_RESIDENCY: Enable the genpd governor to consider its + * components' next wakeup when determining the + * optimal idle state. */ #define GENPD_FLAG_PM_CLK (1U << 0) #define GENPD_FLAG_IRQ_SAFE (1U << 1) @@ -63,6 +67,7 @@ #define GENPD_FLAG_ACTIVE_WAKEUP (1U << 3) #define GENPD_FLAG_CPU_DOMAIN (1U << 4) #define GENPD_FLAG_RPM_ALWAYS_ON (1U << 5) +#define GENPD_FLAG_MIN_RESIDENCY (1U << 6) enum gpd_status { GENPD_STATE_ON = 0, /* PM domain is on */ @@ -130,6 +135,7 @@ struct generic_pm_domain { unsigned int state); struct gpd_dev_ops dev_ops; s64 max_off_time_ns; /* Maximum allowed "suspended" time. */ + ktime_t next_wakeup; /* Maintained by the domain governor */ bool max_off_time_changed; bool cached_power_down_ok; bool cached_power_down_state_idx; -- cgit v1.2.3 From f3196bb0f14c0ffb5089c15668bda196c98d3900 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Fri, 11 Dec 2020 22:12:16 -0800 Subject: net/mlx5: Introduce vhca state event notifier vhca state events indicates change in the state of the vhca that may occur due to a SF allocation, deallocation or enabling/disabling the SF HCA. Introduce vhca state event handler which will be used by SF devlink port manager and SF hardware id allocator in subsequent patches to act on the event. This enables single entity to subscribe, query and rearm the event for a function. Signed-off-by: Parav Pandit Reviewed-by: Vu Pham Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f93bfe7473aa..ffba0786051e 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -507,6 +507,7 @@ struct mlx5_devcom; struct mlx5_fw_reset; struct mlx5_eq_table; struct mlx5_irq_table; +struct mlx5_vhca_state_notifier; struct mlx5_rate_limit { u32 rate; @@ -603,6 +604,9 @@ struct mlx5_priv { struct mlx5_bfreg_data bfregs; struct mlx5_uars_page *uar; +#ifdef CONFIG_MLX5_SF + struct mlx5_vhca_state_notifier *vhca_state_notifier; +#endif }; enum mlx5_device_state { -- cgit v1.2.3 From 90d010b8634b89a97ca3b7aa6a88fd566fc77717 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Fri, 11 Dec 2020 22:12:17 -0800 Subject: net/mlx5: SF, Add auxiliary device support Introduce API to add and delete an auxiliary device for an SF. Each SF has its own dedicated window in the PCI BAR 2. SF device is similar to PCI PF and VF that supports multiple class of devices such as net, rdma and vdpa. SF device will be added or removed in subsequent patch during SF devlink port function state change command. A subfunction device exposes user supplied subfunction number which will be further used by systemd/udev to have deterministic name for its netdevice and rdma device. An mlx5 subfunction auxiliary device example: $ devlink dev eswitch set pci/0000:06:00.0 mode switchdev $ devlink port show pci/0000:06:00.0/65535: type eth netdev ens2f0np0 flavour physical port 0 splittable false $ devlink port add pci/0000:06:00.0 flavour pcisf pfnum 0 sfnum 88 pci/0000:08:00.0/32768: type eth netdev eth6 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false function: hw_addr 00:00:00:00:00:00 state inactive opstate detached $ devlink port show ens2f0npf0sf88 pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false function: hw_addr 00:00:00:00:88:88 state inactive opstate detached $ devlink port function set ens2f0npf0sf88 hw_addr 00:00:00:00:88:88 state active On activation, $ ls -l /sys/bus/auxiliary/devices/ mlx5_core.sf.4 -> ../../../devices/pci0000:00/0000:00:03.0/0000:06:00.0/mlx5_core.sf.4 $ cat /sys/bus/auxiliary/devices/mlx5_core.sf.4/sfnum 88 Signed-off-by: Parav Pandit Reviewed-by: Vu Pham Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index ffba0786051e..08e5fbe97df0 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -508,6 +508,7 @@ struct mlx5_fw_reset; struct mlx5_eq_table; struct mlx5_irq_table; struct mlx5_vhca_state_notifier; +struct mlx5_sf_dev_table; struct mlx5_rate_limit { u32 rate; @@ -606,6 +607,7 @@ struct mlx5_priv { struct mlx5_uars_page *uar; #ifdef CONFIG_MLX5_SF struct mlx5_vhca_state_notifier *vhca_state_notifier; + struct mlx5_sf_dev_table *sf_dev_table; #endif }; -- cgit v1.2.3 From 1958fc2f0712ae771bfd2351b55e5a5b6b0bcfa4 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Fri, 11 Dec 2020 22:12:18 -0800 Subject: net/mlx5: SF, Add auxiliary device driver Add auxiliary device driver for mlx5 subfunction auxiliary device. A mlx5 subfunction is similar to PCI PF and VF. For a subfunction an auxiliary device is created. As a result, when mlx5 SF auxiliary device binds to the driver, its netdev and rdma device are created, they appear as $ ls -l /sys/bus/auxiliary/devices/ mlx5_core.sf.4 -> ../../../devices/pci0000:00/0000:00:03.0/0000:06:00.0/mlx5_core.sf.4 $ ls -l /sys/class/net/eth1/device /sys/class/net/eth1/device -> ../../../mlx5_core.sf.4 $ cat /sys/bus/auxiliary/devices/mlx5_core.sf.4/sfnum 88 $ devlink dev show pci/0000:06:00.0 auxiliary/mlx5_core.sf.4 $ devlink port show auxiliary/mlx5_core.sf.4/1 auxiliary/mlx5_core.sf.4/1: type eth netdev p0sf88 flavour virtual port 0 splittable false $ rdma link show mlx5_0/1 link mlx5_0/1 state ACTIVE physical_state LINK_UP netdev p0sf88 $ rdma dev show 8: rocep6s0f1: node_type ca fw 16.29.0550 node_guid 248a:0703:00b3:d113 sys_image_guid 248a:0703:00b3:d112 13: mlx5_0: node_type ca fw 16.29.0550 node_guid 0000:00ff:fe00:8888 sys_image_guid 248a:0703:00b3:d112 In future, devlink device instance name will adapt to have sfnum annotation using either an alias or as devlink instance name described in RFC [1]. [1] https://lore.kernel.org/netdev/20200519092258.GF4655@nanopsycho/ Signed-off-by: Parav Pandit Reviewed-by: Vu Pham Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 08e5fbe97df0..48e3638b1185 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -193,7 +193,8 @@ enum port_state_policy { enum mlx5_coredev_type { MLX5_COREDEV_PF, - MLX5_COREDEV_VF + MLX5_COREDEV_VF, + MLX5_COREDEV_SF, }; struct mlx5_field_desc { @@ -608,6 +609,7 @@ struct mlx5_priv { #ifdef CONFIG_MLX5_SF struct mlx5_vhca_state_notifier *vhca_state_notifier; struct mlx5_sf_dev_table *sf_dev_table; + struct mlx5_core_dev *parent_mdev; #endif }; -- cgit v1.2.3 From 8f01054186683fe0986d54d584aa13723d51edce Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Fri, 11 Dec 2020 22:12:21 -0800 Subject: net/mlx5: SF, Add port add delete functionality To handle SF port management outside of the eswitch as independent software layer, introduce eswitch notifier APIs so that mlx5 upper layer who wish to support sf port management in switchdev mode can perform its task whenever eswitch mode is set to switchdev or before eswitch is disabled. Initialize sf port table on such eswitch event. Add SF port add and delete functionality in switchdev mode. Destroy all SF ports when eswitch is disabled. Expose SF port add and delete to user via devlink commands. $ devlink dev eswitch set pci/0000:06:00.0 mode switchdev $ devlink port show pci/0000:06:00.0/65535: type eth netdev ens2f0np0 flavour physical port 0 splittable false $ devlink port add pci/0000:06:00.0 flavour pcisf pfnum 0 sfnum 88 pci/0000:06:00.0/32768: type eth netdev eth6 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false function: hw_addr 00:00:00:00:00:00 state inactive opstate detached $ devlink port show ens2f0npf0sf88 pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false function: hw_addr 00:00:00:00:00:00 state inactive opstate detached or by its unique port index: $ devlink port show pci/0000:06:00.0/32768 pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false function: hw_addr 00:00:00:00:00:00 state inactive opstate detached $ devlink port show ens2f0npf0sf88 -jp { "port": { "pci/0000:06:00.0/32768": { "type": "eth", "netdev": "ens2f0npf0sf88", "flavour": "pcisf", "controller": 0, "pfnum": 0, "sfnum": 88, "external": false, "splittable": false, "function": { "hw_addr": "00:00:00:00:00:00", "state": "inactive", "opstate": "detached" } } } } Signed-off-by: Parav Pandit Reviewed-by: Vu Pham Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 48e3638b1185..7e357c7f0d5e 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -510,6 +510,8 @@ struct mlx5_eq_table; struct mlx5_irq_table; struct mlx5_vhca_state_notifier; struct mlx5_sf_dev_table; +struct mlx5_sf_hw_table; +struct mlx5_sf_table; struct mlx5_rate_limit { u32 rate; @@ -611,6 +613,10 @@ struct mlx5_priv { struct mlx5_sf_dev_table *sf_dev_table; struct mlx5_core_dev *parent_mdev; #endif +#ifdef CONFIG_MLX5_SF_MANAGER + struct mlx5_sf_hw_table *sf_hw_table; + struct mlx5_sf_table *sf_table; +#endif }; enum mlx5_device_state { -- cgit v1.2.3 From 8e7f37f2aaa56b723a24f6872817cf9c6410b613 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 7 Dec 2020 17:41:02 -0800 Subject: mm: Add mem_dump_obj() to print source of memory block There are kernel facilities such as per-CPU reference counts that give error messages in generic handlers or callbacks, whose messages are unenlightening. In the case of per-CPU reference-count underflow, this is not a problem when creating a new use of this facility because in that case the bug is almost certainly in the code implementing that new use. However, trouble arises when deploying across many systems, which might exercise corner cases that were not seen during development and testing. Here, it would be really nice to get some kind of hint as to which of several uses the underflow was caused by. This commit therefore exposes a mem_dump_obj() function that takes a pointer to memory (which must still be allocated if it has been dynamically allocated) and prints available information on where that memory came from. This pointer can reference the middle of the block as well as the beginning of the block, as needed by things like RCU callback functions and timer handlers that might not know where the beginning of the memory block is. These functions and handlers can use mem_dump_obj() to print out better hints as to where the problem might lie. The information printed can depend on kernel configuration. For example, the allocation return address can be printed only for slab and slub, and even then only when the necessary debug has been enabled. For slab, build with CONFIG_DEBUG_SLAB=y, and either use sizes with ample space to the next power of two or use the SLAB_STORE_USER when creating the kmem_cache structure. For slub, build with CONFIG_SLUB_DEBUG=y and boot with slub_debug=U, or pass SLAB_STORE_USER to kmem_cache_create() if more focused use is desired. Also for slub, use CONFIG_STACKTRACE to enable printing of the allocation-time stack trace. Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Andrew Morton Cc: Reported-by: Andrii Nakryiko [ paulmck: Convert to printing and change names per Joonsoo Kim. ] [ paulmck: Move slab definition per Stephen Rothwell and kbuild test robot. ] [ paulmck: Handle CONFIG_MMU=n case where vmalloc() is kmalloc(). ] [ paulmck: Apply Vlastimil Babka feedback on slab.c kmem_provenance(). ] [ paulmck: Extract more info from !SLUB_DEBUG per Joonsoo Kim. ] [ paulmck: Explicitly check for small pointers per Naresh Kamboju. ] Acked-by: Joonsoo Kim Acked-by: Vlastimil Babka Tested-by: Naresh Kamboju Signed-off-by: Paul E. McKenney --- include/linux/mm.h | 2 ++ include/linux/slab.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 5299b90a6c40..af7d050900e7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3169,5 +3169,7 @@ unsigned long wp_shared_mapping_range(struct address_space *mapping, extern int sysctl_nr_trim_pages; +void mem_dump_obj(void *object); + #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ diff --git a/include/linux/slab.h b/include/linux/slab.h index be4ba5867ac5..7ae604076767 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -186,6 +186,8 @@ void kfree(const void *); void kfree_sensitive(const void *); size_t __ksize(const void *); size_t ksize(const void *); +bool kmem_valid_obj(void *object); +void kmem_dump_obj(void *object); #ifdef CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR void __check_heap_object(const void *ptr, unsigned long n, struct page *page, -- cgit v1.2.3 From 98f180837a896ecedf8f7e12af22b57f271d43c9 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 8 Dec 2020 16:13:57 -0800 Subject: mm: Make mem_dump_obj() handle vmalloc() memory This commit adds vmalloc() support to mem_dump_obj(). Note that the vmalloc_dump_obj() function combines the checking and dumping, in contrast with the split between kmem_valid_obj() and kmem_dump_obj(). The reason for the difference is that the checking in the vmalloc() case involves acquiring a global lock, and redundant acquisitions of global locks should be avoided, even on not-so-fast paths. Note that this change causes on-stack variables to be reported as vmalloc() storage from kernel_clone() or similar, depending on the degree of inlining that your compiler does. This is likely more helpful than the earlier "non-paged (local) memory". Cc: Andrew Morton Cc: Joonsoo Kim Cc: Reported-by: Andrii Nakryiko Acked-by: Vlastimil Babka Tested-by: Naresh Kamboju Signed-off-by: Paul E. McKenney --- include/linux/vmalloc.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 80c0181c411d..c18f4751a704 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -246,4 +246,10 @@ pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms) int register_vmap_purge_notifier(struct notifier_block *nb); int unregister_vmap_purge_notifier(struct notifier_block *nb); +#ifdef CONFIG_MMU +bool vmalloc_dump_obj(void *object); +#else +static inline bool vmalloc_dump_obj(void *object) { return false; } +#endif + #endif /* _LINUX_VMALLOC_H */ -- cgit v1.2.3 From e7ed11ee945438b737e2ae2370e35591e16ec371 Mon Sep 17 00:00:00 2001 From: Yousuk Seung Date: Wed, 20 Jan 2021 12:41:55 -0800 Subject: tcp: add TTL to SCM_TIMESTAMPING_OPT_STATS This patch adds TCP_NLA_TTL to SCM_TIMESTAMPING_OPT_STATS that exports the time-to-live or hop limit of the latest incoming packet with SCM_TSTAMP_ACK. The value exported may not be from the packet that acks the sequence when incoming packets are aggregated. Exporting the time-to-live or hop limit value of incoming packets helps to estimate the hop count of the path of the flow that may change over time. Signed-off-by: Yousuk Seung Signed-off-by: Eric Dumazet Signed-off-by: Neal Cardwell Link: https://lore.kernel.org/r/20210120204155.552275-1-ysseung@google.com Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 2 +- include/linux/tcp.h | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 186dad231e30..9313b5aaf45b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3859,7 +3859,7 @@ static inline bool skb_defer_rx_timestamp(struct sk_buff *skb) void skb_complete_tx_timestamp(struct sk_buff *skb, struct skb_shared_hwtstamps *hwtstamps); -void __skb_tstamp_tx(struct sk_buff *orig_skb, +void __skb_tstamp_tx(struct sk_buff *orig_skb, const struct sk_buff *ack_skb, struct skb_shared_hwtstamps *hwtstamps, struct sock *sk, int tstype); diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 2f87377e9af7..48d8a363319e 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -496,7 +496,8 @@ static inline u32 tcp_saved_syn_len(const struct saved_syn *saved_syn) } struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, - const struct sk_buff *orig_skb); + const struct sk_buff *orig_skb, + const struct sk_buff *ack_skb); static inline u16 tcp_mss_clamp(const struct tcp_sock *tp, u16 mss) { -- cgit v1.2.3 From d03b195b5aa015f6c11988b86a3625f8d5dbac52 Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Tue, 19 Jan 2021 14:08:13 +0200 Subject: sch_htb: Hierarchical QoS hardware offload HTB doesn't scale well because of contention on a single lock, and it also consumes CPU. This patch adds support for offloading HTB to hardware that supports hierarchical rate limiting. In the offload mode, HTB passes control commands to the driver using ndo_setup_tc. The driver has to replicate the whole hierarchy of classes and their settings (rate, ceil) in the NIC. Every modification of the HTB tree caused by the admin results in ndo_setup_tc being called. After this setup, the HTB algorithm is done completely in the NIC. An SQ (send queue) is created for every leaf class and attached to the hierarchy, so that the NIC can calculate and obey aggregated rate limits, too. In the future, it can be changed, so that multiple SQs will back a single leaf class. ndo_select_queue is responsible for selecting the right queue that serves the traffic class of each packet. The data path works as follows: a packet is classified by clsact, the driver selects a hardware queue according to its class, and the packet is enqueued into this queue's qdisc. This solution addresses two main problems of scaling HTB: 1. Contention by flow classification. Currently the filters are attached to the HTB instance as follows: # tc filter add dev eth0 parent 1:0 protocol ip flower dst_port 80 classid 1:10 It's possible to move classification to clsact egress hook, which is thread-safe and lock-free: # tc filter add dev eth0 egress protocol ip flower dst_port 80 action skbedit priority 1:10 This way classification still happens in software, but the lock contention is eliminated, and it happens before selecting the TX queue, allowing the driver to translate the class to the corresponding hardware queue in ndo_select_queue. Note that this is already compatible with non-offloaded HTB and doesn't require changes to the kernel nor iproute2. 2. Contention by handling packets. HTB is not multi-queue, it attaches to a whole net device, and handling of all packets takes the same lock. When HTB is offloaded, it registers itself as a multi-queue qdisc, similarly to mq: HTB is attached to the netdev, and each queue has its own qdisc. Some features of HTB may be not supported by some particular hardware, for example, the maximum number of classes may be limited, the granularity of rate and ceil parameters may be different, etc. - so, the offload is not enabled by default, a new parameter is used to enable it: # tc qdisc replace dev eth0 root handle 1: htb offload Signed-off-by: Maxim Mikityanskiy Reviewed-by: Tariq Toukan Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ef517254367d..9e8572533d8e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -858,6 +858,7 @@ enum tc_setup_type { TC_SETUP_QDISC_ETS, TC_SETUP_QDISC_TBF, TC_SETUP_QDISC_FIFO, + TC_SETUP_QDISC_HTB, }; /* These structures hold the attributes of bpf state that are being passed -- cgit v1.2.3 From 214baf22870cfa437522f3bd4fbae56338674b04 Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Tue, 19 Jan 2021 14:08:15 +0200 Subject: net/mlx5e: Support HTB offload This commit adds support for HTB offload in the mlx5e driver. Performance: NIC: Mellanox ConnectX-6 Dx CPU: Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz (24 cores with HT) 100 Gbit/s line rate, 500 UDP streams @ ~200 Mbit/s each 48 traffic classes, flower used for steering No shaping (rate limits set to 4 Gbit/s per TC) - checking for max throughput. Baseline: 98.7 Gbps, 8.25 Mpps HTB: 6.7 Gbps, 0.56 Mpps HTB offload: 95.6 Gbps, 8.00 Mpps Limitations: 1. 256 leaf nodes, 3 levels of depth. 2. Granularity for ceil is 1 Mbit/s. Rates are converted to weights, and the bandwidth is split among the siblings according to these weights. Other parameters for classes are not supported. Ethtool statistics support for QoS SQs are also added. The counters are called qos_txN_*, where N is the QoS queue number (starting from 0, the numeration is separate from the normal SQs), and * is the counter name (the counters are the same as for the normal SQs). Signed-off-by: Maxim Mikityanskiy Reviewed-by: Tariq Toukan Signed-off-by: Jakub Kicinski --- include/linux/mlx5/mlx5_ifc.h | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 823411e288c0..71ae6aac3410 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -842,11 +842,16 @@ struct mlx5_ifc_qos_cap_bits { u8 reserved_at_4[0x1]; u8 packet_pacing_burst_bound[0x1]; u8 packet_pacing_typical_size[0x1]; - u8 reserved_at_7[0x4]; + u8 reserved_at_7[0x1]; + u8 nic_sq_scheduling[0x1]; + u8 nic_bw_share[0x1]; + u8 nic_rate_limit[0x1]; u8 packet_pacing_uid[0x1]; u8 reserved_at_c[0x14]; - u8 reserved_at_20[0x20]; + u8 reserved_at_20[0xb]; + u8 log_max_qos_nic_queue_group[0x5]; + u8 reserved_at_30[0x10]; u8 packet_pacing_max_rate[0x20]; @@ -3347,7 +3352,7 @@ struct mlx5_ifc_sqc_bits { u8 reserved_at_e0[0x10]; u8 packet_pacing_rate_limit_index[0x10]; u8 tis_lst_sz[0x10]; - u8 reserved_at_110[0x10]; + u8 qos_queue_group_id[0x10]; u8 reserved_at_120[0x40]; @@ -3362,6 +3367,7 @@ enum { SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT = 0x1, SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT_TC = 0x2, SCHEDULING_CONTEXT_ELEMENT_TYPE_PARA_VPORT_TC = 0x3, + SCHEDULING_CONTEXT_ELEMENT_TYPE_QUEUE_GROUP = 0x4, }; enum { @@ -4805,6 +4811,7 @@ struct mlx5_ifc_query_scheduling_element_out_bits { enum { SCHEDULING_HIERARCHY_E_SWITCH = 0x2, + SCHEDULING_HIERARCHY_NIC = 0x3, }; struct mlx5_ifc_query_scheduling_element_in_bits { -- cgit v1.2.3 From 9d0735519f99948c5b5c22426b682ced7f7af9be Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 20 Jan 2021 16:41:56 +0100 Subject: rtc: remove sirfsoc driver The CSR SiRF prima2/atlas platforms are getting removed, so this driver is no longer needed. Cc: Barry Song Signed-off-by: Arnd Bergmann Acked-by: Barry Song Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20210120154158.1860736-2-arnd@kernel.org --- include/linux/rtc/sirfsoc_rtciobrg.h | 21 --------------------- 1 file changed, 21 deletions(-) delete mode 100644 include/linux/rtc/sirfsoc_rtciobrg.h (limited to 'include/linux') diff --git a/include/linux/rtc/sirfsoc_rtciobrg.h b/include/linux/rtc/sirfsoc_rtciobrg.h deleted file mode 100644 index b31f2856733d..000000000000 --- a/include/linux/rtc/sirfsoc_rtciobrg.h +++ /dev/null @@ -1,21 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * RTC I/O Bridge interfaces for CSR SiRFprimaII - * ARM access the registers of SYSRTC, GPSRTC and PWRC through this module - * - * Copyright (c) 2011 Cambridge Silicon Radio Limited, a CSR plc group company. - */ -#ifndef _SIRFSOC_RTC_IOBRG_H_ -#define _SIRFSOC_RTC_IOBRG_H_ - -struct regmap_config; - -extern void sirfsoc_rtc_iobrg_besyncing(void); - -extern u32 sirfsoc_rtc_iobrg_readl(u32 addr); - -extern void sirfsoc_rtc_iobrg_writel(u32 val, u32 addr); -struct regmap *devm_regmap_init_iobg(struct device *dev, - const struct regmap_config *config); - -#endif -- cgit v1.2.3 From 2f63296578cad1ae681152d5b2122a4595195f16 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 23 Jan 2021 10:06:09 -0800 Subject: iomap: pass a flags argument to iomap_dio_rw Pass a set of flags to iomap_dio_rw instead of the boolean wait_for_completion argument. The IOMAP_DIO_FORCE_WAIT flag replaces the wait_for_completion, but only needs to be passed when the iocb isn't synchronous to start with to simplify the callers. Signed-off-by: Christoph Hellwig Reviewed-by: Dave Chinner Reviewed-by: Brian Foster [djwong: rework xfs_file.c so that we can push iomap changes separately] Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- include/linux/iomap.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 5bd3cac4df9c..be4e1e1e01e8 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -256,12 +256,18 @@ struct iomap_dio_ops { struct bio *bio, loff_t file_offset); }; +/* + * Wait for the I/O to complete in iomap_dio_rw even if the kiocb is not + * synchronous. + */ +#define IOMAP_DIO_FORCE_WAIT (1 << 0) + ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, - bool wait_for_completion); + unsigned int dio_flags); struct iomap_dio *__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, - bool wait_for_completion); + unsigned int dio_flags); ssize_t iomap_dio_complete(struct iomap_dio *dio); int iomap_dio_iopoll(struct kiocb *kiocb, bool spin); -- cgit v1.2.3 From 213f627104daf8589aad8ee73fcaeb603ab0af15 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 23 Jan 2021 10:06:10 -0800 Subject: iomap: add a IOMAP_DIO_OVERWRITE_ONLY flag Add a flag to signal that only pure overwrites are allowed. Signed-off-by: Christoph Hellwig Reviewed-by: Dave Chinner Reviewed-by: Brian Foster Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- include/linux/iomap.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index be4e1e1e01e8..1a86f520de56 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -122,6 +122,7 @@ struct iomap_page_ops { #define IOMAP_FAULT (1 << 3) /* mapping for page fault */ #define IOMAP_DIRECT (1 << 4) /* direct I/O */ #define IOMAP_NOWAIT (1 << 5) /* do not block */ +#define IOMAP_OVERWRITE_ONLY (1 << 6) /* only pure overwrites allowed */ struct iomap_ops { /* @@ -262,6 +263,13 @@ struct iomap_dio_ops { */ #define IOMAP_DIO_FORCE_WAIT (1 << 0) +/* + * Do not allocate blocks or zero partial blocks, but instead fall back to + * the caller by returning -EAGAIN. Used to optimize direct I/O writes that + * are not aligned to the file system block size. + */ +#define IOMAP_DIO_OVERWRITE_ONLY (1 << 1) + ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, unsigned int dio_flags); -- cgit v1.2.3 From 6f1c0ea133a6e4a193a7b285efe209664caeea43 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Fri, 22 Jan 2021 18:19:48 +0000 Subject: net: introduce a netdev feature for UDP GRO forwarding Introduce a new netdev feature, NETIF_F_GRO_UDP_FWD, to allow user to turn UDP GRO on and off for forwarding. Defaults to off to not change current datapath. Suggested-by: Paolo Abeni Signed-off-by: Alexander Lobakin Signed-off-by: Jakub Kicinski --- include/linux/netdev_features.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 934de56644e7..c06d6aaba9df 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -84,6 +84,7 @@ enum { NETIF_F_GRO_FRAGLIST_BIT, /* Fraglist GRO */ NETIF_F_HW_MACSEC_BIT, /* Offload MACsec operations */ + NETIF_F_GRO_UDP_FWD_BIT, /* Allow UDP GRO for forwarding */ /* * Add your fresh new feature above and remember to update @@ -157,6 +158,7 @@ enum { #define NETIF_F_GRO_FRAGLIST __NETIF_F(GRO_FRAGLIST) #define NETIF_F_GSO_FRAGLIST __NETIF_F(GSO_FRAGLIST) #define NETIF_F_HW_MACSEC __NETIF_F(HW_MACSEC) +#define NETIF_F_GRO_UDP_FWD __NETIF_F(GRO_UDP_FWD) /* Finds the next feature with the highest number of the range of start till 0. */ @@ -234,7 +236,7 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start) #define NETIF_F_SOFT_FEATURES (NETIF_F_GSO | NETIF_F_GRO) /* Changeable features with no special hardware requirements that defaults to off. */ -#define NETIF_F_SOFT_FEATURES_OFF NETIF_F_GRO_FRAGLIST +#define NETIF_F_SOFT_FEATURES_OFF (NETIF_F_GRO_FRAGLIST | NETIF_F_GRO_UDP_FWD) #define NETIF_F_VLAN_FEATURES (NETIF_F_HW_VLAN_CTAG_FILTER | \ NETIF_F_HW_VLAN_CTAG_RX | \ -- cgit v1.2.3 From a6435940b62f81a1718bf2bd46a051379fc89b9d Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:20 +0100 Subject: mount: attach mappings to mounts In order to support per-mount idmappings vfsmounts are marked with user namespaces. The idmapping of the user namespace will be used to map the ids of vfs objects when they are accessed through that mount. By default all vfsmounts are marked with the initial user namespace. The initial user namespace is used to indicate that a mount is not idmapped. All operations behave as before. Based on prior discussions we want to attach the whole user namespace and not just a dedicated idmapping struct. This allows us to reuse all the helpers that already exist for dealing with idmappings instead of introducing a whole new range of helpers. In addition, if we decide in the future that we are confident enough to enable unprivileged users to setup idmapped mounts the permission checking can take into account whether the caller is privileged in the user namespace the mount is currently marked with. Later patches enforce that once a mount has been idmapped it can't be remapped. This keeps permission checking and life-cycle management simple. Users wanting to change the idmapped can always create a new detached mount with a different idmapping. Add a new mnt_userns member to vfsmount and two simple helpers to retrieve the mnt_userns from vfsmounts and files. The idea to attach user namespaces to vfsmounts has been floated around in various forms at Linux Plumbers in ~2018 with the original idea tracing back to a discussion in 2017 at a conference in St. Petersburg between Christoph, Tycho, and myself. Link: https://lore.kernel.org/r/20210121131959.646623-2-christian.brauner@ubuntu.com Cc: Christoph Hellwig Cc: David Howells Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner --- include/linux/fs.h | 6 ++++++ include/linux/mount.h | 6 ++++++ 2 files changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index fd47deea7c17..fd0b80e6361d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -39,6 +39,7 @@ #include #include #include +#include #include #include @@ -2231,6 +2232,7 @@ struct file_system_type { #define FS_HAS_SUBTYPE 4 #define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ #define FS_DISALLOW_NOTIFY_PERM 16 /* Disable fanotify permission events */ +#define FS_ALLOW_IDMAP 32 /* FS has been updated to handle vfs idmappings. */ #define FS_THP_SUPPORT 8192 /* Remove once all fs converted */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ int (*init_fs_context)(struct fs_context *); @@ -2517,6 +2519,10 @@ struct filename { }; static_assert(offsetof(struct filename, iname) % sizeof(long) == 0); +static inline struct user_namespace *file_mnt_user_ns(struct file *file) +{ + return mnt_user_ns(file->f_path.mnt); +} extern long vfs_truncate(const struct path *, loff_t); extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs, struct file *filp); diff --git a/include/linux/mount.h b/include/linux/mount.h index aaf343b38671..52de25e08319 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -72,8 +72,14 @@ struct vfsmount { struct dentry *mnt_root; /* root of the mounted tree */ struct super_block *mnt_sb; /* pointer to superblock */ int mnt_flags; + struct user_namespace *mnt_userns; } __randomize_layout; +static inline struct user_namespace *mnt_user_ns(const struct vfsmount *mnt) +{ + return mnt->mnt_userns; +} + struct file; /* forward dec */ struct path; -- cgit v1.2.3 From e6c9a71451560edba343cbcbd500bea0a188f0d1 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:21 +0100 Subject: fs: add id translation helpers Add simple helpers to make it easy to map kuids into and from idmapped mounts. We provide simple wrappers that filesystems can use to e.g. initialize inodes similar to i_{uid,gid}_read() and i_{uid,gid}_write(). Accessing an inode through an idmapped mount maps the i_uid and i_gid of the inode to the mount's user namespace. If the fsids are used to initialize inodes they are unmapped according to the mount's user namespace. Passing the initial user namespace to these helpers makes them a nop and so any non-idmapped paths will not be impacted. Link: https://lore.kernel.org/r/20210121131959.646623-3-christian.brauner@ubuntu.com Cc: David Howells Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner --- include/linux/fs.h | 47 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index fd0b80e6361d..3165998e2294 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -40,6 +40,7 @@ #include #include #include +#include #include #include @@ -1573,6 +1574,52 @@ static inline void i_gid_write(struct inode *inode, gid_t gid) inode->i_gid = make_kgid(inode->i_sb->s_user_ns, gid); } +static inline kuid_t kuid_into_mnt(struct user_namespace *mnt_userns, + kuid_t kuid) +{ + return make_kuid(mnt_userns, __kuid_val(kuid)); +} + +static inline kgid_t kgid_into_mnt(struct user_namespace *mnt_userns, + kgid_t kgid) +{ + return make_kgid(mnt_userns, __kgid_val(kgid)); +} + +static inline kuid_t i_uid_into_mnt(struct user_namespace *mnt_userns, + const struct inode *inode) +{ + return kuid_into_mnt(mnt_userns, inode->i_uid); +} + +static inline kgid_t i_gid_into_mnt(struct user_namespace *mnt_userns, + const struct inode *inode) +{ + return kgid_into_mnt(mnt_userns, inode->i_gid); +} + +static inline kuid_t kuid_from_mnt(struct user_namespace *mnt_userns, + kuid_t kuid) +{ + return KUIDT_INIT(from_kuid(mnt_userns, kuid)); +} + +static inline kgid_t kgid_from_mnt(struct user_namespace *mnt_userns, + kgid_t kgid) +{ + return KGIDT_INIT(from_kgid(mnt_userns, kgid)); +} + +static inline kuid_t fsuid_into_mnt(struct user_namespace *mnt_userns) +{ + return kuid_from_mnt(mnt_userns, current_fsuid()); +} + +static inline kgid_t fsgid_into_mnt(struct user_namespace *mnt_userns) +{ + return kgid_from_mnt(mnt_userns, current_fsgid()); +} + extern struct timespec64 current_time(struct inode *inode); /* -- cgit v1.2.3 From 02f92b3868a1b34ab98464e76b0e4e060474ba10 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:22 +0100 Subject: fs: add file and path permissions helpers Add two simple helpers to check permissions on a file and path respectively and convert over some callers. It simplifies quite a few codepaths and also reduces the churn in later patches quite a bit. Christoph also correctly points out that this makes codepaths (e.g. ioctls) way easier to follow that would otherwise have to do more complex argument passing than necessary. Link: https://lore.kernel.org/r/20210121131959.646623-4-christian.brauner@ubuntu.com Cc: David Howells Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Suggested-by: Christoph Hellwig Reviewed-by: Christoph Hellwig Reviewed-by: James Morris Signed-off-by: Christian Brauner --- include/linux/fs.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 3165998e2294..bcd17097d441 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2812,6 +2812,14 @@ static inline int bmap(struct inode *inode, sector_t *block) extern int notify_change(struct dentry *, struct iattr *, struct inode **); extern int inode_permission(struct inode *, int); extern int generic_permission(struct inode *, int); +static inline int file_permission(struct file *file, int mask) +{ + return inode_permission(file_inode(file), mask); +} +static inline int path_permission(const struct path *path, int mask) +{ + return inode_permission(d_inode(path->dentry), mask); +} extern int __check_sticky(struct inode *dir, struct inode *inode); static inline bool execute_ok(struct inode *inode) -- cgit v1.2.3 From 0558c1bf5a0811bf5e3753eed911a15b9bd08271 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:23 +0100 Subject: capability: handle idmapped mounts In order to determine whether a caller holds privilege over a given inode the capability framework exposes the two helpers privileged_wrt_inode_uidgid() and capable_wrt_inode_uidgid(). The former verifies that the inode has a mapping in the caller's user namespace and the latter additionally verifies that the caller has the requested capability in their current user namespace. If the inode is accessed through an idmapped mount map it into the mount's user namespace. Afterwards the checks are identical to non-idmapped inodes. If the initial user namespace is passed all operations are a nop so non-idmapped mounts will not see a change in behavior. Link: https://lore.kernel.org/r/20210121131959.646623-5-christian.brauner@ubuntu.com Cc: Christoph Hellwig Cc: David Howells Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig Reviewed-by: James Morris Acked-by: Serge Hallyn Signed-off-by: Christian Brauner --- include/linux/capability.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/capability.h b/include/linux/capability.h index b2f698915c0f..62bfa3ed84d7 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -247,8 +247,11 @@ static inline bool ns_capable_setid(struct user_namespace *ns, int cap) return true; } #endif /* CONFIG_MULTIUSER */ -extern bool privileged_wrt_inode_uidgid(struct user_namespace *ns, const struct inode *inode); -extern bool capable_wrt_inode_uidgid(const struct inode *inode, int cap); +bool privileged_wrt_inode_uidgid(struct user_namespace *ns, + struct user_namespace *mnt_userns, + const struct inode *inode); +bool capable_wrt_inode_uidgid(struct user_namespace *mnt_userns, + const struct inode *inode, int cap); extern bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap); extern bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns); static inline bool perfmon_capable(void) -- cgit v1.2.3 From 47291baa8ddfdae10663624ff0a15ab165952708 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:24 +0100 Subject: namei: make permission helpers idmapped mount aware The two helpers inode_permission() and generic_permission() are used by the vfs to perform basic permission checking by verifying that the caller is privileged over an inode. In order to handle idmapped mounts we extend the two helpers with an additional user namespace argument. On idmapped mounts the two helpers will make sure to map the inode according to the mount's user namespace and then peform identical permission checks to inode_permission() and generic_permission(). If the initial user namespace is passed nothing changes so non-idmapped mounts will see identical behavior as before. Link: https://lore.kernel.org/r/20210121131959.646623-6-christian.brauner@ubuntu.com Cc: Christoph Hellwig Cc: David Howells Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig Reviewed-by: James Morris Acked-by: Serge Hallyn Signed-off-by: Christian Brauner --- include/linux/fs.h | 10 ++++++---- include/linux/posix_acl.h | 7 +++++-- 2 files changed, 11 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index bcd17097d441..a85dfe6962df 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2810,15 +2810,17 @@ static inline int bmap(struct inode *inode, sector_t *block) #endif extern int notify_change(struct dentry *, struct iattr *, struct inode **); -extern int inode_permission(struct inode *, int); -extern int generic_permission(struct inode *, int); +int inode_permission(struct user_namespace *, struct inode *, int); +int generic_permission(struct user_namespace *, struct inode *, int); static inline int file_permission(struct file *file, int mask) { - return inode_permission(file_inode(file), mask); + return inode_permission(file_mnt_user_ns(file), + file_inode(file), mask); } static inline int path_permission(const struct path *path, int mask) { - return inode_permission(d_inode(path->dentry), mask); + return inode_permission(mnt_user_ns(path->mnt), + d_inode(path->dentry), mask); } extern int __check_sticky(struct inode *dir, struct inode *inode); diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 90797f1b421d..85fb4c0c650a 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -15,6 +15,8 @@ #include #include +struct user_namespace; + struct posix_acl_entry { short e_tag; unsigned short e_perm; @@ -61,8 +63,6 @@ posix_acl_release(struct posix_acl *acl) extern void posix_acl_init(struct posix_acl *, int); extern struct posix_acl *posix_acl_alloc(int, gfp_t); -extern int posix_acl_valid(struct user_namespace *, const struct posix_acl *); -extern int posix_acl_permission(struct inode *, const struct posix_acl *, int); extern struct posix_acl *posix_acl_from_mode(umode_t, gfp_t); extern int posix_acl_equiv_mode(const struct posix_acl *, umode_t *); extern int __posix_acl_create(struct posix_acl **, gfp_t, umode_t *); @@ -85,6 +85,9 @@ struct posix_acl *get_cached_acl_rcu(struct inode *inode, int type); void set_cached_acl(struct inode *inode, int type, struct posix_acl *acl); void forget_cached_acl(struct inode *inode, int type); void forget_all_cached_acls(struct inode *inode); +int posix_acl_valid(struct user_namespace *, const struct posix_acl *); +int posix_acl_permission(struct user_namespace *, struct inode *, + const struct posix_acl *, int); static inline void cache_no_acl(struct inode *inode) { -- cgit v1.2.3 From 21cb47be6fb9ece7e6ee63f6780986faa384a77c Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:25 +0100 Subject: inode: make init and permission helpers idmapped mount aware The inode_owner_or_capable() helper determines whether the caller is the owner of the inode or is capable with respect to that inode. Allow it to handle idmapped mounts. If the inode is accessed through an idmapped mount it according to the mount's user namespace. Afterwards the checks are identical to non-idmapped mounts. If the initial user namespace is passed nothing changes so non-idmapped mounts will see identical behavior as before. Similarly, allow the inode_init_owner() helper to handle idmapped mounts. It initializes a new inode on idmapped mounts by mapping the fsuid and fsgid of the caller from the mount's user namespace. If the initial user namespace is passed nothing changes so non-idmapped mounts will see identical behavior as before. Link: https://lore.kernel.org/r/20210121131959.646623-7-christian.brauner@ubuntu.com Cc: Christoph Hellwig Cc: David Howells Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig Reviewed-by: James Morris Signed-off-by: Christian Brauner --- include/linux/fs.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index a85dfe6962df..2a9d4af6a64d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1762,8 +1762,8 @@ static inline bool sb_start_intwrite_trylock(struct super_block *sb) return __sb_start_write_trylock(sb, SB_FREEZE_FS); } - -extern bool inode_owner_or_capable(const struct inode *inode); +bool inode_owner_or_capable(struct user_namespace *mnt_userns, + const struct inode *inode); /* * VFS helper functions.. @@ -1805,8 +1805,8 @@ extern long compat_ptr_ioctl(struct file *file, unsigned int cmd, /* * VFS file helper functions. */ -extern void inode_init_owner(struct inode *inode, const struct inode *dir, - umode_t mode); +void inode_init_owner(struct user_namespace *mnt_userns, struct inode *inode, + const struct inode *dir, umode_t mode); extern bool may_open_dev(const struct path *path); /* -- cgit v1.2.3 From 2f221d6f7b881d95de1f356a3097d755ab1e47d4 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:26 +0100 Subject: attr: handle idmapped mounts When file attributes are changed most filesystems rely on the setattr_prepare(), setattr_copy(), and notify_change() helpers for initialization and permission checking. Let them handle idmapped mounts. If the inode is accessed through an idmapped mount map it into the mount's user namespace. Afterwards the checks are identical to non-idmapped mounts. If the initial user namespace is passed nothing changes so non-idmapped mounts will see identical behavior as before. Helpers that perform checks on the ia_uid and ia_gid fields in struct iattr assume that ia_uid and ia_gid are intended values and have already been mapped correctly at the userspace-kernelspace boundary as we already do today. If the initial user namespace is passed nothing changes so non-idmapped mounts will see identical behavior as before. Link: https://lore.kernel.org/r/20210121131959.646623-8-christian.brauner@ubuntu.com Cc: Christoph Hellwig Cc: David Howells Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner --- include/linux/fs.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 2a9d4af6a64d..e3ea1d7c3367 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2809,7 +2809,8 @@ static inline int bmap(struct inode *inode, sector_t *block) } #endif -extern int notify_change(struct dentry *, struct iattr *, struct inode **); +int notify_change(struct user_namespace *, struct dentry *, + struct iattr *, struct inode **); int inode_permission(struct user_namespace *, struct inode *, int); int generic_permission(struct user_namespace *, struct inode *, int); static inline int file_permission(struct file *file, int mask) @@ -3274,9 +3275,10 @@ extern int buffer_migrate_page_norefs(struct address_space *, #define buffer_migrate_page_norefs NULL #endif -extern int setattr_prepare(struct dentry *, struct iattr *); +int setattr_prepare(struct user_namespace *, struct dentry *, struct iattr *); extern int inode_newsize_ok(const struct inode *, loff_t offset); -extern void setattr_copy(struct inode *inode, const struct iattr *attr); +void setattr_copy(struct user_namespace *, struct inode *inode, + const struct iattr *attr); extern int file_update_time(struct file *file); -- cgit v1.2.3 From e65ce2a50cf6af216bea6fd80d771fcbb4c0aaa1 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:27 +0100 Subject: acl: handle idmapped mounts The posix acl permission checking helpers determine whether a caller is privileged over an inode according to the acls associated with the inode. Add helpers that make it possible to handle acls on idmapped mounts. The vfs and the filesystems targeted by this first iteration make use of posix_acl_fix_xattr_from_user() and posix_acl_fix_xattr_to_user() to translate basic posix access and default permissions such as the ACL_USER and ACL_GROUP type according to the initial user namespace (or the superblock's user namespace) to and from the caller's current user namespace. Adapt these two helpers to handle idmapped mounts whereby we either map from or into the mount's user namespace depending on in which direction we're translating. Similarly, cap_convert_nscap() is used by the vfs to translate user namespace and non-user namespace aware filesystem capabilities from the superblock's user namespace to the caller's user namespace. Enable it to handle idmapped mounts by accounting for the mount's user namespace. In addition the fileystems targeted in the first iteration of this patch series make use of the posix_acl_chmod() and, posix_acl_update_mode() helpers. Both helpers perform permission checks on the target inode. Let them handle idmapped mounts. These two helpers are called when posix acls are set by the respective filesystems to handle this case we extend the ->set() method to take an additional user namespace argument to pass the mount's user namespace down. Link: https://lore.kernel.org/r/20210121131959.646623-9-christian.brauner@ubuntu.com Cc: Christoph Hellwig Cc: David Howells Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner --- include/linux/capability.h | 3 ++- include/linux/posix_acl.h | 11 +++++++---- include/linux/posix_acl_xattr.h | 12 ++++++++---- include/linux/xattr.h | 3 ++- 4 files changed, 19 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/capability.h b/include/linux/capability.h index 62bfa3ed84d7..da21ef118b04 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -273,6 +273,7 @@ static inline bool checkpoint_restore_ns_capable(struct user_namespace *ns) /* audit system wants to get cap info from files as well */ extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps); -extern int cap_convert_nscap(struct dentry *dentry, const void **ivalue, size_t size); +int cap_convert_nscap(struct user_namespace *mnt_userns, struct dentry *dentry, + const void **ivalue, size_t size); #endif /* !_LINUX_CAPABILITY_H */ diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 85fb4c0c650a..6dcd8b8f6ab5 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -69,13 +69,15 @@ extern int __posix_acl_create(struct posix_acl **, gfp_t, umode_t *); extern int __posix_acl_chmod(struct posix_acl **, gfp_t, umode_t); extern struct posix_acl *get_posix_acl(struct inode *, int); -extern int set_posix_acl(struct inode *, int, struct posix_acl *); +extern int set_posix_acl(struct user_namespace *, struct inode *, int, + struct posix_acl *); #ifdef CONFIG_FS_POSIX_ACL -extern int posix_acl_chmod(struct inode *, umode_t); +int posix_acl_chmod(struct user_namespace *, struct inode *, umode_t); extern int posix_acl_create(struct inode *, umode_t *, struct posix_acl **, struct posix_acl **); -extern int posix_acl_update_mode(struct inode *, umode_t *, struct posix_acl **); +int posix_acl_update_mode(struct user_namespace *, struct inode *, umode_t *, + struct posix_acl **); extern int simple_set_acl(struct inode *, struct posix_acl *, int); extern int simple_acl_create(struct inode *, struct inode *); @@ -95,7 +97,8 @@ static inline void cache_no_acl(struct inode *inode) inode->i_default_acl = NULL; } #else -static inline int posix_acl_chmod(struct inode *inode, umode_t mode) +static inline int posix_acl_chmod(struct user_namespace *mnt_userns, + struct inode *inode, umode_t mode) { return 0; } diff --git a/include/linux/posix_acl_xattr.h b/include/linux/posix_acl_xattr.h index 2387709991b5..060e8d203181 100644 --- a/include/linux/posix_acl_xattr.h +++ b/include/linux/posix_acl_xattr.h @@ -33,13 +33,17 @@ posix_acl_xattr_count(size_t size) } #ifdef CONFIG_FS_POSIX_ACL -void posix_acl_fix_xattr_from_user(void *value, size_t size); -void posix_acl_fix_xattr_to_user(void *value, size_t size); +void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns, + void *value, size_t size); +void posix_acl_fix_xattr_to_user(struct user_namespace *mnt_userns, + void *value, size_t size); #else -static inline void posix_acl_fix_xattr_from_user(void *value, size_t size) +static inline void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns, + void *value, size_t size) { } -static inline void posix_acl_fix_xattr_to_user(void *value, size_t size) +static inline void posix_acl_fix_xattr_to_user(struct user_namespace *mnt_userns, + void *value, size_t size) { } #endif diff --git a/include/linux/xattr.h b/include/linux/xattr.h index 10b4dc2709f0..260c9bcb0edb 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -34,7 +34,8 @@ struct xattr_handler { int (*get)(const struct xattr_handler *, struct dentry *dentry, struct inode *inode, const char *name, void *buffer, size_t size); - int (*set)(const struct xattr_handler *, struct dentry *dentry, + int (*set)(const struct xattr_handler *, + struct user_namespace *mnt_userns, struct dentry *dentry, struct inode *inode, const char *name, const void *buffer, size_t size, int flags); }; -- cgit v1.2.3 From c7c7a1a18af4c3bb7749d33e3df3acdf0a95bbb5 Mon Sep 17 00:00:00 2001 From: Tycho Andersen Date: Thu, 21 Jan 2021 14:19:28 +0100 Subject: xattr: handle idmapped mounts When interacting with extended attributes the vfs verifies that the caller is privileged over the inode with which the extended attribute is associated. For posix access and posix default extended attributes a uid or gid can be stored on-disk. Let the functions handle posix extended attributes on idmapped mounts. If the inode is accessed through an idmapped mount we need to map it according to the mount's user namespace. Afterwards the checks are identical to non-idmapped mounts. This has no effect for e.g. security xattrs since they don't store uids or gids and don't perform permission checks on them like posix acls do. Link: https://lore.kernel.org/r/20210121131959.646623-10-christian.brauner@ubuntu.com Cc: Christoph Hellwig Cc: David Howells Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig Reviewed-by: James Morris Signed-off-by: Tycho Andersen Signed-off-by: Christian Brauner --- include/linux/xattr.h | 27 ++++++++++++++++++--------- 1 file changed, 18 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xattr.h b/include/linux/xattr.h index 260c9bcb0edb..4c379d23ec6e 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -16,6 +16,7 @@ #include #include #include +#include #include struct inode; @@ -49,18 +50,26 @@ struct xattr { }; ssize_t __vfs_getxattr(struct dentry *, struct inode *, const char *, void *, size_t); -ssize_t vfs_getxattr(struct dentry *, const char *, void *, size_t); +ssize_t vfs_getxattr(struct user_namespace *, struct dentry *, const char *, + void *, size_t); ssize_t vfs_listxattr(struct dentry *d, char *list, size_t size); -int __vfs_setxattr(struct dentry *, struct inode *, const char *, const void *, size_t, int); -int __vfs_setxattr_noperm(struct dentry *, const char *, const void *, size_t, int); -int __vfs_setxattr_locked(struct dentry *, const char *, const void *, size_t, int, struct inode **); -int vfs_setxattr(struct dentry *, const char *, const void *, size_t, int); -int __vfs_removexattr(struct dentry *, const char *); -int __vfs_removexattr_locked(struct dentry *, const char *, struct inode **); -int vfs_removexattr(struct dentry *, const char *); +int __vfs_setxattr(struct user_namespace *, struct dentry *, struct inode *, + const char *, const void *, size_t, int); +int __vfs_setxattr_noperm(struct user_namespace *, struct dentry *, + const char *, const void *, size_t, int); +int __vfs_setxattr_locked(struct user_namespace *, struct dentry *, + const char *, const void *, size_t, int, + struct inode **); +int vfs_setxattr(struct user_namespace *, struct dentry *, const char *, + const void *, size_t, int); +int __vfs_removexattr(struct user_namespace *, struct dentry *, const char *); +int __vfs_removexattr_locked(struct user_namespace *, struct dentry *, + const char *, struct inode **); +int vfs_removexattr(struct user_namespace *, struct dentry *, const char *); ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size); -ssize_t vfs_getxattr_alloc(struct dentry *dentry, const char *name, +ssize_t vfs_getxattr_alloc(struct user_namespace *mnt_userns, + struct dentry *dentry, const char *name, char **xattr_value, size_t size, gfp_t flags); int xattr_supported_namespace(struct inode *inode, const char *prefix); -- cgit v1.2.3 From 71bc356f93a1c589fad13f7487258f89c417976e Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:29 +0100 Subject: commoncap: handle idmapped mounts When interacting with user namespace and non-user namespace aware filesystem capabilities the vfs will perform various security checks to determine whether or not the filesystem capabilities can be used by the caller, whether they need to be removed and so on. The main infrastructure for this resides in the capability codepaths but they are called through the LSM security infrastructure even though they are not technically an LSM or optional. This extends the existing security hooks security_inode_removexattr(), security_inode_killpriv(), security_inode_getsecurity() to pass down the mount's user namespace and makes them aware of idmapped mounts. In order to actually get filesystem capabilities from disk the capability infrastructure exposes the get_vfs_caps_from_disk() helper. For user namespace aware filesystem capabilities a root uid is stored alongside the capabilities. In order to determine whether the caller can make use of the filesystem capability or whether it needs to be ignored it is translated according to the superblock's user namespace. If it can be translated to uid 0 according to that id mapping the caller can use the filesystem capabilities stored on disk. If we are accessing the inode that holds the filesystem capabilities through an idmapped mount we map the root uid according to the mount's user namespace. Afterwards the checks are identical to non-idmapped mounts: reading filesystem caps from disk enforces that the root uid associated with the filesystem capability must have a mapping in the superblock's user namespace and that the caller is either in the same user namespace or is a descendant of the superblock's user namespace. For filesystems that are mountable inside user namespace the caller can just mount the filesystem and won't usually need to idmap it. If they do want to idmap it they can create an idmapped mount and mark it with a user namespace they created and which is thus a descendant of s_user_ns. For filesystems that are not mountable inside user namespaces the descendant rule is trivially true because the s_user_ns will be the initial user namespace. If the initial user namespace is passed nothing changes so non-idmapped mounts will see identical behavior as before. Link: https://lore.kernel.org/r/20210121131959.646623-11-christian.brauner@ubuntu.com Cc: Christoph Hellwig Cc: David Howells Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig Acked-by: James Morris Signed-off-by: Christian Brauner --- include/linux/capability.h | 4 +++- include/linux/lsm_hook_defs.h | 15 +++++++----- include/linux/lsm_hooks.h | 1 + include/linux/security.h | 54 +++++++++++++++++++++++++++---------------- 4 files changed, 47 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/capability.h b/include/linux/capability.h index da21ef118b04..65efb74c3585 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -271,7 +271,9 @@ static inline bool checkpoint_restore_ns_capable(struct user_namespace *ns) } /* audit system wants to get cap info from files as well */ -extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps); +int get_vfs_caps_from_disk(struct user_namespace *mnt_userns, + const struct dentry *dentry, + struct cpu_vfs_cap_data *cpu_caps); int cap_convert_nscap(struct user_namespace *mnt_userns, struct dentry *dentry, const void **ivalue, size_t size); diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 7aaa753b8608..df4cdad6681e 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -133,17 +133,20 @@ LSM_HOOK(int, 0, inode_follow_link, struct dentry *dentry, struct inode *inode, LSM_HOOK(int, 0, inode_permission, struct inode *inode, int mask) LSM_HOOK(int, 0, inode_setattr, struct dentry *dentry, struct iattr *attr) LSM_HOOK(int, 0, inode_getattr, const struct path *path) -LSM_HOOK(int, 0, inode_setxattr, struct dentry *dentry, const char *name, - const void *value, size_t size, int flags) +LSM_HOOK(int, 0, inode_setxattr, struct user_namespace *mnt_userns, + struct dentry *dentry, const char *name, const void *value, + size_t size, int flags) LSM_HOOK(void, LSM_RET_VOID, inode_post_setxattr, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) LSM_HOOK(int, 0, inode_getxattr, struct dentry *dentry, const char *name) LSM_HOOK(int, 0, inode_listxattr, struct dentry *dentry) -LSM_HOOK(int, 0, inode_removexattr, struct dentry *dentry, const char *name) +LSM_HOOK(int, 0, inode_removexattr, struct user_namespace *mnt_userns, + struct dentry *dentry, const char *name) LSM_HOOK(int, 0, inode_need_killpriv, struct dentry *dentry) -LSM_HOOK(int, 0, inode_killpriv, struct dentry *dentry) -LSM_HOOK(int, -EOPNOTSUPP, inode_getsecurity, struct inode *inode, - const char *name, void **buffer, bool alloc) +LSM_HOOK(int, 0, inode_killpriv, struct user_namespace *mnt_userns, + struct dentry *dentry) +LSM_HOOK(int, -EOPNOTSUPP, inode_getsecurity, struct user_namespace *mnt_userns, + struct inode *inode, const char *name, void **buffer, bool alloc) LSM_HOOK(int, -EOPNOTSUPP, inode_setsecurity, struct inode *inode, const char *name, const void *value, size_t size, int flags) LSM_HOOK(int, 0, inode_listsecurity, struct inode *inode, char *buffer, diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index a19adef1f088..98a5e263aabb 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -444,6 +444,7 @@ * @inode_killpriv: * The setuid bit is being removed. Remove similar security labels. * Called with the dentry->d_inode->i_mutex held. + * @mnt_userns: user namespace of the mount * @dentry is the dentry being changed. * Return 0 on success. If error is returned, then the operation * causing setuid bit removal is failed. diff --git a/include/linux/security.h b/include/linux/security.h index c35ea0ffccd9..4e4f6c31e413 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -145,13 +145,16 @@ extern int cap_capset(struct cred *new, const struct cred *old, const kernel_cap_t *inheritable, const kernel_cap_t *permitted); extern int cap_bprm_creds_from_file(struct linux_binprm *bprm, struct file *file); -extern int cap_inode_setxattr(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags); -extern int cap_inode_removexattr(struct dentry *dentry, const char *name); -extern int cap_inode_need_killpriv(struct dentry *dentry); -extern int cap_inode_killpriv(struct dentry *dentry); -extern int cap_inode_getsecurity(struct inode *inode, const char *name, - void **buffer, bool alloc); +int cap_inode_setxattr(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags); +int cap_inode_removexattr(struct user_namespace *mnt_userns, + struct dentry *dentry, const char *name); +int cap_inode_need_killpriv(struct dentry *dentry); +int cap_inode_killpriv(struct user_namespace *mnt_userns, + struct dentry *dentry); +int cap_inode_getsecurity(struct user_namespace *mnt_userns, + struct inode *inode, const char *name, void **buffer, + bool alloc); extern int cap_mmap_addr(unsigned long addr); extern int cap_mmap_file(struct file *file, unsigned long reqprot, unsigned long prot, unsigned long flags); @@ -345,16 +348,21 @@ int security_inode_follow_link(struct dentry *dentry, struct inode *inode, int security_inode_permission(struct inode *inode, int mask); int security_inode_setattr(struct dentry *dentry, struct iattr *attr); int security_inode_getattr(const struct path *path); -int security_inode_setxattr(struct dentry *dentry, const char *name, +int security_inode_setxattr(struct user_namespace *mnt_userns, + struct dentry *dentry, const char *name, const void *value, size_t size, int flags); void security_inode_post_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags); int security_inode_getxattr(struct dentry *dentry, const char *name); int security_inode_listxattr(struct dentry *dentry); -int security_inode_removexattr(struct dentry *dentry, const char *name); +int security_inode_removexattr(struct user_namespace *mnt_userns, + struct dentry *dentry, const char *name); int security_inode_need_killpriv(struct dentry *dentry); -int security_inode_killpriv(struct dentry *dentry); -int security_inode_getsecurity(struct inode *inode, const char *name, void **buffer, bool alloc); +int security_inode_killpriv(struct user_namespace *mnt_userns, + struct dentry *dentry); +int security_inode_getsecurity(struct user_namespace *mnt_userns, + struct inode *inode, const char *name, + void **buffer, bool alloc); int security_inode_setsecurity(struct inode *inode, const char *name, const void *value, size_t size, int flags); int security_inode_listsecurity(struct inode *inode, char *buffer, size_t buffer_size); void security_inode_getsecid(struct inode *inode, u32 *secid); @@ -831,8 +839,9 @@ static inline int security_inode_getattr(const struct path *path) return 0; } -static inline int security_inode_setxattr(struct dentry *dentry, - const char *name, const void *value, size_t size, int flags) +static inline int security_inode_setxattr(struct user_namespace *mnt_userns, + struct dentry *dentry, const char *name, const void *value, + size_t size, int flags) { return cap_inode_setxattr(dentry, name, value, size, flags); } @@ -852,10 +861,11 @@ static inline int security_inode_listxattr(struct dentry *dentry) return 0; } -static inline int security_inode_removexattr(struct dentry *dentry, - const char *name) +static inline int security_inode_removexattr(struct user_namespace *mnt_userns, + struct dentry *dentry, + const char *name) { - return cap_inode_removexattr(dentry, name); + return cap_inode_removexattr(mnt_userns, dentry, name); } static inline int security_inode_need_killpriv(struct dentry *dentry) @@ -863,14 +873,18 @@ static inline int security_inode_need_killpriv(struct dentry *dentry) return cap_inode_need_killpriv(dentry); } -static inline int security_inode_killpriv(struct dentry *dentry) +static inline int security_inode_killpriv(struct user_namespace *mnt_userns, + struct dentry *dentry) { - return cap_inode_killpriv(dentry); + return cap_inode_killpriv(mnt_userns, dentry); } -static inline int security_inode_getsecurity(struct inode *inode, const char *name, void **buffer, bool alloc) +static inline int security_inode_getsecurity(struct user_namespace *mnt_userns, + struct inode *inode, + const char *name, void **buffer, + bool alloc) { - return cap_inode_getsecurity(inode, name, buffer, alloc); + return cap_inode_getsecurity(mnt_userns, inode, name, buffer, alloc); } static inline int security_inode_setsecurity(struct inode *inode, const char *name, const void *value, size_t size, int flags) -- cgit v1.2.3 From 0d56a4518d5eaf595a24ab2202e171330bb2ed72 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:30 +0100 Subject: stat: handle idmapped mounts The generic_fillattr() helper fills in the basic attributes associated with an inode. Enable it to handle idmapped mounts. If the inode is accessed through an idmapped mount map it into the mount's user namespace before we store the uid and gid. If the initial user namespace is passed nothing changes so non-idmapped mounts will see identical behavior as before. Link: https://lore.kernel.org/r/20210121131959.646623-12-christian.brauner@ubuntu.com Cc: Christoph Hellwig Cc: David Howells Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig Reviewed-by: James Morris Signed-off-by: Christian Brauner --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index e3ea1d7c3367..182641d8322f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3154,7 +3154,7 @@ extern int __page_symlink(struct inode *inode, const char *symname, int len, extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; extern void kfree_link(void *); -extern void generic_fillattr(struct inode *, struct kstat *); +void generic_fillattr(struct user_namespace *, struct inode *, struct kstat *); extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int); extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int); void __inode_add_bytes(struct inode *inode, loff_t bytes); -- cgit v1.2.3 From ba73d98745be1c10dc3cce68e8d7b95012d07d05 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:31 +0100 Subject: namei: handle idmapped mounts in may_*() helpers The may_follow_link(), may_linkat(), may_lookup(), may_open(), may_o_create(), may_create_in_sticky(), may_delete(), and may_create() helpers determine whether the caller is privileged enough to perform the associated operations. Let them handle idmapped mounts by mapping the inode or fsids according to the mount's user namespace. Afterwards the checks are identical to non-idmapped inodes. The patch takes care to retrieve the mount's user namespace right before performing permission checks and passing it down into the fileystem so the user namespace can't change in between by someone idmapping a mount that is currently not idmapped. If the initial user namespace is passed nothing changes so non-idmapped mounts will see identical behavior as before. Link: https://lore.kernel.org/r/20210121131959.646623-13-christian.brauner@ubuntu.com Cc: Christoph Hellwig Cc: David Howells Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig Reviewed-by: James Morris Signed-off-by: Christian Brauner --- include/linux/fs.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 182641d8322f..a27884af7222 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2083,9 +2083,11 @@ static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags #define IS_WHITEOUT(inode) (S_ISCHR(inode->i_mode) && \ (inode)->i_rdev == WHITEOUT_DEV) -static inline bool HAS_UNMAPPED_ID(struct inode *inode) +static inline bool HAS_UNMAPPED_ID(struct user_namespace *mnt_userns, + struct inode *inode) { - return !uid_valid(inode->i_uid) || !gid_valid(inode->i_gid); + return !uid_valid(i_uid_into_mnt(mnt_userns, inode)) || + !gid_valid(i_gid_into_mnt(mnt_userns, inode)); } static inline enum rw_hint file_write_hint(struct file *file) @@ -2823,7 +2825,8 @@ static inline int path_permission(const struct path *path, int mask) return inode_permission(mnt_user_ns(path->mnt), d_inode(path->dentry), mask); } -extern int __check_sticky(struct inode *dir, struct inode *inode); +int __check_sticky(struct user_namespace *mnt_userns, struct inode *dir, + struct inode *inode); static inline bool execute_ok(struct inode *inode) { @@ -3442,12 +3445,13 @@ static inline bool is_sxid(umode_t mode) return (mode & S_ISUID) || ((mode & S_ISGID) && (mode & S_IXGRP)); } -static inline int check_sticky(struct inode *dir, struct inode *inode) +static inline int check_sticky(struct user_namespace *mnt_userns, + struct inode *dir, struct inode *inode) { if (!(dir->i_mode & S_ISVTX)) return 0; - return __check_sticky(dir, inode); + return __check_sticky(mnt_userns, dir, inode); } static inline void inode_has_no_xattr(struct inode *inode) -- cgit v1.2.3 From 9fe61450972d3900bffb1dc26a17ebb9cdd92db2 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:32 +0100 Subject: namei: introduce struct renamedata In order to handle idmapped mounts we will extend the vfs rename helper to take two new arguments in follow up patches. Since this operations already takes a bunch of arguments add a simple struct renamedata and make the current helper use it before we extend it. Link: https://lore.kernel.org/r/20210121131959.646623-14-christian.brauner@ubuntu.com Cc: Christoph Hellwig Cc: David Howells Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner --- include/linux/fs.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index a27884af7222..430e457f67f1 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1775,7 +1775,17 @@ extern int vfs_symlink(struct inode *, struct dentry *, const char *); extern int vfs_link(struct dentry *, struct inode *, struct dentry *, struct inode **); extern int vfs_rmdir(struct inode *, struct dentry *); extern int vfs_unlink(struct inode *, struct dentry *, struct inode **); -extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int); + +struct renamedata { + struct inode *old_dir; + struct dentry *old_dentry; + struct inode *new_dir; + struct dentry *new_dentry; + struct inode **delegated_inode; + unsigned int flags; +} __randomize_layout; + +int vfs_rename(struct renamedata *); static inline int vfs_whiteout(struct inode *dir, struct dentry *dentry) { -- cgit v1.2.3 From 6521f8917082928a4cb637eb64b77b5f2f5b30fc Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:33 +0100 Subject: namei: prepare for idmapped mounts The various vfs_*() helpers are called by filesystems or by the vfs itself to perform core operations such as create, link, mkdir, mknod, rename, rmdir, tmpfile and unlink. Enable them to handle idmapped mounts. If the inode is accessed through an idmapped mount map it into the mount's user namespace and pass it down. Afterwards the checks and operations are identical to non-idmapped mounts. If the initial user namespace is passed nothing changes so non-idmapped mounts will see identical behavior as before. Link: https://lore.kernel.org/r/20210121131959.646623-15-christian.brauner@ubuntu.com Cc: Christoph Hellwig Cc: David Howells Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner --- include/linux/fs.h | 32 +++++++++++++++++++++----------- 1 file changed, 21 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 430e457f67f1..29d7b2fe7de4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1768,17 +1768,25 @@ bool inode_owner_or_capable(struct user_namespace *mnt_userns, /* * VFS helper functions.. */ -extern int vfs_create(struct inode *, struct dentry *, umode_t, bool); -extern int vfs_mkdir(struct inode *, struct dentry *, umode_t); -extern int vfs_mknod(struct inode *, struct dentry *, umode_t, dev_t); -extern int vfs_symlink(struct inode *, struct dentry *, const char *); -extern int vfs_link(struct dentry *, struct inode *, struct dentry *, struct inode **); -extern int vfs_rmdir(struct inode *, struct dentry *); -extern int vfs_unlink(struct inode *, struct dentry *, struct inode **); +int vfs_create(struct user_namespace *, struct inode *, + struct dentry *, umode_t, bool); +int vfs_mkdir(struct user_namespace *, struct inode *, + struct dentry *, umode_t); +int vfs_mknod(struct user_namespace *, struct inode *, struct dentry *, + umode_t, dev_t); +int vfs_symlink(struct user_namespace *, struct inode *, + struct dentry *, const char *); +int vfs_link(struct dentry *, struct user_namespace *, struct inode *, + struct dentry *, struct inode **); +int vfs_rmdir(struct user_namespace *, struct inode *, struct dentry *); +int vfs_unlink(struct user_namespace *, struct inode *, struct dentry *, + struct inode **); struct renamedata { + struct user_namespace *old_mnt_userns; struct inode *old_dir; struct dentry *old_dentry; + struct user_namespace *new_mnt_userns; struct inode *new_dir; struct dentry *new_dentry; struct inode **delegated_inode; @@ -1787,13 +1795,15 @@ struct renamedata { int vfs_rename(struct renamedata *); -static inline int vfs_whiteout(struct inode *dir, struct dentry *dentry) +static inline int vfs_whiteout(struct user_namespace *mnt_userns, + struct inode *dir, struct dentry *dentry) { - return vfs_mknod(dir, dentry, S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV); + return vfs_mknod(mnt_userns, dir, dentry, S_IFCHR | WHITEOUT_MODE, + WHITEOUT_DEV); } -extern struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, - int open_flag); +struct dentry *vfs_tmpfile(struct user_namespace *mnt_userns, + struct dentry *dentry, umode_t mode, int open_flag); int vfs_mkobj(struct dentry *, umode_t, int (*f)(struct dentry *, umode_t, void *), -- cgit v1.2.3 From 643fe55a0679ae5582a1a2a1df86dc240292cd1b Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:34 +0100 Subject: open: handle idmapped mounts in do_truncate() When truncating files the vfs will verify that the caller is privileged over the inode. Extend it to handle idmapped mounts. If the inode is accessed through an idmapped mount it is mapped according to the mount's user namespace. Afterwards the permissions checks are identical to non-idmapped mounts. If the initial user namespace is passed nothing changes so non-idmapped mounts will see identical behavior as before. Link: https://lore.kernel.org/r/20210121131959.646623-16-christian.brauner@ubuntu.com Cc: Christoph Hellwig Cc: David Howells Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner --- include/linux/fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 29d7b2fe7de4..f0601cca1930 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2593,8 +2593,8 @@ static inline struct user_namespace *file_mnt_user_ns(struct file *file) return mnt_user_ns(file->f_path.mnt); } extern long vfs_truncate(const struct path *, loff_t); -extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs, - struct file *filp); +int do_truncate(struct user_namespace *, struct dentry *, loff_t start, + unsigned int time_attrs, struct file *filp); extern int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len); extern long do_sys_open(int dfd, const char __user *filename, int flags, -- cgit v1.2.3 From 549c7297717c32ee53f156cd949e055e601f67bb Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:43 +0100 Subject: fs: make helpers idmap mount aware Extend some inode methods with an additional user namespace argument. A filesystem that is aware of idmapped mounts will receive the user namespace the mount has been marked with. This can be used for additional permission checking and also to enable filesystems to translate between uids and gids if they need to. We have implemented all relevant helpers in earlier patches. As requested we simply extend the exisiting inode method instead of introducing new ones. This is a little more code churn but it's mostly mechanical and doesnt't leave us with additional inode methods. Link: https://lore.kernel.org/r/20210121131959.646623-25-christian.brauner@ubuntu.com Cc: Christoph Hellwig Cc: David Howells Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner --- include/linux/fs.h | 39 +++++++++++++++++++++++++-------------- include/linux/nfs_fs.h | 7 ++++--- include/linux/posix_acl.h | 3 ++- 3 files changed, 31 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index f0601cca1930..7762d3d75230 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1930,22 +1930,28 @@ struct file_operations { struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *); - int (*permission) (struct inode *, int); + int (*permission) (struct user_namespace *, struct inode *, int); struct posix_acl * (*get_acl)(struct inode *, int); int (*readlink) (struct dentry *, char __user *,int); - int (*create) (struct inode *,struct dentry *, umode_t, bool); + int (*create) (struct user_namespace *, struct inode *,struct dentry *, + umode_t, bool); int (*link) (struct dentry *,struct inode *,struct dentry *); int (*unlink) (struct inode *,struct dentry *); - int (*symlink) (struct inode *,struct dentry *,const char *); - int (*mkdir) (struct inode *,struct dentry *,umode_t); + int (*symlink) (struct user_namespace *, struct inode *,struct dentry *, + const char *); + int (*mkdir) (struct user_namespace *, struct inode *,struct dentry *, + umode_t); int (*rmdir) (struct inode *,struct dentry *); - int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t); - int (*rename) (struct inode *, struct dentry *, + int (*mknod) (struct user_namespace *, struct inode *,struct dentry *, + umode_t,dev_t); + int (*rename) (struct user_namespace *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); - int (*setattr) (struct dentry *, struct iattr *); - int (*getattr) (const struct path *, struct kstat *, u32, unsigned int); + int (*setattr) (struct user_namespace *, struct dentry *, + struct iattr *); + int (*getattr) (struct user_namespace *, const struct path *, + struct kstat *, u32, unsigned int); ssize_t (*listxattr) (struct dentry *, char *, size_t); int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); @@ -1953,8 +1959,10 @@ struct inode_operations { int (*atomic_open)(struct inode *, struct dentry *, struct file *, unsigned open_flag, umode_t create_mode); - int (*tmpfile) (struct inode *, struct dentry *, umode_t); - int (*set_acl)(struct inode *, struct posix_acl *, int); + int (*tmpfile) (struct user_namespace *, struct inode *, + struct dentry *, umode_t); + int (*set_acl)(struct user_namespace *, struct inode *, + struct posix_acl *, int); } ____cacheline_aligned; static inline ssize_t call_read_iter(struct file *file, struct kiocb *kio, @@ -3227,15 +3235,18 @@ extern int dcache_dir_open(struct inode *, struct file *); extern int dcache_dir_close(struct inode *, struct file *); extern loff_t dcache_dir_lseek(struct file *, loff_t, int); extern int dcache_readdir(struct file *, struct dir_context *); -extern int simple_setattr(struct dentry *, struct iattr *); -extern int simple_getattr(const struct path *, struct kstat *, u32, unsigned int); +extern int simple_setattr(struct user_namespace *, struct dentry *, + struct iattr *); +extern int simple_getattr(struct user_namespace *, const struct path *, + struct kstat *, u32, unsigned int); extern int simple_statfs(struct dentry *, struct kstatfs *); extern int simple_open(struct inode *inode, struct file *file); extern int simple_link(struct dentry *, struct inode *, struct dentry *); extern int simple_unlink(struct inode *, struct dentry *); extern int simple_rmdir(struct inode *, struct dentry *); -extern int simple_rename(struct inode *, struct dentry *, - struct inode *, struct dentry *, unsigned int); +extern int simple_rename(struct user_namespace *, struct inode *, + struct dentry *, struct inode *, struct dentry *, + unsigned int); extern void simple_recursive_removal(struct dentry *, void (*callback)(struct dentry *)); extern int noop_fsync(struct file *, loff_t, loff_t, int); diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 681ed98e4ba8..8c6c4e32fc2f 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -379,10 +379,11 @@ extern int nfs_refresh_inode(struct inode *, struct nfs_fattr *); extern int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fattr *fattr); -extern int nfs_getattr(const struct path *, struct kstat *, u32, unsigned int); +extern int nfs_getattr(struct user_namespace *, const struct path *, + struct kstat *, u32, unsigned int); extern void nfs_access_add_cache(struct inode *, struct nfs_access_entry *); extern void nfs_access_set_mask(struct nfs_access_entry *, u32); -extern int nfs_permission(struct inode *, int); +extern int nfs_permission(struct user_namespace *, struct inode *, int); extern int nfs_open(struct inode *, struct file *); extern int nfs_attribute_cache_expired(struct inode *inode); extern int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode); @@ -390,7 +391,7 @@ extern int __nfs_revalidate_inode(struct nfs_server *, struct inode *); extern bool nfs_mapping_need_revalidate_inode(struct inode *inode); extern int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping); extern int nfs_revalidate_mapping_rcu(struct inode *inode); -extern int nfs_setattr(struct dentry *, struct iattr *); +extern int nfs_setattr(struct user_namespace *, struct dentry *, struct iattr *); extern void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, struct nfs_fattr *); extern void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr, struct nfs4_label *label); diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 6dcd8b8f6ab5..307094ebb88c 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -79,7 +79,8 @@ extern int posix_acl_create(struct inode *, umode_t *, struct posix_acl **, int posix_acl_update_mode(struct user_namespace *, struct inode *, umode_t *, struct posix_acl **); -extern int simple_set_acl(struct inode *, struct posix_acl *, int); +extern int simple_set_acl(struct user_namespace *, struct inode *, + struct posix_acl *, int); extern int simple_acl_create(struct inode *, struct inode *); struct posix_acl *get_cached_acl(struct inode *inode, int type); -- cgit v1.2.3 From a2d2329e30e224ea68d575d2525b866df9805ea0 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:45 +0100 Subject: ima: handle idmapped mounts IMA does sometimes access the inode's i_uid and compares it against the rules' fowner. Enable IMA to handle idmapped mounts by passing down the mount's user namespace. We simply make use of the helpers we introduced before. If the initial user namespace is passed nothing changes so non-idmapped mounts will see identical behavior as before. Link: https://lore.kernel.org/r/20210121131959.646623-27-christian.brauner@ubuntu.com Signed-off-by: Christian Brauner --- include/linux/ima.h | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ima.h b/include/linux/ima.h index 7db9cca1af34..5486312d8ee6 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -16,7 +16,8 @@ struct linux_binprm; #ifdef CONFIG_IMA extern int ima_bprm_check(struct linux_binprm *bprm); extern int ima_file_check(struct file *file, int mask); -extern void ima_post_create_tmpfile(struct inode *inode); +extern void ima_post_create_tmpfile(struct user_namespace *mnt_userns, + struct inode *inode); extern void ima_file_free(struct file *file); extern int ima_file_mmap(struct file *file, unsigned long prot); extern int ima_file_mprotect(struct vm_area_struct *vma, unsigned long prot); @@ -27,7 +28,8 @@ extern int ima_read_file(struct file *file, enum kernel_read_file_id id, bool contents); extern int ima_post_read_file(struct file *file, void *buf, loff_t size, enum kernel_read_file_id id); -extern void ima_post_path_mknod(struct dentry *dentry); +extern void ima_post_path_mknod(struct user_namespace *mnt_userns, + struct dentry *dentry); extern int ima_file_hash(struct file *file, char *buf, size_t buf_size); extern int ima_inode_hash(struct inode *inode, char *buf, size_t buf_size); extern void ima_kexec_cmdline(int kernel_fd, const void *buf, int size); @@ -68,7 +70,8 @@ static inline int ima_file_check(struct file *file, int mask) return 0; } -static inline void ima_post_create_tmpfile(struct inode *inode) +static inline void ima_post_create_tmpfile(struct user_namespace *mnt_userns, + struct inode *inode) { } @@ -112,7 +115,8 @@ static inline int ima_post_read_file(struct file *file, void *buf, loff_t size, return 0; } -static inline void ima_post_path_mknod(struct dentry *dentry) +static inline void ima_post_path_mknod(struct user_namespace *mnt_userns, + struct dentry *dentry) { return; } @@ -153,7 +157,8 @@ static inline void ima_post_key_create_or_update(struct key *keyring, #ifdef CONFIG_IMA_APPRAISE extern bool is_ima_appraise_enabled(void); -extern void ima_inode_post_setattr(struct dentry *dentry); +extern void ima_inode_post_setattr(struct user_namespace *mnt_userns, + struct dentry *dentry); extern int ima_inode_setxattr(struct dentry *dentry, const char *xattr_name, const void *xattr_value, size_t xattr_value_len); extern int ima_inode_removexattr(struct dentry *dentry, const char *xattr_name); @@ -163,7 +168,8 @@ static inline bool is_ima_appraise_enabled(void) return 0; } -static inline void ima_inode_post_setattr(struct dentry *dentry) +static inline void ima_inode_post_setattr(struct user_namespace *mnt_userns, + struct dentry *dentry) { return; } -- cgit v1.2.3 From 2a1867219c7b27f928e2545782b86daaf9ad50bd Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:53 +0100 Subject: fs: add mount_setattr() This implements the missing mount_setattr() syscall. While the new mount api allows to change the properties of a superblock there is currently no way to change the properties of a mount or a mount tree using file descriptors which the new mount api is based on. In addition the old mount api has the restriction that mount options cannot be applied recursively. This hasn't changed since changing mount options on a per-mount basis was implemented in [1] and has been a frequent request not just for convenience but also for security reasons. The legacy mount syscall is unable to accommodate this behavior without introducing a whole new set of flags because MS_REC | MS_REMOUNT | MS_BIND | MS_RDONLY | MS_NOEXEC | [...] only apply the mount option to the topmost mount. Changing MS_REC to apply to the whole mount tree would mean introducing a significant uapi change and would likely cause significant regressions. The new mount_setattr() syscall allows to recursively clear and set mount options in one shot. Multiple calls to change mount options requesting the same changes are idempotent: int mount_setattr(int dfd, const char *path, unsigned flags, struct mount_attr *uattr, size_t usize); Flags to modify path resolution behavior are specified in the @flags argument. Currently, AT_EMPTY_PATH, AT_RECURSIVE, AT_SYMLINK_NOFOLLOW, and AT_NO_AUTOMOUNT are supported. If useful, additional lookup flags to restrict path resolution as introduced with openat2() might be supported in the future. The mount_setattr() syscall can be expected to grow over time and is designed with extensibility in mind. It follows the extensible syscall pattern we have used with other syscalls such as openat2(), clone3(), sched_{set,get}attr(), and others. The set of mount options is passed in the uapi struct mount_attr which currently has the following layout: struct mount_attr { __u64 attr_set; __u64 attr_clr; __u64 propagation; __u64 userns_fd; }; The @attr_set and @attr_clr members are used to clear and set mount options. This way a user can e.g. request that a set of flags is to be raised such as turning mounts readonly by raising MOUNT_ATTR_RDONLY in @attr_set while at the same time requesting that another set of flags is to be lowered such as removing noexec from a mount tree by specifying MOUNT_ATTR_NOEXEC in @attr_clr. Note, since the MOUNT_ATTR_ values are an enum starting from 0, not a bitmap, users wanting to transition to a different atime setting cannot simply specify the atime setting in @attr_set, but must also specify MOUNT_ATTR__ATIME in the @attr_clr field. So we ensure that MOUNT_ATTR__ATIME can't be partially set in @attr_clr and that @attr_set can't have any atime bits set if MOUNT_ATTR__ATIME isn't set in @attr_clr. The @propagation field lets callers specify the propagation type of a mount tree. Propagation is a single property that has four different settings and as such is not really a flag argument but an enum. Specifically, it would be unclear what setting and clearing propagation settings in combination would amount to. The legacy mount() syscall thus forbids the combination of multiple propagation settings too. The goal is to keep the semantics of mount propagation somewhat simple as they are overly complex as it is. The @userns_fd field lets user specify a user namespace whose idmapping becomes the idmapping of the mount. This is implemented and explained in detail in the next patch. [1]: commit 2e4b7fcd9260 ("[PATCH] r/o bind mounts: honor mount writer counts at remount") Link: https://lore.kernel.org/r/20210121131959.646623-35-christian.brauner@ubuntu.com Cc: David Howells Cc: Aleksa Sarai Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Cc: linux-api@vger.kernel.org Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner --- include/linux/syscalls.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 7688bc983de5..cd7b5c817ba2 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -68,6 +68,7 @@ union bpf_attr; struct io_uring_params; struct clone_args; struct open_how; +struct mount_attr; #include #include @@ -1028,6 +1029,9 @@ asmlinkage long sys_open_tree(int dfd, const char __user *path, unsigned flags); asmlinkage long sys_move_mount(int from_dfd, const char __user *from_path, int to_dfd, const char __user *to_path, unsigned int ms_flags); +asmlinkage long sys_mount_setattr(int dfd, const char __user *path, + unsigned int flags, + struct mount_attr __user *uattr, size_t usize); asmlinkage long sys_fsopen(const char __user *fs_name, unsigned int flags); asmlinkage long sys_fsconfig(int fs_fd, unsigned int cmd, const char __user *key, const void __user *value, int aux); -- cgit v1.2.3 From 9caccd41541a6f7d6279928d9f971f6642c361af Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 21 Jan 2021 14:19:54 +0100 Subject: fs: introduce MOUNT_ATTR_IDMAP MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduce a new mount bind mount property to allow idmapping mounts. The MOUNT_ATTR_IDMAP flag can be set via the new mount_setattr() syscall together with a file descriptor referring to a user namespace. The user namespace referenced by the namespace file descriptor will be attached to the bind mount. All interactions with the filesystem going through that mount will be mapped according to the mapping specified in the user namespace attached to it. Using user namespaces to mark mounts means we can reuse all the existing infrastructure in the kernel that already exists to handle idmappings and can also use this for permission checking to allow unprivileged user to create idmapped mounts in the future. Idmapping a mount is decoupled from the caller's user and mount namespace. This means idmapped mounts can be created in the initial user namespace which is an important use-case for systemd-homed, portable usb-sticks between systems, sharing data between the initial user namespace and unprivileged containers, and other use-cases that have been brought up. For example, assume a home directory where all files are owned by uid and gid 1000 and the home directory is brought to a new laptop where the user has id 12345. The system administrator can simply create a mount of this home directory with a mapping of 1000:12345:1 and other mappings to indicate the ids should be kept. (With this it is e.g. also possible to create idmapped mounts on the host with an identity mapping 1:1:100000 where the root user is not mapped. A user with root access that e.g. has been pivot rooted into such a mount on the host will be not be able to execute, read, write, or create files as root.) Given that mapping a mount is decoupled from the caller's user namespace a sufficiently privileged process such as a container manager can set up an idmapped mount for the container and the container can simply pivot root to it. There's no need for the container to do anything. The mount will appear correctly mapped independent of the user namespace the container uses. This means we don't need to mark a mount as idmappable. In order to create an idmapped mount the caller must currently be privileged in the user namespace of the superblock the mount belongs to. Once a mount has been idmapped we don't allow it to change its mapping. This keeps permission checking and life-cycle management simple. Users wanting to change the idmapped can always create a new detached mount with a different idmapping. Link: https://lore.kernel.org/r/20210121131959.646623-36-christian.brauner@ubuntu.com Cc: Christoph Hellwig Cc: David Howells Cc: Mauricio Vásquez Bernal Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner --- include/linux/mount.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mount.h b/include/linux/mount.h index 52de25e08319..161f4419db6c 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -77,7 +77,8 @@ struct vfsmount { static inline struct user_namespace *mnt_user_ns(const struct vfsmount *mnt) { - return mnt->mnt_userns; + /* Pairs with smp_store_release() in do_idmap_mount(). */ + return smp_load_acquire(&mnt->mnt_userns); } struct file; /* forward dec */ -- cgit v1.2.3 From 52f019d43c229afd65dc11c8c1b05b6436bf6765 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 9 Jan 2021 11:42:51 +0100 Subject: block: add a hard-readonly flag to struct gendisk Commit 20bd1d026aac ("scsi: sd: Keep disk read-only when re-reading partition") addressed a long-standing problem with user read-only policy being overridden as a result of a device-initiated revalidate. The commit has since been reverted due to a regression that left some USB devices read-only indefinitely. To fix the underlying problems with revalidate we need to keep track of hardware state and user policy separately. The gendisk has been updated to reflect the current hardware state set by the device driver. This is done to allow returning the device to the hardware state once the user clears the BLKROSET flag. The resulting semantics are as follows: - If BLKROSET sets a given partition read-only, that partition will remain read-only even if the underlying storage stack initiates a revalidate. However, the BLKRRPART ioctl will cause the partition table to be dropped and any user policy on partitions will be lost. - If BLKROSET has not been set, both the whole disk device and any partitions will reflect the current write-protect state of the underlying device. Based on a patch from Martin K. Petersen . Reported-by: Oleksii Kurochko Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=201221 Signed-off-by: Christoph Hellwig Reviewed-by: Ming Lei Reviewed-by: Martin K. Petersen Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/genhd.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 809aaa32d53c..a62ccbfac54b 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -163,6 +163,7 @@ struct gendisk { int flags; unsigned long state; #define GD_NEED_PART_SCAN 0 +#define GD_READ_ONLY 1 struct kobject *slave_dir; struct timer_rand_state *random; @@ -249,11 +250,12 @@ static inline void add_disk_no_queue_reg(struct gendisk *disk) extern void del_gendisk(struct gendisk *gp); extern struct block_device *bdget_disk(struct gendisk *disk, int partno); -extern void set_disk_ro(struct gendisk *disk, int flag); +void set_disk_ro(struct gendisk *disk, bool read_only); static inline int get_disk_ro(struct gendisk *disk) { - return disk->part0->bd_read_only; + return disk->part0->bd_read_only || + test_bit(GD_READ_ONLY, &disk->state); } extern void disk_block_events(struct gendisk *disk); -- cgit v1.2.3 From 309dca309fc39a9e3c31b916393b74bd174fd74e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 24 Jan 2021 11:02:34 +0100 Subject: block: store a block_device pointer in struct bio Replace the gendisk pointer in struct bio with a pointer to the newly improved struct block device. From that the gendisk can be trivially accessed with an extra indirection, but it also allows to directly look up all information related to partition remapping. Signed-off-by: Christoph Hellwig Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/bio.h | 18 ++++++++---------- include/linux/blk-mq.h | 4 ++-- include/linux/blk_types.h | 3 +-- include/linux/blkdev.h | 5 +++-- 4 files changed, 14 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 1edda614f7ce..12af7aa5db37 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -483,24 +483,22 @@ extern void bvec_free(mempool_t *, struct bio_vec *, unsigned int); extern unsigned int bvec_nr_vecs(unsigned short idx); extern const char *bio_devname(struct bio *bio, char *buffer); -#define bio_set_dev(bio, bdev) \ -do { \ - if ((bio)->bi_disk != (bdev)->bd_disk) \ - bio_clear_flag(bio, BIO_THROTTLED);\ - (bio)->bi_disk = (bdev)->bd_disk; \ - (bio)->bi_partno = (bdev)->bd_partno; \ - bio_associate_blkg(bio); \ +#define bio_set_dev(bio, bdev) \ +do { \ + if ((bio)->bi_bdev != (bdev)) \ + bio_clear_flag(bio, BIO_THROTTLED); \ + (bio)->bi_bdev = (bdev); \ + bio_associate_blkg(bio); \ } while (0) #define bio_copy_dev(dst, src) \ do { \ - (dst)->bi_disk = (src)->bi_disk; \ - (dst)->bi_partno = (src)->bi_partno; \ + (dst)->bi_bdev = (src)->bi_bdev; \ bio_clone_blkg_association(dst, src); \ } while (0) #define bio_dev(bio) \ - disk_devt((bio)->bi_disk) + disk_devt((bio)->bi_bdev->bd_disk) #ifdef CONFIG_BLK_CGROUP void bio_associate_blkg(struct bio *bio); diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index d705b174d346..6b410dab48ee 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -602,8 +602,8 @@ static inline void blk_rq_bio_prep(struct request *rq, struct bio *bio, rq->bio = rq->biotail = bio; rq->ioprio = bio_prio(bio); - if (bio->bi_disk) - rq->rq_disk = bio->bi_disk; + if (bio->bi_bdev) + rq->rq_disk = bio->bi_bdev->bd_disk; } blk_qc_t blk_mq_submit_bio(struct bio *bio); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 866f74261b3b..8ebd8be3e050 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -222,7 +222,7 @@ static inline void bio_issue_init(struct bio_issue *issue, */ struct bio { struct bio *bi_next; /* request queue link */ - struct gendisk *bi_disk; + struct block_device *bi_bdev; unsigned int bi_opf; /* bottom bits req flags, * top bits REQ_OP. Use * accessors. @@ -231,7 +231,6 @@ struct bio { unsigned short bi_ioprio; unsigned short bi_write_hint; blk_status_t bi_status; - u8 bi_partno; atomic_t __bi_remaining; struct bvec_iter bi_iter; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f94ee3089e01..b55bd534b2e1 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1967,7 +1967,8 @@ void part_end_io_acct(struct block_device *part, struct bio *bio, */ static inline unsigned long bio_start_io_acct(struct bio *bio) { - return disk_start_io_acct(bio->bi_disk, bio_sectors(bio), bio_op(bio)); + return disk_start_io_acct(bio->bi_bdev->bd_disk, bio_sectors(bio), + bio_op(bio)); } /** @@ -1977,7 +1978,7 @@ static inline unsigned long bio_start_io_acct(struct bio *bio) */ static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time) { - return disk_end_io_acct(bio->bi_disk, bio_op(bio), start_time); + return disk_end_io_acct(bio->bi_bdev->bd_disk, bio_op(bio), start_time); } int bdev_read_only(struct block_device *bdev); -- cgit v1.2.3 From 30c5d3456c272f0de0d7e7eb9fc355fa64a5f649 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 24 Jan 2021 11:02:36 +0100 Subject: block: do not reassig ->bi_bdev when partition remapping There is no good reason to reassign ->bi_bdev when remapping the partition-relative block number to the device wide one, as all the information required by the drivers comes from the gendisk anyway. Keeping the original ->bi_bdev alive will allow to greatly simplify the partition-away I/O accounting. Signed-off-by: Christoph Hellwig Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/bio.h | 2 ++ include/linux/blk_types.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 12af7aa5db37..2f1155eabaff 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -485,6 +485,7 @@ extern const char *bio_devname(struct bio *bio, char *buffer); #define bio_set_dev(bio, bdev) \ do { \ + bio_clear_flag(bio, BIO_REMAPPED); \ if ((bio)->bi_bdev != (bdev)) \ bio_clear_flag(bio, BIO_THROTTLED); \ (bio)->bi_bdev = (bdev); \ @@ -493,6 +494,7 @@ do { \ #define bio_copy_dev(dst, src) \ do { \ + bio_clear_flag(dst, BIO_REMAPPED); \ (dst)->bi_bdev = (src)->bi_bdev; \ bio_clone_blkg_association(dst, src); \ } while (0) diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 8ebd8be3e050..1bc6f6a01070 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -303,6 +303,7 @@ enum { * of this bio. */ BIO_CGROUP_ACCT, /* has been accounted to a cgroup */ BIO_TRACKED, /* set if bio goes through the rq_qos path */ + BIO_REMAPPED, BIO_FLAG_LAST }; -- cgit v1.2.3 From 99dfc43ecbf67f12a06512918aaba61d55863efc Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 24 Jan 2021 11:02:37 +0100 Subject: block: use ->bi_bdev for bio based I/O accounting Rework the I/O accounting for bio based drivers to use ->bi_bdev. This means all drivers can now simply use bio_start_io_acct to start accounting, and it will take partitions into account automatically. To end I/O account either bio_end_io_acct can be used if the driver never remaps I/O to a different device, or bio_end_io_acct_remapped if the driver did remap the I/O. Signed-off-by: Christoph Hellwig Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 21 ++++----------------- 1 file changed, 4 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index b55bd534b2e1..4526b9ef8edb 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1954,22 +1954,9 @@ unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, void disk_end_io_acct(struct gendisk *disk, unsigned int op, unsigned long start_time); -unsigned long part_start_io_acct(struct gendisk *disk, - struct block_device **part, struct bio *bio); -void part_end_io_acct(struct block_device *part, struct bio *bio, - unsigned long start_time); - -/** - * bio_start_io_acct - start I/O accounting for bio based drivers - * @bio: bio to start account for - * - * Returns the start time that should be passed back to bio_end_io_acct(). - */ -static inline unsigned long bio_start_io_acct(struct bio *bio) -{ - return disk_start_io_acct(bio->bi_bdev->bd_disk, bio_sectors(bio), - bio_op(bio)); -} +unsigned long bio_start_io_acct(struct bio *bio); +void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time, + struct block_device *orig_bdev); /** * bio_end_io_acct - end I/O accounting for bio based drivers @@ -1978,7 +1965,7 @@ static inline unsigned long bio_start_io_acct(struct bio *bio) */ static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time) { - return disk_end_io_acct(bio->bi_bdev->bd_disk, bio_op(bio), start_time); + return bio_end_io_acct_remapped(bio, start_time, bio->bi_bdev); } int bdev_read_only(struct block_device *bdev); -- cgit v1.2.3 From bc359d03c7ec1bf3b86d03bafaf6bbb21e6414fd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 24 Jan 2021 11:02:39 +0100 Subject: block: add a disk_uevent helper Add a helper to call kobject_uevent for the disk and all partitions, and unexport the disk_part_iter_* helpers that are now only used in the core block code. Signed-off-by: Christoph Hellwig Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/genhd.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index a62ccbfac54b..670eaef0e876 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -213,6 +213,8 @@ static inline dev_t disk_devt(struct gendisk *disk) return MKDEV(disk->major, disk->first_minor); } +void disk_uevent(struct gendisk *disk, enum kobject_action action); + /* * Smarter partition iterator without context limits. */ -- cgit v1.2.3 From 0470dd9d5f103e7f1d5ba8f755f687c3106c7df1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 24 Jan 2021 11:02:40 +0100 Subject: block: remove DISK_PITER_REVERSE There is good reason to iterate backwards when deleting all partitions in del_gendisk, just like we don't in blk_drop_partitions. Signed-off-by: Christoph Hellwig Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/genhd.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 670eaef0e876..51609133c9a3 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -218,7 +218,6 @@ void disk_uevent(struct gendisk *disk, enum kobject_action action); /* * Smarter partition iterator without context limits. */ -#define DISK_PITER_REVERSE (1 << 0) /* iterate in the reverse direction */ #define DISK_PITER_INCL_EMPTY (1 << 1) /* include 0-sized parts */ #define DISK_PITER_INCL_PART0 (1 << 2) /* include partition 0 */ #define DISK_PITER_INCL_EMPTY_PART0 (1 << 3) /* include empty partition 0 */ -- cgit v1.2.3 From a33df75c6328bf40078b35f2040d8e54d574c357 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 24 Jan 2021 11:02:41 +0100 Subject: block: use an xarray for disk->part_tbl Now that no fast path lookups in the partition table are left, there is no point in micro-optimizing the data structure for it. Just use a bog standard xarray. Signed-off-by: Christoph Hellwig Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/genhd.h | 18 +++--------------- 1 file changed, 3 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 51609133c9a3..f364619092cc 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -32,6 +32,7 @@ extern struct class block_class; #include #include #include +#include #define PARTITION_META_INFO_VOLNAMELTH 64 /* @@ -116,13 +117,6 @@ enum { DISK_EVENT_FLAG_UEVENT = 1 << 1, }; -struct disk_part_tbl { - struct rcu_head rcu_head; - int len; - struct block_device __rcu *last_lookup; - struct block_device __rcu *part[]; -}; - struct disk_events; struct badblocks; @@ -148,12 +142,7 @@ struct gendisk { unsigned short events; /* supported events */ unsigned short event_flags; /* flags related to event processing */ - /* Array of pointers to partitions indexed by partno. - * Protected with matching bdev lock but stat and other - * non-critical accesses use RCU. Always access through - * helpers. - */ - struct disk_part_tbl __rcu *part_tbl; + struct xarray part_tbl; struct block_device *part0; const struct block_device_operations *fops; @@ -225,7 +214,7 @@ void disk_uevent(struct gendisk *disk, enum kobject_action action); struct disk_part_iter { struct gendisk *disk; struct block_device *part; - int idx; + unsigned long idx; unsigned int flags; }; @@ -233,7 +222,6 @@ extern void disk_part_iter_init(struct disk_part_iter *piter, struct gendisk *disk, unsigned int flags); struct block_device *disk_part_iter_next(struct disk_part_iter *piter); extern void disk_part_iter_exit(struct disk_part_iter *piter); -extern bool disk_has_partitions(struct gendisk *disk); /* block/genhd.c */ extern void device_add_disk(struct device *parent, struct gendisk *disk, -- cgit v1.2.3 From 5ac83c644f5fb924f0b2c09102ab82fc788f8411 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 11 Jan 2021 17:47:16 +0100 Subject: Revert "blk-mq, elevator: Count requests per hctx to improve performance" This reverts commit b445547ec1bbd3e7bf4b1c142550942f70527d95. Since both mq-deadline and BFQ completely ignore hctx they are passed to their dispatch function and dispatch whatever request they deem fit checking whether any request for a particular hctx is queued is just pointless since we'll very likely get a request from a different hctx anyway. In the following commit we'll deal with lock contention in these IO schedulers in presence of multiple HW queues in a different way. Signed-off-by: Jan Kara Reviewed-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 6b410dab48ee..aabbf6830ffc 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -140,10 +140,6 @@ struct blk_mq_hw_ctx { * shared across request queues. */ atomic_t nr_active; - /** - * @elevator_queued: Number of queued requests on hctx. - */ - atomic_t elevator_queued; /** @cpuhp_online: List to store request if CPU is going to die */ struct hlist_node cpuhp_online; -- cgit v1.2.3 From b6e68ee82585f2ee890b0a897a6aacbf49a467bb Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 11 Jan 2021 17:47:17 +0100 Subject: blk-mq: Improve performance of non-mq IO schedulers with multiple HW queues Currently when non-mq aware IO scheduler (BFQ, mq-deadline) is used for a queue with multiple HW queues, the performance it rather bad. The problem is that these IO schedulers use queue-wide locking and their dispatch function does not respect the hctx it is passed in and returns any request it finds appropriate. Thus locality of request access is broken and dispatch from multiple CPUs just contends on IO scheduler locks. For these IO schedulers there's little point in dispatching from multiple CPUs. Instead dispatch always only from a single CPU to limit contention. Below is a comparison of dbench runs on XFS filesystem where the storage is a raid card with 64 HW queues and to it attached a single rotating disk. BFQ is used as IO scheduler: clients MQ SQ MQ-Patched Amean 1 39.12 (0.00%) 43.29 * -10.67%* 36.09 * 7.74%* Amean 2 128.58 (0.00%) 101.30 * 21.22%* 96.14 * 25.23%* Amean 4 577.42 (0.00%) 494.47 * 14.37%* 508.49 * 11.94%* Amean 8 610.95 (0.00%) 363.86 * 40.44%* 362.12 * 40.73%* Amean 16 391.78 (0.00%) 261.49 * 33.25%* 282.94 * 27.78%* Amean 32 324.64 (0.00%) 267.71 * 17.54%* 233.00 * 28.23%* Amean 64 295.04 (0.00%) 253.02 * 14.24%* 242.37 * 17.85%* Amean 512 10281.61 (0.00%) 10211.16 * 0.69%* 10447.53 * -1.61%* Numbers are times so lower is better. MQ is stock 5.10-rc6 kernel. SQ is the same kernel with megaraid_sas.host_tagset_enable=0 so that the card advertises just a single HW queue. MQ-Patched is a kernel with this patch applied. You can see multiple hardware queues heavily hurt performance in combination with BFQ. The patch restores the performance. Signed-off-by: Jan Kara Reviewed-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/elevator.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/elevator.h b/include/linux/elevator.h index bacc40a0bdf3..1fe8e105b83b 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -172,6 +172,8 @@ extern struct request *elv_rb_find(struct rb_root *, sector_t); /* Supports zoned block devices sequential write constraint */ #define ELEVATOR_F_ZBD_SEQ_WRITE (1U << 0) +/* Supports scheduling on multiple hardware queues */ +#define ELEVATOR_F_MQ_AWARE (1U << 1) #endif /* CONFIG_BLOCK */ #endif -- cgit v1.2.3 From 9f180e315a93cde559ac1c9c4c5ce980aa681c1c Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Mon, 11 Jan 2021 11:05:54 +0800 Subject: block: don't allocate inline bvecs if this bioset needn't bvecs The inline bvecs won't be used if user needn't bvecs by not passing BIOSET_NEED_BVECS, so don't allocate bvecs in this situation. Reviewed-by: Christoph Hellwig Signed-off-by: Ming Lei Reviewed-by: Pavel Begunkov Tested-by: Pavel Begunkov Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/bio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 2f1155eabaff..5d8977aafa19 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -703,6 +703,7 @@ struct bio_set { mempool_t bvec_integrity_pool; #endif + unsigned int back_pad; /* * Deadlock avoidance for stacking block drivers: see comments in * bio_alloc_bioset() for details -- cgit v1.2.3 From eec716a1c18c796a69db0be5e2a6f282ba5bccd6 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Mon, 11 Jan 2021 11:05:56 +0800 Subject: block: move three bvec helpers declaration into private helper bvec_alloc(), bvec_free() and bvec_nr_vecs() are only used inside block layer core functions, no need to declare them in public header. Reviewed-by: Christoph Hellwig Signed-off-by: Ming Lei Reviewed-by: Pavel Begunkov Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/bio.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 5d8977aafa19..e135b500df5d 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -478,9 +478,6 @@ static inline void zero_fill_bio(struct bio *bio) zero_fill_bio_iter(bio, bio->bi_iter); } -extern struct bio_vec *bvec_alloc(gfp_t, int, unsigned long *, mempool_t *); -extern void bvec_free(mempool_t *, struct bio_vec *, unsigned int); -extern unsigned int bvec_nr_vecs(unsigned short idx); extern const char *bio_devname(struct bio *bio, char *buffer); #define bio_set_dev(bio, bdev) \ -- cgit v1.2.3 From 8eeed0b554b9fda61be05b17cbb0b89ea2cbbb65 Mon Sep 17 00:00:00 2001 From: Guoqing Jiang Date: Mon, 25 Jan 2021 05:49:57 +0100 Subject: block: remove unnecessary argument from blk_execute_rq_nowait The 'q' is not used since commit a1ce35fa4985 ("block: remove dead elevator code"), also update the comment of the function. And more importantly it never really was needed to start with given that we can trivial derive it from struct request. Cc: target-devel@vger.kernel.org Cc: linux-scsi@vger.kernel.org Cc: virtualization@lists.linux-foundation.org Cc: linux-ide@vger.kernel.org Cc: linux-mmc@vger.kernel.org Cc: linux-nvme@lists.infradead.org Cc: linux-nfs@vger.kernel.org Signed-off-by: Guoqing Jiang Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 4526b9ef8edb..623a61239429 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -950,7 +950,7 @@ extern int blk_rq_map_user_iov(struct request_queue *, struct request *, gfp_t); extern void blk_execute_rq(struct request_queue *, struct gendisk *, struct request *, int); -extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *, +extern void blk_execute_rq_nowait(struct gendisk *, struct request *, int, rq_end_io_fn *); /* Helper to convert REQ_OP_XXX to its string format XXX */ -- cgit v1.2.3 From 684da7628d93bbdcfba9081b917d99f29ad04c23 Mon Sep 17 00:00:00 2001 From: Guoqing Jiang Date: Mon, 25 Jan 2021 05:49:58 +0100 Subject: block: remove unnecessary argument from blk_execute_rq We can remove 'q' from blk_execute_rq as well after the previous change in blk_execute_rq_nowait. And more importantly it never really was needed to start with given that we can trivial derive it from struct request. Cc: linux-scsi@vger.kernel.org Cc: virtualization@lists.linux-foundation.org Cc: linux-ide@vger.kernel.org Cc: linux-mmc@vger.kernel.org Cc: linux-nvme@lists.infradead.org Cc: linux-nfs@vger.kernel.org Acked-by: Ulf Hansson # for mmc Signed-off-by: Guoqing Jiang Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 623a61239429..20f3706b6b2e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -948,8 +948,7 @@ extern int blk_rq_map_kern(struct request_queue *, struct request *, void *, uns extern int blk_rq_map_user_iov(struct request_queue *, struct request *, struct rq_map_data *, const struct iov_iter *, gfp_t); -extern void blk_execute_rq(struct request_queue *, struct gendisk *, - struct request *, int); +extern void blk_execute_rq(struct gendisk *, struct request *, int); extern void blk_execute_rq_nowait(struct gendisk *, struct request *, int, rq_end_io_fn *); -- cgit v1.2.3 From f75a1025c0b94d58de56c9421104ed6e987ddcd2 Mon Sep 17 00:00:00 2001 From: Kyle Tso Date: Sat, 16 Jan 2021 00:33:11 +0800 Subject: usb: typec: tcpm: Create legacy PDOs for PD2 connection If the port partner is PD2, the PDOs of the local port should follow the format defined in PD2 Spec. Dynamically modify the pre-defined PD3 PDOs and transform them into PD2 format before sending them to the PD2 port partner. Reviewed-by: Guenter Roeck Signed-off-by: Kyle Tso Link: https://lore.kernel.org/r/20210115163311.391332-1-kyletso@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/pd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/pd.h b/include/linux/usb/pd.h index 272454f9cd67..70d681918d01 100644 --- a/include/linux/usb/pd.h +++ b/include/linux/usb/pd.h @@ -225,6 +225,7 @@ enum pd_pdo_type { #define PDO_FIXED_EXTPOWER BIT(27) /* Externally powered */ #define PDO_FIXED_USB_COMM BIT(26) /* USB communications capable */ #define PDO_FIXED_DATA_SWAP BIT(25) /* Data role swap supported */ +#define PDO_FIXED_UNCHUNK_EXT BIT(24) /* Unchunked Extended Message supported (Source) */ #define PDO_FIXED_FRS_CURR_MASK (BIT(24) | BIT(23)) /* FR_Swap Current (Sink) */ #define PDO_FIXED_FRS_CURR_SHIFT 23 #define PDO_FIXED_VOLT_SHIFT 10 /* 50mV units */ -- cgit v1.2.3 From 2289e87b5951f97783f07fc895e6c5e804b53668 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 17 Sep 2020 17:22:49 -0400 Subject: SUNRPC: Make trace_svc_process() display the RPC procedure symbolically The next few patches will employ these strings to help make server- side trace logs more human-readable. A similar technique is already in use in kernel RPC client code. Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 34c2a69820e9..31ee3b6047c3 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -463,6 +463,7 @@ struct svc_procedure { unsigned int pc_ressize; /* result struct size */ unsigned int pc_cachetype; /* cache info (NFS) */ unsigned int pc_xdrressize; /* maximum size of XDR reply */ + const char * pc_name; /* for display */ }; /* -- cgit v1.2.3 From 81d217474326b25d7f14274b02fe3da1e85ad934 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 27 Nov 2020 17:37:02 -0500 Subject: SUNRPC: Move definition of XDR_UNIT Clean up: The unit of XDR alignment is defined by RFC 4506, not as part of the RPC message header. Thus it belongs in include/linux/sunrpc/xdr.h. Signed-off-by: Chuck Lever --- include/linux/sunrpc/msg_prot.h | 3 --- include/linux/sunrpc/xdr.h | 13 ++++++++++--- 2 files changed, 10 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/msg_prot.h b/include/linux/sunrpc/msg_prot.h index 43f854487539..938c2bf29db8 100644 --- a/include/linux/sunrpc/msg_prot.h +++ b/include/linux/sunrpc/msg_prot.h @@ -10,9 +10,6 @@ #define RPC_VERSION 2 -/* size of an XDR encoding unit in bytes, i.e. 32bit */ -#define XDR_UNIT (4) - /* spec defines authentication flavor as an unsigned 32 bit integer */ typedef u32 rpc_authflavor_t; diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 19b6dea27367..dbba537caab6 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -19,6 +19,13 @@ struct bio_vec; struct rpc_rqst; +/* + * Size of an XDR encoding unit in bytes, i.e. 32 bits, + * as defined in Section 3 of RFC 4506. All encoded + * XDR data items are aligned on a boundary of 32 bits. + */ +#define XDR_UNIT sizeof(__be32) + /* * Buffer adjustment */ @@ -330,7 +337,7 @@ ssize_t xdr_stream_decode_string_dup(struct xdr_stream *xdr, char **str, static inline size_t xdr_align_size(size_t n) { - const size_t mask = sizeof(__u32) - 1; + const size_t mask = XDR_UNIT - 1; return (n + mask) & ~mask; } @@ -360,7 +367,7 @@ static inline size_t xdr_pad_size(size_t n) */ static inline ssize_t xdr_stream_encode_item_present(struct xdr_stream *xdr) { - const size_t len = sizeof(__be32); + const size_t len = XDR_UNIT; __be32 *p = xdr_reserve_space(xdr, len); if (unlikely(!p)) @@ -379,7 +386,7 @@ static inline ssize_t xdr_stream_encode_item_present(struct xdr_stream *xdr) */ static inline int xdr_stream_encode_item_absent(struct xdr_stream *xdr) { - const size_t len = sizeof(__be32); + const size_t len = XDR_UNIT; __be32 *p = xdr_reserve_space(xdr, len); if (unlikely(!p)) -- cgit v1.2.3 From 6bb844b4eb6e3b109a2fdaffb60e6da722dc4356 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 17 Nov 2020 10:38:46 -0500 Subject: NFSD: Add an xdr_stream-based decoder for NFSv2/3 ACLs Signed-off-by: Chuck Lever --- include/linux/nfsacl.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfsacl.h b/include/linux/nfsacl.h index 103d44695323..0ba99c513649 100644 --- a/include/linux/nfsacl.h +++ b/include/linux/nfsacl.h @@ -38,5 +38,8 @@ nfsacl_encode(struct xdr_buf *buf, unsigned int base, struct inode *inode, extern int nfsacl_decode(struct xdr_buf *buf, unsigned int base, unsigned int *aclcnt, struct posix_acl **pacl); +extern bool +nfs_stream_decode_acl(struct xdr_stream *xdr, unsigned int *aclcnt, + struct posix_acl **pacl); #endif /* __LINUX_NFSACL_H */ -- cgit v1.2.3 From df971cd853c05778ae1175e8aeb80a04bb9d4be5 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 29 Dec 2020 15:47:44 -0500 Subject: svcrdma: Convert rdma_stat_recv to a per-CPU counter Receives are frequent events. Avoid the overhead of a memory bus lock cycle for counting a value that is hardly every used. Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc_rdma.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 294b56e61522..ff32c59a27e7 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -49,6 +49,7 @@ #include #include +#include #include #include @@ -65,7 +66,7 @@ extern unsigned int svcrdma_max_requests; extern unsigned int svcrdma_max_bc_requests; extern unsigned int svcrdma_max_req_size; -extern atomic_t rdma_stat_recv; +extern struct percpu_counter svcrdma_stat_recv; extern atomic_t rdma_stat_read; extern atomic_t rdma_stat_write; extern atomic_t rdma_stat_sq_starve; -- cgit v1.2.3 From 22df5a22462e836ccb30634c3a52602091179a73 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 29 Dec 2020 15:55:17 -0500 Subject: svcrdma: Convert rdma_stat_sq_starve to a per-CPU counter Avoid the overhead of a memory bus lock cycle for counting a value that is hardly every used. Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc_rdma.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index ff32c59a27e7..c06b16ccf83e 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -69,7 +69,7 @@ extern unsigned int svcrdma_max_req_size; extern struct percpu_counter svcrdma_stat_recv; extern atomic_t rdma_stat_read; extern atomic_t rdma_stat_write; -extern atomic_t rdma_stat_sq_starve; +extern struct percpu_counter svcrdma_stat_sq_starve; extern atomic_t rdma_stat_rq_starve; extern atomic_t rdma_stat_rq_poll; extern atomic_t rdma_stat_rq_prod; -- cgit v1.2.3 From 1e7e55731628c90d8c701c45f9c3a3b8718840d6 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 29 Dec 2020 16:09:36 -0500 Subject: svcrdma: Restore read and write stats Now that we have an efficient mechanism to update these two stats, let's start maintaining them again. Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc_rdma.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index c06b16ccf83e..c882816cba8e 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -66,10 +66,10 @@ extern unsigned int svcrdma_max_requests; extern unsigned int svcrdma_max_bc_requests; extern unsigned int svcrdma_max_req_size; +extern struct percpu_counter svcrdma_stat_read; extern struct percpu_counter svcrdma_stat_recv; -extern atomic_t rdma_stat_read; -extern atomic_t rdma_stat_write; extern struct percpu_counter svcrdma_stat_sq_starve; +extern struct percpu_counter svcrdma_stat_write; extern atomic_t rdma_stat_rq_starve; extern atomic_t rdma_stat_rq_poll; extern atomic_t rdma_stat_rq_prod; -- cgit v1.2.3 From c6226ff9a62a17182b8092883ca201df5cd47f59 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 29 Dec 2020 14:53:09 -0500 Subject: svcrdma: Deprecate stat variables that are no longer used Clean up. We are not permitted to remove old proc files. Instead, convert these variables to stubs that are only ever allowed to display a value of zero. Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc_rdma.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index c882816cba8e..1e76ed688044 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -70,11 +70,6 @@ extern struct percpu_counter svcrdma_stat_read; extern struct percpu_counter svcrdma_stat_recv; extern struct percpu_counter svcrdma_stat_sq_starve; extern struct percpu_counter svcrdma_stat_write; -extern atomic_t rdma_stat_rq_starve; -extern atomic_t rdma_stat_rq_poll; -extern atomic_t rdma_stat_rq_prod; -extern atomic_t rdma_stat_sq_poll; -extern atomic_t rdma_stat_sq_prod; struct svcxprt_rdma { struct svc_xprt sc_xprt; /* SVC transport structure */ -- cgit v1.2.3 From 43042b90cae11cc2d9827c91df6d6b5fe498d5ce Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 8 Dec 2020 13:14:15 -0500 Subject: svcrdma: Reduce Receive doorbell rate This is similar to commit e340c2d6ef2a ("xprtrdma: Reduce the doorbell rate (Receive)") which added Receive batching to the client. Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc_rdma.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 1e76ed688044..7c693b31965e 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -104,6 +104,7 @@ struct svcxprt_rdma { wait_queue_head_t sc_send_wait; /* SQ exhaustion waitlist */ unsigned long sc_flags; + u32 sc_pending_recvs; struct list_head sc_read_complete_q; struct work_struct sc_work; -- cgit v1.2.3 From 3e1a88ec96259282b9a8b45c3f1fda7a3ff4f6ea Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Sat, 9 Jan 2021 16:03:02 +0000 Subject: bio: add a helper calculating nr segments to alloc Add a helper function calculating the number of bvec segments we need to allocate to construct a bio. It doesn't change anything functionally, but will be used to not duplicate special cases in the future. Reviewed-by: Christoph Hellwig Signed-off-by: Pavel Begunkov Reviewed-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/bio.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index e135b500df5d..9ddb19801a03 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -10,6 +10,7 @@ #include /* struct bio, bio_vec and BIO_* flags are defined in blk_types.h */ #include +#include #define BIO_DEBUG @@ -441,6 +442,15 @@ static inline void bio_wouldblock_error(struct bio *bio) bio_endio(bio); } +/* + * Calculate number of bvec segments that should be allocated to fit data + * pointed by @iter. + */ +static inline int bio_iov_vecs_to_alloc(struct iov_iter *iter, int max_segs) +{ + return iov_iter_npages(iter, max_segs); +} + struct request_queue; extern int submit_bio_wait(struct bio *bio); -- cgit v1.2.3 From c42bca92be928ce7dece5fc04cf68d0e37ee6718 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Sat, 9 Jan 2021 16:03:03 +0000 Subject: bio: don't copy bvec for direct IO The block layer spends quite a while in blkdev_direct_IO() to copy and initialise bio's bvec. However, if we've already got a bvec in the input iterator it might be reused in some cases, i.e. when new ITER_BVEC_FLAG_FIXED flag is set. Simple tests show considerable performance boost, and it also reduces memory footprint. Suggested-by: Matthew Wilcox Reviewed-by: Christoph Hellwig Signed-off-by: Pavel Begunkov Reviewed-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/bio.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 9ddb19801a03..676870b2c88d 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -444,10 +444,13 @@ static inline void bio_wouldblock_error(struct bio *bio) /* * Calculate number of bvec segments that should be allocated to fit data - * pointed by @iter. + * pointed by @iter. If @iter is backed by bvec it's going to be reused + * instead of allocating a new one. */ static inline int bio_iov_vecs_to_alloc(struct iov_iter *iter, int max_segs) { + if (iov_iter_is_bvec(iter)) + return 0; return iov_iter_npages(iter, max_segs); } -- cgit v1.2.3 From 9d56653d14cd5e545599cd9e3013daa17df50cd4 Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Mon, 25 Jan 2021 12:59:56 +0100 Subject: ACPI: platform-profile: Drop const qualifier for cur_profile Drop the const qualifier from the static global cur_profile pointer declaration. This is a preparation patch for passing the cur_profile pointer as parameter to the profile_get() and profile_set() callbacks so that drivers dynamically allocating their driver-data struct, with their platform_profile_handler struct embedded, can use this pointer to get to their driver-data. Note this also requires dropping the const from the pprof platform_profile_register() function argument. Dropping this const is not a problem, non of the queued up consumers of platform_profile_register() actually pass in a const pointer. Link: https://lore.kernel.org/linux-acpi/5e7a4d87-52ef-e487-9cc2-8e7094beaa08@redhat.com/ Link: https://lore.kernel.org/r/20210114073429.176462-2-jiaxun.yang@flygoat.com Suggested-by: Hans de Goede Signed-off-by: Jiaxun Yang [ hdegoede@redhat.com: Also remove const from platform_profile_register() ] Signed-off-by: Hans de Goede Signed-off-by: Rafael J. Wysocki --- include/linux/platform_profile.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_profile.h b/include/linux/platform_profile.h index 3623d7108421..c797fdb3d91a 100644 --- a/include/linux/platform_profile.h +++ b/include/linux/platform_profile.h @@ -32,7 +32,7 @@ struct platform_profile_handler { int (*profile_set)(enum platform_profile_option profile); }; -int platform_profile_register(const struct platform_profile_handler *pprof); +int platform_profile_register(struct platform_profile_handler *pprof); int platform_profile_remove(void); void platform_profile_notify(void); -- cgit v1.2.3 From d17655759b3fc660ea49bd7be665c193030c77c0 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Sat, 23 Jan 2021 19:34:45 +0300 Subject: reset: Add devm_reset_control_get_optional_exclusive_released() NVIDIA Tegra DRM and media drivers will need a resource-managed-optional variant of reset_control_get_exclusive_released() in order to switch away from a legacy Tegra-specific PD API to a GENPD API without much hassle. Add the new reset helper to the reset API. Tested-by: Peter Geis # Ouya T30 Tested-by: Nicolas Chauvet # PAZ00 T20 Tested-by: Matt Merhar # Ouya T30 Signed-off-by: Dmitry Osipenko Signed-off-by: Philipp Zabel --- include/linux/reset.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/reset.h b/include/linux/reset.h index 439fec7112a9..b9109efa2a5c 100644 --- a/include/linux/reset.h +++ b/include/linux/reset.h @@ -362,6 +362,25 @@ __must_check devm_reset_control_get_exclusive_released(struct device *dev, return __devm_reset_control_get(dev, id, 0, false, false, false); } +/** + * devm_reset_control_get_optional_exclusive_released - resource managed + * reset_control_get_optional_exclusive_released() + * @dev: device to be reset by the controller + * @id: reset line name + * + * Managed-and-optional variant of reset_control_get_exclusive_released(). For + * reset controllers returned from this function, reset_control_put() is called + * automatically on driver detach. + * + * See reset_control_get_exclusive_released() for more information. + */ +static inline struct reset_control * +__must_check devm_reset_control_get_optional_exclusive_released(struct device *dev, + const char *id) +{ + return __devm_reset_control_get(dev, id, 0, false, true, false); +} + /** * devm_reset_control_get_shared - resource managed reset_control_get_shared() * @dev: device to be reset by the controller -- cgit v1.2.3 From 83ace77f51175023c3757e2d08a92565f9b1c7f3 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 20 Jan 2021 16:30:03 +0100 Subject: netfilter: ctnetlink: remove get_ct indirection Use nf_ct_get() directly, its a small inline helper without dependencies. Add CONFIG_NF_CONNTRACK guards to elide the relevant part when conntrack isn't available at all. v2: add ifdef guard around nf_ct_get call (kernel test robot) Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 0101747de549..f0f3a8354c3c 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -463,8 +463,6 @@ extern struct nf_ct_hook __rcu *nf_ct_hook; struct nlattr; struct nfnl_ct_hook { - struct nf_conn *(*get_ct)(const struct sk_buff *skb, - enum ip_conntrack_info *ctinfo); size_t (*build_size)(const struct nf_conn *ct); int (*build)(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, -- cgit v1.2.3 From 30e88d017fcbeb50c4b07577fe059558361067e7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 22 Jan 2021 10:24:49 +0100 Subject: isa: Make the remove callback for isa drivers return void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver core ignores the return value of the remove callback, so don't give isa drivers the chance to provide a value. Adapt all isa_drivers with a remove callbacks accordingly; they all return 0 unconditionally anyhow. Acked-by: Marc Kleine-Budde # for drivers/net/can/sja1000/tscan1.c Acked-by: William Breathitt Gray Acked-by: Wolfram Sang # for drivers/i2c/ Reviewed-by: Takashi Iway # for sound/ Reviewed-by: Hans Verkuil # for drivers/media/ Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20210122092449.426097-4-uwe@kleine-koenig.org Signed-off-by: Takashi Iwai --- include/linux/isa.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/isa.h b/include/linux/isa.h index 41336da0f4e7..e30963190968 100644 --- a/include/linux/isa.h +++ b/include/linux/isa.h @@ -13,7 +13,7 @@ struct isa_driver { int (*match)(struct device *, unsigned int); int (*probe)(struct device *, unsigned int); - int (*remove)(struct device *, unsigned int); + void (*remove)(struct device *, unsigned int); void (*shutdown)(struct device *, unsigned int); int (*suspend)(struct device *, unsigned int, pm_message_t); int (*resume)(struct device *, unsigned int); -- cgit v1.2.3 From ceecd1bff6f9a741adc173f062f1f9312c3a66c8 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 19 Jan 2021 12:07:22 -0800 Subject: HID: correct kernel-doc notation in Correct kernel-doc notation in HID header files (include/linux/hid*.h). Add notation (comments) where it is missing. Use the documented "Return:" notation for function return values. Fix a few typos/spellos. Signed-off-by: Randy Dunlap Cc: Jiri Kosina Cc: Benjamin Tissoires Cc: linux-input@vger.kernel.org Signed-off-by: Jiri Kosina --- include/linux/hid-sensor-hub.h | 9 +++++---- include/linux/hid.h | 15 +++++++++++---- 2 files changed, 16 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hid-sensor-hub.h b/include/linux/hid-sensor-hub.h index 46bcef380446..763802b2b8f9 100644 --- a/include/linux/hid-sensor-hub.h +++ b/include/linux/hid-sensor-hub.h @@ -150,7 +150,7 @@ int sensor_hub_remove_callback(struct hid_sensor_hub_device *hsdev, * @info: return information about attribute after parsing report * * Parses report and returns the attribute information such as report id, -* field index, units and exponet etc. +* field index, units and exponent etc. */ int sensor_hub_input_get_attribute_info(struct hid_sensor_hub_device *hsdev, u8 type, @@ -167,7 +167,7 @@ int sensor_hub_input_get_attribute_info(struct hid_sensor_hub_device *hsdev, * @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. +* Return: data up to 32 bits. */ enum sensor_hub_read_flags { @@ -205,8 +205,9 @@ int sensor_hub_set_feature(struct hid_sensor_hub_device *hsdev, u32 report_id, * @buffer: buffer to copy output * * Used to get a field in feature report. For example this can get polling -* interval, sensitivity, activate/deactivate state. On success it returns -* number of bytes copied to buffer. On failure, it returns value < 0. +* interval, sensitivity, activate/deactivate state. +* Return: On success, it returns the number of bytes copied to buffer. +* On failure, it returns value < 0. */ int sensor_hub_get_feature(struct hid_sensor_hub_device *hsdev, u32 report_id, u32 field_index, int buffer_size, void *buffer); diff --git a/include/linux/hid.h b/include/linux/hid.h index c39d71eb1fd0..ef702b3f56e3 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -918,7 +918,7 @@ __u32 hid_field_extract(const struct hid_device *hid, __u8 *report, /** * hid_device_io_start - enable HID input during probe, remove * - * @hid - the device + * @hid: the device * * This should only be called during probe or remove and only be * called by the thread calling probe or remove. It will allow @@ -936,7 +936,7 @@ static inline void hid_device_io_start(struct hid_device *hid) { /** * hid_device_io_stop - disable HID input during probe, remove * - * @hid - the device + * @hid: the device * * Should only be called after hid_device_io_start. It will prevent * incoming packets from going to the driver for the duration of @@ -1010,6 +1010,13 @@ static inline void hid_map_usage(struct hid_input *hidinput, /** * hid_map_usage_clear - map usage input bits and clear the input bit * + * @hidinput: hidinput which we are interested in + * @usage: usage to fill in + * @bit: pointer to input->{}bit (out parameter) + * @max: maximal valid usage->code to consider later (out parameter) + * @type: input event type (EV_KEY, EV_REL, ...) + * @c: code which corresponds to this usage and type + * * The same as hid_map_usage, except the @c bit is also cleared in supported * bits (@bit). */ @@ -1084,7 +1091,7 @@ static inline void hid_hw_request(struct hid_device *hdev, * @rtype: HID report type * @reqtype: HID_REQ_GET_REPORT or HID_REQ_SET_REPORT * - * @return: count of data transfered, negative if error + * Return: count of data transferred, negative if error * * Same behavior as hid_hw_request, but with raw buffers instead. */ @@ -1106,7 +1113,7 @@ static inline int hid_hw_raw_request(struct hid_device *hdev, * @buf: raw data to transfer * @len: length of buf * - * @return: count of data transfered, negative if error + * Return: count of data transferred, negative if error */ static inline int hid_hw_output_report(struct hid_device *hdev, __u8 *buf, size_t len) -- cgit v1.2.3 From 081df94301e317e84c3413686043987da2c3e39d Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Thu, 21 Jan 2021 15:29:23 -0600 Subject: objtool: Add asm version of STACK_FRAME_NON_STANDARD To be used for adding asm functions to the ignore list. The "aw" is needed to help the ELF section metadata match GCC-created sections. Otherwise the linker creates duplicate sections instead of combining them. Signed-off-by: Josh Poimboeuf Link: https://lore.kernel.org/r/8faa476f9a5ac89af27944ec184c89f95f3c6c49.1611263462.git.jpoimboe@redhat.com --- include/linux/objtool.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 577f51436cf9..add1c6eb157e 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -109,6 +109,12 @@ struct unwind_hint { .popsection .endm +.macro STACK_FRAME_NON_STANDARD func:req + .pushsection .discard.func_stack_frame_non_standard, "aw" + .long \func - . + .popsection +.endm + #endif /* __ASSEMBLY__ */ #else /* !CONFIG_STACK_VALIDATION */ @@ -122,6 +128,8 @@ struct unwind_hint { #define ANNOTATE_INTRA_FUNCTION_CALL .macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0 .endm +.macro STACK_FRAME_NON_STANDARD func:req +.endm #endif #endif /* CONFIG_STACK_VALIDATION */ -- cgit v1.2.3 From b735bd3e68824316655252a931a3353a6ebc036f Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Thu, 21 Jan 2021 15:29:24 -0600 Subject: objtool: Combine UNWIND_HINT_RET_OFFSET and UNWIND_HINT_FUNC The ORC metadata generated for UNWIND_HINT_FUNC isn't actually very func-like. With certain usages it can cause stack state mismatches because it doesn't set the return address (CFI_RA). Also, users of UNWIND_HINT_RET_OFFSET no longer need to set a custom return stack offset. Instead they just need to specify a func-like situation, so the current ret_offset code is hacky for no good reason. Solve both problems by simplifying the RET_OFFSET handling and converting it into a more useful UNWIND_HINT_FUNC. If we end up needing the old 'ret_offset' functionality again in the future, we should be able to support it pretty easily with the addition of a custom 'sp_offset' in UNWIND_HINT_FUNC. Signed-off-by: Josh Poimboeuf Link: https://lore.kernel.org/r/db9d1f5d79dddfbb3725ef6d8ec3477ad199948d.1611263462.git.jpoimboe@redhat.com --- include/linux/objtool.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/objtool.h b/include/linux/objtool.h index add1c6eb157e..7e72d975cb76 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -29,11 +29,14 @@ struct unwind_hint { * * UNWIND_HINT_TYPE_REGS_PARTIAL: Used in entry code to indicate that * sp_reg+sp_offset points to the iret return frame. + * + * UNWIND_HINT_FUNC: Generate the unwind metadata of a callable function. + * Useful for code which doesn't have an ELF function annotation. */ #define UNWIND_HINT_TYPE_CALL 0 #define UNWIND_HINT_TYPE_REGS 1 #define UNWIND_HINT_TYPE_REGS_PARTIAL 2 -#define UNWIND_HINT_TYPE_RET_OFFSET 3 +#define UNWIND_HINT_TYPE_FUNC 3 #ifdef CONFIG_STACK_VALIDATION -- cgit v1.2.3 From d07b6621d948944c6828fc9b5cbdcb6f389b3b04 Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Mon, 18 Jan 2021 09:15:48 -0300 Subject: dmaengine: imx-sdma: Remove platform data support Since 5.10-rc1, i.MX has been converted to a devicetree-only platform. The platform data support in this driver was only used for non-DT platforms. Remove the platform data support as it has no more users. Signed-off-by: Fabio Estevam Link: https://lore.kernel.org/r/20210118121549.1625217-1-festevam@gmail.com Signed-off-by: Vinod Koul --- include/linux/platform_data/dma-imx-sdma.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/dma-imx-sdma.h b/include/linux/platform_data/dma-imx-sdma.h index 30e676b36b24..725602d9df91 100644 --- a/include/linux/platform_data/dma-imx-sdma.h +++ b/include/linux/platform_data/dma-imx-sdma.h @@ -57,15 +57,4 @@ struct sdma_script_start_addrs { /* End of v4 array */ }; -/** - * struct sdma_platform_data - platform specific data for SDMA engine - * - * @fw_name The firmware name - * @script_addrs SDMA scripts addresses in SDMA ROM - */ -struct sdma_platform_data { - char *fw_name; - struct sdma_script_start_addrs *script_addrs; -}; - #endif /* __MACH_MXC_SDMA_H__ */ -- cgit v1.2.3 From ec6ab42f5aadd765b0b8c4e2d21508ac1e20f2ed Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 20 Jan 2021 14:18:57 +0100 Subject: dmaengine: remove sirfsoc driver The CSR SiRF prima2/atlas platforms are getting removed, so this driver is no longer needed. Signed-off-by: Arnd Bergmann Acked-by: Barry Song Cc: Barry Song Link: https://lore.kernel.org/r/20210120131859.2056308-2-arnd@kernel.org Signed-off-by: Vinod Koul --- include/linux/sirfsoc_dma.h | 7 ------- 1 file changed, 7 deletions(-) delete mode 100644 include/linux/sirfsoc_dma.h (limited to 'include/linux') diff --git a/include/linux/sirfsoc_dma.h b/include/linux/sirfsoc_dma.h deleted file mode 100644 index 50161b6afb61..000000000000 --- a/include/linux/sirfsoc_dma.h +++ /dev/null @@ -1,7 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _SIRFSOC_DMA_H_ -#define _SIRFSOC_DMA_H_ - -bool sirfsoc_dma_filter_id(struct dma_chan *chan, void *chan_id); - -#endif -- cgit v1.2.3 From a033a74e8b66336fc2ea379842be6bcf176cbfbc Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 20 Jan 2021 14:18:59 +0100 Subject: dmaengine: remove coh901318 driver The ST-Ericsson U300 platform is getting removed, so this driver is no longer needed. Signed-off-by: Arnd Bergmann Reviewed-by: Linus Walleij Cc: Linus Walleij Link: https://lore.kernel.org/r/20210120131859.2056308-4-arnd@kernel.org Signed-off-by: Vinod Koul --- include/linux/platform_data/dma-coh901318.h | 72 ----------------------------- 1 file changed, 72 deletions(-) delete mode 100644 include/linux/platform_data/dma-coh901318.h (limited to 'include/linux') diff --git a/include/linux/platform_data/dma-coh901318.h b/include/linux/platform_data/dma-coh901318.h deleted file mode 100644 index 4cca529f8d56..000000000000 --- a/include/linux/platform_data/dma-coh901318.h +++ /dev/null @@ -1,72 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Platform data for the COH901318 DMA controller - * Copyright (C) 2007-2013 ST-Ericsson - */ - -#ifndef PLAT_COH901318_H -#define PLAT_COH901318_H - -#ifdef CONFIG_COH901318 - -/* We only support the U300 DMA channels */ -#define U300_DMA_MSL_TX_0 0 -#define U300_DMA_MSL_TX_1 1 -#define U300_DMA_MSL_TX_2 2 -#define U300_DMA_MSL_TX_3 3 -#define U300_DMA_MSL_TX_4 4 -#define U300_DMA_MSL_TX_5 5 -#define U300_DMA_MSL_TX_6 6 -#define U300_DMA_MSL_RX_0 7 -#define U300_DMA_MSL_RX_1 8 -#define U300_DMA_MSL_RX_2 9 -#define U300_DMA_MSL_RX_3 10 -#define U300_DMA_MSL_RX_4 11 -#define U300_DMA_MSL_RX_5 12 -#define U300_DMA_MSL_RX_6 13 -#define U300_DMA_MMCSD_RX_TX 14 -#define U300_DMA_MSPRO_TX 15 -#define U300_DMA_MSPRO_RX 16 -#define U300_DMA_UART0_TX 17 -#define U300_DMA_UART0_RX 18 -#define U300_DMA_APEX_TX 19 -#define U300_DMA_APEX_RX 20 -#define U300_DMA_PCM_I2S0_TX 21 -#define U300_DMA_PCM_I2S0_RX 22 -#define U300_DMA_PCM_I2S1_TX 23 -#define U300_DMA_PCM_I2S1_RX 24 -#define U300_DMA_XGAM_CDI 25 -#define U300_DMA_XGAM_PDI 26 -#define U300_DMA_SPI_TX 27 -#define U300_DMA_SPI_RX 28 -#define U300_DMA_GENERAL_PURPOSE_0 29 -#define U300_DMA_GENERAL_PURPOSE_1 30 -#define U300_DMA_GENERAL_PURPOSE_2 31 -#define U300_DMA_GENERAL_PURPOSE_3 32 -#define U300_DMA_GENERAL_PURPOSE_4 33 -#define U300_DMA_GENERAL_PURPOSE_5 34 -#define U300_DMA_GENERAL_PURPOSE_6 35 -#define U300_DMA_GENERAL_PURPOSE_7 36 -#define U300_DMA_GENERAL_PURPOSE_8 37 -#define U300_DMA_UART1_TX 38 -#define U300_DMA_UART1_RX 39 - -#define U300_DMA_DEVICE_CHANNELS 32 -#define U300_DMA_CHANNELS 40 - -/** - * coh901318_filter_id() - DMA channel filter function - * @chan: dma channel handle - * @chan_id: id of dma channel to be filter out - * - * In dma_request_channel() it specifies what channel id to be requested - */ -bool coh901318_filter_id(struct dma_chan *chan, void *chan_id); -#else -static inline bool coh901318_filter_id(struct dma_chan *chan, void *chan_id) -{ - return false; -} -#endif - -#endif /* PLAT_COH901318_H */ -- cgit v1.2.3 From e247f85a9bf6af9ce6bc36d86ac242f782ae0947 Mon Sep 17 00:00:00 2001 From: Lubomir Rintel Date: Thu, 21 Jan 2021 12:03:54 +0100 Subject: dmaengine: mmp_pdma: Remove mmp_pdma_filter_fn() It's not used anywhere -- drop it. Signed-off-by: Lubomir Rintel Link: https://lore.kernel.org/r/20210121110356.1768635-2-lkundrak@v3.sk Signed-off-by: Vinod Koul --- include/linux/dma/mmp-pdma.h | 16 ---------------- 1 file changed, 16 deletions(-) delete mode 100644 include/linux/dma/mmp-pdma.h (limited to 'include/linux') diff --git a/include/linux/dma/mmp-pdma.h b/include/linux/dma/mmp-pdma.h deleted file mode 100644 index 25cab62a28c4..000000000000 --- a/include/linux/dma/mmp-pdma.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _MMP_PDMA_H_ -#define _MMP_PDMA_H_ - -struct dma_chan; - -#ifdef CONFIG_MMP_PDMA -bool mmp_pdma_filter_fn(struct dma_chan *chan, void *param); -#else -static inline bool mmp_pdma_filter_fn(struct dma_chan *chan, void *param) -{ - return false; -} -#endif - -#endif /* _MMP_PDMA_H_ */ -- cgit v1.2.3 From fd765da06066215b5e75c5c2a0db1543a81aa14d Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 21 Jan 2021 08:18:12 +0100 Subject: staging: hikey9xx: hi6421v600-regulator: fix delay logic The original driver, which can be seen at commit 42f24d9d446a ("staging: regulator: add a regulator driver for HiSilicon 6421v600 SPMI PMIC") had a complex logic to ensure that there won't be multiple power enable/disable commands running at the same time. At the original logic, it were ensured that: - a next power up/down would wait for at least the on/off period; - an extra delay would be granted. It turns that such extra delay has a value of zero, but it was relying on gettimeofday() call, which can take some time. This was later simplified, but there are still some possible issues. In order to avoid that, let's simply add a delay to wait for the power up line to stabilize after powering up a device. Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/6733dac9813ba6688def404142cb7b964accf758.1611212783.git.mchehab+huawei@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mfd/hi6421-spmi-pmic.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/hi6421-spmi-pmic.h b/include/linux/mfd/hi6421-spmi-pmic.h index 2c8896fd852e..0c2214612c4e 100644 --- a/include/linux/mfd/hi6421-spmi-pmic.h +++ b/include/linux/mfd/hi6421-spmi-pmic.h @@ -13,7 +13,6 @@ #include -#define HISI_REGS_ENA_PROTECT_TIME (0) /* in microseconds */ #define HISI_ECO_MODE_ENABLE (1) #define HISI_ECO_MODE_DISABLE (0) -- cgit v1.2.3 From 7eecea89e44f64e60f1410483e79a0cab18ad580 Mon Sep 17 00:00:00 2001 From: Jorgen Hansen Date: Wed, 20 Jan 2021 08:33:40 -0800 Subject: VMCI: Enforce queuepair max size for IOCTL_VMCI_QUEUEPAIR_ALLOC When create the VMCI queue pair tracking data structures on the host side, the IOCTL for creating the VMCI queue pair didn't validate the queue pair size parameters. This change adds checks for this. This avoids a memory allocation issue in qp_host_alloc_queue, as reported by nslusarek@gmx.net. The check in qp_host_alloc_queue has also been updated to enforce the maximum queue pair size as defined by VMCI_MAX_GUEST_QP_MEMORY. The fix has been verified using sample code supplied by nslusarek@gmx.net. Reported-by: nslusarek@gmx.net Reviewed-by: Vishnu Dasa Signed-off-by: Jorgen Hansen Link: https://lore.kernel.org/r/1611160420-30573-1-git-send-email-jhansen@vmware.com Signed-off-by: Greg Kroah-Hartman --- include/linux/vmw_vmci_defs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmw_vmci_defs.h b/include/linux/vmw_vmci_defs.h index be0afe6f379b..e36cb114c188 100644 --- a/include/linux/vmw_vmci_defs.h +++ b/include/linux/vmw_vmci_defs.h @@ -66,7 +66,7 @@ enum { * consists of at least two pages, the memory limit also dictates the * number of queue pairs a guest can create. */ -#define VMCI_MAX_GUEST_QP_MEMORY (128 * 1024 * 1024) +#define VMCI_MAX_GUEST_QP_MEMORY ((size_t)(128 * 1024 * 1024)) #define VMCI_MAX_GUEST_QP_COUNT (VMCI_MAX_GUEST_QP_MEMORY / PAGE_SIZE / 2) /* @@ -80,7 +80,7 @@ enum { * too much kernel memory (especially on vmkernel). We limit a queuepair to * 32 KB, or 16 KB per queue for symmetrical pairs. */ -#define VMCI_MAX_PINNED_QP_MEMORY (32 * 1024) +#define VMCI_MAX_PINNED_QP_MEMORY ((size_t)(32 * 1024)) /* * We have a fixed set of resource IDs available in the VMX. -- cgit v1.2.3 From e9103f47bf1a1bbf0ab0ea90eda3e208653a5f57 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 25 Jan 2021 17:02:38 +0200 Subject: serial: ifx6x60: Remove driver for deprecated platform Intel Moorestown and Medfield are quite old Intel Atom based 32-bit platforms, which were in limited use in some Android phones, tablets and consumer electronics more than eight years ago. There are no bugs or problems ever reported outside from Intel for breaking any of that platforms for years. It seems no real users exists who run more or less fresh kernel on it. The commit 05f4434bc130 ("ASoC: Intel: remove mfld_machine") also in align with this theory. Due to above and to reduce a burden of supporting outdated drivers we remove the support of outdated platforms completely. Signed-off-by: Andy Shevchenko Acked-by: Linus Walleij Link: https://lore.kernel.org/r/20210125150238.16980-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/spi/ifx_modem.h | 15 --------------- 1 file changed, 15 deletions(-) delete mode 100644 include/linux/spi/ifx_modem.h (limited to 'include/linux') diff --git a/include/linux/spi/ifx_modem.h b/include/linux/spi/ifx_modem.h deleted file mode 100644 index 6d19b09139d0..000000000000 --- a/include/linux/spi/ifx_modem.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef LINUX_IFX_MODEM_H -#define LINUX_IFX_MODEM_H - -struct ifx_modem_platform_data { - unsigned short tx_pwr; /* modem power threshold */ - unsigned char modem_type; /* Modem type */ - unsigned long max_hz; /* max SPI frequency */ - unsigned short use_dma:1; /* spi protocol driver supplies - dma-able addrs */ -}; -#define IFX_MODEM_6160 1 -#define IFX_MODEM_6260 2 - -#endif -- cgit v1.2.3 From 529b56a854c5a8bd5e6f045cdcbbcd21a1616fbd Mon Sep 17 00:00:00 2001 From: Daniel Scally Date: Thu, 7 Jan 2021 14:28:30 +0100 Subject: media: device property: Define format macros for ports and endpoints OF, ACPI and software_nodes all implement graphs including nodes for ports and endpoints. These are all intended to be named with a common schema, as "port@n" and "endpoint@n" where n is an unsigned int representing the index of the node. To ensure commonality across the subsystems, provide a set of macros to define the format. Suggested-by: Andy Shevchenko Reviewed-by: Andy Shevchenko Reviewed-by: Laurent Pinchart Signed-off-by: Daniel Scally Reviewed-by: Heikki Krogerus Acked-by: Rafael J. Wysocki Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/linux/fwnode.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index fde4ad97564c..77414e431e89 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -50,6 +50,13 @@ struct fwnode_endpoint { const struct fwnode_handle *local_fwnode; }; +/* + * ports and endpoints defined as software_nodes should all follow a common + * naming scheme; use these macros to ensure commonality. + */ +#define SWNODE_GRAPH_PORT_NAME_FMT "port@%u" +#define SWNODE_GRAPH_ENDPOINT_NAME_FMT "endpoint@%u" + #define NR_FWNODE_REFERENCE_ARGS 8 /** -- cgit v1.2.3 From 0fc99422bc034de018607ef6b70f92d4bc4a236d Mon Sep 17 00:00:00 2001 From: Michal Simek Date: Mon, 18 Jan 2021 09:48:56 +0100 Subject: firmware: xilinx: Remove PM_API_MAX value There is no reason to keep PM_API_MAX around. The commit acfdd18591ea ("firmware: xilinx: Use hash-table for api feature check") removed its usage that's why it is not used anywhere now. Signed-off-by: Michal Simek Link: https://lore.kernel.org/r/86e94593a29a1b5b1958c539a1bfabdd08c0948e.1610959734.git.michal.simek@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 2a0da841c942..0a483249ff30 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -85,7 +85,6 @@ enum pm_api_id { PM_CLOCK_GETPARENT, PM_SECURE_AES = 47, PM_FEATURE_CHECK = 63, - PM_API_MAX, }; /* PMU-FW return status codes */ -- cgit v1.2.3 From 2c2b9fd6b496b3616e9b9537ea0258b3040914f3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 9 Jan 2021 12:13:32 +0100 Subject: block: unexport truncate_bdev_range truncate_bdev_range is only used in always built-in block layer code, so remove the export and the !CONFIG_BLOCK stub. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 20f3706b6b2e..2491e17b61c4 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1999,21 +1999,16 @@ void bdev_add(struct block_device *bdev, dev_t dev); struct block_device *I_BDEV(struct inode *inode); struct block_device *bdgrab(struct block_device *bdev); void bdput(struct block_device *); +int truncate_bdev_range(struct block_device *bdev, fmode_t mode, loff_t lstart, + loff_t lend); #ifdef CONFIG_BLOCK void invalidate_bdev(struct block_device *bdev); -int truncate_bdev_range(struct block_device *bdev, fmode_t mode, loff_t lstart, - loff_t lend); int sync_blockdev(struct block_device *bdev); #else static inline void invalidate_bdev(struct block_device *bdev) { } -static inline int truncate_bdev_range(struct block_device *bdev, fmode_t mode, - loff_t lstart, loff_t lend) -{ - return 0; -} static inline int sync_blockdev(struct block_device *bdev) { return 0; -- cgit v1.2.3 From 6b2e04bc240fe9be9e690059f710e9f95346d34d Mon Sep 17 00:00:00 2001 From: Praveen Chaudhary Date: Mon, 25 Jan 2021 13:44:30 -0800 Subject: net: allow user to set metric on default route learned via Router Advertisement For IPv4, default route is learned via DHCPv4 and user is allowed to change metric using config etc/network/interfaces. But for IPv6, default route can be learned via RA, for which, currently a fixed metric value 1024 is used. Ideally, user should be able to configure metric on default route for IPv6 similar to IPv4. This patch adds sysctl for the same. Logs: For IPv4: Config in etc/network/interfaces: auto eth0 iface eth0 inet dhcp metric 4261413864 IPv4 Kernel Route Table: $ ip route list default via 172.21.47.1 dev eth0 metric 4261413864 FRR Table, if a static route is configured: [In real scenario, it is useful to prefer BGP learned default route over DHCPv4 default route.] Codes: K - kernel route, C - connected, S - static, R - RIP, O - OSPF, I - IS-IS, B - BGP, P - PIM, E - EIGRP, N - NHRP, T - Table, v - VNC, V - VNC-Direct, A - Babel, D - SHARP, > - selected route, * - FIB route S>* 0.0.0.0/0 [20/0] is directly connected, eth0, 00:00:03 K 0.0.0.0/0 [254/1000] via 172.21.47.1, eth0, 6d08h51m i.e. User can prefer Default Router learned via Routing Protocol in IPv4. Similar behavior is not possible for IPv6, without this fix. After fix [for IPv6]: sudo sysctl -w net.ipv6.conf.eth0.net.ipv6.conf.eth0.ra_defrtr_metric=1996489705 IP monitor: [When IPv6 RA is received] default via fe80::xx16:xxxx:feb3:ce8e dev eth0 proto ra metric 1996489705 pref high Kernel IPv6 routing table $ ip -6 route list default via fe80::be16:65ff:feb3:ce8e dev eth0 proto ra metric 1996489705 expires 21sec hoplimit 64 pref high FRR Table, if a static route is configured: [In real scenario, it is useful to prefer BGP learned default route over IPv6 RA default route.] Codes: K - kernel route, C - connected, S - static, R - RIPng, O - OSPFv3, I - IS-IS, B - BGP, N - NHRP, T - Table, v - VNC, V - VNC-Direct, A - Babel, D - SHARP, > - selected route, * - FIB route S>* ::/0 [20/0] is directly connected, eth0, 00:00:06 K ::/0 [119/1001] via fe80::xx16:xxxx:feb3:ce8e, eth0, 6d07h43m If the metric is changed later, the effect will be seen only when next IPv6 RA is received, because the default route must be fully controlled by RA msg. Below metric is changed from 1996489705 to 1996489704. $ sudo sysctl -w net.ipv6.conf.eth0.ra_defrtr_metric=1996489704 net.ipv6.conf.eth0.ra_defrtr_metric = 1996489704 IP monitor: [On next IPv6 RA msg, Kernel deletes prev route and installs new route with updated metric] Deleted default via fe80::xx16:xxxx:feb3:ce8e dev eth0 proto ra metric 1996489705 expires 3sec hoplimit 64 pref high default via fe80::xx16:xxxx:feb3:ce8e dev eth0 proto ra metric 1996489704 pref high Signed-off-by: Praveen Chaudhary Signed-off-by: Zhenggen Xu Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20210125214430.24079-1-pchaudhary@linkedin.com Signed-off-by: Jakub Kicinski --- include/linux/ipv6.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index dda61d150a13..9d1f29f0c512 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -31,6 +31,7 @@ struct ipv6_devconf { __s32 max_desync_factor; __s32 max_addresses; __s32 accept_ra_defrtr; + __u32 ra_defrtr_metric; __s32 accept_ra_min_hop_limit; __s32 accept_ra_pinfo; __s32 ignore_routes_with_linkdown; -- cgit v1.2.3 From 6fe27d68b45666381691b6a841a2adbda8c8d153 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Wed, 20 Jan 2021 02:03:55 +0900 Subject: can: dev: export can_get_state_str() function The can_get_state_str() function is also relevant to the drivers. Export the symbol and make it visible in the can/dev.h header. Link: https://lore.kernel.org/r/20210119170355.12040-1-mailhol.vincent@wanadoo.fr Signed-off-by: Vincent Mailhol Signed-off-by: Marc Kleine-Budde --- include/linux/can/dev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 7faf6a37d5b2..ac4d83a1ab81 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -123,6 +123,7 @@ void unregister_candev(struct net_device *dev); int can_restart_now(struct net_device *dev); void can_bus_off(struct net_device *dev); +const char *can_get_state_str(const enum can_state state); void can_change_state(struct net_device *dev, struct can_frame *cf, enum can_state tx_state, enum can_state rx_state); -- cgit v1.2.3 From 9cc0aaeb96e7f894d4735f069174948c1516fea7 Mon Sep 17 00:00:00 2001 From: John Garry Date: Wed, 6 Jan 2021 21:35:06 +0800 Subject: iova: Make has_iova_flush_queue() private Function has_iova_flush_queue() has no users outside iova.c, so make it private. Signed-off-by: John Garry Acked-by: Will Deacon Link: https://lore.kernel.org/r/1609940111-28563-2-git-send-email-john.garry@huawei.com Signed-off-by: Joerg Roedel --- include/linux/iova.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iova.h b/include/linux/iova.h index 76e16ae20729..2b76e0be1c5b 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -153,7 +153,6 @@ struct iova *reserve_iova(struct iova_domain *iovad, unsigned long pfn_lo, void copy_reserved_iova(struct iova_domain *from, struct iova_domain *to); void init_iova_domain(struct iova_domain *iovad, unsigned long granule, unsigned long start_pfn); -bool has_iova_flush_queue(struct iova_domain *iovad); int init_iova_flush_queue(struct iova_domain *iovad, iova_flush_cb flush_cb, iova_entry_dtor entry_dtor); struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn); @@ -223,11 +222,6 @@ static inline void init_iova_domain(struct iova_domain *iovad, { } -static inline bool has_iova_flush_queue(struct iova_domain *iovad) -{ - return false; -} - static inline int init_iova_flush_queue(struct iova_domain *iovad, iova_flush_cb flush_cb, iova_entry_dtor entry_dtor) -- cgit v1.2.3 From 87baa23e0236bc1c41ce744f524bf12dbe7fde66 Mon Sep 17 00:00:00 2001 From: Hemant Kumar Date: Mon, 11 Jan 2021 19:07:40 +0100 Subject: bus: mhi: core: Add helper API to return number of free TREs Introduce mhi_get_free_desc_count() API to return number of TREs available to queue buffer. MHI clients can use this API to know before hand if ring is full without calling queue API. Signed-off-by: Hemant Kumar Reviewed-by: Jeffrey Hugo Reviewed-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/1610388462-16322-1-git-send-email-loic.poulain@linaro.org Signed-off-by: Manivannan Sadhasivam --- include/linux/mhi.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 562862ff819c..ece53a252217 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -598,6 +598,15 @@ void mhi_set_mhi_state(struct mhi_controller *mhi_cntrl, */ void mhi_notify(struct mhi_device *mhi_dev, enum mhi_callback cb_reason); +/** + * mhi_get_free_desc_count - Get transfer ring length + * Get # of TD available to queue buffers + * @mhi_dev: Device associated with the channels + * @dir: Direction of the channel + */ +int mhi_get_free_desc_count(struct mhi_device *mhi_dev, + enum dma_data_direction dir); + /** * mhi_prepare_for_power_up - Do pre-initialization before power up. * This is optional, call this before power up if -- cgit v1.2.3 From 622106190175dbac2b0b0ee7d4275c474e5fe051 Mon Sep 17 00:00:00 2001 From: John Garry Date: Wed, 6 Jan 2021 21:35:07 +0800 Subject: iova: Delete copy_reserved_iova() Since commit c588072bba6b ("iommu/vt-d: Convert intel iommu driver to the iommu ops"), function copy_reserved_iova() is not referenced, so delete it. Signed-off-by: John Garry Acked-by: Will Deacon Link: https://lore.kernel.org/r/1609940111-28563-3-git-send-email-john.garry@huawei.com Signed-off-by: Joerg Roedel --- include/linux/iova.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iova.h b/include/linux/iova.h index 2b76e0be1c5b..c834c01c0a5b 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -150,7 +150,6 @@ unsigned long alloc_iova_fast(struct iova_domain *iovad, unsigned long size, unsigned long limit_pfn, bool flush_rcache); struct iova *reserve_iova(struct iova_domain *iovad, unsigned long pfn_lo, unsigned long pfn_hi); -void copy_reserved_iova(struct iova_domain *from, struct iova_domain *to); void init_iova_domain(struct iova_domain *iovad, unsigned long granule, unsigned long start_pfn); int init_iova_flush_queue(struct iova_domain *iovad, @@ -211,11 +210,6 @@ static inline struct iova *reserve_iova(struct iova_domain *iovad, return NULL; } -static inline void copy_reserved_iova(struct iova_domain *from, - struct iova_domain *to) -{ -} - static inline void init_iova_domain(struct iova_domain *iovad, unsigned long granule, unsigned long start_pfn) -- cgit v1.2.3 From ab0a7119ba67be9e377b195d2b9baa9fb8b3b53e Mon Sep 17 00:00:00 2001 From: John Garry Date: Wed, 6 Jan 2021 21:35:10 +0800 Subject: iommu: Delete iommu_domain_window_disable() Function iommu_domain_window_disable() is not referenced in the tree, so delete it. Signed-off-by: John Garry Acked-by: Will Deacon Link: https://lore.kernel.org/r/1609940111-28563-6-git-send-email-john.garry@huawei.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index b3f0e2018c62..72059fcfa108 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -514,7 +514,6 @@ extern int iommu_domain_set_attr(struct iommu_domain *domain, enum iommu_attr, extern int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr, phys_addr_t offset, u64 size, int prot); -extern void iommu_domain_window_disable(struct iommu_domain *domain, u32 wnd_nr); extern int report_iommu_fault(struct iommu_domain *domain, struct device *dev, unsigned long iova, int flags); @@ -746,11 +745,6 @@ static inline int iommu_domain_window_enable(struct iommu_domain *domain, return -ENODEV; } -static inline void iommu_domain_window_disable(struct iommu_domain *domain, - u32 wnd_nr) -{ -} - static inline phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova) { return 0; -- cgit v1.2.3 From 262948f8ba573dc9c61650df8f23eaea7d43bc61 Mon Sep 17 00:00:00 2001 From: John Garry Date: Wed, 6 Jan 2021 21:35:11 +0800 Subject: iommu: Delete iommu_dev_has_feature() Function iommu_dev_has_feature() has never been referenced in the tree, and there does not appear to be anything coming soon to use it, so delete it. Signed-off-by: John Garry Acked-by: Will Deacon Link: https://lore.kernel.org/r/1609940111-28563-7-git-send-email-john.garry@huawei.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 72059fcfa108..91d94c014f47 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -626,7 +626,6 @@ static inline void dev_iommu_priv_set(struct device *dev, void *priv) int iommu_probe_device(struct device *dev); void iommu_release_device(struct device *dev); -bool iommu_dev_has_feature(struct device *dev, enum iommu_dev_features f); int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features f); int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features f); bool iommu_dev_feature_enabled(struct device *dev, enum iommu_dev_features f); @@ -975,12 +974,6 @@ const struct iommu_ops *iommu_ops_from_fwnode(struct fwnode_handle *fwnode) return NULL; } -static inline bool -iommu_dev_has_feature(struct device *dev, enum iommu_dev_features feat) -{ - return false; -} - static inline bool iommu_dev_feature_enabled(struct device *dev, enum iommu_dev_features feat) { -- cgit v1.2.3 From 2ebbd25873cef06f739489fd8ff9f707a3dfa2fa Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Thu, 7 Jan 2021 20:29:04 +0800 Subject: iommu: Add iova and size as parameters in iotlb_sync_map iotlb_sync_map allow IOMMU drivers tlb sync after completing the whole mapping. This patch adds iova and size as the parameters in it. then the IOMMU driver could flush tlb with the whole range once after iova mapping to improve performance. Signed-off-by: Yong Wu Reviewed-by: Robin Murphy Acked-by: Will Deacon Link: https://lore.kernel.org/r/20210107122909.16317-3-yong.wu@mediatek.com Signed-off-by: Will Deacon --- include/linux/iommu.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index b3f0e2018c62..9ce0aa9e236b 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -246,7 +246,8 @@ struct iommu_ops { size_t (*unmap)(struct iommu_domain *domain, unsigned long iova, size_t size, struct iommu_iotlb_gather *iotlb_gather); void (*flush_iotlb_all)(struct iommu_domain *domain); - void (*iotlb_sync_map)(struct iommu_domain *domain); + void (*iotlb_sync_map)(struct iommu_domain *domain, unsigned long iova, + size_t size); void (*iotlb_sync)(struct iommu_domain *domain, struct iommu_iotlb_gather *iotlb_gather); phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, dma_addr_t iova); -- cgit v1.2.3 From 862c3715de8f3e5350489240c951d697f04bd8c9 Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Thu, 7 Jan 2021 20:29:06 +0800 Subject: iommu: Switch gather->end to the inclusive end Currently gather->end is "unsigned long" which may be overflow in arch32 in the corner case: 0xfff00000 + 0x100000(iova + size). Although it doesn't affect the size(end - start), it affects the checking "gather->end < end" This patch changes this "end" to the real end address (end = start + size - 1). Correspondingly, update the length to "end - start + 1". Fixes: a7d20dc19d9e ("iommu: Introduce struct iommu_iotlb_gather for batching TLB flushes") Signed-off-by: Yong Wu Reviewed-by: Robin Murphy Acked-by: Will Deacon Link: https://lore.kernel.org/r/20210107122909.16317-5-yong.wu@mediatek.com Signed-off-by: Will Deacon --- include/linux/iommu.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 9ce0aa9e236b..ae8eddd4621b 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -170,7 +170,7 @@ enum iommu_dev_features { * struct iommu_iotlb_gather - Range information for a pending IOTLB flush * * @start: IOVA representing the start of the range to be flushed - * @end: IOVA representing the end of the range to be flushed (exclusive) + * @end: IOVA representing the end of the range to be flushed (inclusive) * @pgsize: The interval at which to perform the flush * * This structure is intended to be updated by multiple calls to the @@ -539,7 +539,7 @@ static inline void iommu_iotlb_gather_add_page(struct iommu_domain *domain, struct iommu_iotlb_gather *gather, unsigned long iova, size_t size) { - unsigned long start = iova, end = start + size; + unsigned long start = iova, end = start + size - 1; /* * If the new page is disjoint from the current range or is mapped at -- cgit v1.2.3 From 77e0992aee4e980e8c553e512a5dfa3e704cf030 Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Thu, 7 Jan 2021 20:29:07 +0800 Subject: iommu/io-pgtable: Allow io_pgtable_tlb ops optional This patch allows io_pgtable_tlb ops could be null since the IOMMU drivers may use the tlb ops from iommu framework. Signed-off-by: Yong Wu Reviewed-by: Robin Murphy Acked-by: Will Deacon Link: https://lore.kernel.org/r/20210107122909.16317-6-yong.wu@mediatek.com Signed-off-by: Will Deacon --- include/linux/io-pgtable.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index ea727eb1a1a9..2a5686ca2ba3 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -214,14 +214,16 @@ struct io_pgtable_domain_attr { static inline void io_pgtable_tlb_flush_all(struct io_pgtable *iop) { - iop->cfg.tlb->tlb_flush_all(iop->cookie); + if (iop->cfg.tlb && iop->cfg.tlb->tlb_flush_all) + iop->cfg.tlb->tlb_flush_all(iop->cookie); } static inline void io_pgtable_tlb_flush_walk(struct io_pgtable *iop, unsigned long iova, size_t size, size_t granule) { - iop->cfg.tlb->tlb_flush_walk(iova, size, granule, iop->cookie); + if (iop->cfg.tlb && iop->cfg.tlb->tlb_flush_walk) + iop->cfg.tlb->tlb_flush_walk(iova, size, granule, iop->cookie); } static inline void @@ -229,7 +231,7 @@ io_pgtable_tlb_add_page(struct io_pgtable *iop, struct iommu_iotlb_gather * gather, unsigned long iova, size_t granule) { - if (iop->cfg.tlb->tlb_add_page) + if (iop->cfg.tlb && iop->cfg.tlb->tlb_add_page) iop->cfg.tlb->tlb_add_page(gather, iova, granule, iop->cookie); } -- cgit v1.2.3 From 8ba59e9dee31246fc34b4d4bec032093e9c06510 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 22 Jan 2021 13:43:58 +0200 Subject: misc: pti: Remove driver for deprecated platform Intel Moorestown and Medfield are quite old Intel Atom based 32-bit platforms, which were in limited use in some Android phones, tablets and consumer electronics more than eight years ago. There are no bugs or problems ever reported outside from Intel for breaking any of that platforms for years. It seems no real users exists who run more or less fresh kernel on it. The commit 05f4434bc130 ("ASoC: Intel: remove mfld_machine") also in align with this theory. Due to above and to reduce a burden of supporting outdated drivers we remove the support of outdated platforms completely. Cc: Alexander Shishkin Acked-by: Linus Walleij Acked-by: Arnd Bergmann Acked-by: Alexander Shishkin Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20210122114358.39299-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/intel-pti.h | 35 ----------------------------------- 1 file changed, 35 deletions(-) delete mode 100644 include/linux/intel-pti.h (limited to 'include/linux') diff --git a/include/linux/intel-pti.h b/include/linux/intel-pti.h deleted file mode 100644 index fcd841a90f2f..000000000000 --- a/include/linux/intel-pti.h +++ /dev/null @@ -1,35 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) Intel 2011 - * - * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - * - * The PTI (Parallel Trace Interface) driver directs trace data routed from - * various parts in the system out through the Intel Penwell PTI port and - * out of the mobile device for analysis with a debugging tool - * (Lauterbach, Fido). This is part of a solution for the MIPI P1149.7, - * compact JTAG, standard. - * - * This header file will allow other parts of the OS to use the - * interface to write out it's contents for debugging a mobile system. - */ - -#ifndef LINUX_INTEL_PTI_H_ -#define LINUX_INTEL_PTI_H_ - -/* offset for last dword of any PTI message. Part of MIPI P1149.7 */ -#define PTI_LASTDWORD_DTS 0x30 - -/* basic structure used as a write address to the PTI HW */ -struct pti_masterchannel { - u8 master; - u8 channel; -}; - -/* the following functions are defined in misc/pti.c */ -void pti_writedata(struct pti_masterchannel *mc, u8 *buf, int count); -struct pti_masterchannel *pti_request_masterchannel(u8 type, - const char *thread_name); -void pti_release_masterchannel(struct pti_masterchannel *mc); - -#endif /* LINUX_INTEL_PTI_H_ */ -- cgit v1.2.3 From 8544717cdacc2f33f0f53a3b34c5125b37e13ce9 Mon Sep 17 00:00:00 2001 From: Ioana Ciornei Date: Thu, 14 Jan 2021 19:07:48 +0200 Subject: bus: fsl-mc: move fsl_mc_command struct in a uapi header Define "struct fsl_mc_command" as a structure that can cross the user/kernel boundary. Acked-by: Laurentiu Tudor Signed-off-by: Ioana Ciornei Link: https://lore.kernel.org/r/20210114170752.2927915-2-ciorneiioana@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/linux/fsl/mc.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index db244874e834..63b56aba925a 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -13,6 +13,7 @@ #include #include #include +#include #define FSL_MC_VENDOR_FREESCALE 0x1957 @@ -209,8 +210,6 @@ struct fsl_mc_device { #define to_fsl_mc_device(_dev) \ container_of(_dev, struct fsl_mc_device, dev) -#define MC_CMD_NUM_OF_PARAMS 7 - struct mc_cmd_header { u8 src_id; u8 flags_hw; @@ -220,11 +219,6 @@ struct mc_cmd_header { __le16 cmd_id; }; -struct fsl_mc_command { - __le64 header; - __le64 params[MC_CMD_NUM_OF_PARAMS]; -}; - enum mc_cmd_status { MC_CMD_STATUS_OK = 0x0, /* Completed successfully */ MC_CMD_STATUS_READY = 0x1, /* Ready to be processed */ -- cgit v1.2.3 From 1423de718e6a0ce00372ab119fa40060ff50883e Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 2 Jun 2020 15:56:55 -0500 Subject: PCI/ACPI: Make acpi_pci_osc_control_set() static acpi_pci_osc_control_set() is only called from pci_root.c, so stop exporting it and make it static. Signed-off-by: Bjorn Helgaas Acked-by: Rafael J. Wysocki --- include/linux/acpi.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 053bf05fb1f7..4703daafcce9 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -581,9 +581,6 @@ extern bool osc_pc_lpi_support_confirmed; #define ACPI_GSB_ACCESS_ATTRIB_RAW_BYTES 0x0000000E #define ACPI_GSB_ACCESS_ATTRIB_RAW_PROCESS 0x0000000F -extern acpi_status acpi_pci_osc_control_set(acpi_handle handle, - u32 *mask, u32 req); - /* Enable _OST when all relevant hotplug operations are enabled */ #if defined(CONFIG_ACPI_HOTPLUG_CPU) && \ defined(CONFIG_ACPI_HOTPLUG_MEMORY) && \ -- cgit v1.2.3 From 620a6dc40754dc218f5b6389b5d335e9a107fd29 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Fri, 22 Jan 2021 12:39:43 +0000 Subject: sched/topology: Make sched_init_numa() use a set for the deduplicating sort MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The deduplicating sort in sched_init_numa() assumes that the first line in the distance table contains all unique values in the entire table. I've been trying to pen what this exactly means for the topology, but it's not straightforward. For instance, topology.c uses this example: node 0 1 2 3 0: 10 20 20 30 1: 20 10 20 20 2: 20 20 10 20 3: 30 20 20 10 0 ----- 1 | / | | / | | / | 2 ----- 3 Which works out just fine. However, if we swap nodes 0 and 1: 1 ----- 0 | / | | / | | / | 2 ----- 3 we get this distance table: node 0 1 2 3 0: 10 20 20 20 1: 20 10 20 30 2: 20 20 10 20 3: 20 30 20 10 Which breaks the deduplicating sort (non-representative first line). In this case this would just be a renumbering exercise, but it so happens that we can have a deduplicating sort that goes through the whole table in O(n²) at the extra cost of a temporary memory allocation (i.e. any form of set). The ACPI spec (SLIT) mentions distances are encoded on 8 bits. Following this, implement the set as a 256-bits bitmap. Should this not be satisfactory (i.e. we want to support 32-bit values), then we'll have to go for some other sparse set implementation. This has the added benefit of letting us allocate just the right amount of memory for sched_domains_numa_distance[], rather than an arbitrary (nr_node_ids + 1). Note: DT binding equivalent (distance-map) decodes distances as 32-bit values. Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20210122123943.1217-2-valentin.schneider@arm.com --- include/linux/topology.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/topology.h b/include/linux/topology.h index ad03df1cc266..7634cd737061 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -48,6 +48,7 @@ int arch_update_cpu_topology(void); /* Conform to ACPI 2.0 SLIT distance definitions */ #define LOCAL_DISTANCE 10 #define REMOTE_DISTANCE 20 +#define DISTANCE_BITS 8 #ifndef node_distance #define node_distance(from,to) ((from) == (to) ? LOCAL_DISTANCE : REMOTE_DISTANCE) #endif -- cgit v1.2.3 From 1875dc5b8ff4690547c446ef222083e28e2d9463 Mon Sep 17 00:00:00 2001 From: Peter Oskolkov Date: Tue, 26 Jan 2021 11:34:49 -0800 Subject: sched: Correctly sort struct predeclarations The comment says: /* task_struct member predeclarations (sorted alphabetically): */ So move io_uring_task where it belongs (alphabetically). Signed-off-by: Peter Oskolkov Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20210126193449.487547-1-posk@google.com --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 31169e70476a..e1152227bb79 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -47,6 +47,7 @@ struct cfs_rq; struct fs_struct; struct futex_pi_state; struct io_context; +struct io_uring_task; struct mempolicy; struct nameidata; struct nsproxy; @@ -65,7 +66,6 @@ struct sighand_struct; struct signal_struct; struct task_delay_info; struct task_group; -struct io_uring_task; /* * Task state bitmask. NOTE! These bits are also -- cgit v1.2.3 From 3175199ab0ac8c874ec25c6bf169f74888917435 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 26 Jan 2021 15:52:34 +0100 Subject: block: split bio_kmalloc from bio_alloc_bioset bio_kmalloc shares almost no logic with the bio_set based fast path in bio_alloc_bioset. Split it into an entirely separate implementation. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Reviewed-by: Chaitanya Kulkarni Acked-by: Damien Le Moal Signed-off-by: Jens Axboe --- include/linux/bio.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 676870b2c88d..c74857cf1252 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -408,6 +408,7 @@ extern int biovec_init_pool(mempool_t *pool, int pool_entries); extern int bioset_init_from_src(struct bio_set *bs, struct bio_set *src); extern struct bio *bio_alloc_bioset(gfp_t, unsigned int, struct bio_set *); +struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned int nr_iovecs); extern void bio_put(struct bio *); extern void __bio_clone_fast(struct bio *, struct bio *); @@ -420,11 +421,6 @@ static inline struct bio *bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs) return bio_alloc_bioset(gfp_mask, nr_iovecs, &fs_bio_set); } -static inline struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned int nr_iovecs) -{ - return bio_alloc_bioset(gfp_mask, nr_iovecs, NULL); -} - extern blk_qc_t submit_bio(struct bio *); extern void bio_endio(struct bio *); -- cgit v1.2.3 From c6bf3f0e25f4c0f0ecce6cf8d1c589bd9d74d3cf Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 26 Jan 2021 15:52:35 +0100 Subject: block: use an on-stack bio in blkdev_issue_flush There is no point in allocating memory for a synchronous flush. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Reviewed-by: Chaitanya Kulkarni Acked-by: Damien Le Moal Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 2491e17b61c4..0dea268bd61b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1288,7 +1288,7 @@ static inline bool blk_needs_flush_plug(struct task_struct *tsk) !list_empty(&plug->cb_list)); } -int blkdev_issue_flush(struct block_device *, gfp_t); +int blkdev_issue_flush(struct block_device *bdev); long nr_blockdev_pages(void); #else /* CONFIG_BLOCK */ struct blk_plug { @@ -1316,7 +1316,7 @@ static inline bool blk_needs_flush_plug(struct task_struct *tsk) return false; } -static inline int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask) +static inline int blkdev_issue_flush(struct block_device *bdev) { return 0; } -- cgit v1.2.3 From 48d15436fde6feebcded7bd0fdc8ea4a9181b8fa Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 26 Jan 2021 15:52:47 +0100 Subject: mm: remove get_swap_bio Just reuse the block_device and sector from the swap_info structure, just as used by the SWP_SYNCHRONOUS path. Also remove the checks for NULL returns from bio_alloc as that can't happen for sleeping allocations. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Reviewed-by: Chaitanya Kulkarni Acked-by: Damien Le Moal Signed-off-by: Jens Axboe --- include/linux/swap.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 596bc2f4d9b0..3f1f7ae0fbe9 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -468,7 +468,6 @@ extern int free_swap_and_cache(swp_entry_t); int swap_type_of(dev_t device, sector_t offset); int find_first_swap(dev_t *device); extern unsigned int count_swap_pages(int, int); -extern sector_t map_swap_page(struct page *, struct block_device **); extern sector_t swapdev_block(int, pgoff_t); extern int page_swapcount(struct page *); extern int __swap_count(swp_entry_t entry); -- cgit v1.2.3 From 84f9017c37c479c4f70456a645d24d2296ad2208 Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Mon, 25 Jan 2021 12:59:57 +0100 Subject: ACPI: platform-profile: Introduce object pointers to callbacks Add an object pointer to handler callbacks to avoid the need for drivers to have a global variable to get to their driver-data struct. Link: https://lore.kernel.org/linux-acpi/6a29f338-d9e4-150c-81dd-2ffb54f5bc35@redhat.com/ Link: https://lore.kernel.org/r/20210114073429.176462-3-jiaxun.yang@flygoat.com Signed-off-by: Jiaxun Yang Suggested-by: Hans de Goede Signed-off-by: Hans de Goede Signed-off-by: Rafael J. Wysocki --- include/linux/platform_profile.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_profile.h b/include/linux/platform_profile.h index c797fdb3d91a..a26542d53058 100644 --- a/include/linux/platform_profile.h +++ b/include/linux/platform_profile.h @@ -28,8 +28,10 @@ enum platform_profile_option { struct platform_profile_handler { unsigned long choices[BITS_TO_LONGS(PLATFORM_PROFILE_LAST)]; - int (*profile_get)(enum platform_profile_option *profile); - int (*profile_set)(enum platform_profile_option profile); + int (*profile_get)(struct platform_profile_handler *pprof, + enum platform_profile_option *profile); + int (*profile_set)(struct platform_profile_handler *pprof, + enum platform_profile_option profile); }; int platform_profile_register(struct platform_profile_handler *pprof); -- cgit v1.2.3 From 0bfa0820c274b019583b3454c6c889c99c24558d Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Mon, 25 Jan 2021 14:29:18 -0500 Subject: PM: clk: make PM clock layer compatible with clocks that must sleep The clock API splits its interface into sleepable ant atomic contexts: - clk_prepare/clk_unprepare for stuff that might sleep - clk_enable_clk_disable for anything that may be done in atomic context The code handling runtime PM for clocks only calls clk_disable() on suspend requests, and clk_enable on resume requests. This means that runtime PM with clock providers that only have the prepare/unprepare methods implemented is basically useless. Many clock implementations can't accommodate atomic contexts. This is often the case when communication with the clock happens through another subsystem like I2C or SCMI. Let's make the clock PM code useful with such clocks by safely invoking clk_prepare/clk_unprepare upon resume/suspend requests. Of course, when such clocks are registered with the PM layer then pm_runtime_irq_safe() can't be used, and neither pm_runtime_suspend() nor pm_runtime_resume() may be invoked in atomic context. For clocks that do implement the enable and disable methods then everything just works as before. A note on sparse: According to https://lwn.net/Articles/109066/ there are things that sparse can't cope with. In particular, pm_clk_op_lock() and pm_clk_op_unlock() may or may not lock/unlock psd->lock depending on some runtime condition. To work around that we tell it the lock is always untaken for the purpose of static analisys. Thanks to Naresh Kamboju for reporting issues with the initial patch. Signed-off-by: Nicolas Pitre Tested-by: Naresh Kamboju Signed-off-by: Rafael J. Wysocki --- include/linux/clk.h | 24 +++++++++++++++++++++++- include/linux/pm.h | 2 ++ 2 files changed, 25 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/clk.h b/include/linux/clk.h index 31ff1bf1b79f..a4a86aa8b11a 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -238,6 +238,7 @@ static inline bool clk_is_match(const struct clk *p, const struct clk *q) #endif +#ifdef CONFIG_HAVE_CLK_PREPARE /** * clk_prepare - prepare a clock source * @clk: clock source @@ -246,10 +247,26 @@ static inline bool clk_is_match(const struct clk *p, const struct clk *q) * * Must not be called from within atomic context. */ -#ifdef CONFIG_HAVE_CLK_PREPARE int clk_prepare(struct clk *clk); int __must_check clk_bulk_prepare(int num_clks, const struct clk_bulk_data *clks); + +/** + * clk_is_enabled_when_prepared - indicate if preparing a clock also enables it. + * @clk: clock source + * + * Returns true if clk_prepare() implicitly enables the clock, effectively + * making clk_enable()/clk_disable() no-ops, false otherwise. + * + * This is of interest mainly to the power management code where actually + * disabling the clock also requires unpreparing it to have any material + * effect. + * + * Regardless of the value returned here, the caller must always invoke + * clk_enable() or clk_prepare_enable() and counterparts for usage counts + * to be right. + */ +bool clk_is_enabled_when_prepared(struct clk *clk); #else static inline int clk_prepare(struct clk *clk) { @@ -263,6 +280,11 @@ clk_bulk_prepare(int num_clks, const struct clk_bulk_data *clks) might_sleep(); return 0; } + +static inline bool clk_is_enabled_when_prepared(struct clk *clk) +{ + return false; +} #endif /** diff --git a/include/linux/pm.h b/include/linux/pm.h index 47aca6bac1d6..482313a8ccfc 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -537,6 +537,8 @@ struct pm_subsys_data { spinlock_t lock; unsigned int refcount; #ifdef CONFIG_PM_CLK + unsigned int clock_op_might_sleep; + struct mutex clock_mutex; struct list_head clock_list; #endif #ifdef CONFIG_PM_GENERIC_DOMAINS -- cgit v1.2.3 From 3fde13f817e23f05ce407d136325df4cbc913e67 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Fri, 22 Jan 2021 17:46:43 +0800 Subject: f2fs: compress: support compress level Expand 'compress_algorithm' mount option to accept parameter as format of :, by this way, it gives a way to allow user to do more specified config on lz4 and zstd compression level, then f2fs compression can provide higher compress ratio. In order to set compress level for lz4 algorithm, it needs to set CONFIG_LZ4HC_COMPRESS and CONFIG_F2FS_FS_LZ4HC config to enable lz4hc compress algorithm. CR and performance number on lz4/lz4hc algorithm: dd if=enwik9 of=compressed_file conv=fsync Original blocks: 244382 lz4 lz4hc-9 compressed blocks 170647 163270 compress ratio 69.8% 66.8% speed 16.4207 s, 60.9 MB/s 26.7299 s, 37.4 MB/s compress ratio = after / before Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 7dc2a06cf19a..c6cc0a566ef5 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -274,6 +274,9 @@ struct f2fs_inode { __u8 i_compress_algorithm; /* compress algorithm */ __u8 i_log_cluster_size; /* log of cluster size */ __le16 i_compress_flag; /* compress flag */ + /* 0 bit: chksum flag + * [10,15] bits: compress level + */ __le32 i_extra_end[0]; /* for attribute size calculation */ } __packed; __le32 i_addr[DEF_ADDRS_PER_INODE]; /* Pointers to data blocks */ -- cgit v1.2.3 From 794c43f716845e2d48ce195ed5c4179a4e05ce5f Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 28 Dec 2020 15:25:29 -0800 Subject: libfs: unexport generic_ci_d_compare() and generic_ci_d_hash() Now that generic_set_encrypted_ci_d_ops() has been added and ext4 and f2fs are using it, it's no longer necessary to export generic_ci_d_compare() and generic_ci_d_hash() to filesystems. Reviewed-by: Gabriel Krisman Bertazi Signed-off-by: Eric Biggers Signed-off-by: Jaegeuk Kim --- include/linux/fs.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index fd47deea7c17..6d8b1e7337e4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3192,11 +3192,6 @@ extern int generic_file_fsync(struct file *, loff_t, loff_t, int); extern int generic_check_addressable(unsigned, u64); -#ifdef CONFIG_UNICODE -extern int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str); -extern int generic_ci_d_compare(const struct dentry *dentry, unsigned int len, - const char *str, const struct qstr *name); -#endif extern void generic_set_encrypted_ci_d_ops(struct dentry *dentry); #ifdef CONFIG_MIGRATION -- cgit v1.2.3 From 8063e184e49011f6f3f34f6c358dc8a83890bb5b Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Wed, 27 Jan 2021 14:15:01 -0800 Subject: skmsg: Make sk_psock_destroy() static sk_psock_destroy() is a RCU callback, I can't see any reason why it could be used outside. Signed-off-by: Cong Wang Signed-off-by: Daniel Borkmann Cc: John Fastabend Cc: Jakub Sitnicki Cc: Lorenz Bauer Link: https://lore.kernel.org/bpf/20210127221501.46866-1-xiyou.wangcong@gmail.com --- include/linux/skmsg.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index fec0c5ac1c4f..8edbbf5f2f93 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -390,7 +390,6 @@ static inline struct sk_psock *sk_psock_get(struct sock *sk) } void sk_psock_stop(struct sock *sk, struct sk_psock *psock); -void sk_psock_destroy(struct rcu_head *rcu); void sk_psock_drop(struct sock *sk, struct sk_psock *psock); static inline void sk_psock_put(struct sock *sk, struct sk_psock *psock) -- cgit v1.2.3 From e5befc024cb4515d815662ed8746712cc5366bfc Mon Sep 17 00:00:00 2001 From: Eddie James Date: Tue, 22 Dec 2020 09:26:39 -0600 Subject: hwmon: (pmbus) Add a PMBUS_NO_CAPABILITY platform data flag Some PMBus chips don't respond with valid data when reading the CAPABILITY register. Add a flag that device drivers can set so that the PMBus core driver doesn't use CAPABILITY to determine it's behavior. Signed-off-by: Eddie James Link: https://lore.kernel.org/r/20201222152640.27749-2-eajames@linux.ibm.com Signed-off-by: Guenter Roeck --- include/linux/pmbus.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pmbus.h b/include/linux/pmbus.h index 1ea5bae708a1..12cbbf305969 100644 --- a/include/linux/pmbus.h +++ b/include/linux/pmbus.h @@ -34,6 +34,15 @@ */ #define PMBUS_WRITE_PROTECTED BIT(1) +/* + * PMBUS_NO_CAPABILITY + * + * Some PMBus chips don't respond with valid data when reading the CAPABILITY + * register. For such chips, this flag should be set so that the PMBus core + * driver doesn't use CAPABILITY to determine it's behavior. + */ +#define PMBUS_NO_CAPABILITY BIT(2) + struct pmbus_platform_data { u32 flags; /* Device specific flags */ -- cgit v1.2.3 From 772412176fb98493158929b220fe250127f611af Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Wed, 27 Jan 2021 11:31:39 -0800 Subject: bpf: Allow rewriting to ports under ip_unprivileged_port_start At the moment, BPF_CGROUP_INET{4,6}_BIND hooks can rewrite user_port to the privileged ones (< ip_unprivileged_port_start), but it will be rejected later on in the __inet_bind or __inet6_bind. Let's add another return value to indicate that CAP_NET_BIND_SERVICE check should be ignored. Use the same idea as we currently use in cgroup/egress where bit #1 indicates CN. Instead, for cgroup/bind{4,6}, bit #1 indicates that CAP_NET_BIND_SERVICE should be bypassed. v5: - rename flags to be less confusing (Andrey Ignatov) - rework BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY to work on flags and accept BPF_RET_SET_CN (no behavioral changes) v4: - Add missing IPv6 support (Martin KaFai Lau) v3: - Update description (Martin KaFai Lau) - Fix capability restore in selftest (Martin KaFai Lau) v2: - Switch to explicit return code (Martin KaFai Lau) Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov Reviewed-by: Martin KaFai Lau Acked-by: Andrey Ignatov Link: https://lore.kernel.org/bpf/20210127193140.3170382-1-sdf@google.com --- include/linux/bpf-cgroup.h | 38 ++++++++++++++++++++++++--------- include/linux/bpf.h | 52 +++++++++++++++++++++++++++++----------------- 2 files changed, 61 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 0748fd87969e..c42e02b4d84b 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -125,7 +125,8 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk, int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, struct sockaddr *uaddr, enum bpf_attach_type type, - void *t_ctx); + void *t_ctx, + u32 *flags); int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, struct bpf_sock_ops_kern *sock_ops, @@ -231,30 +232,48 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, #define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, type) \ ({ \ + u32 __unused_flags; \ int __ret = 0; \ if (cgroup_bpf_enabled(type)) \ __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \ - NULL); \ + NULL, \ + &__unused_flags); \ __ret; \ }) #define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, type, t_ctx) \ ({ \ + u32 __unused_flags; \ int __ret = 0; \ if (cgroup_bpf_enabled(type)) { \ lock_sock(sk); \ __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \ - t_ctx); \ + t_ctx, \ + &__unused_flags); \ release_sock(sk); \ } \ __ret; \ }) -#define BPF_CGROUP_RUN_PROG_INET4_BIND_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET4_BIND, NULL) - -#define BPF_CGROUP_RUN_PROG_INET6_BIND_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET6_BIND, NULL) +/* BPF_CGROUP_INET4_BIND and BPF_CGROUP_INET6_BIND can return extra flags + * via upper bits of return code. The only flag that is supported + * (at bit position 0) is to indicate CAP_NET_BIND_SERVICE capability check + * should be bypassed (BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE). + */ +#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, type, bind_flags) \ +({ \ + u32 __flags = 0; \ + int __ret = 0; \ + if (cgroup_bpf_enabled(type)) { \ + lock_sock(sk); \ + __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \ + NULL, &__flags); \ + release_sock(sk); \ + if (__flags & BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE) \ + *bind_flags |= BIND_NO_CAP_NET_BIND_SERVICE; \ + } \ + __ret; \ +}) #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) \ ((cgroup_bpf_enabled(BPF_CGROUP_INET4_CONNECT) || \ @@ -453,8 +472,7 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_INET4_BIND_LOCK(sk, uaddr) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_INET6_BIND_LOCK(sk, uaddr) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, type, flags) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr) ({ 0; }) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1aac2af12fed..321966fc35db 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1073,6 +1073,34 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array, struct bpf_prog *include_prog, struct bpf_prog_array **new_array); +/* BPF program asks to bypass CAP_NET_BIND_SERVICE in bind. */ +#define BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE (1 << 0) +/* BPF program asks to set CN on the packet. */ +#define BPF_RET_SET_CN (1 << 0) + +#define BPF_PROG_RUN_ARRAY_FLAGS(array, ctx, func, ret_flags) \ + ({ \ + struct bpf_prog_array_item *_item; \ + struct bpf_prog *_prog; \ + struct bpf_prog_array *_array; \ + u32 _ret = 1; \ + u32 func_ret; \ + migrate_disable(); \ + rcu_read_lock(); \ + _array = rcu_dereference(array); \ + _item = &_array->items[0]; \ + while ((_prog = READ_ONCE(_item->prog))) { \ + bpf_cgroup_storage_set(_item->cgroup_storage); \ + func_ret = func(_prog, ctx); \ + _ret &= (func_ret & 1); \ + *(ret_flags) |= (func_ret >> 1); \ + _item++; \ + } \ + rcu_read_unlock(); \ + migrate_enable(); \ + _ret; \ + }) + #define __BPF_PROG_RUN_ARRAY(array, ctx, func, check_non_null) \ ({ \ struct bpf_prog_array_item *_item; \ @@ -1120,25 +1148,11 @@ _out: \ */ #define BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY(array, ctx, func) \ ({ \ - struct bpf_prog_array_item *_item; \ - struct bpf_prog *_prog; \ - struct bpf_prog_array *_array; \ - u32 ret; \ - u32 _ret = 1; \ - u32 _cn = 0; \ - migrate_disable(); \ - rcu_read_lock(); \ - _array = rcu_dereference(array); \ - _item = &_array->items[0]; \ - while ((_prog = READ_ONCE(_item->prog))) { \ - bpf_cgroup_storage_set(_item->cgroup_storage); \ - ret = func(_prog, ctx); \ - _ret &= (ret & 1); \ - _cn |= (ret & 2); \ - _item++; \ - } \ - rcu_read_unlock(); \ - migrate_enable(); \ + u32 _flags = 0; \ + bool _cn; \ + u32 _ret; \ + _ret = BPF_PROG_RUN_ARRAY_FLAGS(array, ctx, func, &_flags); \ + _cn = _flags & BPF_RET_SET_CN; \ if (_ret) \ _ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS); \ else \ -- cgit v1.2.3 From 3d347b1b19da20f973d1d3c6bb60c11185606afd Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Tue, 26 Jan 2021 15:24:07 -0800 Subject: net/mlx5: Add support for devlink traps in mlx5 core driver Add devlink traps infra-structure to mlx5 core driver. Add traps list to mlx5_priv and corresponding API: - mlx5_devlink_trap_report() to wrap trap reports to devlink - mlx5_devlink_trap_get_num_active() to decide whether to open/close trap resources. Signed-off-by: Aya Levin Reviewed-by: Tariq Toukan Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed Signed-off-by: Jakub Kicinski --- include/linux/mlx5/driver.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f93bfe7473aa..c4615dc51b6f 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -564,6 +564,7 @@ struct mlx5_priv { int host_pf_pages; struct mlx5_core_health health; + struct list_head traps; /* start: qp staff */ struct dentry *qp_debugfs; -- cgit v1.2.3 From 241dc159391fb9d351362d911a39dff84074cc92 Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Tue, 26 Jan 2021 15:24:11 -0800 Subject: net/mlx5: Notify on trap action by blocking event In order to allow mlx5 core driver to trigger synchronous operations to its consumers, add a blocking events handler. Add wrappers to blocking_notifier_[call_chain/chain_register/chain_unregister]. Add trap callback for action set and notify about this change. Following patches in the set add a listener for this event. Signed-off-by: Aya Levin Reviewed-by: Tariq Toukan Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed Signed-off-by: Jakub Kicinski --- include/linux/mlx5/device.h | 4 ++++ include/linux/mlx5/driver.h | 15 +++++++++++++++ 2 files changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index f1de49d64a98..77ba54d38772 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -359,6 +359,10 @@ enum mlx5_event { MLX5_EVENT_TYPE_MAX = 0x100, }; +enum mlx5_driver_event { + MLX5_DRIVER_EVENT_TYPE_TRAP = 0, +}; + enum { MLX5_TRACER_SUBTYPE_OWNERSHIP_CHANGE = 0x0, MLX5_TRACER_SUBTYPE_TRACES_AVAILABLE = 0x1, diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index c4615dc51b6f..45df5b465ba8 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1073,11 +1073,26 @@ enum { MAX_MR_CACHE_ENTRIES }; +/* Async-atomic event notifier used by mlx5 core to forward FW + * evetns recived from event queue to mlx5 consumers. + * Optimise event queue dipatching. + */ int mlx5_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb); int mlx5_notifier_unregister(struct mlx5_core_dev *dev, struct notifier_block *nb); + +/* Async-atomic event notifier used for forwarding + * evetns from the event queue into the to mlx5 events dispatcher, + * eswitch, clock and others. + */ int mlx5_eq_notifier_register(struct mlx5_core_dev *dev, struct mlx5_nb *nb); int mlx5_eq_notifier_unregister(struct mlx5_core_dev *dev, struct mlx5_nb *nb); +/* Blocking event notifier used to forward SW events, used for slow path */ +int mlx5_blocking_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb); +int mlx5_blocking_notifier_unregister(struct mlx5_core_dev *dev, struct notifier_block *nb); +int mlx5_blocking_notifier_call_chain(struct mlx5_core_dev *dev, unsigned int event, + void *data); + int mlx5_core_query_vendor_id(struct mlx5_core_dev *mdev, u32 *vendor_id); int mlx5_cmd_create_vport_lag(struct mlx5_core_dev *dev); -- cgit v1.2.3 From 5543e989fe5e2fe6a5829ee42c00152cac2bb8a0 Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Tue, 26 Jan 2021 15:24:16 -0800 Subject: net/mlx5e: Add trap entity to ETH driver Introduce mlx5e_trap which includes a dedicated RQ and NAPI for trapped packets. Trap-RQ processes packets that were destined to be dropped, but for debug and visibility sake these packets are trapped and reported to devlink. Trap-RQ connects between the HW and the driver and is not a part of a channel. Open mlx5e_create_rq() and mlx5_core_destroy_rq() as API and add dedicate RQ handlers which report to devlink of trapped packets. Signed-off-by: Aya Levin Reviewed-by: Tariq Toukan Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed Signed-off-by: Jakub Kicinski --- include/linux/mlx5/device.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 77ba54d38772..00057eae89ab 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -903,6 +903,11 @@ static inline u64 get_cqe_ts(struct mlx5_cqe64 *cqe) return (u64)lo | ((u64)hi << 32); } +static inline u16 get_cqe_flow_tag(struct mlx5_cqe64 *cqe) +{ + return be32_to_cpu(cqe->sop_drop_qpn) & 0xFFF; +} + #define MLX5_MPWQE_LOG_NUM_STRIDES_BASE (9) #define MLX5_MPWQE_LOG_STRIDE_SZ_BASE (6) -- cgit v1.2.3 From a8ce9ebbecdfda3322bbcece6b3b25888217f8e3 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Fri, 15 Jan 2021 08:42:02 +0800 Subject: iommu/vt-d: Preset Access/Dirty bits for IOVA over FL The Access/Dirty bits in the first level page table entry will be set whenever a page table entry was used for address translation or write permission was successfully translated. This is always true when using the first-level page table for kernel IOVA. Instead of wasting hardware cycles to update the certain bits, it's better to set them up at the beginning. Suggested-by: Ashok Raj Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20210115004202.953965-1-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 09c6a0bf3892..ecb35fdff03e 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -42,6 +42,8 @@ #define DMA_FL_PTE_PRESENT BIT_ULL(0) #define DMA_FL_PTE_US BIT_ULL(2) +#define DMA_FL_PTE_ACCESS BIT_ULL(5) +#define DMA_FL_PTE_DIRTY BIT_ULL(6) #define DMA_FL_PTE_XD BIT_ULL(63) #define ADDR_WIDTH_5LEVEL (57) -- cgit v1.2.3 From 1ce53e2c2ac069e7b3c400a427002a70deb4a916 Mon Sep 17 00:00:00 2001 From: Alejandro Colomar Date: Sat, 28 Nov 2020 13:39:46 +0100 Subject: futex: Change utime parameter to be 'const ... *' futex(2) says that 'utime' is a pointer to 'const'. The implementation doesn't use 'const'; however, it _never_ modifies the contents of utime. - futex() either uses 'utime' as a pointer to struct or as a 'u32'. - In case it's used as a 'u32', it makes a copy of it, and of course it is not dereferenced. - In case it's used as a 'struct __kernel_timespec __user *', the pointer is not dereferenced inside the futex() definition, and it is only passed to a function: get_timespec64(), which accepts a 'const struct __kernel_timespec __user *'. [ tglx: Make the same change to the compat syscall and fixup the prototypes. ] Signed-off-by: Alejandro Colomar Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20201128123945.4592-1-alx.manpages@gmail.com --- include/linux/syscalls.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index f3929aff39cf..5cb74edd9a4f 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -583,11 +583,11 @@ asmlinkage long sys_unshare(unsigned long unshare_flags); /* kernel/futex.c */ asmlinkage long sys_futex(u32 __user *uaddr, int op, u32 val, - struct __kernel_timespec __user *utime, u32 __user *uaddr2, - u32 val3); + const struct __kernel_timespec __user *utime, + u32 __user *uaddr2, u32 val3); asmlinkage long sys_futex_time32(u32 __user *uaddr, int op, u32 val, - struct old_timespec32 __user *utime, u32 __user *uaddr2, - u32 val3); + const struct old_timespec32 __user *utime, + u32 __user *uaddr2, u32 val3); asmlinkage long sys_get_robust_list(int pid, struct robust_list_head __user * __user *head_ptr, size_t __user *len_ptr); -- cgit v1.2.3 From 3ab657291638ea267654c3e4798161b2cee6ae01 Mon Sep 17 00:00:00 2001 From: Lianbo Jiang Date: Tue, 26 Jan 2021 19:53:37 +0800 Subject: iommu: use the __iommu_attach_device() directly for deferred attach Currently, because domain attach allows to be deferred from iommu driver to device driver, and when iommu initializes, the devices on the bus will be scanned and the default groups will be allocated. Due to the above changes, some devices could be added to the same group as below: [ 3.859417] pci 0000:01:00.0: Adding to iommu group 16 [ 3.864572] pci 0000:01:00.1: Adding to iommu group 16 [ 3.869738] pci 0000:02:00.0: Adding to iommu group 17 [ 3.874892] pci 0000:02:00.1: Adding to iommu group 17 But when attaching these devices, it doesn't allow that a group has more than one device, otherwise it will return an error. This conflicts with the deferred attaching. Unfortunately, it has two devices in the same group for my side, for example: [ 9.627014] iommu_group_device_count(): device name[0]:0000:01:00.0 [ 9.633545] iommu_group_device_count(): device name[1]:0000:01:00.1 ... [ 10.255609] iommu_group_device_count(): device name[0]:0000:02:00.0 [ 10.262144] iommu_group_device_count(): device name[1]:0000:02:00.1 Finally, which caused the failure of tg3 driver when tg3 driver calls the dma_alloc_coherent() to allocate coherent memory in the tg3_test_dma(). [ 9.660310] tg3 0000:01:00.0: DMA engine test failed, aborting [ 9.754085] tg3: probe of 0000:01:00.0 failed with error -12 [ 9.997512] tg3 0000:01:00.1: DMA engine test failed, aborting [ 10.043053] tg3: probe of 0000:01:00.1 failed with error -12 [ 10.288905] tg3 0000:02:00.0: DMA engine test failed, aborting [ 10.334070] tg3: probe of 0000:02:00.0 failed with error -12 [ 10.578303] tg3 0000:02:00.1: DMA engine test failed, aborting [ 10.622629] tg3: probe of 0000:02:00.1 failed with error -12 In addition, the similar situations also occur in other drivers such as the bnxt_en driver. That can be reproduced easily in kdump kernel when SME is active. Let's move the handling currently in iommu_dma_deferred_attach() into the iommu core code so that it can call the __iommu_attach_device() directly instead of the iommu_attach_device(). The external interface iommu_attach_device() is not suitable for handling this situation. Signed-off-by: Lianbo Jiang Reviewed-by: Robin Murphy Link: https://lore.kernel.org/r/20210126115337.20068-3-lijiang@redhat.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 91d94c014f47..524ffc2ff64f 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -376,6 +376,7 @@ int iommu_device_sysfs_add(struct iommu_device *iommu, void iommu_device_sysfs_remove(struct iommu_device *iommu); int iommu_device_link(struct iommu_device *iommu, struct device *link); void iommu_device_unlink(struct iommu_device *iommu, struct device *link); +int iommu_deferred_attach(struct device *dev, struct iommu_domain *domain); static inline void __iommu_device_set_ops(struct iommu_device *iommu, const struct iommu_ops *ops) -- cgit v1.2.3 From c9b258c6be09283663c6851725b322568d867c0b Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Tue, 15 Dec 2020 01:36:54 -0600 Subject: iommu/amd: Prepare for generic IO page table framework Add initial hook up code to implement generic IO page table framework. Signed-off-by: Suravee Suthikulpanit Link: https://lore.kernel.org/r/20201215073705.123786-3-suravee.suthikulpanit@amd.com Signed-off-by: Joerg Roedel --- include/linux/io-pgtable.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index ea727eb1a1a9..f58c14218ee1 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -15,6 +15,7 @@ enum io_pgtable_fmt { ARM_64_LPAE_S2, ARM_V7S, ARM_MALI_LPAE, + AMD_IOMMU_V1, IO_PGTABLE_NUM_FMTS, }; @@ -251,5 +252,6 @@ extern struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s1_init_fns; extern struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s2_init_fns; extern struct io_pgtable_init_fns io_pgtable_arm_v7s_init_fns; extern struct io_pgtable_init_fns io_pgtable_arm_mali_lpae_init_fns; +extern struct io_pgtable_init_fns io_pgtable_amd_iommu_v1_init_fns; #endif /* __IO_PGTABLE_H */ -- cgit v1.2.3 From 3d5eab41451f8e28f3e45eef8f6b372bf56612fb Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Wed, 27 Jan 2021 16:29:29 +0000 Subject: iommu/io-pgtable: Remove TLBI_ON_MAP quirk IO_PGTABLE_QUIRK_TLBI_ON_MAP is now fully superseded by the core API's iotlb_sync_map callback. Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/5abb80bba3a7c371d5ffb7e59c05586deddb9a91.1611764372.git.robin.murphy@arm.com [will: Remove unused 'iop' local variable from arm_v7s_map()] Signed-off-by: Will Deacon --- include/linux/io-pgtable.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index 2a5686ca2ba3..06753323a15e 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -68,10 +68,6 @@ struct io_pgtable_cfg { * hardware which does not implement the permissions of a given * format, and/or requires some format-specific default value. * - * IO_PGTABLE_QUIRK_TLBI_ON_MAP: If the format forbids caching invalid - * (unmapped) entries but the hardware might do so anyway, perform - * TLB maintenance when mapping as well as when unmapping. - * * IO_PGTABLE_QUIRK_ARM_MTK_EXT: (ARM v7s format) MediaTek IOMMUs extend * to support up to 34 bits PA where the bit32 and bit33 are * encoded in the bit9 and bit4 of the PTE respectively. @@ -88,7 +84,6 @@ struct io_pgtable_cfg { */ #define IO_PGTABLE_QUIRK_ARM_NS BIT(0) #define IO_PGTABLE_QUIRK_NO_PERMS BIT(1) - #define IO_PGTABLE_QUIRK_TLBI_ON_MAP BIT(2) #define IO_PGTABLE_QUIRK_ARM_MTK_EXT BIT(3) #define IO_PGTABLE_QUIRK_NON_STRICT BIT(4) #define IO_PGTABLE_QUIRK_ARM_TTBR1 BIT(5) -- cgit v1.2.3 From c52eef0b6ee1a3c57f6fccb30ea0b5ae19358471 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Fri, 22 Jan 2021 19:44:28 -0800 Subject: of/device: Don't NULLify match table in of_match_device() with CONFIG_OF=n This effectively reverts 1db73ae39a97 ("of/device: Nullify match table in of_match_device() for CONFIG_OF=n") because that commit makes it more surprising to users of this API that the arguments may never be referenced by any code. This is because the pre-processor will replace the argument with NULL and then the match table will be left unreferenced by any code but the compiler optimizer doesn't know to drop it. This can lead to compilers warning that match tables are unused, when we really want to pass the match table to the API but have the compiler see that it's all inlined and not used and then drop the match table while silencing the warning. We're being too smart here and not giving the compiler the chance to do dead code elimination. Signed-off-by: Stephen Boyd Acked-by: Frank Rowand Cc: Arnd Bergmann Cc: Geert Uytterhoeven Cc: Rob Herring Cc: Frank Rowand Reviewed-by: Geert Uytterhoeven Acked-by: Geert Uytterhoeven Reviewed-by: Arnd Bergmann Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20210123034428.2841052-7-swboyd@chromium.org --- include/linux/of_device.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_device.h b/include/linux/of_device.h index 07ca187fc5e4..937f32f6aecb 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -99,13 +99,11 @@ static inline int of_device_uevent_modalias(struct device *dev, static inline void of_device_node_put(struct device *dev) { } -static inline const struct of_device_id *__of_match_device( +static inline const struct of_device_id *of_match_device( const struct of_device_id *matches, const struct device *dev) { return NULL; } -#define of_match_device(matches, dev) \ - __of_match_device(of_match_ptr(matches), (dev)) static inline struct device_node *of_cpu_device_node_get(int cpu) { -- cgit v1.2.3 From 28af22c6c8dff6a16163e5b6a56211d5b535c97b Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Tue, 26 Jan 2021 18:39:39 +0100 Subject: net: adjust net_device layout for cacheline usage The current layout of net_device is not optimal for cacheline usage. The member adj_list.lower linked list is split between cacheline 2 and 3. The ifindex is placed together with stats (struct net_device_stats), although most modern drivers don't update this stats member. The members netdev_ops, mtu and hard_header_len are placed on three different cachelines. These members are accessed for XDP redirect into devmap, which were noticeably with perf tool. When not using the map redirect variant (like TC-BPF does), then ifindex is also used, which is placed on a separate fourth cacheline. These members are also accessed during forwarding with regular network stack. The members priv_flags and flags are on fast-path for network stack transmit path in __dev_queue_xmit (currently located together with mtu cacheline). This patch creates a read mostly cacheline, with the purpose of keeping the above mentioned members on the same cacheline. Some netdev_features_t members also becomes part of this cacheline, which is on purpose, as function netif_skb_features() is on fast-path via validate_xmit_skb(). Signed-off-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/r/161168277983.410784.12401225493601624417.stgit@firesoul Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 53 ++++++++++++++++++++++++----------------------- 1 file changed, 27 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9e8572533d8e..e9e7ada07ea1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1858,7 +1858,6 @@ struct net_device { unsigned long mem_end; unsigned long mem_start; unsigned long base_addr; - int irq; /* * Some hardware also needs these fields (state,dev_list, @@ -1880,6 +1879,23 @@ struct net_device { struct list_head lower; } adj_list; + /* Read-mostly cache-line for fast-path access */ + unsigned int flags; + unsigned int priv_flags; + const struct net_device_ops *netdev_ops; + int ifindex; + unsigned short gflags; + unsigned short hard_header_len; + + /* Note : dev->mtu is often read without holding a lock. + * Writers usually hold RTNL. + * It is recommended to use READ_ONCE() to annotate the reads, + * and to use WRITE_ONCE() to annotate the writes. + */ + unsigned int mtu; + unsigned short needed_headroom; + unsigned short needed_tailroom; + netdev_features_t features; netdev_features_t hw_features; netdev_features_t wanted_features; @@ -1888,10 +1904,15 @@ struct net_device { netdev_features_t mpls_features; netdev_features_t gso_partial_features; - int ifindex; + unsigned int min_mtu; + unsigned int max_mtu; + unsigned short type; + unsigned char min_header_len; + unsigned char name_assign_type; + int group; - struct net_device_stats stats; + struct net_device_stats stats; /* not used by modern drivers */ atomic_long_t rx_dropped; atomic_long_t tx_dropped; @@ -1905,7 +1926,6 @@ struct net_device { const struct iw_handler_def *wireless_handlers; struct iw_public_data *wireless_data; #endif - const struct net_device_ops *netdev_ops; const struct ethtool_ops *ethtool_ops; #ifdef CONFIG_NET_L3_MASTER_DEV const struct l3mdev_ops *l3mdev_ops; @@ -1924,34 +1944,12 @@ struct net_device { const struct header_ops *header_ops; - unsigned int flags; - unsigned int priv_flags; - - unsigned short gflags; - unsigned short padded; - unsigned char operstate; unsigned char link_mode; unsigned char if_port; unsigned char dma; - /* Note : dev->mtu is often read without holding a lock. - * Writers usually hold RTNL. - * It is recommended to use READ_ONCE() to annotate the reads, - * and to use WRITE_ONCE() to annotate the writes. - */ - unsigned int mtu; - unsigned int min_mtu; - unsigned int max_mtu; - unsigned short type; - unsigned short hard_header_len; - unsigned char min_header_len; - unsigned char name_assign_type; - - unsigned short needed_headroom; - unsigned short needed_tailroom; - /* Interface address info. */ unsigned char perm_addr[MAX_ADDR_LEN]; unsigned char addr_assign_type; @@ -1962,7 +1960,10 @@ struct net_device { unsigned short neigh_priv_len; unsigned short dev_id; unsigned short dev_port; + unsigned short padded; + spinlock_t addr_list_lock; + int irq; struct netdev_hw_addr_list uc; struct netdev_hw_addr_list mc; -- cgit v1.2.3 From f8408264c77a0cebb20244d1f4750501b36abe0e Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Thu, 14 Jan 2021 17:05:30 +0530 Subject: drivers: Remove CONFIG_OPROFILE support The "oprofile" user-space tools don't use the kernel OPROFILE support any more, and haven't in a long time. User-space has been converted to the perf interfaces. Remove kernel's old oprofile support. Suggested-by: Christoph Hellwig Suggested-by: Linus Torvalds Signed-off-by: Viresh Kumar Acked-by: Robert Richter Acked-by: Paul E. McKenney #RCU Acked-by: William Cohen Acked-by: Al Viro Acked-by: Thomas Gleixner --- include/linux/oprofile.h | 209 ----------------------------------------------- 1 file changed, 209 deletions(-) delete mode 100644 include/linux/oprofile.h (limited to 'include/linux') diff --git a/include/linux/oprofile.h b/include/linux/oprofile.h deleted file mode 100644 index b2a0f15f11fe..000000000000 --- a/include/linux/oprofile.h +++ /dev/null @@ -1,209 +0,0 @@ -/** - * @file oprofile.h - * - * API for machine-specific interrupts to interface - * to oprofile. - * - * @remark Copyright 2002 OProfile authors - * @remark Read the file COPYING - * - * @author John Levon - */ - -#ifndef OPROFILE_H -#define OPROFILE_H - -#include -#include -#include -#include -#include -#include - -/* Each escaped entry is prefixed by ESCAPE_CODE - * then one of the following codes, then the - * relevant data. - * These #defines live in this file so that arch-specific - * buffer sync'ing code can access them. - */ -#define ESCAPE_CODE ~0UL -#define CTX_SWITCH_CODE 1 -#define CPU_SWITCH_CODE 2 -#define COOKIE_SWITCH_CODE 3 -#define KERNEL_ENTER_SWITCH_CODE 4 -#define KERNEL_EXIT_SWITCH_CODE 5 -#define MODULE_LOADED_CODE 6 -#define CTX_TGID_CODE 7 -#define TRACE_BEGIN_CODE 8 -#define TRACE_END_CODE 9 -#define XEN_ENTER_SWITCH_CODE 10 -#define SPU_PROFILING_CODE 11 -#define SPU_CTX_SWITCH_CODE 12 -#define IBS_FETCH_CODE 13 -#define IBS_OP_CODE 14 - -struct dentry; -struct file_operations; -struct pt_regs; - -/* Operations structure to be filled in */ -struct oprofile_operations { - /* create any necessary configuration files in the oprofile fs. - * Optional. */ - int (*create_files)(struct dentry * root); - /* Do any necessary interrupt setup. Optional. */ - int (*setup)(void); - /* Do any necessary interrupt shutdown. Optional. */ - void (*shutdown)(void); - /* Start delivering interrupts. */ - int (*start)(void); - /* Stop delivering interrupts. */ - void (*stop)(void); - /* Arch-specific buffer sync functions. - * Return value = 0: Success - * Return value = -1: Failure - * Return value = 1: Run generic sync function - */ - int (*sync_start)(void); - int (*sync_stop)(void); - - /* Initiate a stack backtrace. Optional. */ - void (*backtrace)(struct pt_regs * const regs, unsigned int depth); - - /* Multiplex between different events. Optional. */ - int (*switch_events)(void); - /* CPU identification string. */ - char * cpu_type; -}; - -/** - * One-time initialisation. *ops must be set to a filled-in - * operations structure. This is called even in timer interrupt - * mode so an arch can set a backtrace callback. - * - * If an error occurs, the fields should be left untouched. - */ -int oprofile_arch_init(struct oprofile_operations * ops); - -/** - * One-time exit/cleanup for the arch. - */ -void oprofile_arch_exit(void); - -/** - * Add a sample. This may be called from any context. - */ -void oprofile_add_sample(struct pt_regs * const regs, unsigned long event); - -/** - * Add an extended sample. Use this when the PC is not from the regs, and - * we cannot determine if we're in kernel mode from the regs. - * - * This function does perform a backtrace. - * - */ -void oprofile_add_ext_sample(unsigned long pc, struct pt_regs * const regs, - unsigned long event, int is_kernel); - -/** - * Add an hardware sample. - */ -void oprofile_add_ext_hw_sample(unsigned long pc, struct pt_regs * const regs, - unsigned long event, int is_kernel, - struct task_struct *task); - -/* Use this instead when the PC value is not from the regs. Doesn't - * backtrace. */ -void oprofile_add_pc(unsigned long pc, int is_kernel, unsigned long event); - -/* add a backtrace entry, to be called from the ->backtrace callback */ -void oprofile_add_trace(unsigned long eip); - - -/** - * Create a file of the given name as a child of the given root, with - * the specified file operations. - */ -int oprofilefs_create_file(struct dentry * root, - char const * name, const struct file_operations * fops); - -int oprofilefs_create_file_perm(struct dentry * root, - char const * name, const struct file_operations * fops, int perm); - -/** Create a file for read/write access to an unsigned long. */ -int oprofilefs_create_ulong(struct dentry * root, - char const * name, ulong * val); - -/** Create a file for read-only access to an unsigned long. */ -int oprofilefs_create_ro_ulong(struct dentry * root, - char const * name, ulong * val); - -/** Create a file for read-only access to an atomic_t. */ -int oprofilefs_create_ro_atomic(struct dentry * root, - char const * name, atomic_t * val); - -/** create a directory */ -struct dentry *oprofilefs_mkdir(struct dentry *parent, char const *name); - -/** - * Write the given asciz string to the given user buffer @buf, updating *offset - * appropriately. Returns bytes written or -EFAULT. - */ -ssize_t oprofilefs_str_to_user(char const * str, char __user * buf, size_t count, loff_t * offset); - -/** - * Convert an unsigned long value into ASCII and copy it to the user buffer @buf, - * updating *offset appropriately. Returns bytes written or -EFAULT. - */ -ssize_t oprofilefs_ulong_to_user(unsigned long val, char __user * buf, size_t count, loff_t * offset); - -/** - * Read an ASCII string for a number from a userspace buffer and fill *val on success. - * Returns 0 on success, < 0 on error. - */ -int oprofilefs_ulong_from_user(unsigned long * val, char const __user * buf, size_t count); - -/** lock for read/write safety */ -extern raw_spinlock_t oprofilefs_lock; - -/** - * Add the contents of a circular buffer to the event buffer. - */ -void oprofile_put_buff(unsigned long *buf, unsigned int start, - unsigned int stop, unsigned int max); - -unsigned long oprofile_get_cpu_buffer_size(void); -void oprofile_cpu_buffer_inc_smpl_lost(void); - -/* cpu buffer functions */ - -struct op_sample; - -struct op_entry { - struct ring_buffer_event *event; - struct op_sample *sample; - unsigned long size; - unsigned long *data; -}; - -void oprofile_write_reserve(struct op_entry *entry, - struct pt_regs * const regs, - unsigned long pc, int code, int size); -int oprofile_add_data(struct op_entry *entry, unsigned long val); -int oprofile_add_data64(struct op_entry *entry, u64 val); -int oprofile_write_commit(struct op_entry *entry); - -#ifdef CONFIG_HW_PERF_EVENTS -int __init oprofile_perf_init(struct oprofile_operations *ops); -void oprofile_perf_exit(void); -char *op_name_from_perf_id(void); -#else -static inline int __init oprofile_perf_init(struct oprofile_operations *ops) -{ - pr_info("oprofile: hardware counters not available\n"); - return -ENODEV; -} -static inline void oprofile_perf_exit(void) { } -#endif /* CONFIG_HW_PERF_EVENTS */ - -#endif /* OPROFILE_H */ -- cgit v1.2.3 From be65de6b03aa638c46ea51e9d11a92e4914d8103 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Thu, 14 Jan 2021 17:05:31 +0530 Subject: fs: Remove dcookies support The dcookies stuff was only used by the kernel's old oprofile code. Now that oprofile's support is removed from the kernel, there is no need for dcookies as well. Remove it. Suggested-by: Christoph Hellwig Suggested-by: Linus Torvalds Signed-off-by: Viresh Kumar Acked-by: Robert Richter Acked-by: William Cohen Acked-by: Al Viro Acked-by: Thomas Gleixner --- include/linux/dcookies.h | 69 ------------------------------------------------ 1 file changed, 69 deletions(-) delete mode 100644 include/linux/dcookies.h (limited to 'include/linux') diff --git a/include/linux/dcookies.h b/include/linux/dcookies.h deleted file mode 100644 index ddfdac20cad0..000000000000 --- a/include/linux/dcookies.h +++ /dev/null @@ -1,69 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * dcookies.h - * - * Persistent cookie-path mappings - * - * Copyright 2002 John Levon - */ - -#ifndef DCOOKIES_H -#define DCOOKIES_H - - -#ifdef CONFIG_PROFILING - -#include -#include - -struct dcookie_user; -struct path; - -/** - * dcookie_register - register a user of dcookies - * - * Register as a dcookie user. Returns %NULL on failure. - */ -struct dcookie_user * dcookie_register(void); - -/** - * dcookie_unregister - unregister a user of dcookies - * - * Unregister as a dcookie user. This may invalidate - * any dcookie values returned from get_dcookie(). - */ -void dcookie_unregister(struct dcookie_user * user); - -/** - * get_dcookie - acquire a dcookie - * - * Convert the given dentry/vfsmount pair into - * a cookie value. - * - * Returns -EINVAL if no living task has registered as a - * dcookie user. - * - * Returns 0 on success, with *cookie filled in - */ -int get_dcookie(const struct path *path, unsigned long *cookie); - -#else - -static inline struct dcookie_user * dcookie_register(void) -{ - return NULL; -} - -static inline void dcookie_unregister(struct dcookie_user * user) -{ - return; -} - -static inline int get_dcookie(const struct path *path, unsigned long *cookie) -{ - return -ENOSYS; -} - -#endif /* CONFIG_PROFILING */ - -#endif /* DCOOKIES_H */ -- cgit v1.2.3 From 1d3f9bb1be8556bce237934ae82b3cdeda3242fd Mon Sep 17 00:00:00 2001 From: dingsenjie Date: Wed, 27 Jan 2021 10:28:01 +0800 Subject: linux/qed: fix spelling typo in qed_chain.h allocted -> allocated Signed-off-by: dingsenjie Link: https://lore.kernel.org/r/20210127022801.8028-1-dingsenjie@163.com Signed-off-by: Jakub Kicinski --- include/linux/qed/qed_chain.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index 4d58dc8943f0..e339b48de32d 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -470,7 +470,7 @@ static inline void *qed_chain_consume(struct qed_chain *p_chain) /** * @brief qed_chain_reset - Resets the chain to its start state * - * @param p_chain pointer to a previously allocted chain + * @param p_chain pointer to a previously allocated chain */ static inline void qed_chain_reset(struct qed_chain *p_chain) { -- cgit v1.2.3 From ae8eba8b5d723a4ca543024b6e51f4d0f4fb6b6b Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Wed, 27 Jan 2021 23:53:43 +0000 Subject: tlb: mmu_gather: Remove unused start/end arguments from tlb_finish_mmu() Since commit 7a30df49f63a ("mm: mmu_gather: remove __tlb_reset_range() for force flush"), the 'start' and 'end' arguments to tlb_finish_mmu() are no longer used, since we flush the whole mm in case of a nested invalidation. Remove the unused arguments and update all callers. Signed-off-by: Will Deacon Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Yu Zhao Acked-by: Peter Zijlstra (Intel) Acked-by: Linus Torvalds Link: https://lkml.kernel.org/r/20210127235347.1402-3-will@kernel.org --- include/linux/mm_types.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 07d9acb5b19c..1fe6a51298a6 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -590,8 +590,7 @@ static inline cpumask_t *mm_cpumask(struct mm_struct *mm) struct mmu_gather; extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end); -extern void tlb_finish_mmu(struct mmu_gather *tlb, - unsigned long start, unsigned long end); +extern void tlb_finish_mmu(struct mmu_gather *tlb); static inline void init_tlb_flush_pending(struct mm_struct *mm) { -- cgit v1.2.3 From d8b450530b90f8845ab962af18b8a10ed77fc889 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Wed, 27 Jan 2021 23:53:44 +0000 Subject: tlb: mmu_gather: Introduce tlb_gather_mmu_fullmm() Passing the range '0, -1' to tlb_gather_mmu() sets the 'fullmm' flag, which indicates that the mm_struct being operated on is going away. In this case, some architectures (such as arm64) can elide TLB invalidation by ensuring that the TLB tag (ASID) associated with this mm is not immediately reclaimed. Although this behaviour is documented in asm-generic/tlb.h, it's subtle and easily missed. Introduce tlb_gather_mmu_fullmm() to make it clearer that this is for the entire mm and WARN() if tlb_gather_mmu() is called with the 'fullmm' address range. Signed-off-by: Will Deacon Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Yu Zhao Acked-by: Peter Zijlstra (Intel) Acked-by: Linus Torvalds Link: https://lkml.kernel.org/r/20210127235347.1402-4-will@kernel.org --- include/linux/mm_types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 1fe6a51298a6..e49868bc12a7 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -590,6 +590,7 @@ static inline cpumask_t *mm_cpumask(struct mm_struct *mm) struct mmu_gather; extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end); +extern void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm); extern void tlb_finish_mmu(struct mmu_gather *tlb); static inline void init_tlb_flush_pending(struct mm_struct *mm) -- cgit v1.2.3 From a72afd873089c697053e9daa85ff343b3140d2e7 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Wed, 27 Jan 2021 23:53:45 +0000 Subject: tlb: mmu_gather: Remove start/end arguments from tlb_gather_mmu() The 'start' and 'end' arguments to tlb_gather_mmu() are no longer needed now that there is a separate function for 'fullmm' flushing. Remove the unused arguments and update all callers. Suggested-by: Linus Torvalds Signed-off-by: Will Deacon Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Yu Zhao Acked-by: Peter Zijlstra (Intel) Acked-by: Linus Torvalds Link: https://lore.kernel.org/r/CAHk-=wjQWa14_4UpfDf=fiineNP+RH74kZeDMo_f1D35xNzq9w@mail.gmail.com --- include/linux/mm_types.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index e49868bc12a7..0974ad501a47 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -588,8 +588,7 @@ static inline cpumask_t *mm_cpumask(struct mm_struct *mm) } struct mmu_gather; -extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, - unsigned long start, unsigned long end); +extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm); extern void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm); extern void tlb_finish_mmu(struct mmu_gather *tlb); -- cgit v1.2.3 From 9c7caf28068421c9e0d1faea437e35e6b8983ac6 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 29 Jan 2021 02:59:59 +0200 Subject: net: dsa: tag_8021q: add helpers to deduce whether a VLAN ID is RX or TX VLAN The sja1105 implementation can be blind about this, but the felix driver doesn't do exactly what it's being told, so it needs to know whether it is a TX or an RX VLAN, so it can install the appropriate type of TCAM rule. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: Jakub Kicinski --- include/linux/dsa/8021q.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 88cd72dfa4e0..b12b05f1c8b4 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -64,6 +64,10 @@ int dsa_8021q_rx_source_port(u16 vid); u16 dsa_8021q_rx_subvlan(u16 vid); +bool vid_is_dsa_8021q_rxvlan(u16 vid); + +bool vid_is_dsa_8021q_txvlan(u16 vid); + bool vid_is_dsa_8021q(u16 vid); #else @@ -123,6 +127,16 @@ u16 dsa_8021q_rx_subvlan(u16 vid) return 0; } +bool vid_is_dsa_8021q_rxvlan(u16 vid) +{ + return false; +} + +bool vid_is_dsa_8021q_txvlan(u16 vid) +{ + return false; +} + bool vid_is_dsa_8021q(u16 vid) { return false; -- cgit v1.2.3 From de5774d192ba15539191ed8b0c79f3d52464b8e3 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Tue, 26 Jan 2021 12:45:39 +0000 Subject: clk: imx: Move 'imx6sl_set_wait_clk()'s prototype out to accessible header MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixes the following W=1 kernel build warning(s): drivers/clk/imx/clk-imx6sl.c:156:6: warning: no previous prototype for ‘imx6sl_set_wait_clk’ [-Wmissing-prototypes] Cc: Russell King Cc: Shawn Guo Cc: Sascha Hauer Cc: Pengutronix Kernel Team Cc: Fabio Estevam Cc: NXP Linux Team Cc: Ahmad Fatoum Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Lee Jones Signed-off-by: Shawn Guo --- include/linux/clk/imx.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) create mode 100644 include/linux/clk/imx.h (limited to 'include/linux') diff --git a/include/linux/clk/imx.h b/include/linux/clk/imx.h new file mode 100644 index 000000000000..75a0d9696552 --- /dev/null +++ b/include/linux/clk/imx.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 Freescale Semiconductor, Inc. + * + * Author: Lee Jones + */ + +#ifndef __LINUX_CLK_IMX_H +#define __LINUX_CLK_IMX_H + +#include + +void imx6sl_set_wait_clk(bool enter); + +#endif -- cgit v1.2.3 From 3cc55f4434b421d37300aa9a167ace7d60b45ccf Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Fri, 29 Jan 2021 14:26:29 -0500 Subject: nfs: use change attribute for NFS re-exports When exporting NFS, we may as well use the real change attribute returned by the original server instead of faking up a change attribute from the ctime. Note we can't do that by setting I_VERSION--that would also turn on the logic in iversion.h which treats the lower bit specially, and that doesn't make sense for NFS. So instead we define a new export operation for filesystems like NFS that want to manage the change attribute themselves. Signed-off-by: J. Bruce Fields Reviewed-by: Christoph Hellwig Signed-off-by: Chuck Lever --- include/linux/exportfs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index 9f4d4bcbf251..fe848901fcc3 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -213,6 +213,7 @@ struct export_operations { bool write, u32 *device_generation); int (*commit_blocks)(struct inode *inode, struct iomap *iomaps, int nr_iomaps, struct iattr *iattr); + u64 (*fetch_iversion)(struct inode *); #define EXPORT_OP_NOWCC (0x1) /* don't collect v3 wcc data */ #define EXPORT_OP_NOSUBTREECHK (0x2) /* no subtree checking */ #define EXPORT_OP_CLOSE_BEFORE_UNLINK (0x4) /* close files before unlink */ -- cgit v1.2.3 From 207f13b419a60c56fb75baeb3d668de080514354 Mon Sep 17 00:00:00 2001 From: Fabien Parent Date: Wed, 9 Dec 2020 14:32:37 +0100 Subject: soc: mediatek: pm-domains: Add support for mt8167 Add the needed board data to support mt8167 SoC. Signed-off-by: Fabien Parent Reviewed-by: Enric Balletbo i Serra Link: https://lore.kernel.org/r/20201209133238.384030-2-fparent@baylibre.com Signed-off-by: Matthias Brugger --- include/linux/soc/mediatek/infracfg.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/mediatek/infracfg.h b/include/linux/soc/mediatek/infracfg.h index e7842debc05d..4615a228da51 100644 --- a/include/linux/soc/mediatek/infracfg.h +++ b/include/linux/soc/mediatek/infracfg.h @@ -123,6 +123,14 @@ #define MT8173_TOP_AXI_PROT_EN_MFG_M1 BIT(22) #define MT8173_TOP_AXI_PROT_EN_MFG_SNOOP_OUT BIT(23) +#define MT8167_TOP_AXI_PROT_EN_MM_EMI BIT(1) +#define MT8167_TOP_AXI_PROT_EN_MCU_MFG BIT(2) +#define MT8167_TOP_AXI_PROT_EN_CONN_EMI BIT(4) +#define MT8167_TOP_AXI_PROT_EN_MFG_EMI BIT(5) +#define MT8167_TOP_AXI_PROT_EN_CONN_MCU BIT(8) +#define MT8167_TOP_AXI_PROT_EN_MCU_CONN BIT(9) +#define MT8167_TOP_AXI_PROT_EN_MCU_MM BIT(11) + #define MT2701_TOP_AXI_PROT_EN_MM_M0 BIT(1) #define MT2701_TOP_AXI_PROT_EN_CONN_M BIT(2) #define MT2701_TOP_AXI_PROT_EN_CONN_S BIT(8) -- cgit v1.2.3 From 1570db1da9f57dfbe5dfa3010233c98947497466 Mon Sep 17 00:00:00 2001 From: Chun-Kuang Hu Date: Thu, 3 Dec 2020 07:58:55 +0800 Subject: soc: mediatek: cmdq: Remove cmdq_pkt_flush() rx_callback is a standard mailbox callback mechanism and could cover the function of proprietary cmdq_task_cb, so it is better to use the standard one instead of the proprietary one. But register rx_callback should before mbox_request_channel(), so remove cmdq_pkt_flush() and let client driver implement its own synchronous flush. Signed-off-by: Chun-Kuang Hu Link: https://lore.kernel.org/r/20201202235856.7652-1-chunkuang.hu@kernel.org Signed-off-by: Matthias Brugger --- include/linux/soc/mediatek/mtk-cmdq.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h index 8e9996610978..ac6b5f3cba95 100644 --- a/include/linux/soc/mediatek/mtk-cmdq.h +++ b/include/linux/soc/mediatek/mtk-cmdq.h @@ -280,16 +280,4 @@ int cmdq_pkt_finalize(struct cmdq_pkt *pkt); int cmdq_pkt_flush_async(struct cmdq_pkt *pkt, cmdq_async_flush_cb cb, void *data); -/** - * cmdq_pkt_flush() - trigger CMDQ to execute the CMDQ packet - * @pkt: the CMDQ packet - * - * Return: 0 for success; else the error code is returned - * - * Trigger CMDQ to execute the CMDQ packet. Note that this is a - * synchronous flush function. When the function returned, the recorded - * commands have been done. - */ -int cmdq_pkt_flush(struct cmdq_pkt *pkt); - #endif /* __MTK_CMDQ_H__ */ -- cgit v1.2.3 From fb02e3ebfb2da27172da47f79a5481c4fe83d751 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 29 Jan 2021 20:51:47 +0100 Subject: staging: hikey9xx: spmi driver: convert to regmap Instead of doing its own SPMI I/O implementation, use the already-existing regmap one. Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/7084885f3007ca5daf0d5bc85d038e26ee82dc0d.1611949675.git.mchehab+huawei@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mfd/hi6421-spmi-pmic.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/hi6421-spmi-pmic.h b/include/linux/mfd/hi6421-spmi-pmic.h index 0c2214612c4e..c5a4eac1fdc0 100644 --- a/include/linux/mfd/hi6421-spmi-pmic.h +++ b/include/linux/mfd/hi6421-spmi-pmic.h @@ -12,6 +12,7 @@ #define __HISI_PMIC_H #include +#include #define HISI_ECO_MODE_ENABLE (1) #define HISI_ECO_MODE_DISABLE (0) @@ -25,13 +26,9 @@ struct hi6421_spmi_pmic { int irq; int gpio; unsigned int *irqs; + struct regmap *map; }; -int hi6421_spmi_pmic_read(struct hi6421_spmi_pmic *pmic, int reg); -int hi6421_spmi_pmic_write(struct hi6421_spmi_pmic *pmic, int reg, u32 val); -int hi6421_spmi_pmic_rmw(struct hi6421_spmi_pmic *pmic, int reg, - u32 mask, u32 bits); - enum hi6421_spmi_pmic_irq_list { OTMP = 0, VBUS_CONNECT, -- cgit v1.2.3 From fcd732406c5d65ba92515af81ca281a4f8348687 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 29 Jan 2021 20:51:49 +0100 Subject: staging: hikey9xx: hi6421-spmi-pmic: rename some vars - When referring to regmap, rename map to regmap - inside hi6421-spmi-pmic, call private data struct as ddata. No functional changes. Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/d23592b11ac606e3b9a3ff95a754cb75921e60aa.1611949675.git.mchehab+huawei@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mfd/hi6421-spmi-pmic.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/hi6421-spmi-pmic.h b/include/linux/mfd/hi6421-spmi-pmic.h index c5a4eac1fdc0..aa8d5382f559 100644 --- a/include/linux/mfd/hi6421-spmi-pmic.h +++ b/include/linux/mfd/hi6421-spmi-pmic.h @@ -26,7 +26,7 @@ struct hi6421_spmi_pmic { int irq; int gpio; unsigned int *irqs; - struct regmap *map; + struct regmap *regmap; }; enum hi6421_spmi_pmic_irq_list { -- cgit v1.2.3 From 9d8dbe989029e6d767ed56773ac65409da625381 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 29 Jan 2021 20:51:51 +0100 Subject: staging: hikey9xx: hi6421-spmi-pmic: cleanup header file Remove the IRQ list from the header, as this is used only inside the driver itself. Also, get rid of two unused defines. The net result is that only struct hi6421_spmi_pmic remains on it, as this is used by the regulator driver. Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/138c3a11e4de0ebabdf27932957852136c2f7510.1611949675.git.mchehab+huawei@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mfd/hi6421-spmi-pmic.h | 20 -------------------- 1 file changed, 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/hi6421-spmi-pmic.h b/include/linux/mfd/hi6421-spmi-pmic.h index aa8d5382f559..4d61cb266a18 100644 --- a/include/linux/mfd/hi6421-spmi-pmic.h +++ b/include/linux/mfd/hi6421-spmi-pmic.h @@ -14,9 +14,6 @@ #include #include -#define HISI_ECO_MODE_ENABLE (1) -#define HISI_ECO_MODE_DISABLE (0) - struct hi6421_spmi_pmic { struct resource *res; struct device *dev; @@ -29,21 +26,4 @@ struct hi6421_spmi_pmic { struct regmap *regmap; }; -enum hi6421_spmi_pmic_irq_list { - OTMP = 0, - VBUS_CONNECT, - VBUS_DISCONNECT, - ALARMON_R, - HOLD_6S, - HOLD_1S, - POWERKEY_UP, - POWERKEY_DOWN, - OCP_SCP_R, - COUL_R, - SIM0_HPD_R, - SIM0_HPD_F, - SIM1_HPD_R, - SIM1_HPD_F, - PMIC_IRQ_LIST_MAX, -}; #endif /* __HISI_PMIC_H */ -- cgit v1.2.3 From fb7ba1870d5fdf45513fc04af8e46492eb65a5e3 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 29 Jan 2021 20:51:55 +0100 Subject: staging: hikey9xx: hi6421-spmi-pmic: update copyright notes At PMIC subsystem, C89 comments are preferred over C99. While here, also update the copyrights of the header file. Signed-off-by: Mauro Carvalho Chehab Link: https://lore.kernel.org/r/5a86478c8ccb93d3105485b5f16e20e9c12e2196.1611949675.git.mchehab+huawei@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mfd/hi6421-spmi-pmic.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/hi6421-spmi-pmic.h b/include/linux/mfd/hi6421-spmi-pmic.h index 4d61cb266a18..2660226138b8 100644 --- a/include/linux/mfd/hi6421-spmi-pmic.h +++ b/include/linux/mfd/hi6421-spmi-pmic.h @@ -4,6 +4,7 @@ * * Copyright (c) 2013 Linaro Ltd. * Copyright (C) 2011 Hisilicon. + * Copyright (c) 2020-2021 Huawei Technologies Co., Ltd * * Guodong Xu */ -- cgit v1.2.3 From a0f2a1cb65c9d8a66853e1b67184022663950f6d Mon Sep 17 00:00:00 2001 From: Grygorii Strashko Date: Fri, 29 Jan 2021 21:31:17 +0200 Subject: dmaengine: ti: k3-psil: optimize struct psil_endpoint_config for size Optimize struct psil_endpoint_config for size by - reordering fields - grouping bitfields - change mapped_channel_id type to s16 (32K channel is enough) - default_flow_id type to s16 as it's assigned to -1 before: text data bss dec hex filename 12654100 5211472 666904 18532476 11ac87c vmlinux after: 12654100 5208528 666904 18529532 11abcfc vmlinux diff: 2944 bytes Signed-off-by: Grygorii Strashko Link: https://lore.kernel.org/r/20210129193117.28833-1-grygorii.strashko@ti.com Signed-off-by: Vinod Koul --- include/linux/dma/k3-psil.h | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma/k3-psil.h b/include/linux/dma/k3-psil.h index 36e22c5a0f29..5f106d852f1c 100644 --- a/include/linux/dma/k3-psil.h +++ b/include/linux/dma/k3-psil.h @@ -42,14 +42,14 @@ enum psil_endpoint_type { /** * struct psil_endpoint_config - PSI-L Endpoint configuration * @ep_type: PSI-L endpoint type + * @channel_tpl: Desired throughput level for the channel * @pkt_mode: If set, the channel must be in Packet mode, otherwise in * TR mode * @notdpkt: TDCM must be suppressed on the TX channel * @needs_epib: Endpoint needs EPIB - * @psd_size: If set, PSdata is used by the endpoint - * @channel_tpl: Desired throughput level for the channel * @pdma_acc32: ACC32 must be enabled on the PDMA side * @pdma_burst: BURST must be enabled on the PDMA side + * @psd_size: If set, PSdata is used by the endpoint * @mapped_channel_id: PKTDMA thread to channel mapping for mapped channels. * The thread must be serviced by the specified channel if * mapped_channel_id is >= 0 in case of PKTDMA @@ -62,23 +62,22 @@ enum psil_endpoint_type { */ struct psil_endpoint_config { enum psil_endpoint_type ep_type; + enum udma_tp_level channel_tpl; unsigned pkt_mode:1; unsigned notdpkt:1; unsigned needs_epib:1; - u32 psd_size; - enum udma_tp_level channel_tpl; - /* PDMA properties, valid for PSIL_EP_PDMA_* */ unsigned pdma_acc32:1; unsigned pdma_burst:1; + u32 psd_size; /* PKDMA mapped channel */ - int mapped_channel_id; + s16 mapped_channel_id; /* PKTDMA tflow and rflow ranges for mapped channel */ u16 flow_start; u16 flow_num; - u16 default_flow_id; + s16 default_flow_id; }; int psil_set_new_ep_config(struct device *dev, const char *name, -- cgit v1.2.3 From 67a73230fbaed9ff4902389d4f040abe57c5783c Mon Sep 17 00:00:00 2001 From: "H. Nikolaus Schaller" Date: Wed, 23 Dec 2020 10:01:51 +0100 Subject: mmc: omap: remove unused struct component card_detect_irq I have not found any user for this struct component. Signed-off-by: H. Nikolaus Schaller Link: https://lore.kernel.org/r/b6f2168b863e4273c6bca5a22fbd4a3a8ddf68d6.1608714110.git.hns@goldelico.com Signed-off-by: Ulf Hansson --- include/linux/platform_data/mmc-omap.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/mmc-omap.h b/include/linux/platform_data/mmc-omap.h index f0b8947e6b07..91051e9907f3 100644 --- a/include/linux/platform_data/mmc-omap.h +++ b/include/linux/platform_data/mmc-omap.h @@ -108,8 +108,7 @@ struct omap_mmc_platform_data { const char *name; u32 ocr_mask; - /* Card detection IRQs */ - int card_detect_irq; + /* Card detection */ int (*card_detect)(struct device *dev, int slot); unsigned int ban_openended:1; -- cgit v1.2.3 From 3561afa02605b398d1b98e1ce913ea6411cdc5dd Mon Sep 17 00:00:00 2001 From: Andrew Jeffery Date: Thu, 14 Jan 2021 13:44:28 +1030 Subject: mmc: core: Add helper for parsing clock phase properties Drivers for MMC hosts that accept phase corrections can take advantage of the helper by embedding an instance of struct mmc_clk_phase_map in their private data and invoking mmc_of_parse_clk_phase() to extract phase parameters. It is the responsibility of the host driver to translate and apply the extracted values to hardware as required. Signed-off-by: Andrew Jeffery Link: https://lore.kernel.org/r/20210114031433.2388532-2-andrew@aj.id.au Signed-off-by: Ulf Hansson --- include/linux/mmc/host.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 01bba36545c5..8cf686d98a68 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -79,6 +79,17 @@ struct mmc_ios { bool enhanced_strobe; /* hs400es selection */ }; +struct mmc_clk_phase { + bool valid; + u16 in_deg; + u16 out_deg; +}; + +#define MMC_NUM_CLK_PHASES (MMC_TIMING_MMC_HS400 + 1) +struct mmc_clk_phase_map { + struct mmc_clk_phase phase[MMC_NUM_CLK_PHASES]; +}; + struct mmc_host; struct mmc_host_ops { @@ -490,6 +501,8 @@ struct mmc_host *mmc_alloc_host(int extra, struct device *); int mmc_add_host(struct mmc_host *); void mmc_remove_host(struct mmc_host *); void mmc_free_host(struct mmc_host *); +void mmc_of_parse_clk_phase(struct mmc_host *host, + struct mmc_clk_phase_map *map); int mmc_of_parse(struct mmc_host *host); int mmc_of_parse_voltage(struct device_node *np, u32 *mask); -- cgit v1.2.3 From 5851d3b042b694839d2241fbb3200ce958135cdf Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Thu, 21 Jan 2021 00:21:54 -0800 Subject: block/keyslot-manager: introduce devm_blk_ksm_init() Add a resource-managed variant of blk_ksm_init() so that drivers don't have to worry about calling blk_ksm_destroy(). Note that the implementation uses a custom devres action to call blk_ksm_destroy() rather than switching the two allocations to be directly devres-managed, e.g. with devm_kmalloc(). This is because we need to keep zeroing the memory containing the keyslots when it is freed, and also because we want to continue using kvmalloc() (and there is no devm_kvmalloc()). Signed-off-by: Eric Biggers Reviewed-by: Satya Tangirala Acked-by: Jens Axboe Link: https://lore.kernel.org/r/20210121082155.111333-2-ebiggers@kernel.org Signed-off-by: Ulf Hansson --- include/linux/keyslot-manager.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/keyslot-manager.h b/include/linux/keyslot-manager.h index 18f3f5346843..443ad817c6c5 100644 --- a/include/linux/keyslot-manager.h +++ b/include/linux/keyslot-manager.h @@ -85,6 +85,9 @@ struct blk_keyslot_manager { int blk_ksm_init(struct blk_keyslot_manager *ksm, unsigned int num_slots); +int devm_blk_ksm_init(struct device *dev, struct blk_keyslot_manager *ksm, + unsigned int num_slots); + blk_status_t blk_ksm_get_slot_for_key(struct blk_keyslot_manager *ksm, const struct blk_crypto_key *key, struct blk_ksm_keyslot **slot_ptr); -- cgit v1.2.3 From 93f1c150cb0d043e1e8985db7824b4e2e1ac653f Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 25 Jan 2021 16:14:48 -0800 Subject: mmc: core: Add basic support for inline encryption In preparation for adding CQHCI crypto engine (inline encryption) support, add the code required to make mmc_core and mmc_block aware of inline encryption. Specifically: - Add a capability flag MMC_CAP2_CRYPTO to struct mmc_host. Drivers will set this if the host and driver support inline encryption. - Embed a blk_keyslot_manager in struct mmc_host. Drivers will initialize this (as a device-managed resource) if the host and driver support inline encryption. mmc_block registers this keyslot manager with the request_queue of any MMC card attached to the host. - Make mmc_block copy the crypto keyslot and crypto data unit number from struct request to struct mmc_request, so that drivers will have access to them. - If the MMC host is reset, reprogram all the keyslots to ensure that the software state stays in sync with the hardware state. Co-developed-by: Satya Tangirala Signed-off-by: Satya Tangirala Acked-by: Adrian Hunter Reviewed-by: Satya Tangirala Reviewed-and-tested-by: Peng Zhou Signed-off-by: Eric Biggers Link: https://lore.kernel.org/r/20210126001456.382989-2-ebiggers@kernel.org Signed-off-by: Ulf Hansson --- include/linux/mmc/core.h | 6 ++++++ include/linux/mmc/host.h | 11 +++++++++++ 2 files changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index 29aa50711626..ab19245e9945 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -162,6 +162,12 @@ struct mmc_request { bool cap_cmd_during_tfr; int tag; + +#ifdef CONFIG_MMC_CRYPTO + bool crypto_enabled; + int crypto_key_slot; + u32 data_unit_num; +#endif }; struct mmc_card; diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 8cf686d98a68..927ba7566617 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -15,6 +15,7 @@ #include #include #include +#include struct mmc_ios { unsigned int clock; /* clock rate */ @@ -395,6 +396,11 @@ struct mmc_host { #define MMC_CAP2_CQE_DCMD (1 << 24) /* CQE can issue a direct command */ #define MMC_CAP2_AVOID_3_3V (1 << 25) /* Host must negotiate down from 3.3V */ #define MMC_CAP2_MERGE_CAPABLE (1 << 26) /* Host can merge a segment over the segment size */ +#ifdef CONFIG_MMC_CRYPTO +#define MMC_CAP2_CRYPTO (1 << 27) /* Host supports inline encryption */ +#else +#define MMC_CAP2_CRYPTO 0 +#endif int fixed_drv_type; /* fixed driver type for non-removable media */ @@ -489,6 +495,11 @@ struct mmc_host { bool cqe_enabled; bool cqe_on; + /* Inline encryption support */ +#ifdef CONFIG_MMC_CRYPTO + struct blk_keyslot_manager ksm; +#endif + /* Host Software Queue support */ bool hsq_enabled; -- cgit v1.2.3 From 40596d2f2b6075f6c33180b2f55c814ff4885475 Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Mon, 11 Jan 2021 19:18:51 +0800 Subject: iommu/io-pgtable-arm-v7s: Extend PA34 for MediaTek MediaTek extend the bit5 in lvl1 and lvl2 descriptor as PA34. Signed-off-by: Yong Wu Acked-by: Will Deacon Reviewed-by: Robin Murphy Reviewed-by: Tomasz Figa Link: https://lore.kernel.org/r/20210111111914.22211-11-yong.wu@mediatek.com Signed-off-by: Will Deacon --- include/linux/io-pgtable.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index 06753323a15e..d69234a4a65e 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -69,8 +69,8 @@ struct io_pgtable_cfg { * format, and/or requires some format-specific default value. * * IO_PGTABLE_QUIRK_ARM_MTK_EXT: (ARM v7s format) MediaTek IOMMUs extend - * to support up to 34 bits PA where the bit32 and bit33 are - * encoded in the bit9 and bit4 of the PTE respectively. + * to support up to 35 bits PA where the bit32, bit33 and bit34 are + * encoded in the bit9, bit4 and bit5 of the PTE respectively. * * IO_PGTABLE_QUIRK_NON_STRICT: Skip issuing synchronous leaf TLBIs * on unmap, for DMA domains using the flush queue mechanism for -- cgit v1.2.3 From f5030e252687be6e999bd52feb1f79d515b2f684 Mon Sep 17 00:00:00 2001 From: Benson Leung Date: Thu, 28 Jan 2021 22:14:02 -0800 Subject: usb: typec: Provide PD Specification Revision for cable and partner The USB Power Delivery specification Section 6.2.1.1.5 outlines revision backward compatibility requirements starting from Revision 3.0. The Port, the Cable Plug, and the Port Partner may support either revision 2 or revision 3 independently, and communication between ports, partners, and cables of different revisions are allowed under rules that the parties agree to communicate between each other using the lowest common operating revision. This may mean that Port-to-Partner operating revision comms may be different than Port-to-CablePlug operating revision comms. For example, it is possible for a R3.0 port to communicate with a R3.0 partner using R3.0 messages, while the R3.0 port (in the same session) must communicate with the R2.0 cable using R2.0 messages only. Introduce individual revision number properties for cable and port partner so that the port can track them independently. Reviewed-by: Heikki Krogerus Signed-off-by: Benson Leung Link: https://lore.kernel.org/r/20210129061406.2680146-3-bleung@chromium.org Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/typec.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h index 54475323f83b..42c6b7c07a99 100644 --- a/include/linux/usb/typec.h +++ b/include/linux/usb/typec.h @@ -164,6 +164,7 @@ struct typec_plug_desc { * @type: The plug type from USB PD Cable VDO * @active: Is the cable active or passive * @identity: Result of Discover Identity command + * @pd_revision: USB Power Delivery Specification revision if supported * * Represents USB Type-C Cable attached to USB Type-C port. */ @@ -171,6 +172,8 @@ struct typec_cable_desc { enum typec_plug_type type; unsigned int active:1; struct usb_pd_identity *identity; + u16 pd_revision; /* 0300H = "3.0" */ + }; /* @@ -178,15 +181,22 @@ struct typec_cable_desc { * @usb_pd: USB Power Delivery support * @accessory: Audio, Debug or none. * @identity: Discover Identity command data + * @pd_revision: USB Power Delivery Specification Revision if supported * * Details about a partner that is attached to USB Type-C port. If @identity * member exists when partner is registered, a directory named "identity" is * created to sysfs for the partner device. + * + * @pd_revision is based on the setting of the "Specification Revision" field + * in the message header on the initial "Source Capabilities" message received + * from the partner, or a "Request" message received from the partner, depending + * on whether our port is a Sink or a Source. */ struct typec_partner_desc { unsigned int usb_pd:1; enum typec_accessory accessory; struct usb_pd_identity *identity; + u16 pd_revision; /* 0300H = "3.0" */ }; /** -- cgit v1.2.3 From 29b01295a829fba7399ee84afff4e64660e49f04 Mon Sep 17 00:00:00 2001 From: Benson Leung Date: Thu, 28 Jan 2021 22:14:03 -0800 Subject: usb: typec: Add typec_partner_set_pd_revision The partner's PD revision may be resolved later than the port partner registration since the port partner creation may take place once Type-C detects the port has changed state, but before PD communication is completed. Add a setter so that the partner's PD revision can be attached to it once it becomes available. If the revision is set to a valid version (not 0), the setter will also refresh the partner's usb_pd flag and notify on "supports_usb_power_delivery" sysfs property as well. Reviewed-by: Heikki Krogerus Signed-off-by: Benson Leung Link: https://lore.kernel.org/r/20210129061406.2680146-4-bleung@chromium.org Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/typec.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h index 42c6b7c07a99..4946eca742d5 100644 --- a/include/linux/usb/typec.h +++ b/include/linux/usb/typec.h @@ -126,6 +126,7 @@ struct typec_altmode_desc { enum typec_port_data roles; }; +int typec_partner_set_pd_revision(struct typec_partner *partner, u16 pd_revision); int typec_partner_set_num_altmodes(struct typec_partner *partner, int num_altmodes); struct typec_altmode *typec_partner_register_altmode(struct typec_partner *partner, -- cgit v1.2.3 From 2a6c6b7d7ad346f0679d0963cb19b3f0ea7ef32c Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Thu, 28 Jan 2021 14:40:07 -0800 Subject: perf/core: Add PERF_SAMPLE_WEIGHT_STRUCT Current PERF_SAMPLE_WEIGHT sample type is very useful to expresses the cost of an action represented by the sample. This allows the profiler to scale the samples to be more informative to the programmer. It could also help to locate a hotspot, e.g., when profiling by memory latencies, the expensive load appear higher up in the histograms. But current PERF_SAMPLE_WEIGHT sample type is solely determined by one factor. This could be a problem, if users want two or more factors to contribute to the weight. For example, Golden Cove core PMU can provide both the instruction latency and the cache Latency information as factors for the memory profiling. For current X86 platforms, although meminfo::latency is defined as a u64, only the lower 32 bits include the valid data in practice (No memory access could last than 4G cycles). The higher 32 bits can be used to store new factors. Add a new sample type, PERF_SAMPLE_WEIGHT_STRUCT, to indicate the new sample weight structure. It shares the same space as the PERF_SAMPLE_WEIGHT sample type. Users can apply either the PERF_SAMPLE_WEIGHT sample type or the PERF_SAMPLE_WEIGHT_STRUCT sample type to retrieve the sample weight, but they cannot apply both sample types simultaneously. Currently, only X86 and PowerPC use the PERF_SAMPLE_WEIGHT sample type. - For PowerPC, there is nothing changed for the PERF_SAMPLE_WEIGHT sample type. There is no effect for the new PERF_SAMPLE_WEIGHT_STRUCT sample type. PowerPC can re-struct the weight field similarly later. - For X86, the same value will be dumped for the PERF_SAMPLE_WEIGHT sample type or the PERF_SAMPLE_WEIGHT_STRUCT sample type for now. The following patches will apply the new factors for the PERF_SAMPLE_WEIGHT_STRUCT sample type. The field in the union perf_sample_weight should be shared among different architectures. A generic name is required, but it's hard to abstract a name that applies to all architectures. For example, on X86, the fields are to store all kinds of latency. While on PowerPC, it stores MMCRA[TECX/TECM], which should not be latency. So a general name prefix 'var$NUM' is used here. Suggested-by: Peter Zijlstra (Intel) Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/1611873611-156687-2-git-send-email-kan.liang@linux.intel.com --- include/linux/perf_event.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 9a38f579bc76..fab42cfbd350 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -998,7 +998,7 @@ struct perf_sample_data { struct perf_raw_record *raw; struct perf_branch_stack *br_stack; u64 period; - u64 weight; + union perf_sample_weight weight; u64 txn; union perf_mem_data_src data_src; @@ -1047,7 +1047,7 @@ static inline void perf_sample_data_init(struct perf_sample_data *data, data->raw = NULL; data->br_stack = NULL; data->period = period; - data->weight = 0; + data->weight.full = 0; data->data_src.val = PERF_MEM_NA; data->txn = 0; } -- cgit v1.2.3 From 1af7e7f8c12f521c111bd7cf0d138be7e15b51a5 Mon Sep 17 00:00:00 2001 From: Dave Wysochanski Date: Thu, 28 Jan 2021 09:55:01 -0500 Subject: NFS: Refactor nfs_readpage() and nfs_readpage_async() to use nfs_readdesc Both nfs_readpage() and nfs_readpages() use similar code. This patch should be no functional change, and refactors nfs_readpage_async() to use nfs_readdesc to enable future merging of nfs_readpage_async() and nfs_readpage_async_filler(). Signed-off-by: Dave Wysochanski Signed-off-by: Anna Schumaker --- include/linux/nfs_fs.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 681ed98e4ba8..cb0248a34518 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -570,8 +570,7 @@ nfs_have_writebacks(struct inode *inode) extern int nfs_readpage(struct file *, struct page *); extern int nfs_readpages(struct file *, struct address_space *, struct list_head *, unsigned); -extern int nfs_readpage_async(struct nfs_open_context *, struct inode *, - struct page *); +extern int nfs_readpage_async(void *, struct inode *, struct page *); /* * inline functions -- cgit v1.2.3 From 1e83b173b2663b7d357309584678cf24787f0713 Mon Sep 17 00:00:00 2001 From: Dave Wysochanski Date: Thu, 28 Jan 2021 09:55:03 -0500 Subject: NFS: Add nfs_pageio_complete_read() and remove nfs_readpage_async() Add nfs_pageio_complete_read() and call this from both nfs_readpage() and nfs_readpages(), since the submission and accounting is the same for both functions. Signed-off-by: Dave Wysochanski Signed-off-by: Anna Schumaker --- include/linux/nfs_fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index cb0248a34518..3cfcf219e96b 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -570,7 +570,6 @@ nfs_have_writebacks(struct inode *inode) extern int nfs_readpage(struct file *, struct page *); extern int nfs_readpages(struct file *, struct address_space *, struct list_head *, unsigned); -extern int nfs_readpage_async(void *, struct inode *, struct page *); /* * inline functions -- cgit v1.2.3 From ec5e32940cc9d2a8a321cb7d756fb6ae45702d03 Mon Sep 17 00:00:00 2001 From: Steve Sistare Date: Fri, 29 Jan 2021 08:54:10 -0800 Subject: vfio: iommu driver notify callback Define a vfio_iommu_driver_ops notify callback, for sending events to the driver. Drivers are not required to provide the callback, and may ignore any events. The handling of events is driver specific. Define the CONTAINER_CLOSE event, called when the container's file descriptor is closed. This event signifies that no further state changes will occur via container ioctl's. Signed-off-by: Steve Sistare Reviewed-by: Cornelia Huck Signed-off-by: Alex Williamson --- include/linux/vfio.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index f45940b38a02..b7e18bde5aa8 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -57,6 +57,11 @@ extern struct vfio_device *vfio_device_get_from_dev(struct device *dev); extern void vfio_device_put(struct vfio_device *device); extern void *vfio_device_data(struct vfio_device *device); +/* events for the backend driver notify callback */ +enum vfio_iommu_notify_type { + VFIO_IOMMU_CONTAINER_CLOSE = 0, +}; + /** * struct vfio_iommu_driver_ops - VFIO IOMMU driver callbacks */ @@ -92,6 +97,8 @@ struct vfio_iommu_driver_ops { void *data, size_t count, bool write); struct iommu_domain *(*group_iommu_domain)(void *iommu_data, struct iommu_group *group); + void (*notify)(void *iommu_data, + enum vfio_iommu_notify_type event); }; extern int vfio_register_iommu_driver(const struct vfio_iommu_driver_ops *ops); -- cgit v1.2.3 From 9ff0c6db0605e9b88360048c8d0a6a9ff647eb71 Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Fri, 22 Jan 2021 21:24:57 +0200 Subject: platform/x86: mlxcpld: Update module license Update license to SPDX-License. Signed-off-by: Vadim Pasternak Acked-by: Peter Rosin Signed-off-by: Wolfram Sang --- include/linux/platform_data/x86/mlxcpld.h | 34 +++---------------------------- 1 file changed, 3 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/x86/mlxcpld.h b/include/linux/platform_data/x86/mlxcpld.h index b08dcb183fca..e6c18bf017dd 100644 --- a/include/linux/platform_data/x86/mlxcpld.h +++ b/include/linux/platform_data/x86/mlxcpld.h @@ -1,36 +1,8 @@ +/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */ /* - * mlxcpld.h - Mellanox I2C multiplexer support in CPLD + * Mellanox I2C multiplexer support in CPLD * - * Copyright (c) 2016 Mellanox Technologies. All rights reserved. - * Copyright (c) 2016 Michael Shych - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are met: - * - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. Neither the names of the copyright holders nor the names of its - * contributors may be used to endorse or promote products derived from - * this software without specific prior written permission. - * - * Alternatively, this software may be distributed under the terms of the - * GNU General Public License ("GPL") version 2 as published by the Free - * Software Foundation. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" - * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE - * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE - * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE - * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS - * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN - * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) - * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE - * POSSIBILITY OF SUCH DAMAGE. + * Copyright (C) 2016-2020 Mellanox Technologies */ #ifndef _LINUX_I2C_MLXCPLD_H -- cgit v1.2.3 From 98d29c410475f30b627502d845794352e9be4046 Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Fri, 22 Jan 2021 21:24:58 +0200 Subject: i2c: mux: mlxcpld: Move header file out of x86 realm Move out header file from include/linux/platform_data/x86/ to include/linux/platform_data/, since it does not depend on x86 architecture. Signed-off-by: Vadim Pasternak Reviewed-by: Michael Shych Acked-by: Peter Rosin Signed-off-by: Wolfram Sang --- include/linux/platform_data/mlxcpld.h | 24 ++++++++++++++++++++++++ include/linux/platform_data/x86/mlxcpld.h | 24 ------------------------ 2 files changed, 24 insertions(+), 24 deletions(-) create mode 100644 include/linux/platform_data/mlxcpld.h delete mode 100644 include/linux/platform_data/x86/mlxcpld.h (limited to 'include/linux') diff --git a/include/linux/platform_data/mlxcpld.h b/include/linux/platform_data/mlxcpld.h new file mode 100644 index 000000000000..e6c18bf017dd --- /dev/null +++ b/include/linux/platform_data/mlxcpld.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */ +/* + * Mellanox I2C multiplexer support in CPLD + * + * Copyright (C) 2016-2020 Mellanox Technologies + */ + +#ifndef _LINUX_I2C_MLXCPLD_H +#define _LINUX_I2C_MLXCPLD_H + +/* Platform data for the CPLD I2C multiplexers */ + +/* mlxcpld_mux_plat_data - per mux data, used with i2c_register_board_info + * @adap_ids - adapter array + * @num_adaps - number of adapters + * @sel_reg_addr - mux select register offset in CPLD space + */ +struct mlxcpld_mux_plat_data { + int *adap_ids; + int num_adaps; + int sel_reg_addr; +}; + +#endif /* _LINUX_I2C_MLXCPLD_H */ diff --git a/include/linux/platform_data/x86/mlxcpld.h b/include/linux/platform_data/x86/mlxcpld.h deleted file mode 100644 index e6c18bf017dd..000000000000 --- a/include/linux/platform_data/x86/mlxcpld.h +++ /dev/null @@ -1,24 +0,0 @@ -/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */ -/* - * Mellanox I2C multiplexer support in CPLD - * - * Copyright (C) 2016-2020 Mellanox Technologies - */ - -#ifndef _LINUX_I2C_MLXCPLD_H -#define _LINUX_I2C_MLXCPLD_H - -/* Platform data for the CPLD I2C multiplexers */ - -/* mlxcpld_mux_plat_data - per mux data, used with i2c_register_board_info - * @adap_ids - adapter array - * @num_adaps - number of adapters - * @sel_reg_addr - mux select register offset in CPLD space - */ -struct mlxcpld_mux_plat_data { - int *adap_ids; - int num_adaps; - int sel_reg_addr; -}; - -#endif /* _LINUX_I2C_MLXCPLD_H */ -- cgit v1.2.3 From dd9267034c0e364b49261c3e0070b863286d1242 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Thu, 28 Jan 2021 10:10:48 +0100 Subject: i3c: Make remove callback return void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver core ignores the return value of struct bus_type::remove() because there is only little that can be done. To simplify the quest to make this function return void, let struct i3c_driver::remove() return void, too. This makes it obvious that returning an error code is a bad idea and future driver authors cannot get that wrong. Up to now there are no drivers with a remove callback, so there is no need to adapt drivers. Signed-off-by: Uwe Kleine-König Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20210128091048.17006-2-u.kleine-koenig@pengutronix.de --- include/linux/i3c/device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i3c/device.h b/include/linux/i3c/device.h index de102e4418ab..8242e13e7b0b 100644 --- a/include/linux/i3c/device.h +++ b/include/linux/i3c/device.h @@ -176,7 +176,7 @@ struct i3c_device; struct i3c_driver { struct device_driver driver; int (*probe)(struct i3c_device *dev); - int (*remove)(struct i3c_device *dev); + void (*remove)(struct i3c_device *dev); const struct i3c_device_id *id_table; }; -- cgit v1.2.3 From 8dd5cada393f6f4e825833a6ff05b1f51f36a791 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Mon, 18 Jan 2021 03:55:18 +0300 Subject: opp: Add dev_pm_opp_find_level_ceil() Add a ceil version of the dev_pm_opp_find_level(). It's handy to have if levels don't start from 0 in OPP table and zero usually means a minimal level. Tested-by: Peter Geis Tested-by: Nicolas Chauvet Tested-by: Matt Merhar Signed-off-by: Dmitry Osipenko Signed-off-by: Viresh Kumar --- include/linux/pm_opp.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 1435c054016a..2b3030cb2ed2 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -111,6 +111,8 @@ struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, bool available); struct dev_pm_opp *dev_pm_opp_find_level_exact(struct device *dev, unsigned int level); +struct dev_pm_opp *dev_pm_opp_find_level_ceil(struct device *dev, + unsigned int *level); struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev, unsigned long *freq); @@ -226,6 +228,12 @@ static inline struct dev_pm_opp *dev_pm_opp_find_level_exact(struct device *dev, return ERR_PTR(-ENOTSUPP); } +static inline struct dev_pm_opp *dev_pm_opp_find_level_ceil(struct device *dev, + unsigned int *level) +{ + return ERR_PTR(-ENOTSUPP); +} + static inline struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev, unsigned long *freq) { -- cgit v1.2.3 From 597ff5431fd41afa888809f7936508a15c977cde Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Mon, 18 Jan 2021 03:55:19 +0300 Subject: opp: Add dev_pm_opp_get_required_pstate() Add dev_pm_opp_get_required_pstate() which allows OPP users to retrieve required performance state of a given OPP. Tested-by: Peter Geis Tested-by: Nicolas Chauvet Tested-by: Matt Merhar Signed-off-by: Dmitry Osipenko Signed-off-by: Viresh Kumar --- include/linux/pm_opp.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 2b3030cb2ed2..8f926815bad9 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -98,6 +98,9 @@ unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp); unsigned int dev_pm_opp_get_level(struct dev_pm_opp *opp); +unsigned int dev_pm_opp_get_required_pstate(struct dev_pm_opp *opp, + unsigned int index); + bool dev_pm_opp_is_turbo(struct dev_pm_opp *opp); int dev_pm_opp_get_opp_count(struct device *dev); @@ -186,6 +189,13 @@ static inline unsigned int dev_pm_opp_get_level(struct dev_pm_opp *opp) return 0; } +static inline +unsigned int dev_pm_opp_get_required_pstate(struct dev_pm_opp *opp, + unsigned int index) +{ + return 0; +} + static inline bool dev_pm_opp_is_turbo(struct dev_pm_opp *opp) { return false; -- cgit v1.2.3 From ce8073d83f63a2cdcfc1b86d769456726faad51d Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Thu, 21 Jan 2021 01:26:47 +0300 Subject: opp: Add dev_pm_opp_sync_regulators() Extend OPP API with dev_pm_opp_sync_regulators() function, which syncs voltage state of regulators. Tested-by: Peter Geis Tested-by: Nicolas Chauvet Tested-by: Matt Merhar Signed-off-by: Dmitry Osipenko [ Viresh: Added unlikely() ] Signed-off-by: Viresh Kumar --- include/linux/pm_opp.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 8f926815bad9..979b208bc4a8 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -161,6 +161,7 @@ int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, const struct cpumask *cp int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask); void dev_pm_opp_remove_table(struct device *dev); void dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask); +int dev_pm_opp_sync_regulators(struct device *dev); #else static inline struct opp_table *dev_pm_opp_get_opp_table(struct device *dev) { @@ -384,6 +385,11 @@ static inline void dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask { } +static inline int dev_pm_opp_sync_regulators(struct device *dev) +{ + return -ENOTSUPP; +} + #endif /* CONFIG_PM_OPP */ #if defined(CONFIG_PM_OPP) && defined(CONFIG_OF) -- cgit v1.2.3 From 559fef0dfd91145b59b7c61061504f344ecf9ad8 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 27 Jan 2021 14:23:45 +0530 Subject: opp: Add dev_pm_opp_of_add_table_noclk() A few drivers have device's clk but they don't want the OPP core to handle that. Add a new helper for them, dev_pm_opp_of_add_table_noclk(). Signed-off-by: Viresh Kumar Tested-by: Dmitry Osipenko --- include/linux/pm_opp.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 979b208bc4a8..158158620dde 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -395,6 +395,7 @@ static inline int dev_pm_opp_sync_regulators(struct device *dev) #if defined(CONFIG_PM_OPP) && defined(CONFIG_OF) int dev_pm_opp_of_add_table(struct device *dev); int dev_pm_opp_of_add_table_indexed(struct device *dev, int index); +int dev_pm_opp_of_add_table_noclk(struct device *dev, int index); void dev_pm_opp_of_remove_table(struct device *dev); int dev_pm_opp_of_cpumask_add_table(const struct cpumask *cpumask); void dev_pm_opp_of_cpumask_remove_table(const struct cpumask *cpumask); @@ -419,6 +420,11 @@ static inline int dev_pm_opp_of_add_table_indexed(struct device *dev, int index) return -ENOTSUPP; } +static inline int dev_pm_opp_of_add_table_noclk(struct device *dev, int index) +{ + return -ENOTSUPP; +} + static inline void dev_pm_opp_of_remove_table(struct device *dev) { } -- cgit v1.2.3 From a3c47af6942dc8e07a4328913d0263a965786895 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Mon, 18 Jan 2021 03:55:20 +0300 Subject: opp: Add devm_pm_opp_register_set_opp_helper Add resource-managed version of dev_pm_opp_register_set_opp_helper(). Tested-by: Peter Geis Tested-by: Nicolas Chauvet Tested-by: Matt Merhar Signed-off-by: Dmitry Osipenko [ Viresh: Manually apply the patch and relocate the routines ] Signed-off-by: Viresh Kumar --- include/linux/pm_opp.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 158158620dde..473daf34160d 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -152,6 +152,7 @@ struct opp_table *dev_pm_opp_set_clkname(struct device *dev, const char * name); void dev_pm_opp_put_clkname(struct opp_table *opp_table); struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data)); void dev_pm_opp_unregister_set_opp_helper(struct opp_table *opp_table); +struct opp_table *devm_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data)); struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char **names, struct device ***virt_devs); void dev_pm_opp_detach_genpd(struct opp_table *opp_table); int dev_pm_opp_xlate_performance_state(struct opp_table *src_table, struct opp_table *dst_table, unsigned int pstate); @@ -324,6 +325,13 @@ static inline struct opp_table *dev_pm_opp_register_set_opp_helper(struct device static inline void dev_pm_opp_unregister_set_opp_helper(struct opp_table *opp_table) {} +static inline struct opp_table * +devm_pm_opp_register_set_opp_helper(struct device *dev, + int (*set_opp)(struct dev_pm_set_opp_data *data)) +{ + return ERR_PTR(-ENOTSUPP); +} + static inline struct opp_table *dev_pm_opp_set_prop_name(struct device *dev, const char *name) { return ERR_PTR(-ENOTSUPP); -- cgit v1.2.3 From b4b9e223eccaeec6e05d927c292d4425fd18f243 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Mon, 18 Jan 2021 03:55:21 +0300 Subject: opp: Add devm_pm_opp_attach_genpd Add resource-managed version of dev_pm_opp_attach_genpd(). Signed-off-by: Dmitry Osipenko [ Viresh: Manually apply the patch and relocate the routines ] Signed-off-by: Viresh Kumar --- include/linux/pm_opp.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 473daf34160d..a2c871799603 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -155,6 +155,7 @@ void dev_pm_opp_unregister_set_opp_helper(struct opp_table *opp_table); struct opp_table *devm_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data)); struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char **names, struct device ***virt_devs); void dev_pm_opp_detach_genpd(struct opp_table *opp_table); +struct opp_table *devm_pm_opp_attach_genpd(struct device *dev, const char **names, struct device ***virt_devs); int dev_pm_opp_xlate_performance_state(struct opp_table *src_table, struct opp_table *dst_table, unsigned int pstate); int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq); int dev_pm_opp_set_bw(struct device *dev, struct dev_pm_opp *opp); @@ -360,6 +361,12 @@ static inline struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, cons static inline void dev_pm_opp_detach_genpd(struct opp_table *opp_table) {} +static inline struct opp_table *devm_pm_opp_attach_genpd(struct device *dev, + const char **names, struct device ***virt_devs) +{ + return ERR_PTR(-ENOTSUPP); +} + static inline int dev_pm_opp_xlate_performance_state(struct opp_table *src_table, struct opp_table *dst_table, unsigned int pstate) { return -ENOTSUPP; -- cgit v1.2.3 From abbe348340c7df9e08fd7c24491c1be31ab65370 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Thu, 21 Jan 2021 12:15:36 +0530 Subject: opp: Implement dev_pm_opp_set_opp() The new helper dev_pm_opp_set_opp() can be used for configuring the devices for a particular OPP and can be used by different type of devices, even the ones which don't change frequency (like power domains). Signed-off-by: Viresh Kumar Tested-by: Dmitry Osipenko --- include/linux/pm_opp.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index a2c871799603..7b1d47ab3fb3 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -158,6 +158,7 @@ void dev_pm_opp_detach_genpd(struct opp_table *opp_table); struct opp_table *devm_pm_opp_attach_genpd(struct device *dev, const char **names, struct device ***virt_devs); int dev_pm_opp_xlate_performance_state(struct opp_table *src_table, struct opp_table *dst_table, unsigned int pstate); int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq); +int dev_pm_opp_set_opp(struct device *dev, struct dev_pm_opp *opp); int dev_pm_opp_set_bw(struct device *dev, struct dev_pm_opp *opp); int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, const struct cpumask *cpumask); int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask); @@ -377,6 +378,11 @@ static inline int dev_pm_opp_set_rate(struct device *dev, unsigned long target_f return -ENOTSUPP; } +static inline int dev_pm_opp_set_opp(struct device *dev, struct dev_pm_opp *opp) +{ + return -ENOTSUPP; +} + static inline int dev_pm_opp_set_bw(struct device *dev, struct dev_pm_opp *opp) { return -EOPNOTSUPP; -- cgit v1.2.3 From 240ae50e23061cd1fe1937daab195c17226ffd2e Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Thu, 21 Jan 2021 15:27:55 +0530 Subject: opp: Remove dev_pm_opp_set_bw() All the users have migrated to dev_pm_opp_set_opp() now, get rid of the duplicate API, dev_pm_opp_set_bw(), which only performs a part of the new API. While at it, remove the unnecessary parameter to _set_opp_bw(). Signed-off-by: Viresh Kumar Tested-by: Dmitry Osipenko --- include/linux/pm_opp.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 7b1d47ab3fb3..25e47ab937b9 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -159,7 +159,6 @@ struct opp_table *devm_pm_opp_attach_genpd(struct device *dev, const char **name int dev_pm_opp_xlate_performance_state(struct opp_table *src_table, struct opp_table *dst_table, unsigned int pstate); int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq); int dev_pm_opp_set_opp(struct device *dev, struct dev_pm_opp *opp); -int dev_pm_opp_set_bw(struct device *dev, struct dev_pm_opp *opp); int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, const struct cpumask *cpumask); int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask); void dev_pm_opp_remove_table(struct device *dev); @@ -383,11 +382,6 @@ static inline int dev_pm_opp_set_opp(struct device *dev, struct dev_pm_opp *opp) return -ENOTSUPP; } -static inline int dev_pm_opp_set_bw(struct device *dev, struct dev_pm_opp *opp) -{ - return -EOPNOTSUPP; -} - static inline int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, const struct cpumask *cpumask) { return -ENOTSUPP; -- cgit v1.2.3 From f3988bc5d58b768c5cf0dadf5f0e49f7176432df Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Mon, 1 Feb 2021 10:35:07 +0530 Subject: opp: Fix "foo * bar" should be "foo *bar" Fix checkpatch warning: ERROR: "foo * bar" should be "foo *bar". Signed-off-by: Viresh Kumar --- include/linux/pm_opp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 25e47ab937b9..c6c7d73eb015 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -148,7 +148,7 @@ struct opp_table *dev_pm_opp_set_prop_name(struct device *dev, const char *name) void dev_pm_opp_put_prop_name(struct opp_table *opp_table); struct opp_table *dev_pm_opp_set_regulators(struct device *dev, const char * const names[], unsigned int count); void dev_pm_opp_put_regulators(struct opp_table *opp_table); -struct opp_table *dev_pm_opp_set_clkname(struct device *dev, const char * name); +struct opp_table *dev_pm_opp_set_clkname(struct device *dev, const char *name); void dev_pm_opp_put_clkname(struct opp_table *opp_table); struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data)); void dev_pm_opp_unregister_set_opp_helper(struct opp_table *opp_table); @@ -347,7 +347,7 @@ static inline struct opp_table *dev_pm_opp_set_regulators(struct device *dev, co static inline void dev_pm_opp_put_regulators(struct opp_table *opp_table) {} -static inline struct opp_table *dev_pm_opp_set_clkname(struct device *dev, const char * name) +static inline struct opp_table *dev_pm_opp_set_clkname(struct device *dev, const char *name) { return ERR_PTR(-ENOTSUPP); } -- cgit v1.2.3 From 1d614920318b914f86c1fec2adec06ad2f7c3f55 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Mon, 1 Feb 2021 10:48:54 +0530 Subject: opp: Replace ENOTSUPP with EOPNOTSUPP Checkpatch gives following warning for new patches, and the new patches normally follow the existing standards for such stuff. Lets fix it properly. WARNING: ENOTSUPP is not a SUSV4 error code, prefer EOPNOTSUPP. Signed-off-by: Viresh Kumar --- include/linux/pm_opp.h | 64 +++++++++++++++++++++++++------------------------- 1 file changed, 32 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index c6c7d73eb015..ab1d15ce559d 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -167,12 +167,12 @@ int dev_pm_opp_sync_regulators(struct device *dev); #else static inline struct opp_table *dev_pm_opp_get_opp_table(struct device *dev) { - return ERR_PTR(-ENOTSUPP); + return ERR_PTR(-EOPNOTSUPP); } static inline struct opp_table *dev_pm_opp_get_opp_table_indexed(struct device *dev, int index) { - return ERR_PTR(-ENOTSUPP); + return ERR_PTR(-EOPNOTSUPP); } static inline void dev_pm_opp_put_opp_table(struct opp_table *opp_table) {} @@ -232,37 +232,37 @@ static inline unsigned long dev_pm_opp_get_suspend_opp_freq(struct device *dev) static inline struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, unsigned long freq, bool available) { - return ERR_PTR(-ENOTSUPP); + return ERR_PTR(-EOPNOTSUPP); } static inline struct dev_pm_opp *dev_pm_opp_find_level_exact(struct device *dev, unsigned int level) { - return ERR_PTR(-ENOTSUPP); + return ERR_PTR(-EOPNOTSUPP); } static inline struct dev_pm_opp *dev_pm_opp_find_level_ceil(struct device *dev, unsigned int *level) { - return ERR_PTR(-ENOTSUPP); + return ERR_PTR(-EOPNOTSUPP); } static inline struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev, unsigned long *freq) { - return ERR_PTR(-ENOTSUPP); + return ERR_PTR(-EOPNOTSUPP); } static inline struct dev_pm_opp *dev_pm_opp_find_freq_ceil_by_volt(struct device *dev, unsigned long u_volt) { - return ERR_PTR(-ENOTSUPP); + return ERR_PTR(-EOPNOTSUPP); } static inline struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev, unsigned long *freq) { - return ERR_PTR(-ENOTSUPP); + return ERR_PTR(-EOPNOTSUPP); } static inline void dev_pm_opp_put(struct dev_pm_opp *opp) {} @@ -270,7 +270,7 @@ static inline void dev_pm_opp_put(struct dev_pm_opp *opp) {} static inline int dev_pm_opp_add(struct device *dev, unsigned long freq, unsigned long u_volt) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline void dev_pm_opp_remove(struct device *dev, unsigned long freq) @@ -301,19 +301,19 @@ static inline int dev_pm_opp_disable(struct device *dev, unsigned long freq) static inline int dev_pm_opp_register_notifier(struct device *dev, struct notifier_block *nb) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline int dev_pm_opp_unregister_notifier(struct device *dev, struct notifier_block *nb) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline struct opp_table *dev_pm_opp_set_supported_hw(struct device *dev, const u32 *versions, unsigned int count) { - return ERR_PTR(-ENOTSUPP); + return ERR_PTR(-EOPNOTSUPP); } static inline void dev_pm_opp_put_supported_hw(struct opp_table *opp_table) {} @@ -321,7 +321,7 @@ static inline void dev_pm_opp_put_supported_hw(struct opp_table *opp_table) {} static inline struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data)) { - return ERR_PTR(-ENOTSUPP); + return ERR_PTR(-EOPNOTSUPP); } static inline void dev_pm_opp_unregister_set_opp_helper(struct opp_table *opp_table) {} @@ -330,33 +330,33 @@ static inline struct opp_table * devm_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data)) { - return ERR_PTR(-ENOTSUPP); + return ERR_PTR(-EOPNOTSUPP); } static inline struct opp_table *dev_pm_opp_set_prop_name(struct device *dev, const char *name) { - return ERR_PTR(-ENOTSUPP); + return ERR_PTR(-EOPNOTSUPP); } static inline void dev_pm_opp_put_prop_name(struct opp_table *opp_table) {} static inline struct opp_table *dev_pm_opp_set_regulators(struct device *dev, const char * const names[], unsigned int count) { - return ERR_PTR(-ENOTSUPP); + return ERR_PTR(-EOPNOTSUPP); } static inline void dev_pm_opp_put_regulators(struct opp_table *opp_table) {} static inline struct opp_table *dev_pm_opp_set_clkname(struct device *dev, const char *name) { - return ERR_PTR(-ENOTSUPP); + return ERR_PTR(-EOPNOTSUPP); } static inline void dev_pm_opp_put_clkname(struct opp_table *opp_table) {} static inline struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char **names, struct device ***virt_devs) { - return ERR_PTR(-ENOTSUPP); + return ERR_PTR(-EOPNOTSUPP); } static inline void dev_pm_opp_detach_genpd(struct opp_table *opp_table) {} @@ -364,27 +364,27 @@ static inline void dev_pm_opp_detach_genpd(struct opp_table *opp_table) {} static inline struct opp_table *devm_pm_opp_attach_genpd(struct device *dev, const char **names, struct device ***virt_devs) { - return ERR_PTR(-ENOTSUPP); + return ERR_PTR(-EOPNOTSUPP); } static inline int dev_pm_opp_xlate_performance_state(struct opp_table *src_table, struct opp_table *dst_table, unsigned int pstate) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline int dev_pm_opp_set_opp(struct device *dev, struct dev_pm_opp *opp) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, const struct cpumask *cpumask) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask) @@ -402,7 +402,7 @@ static inline void dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask static inline int dev_pm_opp_sync_regulators(struct device *dev) { - return -ENOTSUPP; + return -EOPNOTSUPP; } #endif /* CONFIG_PM_OPP */ @@ -427,17 +427,17 @@ static inline void dev_pm_opp_of_unregister_em(struct device *dev) #else static inline int dev_pm_opp_of_add_table(struct device *dev) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline int dev_pm_opp_of_add_table_indexed(struct device *dev, int index) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline int dev_pm_opp_of_add_table_noclk(struct device *dev, int index) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline void dev_pm_opp_of_remove_table(struct device *dev) @@ -446,7 +446,7 @@ static inline void dev_pm_opp_of_remove_table(struct device *dev) static inline int dev_pm_opp_of_cpumask_add_table(const struct cpumask *cpumask) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline void dev_pm_opp_of_cpumask_remove_table(const struct cpumask *cpumask) @@ -455,7 +455,7 @@ static inline void dev_pm_opp_of_cpumask_remove_table(const struct cpumask *cpum static inline int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device *dev) @@ -471,7 +471,7 @@ static inline struct device_node *dev_pm_opp_get_of_node(struct dev_pm_opp *opp) static inline int dev_pm_opp_of_register_em(struct device *dev, struct cpumask *cpus) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline void dev_pm_opp_of_unregister_em(struct device *dev) @@ -480,12 +480,12 @@ static inline void dev_pm_opp_of_unregister_em(struct device *dev) static inline int of_get_required_opp_performance_state(struct device_node *np, int index) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline int dev_pm_opp_of_find_icc_paths(struct device *dev, struct opp_table *opp_table) { - return -ENOTSUPP; + return -EOPNOTSUPP; } #endif -- cgit v1.2.3 From 3254899e0b52f10b9a3e7db4d10f081f60705ba9 Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Thu, 21 Jan 2021 09:09:47 +0000 Subject: nvme: update enumerations for status codes All the updates are mentioned in the ratified NVMe 1.4 spec. Reviewed-by: Hannes Reinecke Signed-off-by: Max Gurtovoy Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 24 ++++++++++++++++++++---- 1 file changed, 20 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index bfed36e342cc..458719544253 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -1473,20 +1473,29 @@ enum { NVME_SC_SGL_INVALID_DATA = 0xf, NVME_SC_SGL_INVALID_METADATA = 0x10, NVME_SC_SGL_INVALID_TYPE = 0x11, - + NVME_SC_CMB_INVALID_USE = 0x12, + NVME_SC_PRP_INVALID_OFFSET = 0x13, + NVME_SC_ATOMIC_WU_EXCEEDED = 0x14, + NVME_SC_OP_DENIED = 0x15, NVME_SC_SGL_INVALID_OFFSET = 0x16, - NVME_SC_SGL_INVALID_SUBTYPE = 0x17, - + NVME_SC_RESERVED = 0x17, + NVME_SC_HOST_ID_INCONSIST = 0x18, + NVME_SC_KA_TIMEOUT_EXPIRED = 0x19, + NVME_SC_KA_TIMEOUT_INVALID = 0x1A, + NVME_SC_ABORTED_PREEMPT_ABORT = 0x1B, NVME_SC_SANITIZE_FAILED = 0x1C, NVME_SC_SANITIZE_IN_PROGRESS = 0x1D, - + NVME_SC_SGL_INVALID_GRANULARITY = 0x1E, + NVME_SC_CMD_NOT_SUP_CMB_QUEUE = 0x1F, NVME_SC_NS_WRITE_PROTECTED = 0x20, NVME_SC_CMD_INTERRUPTED = 0x21, + NVME_SC_TRANSIENT_TR_ERR = 0x22, NVME_SC_LBA_RANGE = 0x80, NVME_SC_CAP_EXCEEDED = 0x81, NVME_SC_NS_NOT_READY = 0x82, NVME_SC_RESERVATION_CONFLICT = 0x83, + NVME_SC_FORMAT_IN_PROGRESS = 0x84, /* * Command Specific Status: @@ -1519,8 +1528,15 @@ enum { NVME_SC_NS_NOT_ATTACHED = 0x11a, NVME_SC_THIN_PROV_NOT_SUPP = 0x11b, NVME_SC_CTRL_LIST_INVALID = 0x11c, + NVME_SC_SELT_TEST_IN_PROGRESS = 0x11d, NVME_SC_BP_WRITE_PROHIBITED = 0x11e, + NVME_SC_CTRL_ID_INVALID = 0x11f, + NVME_SC_SEC_CTRL_STATE_INVALID = 0x120, + NVME_SC_CTRL_RES_NUM_INVALID = 0x121, + NVME_SC_RES_ID_INVALID = 0x122, NVME_SC_PMR_SAN_PROHIBITED = 0x123, + NVME_SC_ANA_GROUP_ID_INVALID = 0x124, + NVME_SC_ANA_ATTACH_FAILED = 0x125, /* * I/O Command Set Specific - NVM commands: -- cgit v1.2.3 From 4a407d5ebc7ac1ea8c6e2692bd79320459dc60f6 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Wed, 27 Jan 2021 02:50:00 +0900 Subject: nvme: add tracing of zns commands When support for the NVMe ZNS commands was merged, tracing of these has been omitted. Add nvme_cmd_zone_mgmt_send, nvme_cmd_zone_mgmt_recv as well as nvme_cmd_zone_append to the nvme driver's tracing facility. Signed-off-by: Johannes Thumshirn Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 458719544253..b08787cd0881 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -697,7 +697,11 @@ enum nvme_opcode { nvme_opcode_name(nvme_cmd_resv_register), \ nvme_opcode_name(nvme_cmd_resv_report), \ nvme_opcode_name(nvme_cmd_resv_acquire), \ - nvme_opcode_name(nvme_cmd_resv_release)) + nvme_opcode_name(nvme_cmd_resv_release), \ + nvme_opcode_name(nvme_cmd_zone_mgmt_send), \ + nvme_opcode_name(nvme_cmd_zone_mgmt_recv), \ + nvme_opcode_name(nvme_cmd_zone_append)) + /* -- cgit v1.2.3 From 3fd269e74f2feec973f45ee11d822faeda4fe284 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 26 Jan 2021 17:58:34 +0100 Subject: amba: Make the remove callback return void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit All amba drivers return 0 in their remove callback. Together with the driver core ignoring the return value anyhow, it doesn't make sense to return a value here. Change the remove prototype to return void, which makes it explicit that returning an error value doesn't work as expected. This simplifies changing the core remove callback to return void, too. Reviewed-by: Ulf Hansson Reviewed-by: Arnd Bergmann Acked-by: Alexandre Belloni Acked-by: Dmitry Torokhov Acked-by: Krzysztof Kozlowski # for drivers/memory Acked-by: Mark Brown Acked-by: Linus Walleij Acked-by: Suzuki K Poulose # for hwtracing/coresight Acked-By: Vinod Koul # for dmaengine Acked-by: Guenter Roeck # for watchdog Acked-by: Wolfram Sang # for I2C Acked-by: Takashi Iwai # for sound Acked-by: Vladimir Zapolskiy # for memory/pl172 Acked-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20210126165835.687514-5-u.kleine-koenig@pengutronix.de Signed-off-by: Uwe Kleine-König --- include/linux/amba/bus.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h index 0bbfd647f5c6..6cc93ab5b809 100644 --- a/include/linux/amba/bus.h +++ b/include/linux/amba/bus.h @@ -76,7 +76,7 @@ struct amba_device { struct amba_driver { struct device_driver drv; int (*probe)(struct amba_device *, const struct amba_id *); - int (*remove)(struct amba_device *); + void (*remove)(struct amba_device *); void (*shutdown)(struct amba_device *); const struct amba_id *id_table; }; -- cgit v1.2.3 From c7020068bf2397b60bb62a1f71ca0fe626c1f7e7 Mon Sep 17 00:00:00 2001 From: Elvira Khabirova Date: Sun, 20 Sep 2020 04:58:57 +0300 Subject: tee: fix some comment typos in header files struct tee_param: revc -> recv. TEE_IOC_SUPPL_SEND: typo introduced by copy-pasting, replace invalid description with description from the according argument struct. Signed-off-by: Elvira Khabirova Signed-off-by: Jens Wiklander --- include/linux/tee_drv.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index cdd049a724b1..54269e47ac9a 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -88,7 +88,7 @@ struct tee_param { * @close_session: close a session * @invoke_func: invoke a trusted function * @cancel_req: request cancel of an ongoing invoke or open - * @supp_revc: called for supplicant to get a command + * @supp_recv: called for supplicant to get a command * @supp_send: called for supplicant to send a response * @shm_register: register shared memory buffer in TEE * @shm_unregister: unregister shared memory buffer in TEE -- cgit v1.2.3 From a69bdb283f79949b67632878ef1822badae9299f Mon Sep 17 00:00:00 2001 From: Badhri Jagan Sridharan Date: Mon, 1 Feb 2021 16:30:59 -0800 Subject: usb: typec: tcpm: Add Callback to Usb Communication capable partner The USB Communications Capable bit indicates if port partner is capable of communication over the USB data lines (e.g. D+/- or SS Tx/Rx). Notify the status of the bit to low level drivers to perform chip specific operation. For instance, low level driver enables USB switches on D+/D- lines to set up data path when the bit is set. Refactored from patch initially authored by Kyle Tso Reviewed-by: Heikki Krogerus Reviewed-by: Guenter Roeck Signed-off-by: Badhri Jagan Sridharan Link: https://lore.kernel.org/r/20210202003101.221145-1-badhri@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/tcpm.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/tcpm.h b/include/linux/usb/tcpm.h index 3af99f85e8b9..42fcfbe10590 100644 --- a/include/linux/usb/tcpm.h +++ b/include/linux/usb/tcpm.h @@ -108,6 +108,10 @@ enum tcpm_transmit_type { * is supported by TCPC, set this callback for TCPM to query * whether vbus is at VSAFE0V when needed. * Returns true when vbus is at VSAFE0V, false otherwise. + * @set_partner_usb_comm_capable: + * Optional; The USB Communications Capable bit indicates if port + * partner is capable of communication over the USB data lines + * (e.g. D+/- or SS Tx/Rx). Called to notify the status of the bit. */ struct tcpc_dev { struct fwnode_handle *fwnode; @@ -139,6 +143,7 @@ struct tcpc_dev { int (*set_auto_vbus_discharge_threshold)(struct tcpc_dev *dev, enum typec_pwr_opmode mode, bool pps_active, u32 requested_vbus_voltage); bool (*is_vbus_vsafe0v)(struct tcpc_dev *dev); + void (*set_partner_usb_comm_capable)(struct tcpc_dev *dev, bool enable); }; struct tcpm_port; -- cgit v1.2.3 From 32e9b48d110ef5fae850036eafaf7895a25b37e3 Mon Sep 17 00:00:00 2001 From: Kyle Tso Date: Tue, 2 Feb 2021 17:55:12 +0800 Subject: usb: typec: Return void in typec_partner_set_pd_revision typec_partner_set_pd_revision doesn't need any return value. Fixes: 29b01295a829 ("usb: typec: Add typec_partner_set_pd_revision") Reviewed-by: Heikki Krogerus Reviewed-by: Benson Leung Signed-off-by: Kyle Tso Link: https://lore.kernel.org/r/20210202095512.761214-1-kyletso@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/typec.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h index 4946eca742d5..a94df82ab62f 100644 --- a/include/linux/usb/typec.h +++ b/include/linux/usb/typec.h @@ -126,7 +126,7 @@ struct typec_altmode_desc { enum typec_port_data roles; }; -int typec_partner_set_pd_revision(struct typec_partner *partner, u16 pd_revision); +void typec_partner_set_pd_revision(struct typec_partner *partner, u16 pd_revision); int typec_partner_set_num_altmodes(struct typec_partner *partner, int num_altmodes); struct typec_altmode *typec_partner_register_altmode(struct typec_partner *partner, -- cgit v1.2.3 From bd0c9706430240e3b7e9323361bb25066540d2a8 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Mon, 21 Dec 2020 08:27:15 -0800 Subject: tracing: Add printf attribute to log function Attributing the function allows the compiler to more thoroughly check the use of the function with -Wformat and similar flags. Link: https://lkml.kernel.org/r/20201221162715.3757291-1-trix@redhat.com Signed-off-by: Tom Rix Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/trace.h b/include/linux/trace.h index 886a4ffd9d45..be1e130ed87c 100644 --- a/include/linux/trace.h +++ b/include/linux/trace.h @@ -34,8 +34,9 @@ int unregister_ftrace_export(struct trace_export *export); struct trace_array; void trace_printk_init_buffers(void); +__printf(3, 4) int trace_array_printk(struct trace_array *tr, unsigned long ip, - const char *fmt, ...); + const char *fmt, ...); int trace_array_init_printk(struct trace_array *tr); void trace_array_put(struct trace_array *tr); struct trace_array *trace_array_get_by_name(const char *name); -- cgit v1.2.3 From 36590c50b2d0729952511129916beeea30d31d81 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Mon, 25 Jan 2021 20:45:08 +0100 Subject: tracing: Merge irqflags + preempt counter. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The state of the interrupts (irqflags) and the preemption counter are both passed down to tracing_generic_entry_update(). Only one bit of irqflags is actually required: The on/off state. The complete 32bit of the preemption counter isn't needed. Just whether of the upper bits (softirq, hardirq and NMI) are set and the preemption depth is needed. The irqflags and the preemption counter could be evaluated early and the information stored in an integer `trace_ctx'. tracing_generic_entry_update() would use the upper bits as the TRACE_FLAG_* and the lower 8bit as the disabled-preemption depth (considering that one must be substracted from the counter in one special cases). The actual preemption value is not used except for the tracing record. The `irqflags' variable is mostly used only for the tracing record. An exception here is for instance wakeup_tracer_call() or probe_wakeup_sched_switch() which explicilty disable interrupts and use that `irqflags' to save (and restore) the IRQ state and to record the state. Struct trace_event_buffer has also the `pc' and flags' members which can be replaced with `trace_ctx' since their actual value is not used outside of trace recording. This will reduce tracing_generic_entry_update() to simply assign values to struct trace_entry. The evaluation of the TRACE_FLAG_* bits is moved to _tracing_gen_ctx_flags() which replaces preempt_count() and local_save_flags() invocations. As an example, ftrace_syscall_enter() may invoke: - trace_buffer_lock_reserve() -> … -> tracing_generic_entry_update() - event_trigger_unlock_commit() -> ftrace_trace_stack() -> … -> tracing_generic_entry_update() -> ftrace_trace_userstack() -> … -> tracing_generic_entry_update() In this case the TRACE_FLAG_* bits were evaluated three times. By using the `trace_ctx' they are evaluated once and assigned three times. A build with all tracers enabled on x86-64 with and without the patch: text data bss dec hex filename 21970669 17084168 7639260 46694097 2c87ed1 vmlinux.old 21970293 17084168 7639260 46693721 2c87d59 vmlinux.new text shrank by 379 bytes, data remained constant. Link: https://lkml.kernel.org/r/20210125194511.3924915-2-bigeasy@linutronix.de Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 25 ++++++++++++++++++------- 1 file changed, 18 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index d321fe5ad1a1..091250b0895a 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -148,17 +148,29 @@ enum print_line_t { enum print_line_t trace_handle_return(struct trace_seq *s); -void tracing_generic_entry_update(struct trace_entry *entry, - unsigned short type, - unsigned long flags, - int pc); +static inline void tracing_generic_entry_update(struct trace_entry *entry, + unsigned short type, + unsigned int trace_ctx) +{ + struct task_struct *tsk = current; + + entry->preempt_count = trace_ctx & 0xff; + entry->pid = (tsk) ? tsk->pid : 0; + entry->type = type; + entry->flags = trace_ctx >> 16; +} + +unsigned int tracing_gen_ctx_flags(unsigned long irqflags); +unsigned int tracing_gen_ctx(void); +unsigned int tracing_gen_ctx_dec(void); + struct trace_event_file; struct ring_buffer_event * trace_event_buffer_lock_reserve(struct trace_buffer **current_buffer, struct trace_event_file *trace_file, int type, unsigned long len, - unsigned long flags, int pc); + unsigned int trace_ctx); #define TRACE_RECORD_CMDLINE BIT(0) #define TRACE_RECORD_TGID BIT(1) @@ -232,8 +244,7 @@ struct trace_event_buffer { struct ring_buffer_event *event; struct trace_event_file *trace_file; void *entry; - unsigned long flags; - int pc; + unsigned int trace_ctx; struct pt_regs *regs; }; -- cgit v1.2.3 From 0c02006e6f5b0a3e73499bbf5943d9174c5ed640 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Mon, 25 Jan 2021 20:45:09 +0100 Subject: tracing: Inline tracing_gen_ctx_flags() Inline tracing_gen_ctx_flags(). This allows to have one ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT. This requires to move `trace_flag_type' so tracing_gen_ctx_flags() can use it. Link: https://lkml.kernel.org/r/20210125194511.3924915-3-bigeasy@linutronix.de Suggested-by: Steven Rostedt Link: https://lkml.kernel.org/r/20210125140323.6b1ff20c@gandalf.local.home Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 54 +++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 51 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 091250b0895a..67ae708de40d 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -160,9 +160,57 @@ static inline void tracing_generic_entry_update(struct trace_entry *entry, entry->flags = trace_ctx >> 16; } -unsigned int tracing_gen_ctx_flags(unsigned long irqflags); -unsigned int tracing_gen_ctx(void); -unsigned int tracing_gen_ctx_dec(void); +unsigned int tracing_gen_ctx_irq_test(unsigned int irqs_status); + +enum trace_flag_type { + TRACE_FLAG_IRQS_OFF = 0x01, + TRACE_FLAG_IRQS_NOSUPPORT = 0x02, + TRACE_FLAG_NEED_RESCHED = 0x04, + TRACE_FLAG_HARDIRQ = 0x08, + TRACE_FLAG_SOFTIRQ = 0x10, + TRACE_FLAG_PREEMPT_RESCHED = 0x20, + TRACE_FLAG_NMI = 0x40, +}; + +#ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT +static inline unsigned int tracing_gen_ctx_flags(unsigned long irqflags) +{ + unsigned int irq_status = irqs_disabled_flags(irqflags) ? + TRACE_FLAG_IRQS_OFF : 0; + return tracing_gen_ctx_irq_test(irq_status); +} +static inline unsigned int tracing_gen_ctx(void) +{ + unsigned long irqflags; + + local_save_flags(irqflags); + return tracing_gen_ctx_flags(irqflags); +} +#else + +static inline unsigned int tracing_gen_ctx_flags(unsigned long irqflags) +{ + return tracing_gen_ctx_irq_test(TRACE_FLAG_IRQS_NOSUPPORT); +} +static inline unsigned int tracing_gen_ctx(void) +{ + return tracing_gen_ctx_irq_test(TRACE_FLAG_IRQS_NOSUPPORT); +} +#endif + +static inline unsigned int tracing_gen_ctx_dec(void) +{ + unsigned int trace_ctx; + + trace_ctx = tracing_gen_ctx(); + /* + * Subtract one from the preeption counter if preemption is enabled, + * see trace_event_buffer_reserve()for details. + */ + if (IS_ENABLED(CONFIG_PREEMPTION)) + trace_ctx--; + return trace_ctx; +} struct trace_event_file; -- cgit v1.2.3 From 5817708493bec547914d23dcdd064919ac409f33 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Mon, 25 Jan 2021 20:45:11 +0100 Subject: tracing: Remove NULL check from current in tracing_generic_entry_update(). I can't imagine when or why `current' would return a NULL pointer. This check was added in commit 72829bc3d63cd ("ftrace: move enums to ftrace.h and make helper function global") but it doesn't give me hint why it was needed. Assume `current' never returns a NULL pointer and remove the check. Link: https://lkml.kernel.org/r/20210125194511.3924915-5-bigeasy@linutronix.de Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 67ae708de40d..5d1eeac4bfbe 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -152,10 +152,8 @@ static inline void tracing_generic_entry_update(struct trace_entry *entry, unsigned short type, unsigned int trace_ctx) { - struct task_struct *tsk = current; - entry->preempt_count = trace_ctx & 0xff; - entry->pid = (tsk) ? tsk->pid : 0; + entry->pid = current->pid; entry->type = type; entry->flags = trace_ctx >> 16; } -- cgit v1.2.3 From 0e1d6f55a12e47942ce207dfb93e23049b454c9e Mon Sep 17 00:00:00 2001 From: Kyle Tso Date: Wed, 3 Feb 2021 00:17:27 +0800 Subject: usb: pd: Update VDO definitions "PD Spec Revision 3.0 Version 2.0 + ECNs 2020-12-10" introduces several changes regarding the ID Header VDO and the Product Type VDOs. Signed-off-by: Kyle Tso Reviewed-by: Heikki Krogerus Link: https://lore.kernel.org/r/20210202161733.932215-3-kyletso@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/pd_vdo.h | 308 ++++++++++++++++++++++++++++++++++----------- 1 file changed, 238 insertions(+), 70 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/pd_vdo.h b/include/linux/usb/pd_vdo.h index 8c08eeb9a74b..e9b6822c54c2 100644 --- a/include/linux/usb/pd_vdo.h +++ b/include/linux/usb/pd_vdo.h @@ -103,34 +103,46 @@ * -------------------- * <31> :: data capable as a USB host * <30> :: data capable as a USB device - * <29:27> :: product type (UFP / Cable) + * <29:27> :: product type (UFP / Cable / VPD) * <26> :: modal operation supported (1b == yes) - * <25:16> :: product type (DFP) + * <25:23> :: product type (DFP) (SVDM version 2.0+ only; set to zero in version 1.0) + * <22:21> :: connector type (SVDM version 2.0+ only; set to zero in version 1.0) + * <20:16> :: Reserved, Shall be set to zero * <15:0> :: USB-IF assigned VID for this cable vendor */ -#define IDH_PTYPE_UNDEF 0 +/* SOP Product Type (UFP) */ +#define IDH_PTYPE_NOT_UFP 0 #define IDH_PTYPE_HUB 1 #define IDH_PTYPE_PERIPH 2 #define IDH_PTYPE_PSD 3 #define IDH_PTYPE_AMA 5 +/* SOP' Product Type (Cable Plug / VPD) */ +#define IDH_PTYPE_NOT_CABLE 0 #define IDH_PTYPE_PCABLE 3 #define IDH_PTYPE_ACABLE 4 +#define IDH_PTYPE_VPD 6 -#define IDH_PTYPE_DFP_UNDEF 0 +/* SOP Product Type (DFP) */ +#define IDH_PTYPE_NOT_DFP 0 #define IDH_PTYPE_DFP_HUB 1 #define IDH_PTYPE_DFP_HOST 2 #define IDH_PTYPE_DFP_PB 3 -#define IDH_PTYPE_DFP_AMC 4 -#define VDO_IDH(usbh, usbd, ptype, is_modal, vid) \ - ((usbh) << 31 | (usbd) << 30 | ((ptype) & 0x7) << 27 \ - | (is_modal) << 26 | ((vid) & 0xffff)) +/* ID Header Mask */ +#define IDH_DFP_MASK GENMASK(25, 23) +#define IDH_CONN_MASK GENMASK(22, 21) + +#define VDO_IDH(usbh, usbd, ufp_cable, is_modal, dfp, conn, vid) \ + ((usbh) << 31 | (usbd) << 30 | ((ufp_cable) & 0x7) << 27 \ + | (is_modal) << 26 | ((dfp) & 0x7) << 23 | ((conn) & 0x3) << 21 \ + | ((vid) & 0xffff)) #define PD_IDH_PTYPE(vdo) (((vdo) >> 27) & 0x7) #define PD_IDH_VID(vdo) ((vdo) & 0xffff) #define PD_IDH_MODAL_SUPP(vdo) ((vdo) & (1 << 26)) #define PD_IDH_DFP_PTYPE(vdo) (((vdo) >> 23) & 0x7) +#define PD_IDH_CONN_TYPE(vdo) (((vdo) >> 21) & 0x3) /* * Cert Stat VDO @@ -138,6 +150,7 @@ * <31:0> : USB-IF assigned XID for this cable */ #define PD_CSTAT_XID(vdo) (vdo) +#define VDO_CERT(xid) ((xid) & 0xffffffff) /* * Product VDO @@ -149,112 +162,267 @@ #define PD_PRODUCT_PID(vdo) (((vdo) >> 16) & 0xffff) /* - * UFP VDO1 + * UFP VDO (PD Revision 3.0+ only) * -------- * <31:29> :: UFP VDO version * <28> :: Reserved * <27:24> :: Device capability - * <23:6> :: Reserved + * <23:22> :: Connector type (10b == receptacle, 11b == captive plug) + * <21:11> :: Reserved + * <10:8> :: Vconn power (AMA only) + * <7> :: Vconn required (AMA only, 0b == no, 1b == yes) + * <6> :: Vbus required (AMA only, 0b == yes, 1b == no) * <5:3> :: Alternate modes * <2:0> :: USB highest speed */ -#define PD_VDO1_UFP_DEVCAP(vdo) (((vdo) & GENMASK(27, 24)) >> 24) +#define PD_VDO_UFP_DEVCAP(vdo) (((vdo) & GENMASK(27, 24)) >> 24) + +/* UFP VDO Version */ +#define UFP_VDO_VER1_2 2 +/* Device Capability */ #define DEV_USB2_CAPABLE BIT(0) #define DEV_USB2_BILLBOARD BIT(1) #define DEV_USB3_CAPABLE BIT(2) #define DEV_USB4_CAPABLE BIT(3) +/* Connector Type */ +#define UFP_RECEPTACLE 2 +#define UFP_CAPTIVE 3 + +/* Vconn Power (AMA only, set to AMA_VCONN_NOT_REQ if Vconn is not required) */ +#define AMA_VCONN_PWR_1W 0 +#define AMA_VCONN_PWR_1W5 1 +#define AMA_VCONN_PWR_2W 2 +#define AMA_VCONN_PWR_3W 3 +#define AMA_VCONN_PWR_4W 4 +#define AMA_VCONN_PWR_5W 5 +#define AMA_VCONN_PWR_6W 6 + +/* Vconn Required (AMA only) */ +#define AMA_VCONN_NOT_REQ 0 +#define AMA_VCONN_REQ 1 + +/* Vbus Required (AMA only) */ +#define AMA_VBUS_REQ 0 +#define AMA_VBUS_NOT_REQ 1 + +/* Alternate Modes */ +#define UFP_ALTMODE_NOT_SUPP 0 +#define UFP_ALTMODE_TBT3 BIT(0) +#define UFP_ALTMODE_RECFG BIT(1) +#define UFP_ALTMODE_NO_RECFG BIT(2) + +/* USB Highest Speed */ +#define UFP_USB2_ONLY 0 +#define UFP_USB32_GEN1 1 +#define UFP_USB32_4_GEN2 2 +#define UFP_USB4_GEN3 3 + +#define VDO_UFP(ver, cap, conn, vcpwr, vcr, vbr, alt, spd) \ + (((ver) & 0x7) << 29 | ((cap) & 0xf) << 24 | ((conn) & 0x3) << 22 \ + | ((vcpwr) & 0x7) << 8 | (vcr) << 7 | (vbr) << 6 | ((alt) & 0x7) << 3 \ + | ((spd) & 0x7)) + /* - * DFP VDO + * DFP VDO (PD Revision 3.0+ only) * -------- * <31:29> :: DFP VDO version * <28:27> :: Reserved * <26:24> :: Host capability - * <23:5> :: Reserved + * <23:22> :: Connector type (10b == receptacle, 11b == captive plug) + * <21:5> :: Reserved * <4:0> :: Port number */ #define PD_VDO_DFP_HOSTCAP(vdo) (((vdo) & GENMASK(26, 24)) >> 24) +#define DFP_VDO_VER1_1 1 #define HOST_USB2_CAPABLE BIT(0) #define HOST_USB3_CAPABLE BIT(1) #define HOST_USB4_CAPABLE BIT(2) +#define DFP_RECEPTACLE 2 +#define DFP_CAPTIVE 3 + +#define VDO_DFP(ver, cap, conn, pnum) \ + (((ver) & 0x7) << 29 | ((cap) & 0x7) << 24 | ((conn) & 0x3) << 22 \ + | ((pnum) & 0x1f)) /* - * Cable VDO + * Passive Cable VDO * --------- * <31:28> :: Cable HW version * <27:24> :: Cable FW version - * <23:20> :: Reserved, Shall be set to zero - * <19:18> :: type-C to Type-A/B/C/Captive (00b == A, 01 == B, 10 == C, 11 == Captive) - * <17> :: Type-C to Plug/Receptacle (0b == plug, 1b == receptacle) + * <23:21> :: VDO version + * <20> :: Reserved, Shall be set to zero + * <19:18> :: Type-C to Type-C/Captive (10b == C, 11b == Captive) + * <17> :: Reserved, Shall be set to zero * <16:13> :: cable latency (0001 == <10ns(~1m length)) - * <12:11> :: cable termination type (11b == both ends active VCONN req) - * <10> :: SSTX1 Directionality support (0b == fixed, 1b == cfgable) - * <9> :: SSTX2 Directionality support - * <8> :: SSRX1 Directionality support - * <7> :: SSRX2 Directionality support - * <6:5> :: Vbus current handling capability + * <12:11> :: cable termination type (10b == Vconn not req, 01b == Vconn req) + * <10:9> :: Maximum Vbus voltage (00b == 20V, 01b == 30V, 10b == 40V, 11b == 50V) + * <8:7> :: Reserved, Shall be set to zero + * <6:5> :: Vbus current handling capability (01b == 3A, 10b == 5A) + * <4:3> :: Reserved, Shall be set to zero + * <2:0> :: USB highest speed + * + * Active Cable VDO 1 + * --------- + * <31:28> :: Cable HW version + * <27:24> :: Cable FW version + * <23:21> :: VDO version + * <20> :: Reserved, Shall be set to zero + * <19:18> :: Connector type (10b == C, 11b == Captive) + * <17> :: Reserved, Shall be set to zero + * <16:13> :: cable latency (0001 == <10ns(~1m length)) + * <12:11> :: cable termination type (10b == one end active, 11b == both ends active VCONN req) + * <10:9> :: Maximum Vbus voltage (00b == 20V, 01b == 30V, 10b == 40V, 11b == 50V) + * <8> :: SBU supported (0b == supported, 1b == not supported) + * <7> :: SBU type (0b == passive, 1b == active) + * <6:5> :: Vbus current handling capability (01b == 3A, 10b == 5A) * <4> :: Vbus through cable (0b == no, 1b == yes) * <3> :: SOP" controller present? (0b == no, 1b == yes) - * <2:0> :: USB SS Signaling support + * <2:0> :: USB highest speed */ -#define CABLE_ATYPE 0 -#define CABLE_BTYPE 1 +/* Cable VDO Version */ +#define CABLE_VDO_VER1_0 0 +#define CABLE_VDO_VER1_3 3 + +/* Connector Type */ #define CABLE_CTYPE 2 #define CABLE_CAPTIVE 3 -#define CABLE_PLUG 0 -#define CABLE_RECEPTACLE 1 -#define CABLE_CURR_1A5 0 + +/* Cable Latency */ +#define CABLE_LATENCY_1M 1 +#define CABLE_LATENCY_2M 2 +#define CABLE_LATENCY_3M 3 +#define CABLE_LATENCY_4M 4 +#define CABLE_LATENCY_5M 5 +#define CABLE_LATENCY_6M 6 +#define CABLE_LATENCY_7M 7 +#define CABLE_LATENCY_7M_PLUS 8 + +/* Cable Termination Type */ +#define PCABLE_VCONN_NOT_REQ 0 +#define PCABLE_VCONN_REQ 1 +#define ACABLE_ONE_END 2 +#define ACABLE_BOTH_END 3 + +/* Maximum Vbus Voltage */ +#define CABLE_MAX_VBUS_20V 0 +#define CABLE_MAX_VBUS_30V 1 +#define CABLE_MAX_VBUS_40V 2 +#define CABLE_MAX_VBUS_50V 3 + +/* Active Cable SBU Supported/Type */ +#define ACABLE_SBU_SUPP 0 +#define ACABLE_SBU_NOT_SUPP 1 +#define ACABLE_SBU_PASSIVE 0 +#define ACABLE_SBU_ACTIVE 1 + +/* Vbus Current Handling Capability */ +#define CABLE_CURR_DEF 0 #define CABLE_CURR_3A 1 #define CABLE_CURR_5A 2 -#define CABLE_USBSS_U2_ONLY 0 -#define CABLE_USBSS_U31_GEN1 1 -#define CABLE_USBSS_U31_GEN2 2 -#define VDO_CABLE(hw, fw, cbl, gdr, lat, term, tx1d, tx2d, rx1d, rx2d, cur,\ - vps, sopp, usbss) \ - (((hw) & 0x7) << 28 | ((fw) & 0x7) << 24 | ((cbl) & 0x3) << 18 \ - | (gdr) << 17 | ((lat) & 0x7) << 13 | ((term) & 0x3) << 11 \ - | (tx1d) << 10 | (tx2d) << 9 | (rx1d) << 8 | (rx2d) << 7 \ - | ((cur) & 0x3) << 5 | (vps) << 4 | (sopp) << 3 \ - | ((usbss) & 0x7)) + +/* USB Highest Speed */ +#define CABLE_USB2_ONLY 0 +#define CABLE_USB32_GEN1 1 +#define CABLE_USB32_4_GEN2 2 +#define CABLE_USB4_GEN3 3 + +#define VDO_PCABLE(hw, fw, ver, conn, lat, term, vbm, cur, spd) \ + (((hw) & 0xf) << 28 | ((fw) & 0xf) << 24 | ((ver) & 0x7) << 21 \ + | ((conn) & 0x3) << 18 | ((lat) & 0xf) << 13 | ((term) & 0x3) << 11 \ + | ((vbm) & 0x3) << 9 | ((cur) & 0x3) << 5 | ((spd) & 0x7)) +#define VDO_ACABLE1(hw, fw, ver, conn, lat, term, vbm, sbu, sbut, cur, vbt, sopp, spd) \ + (((hw) & 0xf) << 28 | ((fw) & 0xf) << 24 | ((ver) & 0x7) << 21 \ + | ((conn) & 0x3) << 18 | ((lat) & 0xf) << 13 | ((term) & 0x3) << 11 \ + | ((vbm) & 0x3) << 9 | (sbu) << 8 | (sbut) << 7 | ((cur) & 0x3) << 5 \ + | (vbt) << 4 | (sopp) << 3 | ((spd) & 0x7)) + #define VDO_TYPEC_CABLE_TYPE(vdo) (((vdo) >> 18) & 0x3) /* - * AMA VDO + * Active Cable VDO 2 * --------- - * <31:28> :: Cable HW version - * <27:24> :: Cable FW version - * <23:12> :: Reserved, Shall be set to zero - * <11> :: SSTX1 Directionality support (0b == fixed, 1b == cfgable) - * <10> :: SSTX2 Directionality support - * <9> :: SSRX1 Directionality support - * <8> :: SSRX2 Directionality support - * <7:5> :: Vconn power - * <4> :: Vconn power required - * <3> :: Vbus power required - * <2:0> :: USB SS Signaling support + * <31:24> :: Maximum operating temperature + * <23:16> :: Shutdown temperature + * <15> :: Reserved, Shall be set to zero + * <14:12> :: U3/CLd power + * <11> :: U3 to U0 transition mode (0b == direct, 1b == through U3S) + * <10> :: Physical connection (0b == copper, 1b == optical) + * <9> :: Active element (0b == redriver, 1b == retimer) + * <8> :: USB4 supported (0b == yes, 1b == no) + * <7:6> :: USB2 hub hops consumed + * <5> :: USB2 supported (0b == yes, 1b == no) + * <4> :: USB3.2 supported (0b == yes, 1b == no) + * <3> :: USB lanes supported (0b == one lane, 1b == two lanes) + * <2> :: Optically isolated active cable (0b == no, 1b == yes) + * <1> :: Reserved, Shall be set to zero + * <0> :: USB gen (0b == gen1, 1b == gen2+) */ -#define VDO_AMA(hw, fw, tx1d, tx2d, rx1d, rx2d, vcpwr, vcr, vbr, usbss) \ - (((hw) & 0x7) << 28 | ((fw) & 0x7) << 24 \ - | (tx1d) << 11 | (tx2d) << 10 | (rx1d) << 9 | (rx2d) << 8 \ - | ((vcpwr) & 0x7) << 5 | (vcr) << 4 | (vbr) << 3 \ - | ((usbss) & 0x7)) - -#define PD_VDO_AMA_VCONN_REQ(vdo) (((vdo) >> 4) & 1) -#define PD_VDO_AMA_VBUS_REQ(vdo) (((vdo) >> 3) & 1) +/* U3/CLd Power*/ +#define ACAB2_U3_CLD_10MW_PLUS 0 +#define ACAB2_U3_CLD_10MW 1 +#define ACAB2_U3_CLD_5MW 2 +#define ACAB2_U3_CLD_1MW 3 +#define ACAB2_U3_CLD_500UW 4 +#define ACAB2_U3_CLD_200UW 5 +#define ACAB2_U3_CLD_50UW 6 + +/* Other Active Cable VDO 2 Fields */ +#define ACAB2_U3U0_DIRECT 0 +#define ACAB2_U3U0_U3S 1 +#define ACAB2_PHY_COPPER 0 +#define ACAB2_PHY_OPTICAL 1 +#define ACAB2_REDRIVER 0 +#define ACAB2_RETIMER 1 +#define ACAB2_USB4_SUPP 0 +#define ACAB2_USB4_NOT_SUPP 1 +#define ACAB2_USB2_SUPP 0 +#define ACAB2_USB2_NOT_SUPP 1 +#define ACAB2_USB32_SUPP 0 +#define ACAB2_USB32_NOT_SUPP 1 +#define ACAB2_LANES_ONE 0 +#define ACAB2_LANES_TWO 1 +#define ACAB2_OPT_ISO_NO 0 +#define ACAB2_OPT_ISO_YES 1 +#define ACAB2_GEN_1 0 +#define ACAB2_GEN_2_PLUS 1 + +#define VDO_ACABLE2(mtemp, stemp, u3p, trans, phy, ele, u4, hops, u2, u32, lane, iso, gen) \ + (((mtemp) & 0xff) << 24 | ((stemp) & 0xff) << 16 | ((u3p) & 0x7) << 12 \ + | (trans) << 11 | (phy) << 10 | (ele) << 9 | (u4) << 8 \ + | ((hops) & 0x3) << 6 | (u2) << 5 | (u32) << 4 | (lane) << 3 \ + | (iso) << 2 | (gen)) -#define AMA_VCONN_PWR_1W 0 -#define AMA_VCONN_PWR_1W5 1 -#define AMA_VCONN_PWR_2W 2 -#define AMA_VCONN_PWR_3W 3 -#define AMA_VCONN_PWR_4W 4 -#define AMA_VCONN_PWR_5W 5 -#define AMA_VCONN_PWR_6W 6 -#define AMA_USBSS_U2_ONLY 0 -#define AMA_USBSS_U31_GEN1 1 -#define AMA_USBSS_U31_GEN2 2 -#define AMA_USBSS_BBONLY 3 +/* + * VPD VDO + * --------- + * <31:28> :: HW version + * <27:24> :: FW version + * <23:21> :: VDO version + * <20:17> :: Reserved, Shall be set to zero + * <16:15> :: Maximum Vbus voltage (00b == 20V, 01b == 30V, 10b == 40V, 11b == 50V) + * <14> :: Charge through current support (0b == 3A, 1b == 5A) + * <13> :: Reserved, Shall be set to zero + * <12:7> :: Vbus impedance + * <6:1> :: Ground impedance + * <0> :: Charge through support (0b == no, 1b == yes) + */ +#define VPD_VDO_VER1_0 0 +#define VPD_MAX_VBUS_20V 0 +#define VPD_MAX_VBUS_30V 1 +#define VPD_MAX_VBUS_40V 2 +#define VPD_MAX_VBUS_50V 3 +#define VPDCT_CURR_3A 0 +#define VPDCT_CURR_5A 1 +#define VPDCT_NOT_SUPP 0 +#define VPDCT_SUPP 1 + +#define VDO_VPD(hw, fw, ver, vbm, curr, vbi, gi, ct) \ + (((hw) & 0xf) << 28 | ((fw) & 0xf) << 24 | ((ver) & 0x7) << 21 \ + | ((vbm) & 0x3) << 15 | (curr) << 14 | ((vbi) & 0x3f) << 7 \ + | ((gi) & 0x3f) << 1 | (ct)) /* * SVDM Discover SVIDs request -> response -- cgit v1.2.3 From 01531ac354051667f80d23bb85bf2643ae11260a Mon Sep 17 00:00:00 2001 From: BingJing Chang Date: Fri, 29 Jan 2021 12:52:42 +0800 Subject: parser: add unsigned int parser Will be used by fs parsing options Link: https://lore.kernel.org/r/20210129045242.10268-1-bingjingc@synology.com Reviewed-by: Robbie Ko Reviewed-by: Chung-Chiang Cheng Signed-off-by: BingJing Chang Signed-off-by: Jan Kara --- include/linux/parser.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/parser.h b/include/linux/parser.h index 89e2b23fb888..dd79f45a37b8 100644 --- a/include/linux/parser.h +++ b/include/linux/parser.h @@ -29,6 +29,7 @@ typedef struct { int match_token(char *, const match_table_t table, substring_t args[]); int match_int(substring_t *, int *result); +int match_uint(substring_t *s, unsigned int *result); int match_u64(substring_t *, u64 *result); int match_octal(substring_t *, int *result); int match_hex(substring_t *, int *result); -- cgit v1.2.3 From 4f4e54366eae20d5867864001db57c5d90693d8c Mon Sep 17 00:00:00 2001 From: Emil Renner Berthing Date: Sun, 31 Jan 2021 00:46:37 +0100 Subject: net: usb: cdc_ncm: use new API for bh tasklet This converts the driver to use the new tasklet API introduced in commit 12cc923f1ccc ("tasklet: Introduce new initialization API") It is unfortunate that we need to add a pointer to the driver context to get back to the usbnet device, but the space will be reclaimed once there are no more users of the old API left and we can remove the data value and flag from the tasklet struct. Signed-off-by: Emil Renner Berthing Link: https://lore.kernel.org/r/20210130234637.26505-1-kernel@esmil.dk Signed-off-by: Jakub Kicinski --- include/linux/usb/cdc_ncm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h index 0ce4377545f8..f7cb3ddce7fb 100644 --- a/include/linux/usb/cdc_ncm.h +++ b/include/linux/usb/cdc_ncm.h @@ -98,6 +98,8 @@ struct cdc_ncm_ctx { struct hrtimer tx_timer; struct tasklet_struct bh; + struct usbnet *dev; + const struct usb_cdc_ncm_desc *func_desc; const struct usb_cdc_mbim_desc *mbim_desc; const struct usb_cdc_mbim_extended_desc *mbim_extended_desc; -- cgit v1.2.3 From 012ce4dd3102a0f4d80167de343e9d44b257c1b8 Mon Sep 17 00:00:00 2001 From: Danielle Ratson Date: Tue, 2 Feb 2021 20:06:06 +0200 Subject: ethtool: Extend link modes settings uAPI with lanes Currently, when auto negotiation is on, the user can advertise all the linkmodes which correspond to a specific speed, but does not have a similar selector for the number of lanes. This is significant when a specific speed can be achieved using different number of lanes. For example, 2x50 or 4x25. Add 'ETHTOOL_A_LINKMODES_LANES' attribute and expand 'struct ethtool_link_settings' with lanes field in order to implement a new lanes-selector that will enable the user to advertise a specific number of lanes as well. When auto negotiation is off, lanes parameter can be forced only if the driver supports it. Add a capability bit in 'struct ethtool_ops' that allows ethtool know if the driver can handle the lanes parameter when auto negotiation is off, so if it does not, an error message will be returned when trying to set lanes. Example: $ ethtool -s swp1 lanes 4 $ ethtool swp1 Settings for swp1: Supported ports: [ FIBRE ] Supported link modes: 1000baseKX/Full 10000baseKR/Full 40000baseCR4/Full 40000baseSR4/Full 40000baseLR4/Full 25000baseCR/Full 25000baseSR/Full 50000baseCR2/Full 100000baseSR4/Full 100000baseCR4/Full Supported pause frame use: Symmetric Receive-only Supports auto-negotiation: Yes Supported FEC modes: Not reported Advertised link modes: 40000baseCR4/Full 40000baseSR4/Full 40000baseLR4/Full 100000baseSR4/Full 100000baseCR4/Full Advertised pause frame use: No Advertised auto-negotiation: Yes Advertised FEC modes: Not reported Speed: Unknown! Duplex: Unknown! (255) Auto-negotiation: on Port: Direct Attach Copper PHYAD: 0 Transceiver: internal Link detected: no Signed-off-by: Danielle Ratson Signed-off-by: Jakub Kicinski --- include/linux/ethtool.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index e3da25b51ae4..1ab13c5dfb2f 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -128,6 +128,7 @@ struct ethtool_link_ksettings { __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising); __ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertising); } link_modes; + u32 lanes; }; /** @@ -265,6 +266,8 @@ struct ethtool_pause_stats { /** * struct ethtool_ops - optional netdev operations + * @cap_link_lanes_supported: indicates if the driver supports lanes + * parameter. * @supported_coalesce_params: supported types of interrupt coalescing. * @get_drvinfo: Report driver/device information. Should only set the * @driver, @version, @fw_version and @bus_info fields. If not @@ -420,6 +423,7 @@ struct ethtool_pause_stats { * of the generic netdev features interface. */ struct ethtool_ops { + u32 cap_link_lanes_supported:1; u32 supported_coalesce_params; void (*get_drvinfo)(struct net_device *, struct ethtool_drvinfo *); int (*get_regs_len)(struct net_device *); -- cgit v1.2.3 From c8907043c6ac9ed58e6c1a76f2824be714b42228 Mon Sep 17 00:00:00 2001 From: Danielle Ratson Date: Tue, 2 Feb 2021 20:06:07 +0200 Subject: ethtool: Get link mode in use instead of speed and duplex parameters Currently, when user space queries the link's parameters, as speed and duplex, each parameter is passed from the driver to ethtool. Instead, get the link mode bit in use, and derive each of the parameters from it in ethtool. Signed-off-by: Danielle Ratson Signed-off-by: Jakub Kicinski --- include/linux/ethtool.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 1ab13c5dfb2f..ec4cd3921c67 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -129,6 +129,7 @@ struct ethtool_link_ksettings { __ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertising); } link_modes; u32 lanes; + enum ethtool_link_mode_bit_indices link_mode; }; /** -- cgit v1.2.3 From 2a1673f0f1de78b146bfdbe8c8a773c4a0499790 Mon Sep 17 00:00:00 2001 From: Kyle Tso Date: Thu, 4 Feb 2021 08:50:36 +0800 Subject: usb: pd: Reland VDO definitions of PD2.0 Reland VDO definitions of PD Revision 2.0 as they are still used in PD2.0 products. Fixes: 0e1d6f55a12e ("usb: pd: Update VDO definitions") Signed-off-by: Kyle Tso Link: https://lore.kernel.org/r/20210204005036.1555294-1-kyletso@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/pd_vdo.h | 69 ++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 66 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/pd_vdo.h b/include/linux/usb/pd_vdo.h index e9b6822c54c2..5de7f550f93e 100644 --- a/include/linux/usb/pd_vdo.h +++ b/include/linux/usb/pd_vdo.h @@ -110,6 +110,10 @@ * <20:16> :: Reserved, Shall be set to zero * <15:0> :: USB-IF assigned VID for this cable vendor */ + +/* PD Rev2.0 definition */ +#define IDH_PTYPE_UNDEF 0 + /* SOP Product Type (UFP) */ #define IDH_PTYPE_NOT_UFP 0 #define IDH_PTYPE_HUB 1 @@ -248,7 +252,25 @@ | ((pnum) & 0x1f)) /* - * Passive Cable VDO + * Cable VDO (for both Passive and Active Cable VDO in PD Rev2.0) + * --------- + * <31:28> :: Cable HW version + * <27:24> :: Cable FW version + * <23:20> :: Reserved, Shall be set to zero + * <19:18> :: type-C to Type-A/B/C/Captive (00b == A, 01 == B, 10 == C, 11 == Captive) + * <17> :: Reserved, Shall be set to zero + * <16:13> :: cable latency (0001 == <10ns(~1m length)) + * <12:11> :: cable termination type (11b == both ends active VCONN req) + * <10> :: SSTX1 Directionality support (0b == fixed, 1b == cfgable) + * <9> :: SSTX2 Directionality support + * <8> :: SSRX1 Directionality support + * <7> :: SSRX2 Directionality support + * <6:5> :: Vbus current handling capability (01b == 3A, 10b == 5A) + * <4> :: Vbus through cable (0b == no, 1b == yes) + * <3> :: SOP" controller present? (0b == no, 1b == yes) + * <2:0> :: USB SS Signaling support + * + * Passive Cable VDO (PD Rev3.0+) * --------- * <31:28> :: Cable HW version * <27:24> :: Cable FW version @@ -264,7 +286,7 @@ * <4:3> :: Reserved, Shall be set to zero * <2:0> :: USB highest speed * - * Active Cable VDO 1 + * Active Cable VDO 1 (PD Rev3.0+) * --------- * <31:28> :: Cable HW version * <27:24> :: Cable FW version @@ -286,7 +308,9 @@ #define CABLE_VDO_VER1_0 0 #define CABLE_VDO_VER1_3 3 -/* Connector Type */ +/* Connector Type (_ATYPE and _BTYPE are for PD Rev2.0 only) */ +#define CABLE_ATYPE 0 +#define CABLE_BTYPE 1 #define CABLE_CTYPE 2 #define CABLE_CAPTIVE 3 @@ -323,12 +347,22 @@ #define CABLE_CURR_3A 1 #define CABLE_CURR_5A 2 +/* USB SuperSpeed Signaling Support (PD Rev2.0) */ +#define CABLE_USBSS_U2_ONLY 0 +#define CABLE_USBSS_U31_GEN1 1 +#define CABLE_USBSS_U31_GEN2 2 + /* USB Highest Speed */ #define CABLE_USB2_ONLY 0 #define CABLE_USB32_GEN1 1 #define CABLE_USB32_4_GEN2 2 #define CABLE_USB4_GEN3 3 +#define VDO_CABLE(hw, fw, cbl, lat, term, tx1d, tx2d, rx1d, rx2d, cur, vps, sopp, usbss) \ + (((hw) & 0x7) << 28 | ((fw) & 0x7) << 24 | ((cbl) & 0x3) << 18 \ + | ((lat) & 0x7) << 13 | ((term) & 0x3) << 11 | (tx1d) << 10 \ + | (tx2d) << 9 | (rx1d) << 8 | (rx2d) << 7 | ((cur) & 0x3) << 5 \ + | (vps) << 4 | (sopp) << 3 | ((usbss) & 0x7)) #define VDO_PCABLE(hw, fw, ver, conn, lat, term, vbm, cur, spd) \ (((hw) & 0xf) << 28 | ((fw) & 0xf) << 24 | ((ver) & 0x7) << 21 \ | ((conn) & 0x3) << 18 | ((lat) & 0xf) << 13 | ((term) & 0x3) << 11 \ @@ -395,6 +429,35 @@ | ((hops) & 0x3) << 6 | (u2) << 5 | (u32) << 4 | (lane) << 3 \ | (iso) << 2 | (gen)) +/* + * AMA VDO (PD Rev2.0) + * --------- + * <31:28> :: Cable HW version + * <27:24> :: Cable FW version + * <23:12> :: Reserved, Shall be set to zero + * <11> :: SSTX1 Directionality support (0b == fixed, 1b == cfgable) + * <10> :: SSTX2 Directionality support + * <9> :: SSRX1 Directionality support + * <8> :: SSRX2 Directionality support + * <7:5> :: Vconn power + * <4> :: Vconn power required + * <3> :: Vbus power required + * <2:0> :: USB SS Signaling support + */ +#define VDO_AMA(hw, fw, tx1d, tx2d, rx1d, rx2d, vcpwr, vcr, vbr, usbss) \ + (((hw) & 0x7) << 28 | ((fw) & 0x7) << 24 \ + | (tx1d) << 11 | (tx2d) << 10 | (rx1d) << 9 | (rx2d) << 8 \ + | ((vcpwr) & 0x7) << 5 | (vcr) << 4 | (vbr) << 3 \ + | ((usbss) & 0x7)) + +#define PD_VDO_AMA_VCONN_REQ(vdo) (((vdo) >> 4) & 1) +#define PD_VDO_AMA_VBUS_REQ(vdo) (((vdo) >> 3) & 1) + +#define AMA_USBSS_U2_ONLY 0 +#define AMA_USBSS_U31_GEN1 1 +#define AMA_USBSS_U31_GEN2 2 +#define AMA_USBSS_BBONLY 3 + /* * VPD VDO * --------- -- cgit v1.2.3 From 3cd542e6e6afb6fa6c34d4094d498f42e22110f5 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Thu, 3 Sep 2020 13:13:21 +0300 Subject: thunderbolt: Add support for PCIe tunneling disabled (SL5) Recent Intel Thunderbolt firmware connection manager has support for another security level, SL5, that disables PCIe tunneling. This option can be turned on from the BIOS. When this is set the driver exposes a new security level "nopcie" to the userspace and hides the authorized attribute under connected devices. While there we also hide it when "dponly" security level is enabled since it is not really usable in that case anyway. Signed-off-by: Mika Westerberg Acked-by: Yehezkel Bernat --- include/linux/thunderbolt.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h index 034dccf93955..659a0a810fa1 100644 --- a/include/linux/thunderbolt.h +++ b/include/linux/thunderbolt.h @@ -45,6 +45,8 @@ enum tb_cfg_pkg_type { * @TB_SECURITY_USBONLY: Only tunnel USB controller of the connected * Thunderbolt dock (and Display Port). All PCIe * links downstream of the dock are removed. + * @TB_SECURITY_NOPCIE: For USB4 systems this level is used when the + * PCIe tunneling is disabled from the BIOS. */ enum tb_security_level { TB_SECURITY_NONE, @@ -52,6 +54,7 @@ enum tb_security_level { TB_SECURITY_SECURE, TB_SECURITY_DPONLY, TB_SECURITY_USBONLY, + TB_SECURITY_NOPCIE, }; /** -- cgit v1.2.3 From 5a6a2c0f0f43676df27632d657a3f18b151a7ef8 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Tue, 18 Feb 2020 16:02:45 +0200 Subject: ACPI: Add support for native USB4 control _OSC ACPI 6.4 introduced a new _OSC capability that is used negotiate native connection manager support. Connection manager is the entity that is responsible for tunneling over the USB4 fabric. If the platform rejects the native access then firmware based connection manager is used. The new _OSC also includes a set of bits that can be used to disable certain tunnel types such as PCIe for security reasons for instance. This implements the new USB4 _OSC so that we try to negotiate native USB4 support if the Thunderbolt/USB4 (CONFIG_USB4) driver is enabled. Drivers can determine what was negotiated by checking two new variables exposed in this patch. Signed-off-by: Mika Westerberg Reviewed-by: Rafael J. Wysocki --- include/linux/acpi.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 2630c2e953f7..ac68c2d4e393 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -546,9 +546,19 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); #define OSC_SB_OSLPI_SUPPORT 0x00000100 #define OSC_SB_CPC_DIVERSE_HIGH_SUPPORT 0x00001000 #define OSC_SB_GENERIC_INITIATOR_SUPPORT 0x00002000 +#define OSC_SB_NATIVE_USB4_SUPPORT 0x00040000 extern bool osc_sb_apei_support_acked; extern bool osc_pc_lpi_support_confirmed; +extern bool osc_sb_native_usb4_support_confirmed; + +/* USB4 Capabilities */ +#define OSC_USB_USB3_TUNNELING 0x00000001 +#define OSC_USB_DP_TUNNELING 0x00000002 +#define OSC_USB_PCIE_TUNNELING 0x00000004 +#define OSC_USB_XDOMAIN 0x00000008 + +extern u32 osc_sb_native_usb4_control; /* PCI Host Bridge _OSC: Capabilities DWORD 2: Support Field */ #define OSC_PCI_EXT_CONFIG_SUPPORT 0x00000001 -- cgit v1.2.3 From 2c07ded06427dd3339278487a1413d5e478f05f9 Mon Sep 17 00:00:00 2001 From: Brijesh Singh Date: Mon, 4 Jan 2021 09:17:49 -0600 Subject: KVM/SVM: add support for SEV attestation command The SEV FW version >= 0.23 added a new command that can be used to query the attestation report containing the SHA-256 digest of the guest memory encrypted through the KVM_SEV_LAUNCH_UPDATE_{DATA, VMSA} commands and sign the report with the Platform Endorsement Key (PEK). See the SEV FW API spec section 6.8 for more details. Note there already exist a command (KVM_SEV_LAUNCH_MEASURE) that can be used to get the SHA-256 digest. The main difference between the KVM_SEV_LAUNCH_MEASURE and KVM_SEV_ATTESTATION_REPORT is that the latter can be called while the guest is running and the measurement value is signed with PEK. Cc: James Bottomley Cc: Tom Lendacky Cc: David Rientjes Cc: Paolo Bonzini Cc: Sean Christopherson Cc: Borislav Petkov Cc: John Allen Cc: Herbert Xu Cc: linux-crypto@vger.kernel.org Reviewed-by: Tom Lendacky Acked-by: David Rientjes Tested-by: James Bottomley Signed-off-by: Brijesh Singh Message-Id: <20210104151749.30248-1-brijesh.singh@amd.com> Signed-off-by: Paolo Bonzini --- include/linux/psp-sev.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h index 49d155cd2dfe..b801ead1e2bb 100644 --- a/include/linux/psp-sev.h +++ b/include/linux/psp-sev.h @@ -66,6 +66,7 @@ enum sev_cmd { SEV_CMD_LAUNCH_MEASURE = 0x033, SEV_CMD_LAUNCH_UPDATE_SECRET = 0x034, SEV_CMD_LAUNCH_FINISH = 0x035, + SEV_CMD_ATTESTATION_REPORT = 0x036, /* Guest migration commands (outgoing) */ SEV_CMD_SEND_START = 0x040, @@ -483,6 +484,22 @@ struct sev_data_dbg { u32 len; /* In */ } __packed; +/** + * struct sev_data_attestation_report - SEV_ATTESTATION_REPORT command parameters + * + * @handle: handle of the VM + * @mnonce: a random nonce that will be included in the report. + * @address: physical address where the report will be copied. + * @len: length of the physical buffer. + */ +struct sev_data_attestation_report { + u32 handle; /* In */ + u32 reserved; + u64 address; /* In */ + u8 mnonce[16]; /* In */ + u32 len; /* In/Out */ +} __packed; + #ifdef CONFIG_CRYPTO_DEV_SP_PSP /** -- cgit v1.2.3 From 26128cb6c7e6731fe644c687af97733adfdb5ee9 Mon Sep 17 00:00:00 2001 From: Ben Gardon Date: Tue, 2 Feb 2021 10:57:12 -0800 Subject: locking/rwlocks: Add contention detection for rwlocks rwlocks do not currently have any facility to detect contention like spinlocks do. In order to allow users of rwlocks to better manage latency, add contention detection for queued rwlocks. CC: Ingo Molnar CC: Will Deacon Acked-by: Peter Zijlstra Acked-by: Davidlohr Bueso Acked-by: Waiman Long Acked-by: Paolo Bonzini Signed-off-by: Ben Gardon Message-Id: <20210202185734.1680553-7-bgardon@google.com> Signed-off-by: Paolo Bonzini --- include/linux/rwlock.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rwlock.h b/include/linux/rwlock.h index 3dcd617e65ae..7ce9a51ae5c0 100644 --- a/include/linux/rwlock.h +++ b/include/linux/rwlock.h @@ -128,4 +128,11 @@ do { \ 1 : ({ local_irq_restore(flags); 0; }); \ }) +#ifdef arch_rwlock_is_contended +#define rwlock_is_contended(lock) \ + arch_rwlock_is_contended(&(lock)->raw_lock) +#else +#define rwlock_is_contended(lock) ((void)(lock), 0) +#endif /* arch_rwlock_is_contended */ + #endif /* __LINUX_RWLOCK_H */ -- cgit v1.2.3 From a09a689a534183c48f200bc2de1ae61ae9c462ad Mon Sep 17 00:00:00 2001 From: Ben Gardon Date: Tue, 2 Feb 2021 10:57:13 -0800 Subject: sched: Add needbreak for rwlocks Contention awareness while holding a spin lock is essential for reducing latency when long running kernel operations can hold that lock. Add the same contention detection interface for read/write spin locks. CC: Ingo Molnar CC: Will Deacon Acked-by: Peter Zijlstra Acked-by: Davidlohr Bueso Acked-by: Waiman Long Acked-by: Paolo Bonzini Signed-off-by: Ben Gardon Message-Id: <20210202185734.1680553-8-bgardon@google.com> Signed-off-by: Paolo Bonzini --- include/linux/sched.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 6e3a5eeec509..5d1378e5a040 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1912,6 +1912,23 @@ static inline int spin_needbreak(spinlock_t *lock) #endif } +/* + * Check if a rwlock is contended. + * Returns non-zero if there is another task waiting on the rwlock. + * Returns zero if the lock is not contended or the system / underlying + * rwlock implementation does not support contention detection. + * Technically does not depend on CONFIG_PREEMPTION, but a general need + * for low latency. + */ +static inline int rwlock_needbreak(rwlock_t *lock) +{ +#ifdef CONFIG_PREEMPTION + return rwlock_is_contended(lock); +#else + return 0; +#endif +} + static __always_inline bool need_resched(void) { return unlikely(tif_need_resched()); -- cgit v1.2.3 From f3d4b4b1dc1c5fb9ea17cac14133463bfe72f170 Mon Sep 17 00:00:00 2001 From: Ben Gardon Date: Tue, 2 Feb 2021 10:57:14 -0800 Subject: sched: Add cond_resched_rwlock Safely rescheduling while holding a spin lock is essential for keeping long running kernel operations running smoothly. Add the facility to cond_resched rwlocks. CC: Ingo Molnar CC: Will Deacon Acked-by: Peter Zijlstra Acked-by: Davidlohr Bueso Acked-by: Waiman Long Acked-by: Paolo Bonzini Signed-off-by: Ben Gardon Message-Id: <20210202185734.1680553-9-bgardon@google.com> Signed-off-by: Paolo Bonzini --- include/linux/sched.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 5d1378e5a040..3052d16da3cf 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1883,12 +1883,24 @@ static inline int _cond_resched(void) { return 0; } }) extern int __cond_resched_lock(spinlock_t *lock); +extern int __cond_resched_rwlock_read(rwlock_t *lock); +extern int __cond_resched_rwlock_write(rwlock_t *lock); #define cond_resched_lock(lock) ({ \ ___might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET);\ __cond_resched_lock(lock); \ }) +#define cond_resched_rwlock_read(lock) ({ \ + __might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET); \ + __cond_resched_rwlock_read(lock); \ +}) + +#define cond_resched_rwlock_write(lock) ({ \ + __might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET); \ + __cond_resched_rwlock_write(lock); \ +}) + static inline void cond_resched_rcu(void) { #if defined(CONFIG_DEBUG_ATOMIC_SLEEP) || !defined(CONFIG_PREEMPT_RCU) -- cgit v1.2.3 From 531810caa9f4bc99ffbb90e09256792c56a6b07a Mon Sep 17 00:00:00 2001 From: Ben Gardon Date: Tue, 2 Feb 2021 10:57:24 -0800 Subject: KVM: x86/mmu: Use an rwlock for the x86 MMU Add a read / write lock to be used in place of the MMU spinlock on x86. The rwlock will enable the TDP MMU to handle page faults, and other operations in parallel in future commits. Reviewed-by: Peter Feiner Signed-off-by: Ben Gardon Message-Id: <20210202185734.1680553-19-bgardon@google.com> [Introduce virt/kvm/mmu_lock.h - Paolo] Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index f3b1013fb22c..f417447129b9 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -451,7 +451,12 @@ struct kvm_memslots { }; struct kvm { +#ifdef KVM_HAVE_MMU_RWLOCK + rwlock_t mmu_lock; +#else spinlock_t mmu_lock; +#endif /* KVM_HAVE_MMU_RWLOCK */ + struct mutex slots_lock; struct mm_struct *mm; /* userspace tied to this vm */ struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM]; -- cgit v1.2.3 From 7d8658ef65a4f891d0cff6340fa717b378384642 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Thu, 4 Feb 2021 16:14:22 +0800 Subject: OPP: Add function to look up required OPP's for a given OPP Add a function that allows looking up required OPPs given a source OPP table, destination OPP table and the source OPP. Signed-off-by: Saravana Kannan Signed-off-by: Hsin-Yi Wang [ Viresh: Rearranged code, fixed return errors ] Signed-off-by: Viresh Kumar --- include/linux/pm_opp.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index ab1d15ce559d..c0371efa4a0f 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -156,6 +156,7 @@ struct opp_table *devm_pm_opp_register_set_opp_helper(struct device *dev, int (* struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char **names, struct device ***virt_devs); void dev_pm_opp_detach_genpd(struct opp_table *opp_table); struct opp_table *devm_pm_opp_attach_genpd(struct device *dev, const char **names, struct device ***virt_devs); +struct dev_pm_opp *dev_pm_opp_xlate_required_opp(struct opp_table *src_table, struct opp_table *dst_table, struct dev_pm_opp *src_opp); int dev_pm_opp_xlate_performance_state(struct opp_table *src_table, struct opp_table *dst_table, unsigned int pstate); int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq); int dev_pm_opp_set_opp(struct device *dev, struct dev_pm_opp *opp); @@ -367,6 +368,12 @@ static inline struct opp_table *devm_pm_opp_attach_genpd(struct device *dev, return ERR_PTR(-EOPNOTSUPP); } +static inline struct dev_pm_opp *dev_pm_opp_xlate_required_opp(struct opp_table *src_table, + struct opp_table *dst_table, struct dev_pm_opp *src_opp) +{ + return ERR_PTR(-EOPNOTSUPP); +} + static inline int dev_pm_opp_xlate_performance_state(struct opp_table *src_table, struct opp_table *dst_table, unsigned int pstate) { return -EOPNOTSUPP; -- cgit v1.2.3 From 26f9c7cc42a6dc036edf871544fd0e6b3a0601c1 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Thu, 4 Feb 2021 16:14:23 +0800 Subject: PM / devfreq: Cache OPP table reference in devfreq The OPP table can be used often in devfreq. Trying to get it each time can be expensive, so cache it in the devfreq struct. Signed-off-by: Saravana Kannan Acked-by: MyungJoo Ham Acked-by: Chanwoo Choi Signed-off-by: Hsin-Yi Wang [ Viresh: Added a blank line ] Signed-off-by: Viresh Kumar --- include/linux/devfreq.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index b6d3bae1c74d..26ea0850be9b 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -137,6 +137,7 @@ struct devfreq_stats { * using devfreq. * @profile: device-specific devfreq profile * @governor: method how to choose frequency based on the usage. + * @opp_table: Reference to OPP table of dev.parent, if one exists. * @nb: notifier block used to notify devfreq object that it should * reevaluate operable frequencies. Devfreq users may use * devfreq.nb to the corresponding register notifier call chain. @@ -173,6 +174,7 @@ struct devfreq { struct device dev; struct devfreq_dev_profile *profile; const struct devfreq_governor *governor; + struct opp_table *opp_table; struct notifier_block nb; struct delayed_work work; -- cgit v1.2.3 From ed8188a0c1f0f49739c727a53df1174826c1a80b Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 4 Feb 2021 09:43:55 +0800 Subject: iommu/vt-d: Fix 'physical' typos Fix misspellings of "physical". Signed-off-by: Bjorn Helgaas Signed-off-by: Lu Baolu Link: https://lore.kernel.org/linux-iommu/20210126211738.2920789-1-helgaas@kernel.org Link: https://lore.kernel.org/r/20210204014401.2846425-2-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index ecb35fdff03e..f8ab154c979d 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -664,7 +664,7 @@ static inline struct dmar_domain *to_dmar_domain(struct iommu_domain *dom) * 7: super page * 8-10: available * 11: snoop behavior - * 12-63: Host physcial address + * 12-63: Host physical address */ struct dma_pte { u64 val; -- cgit v1.2.3 From ad3d19029979b19378ece2011fc8ce07be98c905 Mon Sep 17 00:00:00 2001 From: Kyung Min Park Date: Thu, 4 Feb 2021 09:43:56 +0800 Subject: iommu/vt-d: Audit IOMMU Capabilities and add helper functions Audit IOMMU Capability/Extended Capability and check if the IOMMUs have the consistent value for features. Report out or scale to the lowest supported when IOMMU features have incompatibility among IOMMUs. Report out features when below features are mismatched: - First Level 5 Level Paging Support (FL5LP) - First Level 1 GByte Page Support (FL1GP) - Read Draining (DRD) - Write Draining (DWD) - Page Selective Invalidation (PSI) - Zero Length Read (ZLR) - Caching Mode (CM) - Protected High/Low-Memory Region (PHMR/PLMR) - Required Write-Buffer Flushing (RWBF) - Advanced Fault Logging (AFL) - RID-PASID Support (RPS) - Scalable Mode Page Walk Coherency (SMPWC) - First Level Translation Support (FLTS) - Second Level Translation Support (SLTS) - No Write Flag Support (NWFS) - Second Level Accessed/Dirty Support (SLADS) - Virtual Command Support (VCS) - Scalable Mode Translation Support (SMTS) - Device TLB Invalidation Throttle (DIT) - Page Drain Support (PDS) - Process Address Space ID Support (PASID) - Extended Accessed Flag Support (EAFS) - Supervisor Request Support (SRS) - Execute Request Support (ERS) - Page Request Support (PRS) - Nested Translation Support (NEST) - Snoop Control (SC) - Pass Through (PT) - Device TLB Support (DT) - Queued Invalidation (QI) - Page walk Coherency (C) Set capability to the lowest supported when below features are mismatched: - Maximum Address Mask Value (MAMV) - Number of Fault Recording Registers (NFR) - Second Level Large Page Support (SLLPS) - Fault Recording Offset (FRO) - Maximum Guest Address Width (MGAW) - Supported Adjusted Guest Address Width (SAGAW) - Number of Domains supported (NDOMS) - Pasid Size Supported (PSS) - Maximum Handle Mask Value (MHMV) - IOTLB Register Offset (IRO) Signed-off-by: Kyung Min Park Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20210130184452.31711-1-kyung.min.park@intel.com Link: https://lore.kernel.org/r/20210204014401.2846425-3-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 39 +++++++++++++++++++++------------------ 1 file changed, 21 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index f8ab154c979d..1bc46b88711a 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -170,34 +170,37 @@ * Extended Capability Register */ +#define ecap_rps(e) (((e) >> 49) & 0x1) #define ecap_smpwc(e) (((e) >> 48) & 0x1) #define ecap_flts(e) (((e) >> 47) & 0x1) #define ecap_slts(e) (((e) >> 46) & 0x1) +#define ecap_slads(e) (((e) >> 45) & 0x1) #define ecap_vcs(e) (((e) >> 44) & 0x1) #define ecap_smts(e) (((e) >> 43) & 0x1) -#define ecap_dit(e) ((e >> 41) & 0x1) -#define ecap_pasid(e) ((e >> 40) & 0x1) -#define ecap_pss(e) ((e >> 35) & 0x1f) -#define ecap_eafs(e) ((e >> 34) & 0x1) -#define ecap_nwfs(e) ((e >> 33) & 0x1) -#define ecap_srs(e) ((e >> 31) & 0x1) -#define ecap_ers(e) ((e >> 30) & 0x1) -#define ecap_prs(e) ((e >> 29) & 0x1) -#define ecap_broken_pasid(e) ((e >> 28) & 0x1) -#define ecap_dis(e) ((e >> 27) & 0x1) -#define ecap_nest(e) ((e >> 26) & 0x1) -#define ecap_mts(e) ((e >> 25) & 0x1) -#define ecap_ecs(e) ((e >> 24) & 0x1) +#define ecap_dit(e) (((e) >> 41) & 0x1) +#define ecap_pds(e) (((e) >> 42) & 0x1) +#define ecap_pasid(e) (((e) >> 40) & 0x1) +#define ecap_pss(e) (((e) >> 35) & 0x1f) +#define ecap_eafs(e) (((e) >> 34) & 0x1) +#define ecap_nwfs(e) (((e) >> 33) & 0x1) +#define ecap_srs(e) (((e) >> 31) & 0x1) +#define ecap_ers(e) (((e) >> 30) & 0x1) +#define ecap_prs(e) (((e) >> 29) & 0x1) +#define ecap_broken_pasid(e) (((e) >> 28) & 0x1) +#define ecap_dis(e) (((e) >> 27) & 0x1) +#define ecap_nest(e) (((e) >> 26) & 0x1) +#define ecap_mts(e) (((e) >> 25) & 0x1) +#define ecap_ecs(e) (((e) >> 24) & 0x1) #define ecap_iotlb_offset(e) ((((e) >> 8) & 0x3ff) * 16) #define ecap_max_iotlb_offset(e) (ecap_iotlb_offset(e) + 16) #define ecap_coherent(e) ((e) & 0x1) #define ecap_qis(e) ((e) & 0x2) -#define ecap_pass_through(e) ((e >> 6) & 0x1) -#define ecap_eim_support(e) ((e >> 4) & 0x1) -#define ecap_ir_support(e) ((e >> 3) & 0x1) +#define ecap_pass_through(e) (((e) >> 6) & 0x1) +#define ecap_eim_support(e) (((e) >> 4) & 0x1) +#define ecap_ir_support(e) (((e) >> 3) & 0x1) #define ecap_dev_iotlb_support(e) (((e) >> 2) & 0x1) -#define ecap_max_handle_mask(e) ((e >> 20) & 0xf) -#define ecap_sc_support(e) ((e >> 7) & 0x1) /* Snooping Control */ +#define ecap_max_handle_mask(e) (((e) >> 20) & 0xf) +#define ecap_sc_support(e) (((e) >> 7) & 0x1) /* Snooping Control */ /* Virtual command interface capability */ #define vccap_pasid(v) (((v) & DMA_VCS_PAS)) /* PASID allocation */ -- cgit v1.2.3 From 31a75cbbb9274cf8185f402904bf11386917870b Mon Sep 17 00:00:00 2001 From: Yian Chen Date: Thu, 4 Feb 2021 09:44:00 +0800 Subject: iommu/vt-d: Parse SATC reporting structure Software should parse every SATC table and all devices in the tables reported by the BIOS and keep the information in kernel list for further reference. Signed-off-by: Yian Chen Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20210203093329.1617808-1-baolu.lu@linux.intel.com Link: https://lore.kernel.org/r/20210204014401.2846425-7-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/dmar.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmar.h b/include/linux/dmar.h index 65565820328a..e04436a7ff27 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -138,6 +138,7 @@ extern void intel_iommu_shutdown(void); extern int dmar_parse_one_rmrr(struct acpi_dmar_header *header, void *arg); extern int dmar_parse_one_atsr(struct acpi_dmar_header *header, void *arg); extern int dmar_check_one_atsr(struct acpi_dmar_header *hdr, void *arg); +extern int dmar_parse_one_satc(struct acpi_dmar_header *hdr, void *arg); extern int dmar_release_one_atsr(struct acpi_dmar_header *hdr, void *arg); extern int dmar_iommu_hotplug(struct dmar_drhd_unit *dmaru, bool insert); extern int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info); @@ -149,6 +150,7 @@ static inline void intel_iommu_shutdown(void) { } #define dmar_parse_one_atsr dmar_res_noop #define dmar_check_one_atsr dmar_res_noop #define dmar_release_one_atsr dmar_res_noop +#define dmar_parse_one_satc dmar_res_noop static inline int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info) { -- cgit v1.2.3 From e1e4f7fea37572f0ccf3887430e52c491e9accb6 Mon Sep 17 00:00:00 2001 From: CK Hu Date: Tue, 21 Jul 2020 15:46:06 +0800 Subject: soc / drm: mediatek: Move mtk mutex driver to soc folder mtk mutex is used by DRM and MDP driver, and its function is SoC-specific, so move it to soc folder. Signed-off-by: CK Hu Signed-off-by: Chun-Kuang Hu Acked-by: Matthias Brugger --- include/linux/soc/mediatek/mtk-mutex.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) create mode 100644 include/linux/soc/mediatek/mtk-mutex.h (limited to 'include/linux') diff --git a/include/linux/soc/mediatek/mtk-mutex.h b/include/linux/soc/mediatek/mtk-mutex.h new file mode 100644 index 000000000000..6fe4ffbde290 --- /dev/null +++ b/include/linux/soc/mediatek/mtk-mutex.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2015 MediaTek Inc. + */ + +#ifndef MTK_MUTEX_H +#define MTK_MUTEX_H + +struct regmap; +struct device; +struct mtk_mutex; + +struct mtk_mutex *mtk_mutex_get(struct device *dev); +int mtk_mutex_prepare(struct mtk_mutex *mutex); +void mtk_mutex_add_comp(struct mtk_mutex *mutex, + enum mtk_ddp_comp_id id); +void mtk_mutex_enable(struct mtk_mutex *mutex); +void mtk_mutex_disable(struct mtk_mutex *mutex); +void mtk_mutex_remove_comp(struct mtk_mutex *mutex, + enum mtk_ddp_comp_id id); +void mtk_mutex_unprepare(struct mtk_mutex *mutex); +void mtk_mutex_put(struct mtk_mutex *mutex); +void mtk_mutex_acquire(struct mtk_mutex *mutex); +void mtk_mutex_release(struct mtk_mutex *mutex); + +#endif /* MTK_MUTEX_H */ -- cgit v1.2.3 From 6e736c60a9fe905b3e4f4b07171a31ad602d56d2 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Mon, 1 Feb 2021 11:13:25 -0700 Subject: coresight: Introduce device access abstraction We are about to introduce support for sysreg access to ETMv4.4+ component. Since there are generic routines that access the registers (e.g, CS_LOCK/UNLOCK , claim/disclaim operations, timeout) and in order to preserve the logic of these operations at a single place we introduce an abstraction layer for the accesses to a given device. Link: https://lore.kernel.org/r/20210110224850.1880240-4-suzuki.poulose@arm.com Cc: Mike Leach Signed-off-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Link: https://lore.kernel.org/r/20210201181351.1475223-6-mathieu.poirier@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight.h | 191 +++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 188 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 7d3c87e5b97c..6107cf4021d3 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -7,6 +7,7 @@ #define _LINUX_CORESIGHT_H #include +#include #include #include @@ -114,6 +115,32 @@ struct coresight_platform_data { struct coresight_connection *conns; }; +/** + * struct csdev_access - Abstraction of a CoreSight device access. + * + * @io_mem : True if the device has memory mapped I/O + * @base : When io_mem == true, base address of the component + * @read : Read from the given "offset" of the given instance. + * @write : Write "val" to the given "offset". + */ +struct csdev_access { + bool io_mem; + union { + void __iomem *base; + struct { + u64 (*read)(u32 offset, bool relaxed, bool _64bit); + void (*write)(u64 val, u32 offset, bool relaxed, + bool _64bit); + }; + }; +}; + +#define CSDEV_ACCESS_IOMEM(_addr) \ + ((struct csdev_access) { \ + .io_mem = true, \ + .base = (_addr), \ + }) + /** * struct coresight_desc - description of a component required from drivers * @type: as defined by @coresight_dev_type. @@ -125,6 +152,7 @@ struct coresight_platform_data { * @groups: operations specific to this component. These will end up * in the component's sysfs sub-directory. * @name: name for the coresight device, also shown under sysfs. + * @access: Describe access to the device */ struct coresight_desc { enum coresight_dev_type type; @@ -134,6 +162,7 @@ struct coresight_desc { struct device *dev; const struct attribute_group **groups; const char *name; + struct csdev_access access; }; /** @@ -173,7 +202,8 @@ struct coresight_sysfs_link { * @type: as defined by @coresight_dev_type. * @subtype: as defined by @coresight_dev_subtype. * @ops: generic operations for this component, as defined - by @coresight_ops. + * by @coresight_ops. + * @access: Device i/o access abstraction for this device. * @dev: The device entity associated to this component. * @refcnt: keep track of what is in use. * @orphan: true if the component has connections that haven't been linked. @@ -195,6 +225,7 @@ struct coresight_device { enum coresight_dev_type type; union coresight_dev_subtype subtype; const struct coresight_ops *ops; + struct csdev_access access; struct device dev; atomic_t *refcnt; bool orphan; @@ -326,6 +357,104 @@ struct coresight_ops { }; #if IS_ENABLED(CONFIG_CORESIGHT) + +static inline u32 csdev_access_relaxed_read32(struct csdev_access *csa, + u32 offset) +{ + if (likely(csa->io_mem)) + return readl_relaxed(csa->base + offset); + + return csa->read(offset, true, false); +} + +static inline u32 csdev_access_read32(struct csdev_access *csa, u32 offset) +{ + if (likely(csa->io_mem)) + return readl(csa->base + offset); + + return csa->read(offset, false, false); +} + +static inline void csdev_access_relaxed_write32(struct csdev_access *csa, + u32 val, u32 offset) +{ + if (likely(csa->io_mem)) + writel_relaxed(val, csa->base + offset); + else + csa->write(val, offset, true, false); +} + +static inline void csdev_access_write32(struct csdev_access *csa, u32 val, u32 offset) +{ + if (likely(csa->io_mem)) + writel(val, csa->base + offset); + else + csa->write(val, offset, false, false); +} + +#ifdef CONFIG_64BIT + +static inline u64 csdev_access_relaxed_read64(struct csdev_access *csa, + u32 offset) +{ + if (likely(csa->io_mem)) + return readq_relaxed(csa->base + offset); + + return csa->read(offset, true, true); +} + +static inline u64 csdev_access_read64(struct csdev_access *csa, u32 offset) +{ + if (likely(csa->io_mem)) + return readq(csa->base + offset); + + return csa->read(offset, false, true); +} + +static inline void csdev_access_relaxed_write64(struct csdev_access *csa, + u64 val, u32 offset) +{ + if (likely(csa->io_mem)) + writeq_relaxed(val, csa->base + offset); + else + csa->write(val, offset, true, true); +} + +static inline void csdev_access_write64(struct csdev_access *csa, u64 val, u32 offset) +{ + if (likely(csa->io_mem)) + writeq(val, csa->base + offset); + else + csa->write(val, offset, false, true); +} + +#else /* !CONFIG_64BIT */ + +static inline u64 csdev_access_relaxed_read64(struct csdev_access *csa, + u32 offset) +{ + WARN_ON(1); + return 0; +} + +static inline u64 csdev_access_read64(struct csdev_access *csa, u32 offset) +{ + WARN_ON(1); + return 0; +} + +static inline void csdev_access_relaxed_write64(struct csdev_access *csa, + u64 val, u32 offset) +{ + WARN_ON(1); +} + +static inline void csdev_access_write64(struct csdev_access *csa, u64 val, u32 offset) +{ + WARN_ON(1); +} +#endif /* CONFIG_64BIT */ + extern struct coresight_device * coresight_register(struct coresight_desc *desc); extern void coresight_unregister(struct coresight_device *csdev); @@ -343,6 +472,18 @@ extern char *coresight_alloc_device_name(struct coresight_dev_list *devs, struct device *dev); extern bool coresight_loses_context_with_cpu(struct device *dev); + +u32 coresight_relaxed_read32(struct coresight_device *csdev, u32 offset); +u32 coresight_read32(struct coresight_device *csdev, u32 offset); +void coresight_write32(struct coresight_device *csdev, u32 val, u32 offset); +void coresight_relaxed_write32(struct coresight_device *csdev, + u32 val, u32 offset); +u64 coresight_relaxed_read64(struct coresight_device *csdev, u32 offset); +u64 coresight_read64(struct coresight_device *csdev, u32 offset); +void coresight_relaxed_write64(struct coresight_device *csdev, + u64 val, u32 offset); +void coresight_write64(struct coresight_device *csdev, u64 val, u32 offset); + #else static inline struct coresight_device * coresight_register(struct coresight_desc *desc) { return NULL; } @@ -369,10 +510,54 @@ static inline bool coresight_loses_context_with_cpu(struct device *dev) { return false; } -#endif + +static inline u32 coresight_relaxed_read32(struct coresight_device *csdev, u32 offset) +{ + WARN_ON_ONCE(1); + return 0; +} + +static inline u32 coresight_read32(struct coresight_device *csdev, u32 offset) +{ + WARN_ON_ONCE(1); + return 0; +} + +static inline void coresight_write32(struct coresight_device *csdev, u32 val, u32 offset) +{ +} + +static inline void coresight_relaxed_write32(struct coresight_device *csdev, + u32 val, u32 offset) +{ +} + +static inline u64 coresight_relaxed_read64(struct coresight_device *csdev, + u32 offset) +{ + WARN_ON_ONCE(1); + return 0; +} + +static inline u64 coresight_read64(struct coresight_device *csdev, u32 offset) +{ + WARN_ON_ONCE(1); + return 0; +} + +static inline void coresight_relaxed_write64(struct coresight_device *csdev, + u64 val, u32 offset) +{ +} + +static inline void coresight_write64(struct coresight_device *csdev, u64 val, u32 offset) +{ +} + +#endif /* IS_ENABLED(CONFIG_CORESIGHT) */ extern int coresight_get_cpu(struct device *dev); struct coresight_platform_data *coresight_get_platform_data(struct device *dev); -#endif +#endif /* _LINUX_COREISGHT_H */ -- cgit v1.2.3 From 020052825e49128d381d6444d1ce079e8ca82386 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Mon, 1 Feb 2021 11:13:27 -0700 Subject: coresight: Convert coresight_timeout to use access abstraction Convert the generic routines to use the new access abstraction layer gradually, starting with coresigth_timeout. Link: https://lore.kernel.org/r/20210110224850.1880240-6-suzuki.poulose@arm.com Cc: Mike Leach Signed-off-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Link: https://lore.kernel.org/r/20210201181351.1475223-8-mathieu.poirier@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 6107cf4021d3..18bc7f9fb041 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -460,7 +460,7 @@ coresight_register(struct coresight_desc *desc); extern void coresight_unregister(struct coresight_device *csdev); extern int coresight_enable(struct coresight_device *csdev); extern void coresight_disable(struct coresight_device *csdev); -extern int coresight_timeout(void __iomem *addr, u32 offset, +extern int coresight_timeout(struct csdev_access *csa, u32 offset, int position, int value); extern int coresight_claim_device(void __iomem *base); @@ -491,8 +491,13 @@ static inline void coresight_unregister(struct coresight_device *csdev) {} static inline int coresight_enable(struct coresight_device *csdev) { return -ENOSYS; } static inline void coresight_disable(struct coresight_device *csdev) {} -static inline int coresight_timeout(void __iomem *addr, u32 offset, - int position, int value) { return 1; } + +static inline int coresight_timeout(struct csdev_access *csa, u32 offset, + int position, int value) +{ + return 1; +} + static inline int coresight_claim_device_unlocked(void __iomem *base) { return -EINVAL; -- cgit v1.2.3 From 8ce0029658ba16c52670e869b9ccde02ae7dec6b Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Mon, 1 Feb 2021 11:13:28 -0700 Subject: coresight: Convert claim/disclaim operations to use access wrappers Convert the generic CLAIM tag management APIs to use the device access layer abstraction. Link: https://lore.kernel.org/r/20210110224850.1880240-7-suzuki.poulose@arm.com Cc: Mike Leach Signed-off-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Link: https://lore.kernel.org/r/20210201181351.1475223-9-mathieu.poirier@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 18bc7f9fb041..976ec2697610 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -463,11 +463,11 @@ extern void coresight_disable(struct coresight_device *csdev); extern int coresight_timeout(struct csdev_access *csa, u32 offset, int position, int value); -extern int coresight_claim_device(void __iomem *base); -extern int coresight_claim_device_unlocked(void __iomem *base); +extern int coresight_claim_device(struct coresight_device *csdev); +extern int coresight_claim_device_unlocked(struct coresight_device *csdev); -extern void coresight_disclaim_device(void __iomem *base); -extern void coresight_disclaim_device_unlocked(void __iomem *base); +extern void coresight_disclaim_device(struct coresight_device *csdev); +extern void coresight_disclaim_device_unlocked(struct coresight_device *csdev); extern char *coresight_alloc_device_name(struct coresight_dev_list *devs, struct device *dev); @@ -498,18 +498,18 @@ static inline int coresight_timeout(struct csdev_access *csa, u32 offset, return 1; } -static inline int coresight_claim_device_unlocked(void __iomem *base) +static inline int coresight_claim_device_unlocked(struct coresight_device *csdev) { return -EINVAL; } -static inline int coresight_claim_device(void __iomem *base) +static inline int coresight_claim_device(struct coresight_device *csdev) { return -EINVAL; } -static inline void coresight_disclaim_device(void __iomem *base) {} -static inline void coresight_disclaim_device_unlocked(void __iomem *base) {} +static inline void coresight_disclaim_device(struct coresight_device *csdev) {} +static inline void coresight_disclaim_device_unlocked(struct coresight_device *csdev) {} static inline bool coresight_loses_context_with_cpu(struct device *dev) { -- cgit v1.2.3 From b64afd949ee3a61e180813859b50aced26023c55 Mon Sep 17 00:00:00 2001 From: Prashant Malani Date: Tue, 2 Feb 2021 18:15:37 -0800 Subject: platform/chrome: cros_ec: Import Type C control command This command is used to communicate with the Chrome Embedded Controller (EC) regarding USB Type C events and state. These header updates are included in the latest Chrome OS EC headers [1] [1] https://chromium.googlesource.com/chromiumos/platform/ec/+/refs/heads/main/include/ec_commands.h Signed-off-by: Prashant Malani Link: https://lore.kernel.org/r/20210203021539.745239-1-pmalani@chromium.org Signed-off-by: Benson Leung --- include/linux/platform_data/cros_ec_commands.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index 9787715540c7..50e1caad81be 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -5577,6 +5577,32 @@ struct ec_response_typec_discovery { struct svid_mode_info svids[0]; } __ec_align1; +/* USB Type-C commands for AP-controlled device policy. */ +#define EC_CMD_TYPEC_CONTROL 0x0132 + +enum typec_control_command { + TYPEC_CONTROL_COMMAND_EXIT_MODES, + TYPEC_CONTROL_COMMAND_CLEAR_EVENTS, + TYPEC_CONTROL_COMMAND_ENTER_MODE, +}; + +struct ec_params_typec_control { + uint8_t port; + uint8_t command; /* enum typec_control_command */ + uint16_t reserved; + + /* + * This section will be interpreted based on |command|. Define a + * placeholder structure to avoid having to increase the size and bump + * the command version when adding new sub-commands. + */ + union { + uint32_t clear_events_mask; + uint8_t mode_to_enter; /* enum typec_mode */ + uint8_t placeholder[128]; + }; +} __ec_align1; + /* * Gather all status information for a port. * -- cgit v1.2.3 From 5ae4a4b45d4396aa7f7c008c4ae9eca981d43f8c Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 2 Feb 2021 10:25:11 +0530 Subject: cpufreq: Remove CPUFREQ_STICKY flag During cpufreq driver's registration, if the ->init() callback for all the CPUs fail then there is not much point in keeping the driver around as it will only account for more of unnecessary noise, for example cpufreq core will try to suspend/resume the driver which never got registered properly. The removal of such a driver is avoided if the driver carries the CPUFREQ_STICKY flag. This was added way back [1] in 2004 and perhaps no one should ever need it now. A lot of drivers do set this flag, probably because they just copied it from other drivers. This was added earlier for some platforms [2] because their cpufreq drivers were getting registered before the CPUs were registered with subsys framework. And hence they used to fail. The same isn't true anymore though. The current code flow in the kernel is: start_kernel() -> kernel_init() -> kernel_init_freeable() -> do_basic_setup() -> driver_init() -> cpu_dev_init() -> subsys_system_register() //For CPUs -> do_initcalls() -> cpufreq_register_driver() Clearly, the CPUs will always get registered with subsys framework before any cpufreq driver can get probed. Remove the flag and update the relevant drivers. Link: https://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git/commit/include/linux/cpufreq.h?id=7cc9f0d9a1ab04cedc60d64fd8dcf7df224a3b4d # [1] Link: https://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git/commit/arch/arm/mach-sa1100/cpu-sa1100.c?id=f59d3bbe35f6268d729f51be82af8325d62f20f5 # [2] Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 9c8b7437b6cd..c8e40e91fe9b 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -387,8 +387,13 @@ struct cpufreq_driver { /* flags */ -/* driver isn't removed even if all ->init() calls failed */ -#define CPUFREQ_STICKY BIT(0) +/* + * Set by drivers that need to update internale upper and lower boundaries along + * with the target frequency and so the core and governors should also invoke + * the diver if the target frequency does not change, but the policy min or max + * may have changed. + */ +#define CPUFREQ_NEED_UPDATE_LIMITS BIT(0) /* loops_per_jiffy or other kernel "constants" aren't affected by frequency transitions */ #define CPUFREQ_CONST_LOOPS BIT(1) @@ -432,14 +437,6 @@ struct cpufreq_driver { */ #define CPUFREQ_IS_COOLING_DEV BIT(7) -/* - * Set by drivers that need to update internale upper and lower boundaries along - * with the target frequency and so the core and governors should also invoke - * the diver if the target frequency does not change, but the policy min or max - * may have changed. - */ -#define CPUFREQ_NEED_UPDATE_LIMITS BIT(8) - int cpufreq_register_driver(struct cpufreq_driver *driver_data); int cpufreq_unregister_driver(struct cpufreq_driver *driver_data); -- cgit v1.2.3 From 2f0531869fd22182e769b10dd6cf151861ede791 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 2 Feb 2021 11:11:55 +0530 Subject: cpufreq: Remove unused flag CPUFREQ_PM_NO_WARN This flag is set by one of the drivers but it isn't used in the code otherwise. Remove the unused flag and update the driver. Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index c8e40e91fe9b..353969c7acd3 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -398,8 +398,11 @@ struct cpufreq_driver { /* loops_per_jiffy or other kernel "constants" aren't affected by frequency transitions */ #define CPUFREQ_CONST_LOOPS BIT(1) -/* don't warn on suspend/resume speed mismatches */ -#define CPUFREQ_PM_NO_WARN BIT(2) +/* + * Set by drivers that want the core to automatically register the cpufreq + * driver as a thermal cooling device. + */ +#define CPUFREQ_IS_COOLING_DEV BIT(2) /* * This should be set by platforms having multiple clock-domains, i.e. @@ -431,12 +434,6 @@ struct cpufreq_driver { */ #define CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING BIT(6) -/* - * Set by drivers that want the core to automatically register the cpufreq - * driver as a thermal cooling device. - */ -#define CPUFREQ_IS_COOLING_DEV BIT(7) - int cpufreq_register_driver(struct cpufreq_driver *driver_data); int cpufreq_unregister_driver(struct cpufreq_driver *driver_data); -- cgit v1.2.3 From 7e3ce05e7f650371061d0b9eec1e1cf74ed6fca0 Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Wed, 3 Feb 2021 22:48:16 -0300 Subject: netlink: add tracepoint at NL_SET_ERR_MSG Often userspace won't request the extack information, or they don't log it because of log level or so, and even when they do, sometimes it's not enough to know exactly what caused the error. Netlink extack is the standard way of reporting erros with descriptive error messages. With a trace point on it, we then can know exactly where the error happened, regardless of userspace app. Also, we can even see if the err msg was overwritten. The wrapper do_trace_netlink_extack() is because trace points shouldn't be called from .h files, as trace points are not that small, and the function call to do_trace_netlink_extack() on the macros is not protected by tracepoint_enabled() because the macros are called from modules, and this would require exporting some trace structs. As this is error path, it's better to export just the wrapper instead. v2: removed leftover tracepoint declaration Signed-off-by: Marcelo Ricardo Leitner Reviewed-by: David Ahern Link: https://lore.kernel.org/r/4546b63e67b2989789d146498b13cc09e1fdc543.1612403190.git.marcelo.leitner@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/netlink.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 9f118771e248..0bcf98098c5a 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -11,6 +11,8 @@ struct net; +void do_trace_netlink_extack(const char *msg); + static inline struct nlmsghdr *nlmsg_hdr(const struct sk_buff *skb) { return (struct nlmsghdr *)skb->data; @@ -90,6 +92,8 @@ struct netlink_ext_ack { static const char __msg[] = msg; \ struct netlink_ext_ack *__extack = (extack); \ \ + do_trace_netlink_extack(__msg); \ + \ if (__extack) \ __extack->_msg = __msg; \ } while (0) @@ -110,6 +114,8 @@ struct netlink_ext_ack { static const char __msg[] = msg; \ struct netlink_ext_ack *__extack = (extack); \ \ + do_trace_netlink_extack(__msg); \ + \ if (__extack) { \ __extack->_msg = __msg; \ __extack->bad_attr = (attr); \ -- cgit v1.2.3 From 0053859496baa17c7675526936677c9213bf5a0d Mon Sep 17 00:00:00 2001 From: Brian Vazquez Date: Thu, 4 Feb 2021 18:18:38 +0000 Subject: net: add EXPORT_INDIRECT_CALLABLE wrapper When a static function is annotated with INDIRECT_CALLABLE_SCOPE and CONFIG_RETPOLINE is set, the static keyword is removed. Sometimes the function needs to be exported but EXPORT_SYMBOL can't be used because if CONFIG_RETPOLINE is not set, we will attempt to export a static symbol. This patch introduces a new indirect call wrapper: EXPORT_INDIRECT_CALLABLE. This basically does EXPORT_SYMBOL when CONFIG_RETPOLINE is set, but does nothing when it's not. Reported-by: Stephen Rothwell Signed-off-by: Brian Vazquez Link: https://lore.kernel.org/r/20210204181839.558951-1-brianvv@google.com Signed-off-by: Jakub Kicinski --- include/linux/indirect_call_wrapper.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/indirect_call_wrapper.h b/include/linux/indirect_call_wrapper.h index 54c02c84906a..a8345c8a613d 100644 --- a/include/linux/indirect_call_wrapper.h +++ b/include/linux/indirect_call_wrapper.h @@ -36,6 +36,7 @@ #define INDIRECT_CALLABLE_DECLARE(f) f #define INDIRECT_CALLABLE_SCOPE +#define EXPORT_INDIRECT_CALLABLE(f) EXPORT_SYMBOL(f) #else #define INDIRECT_CALL_1(f, f1, ...) f(__VA_ARGS__) @@ -44,6 +45,7 @@ #define INDIRECT_CALL_4(f, f4, f3, f2, f1, ...) f(__VA_ARGS__) #define INDIRECT_CALLABLE_DECLARE(f) #define INDIRECT_CALLABLE_SCOPE static +#define EXPORT_INDIRECT_CALLABLE(f) #endif /* -- cgit v1.2.3 From 1d7bab6a94458e959f3f55788fd50ddc7d97403b Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Tue, 2 Feb 2021 13:30:54 +0000 Subject: mm: constify page_is_pfmemalloc() argument The function only tests for page->index, so its argument should be const. Signed-off-by: Alexander Lobakin Reviewed-by: Jesse Brandeburg Acked-by: David Rientjes Signed-off-by: Jakub Kicinski --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index ecdf8a8cd6ae..078633d43af9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1584,7 +1584,7 @@ struct address_space *page_mapping_file(struct page *page); * ALLOC_NO_WATERMARKS and the low watermark was not * met implying that the system is under some pressure. */ -static inline bool page_is_pfmemalloc(struct page *page) +static inline bool page_is_pfmemalloc(const struct page *page) { /* * Page index cannot be this large so this must be -- cgit v1.2.3 From 48f971c9c80a728646fc03367a28df747f20d0f4 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Tue, 2 Feb 2021 13:31:05 +0000 Subject: skbuff: constify skb_propagate_pfmemalloc() "page" argument The function doesn't write anything to the page struct itself, so this argument can be const. Misc: align second argument to the brace while at it. Signed-off-by: Alexander Lobakin Reviewed-by: Jesse Brandeburg Acked-by: David Rientjes Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9313b5aaf45b..b027526da4f9 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2943,8 +2943,8 @@ static inline struct page *dev_alloc_page(void) * @page: The page that was allocated from skb_alloc_page * @skb: The skb that may need pfmemalloc set */ -static inline void skb_propagate_pfmemalloc(struct page *page, - struct sk_buff *skb) +static inline void skb_propagate_pfmemalloc(const struct page *page, + struct sk_buff *skb) { if (page_is_pfmemalloc(page)) skb->pfmemalloc = true; -- cgit v1.2.3 From bc38f30f8dbce0afb8af05d917bee084b1329418 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Tue, 2 Feb 2021 13:31:21 +0000 Subject: net: introduce common dev_page_is_reusable() A bunch of drivers test the page before reusing/recycling for two common conditions: - if a page was allocated under memory pressure (pfmemalloc page); - if a page was allocated at a distant memory node (to exclude slowdowns). Introduce a new common inline for doing this, with likely() already folded inside to make driver code a bit simpler. Suggested-by: David Rientjes Suggested-by: Jakub Kicinski Cc: John Hubbard Signed-off-by: Alexander Lobakin Reviewed-by: Jesse Brandeburg Acked-by: David Rientjes Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b027526da4f9..0e42c53b8ca9 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2938,6 +2938,22 @@ static inline struct page *dev_alloc_page(void) return dev_alloc_pages(0); } +/** + * dev_page_is_reusable - check whether a page can be reused for network Rx + * @page: the page to test + * + * A page shouldn't be considered for reusing/recycling if it was allocated + * under memory pressure or at a distant memory node. + * + * Returns false if this page should be returned to page allocator, true + * otherwise. + */ +static inline bool dev_page_is_reusable(const struct page *page) +{ + return likely(page_to_nid(page) == numa_mem_id() && + !page_is_pfmemalloc(page)); +} + /** * skb_propagate_pfmemalloc - Propagate pfmemalloc if skb is allocated after RX page * @page: The page that was allocated from skb_alloc_page -- cgit v1.2.3 From 1faba27f11c8da244e793546a1b35a9b1da8208e Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 3 Feb 2021 15:51:09 +0200 Subject: ipv6: silence compilation warning for non-IPV6 builds The W=1 compilation of allmodconfig generates the following warning: net/ipv6/icmp.c:448:6: warning: no previous prototype for 'icmp6_send' [-Wmissing-prototypes] 448 | void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, | ^~~~~~~~~~ Fix it by providing function declaration for builds with ipv6 as a module. Signed-off-by: Leon Romanovsky Signed-off-by: Jakub Kicinski --- include/linux/icmpv6.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h index 1b3371ae8193..452d8978ffc7 100644 --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -16,9 +16,9 @@ static inline struct icmp6hdr *icmp6_hdr(const struct sk_buff *skb) typedef void ip6_icmp_send_t(struct sk_buff *skb, u8 type, u8 code, __u32 info, const struct in6_addr *force_saddr); -#if IS_BUILTIN(CONFIG_IPV6) void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, const struct in6_addr *force_saddr); +#if IS_BUILTIN(CONFIG_IPV6) static inline void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) { icmp6_send(skb, type, code, info, NULL); -- cgit v1.2.3 From 151f6ff78cdf1d6de76e90556cfc43f1e48abe18 Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Thu, 4 Feb 2021 17:17:06 +0300 Subject: software node: Provide replacement for device_add_properties() At the moment the function device_del() is calling device_remove_properties() unconditionally. That will result into the reference count of the software node attached to the device being decremented, and in most cases it will hit 0 at that point. So in practice device_del() will unregister the software node attached to the device, even if that was not the intention of the caller. Right now software nodes can not be reused or shared because of that. So device_del() can not unregister the software nodes unconditionally like that. Unfortunately some of the users of device_add_properties() are now relying on this behaviour. Because of that, and also in general, we do need a function that can offer similar behaviour where the lifetime of the software node is bound to the lifetime of the device. But it just has to be a separate function so the behaviour is optional. We can not remove the device_remove_properties() call from device_del() before we have that new function, and before we have replaced device_add_properties() calls with it in all the places that require that behaviour. This adds function device_create_managed_software_node() that can be used for exactly that purpose. Software nodes created with it are declared "managed", and separate handling for those nodes is added to the software node code. The reference count of the "managed" nodes is decremented when the device they are attached to is removed. This will not affect the other nodes that are not declared "managed". The function device_create_managed_software_node() has also one additional feature that device_add_properties() does not have. It allows the software nodes created with it to be part of a node hierarchy by taking also an optional parent node as parameter. Reviewed-by: Rafael J. Wysocki Signed-off-by: Heikki Krogerus Link: https://lore.kernel.org/r/20210204141711.53775-2-heikki.krogerus@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/property.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index b0e413dc5927..dafccfce0262 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -491,4 +491,8 @@ void fwnode_remove_software_node(struct fwnode_handle *fwnode); int device_add_software_node(struct device *dev, const struct software_node *swnode); void device_remove_software_node(struct device *dev); +int device_create_managed_software_node(struct device *dev, + const struct property_entry *properties, + const struct software_node *parent); + #endif /* _LINUX_PROPERTY_H_ */ -- cgit v1.2.3 From a8c3209998afb5c4941b49e35b513cea9050cb4a Mon Sep 17 00:00:00 2001 From: Andres Beltran Date: Tue, 8 Dec 2020 05:53:11 +0100 Subject: Drivers: hv: vmbus: Copy packets sent by Hyper-V out of the ring buffer Pointers to ring-buffer packets sent by Hyper-V are used within the guest VM. Hyper-V can send packets with erroneous values or modify packet fields after they are processed by the guest. To defend against these scenarios, return a copy of the incoming VMBus packet after validating its length and offset fields in hv_pkt_iter_first(). In this way, the packet can no longer be modified by the host. Signed-off-by: Andres Beltran Co-developed-by: Andrea Parri (Microsoft) Signed-off-by: Andrea Parri (Microsoft) Cc: "David S. Miller" Cc: Jakub Kicinski Cc: "James E.J. Bottomley" Cc: "Martin K. Petersen" Cc: netdev@vger.kernel.org Cc: linux-scsi@vger.kernel.org Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20201208045311.10244-1-parri.andrea@gmail.com Signed-off-by: Wei Liu --- include/linux/hyperv.h | 48 ++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 40 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 5ddb479c4d4c..fbae8406d5d4 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -181,6 +181,10 @@ struct hv_ring_buffer_info { * being freed while the ring buffer is being accessed. */ struct mutex ring_buffer_mutex; + + /* Buffer that holds a copy of an incoming host packet */ + void *pkt_buffer; + u32 pkt_buffer_size; }; @@ -787,6 +791,8 @@ struct vmbus_device { bool perf_device; }; +#define VMBUS_DEFAULT_MAX_PKT_SIZE 4096 + struct vmbus_channel { struct list_head listentry; @@ -1008,6 +1014,9 @@ struct vmbus_channel { /* request/transaction ids for VMBus */ struct vmbus_requestor requestor; u32 rqstor_size; + + /* The max size of a packet on this channel */ + u32 max_pkt_size; }; u64 vmbus_next_request_id(struct vmbus_requestor *rqstor, u64 rqst_addr); @@ -1642,32 +1651,55 @@ static inline u32 hv_pkt_datalen(const struct vmpacket_descriptor *desc) } +struct vmpacket_descriptor * +hv_pkt_iter_first_raw(struct vmbus_channel *channel); + struct vmpacket_descriptor * hv_pkt_iter_first(struct vmbus_channel *channel); struct vmpacket_descriptor * __hv_pkt_iter_next(struct vmbus_channel *channel, - const struct vmpacket_descriptor *pkt); + const struct vmpacket_descriptor *pkt, + bool copy); void hv_pkt_iter_close(struct vmbus_channel *channel); -/* - * Get next packet descriptor from iterator - * If at end of list, return NULL and update host. - */ static inline struct vmpacket_descriptor * -hv_pkt_iter_next(struct vmbus_channel *channel, - const struct vmpacket_descriptor *pkt) +hv_pkt_iter_next_pkt(struct vmbus_channel *channel, + const struct vmpacket_descriptor *pkt, + bool copy) { struct vmpacket_descriptor *nxt; - nxt = __hv_pkt_iter_next(channel, pkt); + nxt = __hv_pkt_iter_next(channel, pkt, copy); if (!nxt) hv_pkt_iter_close(channel); return nxt; } +/* + * Get next packet descriptor without copying it out of the ring buffer + * If at end of list, return NULL and update host. + */ +static inline struct vmpacket_descriptor * +hv_pkt_iter_next_raw(struct vmbus_channel *channel, + const struct vmpacket_descriptor *pkt) +{ + return hv_pkt_iter_next_pkt(channel, pkt, false); +} + +/* + * Get next packet descriptor from iterator + * If at end of list, return NULL and update host. + */ +static inline struct vmpacket_descriptor * +hv_pkt_iter_next(struct vmbus_channel *channel, + const struct vmpacket_descriptor *pkt) +{ + return hv_pkt_iter_next_pkt(channel, pkt, true); +} + #define foreach_vmbus_pkt(pkt, channel) \ for (pkt = hv_pkt_iter_first(channel); pkt; \ pkt = hv_pkt_iter_next(channel, pkt)) -- cgit v1.2.3 From 06caa778d8b2fbcb4ac3878751e39d116424ba9b Mon Sep 17 00:00:00 2001 From: Andres Beltran Date: Mon, 9 Nov 2020 11:07:04 +0100 Subject: hv_utils: Add validation for untrusted Hyper-V values For additional robustness in the face of Hyper-V errors or malicious behavior, validate all values that originate from packets that Hyper-V has sent to the guest in the host-to-guest ring buffer. Ensure that invalid values cannot cause indexing off the end of the icversion_data array in vmbus_prep_negotiate_resp(). Signed-off-by: Andres Beltran Co-developed-by: Andrea Parri (Microsoft) Signed-off-by: Andrea Parri (Microsoft) Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20201109100704.9152-1-parri.andrea@gmail.com Signed-off-by: Wei Liu --- include/linux/hyperv.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index fbae8406d5d4..2ea967bc17ad 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1480,6 +1480,7 @@ void vmbus_free_mmio(resource_size_t start, resource_size_t size); #define ICMSGTYPE_SHUTDOWN 3 #define ICMSGTYPE_TIMESYNC 4 #define ICMSGTYPE_VSS 5 +#define ICMSGTYPE_FCOPY 7 #define ICMSGHDRFLAG_TRANSACTION 1 #define ICMSGHDRFLAG_REQUEST 2 @@ -1523,6 +1524,12 @@ struct icmsg_hdr { u8 reserved[2]; } __packed; +#define IC_VERSION_NEGOTIATION_MAX_VER_COUNT 100 +#define ICMSG_HDR (sizeof(struct vmbuspipe_hdr) + sizeof(struct icmsg_hdr)) +#define ICMSG_NEGOTIATE_PKT_SIZE(icframe_vercnt, icmsg_vercnt) \ + (ICMSG_HDR + offsetof(struct icmsg_negotiate, icversion_data) + \ + (((icframe_vercnt) + (icmsg_vercnt)) * sizeof(struct ic_version))) + struct icmsg_negotiate { u16 icframe_vercnt; u16 icmsg_vercnt; @@ -1578,7 +1585,7 @@ struct hyperv_service_callback { }; #define MAX_SRV_VER 0x7ffffff -extern bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp, u8 *buf, +extern bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp, u8 *buf, u32 buflen, const int *fw_version, int fw_vercnt, const int *srv_version, int srv_vercnt, int *nego_fw_version, int *nego_srv_version); -- cgit v1.2.3 From e4d221b42354b2e2ddb9187a806afb651eee2cda Mon Sep 17 00:00:00 2001 From: "Andrea Parri (Microsoft)" Date: Wed, 9 Dec 2020 08:08:26 +0100 Subject: Drivers: hv: vmbus: Resolve race condition in vmbus_onoffer_rescind() An erroneous or malicious host could send multiple rescind messages for a same channel. In vmbus_onoffer_rescind(), the guest maps the channel ID to obtain a pointer to the channel object and it eventually releases such object and associated data. The host could time rescind messages and lead to an use-after-free. Add a new flag to the channel structure to make sure that only one instance of vmbus_onoffer_rescind() can get the reference to the channel object. Reported-by: Juan Vazquez Signed-off-by: Andrea Parri (Microsoft) Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20201209070827.29335-6-parri.andrea@gmail.com Signed-off-by: Wei Liu --- include/linux/hyperv.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 2ea967bc17ad..f0d48a368f13 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -809,6 +809,7 @@ struct vmbus_channel { u8 monitor_bit; bool rescind; /* got rescind msg */ + bool rescind_ref; /* got rescind msg, got channel reference */ struct completion rescind_event; u32 ringbuffer_gpadlhandle; -- cgit v1.2.3 From a7a5acba0e06b8f9923faa1a726f0ac1380b719a Mon Sep 17 00:00:00 2001 From: Tudor Ambarus Date: Thu, 21 Jan 2021 13:05:45 +0200 Subject: mtd: spi-nor: Add Global Block Unlock command The Global Block Unlock command has different names depending on the manufacturer, but always the same command value: 0x98. Macronix's MX25U12835F names it Gang Block Unlock, Winbond's W25Q128FV names it Global Block Unlock and Microchip's SST26VF064B names it Global Block Protection Unlock. Used in the Individual Block Protection mode, which is mutually exclusive with the Block Protection mode (BP0-3). Signed-off-by: Tudor Ambarus Reviewed-by: Pratyush Yadav Reviewed-by: Michael Walle Link: https://lore.kernel.org/r/20210121110546.382633-1-tudor.ambarus@microchip.com --- include/linux/mtd/spi-nor.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index d13958de6d8a..a0d572855444 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -53,6 +53,7 @@ #define SPINOR_OP_WREAR 0xc5 /* Write Extended Address Register */ #define SPINOR_OP_SRSTEN 0x66 /* Software Reset Enable */ #define SPINOR_OP_SRST 0x99 /* Software Reset */ +#define SPINOR_OP_GBULK 0x98 /* Global Block Unlock */ /* 4-byte address opcodes - used on Spansion and some Macronix flashes. */ #define SPINOR_OP_READ_4B 0x13 /* Read data bytes (low frequency) */ -- cgit v1.2.3 From 3ce60f443b143e649aa26cd3f668d645434647ac Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Wed, 3 Feb 2021 15:01:29 +0200 Subject: IB/mlx5: Move mlx5_port_caps from mlx5_core_dev to mlx5_ib_dev mlx5_port_caps are RDMA specific capabilities. These are not used by the mlx5_core_device at all. Move them to mlx5_ib_dev where it is used and reduce the scope of it to multiple drivers. Link: https://lore.kernel.org/r/20210203130133.4057329-2-leon@kernel.org Signed-off-by: Parav Pandit Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/linux/mlx5/driver.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f93bfe7473aa..11558c2e99f0 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -305,13 +305,6 @@ struct mlx5_cmd { struct mlx5_cmd_stats *stats; }; -struct mlx5_port_caps { - int gid_table_len; - int pkey_table_len; - u8 ext_port_cap; - bool has_smi; -}; - struct mlx5_cmd_mailbox { void *buf; dma_addr_t dma; @@ -694,7 +687,6 @@ struct mlx5_core_dev { u8 rev_id; char board_id[MLX5_BOARD_ID_LEN]; struct mlx5_cmd cmd; - struct mlx5_port_caps port_caps[MLX5_MAX_PORTS]; struct { u32 hca_cur[MLX5_CAP_NUM][MLX5_UN_SZ_DW(hca_cap_union)]; u32 hca_max[MLX5_CAP_NUM][MLX5_UN_SZ_DW(hca_cap_union)]; -- cgit v1.2.3 From 10742efc20a429b2040658af685d6bb2aa674a73 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Thu, 21 Jan 2021 19:41:52 +0200 Subject: net/mlx5e: VF tunnel TX traffic offloading When tunnel endpoint is on VF, driver still assumes that endpoint is on uplink and incorrectly configures encap rule offload according to that assumption. As a result, traffic is sent directly to the uplink and rules installed on representor of tunnel endpoint VF are ignored. Implement following changes to allow offloading tx traffic with tunnel endpoint on VF: - For tunneling flows perform route lookup on route and out devices pair. If out device is uplink and route device is VF of same physical port, then modify packet reg_c_0 metadata register (source port) with the value of VF vport. Use eswitch vhca_id->vport mapping introduced in one of previous patches in the series to obtain vport from route netdevice. - Recirculate encapsulated packets to VF vport in order to apply any flow rules installed on VF representor that match on encapsulated traffic. Only enable support for this functionality when all following conditions are true: - Hardware advertises capability to preserve reg_c_0 value on packet recirculation. - Vport metadata matching is enabled. - Termination tables are to be used by the flow. Example TC rules for VF tunnel traffic: 1. Rule that redirects packets from UL to VF rep that has the tunnel endpoint IP address: $ tc -s filter show dev enp8s0f0 ingress filter protocol ip pref 4 flower chain 0 filter protocol ip pref 4 flower chain 0 handle 0x1 dst_mac 16:c9:a0:2d:69:2c src_mac 0c:42:a1:58:ab:e4 eth_type ipv4 ip_flags nofrag in_hw in_hw_count 1 action order 1: mirred (Egress Redirect to device enp8s0f0_0) stolen index 3 ref 1 bind 1 installed 377 sec used 0 sec Action statistics: Sent 114096 bytes 952 pkt (dropped 0, overlimits 0 requeues 0) Sent software 0 bytes 0 pkt Sent hardware 114096 bytes 952 pkt backlog 0b 0p requeues 0 cookie 878fa48d8c423fc08c3b6ca599b50a97 no_percpu used_hw_stats delayed 2. Rule that decapsulates the tunneled flow and redirects to destination VF representor: $ tc -s filter show dev vxlan_sys_4789 ingress filter protocol ip pref 4 flower chain 0 filter protocol ip pref 4 flower chain 0 handle 0x1 dst_mac ca:2e:a7:3f:f5:0f src_mac 0a:40:bd:30:89:99 eth_type ipv4 enc_dst_ip 7.7.7.5 enc_src_ip 7.7.7.1 enc_key_id 98 enc_dst_port 4789 enc_tos 0 ip_flags nofrag in_hw in_hw_count 1 action order 1: tunnel_key unset pipe index 2 ref 1 bind 1 installed 434 sec used 434 sec Action statistics: Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 used_hw_stats delayed action order 2: mirred (Egress Redirect to device enp8s0f0_1) stolen index 4 ref 1 bind 1 installed 434 sec used 0 sec Action statistics: Sent 129936 bytes 1082 pkt (dropped 0, overlimits 0 requeues 0) Sent software 0 bytes 0 pkt Sent hardware 129936 bytes 1082 pkt backlog 0b 0p requeues 0 cookie ac17cf398c4c69e4a5b2f7aabd1b88ff no_percpu used_hw_stats delayed Co-developed-by: Dmytro Linkin Signed-off-by: Dmytro Linkin Signed-off-by: Vlad Buslov Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/eswitch.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index 29fd832950e0..67e341274a22 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -96,6 +96,8 @@ static inline u32 mlx5_eswitch_get_vport_metadata_mask(void) u32 mlx5_eswitch_get_vport_metadata_for_match(struct mlx5_eswitch *esw, u16 vport_num); +u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw, + u16 vport_num); u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev); #else /* CONFIG_MLX5_ESWITCH */ -- cgit v1.2.3 From 48d216e5596a58e3cfa6d4548343f982c5921b79 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Mon, 31 Aug 2020 16:18:19 +0300 Subject: net/mlx5e: Refactor reg_c1 usage Following patch in series uses reg_c1 in eswitch code. To use reg_c1 helpers in both TC and eswitch code, refactor existing helpers according to similar use case of reg_c0 and move the functionality into eswitch.h. Calculate reg mappings length from new defines to ensure that they are always in sync and only need to be changed in single place. Signed-off-by: Vlad Buslov Signed-off-by: Dmytro Linkin Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/eswitch.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index 67e341274a22..3b20e84049c1 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -98,6 +98,25 @@ u32 mlx5_eswitch_get_vport_metadata_for_match(struct mlx5_eswitch *esw, u16 vport_num); u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw, u16 vport_num); + +/* Reg C1 usage: + * Reg C1 = < ESW_TUN_ID(12) | ESW_TUN_OPTS(12) | ESW_ZONE_ID(8) > + * + * Highest 12 bits of reg c1 is the encapsulation tunnel id, next 12 bits is + * encapsulation tunnel options, and the lowest 8 bits are used for zone id. + * + * Zone id is used to restore CT flow when packet misses on chain. + * + * Tunnel id and options are used together to restore the tunnel info metadata + * on miss and to support inner header rewrite by means of implicit chain 0 + * flows. + */ +#define ESW_ZONE_ID_BITS 8 +#define ESW_TUN_OPTS_BITS 12 +#define ESW_TUN_ID_BITS 12 +#define ESW_TUN_OFFSET ESW_ZONE_ID_BITS +#define ESW_ZONE_ID_MASK GENMASK(ESW_ZONE_ID_BITS - 1, 0) + u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev); #else /* CONFIG_MLX5_ESWITCH */ -- cgit v1.2.3 From 8e404fefa58b6138531e3d4b5647ee79f75ae9a8 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Mon, 31 Aug 2020 16:18:57 +0300 Subject: net/mlx5e: Match recirculated packet miss in slow table using reg_c1 Previous patch in series that implements stack devices RX path implements indirect table rules that match on tunnel VNI. After such rule is created all tunnel traffic is recirculated to root table. However, recirculated packet might not match on any rules installed in the table (for example, when IP traffic follows ARP traffic). In that case packets appear on representor of tunnel endpoint VF instead being redirected to the VF itself. Extend slow table with additional flow group that matches on reg_c0 (source port value set by indirect tables implemented by previous patch in series) and reg_c1 (special 0xFFF mark). When creating offloads fdb tables, install one rule per VF vport to match on recirculated miss packets and redirect them to appropriate VF vport. Modify indirect tables code to also rewrite reg_c1 with special 0xFFF mark. Implementation reuses reg_c1 tunnel id bits. This is safe to do because recirculated packets are always matched before decapsulation. Signed-off-by: Vlad Buslov Signed-off-by: Dmytro Linkin Reviewed-by: Roi Dayan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/eswitch.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index 3b20e84049c1..994c2c8cb4fd 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -114,8 +114,16 @@ u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw, #define ESW_ZONE_ID_BITS 8 #define ESW_TUN_OPTS_BITS 12 #define ESW_TUN_ID_BITS 12 -#define ESW_TUN_OFFSET ESW_ZONE_ID_BITS +#define ESW_TUN_OPTS_OFFSET ESW_ZONE_ID_BITS +#define ESW_TUN_OFFSET ESW_TUN_OPTS_OFFSET #define ESW_ZONE_ID_MASK GENMASK(ESW_ZONE_ID_BITS - 1, 0) +#define ESW_TUN_OPTS_MASK GENMASK(32 - ESW_TUN_ID_BITS - 1, ESW_TUN_OPTS_OFFSET) +#define ESW_TUN_MASK GENMASK(31, ESW_TUN_OFFSET) +#define ESW_TUN_ID_SLOW_TABLE_GOTO_VPORT 0 /* 0 is not a valid tunnel id */ +#define ESW_TUN_OPTS_SLOW_TABLE_GOTO_VPORT 0xFFF /* 0xFFF is a reserved mapping */ +#define ESW_TUN_SLOW_TABLE_GOTO_VPORT ((ESW_TUN_ID_SLOW_TABLE_GOTO_VPORT << ESW_TUN_OPTS_BITS) | \ + ESW_TUN_OPTS_SLOW_TABLE_GOTO_VPORT) +#define ESW_TUN_SLOW_TABLE_GOTO_VPORT_MARK ESW_TUN_OPTS_MASK u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev); #else /* CONFIG_MLX5_ESWITCH */ -- cgit v1.2.3 From 52c2d15703c3a900d5f78cd599b823db40d5100b Mon Sep 17 00:00:00 2001 From: Thinh Nguyen Date: Tue, 19 Jan 2021 17:36:14 -0800 Subject: usb: common: Parse for USB SSP genXxY The USB "maximum-speed" property can now take the SSP signaling rate generation and lane count with these new strings: "super-speed-plus-gen2x2" "super-speed-plus-gen2x1" "super-speed-plus-gen1x2" Introduce usb_get_maximum_ssp_rate() to parse for the corresponding usb_ssp_rate enum. The original usb_get_maximum_speed() will return USB_SPEED_SUPER_PLUS if it matches one of these new strings. Signed-off-by: Thinh Nguyen Link: https://lore.kernel.org/r/f8ed896313d8cd8e2d2b540fc82db92b3ddf8a47.1611106162.git.Thinh.Nguyen@synopsys.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/ch9.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/ch9.h b/include/linux/usb/ch9.h index 86c50907634e..abdd310c77f0 100644 --- a/include/linux/usb/ch9.h +++ b/include/linux/usb/ch9.h @@ -71,6 +71,17 @@ extern const char *usb_speed_string(enum usb_device_speed speed); */ extern enum usb_device_speed usb_get_maximum_speed(struct device *dev); +/** + * usb_get_maximum_ssp_rate - Get the signaling rate generation and lane count + * of a SuperSpeed Plus capable device. + * @dev: Pointer to the given USB controller device + * + * If the string from "maximum-speed" property is super-speed-plus-genXxY where + * 'X' is the generation number and 'Y' is the number of lanes, then this + * function returns the corresponding enum usb_ssp_rate. + */ +extern enum usb_ssp_rate usb_get_maximum_ssp_rate(struct device *dev); + /** * usb_state_string - Returns human readable name for the state. * @state: The state to return a human-readable name for. If it's not -- cgit v1.2.3 From b358e2122b9d7aa99f681d4edfafd999845d16ff Mon Sep 17 00:00:00 2001 From: Kevin Hao Date: Thu, 4 Feb 2021 18:56:35 +0800 Subject: mm: page_frag: Introduce page_frag_alloc_align() In the current implementation of page_frag_alloc(), it doesn't have any align guarantee for the returned buffer address. But for some hardwares they do require the DMA buffer to be aligned correctly, so we would have to use some workarounds like below if the buffers allocated by the page_frag_alloc() are used by these hardwares for DMA. buf = page_frag_alloc(really_needed_size + align); buf = PTR_ALIGN(buf, align); These codes seems ugly and would waste a lot of memories if the buffers are used in a network driver for the TX/RX. So introduce page_frag_alloc_align() to make sure that an aligned buffer address is returned. Signed-off-by: Kevin Hao Acked-by: Vlastimil Babka Reviewed-by: Alexander Duyck Signed-off-by: Jakub Kicinski --- include/linux/gfp.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 6e479e9c48ce..80544d5c08e7 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -583,8 +583,16 @@ extern void free_pages(unsigned long addr, unsigned int order); struct page_frag_cache; extern void __page_frag_cache_drain(struct page *page, unsigned int count); -extern void *page_frag_alloc(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask); +extern void *page_frag_alloc_align(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask, + unsigned int align_mask); + +static inline void *page_frag_alloc(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask) +{ + return page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u); +} + extern void page_frag_free(void *addr); #define __free_page(page) __free_pages((page), 0) -- cgit v1.2.3 From 3f6e687dff395da43b056c18150a423bc7bf5d14 Mon Sep 17 00:00:00 2001 From: Kevin Hao Date: Thu, 4 Feb 2021 18:56:36 +0800 Subject: net: Introduce {netdev,napi}_alloc_frag_align() In the current implementation of {netdev,napi}_alloc_frag(), it doesn't have any align guarantee for the returned buffer address, But for some hardwares they do require the DMA buffer to be aligned correctly, so we would have to use some workarounds like below if the buffers allocated by the {netdev,napi}_alloc_frag() are used by these hardwares for DMA. buf = napi_alloc_frag(really_needed_size + align); buf = PTR_ALIGN(buf, align); These codes seems ugly and would waste a lot of memories if the buffers are used in a network driver for the TX/RX. We have added the align support for the page_frag functions, so add the corresponding {netdev,napi}_frag functions. Signed-off-by: Kevin Hao Reviewed-by: Alexander Duyck Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 36 ++++++++++++++++++++++++++++++++++-- 1 file changed, 34 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0e42c53b8ca9..0a4e91a2f873 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2818,7 +2818,26 @@ void skb_queue_purge(struct sk_buff_head *list); unsigned int skb_rbtree_purge(struct rb_root *root); -void *netdev_alloc_frag(unsigned int fragsz); +void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask); + +/** + * netdev_alloc_frag - allocate a page fragment + * @fragsz: fragment size + * + * Allocates a frag from a page for receive buffer. + * Uses GFP_ATOMIC allocations. + */ +static inline void *netdev_alloc_frag(unsigned int fragsz) +{ + return __netdev_alloc_frag_align(fragsz, ~0u); +} + +static inline void *netdev_alloc_frag_align(unsigned int fragsz, + unsigned int align) +{ + WARN_ON_ONCE(!is_power_of_2(align)); + return __netdev_alloc_frag_align(fragsz, -align); +} struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int length, gfp_t gfp_mask); @@ -2877,7 +2896,20 @@ static inline void skb_free_frag(void *addr) page_frag_free(addr); } -void *napi_alloc_frag(unsigned int fragsz); +void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask); + +static inline void *napi_alloc_frag(unsigned int fragsz) +{ + return __napi_alloc_frag_align(fragsz, ~0u); +} + +static inline void *napi_alloc_frag_align(unsigned int fragsz, + unsigned int align) +{ + WARN_ON_ONCE(!is_power_of_2(align)); + return __napi_alloc_frag_align(fragsz, -align); +} + struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int length, gfp_t gfp_mask); static inline struct sk_buff *napi_alloc_skb(struct napi_struct *napi, -- cgit v1.2.3 From 167790abb90fa073d8341ee0e408ccad3d2109cd Mon Sep 17 00:00:00 2001 From: Bard Liao Date: Fri, 22 Jan 2021 15:06:29 +0800 Subject: soundwire: export sdw_write/read_no_pm functions sdw_write_no_pm and sdw_read_no_pm are useful when we want to do IO without touching PM. Fixes: 0231453bc08f ('soundwire: bus: add clock stop helpers') Fixes: 60ee9be25571 ('soundwire: bus: add PM/no-PM versions of read/write functions') Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20210122070634.12825-5-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index f0b01b728640..d08039d65825 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -1005,6 +1005,8 @@ int sdw_bus_exit_clk_stop(struct sdw_bus *bus); int sdw_read(struct sdw_slave *slave, u32 addr); int sdw_write(struct sdw_slave *slave, u32 addr, u8 value); +int sdw_write_no_pm(struct sdw_slave *slave, u32 addr, u8 value); +int sdw_read_no_pm(struct sdw_slave *slave, u32 addr); int sdw_nread(struct sdw_slave *slave, u32 addr, size_t count, u8 *val); int sdw_nwrite(struct sdw_slave *slave, u32 addr, size_t count, u8 *val); -- cgit v1.2.3 From e17fe6579de023725ec22a16965e9099e4a05ac9 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Fri, 15 Jan 2021 10:18:16 -0800 Subject: fs-verity: add FS_IOC_READ_VERITY_METADATA ioctl Add an ioctl FS_IOC_READ_VERITY_METADATA which will allow reading verity metadata from a file that has fs-verity enabled, including: - The Merkle tree - The fsverity_descriptor (not including the signature if present) - The built-in signature, if present This ioctl has similar semantics to pread(). It is passed the type of metadata to read (one of the above three), and a buffer, offset, and size. It returns the number of bytes read or an error. Separate patches will add support for each of the above metadata types. This patch just adds the ioctl itself. This ioctl doesn't make any assumption about where the metadata is stored on-disk. It does assume the metadata is in a stable format, but that's basically already the case: - The Merkle tree and fsverity_descriptor are defined by how fs-verity file digests are computed; see the "File digest computation" section of Documentation/filesystems/fsverity.rst. Technically, the way in which the levels of the tree are ordered relative to each other wasn't previously specified, but it's logical to put the root level first. - The built-in signature is the value passed to FS_IOC_ENABLE_VERITY. This ioctl is useful because it allows writing a server program that takes a verity file and serves it to a client program, such that the client can do its own fs-verity compatible verification of the file. This only makes sense if the client doesn't trust the server and if the server needs to provide the storage for the client. More concretely, there is interest in using this ability in Android to export APK files (which are protected by fs-verity) to "protected VMs". This would use Protected KVM (https://lwn.net/Articles/836693), which provides an isolated execution environment without having to trust the traditional "host". A "guest" VM can boot from a signed image and perform specific tasks in a minimum trusted environment using files that have fs-verity enabled on the host, without trusting the host or requiring that the guest has its own trusted storage. Technically, it would be possible to duplicate the metadata and store it in separate files for serving. However, that would be less efficient and would require extra care in userspace to maintain file consistency. In addition to the above, the ability to read the built-in signatures is useful because it allows a system that is using the in-kernel signature verification to migrate to userspace signature verification. Link: https://lore.kernel.org/r/20210115181819.34732-4-ebiggers@kernel.org Reviewed-by: Victor Hsieh Acked-by: Jaegeuk Kim Reviewed-by: Chao Yu Signed-off-by: Eric Biggers --- include/linux/fsverity.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h index c1144a450392..b568b3c7d095 100644 --- a/include/linux/fsverity.h +++ b/include/linux/fsverity.h @@ -138,6 +138,10 @@ int fsverity_file_open(struct inode *inode, struct file *filp); int fsverity_prepare_setattr(struct dentry *dentry, struct iattr *attr); void fsverity_cleanup_inode(struct inode *inode); +/* read_metadata.c */ + +int fsverity_ioctl_read_metadata(struct file *filp, const void __user *uarg); + /* verify.c */ bool fsverity_verify_page(struct page *page); @@ -183,6 +187,14 @@ static inline void fsverity_cleanup_inode(struct inode *inode) { } +/* read_metadata.c */ + +static inline int fsverity_ioctl_read_metadata(struct file *filp, + const void __user *uarg) +{ + return -EOPNOTSUPP; +} + /* verify.c */ static inline bool fsverity_verify_page(struct page *page) -- cgit v1.2.3 From a006050575745ca2be25118b90f1c37f454ac542 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 2 Feb 2021 13:13:25 +0100 Subject: module: use RCU to synchronize find_module Allow for a RCU-sched critical section around find_module, following the lower level find_module_all helper, and switch the two callers outside of module.c to use such a RCU-sched critical section instead of module_mutex. Reviewed-by: Petr Mladek Acked-by: Miroslav Benes Signed-off-by: Christoph Hellwig Signed-off-by: Jessica Yu --- include/linux/module.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 7a0bcb5b1ffc..a64aa84d1b18 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -586,7 +586,7 @@ static inline bool within_module(unsigned long addr, const struct module *mod) return within_module_init(addr, mod) || within_module_core(addr, mod); } -/* Search for module by name: must hold module_mutex. */ +/* Search for module by name: must be in a RCU-sched critical section. */ struct module *find_module(const char *name); struct symsearch { -- cgit v1.2.3 From 4331667fa14e6643859d0498b34281185eb8018b Mon Sep 17 00:00:00 2001 From: Jiapeng Chong Date: Fri, 5 Feb 2021 14:56:39 +0800 Subject: ssb: Use true and false for bool variable MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix the following coccicheck warnings: ./include/linux/ssb/ssb_driver_gige.h:89:8-9: WARNING: return of 0/1 in function 'ssb_gige_one_dma_at_once' with return type bool. ./include/linux/ssb/ssb_driver_gige.h:79:8-9: WARNING: return of 0/1 in function 'ssb_gige_have_roboswitch' with return type bool. ./include/linux/ssb/ssb_driver_gige.h:182:8-9: WARNING: return of 0/1 in function 'ssb_gige_must_flush_posted_writes' with return type bool. ./include/linux/ssb/ssb_driver_gige.h:178:8-9: WARNING: return of 0/1 in function 'ssb_gige_one_dma_at_once' with return type bool. ./include/linux/ssb/ssb_driver_gige.h:174:8-9: WARNING: return of 0/1 in function 'ssb_gige_have_roboswitch' with return type bool. ./include/linux/ssb/ssb_driver_gige.h:170:8-9: WARNING: return of 0/1 in function 'ssb_gige_is_rgmii' with return type bool. ./include/linux/ssb/ssb_driver_gige.h:162:8-9: WARNING: return of 0/1 in function 'pdev_is_ssb_gige_core' with return type bool. Reported-by: Abaci Robot Signed-off-by: Jiapeng Chong Acked-by: Michael Büsch Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/1612508199-92282-1-git-send-email-jiapeng.chong@linux.alibaba.com --- include/linux/ssb/ssb_driver_gige.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ssb/ssb_driver_gige.h b/include/linux/ssb/ssb_driver_gige.h index 31593b34608e..15ba0df1ee0d 100644 --- a/include/linux/ssb/ssb_driver_gige.h +++ b/include/linux/ssb/ssb_driver_gige.h @@ -76,7 +76,7 @@ static inline bool ssb_gige_have_roboswitch(struct pci_dev *pdev) if (dev) return !!(dev->dev->bus->sprom.boardflags_lo & SSB_GIGE_BFL_ROBOSWITCH); - return 0; + return false; } /* Returns whether we can only do one DMA at once. */ @@ -86,7 +86,7 @@ static inline bool ssb_gige_one_dma_at_once(struct pci_dev *pdev) if (dev) return ((dev->dev->bus->chip_id == 0x4785) && (dev->dev->bus->chip_rev < 2)); - return 0; + return false; } /* Returns whether we must flush posted writes. */ @@ -159,7 +159,7 @@ static inline void ssb_gige_exit(void) static inline bool pdev_is_ssb_gige_core(struct pci_dev *pdev) { - return 0; + return false; } static inline struct ssb_gige * pdev_to_ssb_gige(struct pci_dev *pdev) { @@ -167,19 +167,19 @@ static inline struct ssb_gige * pdev_to_ssb_gige(struct pci_dev *pdev) } static inline bool ssb_gige_is_rgmii(struct pci_dev *pdev) { - return 0; + return false; } static inline bool ssb_gige_have_roboswitch(struct pci_dev *pdev) { - return 0; + return false; } static inline bool ssb_gige_one_dma_at_once(struct pci_dev *pdev) { - return 0; + return false; } static inline bool ssb_gige_must_flush_posted_writes(struct pci_dev *pdev) { - return 0; + return false; } static inline int ssb_gige_get_macaddr(struct pci_dev *pdev, u8 *macaddr) { -- cgit v1.2.3 From 3e3552056ab42f883d7723eeb42fed712b66bacf Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 2 Feb 2021 13:13:27 +0100 Subject: kallsyms: only build {,module_}kallsyms_on_each_symbol when required kallsyms_on_each_symbol and module_kallsyms_on_each_symbol are only used by the livepatching code, so don't build them if livepatching is not enabled. Reviewed-by: Miroslav Benes Signed-off-by: Christoph Hellwig Signed-off-by: Jessica Yu --- include/linux/kallsyms.h | 17 ++++------------- include/linux/module.h | 16 ++++------------ 2 files changed, 8 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index 481273f0c72d..465060acc981 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -71,15 +71,14 @@ static inline void *dereference_symbol_descriptor(void *ptr) return ptr; } -#ifdef CONFIG_KALLSYMS -/* Lookup the address for a symbol. Returns 0 if not found. */ -unsigned long kallsyms_lookup_name(const char *name); - -/* Call a function on each kallsyms symbol in the core kernel */ int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, unsigned long), void *data); +#ifdef CONFIG_KALLSYMS +/* Lookup the address for a symbol. Returns 0 if not found. */ +unsigned long kallsyms_lookup_name(const char *name); + extern int kallsyms_lookup_size_offset(unsigned long addr, unsigned long *symbolsize, unsigned long *offset); @@ -108,14 +107,6 @@ static inline unsigned long kallsyms_lookup_name(const char *name) return 0; } -static inline int kallsyms_on_each_symbol(int (*fn)(void *, const char *, - struct module *, - unsigned long), - void *data) -{ - return 0; -} - static inline int kallsyms_lookup_size_offset(unsigned long addr, unsigned long *symbolsize, unsigned long *offset) diff --git a/include/linux/module.h b/include/linux/module.h index a64aa84d1b18..3ea4ffae608f 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -608,10 +608,6 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, /* Look for this name: can be of form module:name. */ unsigned long module_kallsyms_lookup_name(const char *name); -int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, - struct module *, unsigned long), - void *data); - extern void __noreturn __module_put_and_exit(struct module *mod, long code); #define module_put_and_exit(code) __module_put_and_exit(THIS_MODULE, code) @@ -795,14 +791,6 @@ static inline unsigned long module_kallsyms_lookup_name(const char *name) return 0; } -static inline int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, - struct module *, - unsigned long), - void *data) -{ - return 0; -} - static inline int register_module_notifier(struct notifier_block *nb) { /* no events will happen anyway, so this can always succeed */ @@ -891,4 +879,8 @@ static inline bool module_sig_ok(struct module *module) } #endif /* CONFIG_MODULE_SIG */ +int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, + struct module *, unsigned long), + void *data); + #endif /* _LINUX_MODULE_H */ -- cgit v1.2.3 From 922f2a7c822bf76dffb218331bd95b1eea3cf637 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 2 Feb 2021 13:13:28 +0100 Subject: module: mark module_mutex static Except for two lockdep asserts module_mutex is only used in module.c. Remove the two asserts given that the functions they are in are not exported and just called from the module code, and mark module_mutex static. Reviewed-by: Miroslav Benes Signed-off-by: Christoph Hellwig Signed-off-by: Jessica Yu --- include/linux/module.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 3ea4ffae608f..0f360c48fe92 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -550,8 +550,6 @@ static inline unsigned long kallsyms_symbol_value(const Elf_Sym *sym) } #endif -extern struct mutex module_mutex; - /* FIXME: It'd be nice to isolate modules during init, too, so they aren't used before they (may) fail. But presently too much code (IDE & SCSI) require entry into the module during init.*/ -- cgit v1.2.3 From 00cc2c1cd34f81f777085cb2d65267edcd403fd0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 2 Feb 2021 13:13:32 +0100 Subject: module: move struct symsearch to module.c struct symsearch is only used inside of module.h, so move the definition out of module.h. Reviewed-by: Miroslav Benes Reviewed-by: Emil Velikov Signed-off-by: Christoph Hellwig Signed-off-by: Jessica Yu --- include/linux/module.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 0f360c48fe92..da0f5966ee80 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -587,17 +587,6 @@ static inline bool within_module(unsigned long addr, const struct module *mod) /* Search for module by name: must be in a RCU-sched critical section. */ struct module *find_module(const char *name); -struct symsearch { - const struct kernel_symbol *start, *stop; - const s32 *crcs; - enum mod_license { - NOT_GPL_ONLY, - GPL_ONLY, - WILL_BE_GPL_ONLY, - } license; - bool unused; -}; - /* Returns 0 and fills in value, defined and namebuf, or -ERANGE if symnum out of range. */ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, -- cgit v1.2.3 From f1c3d73e973cfad85ff5d3d86086503e742d8c62 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 2 Feb 2021 13:13:33 +0100 Subject: module: remove EXPORT_SYMBOL_GPL_FUTURE As far as I can tell this has never been used at all, and certainly not any time recently. Reviewed-by: Miroslav Benes Reviewed-by: Emil Velikov Signed-off-by: Christoph Hellwig Signed-off-by: Jessica Yu --- include/linux/export.h | 1 - include/linux/module.h | 5 ----- 2 files changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/export.h b/include/linux/export.h index fceb5e855717..362b64f8d4a7 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -157,7 +157,6 @@ struct kernel_symbol { #define EXPORT_SYMBOL(sym) _EXPORT_SYMBOL(sym, "") #define EXPORT_SYMBOL_GPL(sym) _EXPORT_SYMBOL(sym, "_gpl") -#define EXPORT_SYMBOL_GPL_FUTURE(sym) _EXPORT_SYMBOL(sym, "_gpl_future") #define EXPORT_SYMBOL_NS(sym, ns) __EXPORT_SYMBOL(sym, "", #ns) #define EXPORT_SYMBOL_NS_GPL(sym, ns) __EXPORT_SYMBOL(sym, "_gpl", #ns) diff --git a/include/linux/module.h b/include/linux/module.h index da0f5966ee80..e6e50ee30412 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -411,11 +411,6 @@ struct module { bool async_probe_requested; - /* symbols that will be GPL-only in the near future. */ - const struct kernel_symbol *gpl_future_syms; - const s32 *gpl_future_crcs; - unsigned int num_gpl_future_syms; - /* Exception table */ unsigned int num_exentries; struct exception_table_entry *extable; -- cgit v1.2.3 From 367948220fcefcad1bf0d3d595a06efe0694acae Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 2 Feb 2021 13:13:34 +0100 Subject: module: remove EXPORT_UNUSED_SYMBOL* EXPORT_UNUSED_SYMBOL* is not actually used anywhere. Remove the unused functionality as we generally just remove unused code anyway. Reviewed-by: Miroslav Benes Reviewed-by: Emil Velikov Signed-off-by: Christoph Hellwig Signed-off-by: Jessica Yu --- include/linux/export.h | 8 -------- include/linux/module.h | 12 ------------ 2 files changed, 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/export.h b/include/linux/export.h index 362b64f8d4a7..6271a5d9c988 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -160,14 +160,6 @@ struct kernel_symbol { #define EXPORT_SYMBOL_NS(sym, ns) __EXPORT_SYMBOL(sym, "", #ns) #define EXPORT_SYMBOL_NS_GPL(sym, ns) __EXPORT_SYMBOL(sym, "_gpl", #ns) -#ifdef CONFIG_UNUSED_SYMBOLS -#define EXPORT_UNUSED_SYMBOL(sym) _EXPORT_SYMBOL(sym, "_unused") -#define EXPORT_UNUSED_SYMBOL_GPL(sym) _EXPORT_SYMBOL(sym, "_unused_gpl") -#else -#define EXPORT_UNUSED_SYMBOL(sym) -#define EXPORT_UNUSED_SYMBOL_GPL(sym) -#endif - #endif /* !__ASSEMBLY__ */ #endif /* _LINUX_EXPORT_H */ diff --git a/include/linux/module.h b/include/linux/module.h index e6e50ee30412..59f094fa6f74 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -392,18 +392,6 @@ struct module { const s32 *gpl_crcs; bool using_gplonly_symbols; -#ifdef CONFIG_UNUSED_SYMBOLS - /* unused exported symbols. */ - const struct kernel_symbol *unused_syms; - const s32 *unused_crcs; - unsigned int num_unused_syms; - - /* GPL-only, unused exported symbols. */ - unsigned int num_unused_gpl_syms; - const struct kernel_symbol *unused_gpl_syms; - const s32 *unused_gpl_crcs; -#endif - #ifdef CONFIG_MODULE_SIG /* Signature was verified. */ bool sig_ok; -- cgit v1.2.3 From 7aa382cfe714f61b0c29f02c31d389c506b4e2ae Mon Sep 17 00:00:00 2001 From: Hsin-Hsiung Wang Date: Sun, 7 Feb 2021 14:14:16 +0800 Subject: regulator: mt6315: Add support for MT6315 regulator The MT6315 is a regulator found on boards based on MediaTek MT8192 and probably other SoCs. It connects as a slave to SoC using SPMI. Signed-off-by: Hsin-Hsiung Wang Link: https://lore.kernel.org/r/1612678457-11548-3-git-send-email-hsin-hsiung.wang@mediatek.com Signed-off-by: Mark Brown --- include/linux/regulator/mt6315-regulator.h | 44 ++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) create mode 100644 include/linux/regulator/mt6315-regulator.h (limited to 'include/linux') diff --git a/include/linux/regulator/mt6315-regulator.h b/include/linux/regulator/mt6315-regulator.h new file mode 100644 index 000000000000..3b80d3f3910c --- /dev/null +++ b/include/linux/regulator/mt6315-regulator.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2021 MediaTek Inc. + */ + +#ifndef __LINUX_REGULATOR_MT6315_H +#define __LINUX_REGULATOR_MT6315_H + +#define MT6315_RP 3 +#define MT6315_PP 6 +#define MT6315_SP 7 + +enum { + MT6315_VBUCK1 = 0, + MT6315_VBUCK2, + MT6315_VBUCK3, + MT6315_VBUCK4, + MT6315_VBUCK_MAX, +}; + +/* Register */ +#define MT6315_TOP2_ELR7 0x139 +#define MT6315_TOP_TMA_KEY 0x39F +#define MT6315_TOP_TMA_KEY_H 0x3A0 +#define MT6315_BUCK_TOP_CON0 0x1440 +#define MT6315_BUCK_TOP_CON1 0x1443 +#define MT6315_BUCK_TOP_ELR0 0x1449 +#define MT6315_BUCK_TOP_ELR2 0x144B +#define MT6315_BUCK_TOP_ELR4 0x144D +#define MT6315_BUCK_TOP_ELR6 0x144F +#define MT6315_VBUCK1_DBG0 0x1499 +#define MT6315_VBUCK1_DBG4 0x149D +#define MT6315_VBUCK2_DBG0 0x1519 +#define MT6315_VBUCK2_DBG4 0x151D +#define MT6315_VBUCK3_DBG0 0x1599 +#define MT6315_VBUCK3_DBG4 0x159D +#define MT6315_VBUCK4_DBG0 0x1619 +#define MT6315_VBUCK4_DBG4 0x161D +#define MT6315_BUCK_TOP_4PHASE_ANA_CON42 0x16B1 + +#define PROTECTION_KEY_H 0x9C +#define PROTECTION_KEY 0xEA + +#endif /* __LINUX_REGULATOR_MT6315_H */ -- cgit v1.2.3 From 951f6ccfcbb7e4a18bf5fef1fb373d21e5831957 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Tue, 2 Feb 2021 11:19:24 +0100 Subject: mmc: core: Drop redundant member in struct mmc host The Kconfig option to use the blk-mq support was removed in commit 1bec43a3b181 ("mmc: core: Remove option not to use blk-mq"), but forgot to remove the use_blk_mq member in the struct mmc_host, let's fix it. Signed-off-by: Ulf Hansson Link: https://lore.kernel.org/r/20210202101924.69970-1-ulf.hansson@linaro.org --- include/linux/mmc/host.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 927ba7566617..26a3c7bc29ae 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -429,7 +429,6 @@ struct mmc_host { unsigned int doing_retune:1; /* re-tuning in progress */ unsigned int retune_now:1; /* do re-tuning at next req */ unsigned int retune_paused:1; /* re-tuning is temporarily disabled */ - unsigned int use_blk_mq:1; /* use blk-mq */ unsigned int retune_crc_disable:1; /* don't trigger retune upon crc */ unsigned int can_dma_map_merge:1; /* merging can be used */ -- cgit v1.2.3 From 40c735db06e16bf29c74c3626318719783be3784 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Tue, 2 Feb 2021 11:16:26 +0100 Subject: mmc: core: Drop redundant bouncesz from struct mmc_card The commit de3ee99b097d ("mmc: Delete bounce buffer handling") removed the bounce buffer handling from the mmc core, but forgot to remove the bouncesz member from the struct mmc_card, let's fix it. Signed-off-by: Ulf Hansson Link: https://lore.kernel.org/r/20210202101626.64503-1-ulf.hansson@linaro.org --- include/linux/mmc/card.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 42df06c6b19c..f9ad35dd6012 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -311,7 +311,6 @@ struct mmc_card { struct mmc_part part[MMC_NUM_PHY_PARTITION]; /* physical partitions */ unsigned int nr_parts; - unsigned int bouncesz; /* Bounce buffer size */ struct workqueue_struct *complete_wq; /* Private workqueue */ }; -- cgit v1.2.3 From 883c36a32fc031046218ef5802023d5aa54d6cb0 Mon Sep 17 00:00:00 2001 From: Bhaskar Chowdhury Date: Mon, 8 Feb 2021 17:19:28 +0530 Subject: spi: Change provied to provided in the file spi.h s/provied/provided/ Signed-off-by: Bhaskar Chowdhury Link: https://lore.kernel.org/r/20210208114928.32241-1-unixbhaskar@gmail.com Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 797ef28fa7d5..592897fa4f03 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -622,7 +622,7 @@ struct spi_controller { /* * These hooks are for drivers that use a generic implementation - * of transfer_one_message() provied by the core. + * of transfer_one_message() provided by the core. */ void (*set_cs)(struct spi_device *spi, bool enable); int (*transfer_one)(struct spi_controller *ctlr, struct spi_device *spi, -- cgit v1.2.3 From db783e769a950b3f9502dfbc0f7fdbea499a1da6 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Thu, 17 Dec 2020 08:34:20 +0000 Subject: mfd: Standardise MFD_CELL_* helper names Start all helpers with "MFD_CELL_". Cc: Gene Chen Cc: linux-mediatek@lists.infradead.org Signed-off-by: Lee Jones Reviewed-by: Linus Walleij Reviewed-by: Matthias Brugger Signed-off-by: Lee Jones --- include/linux/mfd/core.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h index 4b35baa14d30..2009c4b936d9 100644 --- a/include/linux/mfd/core.h +++ b/include/linux/mfd/core.h @@ -28,13 +28,13 @@ .id = (_id), \ } -#define OF_MFD_CELL_REG(_name, _res, _pdata, _pdsize, _id, _compat, _of_reg) \ +#define MFD_CELL_OF_REG(_name, _res, _pdata, _pdsize, _id, _compat, _of_reg) \ MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, _compat, _of_reg, true, NULL) -#define OF_MFD_CELL(_name, _res, _pdata, _pdsize, _id, _compat) \ +#define MFD_CELL_OF(_name, _res, _pdata, _pdsize, _id, _compat) \ MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, _compat, 0, false, NULL) -#define ACPI_MFD_CELL(_name, _res, _pdata, _pdsize, _id, _match) \ +#define MFD_CELL_ACPI(_name, _res, _pdata, _pdsize, _id, _match) \ MFD_CELL_ALL(_name, _res, _pdata, _pdsize, _id, NULL, 0, false, _match) #define MFD_CELL_BASIC(_name, _res, _pdata, _pdsize, _id) \ -- cgit v1.2.3 From 296f5568c6ee906e2a8db00adc751674f1745bd8 Mon Sep 17 00:00:00 2001 From: Russ Weight Date: Thu, 14 Jan 2021 15:16:48 -0800 Subject: mfd: intel-m10-bmc: Expose MAC address and count Create two sysfs entries for exposing the MAC address and count from the MAX10 BMC register space. The MAC address is the first in a sequential block of MAC addresses reserved for the FPGA card. The MAC count is the number of MAC addresses in the reserved block. Signed-off-by: Russ Weight Signed-off-by: Xu Yilun Signed-off-by: Lee Jones --- include/linux/mfd/intel-m10-bmc.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/intel-m10-bmc.h b/include/linux/mfd/intel-m10-bmc.h index c8ef2f1654a4..74d4e193966a 100644 --- a/include/linux/mfd/intel-m10-bmc.h +++ b/include/linux/mfd/intel-m10-bmc.h @@ -15,6 +15,15 @@ /* Register offset of system registers */ #define NIOS2_FW_VERSION 0x0 +#define M10BMC_MAC_LOW 0x10 +#define M10BMC_MAC_BYTE4 GENMASK(7, 0) +#define M10BMC_MAC_BYTE3 GENMASK(15, 8) +#define M10BMC_MAC_BYTE2 GENMASK(23, 16) +#define M10BMC_MAC_BYTE1 GENMASK(31, 24) +#define M10BMC_MAC_HIGH 0x14 +#define M10BMC_MAC_BYTE6 GENMASK(7, 0) +#define M10BMC_MAC_BYTE5 GENMASK(15, 8) +#define M10BMC_MAC_COUNT GENMASK(23, 16) #define M10BMC_TEST_REG 0x3c #define M10BMC_BUILD_VER 0x68 #define M10BMC_VER_MAJOR_MSK GENMASK(23, 16) -- cgit v1.2.3 From 02e550d5b706f034d24e7e46234eb1982f05a137 Mon Sep 17 00:00:00 2001 From: Jeff LaBundy Date: Sun, 17 Jan 2021 21:57:07 -0600 Subject: mfd: iqs62x: Do not poll during ATI After loading firmware, the driver triggers ATI (calibration) with the newly loaded register configuration in place. Next, the driver polls a register field to ensure ATI completed in a timely fashion and that the device is ready to sense. However, communicating with the device over I2C while ATI is under- way may induce noise in the device and cause ATI to fail. As such, the vendor recommends not to poll the device during ATI. To solve this problem, let the device naturally signal to the host that ATI is complete by way of an interrupt. A completion prevents the sub-devices from being registered until this happens. The former logic that scaled ATI timeout and filter settling delay is not carried forward with the new implementation, as it produces overly conservative delays at lower clock rates. Instead, a single pair of delays that covers all cases is used. Signed-off-by: Jeff LaBundy Signed-off-by: Lee Jones --- include/linux/mfd/iqs62x.h | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/iqs62x.h b/include/linux/mfd/iqs62x.h index 043d3b6de9ec..5ced55eae11b 100644 --- a/include/linux/mfd/iqs62x.h +++ b/include/linux/mfd/iqs62x.h @@ -28,7 +28,7 @@ #define IQS620_GLBL_EVENT_MASK_PMU BIT(6) #define IQS62X_NUM_KEYS 16 -#define IQS62X_NUM_EVENTS (IQS62X_NUM_KEYS + 5) +#define IQS62X_NUM_EVENTS (IQS62X_NUM_KEYS + 6) #define IQS62X_EVENT_SIZE 10 @@ -78,6 +78,7 @@ enum iqs62x_event_flag { /* everything else */ IQS62X_EVENT_SYS_RESET, + IQS62X_EVENT_SYS_ATI, }; struct iqs62x_event_data { @@ -97,12 +98,10 @@ struct iqs62x_dev_desc { const char *dev_name; const struct mfd_cell *sub_devs; int num_sub_devs; - u8 prod_num; u8 sw_num; const u8 *cal_regs; int num_cal_regs; - u8 prox_mask; u8 sar_mask; u8 hall_mask; @@ -110,16 +109,12 @@ struct iqs62x_dev_desc { u8 temp_mask; u8 als_mask; u8 ir_mask; - u8 prox_settings; u8 als_flags; u8 hall_flags; u8 hyst_shift; - u8 interval; u8 interval_div; - - u8 clk_div; const char *fw_name; const enum iqs62x_event_reg (*event_regs)[IQS62X_EVENT_SIZE]; }; @@ -130,8 +125,10 @@ struct iqs62x_core { struct regmap *regmap; struct blocking_notifier_head nh; struct list_head fw_blk_head; + struct completion ati_done; struct completion fw_done; enum iqs62x_ui_sel ui_sel; + unsigned long event_cache; }; extern const struct iqs62x_event_desc iqs62x_events[IQS62X_NUM_EVENTS]; -- cgit v1.2.3 From 6ac0b71537e1c14e7532408fe4aae553aa314237 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 2 Feb 2021 18:19:20 +0100 Subject: block: move struct biovec_slab to bio.c struct biovec_slab is only used inside of bio.c, so move it there. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/bio.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index c74857cf1252..4a84207dd996 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -720,12 +720,6 @@ struct bio_set { struct workqueue_struct *rescue_workqueue; }; -struct biovec_slab { - int nr_vecs; - char *name; - struct kmem_cache *slab; -}; - static inline bool bioset_initialized(struct bio_set *bs) { return bs->bio_slab != NULL; -- cgit v1.2.3 From 0f2e6ab851ae146c468bc5151c302c6e2473f70a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 2 Feb 2021 18:19:24 +0100 Subject: block: turn the nr_iovecs argument to bio_alloc* into an unsigned short The bi_max_vecs and bi_vcnt fields are defined as unsigned short, so don't allow passing larger values in. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/bio.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 4a84207dd996..9ceeb8ecdb7f 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -407,8 +407,9 @@ extern void bioset_exit(struct bio_set *); extern int biovec_init_pool(mempool_t *pool, int pool_entries); extern int bioset_init_from_src(struct bio_set *bs, struct bio_set *src); -extern struct bio *bio_alloc_bioset(gfp_t, unsigned int, struct bio_set *); -struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned int nr_iovecs); +struct bio *bio_alloc_bioset(gfp_t gfp, unsigned short nr_iovecs, + struct bio_set *bs); +struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned short nr_iovecs); extern void bio_put(struct bio *); extern void __bio_clone_fast(struct bio *, struct bio *); @@ -416,7 +417,7 @@ extern struct bio *bio_clone_fast(struct bio *, gfp_t, struct bio_set *); extern struct bio_set fs_bio_set; -static inline struct bio *bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs) +static inline struct bio *bio_alloc(gfp_t gfp_mask, unsigned short nr_iovecs) { return bio_alloc_bioset(gfp_mask, nr_iovecs, &fs_bio_set); } -- cgit v1.2.3 From 7a800a20ae6329e803c5c646b20811a6ae9ca136 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 2 Feb 2021 18:19:29 +0100 Subject: block: use bi_max_vecs to find the bvec pool Instead of encoding of the bvec pool using magic bio flags, just use a helper to find the pool based on the max_vecs value. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/bio.h | 1 - include/linux/blk_types.h | 29 +---------------------------- 2 files changed, 1 insertion(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 9ceeb8ecdb7f..3cbbaf76906e 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -329,7 +329,6 @@ struct bio_integrity_payload { struct bvec_iter bip_iter; - unsigned short bip_slab; /* slab the bip came from */ unsigned short bip_vcnt; /* # of integrity bio_vecs */ unsigned short bip_max_vcnt; /* integrity bio_vec slots */ unsigned short bip_flags; /* control flags */ diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 1bc6f6a01070..db026b6ec15a 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -227,7 +227,7 @@ struct bio { * top bits REQ_OP. Use * accessors. */ - unsigned short bi_flags; /* status, etc and bvec pool number */ + unsigned short bi_flags; /* BIO_* below */ unsigned short bi_ioprio; unsigned short bi_write_hint; blk_status_t bi_status; @@ -307,33 +307,6 @@ enum { BIO_FLAG_LAST }; -/* See BVEC_POOL_OFFSET below before adding new flags */ - -/* - * We support 6 different bvec pools, the last one is magic in that it - * is backed by a mempool. - */ -#define BVEC_POOL_NR 6 -#define BVEC_POOL_MAX (BVEC_POOL_NR - 1) - -/* - * Top 3 bits of bio flags indicate the pool the bvecs came from. We add - * 1 to the actual index so that 0 indicates that there are no bvecs to be - * freed. - */ -#define BVEC_POOL_BITS (3) -#define BVEC_POOL_OFFSET (16 - BVEC_POOL_BITS) -#define BVEC_POOL_IDX(bio) ((bio)->bi_flags >> BVEC_POOL_OFFSET) -#if (1<< BVEC_POOL_BITS) < (BVEC_POOL_NR+1) -# error "BVEC_POOL_BITS is too small" -#endif - -/* - * Flags starting here get preserved by bio_reset() - this includes - * only BVEC_POOL_IDX() - */ -#define BIO_RESET_BITS BVEC_POOL_OFFSET - typedef __u32 __bitwise blk_mq_req_flags_t; /* -- cgit v1.2.3 From 28aa2f9e73e762dbaa28fdca20cccb59c74cc139 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 8 Feb 2021 08:55:47 -0500 Subject: NFS: Always clear an invalid mapping when attempting a buffered write If the page cache is invalid, then we can't do read-modify-write, so ensure that we do clear it when we know it is invalid. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- include/linux/nfs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 3cfcf219e96b..2c662857247a 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -387,6 +387,7 @@ extern int nfs_open(struct inode *, struct file *); extern int nfs_attribute_cache_expired(struct inode *inode); extern int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode); extern int __nfs_revalidate_inode(struct nfs_server *, struct inode *); +extern int nfs_clear_invalid_mapping(struct address_space *mapping); extern bool nfs_mapping_need_revalidate_inode(struct inode *inode); extern int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping); extern int nfs_revalidate_mapping_rcu(struct inode *inode); -- cgit v1.2.3 From 71c36788b9253f086d09763b98804ed473e12a3b Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Fri, 22 Jan 2021 11:58:04 +0200 Subject: lib/zstd: convert constants to defines MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit These constants are really used internally by zstd and including linux/zstd.h into users results in the following warnings: In file included from fs/btrfs/zstd.c:19: ./include/linux/zstd.h:798:21: warning: ‘ZSTD_skippableHeaderSize’ defined but not used [-Wunused-const-variable=] 798 | static const size_t ZSTD_skippableHeaderSize = 8; | ^~~~~~~~~~~~~~~~~~~~~~~~ ./include/linux/zstd.h:796:21: warning: ‘ZSTD_frameHeaderSize_max’ defined but not used [-Wunused-const-variable=] 796 | static const size_t ZSTD_frameHeaderSize_max = ZSTD_FRAMEHEADERSIZE_MAX; | ^~~~~~~~~~~~~~~~~~~~~~~~ ./include/linux/zstd.h:795:21: warning: ‘ZSTD_frameHeaderSize_min’ defined but not used [-Wunused-const-variable=] 795 | static const size_t ZSTD_frameHeaderSize_min = ZSTD_FRAMEHEADERSIZE_MIN; | ^~~~~~~~~~~~~~~~~~~~~~~~ ./include/linux/zstd.h:794:21: warning: ‘ZSTD_frameHeaderSize_prefix’ defined but not used [-Wunused-const-variable=] 794 | static const size_t ZSTD_frameHeaderSize_prefix = 5; So fix those warnings by turning the constants into defines. Reviewed-by: Nick Terrell Signed-off-by: Nikolay Borisov Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/linux/zstd.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/zstd.h b/include/linux/zstd.h index 249575e2485f..e87f78c9b19c 100644 --- a/include/linux/zstd.h +++ b/include/linux/zstd.h @@ -791,11 +791,11 @@ size_t ZSTD_DStreamOutSize(void); /* for static allocation */ #define ZSTD_FRAMEHEADERSIZE_MAX 18 #define ZSTD_FRAMEHEADERSIZE_MIN 6 -static const size_t ZSTD_frameHeaderSize_prefix = 5; -static const size_t ZSTD_frameHeaderSize_min = ZSTD_FRAMEHEADERSIZE_MIN; -static const size_t ZSTD_frameHeaderSize_max = ZSTD_FRAMEHEADERSIZE_MAX; +#define ZSTD_frameHeaderSize_prefix 5 +#define ZSTD_frameHeaderSize_min ZSTD_FRAMEHEADERSIZE_MIN +#define ZSTD_frameHeaderSize_max ZSTD_FRAMEHEADERSIZE_MAX /* magic number + skippable frame length */ -static const size_t ZSTD_skippableHeaderSize = 8; +#define ZSTD_skippableHeaderSize 8 /*-************************************* -- cgit v1.2.3 From ae29333fa644679b96d88c9dd3afbef25cbac0f6 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Thu, 4 Feb 2021 19:21:40 +0900 Subject: block: add bio_add_zone_append_page Add bio_add_zone_append_page(), a wrapper around bio_add_hw_page() which is intended to be used by file systems that directly add pages to a bio instead of using bio_iov_iter_get_pages(). Reviewed-by: Christoph Hellwig Reviewed-by: Josef Bacik Reviewed-by: Chaitanya Kulkarni Acked-by: Jens Axboe Signed-off-by: Johannes Thumshirn Signed-off-by: David Sterba --- include/linux/bio.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 1edda614f7ce..de62911473bb 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -455,6 +455,8 @@ void bio_chain(struct bio *, struct bio *); extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int); extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *, unsigned int, unsigned int); +int bio_add_zone_append_page(struct bio *bio, struct page *page, + unsigned int len, unsigned int offset); bool __bio_try_merge_page(struct bio *bio, struct page *page, unsigned int len, unsigned int off, bool *same_page); void __bio_add_page(struct bio *bio, struct page *page, -- cgit v1.2.3 From c3b0e880bbfafab6beed92b1ee6db2cdaf4bc54c Mon Sep 17 00:00:00 2001 From: Naohiro Aota Date: Thu, 4 Feb 2021 19:21:41 +0900 Subject: iomap: support REQ_OP_ZONE_APPEND A ZONE_APPEND bio must follow hardware restrictions (e.g. not exceeding max_zone_append_sectors) not to be split. bio_iov_iter_get_pages builds such restricted bio using __bio_iov_append_get_pages if bio_op(bio) == REQ_OP_ZONE_APPEND. To utilize it, we need to set the bio_op before calling bio_iov_iter_get_pages(). This commit introduces IOMAP_F_ZONE_APPEND, so that iomap user can set the flag to indicate they want REQ_OP_ZONE_APPEND and restricted bio. Reviewed-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Signed-off-by: Naohiro Aota Signed-off-by: David Sterba --- include/linux/iomap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 5bd3cac4df9c..8ebb1fa6f3b7 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -55,6 +55,7 @@ struct vm_fault; #define IOMAP_F_SHARED 0x04 #define IOMAP_F_MERGED 0x08 #define IOMAP_F_BUFFER_HEAD 0x10 +#define IOMAP_F_ZONE_APPEND 0x20 /* * Flags set by the core iomap code during operations: -- cgit v1.2.3 From db72438c9319cfd37e3c237a7754ca862ae12d63 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Tue, 2 Feb 2021 09:13:09 +0200 Subject: RDMA/mlx5: Cleanup the synchronize_srcu() from the ODP flow Cleanup the synchronize_srcu() from the ODP flow as it was found to be a very heavy time consumer as part of dereg_mr. For example de-registration of 10000 ODP MRs each with size of 2M hugepage took 19.6 sec comparing de-registration of same number of non ODP MRs that took 172 ms. The new locking scheme uses the wait_event() mechanism which follows the use count of the MR instead of using synchronize_srcu(). By that change, the time required for the above test took 95 ms which is even better than the non ODP flow. Once fully dropped the srcu usage, had to come with a lock to protect the XA access. As part of using the above mechanism we could also clean the num_deferred_work stuff and follow the use count instead. Link: https://lore.kernel.org/r/20210202071309.2057998-1-leon@kernel.org Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/linux/mlx5/driver.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 11558c2e99f0..b0a59a18a708 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -366,6 +366,8 @@ struct mlx5_core_mkey { u32 key; u32 pd; u32 type; + struct wait_queue_head wait; + refcount_t usecount; }; #define MLX5_24BIT_MASK ((1 << 24) - 1) -- cgit v1.2.3 From ee7294ba49bf8559b560b21629ed8153082c25cf Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 20 Jan 2021 14:10:26 +0100 Subject: clk: remove u300 driver The ST-Ericsson U300 platform is getting removed, so this driver is no longer needed. Cc: Linus Walleij Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20210120131026.1721788-5-arnd@kernel.org Reviewed-by: Linus Walleij Signed-off-by: Stephen Boyd --- include/linux/platform_data/clk-u300.h | 1 - 1 file changed, 1 deletion(-) delete mode 100644 include/linux/platform_data/clk-u300.h (limited to 'include/linux') diff --git a/include/linux/platform_data/clk-u300.h b/include/linux/platform_data/clk-u300.h deleted file mode 100644 index 8429e73911a1..000000000000 --- a/include/linux/platform_data/clk-u300.h +++ /dev/null @@ -1 +0,0 @@ -void __init u300_clk_init(void __iomem *base); -- cgit v1.2.3 From bf5c9cc8ad7fffd1f72df3baa5870449e4c16d1b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 8 Feb 2021 08:37:05 +0100 Subject: mei: bus: change remove callback to return void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver core ignores the return value of mei_cl_device_remove() so passing an error value doesn't solve any problem. As most mei drivers' remove callbacks return 0 unconditionally and returning a different value doesn't have any effect, change this prototype to return void and return 0 unconditionally in mei_cl_device_remove(). The only driver that could return an error value is modified to emit an explicit warning in the error case. Acked-by: Guenter Roeck Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20210208073705.428185-3-uwe@kleine-koenig.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mei_cl_bus.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mei_cl_bus.h b/include/linux/mei_cl_bus.h index 959ad7d850b4..07f5ef8fc456 100644 --- a/include/linux/mei_cl_bus.h +++ b/include/linux/mei_cl_bus.h @@ -68,7 +68,7 @@ struct mei_cl_driver { int (*probe)(struct mei_cl_device *cldev, const struct mei_cl_device_id *id); - int (*remove)(struct mei_cl_device *cldev); + void (*remove)(struct mei_cl_device *cldev); }; int __mei_cldev_driver_register(struct mei_cl_driver *cldrv, -- cgit v1.2.3 From cae5216387d18c888f9f38a0cf5be341a0af75a6 Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Mon, 8 Feb 2021 22:16:03 +0200 Subject: i2c: mux: mlxcpld: Get rid of adapter numbers enforcement Do not set the argument 'force_nr' of i2c_mux_add_adapter() routine, instead provide argument 'chan_id'. Rename mux ids array from 'adap_ids' to 'chan_ids'. The motivation is to prepare infrastructure to be able to: - Create only the child adapters which are actually needed - for which channel ids are specified. - To assign 'nrs' to these child adapters dynamically, with no 'nr' enforcement. Signed-off-by: Vadim Pasternak Acked-by: Peter Rosin Signed-off-by: Wolfram Sang --- include/linux/platform_data/mlxcpld.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/mlxcpld.h b/include/linux/platform_data/mlxcpld.h index e6c18bf017dd..04d93c563c04 100644 --- a/include/linux/platform_data/mlxcpld.h +++ b/include/linux/platform_data/mlxcpld.h @@ -11,12 +11,12 @@ /* Platform data for the CPLD I2C multiplexers */ /* mlxcpld_mux_plat_data - per mux data, used with i2c_register_board_info - * @adap_ids - adapter array + * @chan_ids - channels array * @num_adaps - number of adapters * @sel_reg_addr - mux select register offset in CPLD space */ struct mlxcpld_mux_plat_data { - int *adap_ids; + int *chan_ids; int num_adaps; int sel_reg_addr; }; -- cgit v1.2.3 From c52a1c5f5db55c6a71110c2db9ae26b9f5269d20 Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Mon, 8 Feb 2021 22:16:04 +0200 Subject: i2c: mux: mlxcpld: Extend driver to support word address space devices Extend driver to allow I2C routing control through CPLD devices with word address space. Till now only CPLD devices with byte address space have been supported. Signed-off-by: Vadim Pasternak Reviewed-by: Michael Shych Acked-by: Peter Rosin Signed-off-by: Wolfram Sang --- include/linux/platform_data/mlxcpld.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/mlxcpld.h b/include/linux/platform_data/mlxcpld.h index 04d93c563c04..a7bee798d991 100644 --- a/include/linux/platform_data/mlxcpld.h +++ b/include/linux/platform_data/mlxcpld.h @@ -14,11 +14,13 @@ * @chan_ids - channels array * @num_adaps - number of adapters * @sel_reg_addr - mux select register offset in CPLD space + * @reg_size: register size in bytes */ struct mlxcpld_mux_plat_data { int *chan_ids; int num_adaps; int sel_reg_addr; + u8 reg_size; }; #endif /* _LINUX_I2C_MLXCPLD_H */ -- cgit v1.2.3 From a39bd92e92b96d05d676fb5c9493cf1c911d2a0a Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Mon, 8 Feb 2021 22:16:06 +0200 Subject: i2c: mux: mlxcpld: Add callback to notify mux creation completion Add notification to inform caller that mux objects array has been created. It allows to user, invoked platform device registration for "i2c-mux-mlxcpld" driver, to be notified that mux infrastructure is available, and thus some devices could be connected to this infrastructure. Signed-off-by: Vadim Pasternak Acked-by: Peter Rosin Signed-off-by: Wolfram Sang --- include/linux/platform_data/mlxcpld.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/mlxcpld.h b/include/linux/platform_data/mlxcpld.h index a7bee798d991..d7610b528856 100644 --- a/include/linux/platform_data/mlxcpld.h +++ b/include/linux/platform_data/mlxcpld.h @@ -15,12 +15,17 @@ * @num_adaps - number of adapters * @sel_reg_addr - mux select register offset in CPLD space * @reg_size: register size in bytes + * @handle: handle to be passed by callback + * @completion_notify: callback to notify when all the adapters are created */ struct mlxcpld_mux_plat_data { int *chan_ids; int num_adaps; int sel_reg_addr; u8 reg_size; + void *handle; + int (*completion_notify)(void *handle, struct i2c_adapter *parent, + struct i2c_adapter *adapters[]); }; #endif /* _LINUX_I2C_MLXCPLD_H */ -- cgit v1.2.3 From 3c5960c0559c44c6628341a82167ee0d3e40ee50 Mon Sep 17 00:00:00 2001 From: Kyle Tso Date: Fri, 5 Feb 2021 11:34:09 +0800 Subject: usb: typec: Manage SVDM version PD Spec Revision 3.0 Version 2.0 + ECNs 2020-12-10 6.4.4.2.3 Structured VDM Version "The Structured VDM Version field of the Discover Identity Command sent and received during VDM discovery Shall be used to determine the lowest common Structured VDM Version supported by the Port Partners or Cable Plug and Shall continue to operate using this Specification Revision until they are Detached." Add a variable in typec_capability to specify the highest SVDM version supported by the port and another variable in typec_partner to cache the negotiated SVDM version between the port and the partner. Also add setter/getter functions for the negotiated SVDM version. Acked-by: Heikki Krogerus Signed-off-by: Kyle Tso Link: https://lore.kernel.org/r/20210205033415.3320439-2-kyletso@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/typec.h | 12 ++++++++++++ include/linux/usb/typec_altmode.h | 10 ++++++++++ 2 files changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h index a94df82ab62f..91b4303ca305 100644 --- a/include/linux/usb/typec.h +++ b/include/linux/usb/typec.h @@ -217,12 +217,19 @@ struct typec_operations { enum typec_port_type type); }; +enum usb_pd_svdm_ver { + SVDM_VER_1_0 = 0, + SVDM_VER_2_0 = 1, + SVDM_VER_MAX = SVDM_VER_2_0, +}; + /* * struct typec_capability - USB Type-C Port Capabilities * @type: Supported power role of the port * @data: Supported data role of the port * @revision: USB Type-C Specification release. Binary coded decimal * @pd_revision: USB Power Delivery Specification revision if supported + * @svdm_version: USB PD Structured VDM version if supported * @prefer_role: Initial role preference (DRP ports). * @accessory: Supported Accessory Modes * @fwnode: Optional fwnode of the port @@ -236,6 +243,7 @@ struct typec_capability { enum typec_port_data data; u16 revision; /* 0120H = "1.2" */ u16 pd_revision; /* 0300H = "3.0" */ + enum usb_pd_svdm_ver svdm_version; int prefer_role; enum typec_accessory accessory[TYPEC_MAX_ACCESSORY]; unsigned int orientation_aware:1; @@ -286,4 +294,8 @@ int typec_find_orientation(const char *name); int typec_find_port_power_role(const char *name); int typec_find_power_role(const char *name); int typec_find_port_data_role(const char *name); + +void typec_partner_set_svdm_version(struct typec_partner *partner, + enum usb_pd_svdm_ver svdm_version); +int typec_get_negotiated_svdm_version(struct typec_port *port); #endif /* __LINUX_USB_TYPEC_H */ diff --git a/include/linux/usb/typec_altmode.h b/include/linux/usb/typec_altmode.h index 5e0a7b7647c3..65933cbe9129 100644 --- a/include/linux/usb/typec_altmode.h +++ b/include/linux/usb/typec_altmode.h @@ -132,6 +132,16 @@ typec_altmode_get_orientation(struct typec_altmode *altmode) return typec_get_orientation(typec_altmode2port(altmode)); } +/** + * typec_altmode_get_svdm_version - Get negotiated SVDM version + * @altmode: Handle to the alternate mode + */ +static inline int +typec_altmode_get_svdm_version(struct typec_altmode *altmode) +{ + return typec_get_negotiated_svdm_version(typec_altmode2port(altmode)); +} + /** * struct typec_altmode_driver - USB Type-C alternate mode device driver * @id_table: Null terminated array of SVIDs -- cgit v1.2.3 From 31737c27d665bb3bc8ad9396c63fae2543dd8818 Mon Sep 17 00:00:00 2001 From: Kyle Tso Date: Fri, 5 Feb 2021 11:34:10 +0800 Subject: usb: pd: Make SVDM Version configurable in VDM header PD Rev 3.0 introduces SVDM Version 2.0. This patch makes the field configuable in the header in order to be able to be compatible with older SVDM version. Acked-by: Heikki Krogerus Signed-off-by: Kyle Tso Link: https://lore.kernel.org/r/20210205033415.3320439-3-kyletso@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/pd_vdo.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/pd_vdo.h b/include/linux/usb/pd_vdo.h index 5de7f550f93e..b057250704e8 100644 --- a/include/linux/usb/pd_vdo.h +++ b/include/linux/usb/pd_vdo.h @@ -21,22 +21,24 @@ * ---------- * <31:16> :: SVID * <15> :: VDM type ( 1b == structured, 0b == unstructured ) - * <14:13> :: Structured VDM version (can only be 00 == 1.0 currently) + * <14:13> :: Structured VDM version * <12:11> :: reserved * <10:8> :: object position (1-7 valid ... used for enter/exit mode only) * <7:6> :: command type (SVDM only?) * <5> :: reserved (SVDM), command type (UVDM) * <4:0> :: command */ -#define VDO(vid, type, custom) \ +#define VDO(vid, type, ver, custom) \ (((vid) << 16) | \ ((type) << 15) | \ + ((ver) << 13) | \ ((custom) & 0x7FFF)) #define VDO_SVDM_TYPE (1 << 15) #define VDO_SVDM_VERS(x) ((x) << 13) #define VDO_OPOS(x) ((x) << 8) #define VDO_CMDT(x) ((x) << 6) +#define VDO_SVDM_VERS_MASK VDO_SVDM_VERS(0x3) #define VDO_OPOS_MASK VDO_OPOS(0x7) #define VDO_CMDT_MASK VDO_CMDT(0x3) @@ -74,6 +76,7 @@ #define PD_VDO_VID(vdo) ((vdo) >> 16) #define PD_VDO_SVDM(vdo) (((vdo) >> 15) & 1) +#define PD_VDO_SVDM_VER(vdo) (((vdo) >> 13) & 0x3) #define PD_VDO_OPOS(vdo) (((vdo) >> 8) & 0x7) #define PD_VDO_CMD(vdo) ((vdo) & 0x1f) #define PD_VDO_CMDT(vdo) (((vdo) >> 6) & 0x3) -- cgit v1.2.3 From 1077d4367ab3b97f6db2f66c87289af863652215 Mon Sep 17 00:00:00 2001 From: Michal Simek Date: Wed, 3 Feb 2021 15:13:50 +0100 Subject: firmware: xilinx: Use explicit values for all enum values Based on discussion at https://lore.kernel.org/r/20200318125003.GA2727094@kroah.com we got recommendation to use explicit values for all enum values. The patch is following this recommendation. Signed-off-by: Michal Simek Link: https://lore.kernel.org/r/daeb67ded45d8a8f6a96717d1fb9c84439dd2ae8.1612361627.git.michal.simek@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 338 +++++++++++++++++------------------ 1 file changed, 169 insertions(+), 169 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 0a483249ff30..71177b17eee5 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -64,25 +64,25 @@ enum pm_api_id { PM_GET_API_VERSION = 1, PM_SYSTEM_SHUTDOWN = 12, PM_REQUEST_NODE = 13, - PM_RELEASE_NODE, - PM_SET_REQUIREMENT, + PM_RELEASE_NODE = 14, + PM_SET_REQUIREMENT = 15, PM_RESET_ASSERT = 17, - PM_RESET_GET_STATUS, + PM_RESET_GET_STATUS = 18, PM_PM_INIT_FINALIZE = 21, - PM_FPGA_LOAD, - PM_FPGA_GET_STATUS, + PM_FPGA_LOAD = 22, + PM_FPGA_GET_STATUS = 23, PM_GET_CHIPID = 24, PM_IOCTL = 34, - PM_QUERY_DATA, - PM_CLOCK_ENABLE, - PM_CLOCK_DISABLE, - PM_CLOCK_GETSTATE, - PM_CLOCK_SETDIVIDER, - PM_CLOCK_GETDIVIDER, - PM_CLOCK_SETRATE, - PM_CLOCK_GETRATE, - PM_CLOCK_SETPARENT, - PM_CLOCK_GETPARENT, + PM_QUERY_DATA = 35, + PM_CLOCK_ENABLE = 36, + PM_CLOCK_DISABLE = 37, + PM_CLOCK_GETSTATE = 38, + PM_CLOCK_SETDIVIDER = 39, + PM_CLOCK_GETDIVIDER = 40, + PM_CLOCK_SETRATE = 41, + PM_CLOCK_GETRATE = 42, + PM_CLOCK_SETPARENT = 43, + PM_CLOCK_GETPARENT = 44, PM_SECURE_AES = 47, PM_FEATURE_CHECK = 63, }; @@ -92,21 +92,21 @@ enum pm_ret_status { XST_PM_SUCCESS = 0, XST_PM_NO_FEATURE = 19, XST_PM_INTERNAL = 2000, - XST_PM_CONFLICT, - XST_PM_NO_ACCESS, - XST_PM_INVALID_NODE, - XST_PM_DOUBLE_REQ, - XST_PM_ABORT_SUSPEND, + XST_PM_CONFLICT = 2001, + XST_PM_NO_ACCESS = 2002, + XST_PM_INVALID_NODE = 2003, + XST_PM_DOUBLE_REQ = 2004, + XST_PM_ABORT_SUSPEND = 2005, XST_PM_MULT_USER = 2008, }; enum pm_ioctl_id { IOCTL_SD_DLL_RESET = 6, - IOCTL_SET_SD_TAPDELAY, - IOCTL_SET_PLL_FRAC_MODE, - IOCTL_GET_PLL_FRAC_MODE, - IOCTL_SET_PLL_FRAC_DATA, - IOCTL_GET_PLL_FRAC_DATA, + IOCTL_SET_SD_TAPDELAY = 7, + IOCTL_SET_PLL_FRAC_MODE = 8, + IOCTL_GET_PLL_FRAC_MODE = 9, + IOCTL_SET_PLL_FRAC_DATA = 10, + IOCTL_GET_PLL_FRAC_DATA = 11, IOCTL_WRITE_GGS = 12, IOCTL_READ_GGS = 13, IOCTL_WRITE_PGGS = 14, @@ -116,185 +116,185 @@ enum pm_ioctl_id { }; enum pm_query_id { - PM_QID_INVALID, - PM_QID_CLOCK_GET_NAME, - PM_QID_CLOCK_GET_TOPOLOGY, - PM_QID_CLOCK_GET_FIXEDFACTOR_PARAMS, - PM_QID_CLOCK_GET_PARENTS, - PM_QID_CLOCK_GET_ATTRIBUTES, + PM_QID_INVALID = 0, + PM_QID_CLOCK_GET_NAME = 1, + PM_QID_CLOCK_GET_TOPOLOGY = 2, + PM_QID_CLOCK_GET_FIXEDFACTOR_PARAMS = 3, + PM_QID_CLOCK_GET_PARENTS = 4, + PM_QID_CLOCK_GET_ATTRIBUTES = 5, PM_QID_CLOCK_GET_NUM_CLOCKS = 12, - PM_QID_CLOCK_GET_MAX_DIVISOR, + PM_QID_CLOCK_GET_MAX_DIVISOR = 13, }; enum zynqmp_pm_reset_action { - PM_RESET_ACTION_RELEASE, - PM_RESET_ACTION_ASSERT, - PM_RESET_ACTION_PULSE, + PM_RESET_ACTION_RELEASE = 0, + PM_RESET_ACTION_ASSERT = 1, + PM_RESET_ACTION_PULSE = 2, }; enum zynqmp_pm_reset { ZYNQMP_PM_RESET_START = 1000, ZYNQMP_PM_RESET_PCIE_CFG = ZYNQMP_PM_RESET_START, - ZYNQMP_PM_RESET_PCIE_BRIDGE, - ZYNQMP_PM_RESET_PCIE_CTRL, - ZYNQMP_PM_RESET_DP, - ZYNQMP_PM_RESET_SWDT_CRF, - ZYNQMP_PM_RESET_AFI_FM5, - ZYNQMP_PM_RESET_AFI_FM4, - ZYNQMP_PM_RESET_AFI_FM3, - ZYNQMP_PM_RESET_AFI_FM2, - ZYNQMP_PM_RESET_AFI_FM1, - ZYNQMP_PM_RESET_AFI_FM0, - ZYNQMP_PM_RESET_GDMA, - ZYNQMP_PM_RESET_GPU_PP1, - ZYNQMP_PM_RESET_GPU_PP0, - ZYNQMP_PM_RESET_GPU, - ZYNQMP_PM_RESET_GT, - ZYNQMP_PM_RESET_SATA, - ZYNQMP_PM_RESET_ACPU3_PWRON, - ZYNQMP_PM_RESET_ACPU2_PWRON, - ZYNQMP_PM_RESET_ACPU1_PWRON, - ZYNQMP_PM_RESET_ACPU0_PWRON, - ZYNQMP_PM_RESET_APU_L2, - ZYNQMP_PM_RESET_ACPU3, - ZYNQMP_PM_RESET_ACPU2, - ZYNQMP_PM_RESET_ACPU1, - ZYNQMP_PM_RESET_ACPU0, - ZYNQMP_PM_RESET_DDR, - ZYNQMP_PM_RESET_APM_FPD, - ZYNQMP_PM_RESET_SOFT, - ZYNQMP_PM_RESET_GEM0, - ZYNQMP_PM_RESET_GEM1, - ZYNQMP_PM_RESET_GEM2, - ZYNQMP_PM_RESET_GEM3, - ZYNQMP_PM_RESET_QSPI, - ZYNQMP_PM_RESET_UART0, - ZYNQMP_PM_RESET_UART1, - ZYNQMP_PM_RESET_SPI0, - ZYNQMP_PM_RESET_SPI1, - ZYNQMP_PM_RESET_SDIO0, - ZYNQMP_PM_RESET_SDIO1, - ZYNQMP_PM_RESET_CAN0, - ZYNQMP_PM_RESET_CAN1, - ZYNQMP_PM_RESET_I2C0, - ZYNQMP_PM_RESET_I2C1, - ZYNQMP_PM_RESET_TTC0, - ZYNQMP_PM_RESET_TTC1, - ZYNQMP_PM_RESET_TTC2, - ZYNQMP_PM_RESET_TTC3, - ZYNQMP_PM_RESET_SWDT_CRL, - ZYNQMP_PM_RESET_NAND, - ZYNQMP_PM_RESET_ADMA, - ZYNQMP_PM_RESET_GPIO, - ZYNQMP_PM_RESET_IOU_CC, - ZYNQMP_PM_RESET_TIMESTAMP, - ZYNQMP_PM_RESET_RPU_R50, - ZYNQMP_PM_RESET_RPU_R51, - ZYNQMP_PM_RESET_RPU_AMBA, - ZYNQMP_PM_RESET_OCM, - ZYNQMP_PM_RESET_RPU_PGE, - ZYNQMP_PM_RESET_USB0_CORERESET, - ZYNQMP_PM_RESET_USB1_CORERESET, - ZYNQMP_PM_RESET_USB0_HIBERRESET, - ZYNQMP_PM_RESET_USB1_HIBERRESET, - ZYNQMP_PM_RESET_USB0_APB, - ZYNQMP_PM_RESET_USB1_APB, - ZYNQMP_PM_RESET_IPI, - ZYNQMP_PM_RESET_APM_LPD, - ZYNQMP_PM_RESET_RTC, - ZYNQMP_PM_RESET_SYSMON, - ZYNQMP_PM_RESET_AFI_FM6, - ZYNQMP_PM_RESET_LPD_SWDT, - ZYNQMP_PM_RESET_FPD, - ZYNQMP_PM_RESET_RPU_DBG1, - ZYNQMP_PM_RESET_RPU_DBG0, - ZYNQMP_PM_RESET_DBG_LPD, - ZYNQMP_PM_RESET_DBG_FPD, - ZYNQMP_PM_RESET_APLL, - ZYNQMP_PM_RESET_DPLL, - ZYNQMP_PM_RESET_VPLL, - ZYNQMP_PM_RESET_IOPLL, - ZYNQMP_PM_RESET_RPLL, - ZYNQMP_PM_RESET_GPO3_PL_0, - ZYNQMP_PM_RESET_GPO3_PL_1, - ZYNQMP_PM_RESET_GPO3_PL_2, - ZYNQMP_PM_RESET_GPO3_PL_3, - ZYNQMP_PM_RESET_GPO3_PL_4, - ZYNQMP_PM_RESET_GPO3_PL_5, - ZYNQMP_PM_RESET_GPO3_PL_6, - ZYNQMP_PM_RESET_GPO3_PL_7, - ZYNQMP_PM_RESET_GPO3_PL_8, - ZYNQMP_PM_RESET_GPO3_PL_9, - ZYNQMP_PM_RESET_GPO3_PL_10, - ZYNQMP_PM_RESET_GPO3_PL_11, - ZYNQMP_PM_RESET_GPO3_PL_12, - ZYNQMP_PM_RESET_GPO3_PL_13, - ZYNQMP_PM_RESET_GPO3_PL_14, - ZYNQMP_PM_RESET_GPO3_PL_15, - ZYNQMP_PM_RESET_GPO3_PL_16, - ZYNQMP_PM_RESET_GPO3_PL_17, - ZYNQMP_PM_RESET_GPO3_PL_18, - ZYNQMP_PM_RESET_GPO3_PL_19, - ZYNQMP_PM_RESET_GPO3_PL_20, - ZYNQMP_PM_RESET_GPO3_PL_21, - ZYNQMP_PM_RESET_GPO3_PL_22, - ZYNQMP_PM_RESET_GPO3_PL_23, - ZYNQMP_PM_RESET_GPO3_PL_24, - ZYNQMP_PM_RESET_GPO3_PL_25, - ZYNQMP_PM_RESET_GPO3_PL_26, - ZYNQMP_PM_RESET_GPO3_PL_27, - ZYNQMP_PM_RESET_GPO3_PL_28, - ZYNQMP_PM_RESET_GPO3_PL_29, - ZYNQMP_PM_RESET_GPO3_PL_30, - ZYNQMP_PM_RESET_GPO3_PL_31, - ZYNQMP_PM_RESET_RPU_LS, - ZYNQMP_PM_RESET_PS_ONLY, - ZYNQMP_PM_RESET_PL, - ZYNQMP_PM_RESET_PS_PL0, - ZYNQMP_PM_RESET_PS_PL1, - ZYNQMP_PM_RESET_PS_PL2, - ZYNQMP_PM_RESET_PS_PL3, + ZYNQMP_PM_RESET_PCIE_BRIDGE = 1001, + ZYNQMP_PM_RESET_PCIE_CTRL = 1002, + ZYNQMP_PM_RESET_DP = 1003, + ZYNQMP_PM_RESET_SWDT_CRF = 1004, + ZYNQMP_PM_RESET_AFI_FM5 = 1005, + ZYNQMP_PM_RESET_AFI_FM4 = 1006, + ZYNQMP_PM_RESET_AFI_FM3 = 1007, + ZYNQMP_PM_RESET_AFI_FM2 = 1008, + ZYNQMP_PM_RESET_AFI_FM1 = 1009, + ZYNQMP_PM_RESET_AFI_FM0 = 1010, + ZYNQMP_PM_RESET_GDMA = 1011, + ZYNQMP_PM_RESET_GPU_PP1 = 1012, + ZYNQMP_PM_RESET_GPU_PP0 = 1013, + ZYNQMP_PM_RESET_GPU = 1014, + ZYNQMP_PM_RESET_GT = 1015, + ZYNQMP_PM_RESET_SATA = 1016, + ZYNQMP_PM_RESET_ACPU3_PWRON = 1017, + ZYNQMP_PM_RESET_ACPU2_PWRON = 1018, + ZYNQMP_PM_RESET_ACPU1_PWRON = 1019, + ZYNQMP_PM_RESET_ACPU0_PWRON = 1020, + ZYNQMP_PM_RESET_APU_L2 = 1021, + ZYNQMP_PM_RESET_ACPU3 = 1022, + ZYNQMP_PM_RESET_ACPU2 = 1023, + ZYNQMP_PM_RESET_ACPU1 = 1024, + ZYNQMP_PM_RESET_ACPU0 = 1025, + ZYNQMP_PM_RESET_DDR = 1026, + ZYNQMP_PM_RESET_APM_FPD = 1027, + ZYNQMP_PM_RESET_SOFT = 1028, + ZYNQMP_PM_RESET_GEM0 = 1029, + ZYNQMP_PM_RESET_GEM1 = 1030, + ZYNQMP_PM_RESET_GEM2 = 1031, + ZYNQMP_PM_RESET_GEM3 = 1032, + ZYNQMP_PM_RESET_QSPI = 1033, + ZYNQMP_PM_RESET_UART0 = 1034, + ZYNQMP_PM_RESET_UART1 = 1035, + ZYNQMP_PM_RESET_SPI0 = 1036, + ZYNQMP_PM_RESET_SPI1 = 1037, + ZYNQMP_PM_RESET_SDIO0 = 1038, + ZYNQMP_PM_RESET_SDIO1 = 1039, + ZYNQMP_PM_RESET_CAN0 = 1040, + ZYNQMP_PM_RESET_CAN1 = 1041, + ZYNQMP_PM_RESET_I2C0 = 1042, + ZYNQMP_PM_RESET_I2C1 = 1043, + ZYNQMP_PM_RESET_TTC0 = 1044, + ZYNQMP_PM_RESET_TTC1 = 1045, + ZYNQMP_PM_RESET_TTC2 = 1046, + ZYNQMP_PM_RESET_TTC3 = 1047, + ZYNQMP_PM_RESET_SWDT_CRL = 1048, + ZYNQMP_PM_RESET_NAND = 1049, + ZYNQMP_PM_RESET_ADMA = 1050, + ZYNQMP_PM_RESET_GPIO = 1051, + ZYNQMP_PM_RESET_IOU_CC = 1052, + ZYNQMP_PM_RESET_TIMESTAMP = 1053, + ZYNQMP_PM_RESET_RPU_R50 = 1054, + ZYNQMP_PM_RESET_RPU_R51 = 1055, + ZYNQMP_PM_RESET_RPU_AMBA = 1056, + ZYNQMP_PM_RESET_OCM = 1057, + ZYNQMP_PM_RESET_RPU_PGE = 1058, + ZYNQMP_PM_RESET_USB0_CORERESET = 1059, + ZYNQMP_PM_RESET_USB1_CORERESET = 1060, + ZYNQMP_PM_RESET_USB0_HIBERRESET = 1061, + ZYNQMP_PM_RESET_USB1_HIBERRESET = 1062, + ZYNQMP_PM_RESET_USB0_APB = 1063, + ZYNQMP_PM_RESET_USB1_APB = 1064, + ZYNQMP_PM_RESET_IPI = 1065, + ZYNQMP_PM_RESET_APM_LPD = 1066, + ZYNQMP_PM_RESET_RTC = 1067, + ZYNQMP_PM_RESET_SYSMON = 1068, + ZYNQMP_PM_RESET_AFI_FM6 = 1069, + ZYNQMP_PM_RESET_LPD_SWDT = 1070, + ZYNQMP_PM_RESET_FPD = 1071, + ZYNQMP_PM_RESET_RPU_DBG1 = 1072, + ZYNQMP_PM_RESET_RPU_DBG0 = 1073, + ZYNQMP_PM_RESET_DBG_LPD = 1074, + ZYNQMP_PM_RESET_DBG_FPD = 1075, + ZYNQMP_PM_RESET_APLL = 1076, + ZYNQMP_PM_RESET_DPLL = 1077, + ZYNQMP_PM_RESET_VPLL = 1078, + ZYNQMP_PM_RESET_IOPLL = 1079, + ZYNQMP_PM_RESET_RPLL = 1080, + ZYNQMP_PM_RESET_GPO3_PL_0 = 1081, + ZYNQMP_PM_RESET_GPO3_PL_1 = 1082, + ZYNQMP_PM_RESET_GPO3_PL_2 = 1083, + ZYNQMP_PM_RESET_GPO3_PL_3 = 1084, + ZYNQMP_PM_RESET_GPO3_PL_4 = 1085, + ZYNQMP_PM_RESET_GPO3_PL_5 = 1086, + ZYNQMP_PM_RESET_GPO3_PL_6 = 1087, + ZYNQMP_PM_RESET_GPO3_PL_7 = 1088, + ZYNQMP_PM_RESET_GPO3_PL_8 = 1089, + ZYNQMP_PM_RESET_GPO3_PL_9 = 1090, + ZYNQMP_PM_RESET_GPO3_PL_10 = 1091, + ZYNQMP_PM_RESET_GPO3_PL_11 = 1092, + ZYNQMP_PM_RESET_GPO3_PL_12 = 1093, + ZYNQMP_PM_RESET_GPO3_PL_13 = 1094, + ZYNQMP_PM_RESET_GPO3_PL_14 = 1095, + ZYNQMP_PM_RESET_GPO3_PL_15 = 1096, + ZYNQMP_PM_RESET_GPO3_PL_16 = 1097, + ZYNQMP_PM_RESET_GPO3_PL_17 = 1098, + ZYNQMP_PM_RESET_GPO3_PL_18 = 1099, + ZYNQMP_PM_RESET_GPO3_PL_19 = 1100, + ZYNQMP_PM_RESET_GPO3_PL_20 = 1101, + ZYNQMP_PM_RESET_GPO3_PL_21 = 1102, + ZYNQMP_PM_RESET_GPO3_PL_22 = 1103, + ZYNQMP_PM_RESET_GPO3_PL_23 = 1104, + ZYNQMP_PM_RESET_GPO3_PL_24 = 1105, + ZYNQMP_PM_RESET_GPO3_PL_25 = 1106, + ZYNQMP_PM_RESET_GPO3_PL_26 = 1107, + ZYNQMP_PM_RESET_GPO3_PL_27 = 1108, + ZYNQMP_PM_RESET_GPO3_PL_28 = 1109, + ZYNQMP_PM_RESET_GPO3_PL_29 = 1110, + ZYNQMP_PM_RESET_GPO3_PL_30 = 1111, + ZYNQMP_PM_RESET_GPO3_PL_31 = 1112, + ZYNQMP_PM_RESET_RPU_LS = 1113, + ZYNQMP_PM_RESET_PS_ONLY = 1114, + ZYNQMP_PM_RESET_PL = 1115, + ZYNQMP_PM_RESET_PS_PL0 = 1116, + ZYNQMP_PM_RESET_PS_PL1 = 1117, + ZYNQMP_PM_RESET_PS_PL2 = 1118, + ZYNQMP_PM_RESET_PS_PL3 = 1119, ZYNQMP_PM_RESET_END = ZYNQMP_PM_RESET_PS_PL3 }; enum zynqmp_pm_suspend_reason { SUSPEND_POWER_REQUEST = 201, - SUSPEND_ALERT, - SUSPEND_SYSTEM_SHUTDOWN, + SUSPEND_ALERT = 202, + SUSPEND_SYSTEM_SHUTDOWN = 203, }; enum zynqmp_pm_request_ack { ZYNQMP_PM_REQUEST_ACK_NO = 1, - ZYNQMP_PM_REQUEST_ACK_BLOCKING, - ZYNQMP_PM_REQUEST_ACK_NON_BLOCKING, + ZYNQMP_PM_REQUEST_ACK_BLOCKING = 2, + ZYNQMP_PM_REQUEST_ACK_NON_BLOCKING = 3, }; enum pm_node_id { NODE_SD_0 = 39, - NODE_SD_1, + NODE_SD_1 = 40, }; enum tap_delay_type { PM_TAPDELAY_INPUT = 0, - PM_TAPDELAY_OUTPUT, + PM_TAPDELAY_OUTPUT = 1, }; enum dll_reset_type { - PM_DLL_RESET_ASSERT, - PM_DLL_RESET_RELEASE, - PM_DLL_RESET_PULSE, + PM_DLL_RESET_ASSERT = 0, + PM_DLL_RESET_RELEASE = 1, + PM_DLL_RESET_PULSE = 2, }; enum zynqmp_pm_shutdown_type { - ZYNQMP_PM_SHUTDOWN_TYPE_SHUTDOWN, - ZYNQMP_PM_SHUTDOWN_TYPE_RESET, - ZYNQMP_PM_SHUTDOWN_TYPE_SETSCOPE_ONLY, + ZYNQMP_PM_SHUTDOWN_TYPE_SHUTDOWN = 0, + ZYNQMP_PM_SHUTDOWN_TYPE_RESET = 1, + ZYNQMP_PM_SHUTDOWN_TYPE_SETSCOPE_ONLY = 2, }; enum zynqmp_pm_shutdown_subtype { - ZYNQMP_PM_SHUTDOWN_SUBTYPE_SUBSYSTEM, - ZYNQMP_PM_SHUTDOWN_SUBTYPE_PS_ONLY, - ZYNQMP_PM_SHUTDOWN_SUBTYPE_SYSTEM, + ZYNQMP_PM_SHUTDOWN_SUBTYPE_SUBSYSTEM = 0, + ZYNQMP_PM_SHUTDOWN_SUBTYPE_PS_ONLY = 1, + ZYNQMP_PM_SHUTDOWN_SUBTYPE_SYSTEM = 2, }; /** -- cgit v1.2.3 From 2adc75fba3289455b9c4349dd6b95cfb7167b7ea Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 27 Jan 2021 22:23:29 +0100 Subject: vme: make remove callback return void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver core ignores the return value of struct bus_type::remove() because there is only little that can be done. To simplify the quest to make this function return void, let struct vme_driver::remove return void, too. There is only a single vme driver and it already returns 0 unconditionally in .remove(). Also fix the bus remove function to always return 0. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20210127212329.98517-1-uwe@kleine-koenig.org Signed-off-by: Greg Kroah-Hartman --- include/linux/vme.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vme.h b/include/linux/vme.h index 7e82bf500f01..b204a9b4be1b 100644 --- a/include/linux/vme.h +++ b/include/linux/vme.h @@ -122,7 +122,7 @@ struct vme_driver { const char *name; int (*match)(struct vme_dev *); int (*probe)(struct vme_dev *); - int (*remove)(struct vme_dev *); + void (*remove)(struct vme_dev *); struct device_driver driver; struct list_head devices; }; -- cgit v1.2.3 From 5c3db63abdb08d8f0ec2c609f7789a199d5c476f Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Fri, 5 Feb 2021 18:06:08 +0100 Subject: device.h: Remove bogus "the" in kerneldoc Remove the bogus word "the" from "...once the it is..." in the documentation describing the "dev_groups" member of the device_driver structure. Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20210205170608.1956223-1-geert@linux-m68k.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h index ee7ba5b5417e..a498ebcf4993 100644 --- a/include/linux/device/driver.h +++ b/include/linux/device/driver.h @@ -75,7 +75,7 @@ enum probe_type { * @resume: Called to bring a device from sleep mode. * @groups: Default attributes that get created by the driver core * automatically. - * @dev_groups: Additional attributes attached to device instance once the + * @dev_groups: Additional attributes attached to device instance once * it is bound to the driver. * @pm: Power management operations of the device which matched * this driver. -- cgit v1.2.3 From 9fd6dad1261a541b3f5fa7dc5b152222306e6702 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Fri, 5 Feb 2021 05:07:11 -0500 Subject: mm: provide a saner PTE walking API for modules Currently, the follow_pfn function is exported for modules but follow_pte is not. However, follow_pfn is very easy to misuse, because it does not provide protections (so most of its callers assume the page is writable!) and because it returns after having already unlocked the page table lock. Provide instead a simplified version of follow_pte that does not have the pmdpp and range arguments. The older version survives as follow_invalidate_pte() for use by fs/dax.c. Reviewed-by: Jason Gunthorpe Signed-off-by: Paolo Bonzini --- include/linux/mm.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index ecdf8a8cd6ae..24b292fce8e5 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1658,9 +1658,11 @@ void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); int copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma); +int follow_invalidate_pte(struct mm_struct *mm, unsigned long address, + struct mmu_notifier_range *range, pte_t **ptepp, + pmd_t **pmdpp, spinlock_t **ptlp); int follow_pte(struct mm_struct *mm, unsigned long address, - struct mmu_notifier_range *range, pte_t **ptepp, pmd_t **pmdpp, - spinlock_t **ptlp); + pte_t **ptepp, spinlock_t **ptlp); int follow_pfn(struct vm_area_struct *vma, unsigned long address, unsigned long *pfn); int follow_phys(struct vm_area_struct *vma, unsigned long address, -- cgit v1.2.3 From c5d1448fa353242635fa3e1fed6ab4558e0e7d9a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 8 Feb 2021 15:31:49 +0100 Subject: USB: serial: make remove callback return void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit All usb_serial drivers return 0 in their remove callbacks and driver core ignores the value returned by usb_serial_device_remove(). So change the remove callback to return void and return 0 unconditionally in usb_serial_device_remove(). Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20210208143149.963644-2-uwe@kleine-koenig.org Signed-off-by: Johan Hovold --- include/linux/usb/serial.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index 1c09b922f8b0..952272002e48 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -260,7 +260,7 @@ struct usb_serial_driver { void (*release)(struct usb_serial *serial); int (*port_probe)(struct usb_serial_port *port); - int (*port_remove)(struct usb_serial_port *port); + void (*port_remove)(struct usb_serial_port *port); int (*suspend)(struct usb_serial *serial, pm_message_t message); int (*resume)(struct usb_serial *serial); -- cgit v1.2.3 From 4fc096a99e01dd06dc55bef76ade7f8d76653245 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Thu, 28 Jan 2021 13:01:31 -0500 Subject: KVM: Raise the maximum number of user memslots Current KVM_USER_MEM_SLOTS limits are arch specific (512 on Power, 509 on x86, 32 on s390, 16 on MIPS) but they don't really need to be. Memory slots are allocated dynamically in KVM when added so the only real limitation is 'id_to_index' array which is 'short'. We don't have any other KVM_MEM_SLOTS_NUM/KVM_USER_MEM_SLOTS-sized statically defined structures. Low KVM_USER_MEM_SLOTS can be a limiting factor for some configurations. In particular, when QEMU tries to start a Windows guest with Hyper-V SynIC enabled and e.g. 256 vCPUs the limit is hit as SynIC requires two pages per vCPU and the guest is free to pick any GFN for each of them, this fragments memslots as QEMU wants to have a separate memslot for each of these pages (which are supposed to act as 'overlay' pages). Signed-off-by: Vitaly Kuznetsov Message-Id: <20210127175731.2020089-3-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index f417447129b9..e126ebda36d0 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -425,9 +425,8 @@ struct kvm_irq_routing_table { #define KVM_PRIVATE_MEM_SLOTS 0 #endif -#ifndef KVM_MEM_SLOTS_NUM -#define KVM_MEM_SLOTS_NUM (KVM_USER_MEM_SLOTS + KVM_PRIVATE_MEM_SLOTS) -#endif +#define KVM_MEM_SLOTS_NUM SHRT_MAX +#define KVM_USER_MEM_SLOTS (KVM_MEM_SLOTS_NUM - KVM_PRIVATE_MEM_SLOTS) #ifndef __KVM_VCPU_MULTIPLE_ADDRESS_SPACE static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu) -- cgit v1.2.3 From 9528e0d9c10027ae80e2aab36e30a1f730b1bbf9 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Fri, 5 Feb 2021 14:26:37 -0800 Subject: driver core: fw_devlink: Detect supplier devices that will never be added During the initial parsing of firmware by fw_devlink, fw_devlink might infer that some supplier firmware nodes would get populated as devices. But the inference is not always correct. This patch tries to logically detect and fix such mistakes as boot progresses or more devices probe. fw_devlink makes a fundamental assumption that once a device binds to a driver, it will populate (i.e: add as struct devices) all the child firmware nodes that could be populated as devices (if they aren't populated already). So, whenever a device probes, we check all its child firmware nodes. If a child firmware node has a corresponding device populated, we don't modify the child node or its descendants. However, if a child firmware node has not been populated as a device, we delete all the fwnode links where the child node or its descendants are suppliers. This ensures that no other device is blocked on a firmware node that will never be populated as a device. We also mark such fwnodes as NOT_DEVICE, so that no new fwnode links are created with these nodes as suppliers. Fixes: e590474768f1 ("driver core: Set fw_devlink=on by default") Tested-by: Marek Szyprowski Acked-by: Rafael J. Wysocki Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20210205222644.2357303-2-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/fwnode.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index fde4ad97564c..21082f11473f 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -19,8 +19,10 @@ struct device; * fwnode link flags * * LINKS_ADDED: The fwnode has already be parsed to add fwnode links. + * NOT_DEVICE: The fwnode will never be populated as a struct device. */ #define FWNODE_FLAG_LINKS_ADDED BIT(0) +#define FWNODE_FLAG_NOT_DEVICE BIT(1) struct fwnode_handle { struct fwnode_handle *secondary; -- cgit v1.2.3 From 19d0f5f6bff878277783fd98fef4ae2441d6a1d8 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Fri, 5 Feb 2021 14:26:39 -0800 Subject: driver core: Add fw_devlink.strict kernel param This param allows forcing all dependencies to be treated as mandatory. This will be useful for boards in which all optional dependencies like IOMMUs and DMAs need to be treated as mandatory dependencies. Tested-by: Marek Szyprowski Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20210205222644.2357303-4-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/fwnode.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 21082f11473f..d5caefe39d93 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -162,6 +162,7 @@ static inline void fwnode_init(struct fwnode_handle *fwnode, } extern u32 fw_devlink_get_flags(void); +extern bool fw_devlink_is_strict(void); int fwnode_link_add(struct fwnode_handle *con, struct fwnode_handle *sup); void fwnode_links_purge(struct fwnode_handle *fwnode); -- cgit v1.2.3 From 74c782cff77b3533290148df1fa6f8c7db5e60d5 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Fri, 5 Feb 2021 14:26:41 -0800 Subject: driver core: fw_devlink: Handle suppliers that don't use driver core Device links only work between devices that use the driver core to match and bind a driver to a device. So, add an API for frameworks to let the driver core know that a fwnode has been initialized by a driver without using the driver core. Then use this information to make sure that fw_devlink doesn't make the consumers wait indefinitely on suppliers that'll never bind to a driver. Tested-by: Marek Szyprowski Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20210205222644.2357303-6-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/fwnode.h | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index d5caefe39d93..dfefd43a737c 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -11,6 +11,7 @@ #include #include +#include struct fwnode_operations; struct device; @@ -18,11 +19,13 @@ struct device; /* * fwnode link flags * - * LINKS_ADDED: The fwnode has already be parsed to add fwnode links. - * NOT_DEVICE: The fwnode will never be populated as a struct device. + * LINKS_ADDED: The fwnode has already be parsed to add fwnode links. + * NOT_DEVICE: The fwnode will never be populated as a struct device. + * INITIALIZED: The hardware corresponding to fwnode has been initialized. */ #define FWNODE_FLAG_LINKS_ADDED BIT(0) #define FWNODE_FLAG_NOT_DEVICE BIT(1) +#define FWNODE_FLAG_INITIALIZED BIT(2) struct fwnode_handle { struct fwnode_handle *secondary; @@ -161,6 +164,18 @@ static inline void fwnode_init(struct fwnode_handle *fwnode, INIT_LIST_HEAD(&fwnode->suppliers); } +static inline void fwnode_dev_initialized(struct fwnode_handle *fwnode, + bool initialized) +{ + if (IS_ERR_OR_NULL(fwnode)) + return; + + if (initialized) + fwnode->flags |= FWNODE_FLAG_INITIALIZED; + else + fwnode->flags &= ~FWNODE_FLAG_INITIALIZED; +} + extern u32 fw_devlink_get_flags(void); extern bool fw_devlink_is_strict(void); int fwnode_link_add(struct fwnode_handle *con, struct fwnode_handle *sup); -- cgit v1.2.3 From ef3c67b6454b8f542f50387ad481633ae30874ac Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 25 Jan 2021 21:39:48 +0200 Subject: mfd: intel_msic: Remove driver for deprecated platform Intel Moorestown and Medfield are quite old Intel Atom based 32-bit platforms, which were in limited use in some Android phones, tablets and consumer electronics more than eight years ago. There are no bugs or problems ever reported outside from Intel for breaking any of that platforms for years. It seems no real users exists who run more or less fresh kernel on it. Commit 05f4434bc130 ("ASoC: Intel: remove mfld_machine") is also in align with this theory. Due to above and to reduce a burden of supporting outdated drivers, remove the support for outdated platforms completely. Signed-off-by: Andy Shevchenko Acked-by: Mika Westerberg Acked-by: Linus Walleij Acked-by: Lee Jones Signed-off-by: Rafael J. Wysocki --- include/linux/mfd/intel_msic.h | 453 ----------------------------------------- 1 file changed, 453 deletions(-) delete mode 100644 include/linux/mfd/intel_msic.h (limited to 'include/linux') diff --git a/include/linux/mfd/intel_msic.h b/include/linux/mfd/intel_msic.h deleted file mode 100644 index 317e8608cf41..000000000000 --- a/include/linux/mfd/intel_msic.h +++ /dev/null @@ -1,453 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Core interface for Intel MSIC - * - * Copyright (C) 2011, Intel Corporation - * Author: Mika Westerberg - */ - -#ifndef __LINUX_MFD_INTEL_MSIC_H__ -#define __LINUX_MFD_INTEL_MSIC_H__ - -/* ID */ -#define INTEL_MSIC_ID0 0x000 /* RO */ -#define INTEL_MSIC_ID1 0x001 /* RO */ - -/* IRQ */ -#define INTEL_MSIC_IRQLVL1 0x002 -#define INTEL_MSIC_ADC1INT 0x003 -#define INTEL_MSIC_CCINT 0x004 -#define INTEL_MSIC_PWRSRCINT 0x005 -#define INTEL_MSIC_PWRSRCINT1 0x006 -#define INTEL_MSIC_CHRINT 0x007 -#define INTEL_MSIC_CHRINT1 0x008 -#define INTEL_MSIC_RTCIRQ 0x009 -#define INTEL_MSIC_GPIO0LVIRQ 0x00a -#define INTEL_MSIC_GPIO1LVIRQ 0x00b -#define INTEL_MSIC_GPIOHVIRQ 0x00c -#define INTEL_MSIC_VRINT 0x00d -#define INTEL_MSIC_OCAUDIO 0x00e -#define INTEL_MSIC_ACCDET 0x00f -#define INTEL_MSIC_RESETIRQ1 0x010 -#define INTEL_MSIC_RESETIRQ2 0x011 -#define INTEL_MSIC_MADC1INT 0x012 -#define INTEL_MSIC_MCCINT 0x013 -#define INTEL_MSIC_MPWRSRCINT 0x014 -#define INTEL_MSIC_MPWRSRCINT1 0x015 -#define INTEL_MSIC_MCHRINT 0x016 -#define INTEL_MSIC_MCHRINT1 0x017 -#define INTEL_MSIC_RTCIRQMASK 0x018 -#define INTEL_MSIC_GPIO0LVIRQMASK 0x019 -#define INTEL_MSIC_GPIO1LVIRQMASK 0x01a -#define INTEL_MSIC_GPIOHVIRQMASK 0x01b -#define INTEL_MSIC_VRINTMASK 0x01c -#define INTEL_MSIC_OCAUDIOMASK 0x01d -#define INTEL_MSIC_ACCDETMASK 0x01e -#define INTEL_MSIC_RESETIRQ1MASK 0x01f -#define INTEL_MSIC_RESETIRQ2MASK 0x020 -#define INTEL_MSIC_IRQLVL1MSK 0x021 -#define INTEL_MSIC_PBCONFIG 0x03e -#define INTEL_MSIC_PBSTATUS 0x03f /* RO */ - -/* GPIO */ -#define INTEL_MSIC_GPIO0LV7CTLO 0x040 -#define INTEL_MSIC_GPIO0LV6CTLO 0x041 -#define INTEL_MSIC_GPIO0LV5CTLO 0x042 -#define INTEL_MSIC_GPIO0LV4CTLO 0x043 -#define INTEL_MSIC_GPIO0LV3CTLO 0x044 -#define INTEL_MSIC_GPIO0LV2CTLO 0x045 -#define INTEL_MSIC_GPIO0LV1CTLO 0x046 -#define INTEL_MSIC_GPIO0LV0CTLO 0x047 -#define INTEL_MSIC_GPIO1LV7CTLOS 0x048 -#define INTEL_MSIC_GPIO1LV6CTLO 0x049 -#define INTEL_MSIC_GPIO1LV5CTLO 0x04a -#define INTEL_MSIC_GPIO1LV4CTLO 0x04b -#define INTEL_MSIC_GPIO1LV3CTLO 0x04c -#define INTEL_MSIC_GPIO1LV2CTLO 0x04d -#define INTEL_MSIC_GPIO1LV1CTLO 0x04e -#define INTEL_MSIC_GPIO1LV0CTLO 0x04f -#define INTEL_MSIC_GPIO0LV7CTLI 0x050 -#define INTEL_MSIC_GPIO0LV6CTLI 0x051 -#define INTEL_MSIC_GPIO0LV5CTLI 0x052 -#define INTEL_MSIC_GPIO0LV4CTLI 0x053 -#define INTEL_MSIC_GPIO0LV3CTLI 0x054 -#define INTEL_MSIC_GPIO0LV2CTLI 0x055 -#define INTEL_MSIC_GPIO0LV1CTLI 0x056 -#define INTEL_MSIC_GPIO0LV0CTLI 0x057 -#define INTEL_MSIC_GPIO1LV7CTLIS 0x058 -#define INTEL_MSIC_GPIO1LV6CTLI 0x059 -#define INTEL_MSIC_GPIO1LV5CTLI 0x05a -#define INTEL_MSIC_GPIO1LV4CTLI 0x05b -#define INTEL_MSIC_GPIO1LV3CTLI 0x05c -#define INTEL_MSIC_GPIO1LV2CTLI 0x05d -#define INTEL_MSIC_GPIO1LV1CTLI 0x05e -#define INTEL_MSIC_GPIO1LV0CTLI 0x05f -#define INTEL_MSIC_PWM0CLKDIV1 0x061 -#define INTEL_MSIC_PWM0CLKDIV0 0x062 -#define INTEL_MSIC_PWM1CLKDIV1 0x063 -#define INTEL_MSIC_PWM1CLKDIV0 0x064 -#define INTEL_MSIC_PWM2CLKDIV1 0x065 -#define INTEL_MSIC_PWM2CLKDIV0 0x066 -#define INTEL_MSIC_PWM0DUTYCYCLE 0x067 -#define INTEL_MSIC_PWM1DUTYCYCLE 0x068 -#define INTEL_MSIC_PWM2DUTYCYCLE 0x069 -#define INTEL_MSIC_GPIO0HV3CTLO 0x06d -#define INTEL_MSIC_GPIO0HV2CTLO 0x06e -#define INTEL_MSIC_GPIO0HV1CTLO 0x06f -#define INTEL_MSIC_GPIO0HV0CTLO 0x070 -#define INTEL_MSIC_GPIO1HV3CTLO 0x071 -#define INTEL_MSIC_GPIO1HV2CTLO 0x072 -#define INTEL_MSIC_GPIO1HV1CTLO 0x073 -#define INTEL_MSIC_GPIO1HV0CTLO 0x074 -#define INTEL_MSIC_GPIO0HV3CTLI 0x075 -#define INTEL_MSIC_GPIO0HV2CTLI 0x076 -#define INTEL_MSIC_GPIO0HV1CTLI 0x077 -#define INTEL_MSIC_GPIO0HV0CTLI 0x078 -#define INTEL_MSIC_GPIO1HV3CTLI 0x079 -#define INTEL_MSIC_GPIO1HV2CTLI 0x07a -#define INTEL_MSIC_GPIO1HV1CTLI 0x07b -#define INTEL_MSIC_GPIO1HV0CTLI 0x07c - -/* SVID */ -#define INTEL_MSIC_SVIDCTRL0 0x080 -#define INTEL_MSIC_SVIDCTRL1 0x081 -#define INTEL_MSIC_SVIDCTRL2 0x082 -#define INTEL_MSIC_SVIDTXLASTPKT3 0x083 /* RO */ -#define INTEL_MSIC_SVIDTXLASTPKT2 0x084 /* RO */ -#define INTEL_MSIC_SVIDTXLASTPKT1 0x085 /* RO */ -#define INTEL_MSIC_SVIDTXLASTPKT0 0x086 /* RO */ -#define INTEL_MSIC_SVIDPKTOUTBYTE3 0x087 -#define INTEL_MSIC_SVIDPKTOUTBYTE2 0x088 -#define INTEL_MSIC_SVIDPKTOUTBYTE1 0x089 -#define INTEL_MSIC_SVIDPKTOUTBYTE0 0x08a -#define INTEL_MSIC_SVIDRXVPDEBUG1 0x08b -#define INTEL_MSIC_SVIDRXVPDEBUG0 0x08c -#define INTEL_MSIC_SVIDRXLASTPKT3 0x08d /* RO */ -#define INTEL_MSIC_SVIDRXLASTPKT2 0x08e /* RO */ -#define INTEL_MSIC_SVIDRXLASTPKT1 0x08f /* RO */ -#define INTEL_MSIC_SVIDRXLASTPKT0 0x090 /* RO */ -#define INTEL_MSIC_SVIDRXCHKSTATUS3 0x091 /* RO */ -#define INTEL_MSIC_SVIDRXCHKSTATUS2 0x092 /* RO */ -#define INTEL_MSIC_SVIDRXCHKSTATUS1 0x093 /* RO */ -#define INTEL_MSIC_SVIDRXCHKSTATUS0 0x094 /* RO */ - -/* VREG */ -#define INTEL_MSIC_VCCLATCH 0x0c0 -#define INTEL_MSIC_VNNLATCH 0x0c1 -#define INTEL_MSIC_VCCCNT 0x0c2 -#define INTEL_MSIC_SMPSRAMP 0x0c3 -#define INTEL_MSIC_VNNCNT 0x0c4 -#define INTEL_MSIC_VNNAONCNT 0x0c5 -#define INTEL_MSIC_VCC122AONCNT 0x0c6 -#define INTEL_MSIC_V180AONCNT 0x0c7 -#define INTEL_MSIC_V500CNT 0x0c8 -#define INTEL_MSIC_VIHFCNT 0x0c9 -#define INTEL_MSIC_LDORAMP1 0x0ca -#define INTEL_MSIC_LDORAMP2 0x0cb -#define INTEL_MSIC_VCC108AONCNT 0x0cc -#define INTEL_MSIC_VCC108ASCNT 0x0cd -#define INTEL_MSIC_VCC108CNT 0x0ce -#define INTEL_MSIC_VCCA100ASCNT 0x0cf -#define INTEL_MSIC_VCCA100CNT 0x0d0 -#define INTEL_MSIC_VCC180AONCNT 0x0d1 -#define INTEL_MSIC_VCC180CNT 0x0d2 -#define INTEL_MSIC_VCC330CNT 0x0d3 -#define INTEL_MSIC_VUSB330CNT 0x0d4 -#define INTEL_MSIC_VCCSDIOCNT 0x0d5 -#define INTEL_MSIC_VPROG1CNT 0x0d6 -#define INTEL_MSIC_VPROG2CNT 0x0d7 -#define INTEL_MSIC_VEMMCSCNT 0x0d8 -#define INTEL_MSIC_VEMMC1CNT 0x0d9 -#define INTEL_MSIC_VEMMC2CNT 0x0da -#define INTEL_MSIC_VAUDACNT 0x0db -#define INTEL_MSIC_VHSPCNT 0x0dc -#define INTEL_MSIC_VHSNCNT 0x0dd -#define INTEL_MSIC_VHDMICNT 0x0de -#define INTEL_MSIC_VOTGCNT 0x0df -#define INTEL_MSIC_V1P35CNT 0x0e0 -#define INTEL_MSIC_V330AONCNT 0x0e1 - -/* RESET */ -#define INTEL_MSIC_CHIPCNTRL 0x100 /* WO */ -#define INTEL_MSIC_ERCONFIG 0x101 - -/* BURST */ -#define INTEL_MSIC_BATCURRENTLIMIT12 0x102 -#define INTEL_MSIC_BATTIMELIMIT12 0x103 -#define INTEL_MSIC_BATTIMELIMIT3 0x104 -#define INTEL_MSIC_BATTIMEDB 0x105 -#define INTEL_MSIC_BRSTCONFIGOUTPUTS 0x106 -#define INTEL_MSIC_BRSTCONFIGACTIONS 0x107 -#define INTEL_MSIC_BURSTCONTROLSTATUS 0x108 - -/* RTC */ -#define INTEL_MSIC_RTCB1 0x140 /* RO */ -#define INTEL_MSIC_RTCB2 0x141 /* RO */ -#define INTEL_MSIC_RTCB3 0x142 /* RO */ -#define INTEL_MSIC_RTCB4 0x143 /* RO */ -#define INTEL_MSIC_RTCOB1 0x144 -#define INTEL_MSIC_RTCOB2 0x145 -#define INTEL_MSIC_RTCOB3 0x146 -#define INTEL_MSIC_RTCOB4 0x147 -#define INTEL_MSIC_RTCAB1 0x148 -#define INTEL_MSIC_RTCAB2 0x149 -#define INTEL_MSIC_RTCAB3 0x14a -#define INTEL_MSIC_RTCAB4 0x14b -#define INTEL_MSIC_RTCWAB1 0x14c -#define INTEL_MSIC_RTCWAB2 0x14d -#define INTEL_MSIC_RTCWAB3 0x14e -#define INTEL_MSIC_RTCWAB4 0x14f -#define INTEL_MSIC_RTCSC1 0x150 -#define INTEL_MSIC_RTCSC2 0x151 -#define INTEL_MSIC_RTCSC3 0x152 -#define INTEL_MSIC_RTCSC4 0x153 -#define INTEL_MSIC_RTCSTATUS 0x154 /* RO */ -#define INTEL_MSIC_RTCCONFIG1 0x155 -#define INTEL_MSIC_RTCCONFIG2 0x156 - -/* CHARGER */ -#define INTEL_MSIC_BDTIMER 0x180 -#define INTEL_MSIC_BATTRMV 0x181 -#define INTEL_MSIC_VBUSDET 0x182 -#define INTEL_MSIC_VBUSDET1 0x183 -#define INTEL_MSIC_ADPHVDET 0x184 -#define INTEL_MSIC_ADPLVDET 0x185 -#define INTEL_MSIC_ADPDETDBDM 0x186 -#define INTEL_MSIC_LOWBATTDET 0x187 -#define INTEL_MSIC_CHRCTRL 0x188 -#define INTEL_MSIC_CHRCVOLTAGE 0x189 -#define INTEL_MSIC_CHRCCURRENT 0x18a -#define INTEL_MSIC_SPCHARGER 0x18b -#define INTEL_MSIC_CHRTTIME 0x18c -#define INTEL_MSIC_CHRCTRL1 0x18d -#define INTEL_MSIC_PWRSRCLMT 0x18e -#define INTEL_MSIC_CHRSTWDT 0x18f -#define INTEL_MSIC_WDTWRITE 0x190 /* WO */ -#define INTEL_MSIC_CHRSAFELMT 0x191 -#define INTEL_MSIC_SPWRSRCINT 0x192 /* RO */ -#define INTEL_MSIC_SPWRSRCINT1 0x193 /* RO */ -#define INTEL_MSIC_CHRLEDPWM 0x194 -#define INTEL_MSIC_CHRLEDCTRL 0x195 - -/* ADC */ -#define INTEL_MSIC_ADC1CNTL1 0x1c0 -#define INTEL_MSIC_ADC1CNTL2 0x1c1 -#define INTEL_MSIC_ADC1CNTL3 0x1c2 -#define INTEL_MSIC_ADC1OFFSETH 0x1c3 /* RO */ -#define INTEL_MSIC_ADC1OFFSETL 0x1c4 /* RO */ -#define INTEL_MSIC_ADC1ADDR0 0x1c5 -#define INTEL_MSIC_ADC1ADDR1 0x1c6 -#define INTEL_MSIC_ADC1ADDR2 0x1c7 -#define INTEL_MSIC_ADC1ADDR3 0x1c8 -#define INTEL_MSIC_ADC1ADDR4 0x1c9 -#define INTEL_MSIC_ADC1ADDR5 0x1ca -#define INTEL_MSIC_ADC1ADDR6 0x1cb -#define INTEL_MSIC_ADC1ADDR7 0x1cc -#define INTEL_MSIC_ADC1ADDR8 0x1cd -#define INTEL_MSIC_ADC1ADDR9 0x1ce -#define INTEL_MSIC_ADC1ADDR10 0x1cf -#define INTEL_MSIC_ADC1ADDR11 0x1d0 -#define INTEL_MSIC_ADC1ADDR12 0x1d1 -#define INTEL_MSIC_ADC1ADDR13 0x1d2 -#define INTEL_MSIC_ADC1ADDR14 0x1d3 -#define INTEL_MSIC_ADC1SNS0H 0x1d4 /* RO */ -#define INTEL_MSIC_ADC1SNS0L 0x1d5 /* RO */ -#define INTEL_MSIC_ADC1SNS1H 0x1d6 /* RO */ -#define INTEL_MSIC_ADC1SNS1L 0x1d7 /* RO */ -#define INTEL_MSIC_ADC1SNS2H 0x1d8 /* RO */ -#define INTEL_MSIC_ADC1SNS2L 0x1d9 /* RO */ -#define INTEL_MSIC_ADC1SNS3H 0x1da /* RO */ -#define INTEL_MSIC_ADC1SNS3L 0x1db /* RO */ -#define INTEL_MSIC_ADC1SNS4H 0x1dc /* RO */ -#define INTEL_MSIC_ADC1SNS4L 0x1dd /* RO */ -#define INTEL_MSIC_ADC1SNS5H 0x1de /* RO */ -#define INTEL_MSIC_ADC1SNS5L 0x1df /* RO */ -#define INTEL_MSIC_ADC1SNS6H 0x1e0 /* RO */ -#define INTEL_MSIC_ADC1SNS6L 0x1e1 /* RO */ -#define INTEL_MSIC_ADC1SNS7H 0x1e2 /* RO */ -#define INTEL_MSIC_ADC1SNS7L 0x1e3 /* RO */ -#define INTEL_MSIC_ADC1SNS8H 0x1e4 /* RO */ -#define INTEL_MSIC_ADC1SNS8L 0x1e5 /* RO */ -#define INTEL_MSIC_ADC1SNS9H 0x1e6 /* RO */ -#define INTEL_MSIC_ADC1SNS9L 0x1e7 /* RO */ -#define INTEL_MSIC_ADC1SNS10H 0x1e8 /* RO */ -#define INTEL_MSIC_ADC1SNS10L 0x1e9 /* RO */ -#define INTEL_MSIC_ADC1SNS11H 0x1ea /* RO */ -#define INTEL_MSIC_ADC1SNS11L 0x1eb /* RO */ -#define INTEL_MSIC_ADC1SNS12H 0x1ec /* RO */ -#define INTEL_MSIC_ADC1SNS12L 0x1ed /* RO */ -#define INTEL_MSIC_ADC1SNS13H 0x1ee /* RO */ -#define INTEL_MSIC_ADC1SNS13L 0x1ef /* RO */ -#define INTEL_MSIC_ADC1SNS14H 0x1f0 /* RO */ -#define INTEL_MSIC_ADC1SNS14L 0x1f1 /* RO */ -#define INTEL_MSIC_ADC1BV0H 0x1f2 /* RO */ -#define INTEL_MSIC_ADC1BV0L 0x1f3 /* RO */ -#define INTEL_MSIC_ADC1BV1H 0x1f4 /* RO */ -#define INTEL_MSIC_ADC1BV1L 0x1f5 /* RO */ -#define INTEL_MSIC_ADC1BV2H 0x1f6 /* RO */ -#define INTEL_MSIC_ADC1BV2L 0x1f7 /* RO */ -#define INTEL_MSIC_ADC1BV3H 0x1f8 /* RO */ -#define INTEL_MSIC_ADC1BV3L 0x1f9 /* RO */ -#define INTEL_MSIC_ADC1BI0H 0x1fa /* RO */ -#define INTEL_MSIC_ADC1BI0L 0x1fb /* RO */ -#define INTEL_MSIC_ADC1BI1H 0x1fc /* RO */ -#define INTEL_MSIC_ADC1BI1L 0x1fd /* RO */ -#define INTEL_MSIC_ADC1BI2H 0x1fe /* RO */ -#define INTEL_MSIC_ADC1BI2L 0x1ff /* RO */ -#define INTEL_MSIC_ADC1BI3H 0x200 /* RO */ -#define INTEL_MSIC_ADC1BI3L 0x201 /* RO */ -#define INTEL_MSIC_CCCNTL 0x202 -#define INTEL_MSIC_CCOFFSETH 0x203 /* RO */ -#define INTEL_MSIC_CCOFFSETL 0x204 /* RO */ -#define INTEL_MSIC_CCADCHA 0x205 /* RO */ -#define INTEL_MSIC_CCADCLA 0x206 /* RO */ - -/* AUDIO */ -#define INTEL_MSIC_AUDPLLCTRL 0x240 -#define INTEL_MSIC_DMICBUF0123 0x241 -#define INTEL_MSIC_DMICBUF45 0x242 -#define INTEL_MSIC_DMICGPO 0x244 -#define INTEL_MSIC_DMICMUX 0x245 -#define INTEL_MSIC_DMICCLK 0x246 -#define INTEL_MSIC_MICBIAS 0x247 -#define INTEL_MSIC_ADCCONFIG 0x248 -#define INTEL_MSIC_MICAMP1 0x249 -#define INTEL_MSIC_MICAMP2 0x24a -#define INTEL_MSIC_NOISEMUX 0x24b -#define INTEL_MSIC_AUDIOMUX12 0x24c -#define INTEL_MSIC_AUDIOMUX34 0x24d -#define INTEL_MSIC_AUDIOSINC 0x24e -#define INTEL_MSIC_AUDIOTXEN 0x24f -#define INTEL_MSIC_HSEPRXCTRL 0x250 -#define INTEL_MSIC_IHFRXCTRL 0x251 -#define INTEL_MSIC_VOICETXVOL 0x252 -#define INTEL_MSIC_SIDETONEVOL 0x253 -#define INTEL_MSIC_MUSICSHARVOL 0x254 -#define INTEL_MSIC_VOICETXCTRL 0x255 -#define INTEL_MSIC_HSMIXER 0x256 -#define INTEL_MSIC_DACCONFIG 0x257 -#define INTEL_MSIC_SOFTMUTE 0x258 -#define INTEL_MSIC_HSLVOLCTRL 0x259 -#define INTEL_MSIC_HSRVOLCTRL 0x25a -#define INTEL_MSIC_IHFLVOLCTRL 0x25b -#define INTEL_MSIC_IHFRVOLCTRL 0x25c -#define INTEL_MSIC_DRIVEREN 0x25d -#define INTEL_MSIC_LINEOUTCTRL 0x25e -#define INTEL_MSIC_VIB1CTRL1 0x25f -#define INTEL_MSIC_VIB1CTRL2 0x260 -#define INTEL_MSIC_VIB1CTRL3 0x261 -#define INTEL_MSIC_VIB1SPIPCM_1 0x262 -#define INTEL_MSIC_VIB1SPIPCM_2 0x263 -#define INTEL_MSIC_VIB1CTRL5 0x264 -#define INTEL_MSIC_VIB2CTRL1 0x265 -#define INTEL_MSIC_VIB2CTRL2 0x266 -#define INTEL_MSIC_VIB2CTRL3 0x267 -#define INTEL_MSIC_VIB2SPIPCM_1 0x268 -#define INTEL_MSIC_VIB2SPIPCM_2 0x269 -#define INTEL_MSIC_VIB2CTRL5 0x26a -#define INTEL_MSIC_BTNCTRL1 0x26b -#define INTEL_MSIC_BTNCTRL2 0x26c -#define INTEL_MSIC_PCM1TXSLOT01 0x26d -#define INTEL_MSIC_PCM1TXSLOT23 0x26e -#define INTEL_MSIC_PCM1TXSLOT45 0x26f -#define INTEL_MSIC_PCM1RXSLOT0123 0x270 -#define INTEL_MSIC_PCM1RXSLOT045 0x271 -#define INTEL_MSIC_PCM2TXSLOT01 0x272 -#define INTEL_MSIC_PCM2TXSLOT23 0x273 -#define INTEL_MSIC_PCM2TXSLOT45 0x274 -#define INTEL_MSIC_PCM2RXSLOT01 0x275 -#define INTEL_MSIC_PCM2RXSLOT23 0x276 -#define INTEL_MSIC_PCM2RXSLOT45 0x277 -#define INTEL_MSIC_PCM1CTRL1 0x278 -#define INTEL_MSIC_PCM1CTRL2 0x279 -#define INTEL_MSIC_PCM1CTRL3 0x27a -#define INTEL_MSIC_PCM2CTRL1 0x27b -#define INTEL_MSIC_PCM2CTRL2 0x27c - -/* HDMI */ -#define INTEL_MSIC_HDMIPUEN 0x280 -#define INTEL_MSIC_HDMISTATUS 0x281 /* RO */ - -/* Physical address of the start of the MSIC interrupt tree in SRAM */ -#define INTEL_MSIC_IRQ_PHYS_BASE 0xffff7fc0 - -/** - * struct intel_msic_gpio_pdata - platform data for the MSIC GPIO driver - * @gpio_base: base number for the GPIOs - */ -struct intel_msic_gpio_pdata { - unsigned gpio_base; -}; - -/** - * struct intel_msic_ocd_pdata - platform data for the MSIC OCD driver - * @gpio: GPIO number used for OCD interrupts - * - * The MSIC MFD driver converts @gpio into an IRQ number and passes it to - * the OCD driver as %IORESOURCE_IRQ. - */ -struct intel_msic_ocd_pdata { - unsigned gpio; -}; - -/* MSIC embedded blocks (subdevices) */ -enum intel_msic_block { - INTEL_MSIC_BLOCK_TOUCH, - INTEL_MSIC_BLOCK_ADC, - INTEL_MSIC_BLOCK_BATTERY, - INTEL_MSIC_BLOCK_GPIO, - INTEL_MSIC_BLOCK_AUDIO, - INTEL_MSIC_BLOCK_HDMI, - INTEL_MSIC_BLOCK_THERMAL, - INTEL_MSIC_BLOCK_POWER_BTN, - INTEL_MSIC_BLOCK_OCD, - - INTEL_MSIC_BLOCK_LAST, -}; - -/** - * struct intel_msic_platform_data - platform data for the MSIC driver - * @irq: array of interrupt numbers, one per device. If @irq is set to %0 - * for a given block, the corresponding platform device is not - * created. For devices which don't have an interrupt, use %0xff - * (this is same as in SFI spec). - * @gpio: platform data for the MSIC GPIO driver - * @ocd: platform data for the MSIC OCD driver - * - * Once the MSIC driver is initialized, the register interface is ready to - * use. All the platform devices for subdevices are created after the - * register interface is ready so that we can guarantee its availability to - * the subdevice drivers. - * - * Interrupt numbers are passed to the subdevices via %IORESOURCE_IRQ - * resources of the created platform device. - */ -struct intel_msic_platform_data { - int irq[INTEL_MSIC_BLOCK_LAST]; - struct intel_msic_gpio_pdata *gpio; - struct intel_msic_ocd_pdata *ocd; -}; - -struct intel_msic; - -extern int intel_msic_reg_read(unsigned short reg, u8 *val); -extern int intel_msic_reg_write(unsigned short reg, u8 val); -extern int intel_msic_reg_update(unsigned short reg, u8 val, u8 mask); -extern int intel_msic_bulk_read(unsigned short *reg, u8 *buf, size_t count); -extern int intel_msic_bulk_write(unsigned short *reg, u8 *buf, size_t count); - -/* - * pdev_to_intel_msic - gets an MSIC instance from the platform device - * @pdev: platform device pointer - * - * The client drivers need to have pointer to the MSIC instance if they - * want to call intel_msic_irq_read(). This macro can be used for - * convenience to get the MSIC pointer from @pdev where needed. This is - * _only_ valid for devices which are managed by the MSIC. - */ -#define pdev_to_intel_msic(pdev) (dev_get_drvdata(pdev->dev.parent)) - -extern int intel_msic_irq_read(struct intel_msic *msic, unsigned short reg, - u8 *val); - -#endif /* __LINUX_MFD_INTEL_MSIC_H__ */ -- cgit v1.2.3 From 81d88ce55092edf1a1f928efb373f289c6b90efd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 24 Nov 2020 16:38:40 +0100 Subject: dma-mapping: remove the {alloc,free}_noncoherent methods It turns out allowing non-contigous allocations here was a rather bad idea, as we'll now need to define ways to get the pages for mmaping or dma_buf sharing. Revert this change and stick to the original concept. A different API for the use case of non-contigous allocations will be added back later. Signed-off-by: Christoph Hellwig Reviewed-by: Tomasz Figa Tested-by: Ricardo Ribalda :wq --- include/linux/dma-map-ops.h | 5 ----- include/linux/dma-mapping.h | 17 +++++++++++++---- 2 files changed, 13 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index 70fcd0f610ea..11e02537b9e0 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -22,11 +22,6 @@ struct dma_map_ops { gfp_t gfp); void (*free_pages)(struct device *dev, size_t size, struct page *vaddr, dma_addr_t dma_handle, enum dma_data_direction dir); - void *(*alloc_noncoherent)(struct device *dev, size_t size, - dma_addr_t *dma_handle, enum dma_data_direction dir, - gfp_t gfp); - void (*free_noncoherent)(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle, enum dma_data_direction dir); int (*mmap)(struct device *, struct vm_area_struct *, void *, dma_addr_t, size_t, unsigned long attrs); diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 2e49996a8f39..fbfa3f5abd94 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -263,10 +263,19 @@ struct page *dma_alloc_pages(struct device *dev, size_t size, dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp); void dma_free_pages(struct device *dev, size_t size, struct page *page, dma_addr_t dma_handle, enum dma_data_direction dir); -void *dma_alloc_noncoherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp); -void dma_free_noncoherent(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle, enum dma_data_direction dir); + +static inline void *dma_alloc_noncoherent(struct device *dev, size_t size, + dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp) +{ + struct page *page = dma_alloc_pages(dev, size, dma_handle, dir, gfp); + return page ? page_address(page) : NULL; +} + +static inline void dma_free_noncoherent(struct device *dev, size_t size, + void *vaddr, dma_addr_t dma_handle, enum dma_data_direction dir) +{ + dma_free_pages(dev, size, virt_to_page(vaddr), dma_handle, dir); +} static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr, size_t size, enum dma_data_direction dir, unsigned long attrs) -- cgit v1.2.3 From 1746fd4416ed5510fe9fdd6a93e49a436187b680 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Mon, 8 Feb 2021 15:09:23 -0500 Subject: tracepoints: Remove unnecessary "data_args" macro parameter While working on a clean up that would restructure the difference between architectures that have static calls vs those that do not, I was stumbling over the "data_args" parameter that includes "__data" in the arguments. The issue was that one version didn't even need it, while the other one did. Instead of injecting a "__data = NULL;" into the macro for the unneeded version, just remove it completely. The original idea behind data_args is that there may be a case of a tracepoint with no arguments. But this is considered bad practice, and all tracepoints should pass something to that location (that's what tracepoints were created for). Link: https://lkml.kernel.org/r/20210208201050.768074128@goodmis.org Acked-by: Peter Zijlstra (Intel) Signed-off-by: Steven Rostedt (VMware) --- include/linux/tracepoint.h | 31 +++++++++++-------------------- 1 file changed, 11 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 966ed8980327..42bb5b753b33 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -160,13 +160,8 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) /* * it_func[0] is never NULL because there is at least one element in the array * when the array itself is non NULL. - * - * Note, the proto and args passed in includes "__data" as the first parameter. - * The reason for this is to handle the "void" prototype. If a tracepoint - * has a "void" prototype, then it is invalid to declare a function - * as "(void *, void)". */ -#define __DO_TRACE(name, proto, args, cond, rcuidle) \ +#define __DO_TRACE(name, args, cond, rcuidle) \ do { \ struct tracepoint_func *it_func_ptr; \ int __maybe_unused __idx = 0; \ @@ -194,7 +189,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) rcu_dereference_raw((&__tracepoint_##name)->funcs); \ if (it_func_ptr) { \ __data = (it_func_ptr)->data; \ - __DO_TRACE_CALL(name)(args); \ + __DO_TRACE_CALL(name)(__data, args); \ } \ \ if (rcuidle) { \ @@ -206,17 +201,16 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) } while (0) #ifndef MODULE -#define __DECLARE_TRACE_RCU(name, proto, args, cond, data_proto, data_args) \ +#define __DECLARE_TRACE_RCU(name, proto, args, cond) \ static inline void trace_##name##_rcuidle(proto) \ { \ if (static_key_false(&__tracepoint_##name.key)) \ __DO_TRACE(name, \ - TP_PROTO(data_proto), \ - TP_ARGS(data_args), \ + TP_ARGS(args), \ TP_CONDITION(cond), 1); \ } #else -#define __DECLARE_TRACE_RCU(name, proto, args, cond, data_proto, data_args) +#define __DECLARE_TRACE_RCU(name, proto, args, cond) #endif /* @@ -231,7 +225,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) * even when this tracepoint is off. This code has no purpose other than * poking RCU a bit. */ -#define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \ +#define __DECLARE_TRACE(name, proto, args, cond, data_proto) \ extern int __traceiter_##name(data_proto); \ DECLARE_STATIC_CALL(tp_func_##name, __traceiter_##name); \ extern struct tracepoint __tracepoint_##name; \ @@ -239,8 +233,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) { \ if (static_key_false(&__tracepoint_##name.key)) \ __DO_TRACE(name, \ - TP_PROTO(data_proto), \ - TP_ARGS(data_args), \ + TP_ARGS(args), \ TP_CONDITION(cond), 0); \ if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) { \ rcu_read_lock_sched_notrace(); \ @@ -249,7 +242,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) } \ } \ __DECLARE_TRACE_RCU(name, PARAMS(proto), PARAMS(args), \ - PARAMS(cond), PARAMS(data_proto), PARAMS(data_args)) \ + PARAMS(cond)) \ static inline int \ register_trace_##name(void (*probe)(data_proto), void *data) \ { \ @@ -332,7 +325,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) #else /* !TRACEPOINTS_ENABLED */ -#define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \ +#define __DECLARE_TRACE(name, proto, args, cond, data_proto) \ static inline void trace_##name(proto) \ { } \ static inline void trace_##name##_rcuidle(proto) \ @@ -412,14 +405,12 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) #define DECLARE_TRACE(name, proto, args) \ __DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), \ cpu_online(raw_smp_processor_id()), \ - PARAMS(void *__data, proto), \ - PARAMS(__data, args)) + PARAMS(void *__data, proto)) #define DECLARE_TRACE_CONDITION(name, proto, args, cond) \ __DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), \ cpu_online(raw_smp_processor_id()) && (PARAMS(cond)), \ - PARAMS(void *__data, proto), \ - PARAMS(__data, args)) + PARAMS(void *__data, proto)) #define TRACE_EVENT_FLAGS(event, flag) -- cgit v1.2.3 From d9a1be1be331fc857d3fe29f86c3a305950b35a9 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Mon, 8 Feb 2021 15:09:24 -0500 Subject: tracepoints: Do not punish non static call users With static calls, a tracepoint can call the callback directly if there is only one callback registered to that tracepoint. When there is more than one, the static call will call the tracepoint's "iterator" function, which needs to reload the tracepoint's "funcs" array again, as it could have changed since the first time it was loaded. But an arch without static calls is punished by having to load the tracepoint's "funcs" array twice. Once in the DO_TRACE macro, and once again in the iterator macro. For archs without static calls, there's no reason to load the array macro in the first place, since the iterator function will do it anyway. Change the __DO_TRACE_CALL() macro to do the load and call of the tracepoints funcs array only for architectures with static calls, and just call the iterator function directly for architectures without static calls. Link: https://lkml.kernel.org/r/20210208201050.909329787@goodmis.org Acked-by: Peter Zijlstra (Intel) Signed-off-by: Steven Rostedt (VMware) --- include/linux/tracepoint.h | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 42bb5b753b33..2aad1c10821a 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -152,9 +152,19 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) #ifdef TRACEPOINTS_ENABLED #ifdef CONFIG_HAVE_STATIC_CALL -#define __DO_TRACE_CALL(name) static_call(tp_func_##name) +#define __DO_TRACE_CALL(name, args) \ + do { \ + struct tracepoint_func *it_func_ptr; \ + void *__data; \ + it_func_ptr = \ + rcu_dereference_raw((&__tracepoint_##name)->funcs); \ + if (it_func_ptr) { \ + __data = (it_func_ptr)->data; \ + static_call(tp_func_##name)(__data, args); \ + } \ + } while (0) #else -#define __DO_TRACE_CALL(name) __traceiter_##name +#define __DO_TRACE_CALL(name, args) __traceiter_##name(NULL, args) #endif /* CONFIG_HAVE_STATIC_CALL */ /* @@ -163,9 +173,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) */ #define __DO_TRACE(name, args, cond, rcuidle) \ do { \ - struct tracepoint_func *it_func_ptr; \ int __maybe_unused __idx = 0; \ - void *__data; \ \ if (!(cond)) \ return; \ @@ -185,12 +193,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) rcu_irq_enter_irqson(); \ } \ \ - it_func_ptr = \ - rcu_dereference_raw((&__tracepoint_##name)->funcs); \ - if (it_func_ptr) { \ - __data = (it_func_ptr)->data; \ - __DO_TRACE_CALL(name)(__data, args); \ - } \ + __DO_TRACE_CALL(name, TP_ARGS(args)); \ \ if (rcuidle) { \ rcu_irq_exit_irqson(); \ -- cgit v1.2.3 From 7211f0a25781ace5f79b272318b4c60b5dcfd413 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 4 Feb 2021 14:30:04 -0500 Subject: tracepoints: Code clean up Restructure the code a bit to make it simpler, fix some formatting problems and add READ_ONCE/WRITE_ONCE to make sure there's no compiler load/store tearing to the variables that can be accessed across CPUs. Started with Mathieu Desnoyers's patch: Link: https://lore.kernel.org/lkml/20210203175741.20665-1-mathieu.desnoyers@efficios.com/ And will keep his signature, but I will take the responsibility of this being correct, and keep the authorship. Link: https://lkml.kernel.org/r/20210204143004.61126582@gandalf.local.home Signed-off-by: Mathieu Desnoyers Signed-off-by: Steven Rostedt (VMware) --- include/linux/tracepoint.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 2aad1c10821a..9cfb099da58f 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -305,7 +305,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) rcu_dereference_raw((&__tracepoint_##_name)->funcs); \ if (it_func_ptr) { \ do { \ - it_func = (it_func_ptr)->func; \ + it_func = READ_ONCE((it_func_ptr)->func); \ __data = (it_func_ptr)->data; \ ((void(*)(void *, proto))(it_func))(__data, args); \ } while ((++it_func_ptr)->func); \ -- cgit v1.2.3 From a1320e0c2fc834264fa2125ef5c40670dbb5b736 Mon Sep 17 00:00:00 2001 From: Jinyang He Date: Thu, 4 Feb 2021 11:34:31 +0800 Subject: ftrace: Remove unused ftrace_force_update() ftrace_force_update() is committed by Commit e1c08bdd9fa7 ("ftrace: force recording") and removed by Commit cb7be3b2fc2c ("ftrace: remove daemon"). Remove it in header file. Link: https://lkml.kernel.org/r/1612409671-8249-1-git-send-email-hejinyang@loongson.cn Signed-off-by: Jinyang He Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 9a8ce28e4485..86e5028bfa20 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -485,7 +485,6 @@ struct dyn_ftrace { struct dyn_arch_ftrace arch; }; -int ftrace_force_update(void); int ftrace_set_filter_ip(struct ftrace_ops *ops, unsigned long ip, int remove, int reset); int ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf, @@ -740,7 +739,6 @@ extern void ftrace_disable_daemon(void); extern void ftrace_enable_daemon(void); #else /* CONFIG_DYNAMIC_FTRACE */ static inline int skip_trace(unsigned long ip) { return 0; } -static inline int ftrace_force_update(void) { return 0; } static inline void ftrace_disable_daemon(void) { } static inline void ftrace_enable_daemon(void) { } static inline void ftrace_module_init(struct module *mod) { } -- cgit v1.2.3 From 8f1fc1c15329a9d53bde5636e85ca98ece2ec7bd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Martin=20Hundeb=C3=B8ll?= Date: Mon, 8 Feb 2021 16:01:57 +0100 Subject: PCI: Add Silicom Denmark vendor ID MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Update pci_ids.h with the vendor ID for Silicom Denmark. The define is going to be referenced in driver(s) for FPGA accelerated smart NICs. Link: https://lore.kernel.org/r/20210208150158.2877414-1-mhu@silicom.dk Signed-off-by: Martin Hundebøll Signed-off-by: Bjorn Helgaas Reviewed-by: Tom Rix Reviewed-by: Krzysztof Wilczyński --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index d8156a5dbee8..aae07d512ca6 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2588,6 +2588,8 @@ #define PCI_VENDOR_ID_REDHAT 0x1b36 +#define PCI_VENDOR_ID_SILICOM_DENMARK 0x1c2c + #define PCI_VENDOR_ID_AMAZON_ANNAPURNA_LABS 0x1c36 #define PCI_VENDOR_ID_CIRCUITCO 0x1cc8 -- cgit v1.2.3 From 29863d41bb6e1d969c62fdb15b0961806942960e Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Mon, 8 Feb 2021 11:34:09 -0800 Subject: net: implement threaded-able napi poll loop support This patch allows running each napi poll loop inside its own kernel thread. The kthread is created during netif_napi_add() if dev->threaded is set. And threaded mode is enabled in napi_enable(). We will provide a way to set dev->threaded and enable threaded mode without a device up/down in the following patch. Once that threaded mode is enabled and the kthread is started, napi_schedule() will wake-up such thread instead of scheduling the softirq. The threaded poll loop behaves quite likely the net_rx_action, but it does not have to manipulate local irqs and uses an explicit scheduling point based on netdev_budget. Co-developed-by: Paolo Abeni Signed-off-by: Paolo Abeni Co-developed-by: Hannes Frederic Sowa Signed-off-by: Hannes Frederic Sowa Co-developed-by: Jakub Kicinski Signed-off-by: Jakub Kicinski Signed-off-by: Wei Wang Reviewed-by: Alexander Duyck Signed-off-by: David S. Miller --- include/linux/netdevice.h | 21 +++++++-------------- 1 file changed, 7 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e9e7ada07ea1..99fb4ec9573e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -347,6 +347,7 @@ struct napi_struct { struct list_head dev_list; struct hlist_node napi_hash_node; unsigned int napi_id; + struct task_struct *thread; }; enum { @@ -358,6 +359,7 @@ enum { NAPI_STATE_NO_BUSY_POLL, /* Do not add in napi_hash, no busy polling */ NAPI_STATE_IN_BUSY_POLL, /* sk_busy_loop() owns this NAPI */ NAPI_STATE_PREFER_BUSY_POLL, /* prefer busy-polling over softirq processing*/ + NAPI_STATE_THREADED, /* The poll is performed inside its own thread*/ }; enum { @@ -369,6 +371,7 @@ enum { NAPIF_STATE_NO_BUSY_POLL = BIT(NAPI_STATE_NO_BUSY_POLL), NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL), NAPIF_STATE_PREFER_BUSY_POLL = BIT(NAPI_STATE_PREFER_BUSY_POLL), + NAPIF_STATE_THREADED = BIT(NAPI_STATE_THREADED), }; enum gro_result { @@ -503,20 +506,7 @@ static inline bool napi_complete(struct napi_struct *n) */ void napi_disable(struct napi_struct *n); -/** - * napi_enable - enable NAPI scheduling - * @n: NAPI context - * - * Resume NAPI from being scheduled on this context. - * Must be paired with napi_disable. - */ -static inline void napi_enable(struct napi_struct *n) -{ - BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state)); - smp_mb__before_atomic(); - clear_bit(NAPI_STATE_SCHED, &n->state); - clear_bit(NAPI_STATE_NPSVC, &n->state); -} +void napi_enable(struct napi_struct *n); /** * napi_synchronize - wait until NAPI is not running @@ -1827,6 +1817,8 @@ enum netdev_priv_flags { * * @wol_enabled: Wake-on-LAN is enabled * + * @threaded: napi threaded mode is enabled + * * @net_notifier_list: List of per-net netdev notifier block * that follow this device when it is moved * to another network namespace. @@ -2145,6 +2137,7 @@ struct net_device { struct lock_class_key *qdisc_running_key; bool proto_down; unsigned wol_enabled:1; + unsigned threaded:1; struct list_head net_notifier_list; -- cgit v1.2.3 From 5fdd2f0e5c64846bf3066689b73fc3b8dddd1c74 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Mon, 8 Feb 2021 11:34:10 -0800 Subject: net: add sysfs attribute to control napi threaded mode This patch adds a new sysfs attribute to the network device class. Said attribute provides a per-device control to enable/disable the threaded mode for all the napi instances of the given network device, without the need for a device up/down. User sets it to 1 or 0 to enable or disable threaded mode. Note: when switching between threaded and the current softirq based mode for a napi instance, it will not immediately take effect if the napi is currently being polled. The mode switch will happen for the next time napi_schedule() is called. Co-developed-by: Paolo Abeni Signed-off-by: Paolo Abeni Co-developed-by: Hannes Frederic Sowa Signed-off-by: Hannes Frederic Sowa Co-developed-by: Felix Fietkau Signed-off-by: Felix Fietkau Signed-off-by: Wei Wang Reviewed-by: Alexander Duyck Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 99fb4ec9573e..1340327f7abf 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -497,6 +497,8 @@ static inline bool napi_complete(struct napi_struct *n) return napi_complete_done(n, 0); } +int dev_set_threaded(struct net_device *dev, bool threaded); + /** * napi_disable - prevent NAPI from scheduling * @n: NAPI context -- cgit v1.2.3 From 0f319d49a4167e402b01b2b56639386f0b6846ba Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 10 Feb 2021 09:52:47 +0100 Subject: locking/mutex: Kill mutex_trylock_recursive() There are not users of mutex_trylock_recursive() in tree as of v5.11-rc7. Remove it. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20210210085248.219210-2-bigeasy@linutronix.de --- include/linux/mutex.h | 25 ------------------------- 1 file changed, 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mutex.h b/include/linux/mutex.h index dcd185cbfe79..0cd631a19727 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -199,29 +199,4 @@ extern void mutex_unlock(struct mutex *lock); extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock); -/* - * These values are chosen such that FAIL and SUCCESS match the - * values of the regular mutex_trylock(). - */ -enum mutex_trylock_recursive_enum { - MUTEX_TRYLOCK_FAILED = 0, - MUTEX_TRYLOCK_SUCCESS = 1, - MUTEX_TRYLOCK_RECURSIVE, -}; - -/** - * mutex_trylock_recursive - trylock variant that allows recursive locking - * @lock: mutex to be locked - * - * This function should not be used, _ever_. It is purely for hysterical GEM - * raisins, and once those are gone this will be removed. - * - * Returns: - * - MUTEX_TRYLOCK_FAILED - trylock failed, - * - MUTEX_TRYLOCK_SUCCESS - lock acquired, - * - MUTEX_TRYLOCK_RECURSIVE - we already owned the lock. - */ -extern /* __deprecated */ __must_check enum mutex_trylock_recursive_enum -mutex_trylock_recursive(struct mutex *lock); - #endif /* __LINUX_MUTEX_H */ -- cgit v1.2.3 From 7cbf1722d5fc5779946ee8f338e9e38b5de15856 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 10 Feb 2021 00:03:20 +0000 Subject: io_uring: provide FIFO ordering for task_work task_work is a LIFO list, due to how it's implemented as a lockless list. For long chains of task_work, this can be problematic as the first entry added is the last one processed. Similarly, we'd waste a lot of CPU cycles reversing this list. Wrap the task_work so we have a single task_work entry per task per ctx, and use that to run it in the right order. Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe --- include/linux/io_uring.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 35b2d845704d..2eb6d19de336 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -22,6 +22,15 @@ struct io_identity { refcount_t count; }; +struct io_wq_work_node { + struct io_wq_work_node *next; +}; + +struct io_wq_work_list { + struct io_wq_work_node *first; + struct io_wq_work_node *last; +}; + struct io_uring_task { /* submission side */ struct xarray xa; @@ -32,6 +41,11 @@ struct io_uring_task { struct io_identity *identity; atomic_t in_idle; bool sqpoll; + + spinlock_t task_lock; + struct io_wq_work_list task_list; + unsigned long task_state; + struct callback_head task_work; }; #if defined(CONFIG_IO_URING) -- cgit v1.2.3 From a805a4fa4fa376bbc145762bb8b09caa2fa8af48 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 28 Jan 2021 13:47:30 +0900 Subject: block: introduce zone_write_granularity limit Per ZBC and ZAC specifications, host-managed SMR hard-disks mandate that all writes into sequential write required zones be aligned to the device physical block size. However, NVMe ZNS does not have this constraint and allows write operations into sequential zones to be aligned to the device logical block size. This inconsistency does not help with software portability across device types. To solve this, introduce the zone_write_granularity queue limit to indicate the alignment constraint, in bytes, of write operations into zones of a zoned block device. This new limit is exported as a read-only sysfs queue attribute and the helper blk_queue_zone_write_granularity() introduced for drivers to set this limit. The function blk_queue_set_zoned() is modified to set this new limit to the device logical block size by default. NVMe ZNS devices as well as zoned nullb devices use this default value as is. The scsi disk driver is modified to execute the blk_queue_zone_write_granularity() helper to set the zone write granularity of host-managed SMR disks to the disk physical block size. The accessor functions queue_zone_write_granularity() and bdev_zone_write_granularity() are also introduced. Signed-off-by: Damien Le Moal Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Reviewed-by: Chaitanya Kulkarni Reviewed-by: Johannes Thumshirn Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 0dea268bd61b..9149f4a5adb3 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -337,6 +337,7 @@ struct queue_limits { unsigned int max_zone_append_sectors; unsigned int discard_granularity; unsigned int discard_alignment; + unsigned int zone_write_granularity; unsigned short max_segments; unsigned short max_integrity_segments; @@ -1160,6 +1161,8 @@ extern void blk_queue_logical_block_size(struct request_queue *, unsigned int); extern void blk_queue_max_zone_append_sectors(struct request_queue *q, unsigned int max_zone_append_sectors); extern void blk_queue_physical_block_size(struct request_queue *, unsigned int); +void blk_queue_zone_write_granularity(struct request_queue *q, + unsigned int size); extern void blk_queue_alignment_offset(struct request_queue *q, unsigned int alignment); void blk_queue_update_readahead(struct request_queue *q); @@ -1473,6 +1476,18 @@ static inline int bdev_io_opt(struct block_device *bdev) return queue_io_opt(bdev_get_queue(bdev)); } +static inline unsigned int +queue_zone_write_granularity(const struct request_queue *q) +{ + return q->limits.zone_write_granularity; +} + +static inline unsigned int +bdev_zone_write_granularity(struct block_device *bdev) +{ + return queue_zone_write_granularity(bdev_get_queue(bdev)); +} + static inline int queue_alignment_offset(const struct request_queue *q) { if (q->limits.misaligned) -- cgit v1.2.3 From 83fba8c8114748a18e20391565cfdfdf8466075c Mon Sep 17 00:00:00 2001 From: Chao Leng Date: Mon, 1 Feb 2021 11:49:38 +0800 Subject: blk-mq: introduce blk_mq_set_request_complete nvme drivers need to set the state of request to MQ_RQ_COMPLETE when directly complete request in queue_rq. So add blk_mq_set_request_complete. Signed-off-by: Chao Leng Signed-off-by: Christoph Hellwig --- include/linux/blk-mq.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index aabbf6830ffc..2c473c9b8990 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -490,6 +490,18 @@ static inline int blk_mq_request_completed(struct request *rq) return blk_mq_rq_state(rq) == MQ_RQ_COMPLETE; } +/* + * + * Set the state to complete when completing a request from inside ->queue_rq. + * This is used by drivers that want to ensure special complete actions that + * need access to the request are called on failure, e.g. by nvme for + * multipathing. + */ +static inline void blk_mq_set_request_complete(struct request *rq) +{ + WRITE_ONCE(rq->state, MQ_RQ_COMPLETE); +} + void blk_mq_start_request(struct request *rq); void blk_mq_end_request(struct request *rq, blk_status_t error); void __blk_mq_end_request(struct request *rq, blk_status_t error); -- cgit v1.2.3 From 1852ebd1354201cf4ab9564947ff2a17a918b294 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Wed, 10 Feb 2021 21:27:56 +1100 Subject: of: irq: make a stub for of_irq_parse_one() Signed-off-by: Stephen Rothwell Link: https://lore.kernel.org/r/20210210214720.02e6a6be@canb.auug.org.au Signed-off-by: Greg Kroah-Hartman --- include/linux/of_irq.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h index e8b78139f78c..f898d838d201 100644 --- a/include/linux/of_irq.h +++ b/include/linux/of_irq.h @@ -33,8 +33,6 @@ static inline int of_irq_parse_oldworld(struct device_node *device, int index, #endif /* CONFIG_PPC32 && CONFIG_PPC_PMAC */ extern int of_irq_parse_raw(const __be32 *addr, struct of_phandle_args *out_irq); -extern int of_irq_parse_one(struct device_node *device, int index, - struct of_phandle_args *out_irq); extern unsigned int irq_create_of_mapping(struct of_phandle_args *irq_data); extern int of_irq_to_resource(struct device_node *dev, int index, struct resource *r); @@ -42,6 +40,8 @@ extern int of_irq_to_resource(struct device_node *dev, int index, extern void of_irq_init(const struct of_device_id *matches); #ifdef CONFIG_OF_IRQ +extern int of_irq_parse_one(struct device_node *device, int index, + struct of_phandle_args *out_irq); extern int of_irq_count(struct device_node *dev); extern int of_irq_get(struct device_node *dev, int index); extern int of_irq_get_byname(struct device_node *dev, const char *name); @@ -57,6 +57,11 @@ extern struct irq_domain *of_msi_map_get_device_domain(struct device *dev, extern void of_msi_configure(struct device *dev, struct device_node *np); u32 of_msi_map_id(struct device *dev, struct device_node *msi_np, u32 id_in); #else +static inline int of_irq_parse_one(struct device_node *device, int index, + struct of_phandle_args *out_irq) +{ + return 0; +} static inline int of_irq_count(struct device_node *dev) { return 0; -- cgit v1.2.3 From 01f810ace9ed37255f27608a0864abebccf0aab3 Mon Sep 17 00:00:00 2001 From: Andrei Matei Date: Sat, 6 Feb 2021 20:10:24 -0500 Subject: bpf: Allow variable-offset stack access Before this patch, variable offset access to the stack was dissalowed for regular instructions, but was allowed for "indirect" accesses (i.e. helpers). This patch removes the restriction, allowing reading and writing to the stack through stack pointers with variable offsets. This makes stack-allocated buffers more usable in programs, and brings stack pointers closer to other types of pointers. The motivation is being able to use stack-allocated buffers for data manipulation. When the stack size limit is sufficient, allocating buffers on the stack is simpler than per-cpu arrays, or other alternatives. In unpriviledged programs, variable-offset reads and writes are disallowed (they were already disallowed for the indirect access case) because the speculative execution checking code doesn't support them. Additionally, when writing through a variable-offset stack pointer, if any pointers are in the accessible range, there's possilibities of later leaking pointers because the write cannot be tracked precisely. Writes with variable offset mark the whole range as initialized, even though we don't know which stack slots are actually written. This is in order to not reject future reads to these slots. Note that this doesn't affect writes done through helpers; like before, helpers need the whole stack range to be initialized to begin with. All the stack slots are in range are considered scalars after the write; variable-offset register spills are not tracked. For reads, all the stack slots in the variable range needs to be initialized (but see above about what writes do), otherwise the read is rejected. All register spilled in stack slots that might be read are marked as having been read, however reads through such pointers don't do register filling; the target register will always be either a scalar or a constant zero. Signed-off-by: Andrei Matei Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20210207011027.676572-2-andreimatei1@gmail.com --- include/linux/bpf.h | 5 +++++ include/linux/bpf_verifier.h | 3 ++- 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 321966fc35db..079162bbd387 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1290,6 +1290,11 @@ static inline bool bpf_allow_ptr_leaks(void) return perfmon_capable(); } +static inline bool bpf_allow_uninit_stack(void) +{ + return perfmon_capable(); +} + static inline bool bpf_allow_ptr_to_map_access(void) { return perfmon_capable(); diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index dfe6f85d97dd..532c97836d0d 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -195,7 +195,7 @@ struct bpf_func_state { * 0 = main function, 1 = first callee. */ u32 frameno; - /* subprog number == index within subprog_stack_depth + /* subprog number == index within subprog_info * zero == main subprog */ u32 subprogno; @@ -404,6 +404,7 @@ struct bpf_verifier_env { u32 used_btf_cnt; /* number of used BTF objects */ u32 id_gen; /* used to generate unique reg IDs */ bool allow_ptr_leaks; + bool allow_uninit_stack; bool allow_ptr_to_map_access; bool bpf_capable; bool bypass_spec_v1; -- cgit v1.2.3 From f31e3386a4e92ba6eda7328cb508462956c94c64 Mon Sep 17 00:00:00 2001 From: Lakshmi Ramasubramanian Date: Thu, 4 Feb 2021 09:49:51 -0800 Subject: ima: Free IMA measurement buffer after kexec syscall IMA allocates kernel virtual memory to carry forward the measurement list, from the current kernel to the next kernel on kexec system call, in ima_add_kexec_buffer() function. This buffer is not freed before completing the kexec system call resulting in memory leak. Add ima_buffer field in "struct kimage" to store the virtual address of the buffer allocated for the IMA measurement list. Free the memory allocated for the IMA measurement list in kimage_file_post_load_cleanup() function. Signed-off-by: Lakshmi Ramasubramanian Suggested-by: Tyler Hicks Reviewed-by: Thiago Jung Bauermann Reviewed-by: Tyler Hicks Fixes: 7b8589cc29e7 ("ima: on soft reboot, save the measurement list") Signed-off-by: Mimi Zohar --- include/linux/kexec.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 9e93bef52968..5f61389f5f36 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -300,6 +300,11 @@ struct kimage { /* Information for loading purgatory */ struct purgatory_info purgatory_info; #endif + +#ifdef CONFIG_IMA_KEXEC + /* Virtual address of IMA measurement buffer for kexec syscall */ + void *ima_buffer; +#endif }; /* kexec interface functions */ -- cgit v1.2.3 From cd1a41ceba8a4caef4d18a3a14d6d0f8c656efe4 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 10 Feb 2021 00:40:52 +0100 Subject: softirq: Move __ARCH_HAS_DO_SOFTIRQ to Kconfig To prepare for inlining do_softirq_own_stack() replace __ARCH_HAS_DO_SOFTIRQ with a Kconfig switch and select it in the affected architectures. This allows in the next step to move the function prototype and the inline stub into a seperate asm-generic header file which is required to avoid include recursion. Signed-off-by: Thomas Gleixner Reviewed-by: Kees Cook Link: https://lore.kernel.org/r/20210210002513.181713427@linutronix.de --- include/linux/interrupt.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index bb8ff9083e7d..f0b918f393a2 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -569,7 +569,7 @@ struct softirq_action asmlinkage void do_softirq(void); asmlinkage void __do_softirq(void); -#ifdef __ARCH_HAS_DO_SOFTIRQ +#ifdef CONFIG_HAVE_SOFTIRQ_ON_OWN_STACK void do_softirq_own_stack(void); #else static inline void do_softirq_own_stack(void) -- cgit v1.2.3 From db1cc7aede37eb9235759131ddfefd9c0ea5136f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 10 Feb 2021 00:40:53 +0100 Subject: softirq: Move do_softirq_own_stack() to generic asm header To avoid include recursion hell move the do_softirq_own_stack() related content into a generic asm header and include it from all places in arch/ which need the prototype. This allows architectures to provide an inline implementation of do_softirq_own_stack() without introducing a lot of #ifdeffery all over the place. Signed-off-by: Thomas Gleixner Reviewed-by: Kees Cook Link: https://lore.kernel.org/r/20210210002513.289960691@linutronix.de --- include/linux/interrupt.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index f0b918f393a2..967e25767153 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -569,15 +569,6 @@ struct softirq_action asmlinkage void do_softirq(void); asmlinkage void __do_softirq(void); -#ifdef CONFIG_HAVE_SOFTIRQ_ON_OWN_STACK -void do_softirq_own_stack(void); -#else -static inline void do_softirq_own_stack(void) -{ - __do_softirq(); -} -#endif - extern void open_softirq(int nr, void (*action)(struct softirq_action *)); extern void softirq_init(void); extern void __raise_softirq_irqoff(unsigned int nr); -- cgit v1.2.3 From 5b74df80f301e872143fa716f3f4361b2e293e19 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Mon, 4 Jan 2021 09:38:57 +0200 Subject: net/mlx5: Delete device list leftover Device list is not stored in mlx5_priv anymore, so delete it as it's not used. Signed-off-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 88197b87bd81..936302b2c141 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -588,7 +588,6 @@ struct mlx5_priv { /* end: alloc staff */ struct dentry *dbg_root; - struct list_head dev_list; struct list_head ctx_list; spinlock_t ctx_lock; struct mlx5_adev **adev; -- cgit v1.2.3 From 8c0381f55bbf70a3b8ab24e4f5ac62125c44c804 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Wed, 10 Feb 2021 12:00:49 -0800 Subject: of: irq: Fix the return value for of_irq_parse_one() stub When commit 1852ebd13542 ("of: irq: make a stub for of_irq_parse_one()") added a stub for of_irq_parse_one() it set the return value to 0. Return value of 0 in this instance means the call succeeded and the out_irq pointer was filled with valid data. So, fix it to return an error value. Fixes: 1852ebd13542 ("of: irq: make a stub for of_irq_parse_one()") Acked-by: Stephen Rothwell Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20210210200050.4106032-1-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/of_irq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h index f898d838d201..aaf219bd0354 100644 --- a/include/linux/of_irq.h +++ b/include/linux/of_irq.h @@ -60,7 +60,7 @@ u32 of_msi_map_id(struct device *dev, struct device_node *msi_np, u32 id_in); static inline int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_args *out_irq) { - return 0; + return -EINVAL; } static inline int of_irq_count(struct device_node *dev) { -- cgit v1.2.3 From 21a4e356d3588806307555c149b80cec3dedb180 Mon Sep 17 00:00:00 2001 From: "Andrea Parri (Microsoft)" Date: Mon, 1 Feb 2021 15:48:12 +0100 Subject: Drivers: hv: vmbus: Restrict vmbus_devices on isolated guests Only the VSCs or ICs that have been hardened and that are critical for the successful adoption of Confidential VMs should be allowed if the guest is running isolated. This change reduces the footprint of the code that will be exercised by Confidential VMs and hence the exposure to bugs and vulnerabilities. Signed-off-by: Andrea Parri (Microsoft) Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20210201144814.2701-3-parri.andrea@gmail.com Signed-off-by: Wei Liu --- include/linux/hyperv.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index f0d48a368f13..e3426f8c12db 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -789,6 +789,7 @@ struct vmbus_device { u16 dev_type; guid_t guid; bool perf_device; + bool allowed_in_isolated; }; #define VMBUS_DEFAULT_MAX_PKT_SIZE 4096 -- cgit v1.2.3 From 78785010d428f7755bf51d1c08cb2566a73dc7f5 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 1 Feb 2021 11:43:34 -0600 Subject: hv: hyperv.h: Replace one-element array with flexible-array in struct icmsg_negotiate MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is a regular need in the kernel to provide a way to declare having a dynamically sized set of trailing elements in a structure. Kernel code should always use “flexible array members”[1] for these cases. The older style of one-element or zero-length arrays should no longer be used[2]. Refactor the code according to the use of a flexible-array member in struct icmsg_negotiate, instead of a one-element array. Also, this helps the ongoing efforts to enable -Warray-bounds and fix the following warnings: drivers/hv/channel_mgmt.c:315:23: warning: array subscript 1 is above array bounds of ‘struct ic_version[1]’ [-Warray-bounds] drivers/hv/channel_mgmt.c:316:23: warning: array subscript 1 is above array bounds of ‘struct ic_version[1]’ [-Warray-bounds] [1] https://en.wikipedia.org/wiki/Flexible_array_member [2] https://www.kernel.org/doc/html/v5.9/process/deprecated.html#zero-length-and-one-element-arrays Link: https://github.com/KSPP/linux/issues/79 Link: https://github.com/KSPP/linux/issues/109 Signed-off-by: Gustavo A. R. Silva Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20210201174334.GA171933@embeddedor Signed-off-by: Wei Liu --- include/linux/hyperv.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index e3426f8c12db..9dd22af1b7f6 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1529,14 +1529,14 @@ struct icmsg_hdr { #define IC_VERSION_NEGOTIATION_MAX_VER_COUNT 100 #define ICMSG_HDR (sizeof(struct vmbuspipe_hdr) + sizeof(struct icmsg_hdr)) #define ICMSG_NEGOTIATE_PKT_SIZE(icframe_vercnt, icmsg_vercnt) \ - (ICMSG_HDR + offsetof(struct icmsg_negotiate, icversion_data) + \ + (ICMSG_HDR + sizeof(struct icmsg_negotiate) + \ (((icframe_vercnt) + (icmsg_vercnt)) * sizeof(struct ic_version))) struct icmsg_negotiate { u16 icframe_vercnt; u16 icmsg_vercnt; u32 reserved; - struct ic_version icversion_data[1]; /* any size array */ + struct ic_version icversion_data[]; /* any size array */ } __packed; struct shutdown_msg_data { -- cgit v1.2.3 From f11e2bc682cc197e33bfd118178cadb61326dc0e Mon Sep 17 00:00:00 2001 From: Daniel Thompson Date: Wed, 10 Feb 2021 14:25:25 +0000 Subject: kgdb: Remove kgdb_schedule_breakpoint() To the very best of my knowledge there has never been any in-tree code that calls this function. It exists largely to support an out-of-tree driver that provides kgdb-over-ethernet using the netpoll API. kgdboe has been out-of-tree for more than 10 years and I don't recall any serious attempt to upstream it at any point in the last five. At this stage it looks better to stop carrying this code in the kernel and integrate the code into the out-of-tree driver instead. The long term trajectory for the kernel looks likely to include effort to remove or reduce the use of tasklets (something that has also been true for the last 10 years). Thus the main real reason for this patch is to make explicit that the in-tree kgdb features do not require tasklets. Signed-off-by: Daniel Thompson Link: https://lore.kernel.org/r/20210210142525.2876648-1-daniel.thompson@linaro.org Reviewed-by: Douglas Anderson Acked-by: Davidlohr Bueso Acked-by: Jason Wessel --- include/linux/kgdb.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index 0d6cf64c8bb1..0444b44bd156 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -325,7 +325,6 @@ extern char *kgdb_mem2hex(char *mem, char *buf, int count); extern int kgdb_hex2mem(char *buf, char *mem, int count); extern int kgdb_isremovedbreak(unsigned long addr); -extern void kgdb_schedule_breakpoint(void); extern int kgdb_has_hit_break(unsigned long addr); extern int -- cgit v1.2.3 From f7684f5a048febd2a7bc98ee81d6dce52f7268b8 Mon Sep 17 00:00:00 2001 From: Frieder Schrempf Date: Thu, 11 Feb 2021 11:55:30 +0100 Subject: regulator: pca9450: Enable system reset on WDOG_B assertion By default the PCA9450 doesn't handle the assertion of the WDOG_B signal, but this is required to guarantee that things like software resets triggered by the watchdog work reliably. As we don't want to rely on the bootloader to enable this, we tell the PMIC to issue a cold reset in case the WDOG_B signal is asserted (WDOG_B_CFG = 10), just as the NXP U-Boot code does. Signed-off-by: Frieder Schrempf Link: https://lore.kernel.org/r/20210211105534.38972-3-frieder.schrempf@kontron.de Signed-off-by: Mark Brown --- include/linux/regulator/pca9450.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/pca9450.h b/include/linux/regulator/pca9450.h index 1bbd3014f906..ccdb5320a240 100644 --- a/include/linux/regulator/pca9450.h +++ b/include/linux/regulator/pca9450.h @@ -216,4 +216,11 @@ enum { #define IRQ_THERM_105 0x02 #define IRQ_THERM_125 0x01 +/* PCA9450_REG_RESET_CTRL bits */ +#define WDOG_B_CFG_MASK 0xC0 +#define WDOG_B_CFG_NONE 0x00 +#define WDOG_B_CFG_WARM 0x40 +#define WDOG_B_CFG_COLD_LDO12 0x80 +#define WDOG_B_CFG_COLD 0xC0 + #endif /* __LINUX_REG_PCA9450_H__ */ -- cgit v1.2.3 From 7bdcc48f4e80b01fd6057dfd382236a5b8123b61 Mon Sep 17 00:00:00 2001 From: Satya Tangirala Date: Mon, 1 Feb 2021 05:10:15 +0000 Subject: block/keyslot-manager: Introduce passthrough keyslot manager The device mapper may map over devices that have inline encryption capabilities, and to make use of those capabilities, the DM device must itself advertise those inline encryption capabilities. One way to do this would be to have the DM device set up a keyslot manager with a "sufficiently large" number of keyslots, but that would use a lot of memory. Also, the DM device itself has no "keyslots", and it doesn't make much sense to talk about "programming a key into a DM device's keyslot manager", so all that extra memory used to represent those keyslots is just wasted. All a DM device really needs to be able to do is advertise the crypto capabilities of the underlying devices in a coherent manner and expose a way to evict keys from the underlying devices. There are also devices with inline encryption hardware that do not have a limited number of keyslots. One can send a raw encryption key along with a bio to these devices (as opposed to typical inline encryption hardware that require users to first program a raw encryption key into a keyslot, and send the index of that keyslot along with the bio). These devices also only need the same things from the keyslot manager that DM devices need - a way to advertise crypto capabilities and potentially a way to expose a function to evict keys from hardware. So we introduce a "passthrough" keyslot manager that provides a way to represent a keyslot manager that doesn't have just a limited number of keyslots, and for which do not require keys to be programmed into keyslots. DM devices can set up a passthrough keyslot manager in their request queues, and advertise appropriate crypto capabilities based on those of the underlying devices. Blk-crypto does not attempt to program keys into any keyslots in the passthrough keyslot manager. Instead, if/when the bio is resubmitted to the underlying device, blk-crypto will try to program the key into the underlying device's keyslot manager. Signed-off-by: Satya Tangirala Reviewed-by: Eric Biggers Acked-by: Jens Axboe Signed-off-by: Mike Snitzer --- include/linux/keyslot-manager.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/keyslot-manager.h b/include/linux/keyslot-manager.h index 18f3f5346843..323e15dd6fa7 100644 --- a/include/linux/keyslot-manager.h +++ b/include/linux/keyslot-manager.h @@ -103,4 +103,6 @@ void blk_ksm_reprogram_all_keys(struct blk_keyslot_manager *ksm); void blk_ksm_destroy(struct blk_keyslot_manager *ksm); +void blk_ksm_init_passthrough(struct blk_keyslot_manager *ksm); + #endif /* __LINUX_KEYSLOT_MANAGER_H */ -- cgit v1.2.3 From d3b17a243790a34bd63fcef3fde63e29e2744938 Mon Sep 17 00:00:00 2001 From: Satya Tangirala Date: Mon, 1 Feb 2021 05:10:16 +0000 Subject: block/keyslot-manager: Introduce functions for device mapper support Introduce blk_ksm_update_capabilities() to update the capabilities of a keyslot manager (ksm) in-place. The pointer to a ksm in a device's request queue may not be easily replaced, because upper layers like the filesystem might access it (e.g. for programming keys/checking capabilities) at the same time the device wants to replace that request queue's ksm (and free the old ksm's memory). This function allows the device to update the capabilities of the ksm in its request queue directly. Devices can safely update the ksm this way without any synchronization with upper layers *only* if the updated (new) ksm continues to support all the crypto capabilities that the old ksm did (see description below for blk_ksm_is_superset() for why this is so). Also introduce blk_ksm_is_superset() which checks whether one ksm's capabilities are a (not necessarily strict) superset of another ksm's. The blk-crypto framework requires that crypto capabilities that were advertised when a bio was created continue to be supported by the device until that bio is ended - in practice this probably means that a device's advertised crypto capabilities can *never* "shrink" (since there's no synchronization between bio creation and when a device may want to change its advertised capabilities) - so a previously advertised crypto capability must always continue to be supported. This function can be used to check that a new ksm is a valid replacement for an old ksm. Signed-off-by: Satya Tangirala Reviewed-by: Eric Biggers Acked-by: Jens Axboe Signed-off-by: Mike Snitzer --- include/linux/keyslot-manager.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/keyslot-manager.h b/include/linux/keyslot-manager.h index 323e15dd6fa7..164568f52be7 100644 --- a/include/linux/keyslot-manager.h +++ b/include/linux/keyslot-manager.h @@ -103,6 +103,15 @@ void blk_ksm_reprogram_all_keys(struct blk_keyslot_manager *ksm); void blk_ksm_destroy(struct blk_keyslot_manager *ksm); +void blk_ksm_intersect_modes(struct blk_keyslot_manager *parent, + const struct blk_keyslot_manager *child); + void blk_ksm_init_passthrough(struct blk_keyslot_manager *ksm); +bool blk_ksm_is_superset(struct blk_keyslot_manager *ksm_superset, + struct blk_keyslot_manager *ksm_subset); + +void blk_ksm_update_capabilities(struct blk_keyslot_manager *target_ksm, + struct blk_keyslot_manager *reference_ksm); + #endif /* __LINUX_KEYSLOT_MANAGER_H */ -- cgit v1.2.3 From aa6ce87a768226802f9a231b3909fe81c503852c Mon Sep 17 00:00:00 2001 From: Satya Tangirala Date: Mon, 1 Feb 2021 05:10:17 +0000 Subject: dm: add support for passing through inline crypto support Update the device-mapper core to support exposing the inline crypto support of the underlying device(s) through the device-mapper device. This works by creating a "passthrough keyslot manager" for the dm device, which declares support for encryption settings which all underlying devices support. When a supported setting is used, the bio cloning code handles cloning the crypto context to the bios for all the underlying devices. When an unsupported setting is used, the blk-crypto fallback is used as usual. Crypto support on each underlying device is ignored unless the corresponding dm target opts into exposing it. This is needed because for inline crypto to semantically operate on the original bio, the data must not be transformed by the dm target. Thus, targets like dm-linear can expose crypto support of the underlying device, but targets like dm-crypt can't. (dm-crypt could use inline crypto itself, though.) A DM device's table can only be changed if the "new" inline encryption capabilities are a (*not* necessarily strict) superset of the "old" inline encryption capabilities. Attempts to make changes to the table that result in some inline encryption capability becoming no longer supported will be rejected. For the sake of clarity, key eviction from underlying devices will be handled in a future patch. Co-developed-by: Eric Biggers Signed-off-by: Eric Biggers Signed-off-by: Satya Tangirala Signed-off-by: Mike Snitzer --- include/linux/device-mapper.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 61a66fb8ebb3..47588130ef5e 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -257,6 +257,12 @@ struct target_type { #define DM_TARGET_NOWAIT 0x00000080 #define dm_target_supports_nowait(type) ((type)->features & DM_TARGET_NOWAIT) +/* + * A target supports passing through inline crypto support. + */ +#define DM_TARGET_PASSES_CRYPTO 0x00000100 +#define dm_target_passes_crypto(type) ((type)->features & DM_TARGET_PASSES_CRYPTO) + struct dm_target { struct dm_table *table; struct target_type *type; @@ -533,6 +539,11 @@ void dm_table_run_md_queue_async(struct dm_table *t); struct dm_table *dm_swap_table(struct mapped_device *md, struct dm_table *t); +/* + * Table keyslot manager functions + */ +void dm_destroy_keyslot_manager(struct blk_keyslot_manager *ksm); + /* * A wrapper around vmalloc. */ -- cgit v1.2.3 From e3290b9491ff5b7ee40f9e0a4c06821988a2a2bf Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Wed, 10 Feb 2021 17:38:30 -0500 Subject: dm: simplify target code conditional on CONFIG_BLK_DEV_ZONED Allow removal of CONFIG_BLK_DEV_ZONED conditionals in target_type definition of various targets. Suggested-by: Eric Biggers Signed-off-by: Mike Snitzer --- include/linux/device-mapper.h | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 47588130ef5e..c98d847b0f0b 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -93,9 +93,18 @@ typedef int (*dm_message_fn) (struct dm_target *ti, unsigned argc, char **argv, typedef int (*dm_prepare_ioctl_fn) (struct dm_target *ti, struct block_device **bdev); +#ifdef CONFIG_BLK_DEV_ZONED typedef int (*dm_report_zones_fn) (struct dm_target *ti, struct dm_report_zones_args *args, unsigned int nr_zones); +#else +/* + * Define dm_report_zones_fn so that targets can assign to NULL if + * CONFIG_BLK_DEV_ZONED disabled. Otherwise each target needs to do + * awkward #ifdefs in their target_type, etc. + */ +typedef int (*dm_report_zones_fn) (struct dm_target *dummy); +#endif /* * These iteration functions are typically used to check (and combine) @@ -187,9 +196,7 @@ struct target_type { dm_status_fn status; dm_message_fn message; dm_prepare_ioctl_fn prepare_ioctl; -#ifdef CONFIG_BLK_DEV_ZONED dm_report_zones_fn report_zones; -#endif dm_busy_fn busy; dm_iterate_devices_fn iterate_devices; dm_io_hints_fn io_hints; @@ -248,8 +255,13 @@ struct target_type { /* * Indicates that a target supports host-managed zoned block devices. */ +#ifdef CONFIG_BLK_DEV_ZONED #define DM_TARGET_ZONED_HM 0x00000040 #define dm_target_supports_zoned_hm(type) ((type)->features & DM_TARGET_ZONED_HM) +#else +#define DM_TARGET_ZONED_HM 0x00000000 +#define dm_target_supports_zoned_hm(type) (false) +#endif /* * A target handles REQ_NOWAIT -- cgit v1.2.3 From a666e5c05e7c4aaabb2c5d58117b0946803d03d2 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Wed, 10 Feb 2021 15:26:23 -0500 Subject: dm: fix deadlock when swapping to encrypted device The system would deadlock when swapping to a dm-crypt device. The reason is that for each incoming write bio, dm-crypt allocates memory that holds encrypted data. These excessive allocations exhaust all the memory and the result is either deadlock or OOM trigger. This patch limits the number of in-flight swap bios, so that the memory consumed by dm-crypt is limited. The limit is enforced if the target set the "limit_swap_bios" variable and if the bio has REQ_SWAP set. Non-swap bios are not affected becuase taking the semaphore would cause performance degradation. This is similar to request-based drivers - they will also block when the number of requests is over the limit. Signed-off-by: Mikulas Patocka Cc: stable@vger.kernel.org Signed-off-by: Mike Snitzer --- include/linux/device-mapper.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index c98d847b0f0b..7f4ac87c0b32 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -343,6 +343,11 @@ struct dm_target { * whether or not its underlying devices have support. */ bool discards_supported:1; + + /* + * Set if we need to limit the number of in-flight bios when swapping. + */ + bool limit_swap_bios:1; }; void *dm_per_bio_data(struct bio *bio, size_t data_size); -- cgit v1.2.3 From 700d4796ef59f5faf240d307839bd419e2b6bdff Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 9 Feb 2021 19:36:26 -0800 Subject: bpf: Optimize program stats Move bpf_prog_stats from prog->aux into prog to avoid one extra load in critical path of program execution. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210210033634.62081-2-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 8 -------- include/linux/filter.h | 14 +++++++++++--- 2 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 079162bbd387..5a388955e6b6 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -14,7 +14,6 @@ #include #include #include -#include #include #include #include @@ -507,12 +506,6 @@ enum bpf_cgroup_storage_type { */ #define MAX_BPF_FUNC_ARGS 12 -struct bpf_prog_stats { - u64 cnt; - u64 nsecs; - struct u64_stats_sync syncp; -} __aligned(2 * sizeof(u64)); - struct btf_func_model { u8 ret_size; u8 nr_args; @@ -845,7 +838,6 @@ struct bpf_prog_aux { u32 linfo_idx; u32 num_exentries; struct exception_table_entry *extable; - struct bpf_prog_stats __percpu *stats; union { struct work_struct work; struct rcu_head rcu; diff --git a/include/linux/filter.h b/include/linux/filter.h index 5b3137d7b690..cecb03c9d251 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -22,6 +22,7 @@ #include #include #include +#include #include @@ -539,6 +540,12 @@ struct bpf_binary_header { u8 image[] __aligned(BPF_IMAGE_ALIGNMENT); }; +struct bpf_prog_stats { + u64 cnt; + u64 nsecs; + struct u64_stats_sync syncp; +} __aligned(2 * sizeof(u64)); + struct bpf_prog { u16 pages; /* Number of allocated pages */ u16 jited:1, /* Is our filter JIT'ed? */ @@ -557,10 +564,11 @@ struct bpf_prog { u32 len; /* Number of filter blocks */ u32 jited_len; /* Size of jited insns in bytes */ u8 tag[BPF_TAG_SIZE]; - struct bpf_prog_aux *aux; /* Auxiliary fields */ - struct sock_fprog_kern *orig_prog; /* Original BPF program */ + struct bpf_prog_stats __percpu *stats; unsigned int (*bpf_func)(const void *ctx, const struct bpf_insn *insn); + struct bpf_prog_aux *aux; /* Auxiliary fields */ + struct sock_fprog_kern *orig_prog; /* Original BPF program */ /* Instructions for interpreter */ struct sock_filter insns[0]; struct bpf_insn insnsi[]; @@ -581,7 +589,7 @@ DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key); struct bpf_prog_stats *__stats; \ u64 __start = sched_clock(); \ __ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func); \ - __stats = this_cpu_ptr(prog->aux->stats); \ + __stats = this_cpu_ptr(prog->stats); \ u64_stats_update_begin(&__stats->syncp); \ __stats->cnt++; \ __stats->nsecs += sched_clock() - __start; \ -- cgit v1.2.3 From f2dd3b39467411c53703125a111f45b3672c1771 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 9 Feb 2021 19:36:28 -0800 Subject: bpf: Compute program stats for sleepable programs Since sleepable programs don't migrate from the cpu the excution stats can be computed for them as well. Reuse the same infrastructure for both sleepable and non-sleepable programs. run_cnt -> the number of times the program was executed. run_time_ns -> the program execution time in nanoseconds including the off-cpu time when the program was sleeping. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Acked-by: KP Singh Link: https://lore.kernel.org/bpf/20210210033634.62081-4-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 5a388955e6b6..e1840ceaf55f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -563,8 +563,8 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end, /* these two functions are called from generated trampoline */ u64 notrace __bpf_prog_enter(void); void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start); -void notrace __bpf_prog_enter_sleepable(void); -void notrace __bpf_prog_exit_sleepable(void); +u64 notrace __bpf_prog_enter_sleepable(void); +void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start); struct bpf_ksym { unsigned long start; -- cgit v1.2.3 From ca06f55b90020cd97f4cc6d52db95436162e7dcf Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 9 Feb 2021 19:36:29 -0800 Subject: bpf: Add per-program recursion prevention mechanism Since both sleepable and non-sleepable programs execute under migrate_disable add recursion prevention mechanism to both types of programs when they're executed via bpf trampoline. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210210033634.62081-5-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 6 +++--- include/linux/filter.h | 1 + 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e1840ceaf55f..1c8ea682c007 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -529,7 +529,7 @@ struct btf_func_model { /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 * bytes on x86. Pick a number to fit into BPF_IMAGE_SIZE / 2 */ -#define BPF_MAX_TRAMP_PROGS 40 +#define BPF_MAX_TRAMP_PROGS 38 struct bpf_tramp_progs { struct bpf_prog *progs[BPF_MAX_TRAMP_PROGS]; @@ -561,9 +561,9 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end, struct bpf_tramp_progs *tprogs, void *orig_call); /* these two functions are called from generated trampoline */ -u64 notrace __bpf_prog_enter(void); +u64 notrace __bpf_prog_enter(struct bpf_prog *prog); void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start); -u64 notrace __bpf_prog_enter_sleepable(void); +u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog); void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start); struct bpf_ksym { diff --git a/include/linux/filter.h b/include/linux/filter.h index cecb03c9d251..6a06f3c69f4e 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -565,6 +565,7 @@ struct bpf_prog { u32 jited_len; /* Size of jited insns in bytes */ u8 tag[BPF_TAG_SIZE]; struct bpf_prog_stats __percpu *stats; + int __percpu *active; unsigned int (*bpf_func)(const void *ctx, const struct bpf_insn *insn); struct bpf_prog_aux *aux; /* Auxiliary fields */ -- cgit v1.2.3 From 9ed9e9ba2337205311398a312796c213737bac35 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 9 Feb 2021 19:36:31 -0800 Subject: bpf: Count the number of times recursion was prevented Add per-program counter for number of times recursion prevention mechanism was triggered and expose it via show_fdinfo and bpf_prog_info. Teach bpftool to print it. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210210033634.62081-7-alexei.starovoitov@gmail.com --- include/linux/filter.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 6a06f3c69f4e..3b00fc906ccd 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -543,6 +543,7 @@ struct bpf_binary_header { struct bpf_prog_stats { u64 cnt; u64 nsecs; + u64 misses; struct u64_stats_sync syncp; } __aligned(2 * sizeof(u64)); -- cgit v1.2.3 From 539cf68cd51bfcd2987ce1c44e628e9da69de7c8 Mon Sep 17 00:00:00 2001 From: Pratyush Yadav Date: Thu, 4 Feb 2021 19:42:17 +0530 Subject: spi: spi-mem: add spi_mem_dtr_supports_op() spi_mem_default_supports_op() rejects DTR ops by default to ensure that the controller drivers that haven't been updated with DTR support continue to reject them. It also makes sure that controllers that don't support DTR mode at all (which is most of them at the moment) also reject them. This means that controller drivers that want to support DTR mode can't use spi_mem_default_supports_op(). Driver authors have to roll their own supports_op() function and mimic the buswidth checks. See spi-cadence-quadspi.c for example. Or even worse, driver authors might skip it completely or get it wrong. Add spi_mem_dtr_supports_op(). It provides a basic sanity check for DTR ops and performs the buswidth requirement check. Move the logic for checking buswidth in spi_mem_default_supports_op() to a separate function so the logic is not repeated twice. Signed-off-by: Pratyush Yadav Reviewed-by: Miquel Raynal Link: https://lore.kernel.org/r/20210204141218.32229-1-p.yadav@ti.com Signed-off-by: Mark Brown --- include/linux/spi/spi-mem.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h index 159463cc659c..2b65c9edc34e 100644 --- a/include/linux/spi/spi-mem.h +++ b/include/linux/spi/spi-mem.h @@ -311,6 +311,9 @@ void spi_controller_dma_unmap_mem_op_data(struct spi_controller *ctlr, bool spi_mem_default_supports_op(struct spi_mem *mem, const struct spi_mem_op *op); +bool spi_mem_dtr_supports_op(struct spi_mem *mem, + const struct spi_mem_op *op); + #else static inline int spi_controller_dma_map_mem_op_data(struct spi_controller *ctlr, @@ -334,6 +337,12 @@ bool spi_mem_default_supports_op(struct spi_mem *mem, return false; } +static inline +bool spi_mem_dtr_supports_op(struct spi_mem *mem, + const struct spi_mem_op *op) +{ + return false; +} #endif /* CONFIG_SPI_MEM */ int spi_mem_adjust_op_size(struct spi_mem *mem, struct spi_mem_op *op); -- cgit v1.2.3 From 53abf3fe831756261f399dad03ccc07235296acf Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Thu, 11 Feb 2021 10:20:36 -0700 Subject: coresight: etm-perf: Clarify comment on perf options In theory, the options should be arbitrary values and are neutral for any ETM version; so far perf tool uses ETMv3.5/PTM ETMCR config bits except for register's bit definitions, also uses as options. This can introduce confusion, especially if we want to add a new option but the new option is not supported by ETMv3.5/PTM ETMCR. But on the other hand, we cannot change options since these options are generic CoreSight PMU ABI. For easier maintenance and avoid confusion, this patch refines the comment to clarify perf options, and gives out the background info for these bits are coming from ETMv3.5/PTM. Afterwards, we should take these options as general knobs, and if there have any confliction with ETMv3.5/PTM, should consider to define saperate macros for ETMv3.5/PTM ETMCR config bits. Suggested-by: Suzuki K Poulose Reviewed-by: Suzuki K Poulose Signed-off-by: Leo Yan Signed-off-by: Mathieu Poirier Link: https://lore.kernel.org/r/20210206150833.42120-2-leo.yan@linaro.org Link: https://lore.kernel.org/r/20210211172038.2483517-2-mathieu.poirier@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight-pmu.h | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/coresight-pmu.h b/include/linux/coresight-pmu.h index b0e35eec6499..5dc47cfdcf07 100644 --- a/include/linux/coresight-pmu.h +++ b/include/linux/coresight-pmu.h @@ -10,11 +10,18 @@ #define CORESIGHT_ETM_PMU_NAME "cs_etm" #define CORESIGHT_ETM_PMU_SEED 0x10 -/* ETMv3.5/PTM's ETMCR config bit */ -#define ETM_OPT_CYCACC 12 -#define ETM_OPT_CTXTID 14 -#define ETM_OPT_TS 28 -#define ETM_OPT_RETSTK 29 +/* + * Below are the definition of bit offsets for perf option, and works as + * arbitrary values for all ETM versions. + * + * Most of them are orignally from ETMv3.5/PTM's ETMCR config, therefore, + * ETMv3.5/PTM doesn't define ETMCR config bits with prefix "ETM3_" and + * directly use below macros as config bits. + */ +#define ETM_OPT_CYCACC 12 +#define ETM_OPT_CTXTID 14 +#define ETM_OPT_TS 28 +#define ETM_OPT_RETSTK 29 /* ETMv4 CONFIGR programming bits for the ETM OPTs */ #define ETM4_CFG_BIT_CYCACC 4 -- cgit v1.2.3 From 88f11864cf1d1324f620059ec747d74b72d9d736 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Thu, 11 Feb 2021 10:20:37 -0700 Subject: coresight: etm-perf: Support PID tracing for kernel at EL2 When the kernel is running at EL2, the PID is stored in CONTEXTIDR_EL2. So, tracing CONTEXTIDR_EL1 doesn't give us the pid of the process. Thus we should trace the VMID with VMIDOPT set to trace CONTEXTIDR_EL2 instead of CONTEXTIDR_EL1. Given that we have an existing config option "contextid" and this will be useful for tracing virtual machines (when we get to support virtualization). So instead, this patch extends option CTXTID with an extra bit ETM_OPT_CTXTID2 (bit 15), thus on an EL2 kernel, we will have another bit available for the perf tool: ETM_OPT_CTXTID is for kernel running in EL1, ETM_OPT_CTXTID2 is used when kernel runs in EL2 with VHE enabled. The tool must be backward compatible for users, i.e, "contextid" today traces PID and that should remain the same; for this purpose, the perf tool is updated to automatically set corresponding bit for the "contextid" config, therefore, the user doesn't have to bother which EL the kernel is running. i.e, perf record -e cs_etm/contextid/u -- will always do the "pid" tracing, independent of the kernel EL. The driver parses the format "contextid", which traces CONTEXTIDR_EL1 for ETM_OPT_CTXTID (on EL1 kernel) and traces CONTEXTIDR_EL2 for ETM_OPT_CTXTID2 (on EL2 kernel). Besides the enhancement for format "contexid", extra two formats are introduced: "contextid1" and "contextid2". This considers to support tracing both CONTEXTIDR_EL1 and CONTEXTIDR_EL2 when the kernel is running at EL2. Finally, the PMU formats are defined as follow: "contextid1": Available on both EL1 kernel and EL2 kernel. When the kernel is running at EL1, "contextid1" enables the PID tracing; when the kernel is running at EL2, this enables tracing the PID of guest applications. "contextid2": Only usable when the kernel is running at EL2. When selected, enables PID tracing on EL2 kernel. "contextid": Will be an alias for the option that enables PID tracing. I.e, contextid == contextid1, on EL1 kernel. contextid == contextid2, on EL2 kernel. Cc: Mathieu Poirier Cc: Al Grant Cc: Mike Leach Cc: Leo Yan Reviewed-by: Mike Leach Signed-off-by: Suzuki K Poulose [ Added two config formats: contextid1, contextid2 ] Signed-off-by: Leo Yan Signed-off-by: Mathieu Poirier Link: https://lore.kernel.org/r/20210206150833.42120-4-leo.yan@linaro.org Link: https://lore.kernel.org/r/20210211172038.2483517-3-mathieu.poirier@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight-pmu.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/coresight-pmu.h b/include/linux/coresight-pmu.h index 5dc47cfdcf07..4ac5c081af93 100644 --- a/include/linux/coresight-pmu.h +++ b/include/linux/coresight-pmu.h @@ -20,14 +20,17 @@ */ #define ETM_OPT_CYCACC 12 #define ETM_OPT_CTXTID 14 +#define ETM_OPT_CTXTID2 15 #define ETM_OPT_TS 28 #define ETM_OPT_RETSTK 29 /* ETMv4 CONFIGR programming bits for the ETM OPTs */ #define ETM4_CFG_BIT_CYCACC 4 #define ETM4_CFG_BIT_CTXTID 6 +#define ETM4_CFG_BIT_VMID 7 #define ETM4_CFG_BIT_TS 11 #define ETM4_CFG_BIT_RETSTK 12 +#define ETM4_CFG_BIT_VMID_OPT 15 static inline int coresight_get_trace_id(int cpu) { -- cgit v1.2.3 From bb90d4bc7b6a536b2e4db45f4763e467c2008251 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Tue, 9 Feb 2021 22:22:14 -0800 Subject: mm/highmem: Lift memcpy_[to|from]_page to core Working through a conversion to a call kmap_local_page() instead of kmap() revealed many places where the pattern kmap/memcpy/kunmap occurred. Eric Biggers, Matthew Wilcox, Christoph Hellwig, Dan Williams, and Al Viro all suggested putting this code into helper functions. Al Viro further pointed out that these functions already existed in the iov_iter code.[1] Various locations for the lifted functions were considered. Headers like mm.h or string.h seem ok but don't really portray the functionality well. pagemap.h made some sense but is for page cache functionality.[2] Another alternative would be to create a new header for the promoted memcpy functions, but it masks the fact that these are designed to copy to/from pages using the kernel direct mappings and complicates matters with a new header. Placing these functions in 'highmem.h' is suboptimal especially with the changes being proposed in the functionality of kmap. From a caller perspective including/using 'highmem.h' implies that the functions defined in that header are only required when highmem is in use which is increasingly not the case with modern processors. However, highmem.h is where all the current functions like this reside (zero_user(), clear_highpage(), clear_user_highpage(), copy_user_highpage(), and copy_highpage()). So it makes the most sense even though it is distasteful for some.[3] Lift memcpy_to_page() and memcpy_from_page() to pagemap.h. [1] https://lore.kernel.org/lkml/20201013200149.GI3576660@ZenIV.linux.org.uk/ https://lore.kernel.org/lkml/20201013112544.GA5249@infradead.org/ [2] https://lore.kernel.org/lkml/20201208122316.GH7338@casper.infradead.org/ [3] https://lore.kernel.org/lkml/20201013200149.GI3576660@ZenIV.linux.org.uk/#t https://lore.kernel.org/lkml/20201208163814.GN1563847@iweiny-DESK2.sc.intel.com/ Cc: Boris Pismenny Cc: Or Gerlitz Cc: Dave Hansen Suggested-by: Matthew Wilcox Suggested-by: Christoph Hellwig Suggested-by: Dan Williams Suggested-by: Al Viro Suggested-by: Eric Biggers Reviewed-by: Chaitanya Kulkarni Reviewed-by: Christoph Hellwig Signed-off-by: Ira Weiny Signed-off-by: David Sterba --- include/linux/highmem.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index d2c70d3772a3..736b6a9f144d 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -276,4 +276,22 @@ static inline void copy_highpage(struct page *to, struct page *from) #endif +static inline void memcpy_from_page(char *to, struct page *page, + size_t offset, size_t len) +{ + char *from = kmap_atomic(page); + + memcpy(to, from + offset, len); + kunmap_atomic(from); +} + +static inline void memcpy_to_page(struct page *page, size_t offset, + const char *from, size_t len) +{ + char *to = kmap_atomic(page); + + memcpy(to + offset, from, len); + kunmap_atomic(to); +} + #endif /* _LINUX_HIGHMEM_H */ -- cgit v1.2.3 From 61b205f579911a11f0b576f73275eca2aed0d108 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Tue, 9 Feb 2021 22:22:15 -0800 Subject: mm/highmem: Convert memcpy_[to|from]_page() to kmap_local_page() kmap_local_page() is more efficient and is well suited for these calls. Convert the kmap() to kmap_local_page() Cc: Andrew Morton Cc: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Reviewed-by: Christoph Hellwig Signed-off-by: Ira Weiny Signed-off-by: David Sterba --- include/linux/highmem.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 736b6a9f144d..c17a175fe5fe 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -279,19 +279,19 @@ static inline void copy_highpage(struct page *to, struct page *from) static inline void memcpy_from_page(char *to, struct page *page, size_t offset, size_t len) { - char *from = kmap_atomic(page); + char *from = kmap_local_page(page); memcpy(to, from + offset, len); - kunmap_atomic(from); + kunmap_local(from); } static inline void memcpy_to_page(struct page *page, size_t offset, const char *from, size_t len) { - char *to = kmap_atomic(page); + char *to = kmap_local_page(page); memcpy(to + offset, from, len); - kunmap_atomic(to); + kunmap_local(to); } #endif /* _LINUX_HIGHMEM_H */ -- cgit v1.2.3 From 6a0996db6879cf09f989c5f44f9edd38240cb346 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Tue, 9 Feb 2021 22:22:16 -0800 Subject: mm/highmem: Introduce memcpy_page(), memmove_page(), and memset_page() 3 more common kmap patterns are kmap/memcpy/kunmap, kmap/memmove/kunmap. and kmap/memset/kunmap. Add helper functions for those patterns which use kmap_local_page(). Cc: Andrew Morton Cc: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Reviewed-by: Christoph Hellwig Signed-off-by: Ira Weiny Signed-off-by: David Sterba --- include/linux/highmem.h | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index c17a175fe5fe..0b5d89621cb9 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -276,6 +276,39 @@ static inline void copy_highpage(struct page *to, struct page *from) #endif +static inline void memcpy_page(struct page *dst_page, size_t dst_off, + struct page *src_page, size_t src_off, + size_t len) +{ + char *dst = kmap_local_page(dst_page); + char *src = kmap_local_page(src_page); + + memcpy(dst + dst_off, src + src_off, len); + kunmap_local(src); + kunmap_local(dst); +} + +static inline void memmove_page(struct page *dst_page, size_t dst_off, + struct page *src_page, size_t src_off, + size_t len) +{ + char *dst = kmap_local_page(dst_page); + char *src = kmap_local_page(src_page); + + memmove(dst + dst_off, src + src_off, len); + kunmap_local(src); + kunmap_local(dst); +} + +static inline void memset_page(struct page *page, size_t offset, int val, + size_t len) +{ + char *addr = kmap_local_page(page); + + memset(addr + offset, val, len); + kunmap_local(addr); +} + static inline void memcpy_from_page(char *to, struct page *page, size_t offset, size_t len) { -- cgit v1.2.3 From ca18f6ea012bf30236b76c3480ac2c97131b6f8f Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Wed, 10 Feb 2021 09:49:28 -0800 Subject: mm/highmem: Add VM_BUG_ON() to mem*_page() calls Add VM_BUG_ON bounds checks to ensure the newly lifted and created page memory operations do not result in corrupted data in neighbor pages.[1][2] [1] https://lore.kernel.org/lkml/20201210053502.GS1563847@iweiny-DESK2.sc.intel.com/ [2] https://lore.kernel.org/lkml/20210209110931.00f00e47d9a0529fcee2ff01@linux-foundation.org/ Suggested-by: Matthew Wilcox Suggested-by: Andrew Morton Reviewed-by: Christoph Hellwig Signed-off-by: Ira Weiny Signed-off-by: David Sterba --- include/linux/highmem.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 0b5d89621cb9..44170f312ae7 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -283,6 +283,7 @@ static inline void memcpy_page(struct page *dst_page, size_t dst_off, char *dst = kmap_local_page(dst_page); char *src = kmap_local_page(src_page); + VM_BUG_ON(dst_off + len > PAGE_SIZE || src_off + len > PAGE_SIZE); memcpy(dst + dst_off, src + src_off, len); kunmap_local(src); kunmap_local(dst); @@ -295,6 +296,7 @@ static inline void memmove_page(struct page *dst_page, size_t dst_off, char *dst = kmap_local_page(dst_page); char *src = kmap_local_page(src_page); + VM_BUG_ON(dst_off + len > PAGE_SIZE || src_off + len > PAGE_SIZE); memmove(dst + dst_off, src + src_off, len); kunmap_local(src); kunmap_local(dst); @@ -305,6 +307,7 @@ static inline void memset_page(struct page *page, size_t offset, int val, { char *addr = kmap_local_page(page); + VM_BUG_ON(offset + len > PAGE_SIZE); memset(addr + offset, val, len); kunmap_local(addr); } @@ -314,6 +317,7 @@ static inline void memcpy_from_page(char *to, struct page *page, { char *from = kmap_local_page(page); + VM_BUG_ON(offset + len > PAGE_SIZE); memcpy(to, from + offset, len); kunmap_local(from); } @@ -323,6 +327,7 @@ static inline void memcpy_to_page(struct page *page, size_t offset, { char *to = kmap_local_page(page); + VM_BUG_ON(offset + len > PAGE_SIZE); memcpy(to + offset, from, len); kunmap_local(to); } -- cgit v1.2.3 From f2ad937b62d984fd1ede3994798fe39f5fabc8d7 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Tue, 26 Jan 2021 12:45:38 +0000 Subject: clk: spear: Move prototype to accessible header MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixes the following W=1 kernel build warning(s): drivers/clk/spear/spear1310_clock.c:385:13: warning: no previous prototype for ‘spear1310_clk_init’ [-Wmissing-prototypes] drivers/clk/spear/spear1340_clock.c:442:13: warning: no previous prototype for ‘spear1340_clk_init’ [-Wmissing-prototypes] Cc: Viresh Kumar Cc: Shiraz Hashim Cc: Russell King Cc: Rajeev Kumar Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20210126124540.3320214-20-lee.jones@linaro.org Acked-by: Viresh Kumar Signed-off-by: Stephen Boyd --- include/linux/clk/spear.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) create mode 100644 include/linux/clk/spear.h (limited to 'include/linux') diff --git a/include/linux/clk/spear.h b/include/linux/clk/spear.h new file mode 100644 index 000000000000..a64d034ceddd --- /dev/null +++ b/include/linux/clk/spear.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2020 STMicroelectronics - All Rights Reserved + * + * Author: Lee Jones + */ + +#ifndef __LINUX_CLK_SPEAR_H +#define __LINUX_CLK_SPEAR_H + +#ifdef CONFIG_MACH_SPEAR1310 +void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base); +#else +static inline void spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base) {} +#endif + +#ifdef CONFIG_MACH_SPEAR1340 +void __init spear1340_clk_init(void __iomem *misc_base); +#else +static inline void spear1340_clk_init(void __iomem *misc_base) {} +#endif + +#endif -- cgit v1.2.3 From 4217a64e18a1647a0dbc68cb3169a5a06f054ec8 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Tue, 9 Feb 2021 17:38:52 +0100 Subject: net: phy: introduce phydev->port At the moment, PORT_MII is reported in the ethtool ops. This is odd because it is an interface between the MAC and the PHY and no external port. Some network card drivers will overwrite the port to twisted pair or fiber, though. Even worse, the MDI/MDIX setting is only used by ethtool if the port is twisted pair. Set the port to PORT_TP by default because most PHY drivers are copper ones. If there is fibre support and it is enabled, the PHY driver will set it to PORT_FIBRE. This will change reporting PORT_MII to either PORT_TP or PORT_FIBRE; except for the genphy fallback driver. Suggested-by: Andrew Lunn Signed-off-by: Michael Walle Reviewed-by: Florian Fainelli Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index bc323fbdd21e..c130788306c8 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -503,6 +503,7 @@ struct macsec_ops; * * @speed: Current link speed * @duplex: Current duplex + * @port: Current port * @pause: Current pause * @asym_pause: Current asymmetric pause * @supported: Combined MAC/PHY supported linkmodes @@ -581,6 +582,7 @@ struct phy_device { */ int speed; int duplex; + int port; int pause; int asym_pause; u8 master_slave_get; -- cgit v1.2.3 From dcf0cd1cc58b8e88793ad6531db9b3a47324ca09 Mon Sep 17 00:00:00 2001 From: George McCollister Date: Tue, 9 Feb 2021 19:02:11 -0600 Subject: net: hsr: add offloading support Add support for offloading of HSR/PRP (IEC 62439-3) tag insertion tag removal, duplicate generation and forwarding. For HSR, insertion involves the switch adding a 6 byte HSR header after the 14 byte Ethernet header. For PRP it adds a 6 byte trailer. Tag removal involves automatically stripping the HSR/PRP header/trailer in the switch. This is possible when the switch also performs auto deduplication using the HSR/PRP header/trailer (making it no longer required). Forwarding involves automatically forwarding between redundant ports in an HSR. This is crucial because delay is accumulated as a frame passes through each node in the ring. Duplication involves the switch automatically sending a single frame from the CPU port to both redundant ports. This is required because the inserted HSR/PRP header/trailer must contain the same sequence number on the frames sent out both redundant ports. Export is_hsr_master so DSA can tell them apart from other devices in dsa_slave_changeupper. Signed-off-by: George McCollister Reviewed-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/if_hsr.h | 27 +++++++++++++++++++++++++++ include/linux/netdev_features.h | 9 +++++++++ 2 files changed, 36 insertions(+) create mode 100644 include/linux/if_hsr.h (limited to 'include/linux') diff --git a/include/linux/if_hsr.h b/include/linux/if_hsr.h new file mode 100644 index 000000000000..38bbc537d4e4 --- /dev/null +++ b/include/linux/if_hsr.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_IF_HSR_H_ +#define _LINUX_IF_HSR_H_ + +/* used to differentiate various protocols */ +enum hsr_version { + HSR_V0 = 0, + HSR_V1, + PRP_V1, +}; + +#if IS_ENABLED(CONFIG_HSR) +extern bool is_hsr_master(struct net_device *dev); +extern int hsr_get_version(struct net_device *dev, enum hsr_version *ver); +#else +static inline bool is_hsr_master(struct net_device *dev) +{ + return false; +} +static inline int hsr_get_version(struct net_device *dev, + enum hsr_version *ver) +{ + return -EINVAL; +} +#endif /* CONFIG_HSR */ + +#endif /*_LINUX_IF_HSR_H_*/ diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index c06d6aaba9df..3de38d6a0aea 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -86,6 +86,11 @@ enum { NETIF_F_HW_MACSEC_BIT, /* Offload MACsec operations */ NETIF_F_GRO_UDP_FWD_BIT, /* Allow UDP GRO for forwarding */ + NETIF_F_HW_HSR_TAG_INS_BIT, /* Offload HSR tag insertion */ + NETIF_F_HW_HSR_TAG_RM_BIT, /* Offload HSR tag removal */ + NETIF_F_HW_HSR_FWD_BIT, /* Offload HSR forwarding */ + NETIF_F_HW_HSR_DUP_BIT, /* Offload HSR duplication */ + /* * Add your fresh new feature above and remember to update * netdev_features_strings[] in net/core/ethtool.c and maybe @@ -159,6 +164,10 @@ enum { #define NETIF_F_GSO_FRAGLIST __NETIF_F(GSO_FRAGLIST) #define NETIF_F_HW_MACSEC __NETIF_F(HW_MACSEC) #define NETIF_F_GRO_UDP_FWD __NETIF_F(GRO_UDP_FWD) +#define NETIF_F_HW_HSR_TAG_INS __NETIF_F(HW_HSR_TAG_INS) +#define NETIF_F_HW_HSR_TAG_RM __NETIF_F(HW_HSR_TAG_RM) +#define NETIF_F_HW_HSR_FWD __NETIF_F(HW_HSR_FWD) +#define NETIF_F_HW_HSR_DUP __NETIF_F(HW_HSR_DUP) /* Finds the next feature with the highest number of the range of start till 0. */ -- cgit v1.2.3 From efbbdaa22bb78761bff8dfdde027ad04bedd47ce Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 15 Oct 2020 23:55:07 +0900 Subject: tracing: Show real address for trace event arguments To help debugging kernel, show real address for trace event arguments in tracefs/trace{,pipe} instead of hashed pointer value. Since ftrace human-readable format uses vsprintf(), all %p are translated to hash values instead of pointer address. However, when debugging the kernel, raw address value gives a hint when comparing with the memory mapping in the kernel. (Those are sometimes used with crash log, which is not hashed too) So converting %p with %px when calling trace_seq_printf(). Moreover, this is not improving the security because the tracefs can be used only by root user and the raw address values are readable from tracefs/percpu/cpu*/trace_pipe_raw file. Link: https://lkml.kernel.org/r/160277370703.29307.5134475491761971203.stgit@devnote2 Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 5d1eeac4bfbe..7077fec653bb 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -55,6 +55,8 @@ struct trace_event; int trace_raw_output_prep(struct trace_iterator *iter, struct trace_event *event); +extern __printf(2, 3) +void trace_event_printf(struct trace_iterator *iter, const char *fmt, ...); /* * The trace entry - the most basic unit of tracing. This is what @@ -87,6 +89,8 @@ struct trace_iterator { unsigned long iter_flags; void *temp; /* temp holder */ unsigned int temp_size; + char *fmt; /* modified format holder */ + unsigned int fmt_size; /* trace_seq for __print_flags() and __print_symbolic() etc. */ struct trace_seq tmp_seq; -- cgit v1.2.3 From 4c236d5dc8b86222dc155cd68e7934624264150f Mon Sep 17 00:00:00 2001 From: Geetha sowjanya Date: Thu, 11 Feb 2021 21:28:27 +0530 Subject: octeontx2-pf: cn10k: Use LMTST lines for NPA/NIX operations This patch adds support to use new LMTST lines for NPA batch free and burst SQE flush. Adds new dev_hw_ops structure to hold platform specific functions and create new files cn10k.c and cn10k.h. Signed-off-by: Geetha sowjanya Signed-off-by: Sunil Goutham Signed-off-by: David S. Miller --- include/linux/soc/marvell/octeontx2/asm.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/marvell/octeontx2/asm.h b/include/linux/soc/marvell/octeontx2/asm.h index ae2279fe830a..28c04d918f0f 100644 --- a/include/linux/soc/marvell/octeontx2/asm.h +++ b/include/linux/soc/marvell/octeontx2/asm.h @@ -22,8 +22,16 @@ : [rs]"r" (ioaddr)); \ (result); \ }) +#define cn10k_lmt_flush(val, addr) \ +({ \ + __asm__ volatile(".cpu generic+lse\n" \ + "steor %x[rf],[%[rs]]" \ + : [rf]"+r"(val) \ + : [rs]"r"(addr)); \ +}) #else #define otx2_lmt_flush(ioaddr) ({ 0; }) +#define cn10k_lmt_flush(val, addr) ({ addr = val; }) #endif #endif /* __SOC_OTX2_ASM_H */ -- cgit v1.2.3 From c5dbb89fc2ac013afe67b9e4fcb3743c02b567cd Mon Sep 17 00:00:00 2001 From: Florent Revest Date: Wed, 10 Feb 2021 12:14:03 +0100 Subject: bpf: Expose bpf_get_socket_cookie to tracing programs This needs a new helper that: - can work in a sleepable context (using sock_gen_cookie) - takes a struct sock pointer and checks that it's not NULL Signed-off-by: Florent Revest Signed-off-by: Alexei Starovoitov Acked-by: KP Singh Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210210111406.785541-2-revest@chromium.org --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1c8ea682c007..cccaef1088ea 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1885,6 +1885,7 @@ extern const struct bpf_func_proto bpf_per_cpu_ptr_proto; extern const struct bpf_func_proto bpf_this_cpu_ptr_proto; extern const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto; extern const struct bpf_func_proto bpf_sock_from_file_proto; +extern const struct bpf_func_proto bpf_get_socket_ptr_cookie_proto; const struct bpf_func_proto *bpf_tracing_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); -- cgit v1.2.3 From 3b23a32a63219f51a5298bc55a65ecee866e79d0 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 11 Feb 2021 11:34:10 -0800 Subject: net: fix dev_ifsioc_locked() race condition dev_ifsioc_locked() is called with only RCU read lock, so when there is a parallel writer changing the mac address, it could get a partially updated mac address, as shown below: Thread 1 Thread 2 // eth_commit_mac_addr_change() memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN); // dev_ifsioc_locked() memcpy(ifr->ifr_hwaddr.sa_data, dev->dev_addr,...); Close this race condition by guarding them with a RW semaphore, like netdev_get_name(). We can not use seqlock here as it does not allow blocking. The writers already take RTNL anyway, so this does not affect the slow path. To avoid bothering existing dev_set_mac_address() callers in drivers, introduce a new wrapper just for user-facing callers on ioctl and rtnetlink paths. Note, bonding also changes slave mac addresses but that requires a separate patch due to the complexity of bonding code. Fixes: 3710becf8a58 ("net: RCU locking for simple ioctl()") Reported-by: "Gong, Sishuai" Cc: Eric Dumazet Cc: Jakub Kicinski Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a20310ff5083..bfadf3b82f9c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3902,6 +3902,9 @@ int dev_pre_changeaddr_notify(struct net_device *dev, const char *addr, struct netlink_ext_ack *extack); int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa, struct netlink_ext_ack *extack); +int dev_set_mac_address_user(struct net_device *dev, struct sockaddr *sa, + struct netlink_ext_ack *extack); +int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name); int dev_change_carrier(struct net_device *, bool new_carrier); int dev_get_phys_port_id(struct net_device *dev, struct netdev_phys_item_id *ppid); -- cgit v1.2.3 From c294554111a835598b557db789d9ad2379b512a2 Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Fri, 12 Feb 2021 10:00:23 +0200 Subject: regulator: bd718x7, bd71828, Fix dvs voltage levels The ROHM BD718x7 and BD71828 drivers support setting HW state specific voltages from device-tree. This is used also by various in-tree DTS files. These drivers do incorrectly try to compose bit-map using enum values. By a chance this works for first two valid levels having values 1 and 2 - but setting values for the rest of the levels do indicate capability of setting values for first levels as well. Luckily the regulators which support setting values for SUSPEND/LPSR do usually also support setting values for RUN and IDLE too - thus this has not been such a fatal issue. Fix this by defining the old enum values as bits and fixing the parsing code. This allows keeping existing IC specific drivers intact and only slightly changing the rohm-regulator.c Fixes: 21b72156ede8b ("regulator: bd718x7: Split driver to common and bd718x7 specific parts") Signed-off-by: Matti Vaittinen Acked-by: Lee Jones Link: https://lore.kernel.org/r/20210212080023.GA880728@localhost.localdomain Signed-off-by: Mark Brown --- include/linux/mfd/rohm-generic.h | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/rohm-generic.h b/include/linux/mfd/rohm-generic.h index 4283b5b33e04..2b85b9deb03a 100644 --- a/include/linux/mfd/rohm-generic.h +++ b/include/linux/mfd/rohm-generic.h @@ -20,14 +20,12 @@ struct rohm_regmap_dev { struct regmap *regmap; }; -enum { - ROHM_DVS_LEVEL_UNKNOWN, - ROHM_DVS_LEVEL_RUN, - ROHM_DVS_LEVEL_IDLE, - ROHM_DVS_LEVEL_SUSPEND, - ROHM_DVS_LEVEL_LPSR, - ROHM_DVS_LEVEL_MAX = ROHM_DVS_LEVEL_LPSR, -}; +#define ROHM_DVS_LEVEL_RUN BIT(0) +#define ROHM_DVS_LEVEL_IDLE BIT(1) +#define ROHM_DVS_LEVEL_SUSPEND BIT(2) +#define ROHM_DVS_LEVEL_LPSR BIT(3) +#define ROHM_DVS_LEVEL_VALID_AMOUNT 4 +#define ROHM_DVS_LEVEL_UNKNOWN 0 /** * struct rohm_dvs_config - dynamic voltage scaling register descriptions -- cgit v1.2.3 From 38f3885edbef8a77b25c4d13f3de06a7b93d02de Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 12 Feb 2021 16:11:17 +0200 Subject: ACPI: property: Remove dead code After the commit 3a7a2ab839ad couple of functions became a dead code. Moreover, for all these years nobody used them. Remove. Fixes: 3a7a2ab839ad ("ACPI / property: Extend fwnode_property_* to data-only subnodes") Signed-off-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 21 --------------------- 1 file changed, 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 053bf05fb1f7..a47eaf448131 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1114,14 +1114,9 @@ acpi_data_add_props(struct acpi_device_data *data, const guid_t *guid, int acpi_node_prop_get(const struct fwnode_handle *fwnode, const char *propname, void **valptr); -int acpi_dev_prop_read_single(struct acpi_device *adev, - const char *propname, enum dev_prop_type proptype, - void *val); int acpi_node_prop_read(const struct fwnode_handle *fwnode, const char *propname, enum dev_prop_type proptype, void *val, size_t nval); -int acpi_dev_prop_read(const struct acpi_device *adev, const char *propname, - enum dev_prop_type proptype, void *val, size_t nval); struct fwnode_handle *acpi_get_next_subnode(const struct fwnode_handle *fwnode, struct fwnode_handle *child); @@ -1223,14 +1218,6 @@ static inline int acpi_node_prop_get(const struct fwnode_handle *fwnode, return -ENXIO; } -static inline int acpi_dev_prop_read_single(const struct acpi_device *adev, - const char *propname, - enum dev_prop_type proptype, - void *val) -{ - return -ENXIO; -} - static inline int acpi_node_prop_read(const struct fwnode_handle *fwnode, const char *propname, enum dev_prop_type proptype, @@ -1239,14 +1226,6 @@ static inline int acpi_node_prop_read(const struct fwnode_handle *fwnode, return -ENXIO; } -static inline int acpi_dev_prop_read(const struct acpi_device *adev, - const char *propname, - enum dev_prop_type proptype, - void *val, size_t nval) -{ - return -ENXIO; -} - static inline struct fwnode_handle * acpi_get_next_subnode(const struct fwnode_handle *fwnode, struct fwnode_handle *child) -- cgit v1.2.3 From 325aa816143228a0b3472074ffb50d55ac3f04fe Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 12 Feb 2021 16:11:18 +0200 Subject: ACPI: property: Make acpi_node_prop_read() static There is no users outside of property.c. No need to export acpi_node_prop_read(), hence make it static. Fixes: 3708184afc77 ("device property: Move FW type specific functionality to FW specific files") Signed-off-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index a47eaf448131..dc6e1f39dc6f 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1114,9 +1114,6 @@ acpi_data_add_props(struct acpi_device_data *data, const guid_t *guid, int acpi_node_prop_get(const struct fwnode_handle *fwnode, const char *propname, void **valptr); -int acpi_node_prop_read(const struct fwnode_handle *fwnode, - const char *propname, enum dev_prop_type proptype, - void *val, size_t nval); struct fwnode_handle *acpi_get_next_subnode(const struct fwnode_handle *fwnode, struct fwnode_handle *child); @@ -1218,14 +1215,6 @@ static inline int acpi_node_prop_get(const struct fwnode_handle *fwnode, return -ENXIO; } -static inline int acpi_node_prop_read(const struct fwnode_handle *fwnode, - const char *propname, - enum dev_prop_type proptype, - void *val, size_t nval) -{ - return -ENXIO; -} - static inline struct fwnode_handle * acpi_get_next_subnode(const struct fwnode_handle *fwnode, struct fwnode_handle *child) -- cgit v1.2.3 From f9ab49184af093f0bf6c0e6583f5b25da2c09ff5 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Sat, 23 Jan 2021 21:10:27 +0100 Subject: blk-mq: Use llist_head for blk_cpu_done With llist_head it is possible to avoid the locking (the irq-off region) when items are added. This makes it possible to add items on a remote CPU without additional locking. llist_add() returns true if the list was previously empty. This can be used to invoke the SMP function call / raise sofirq only if the first item was added (otherwise it is already pending). This simplifies the code a little and reduces the IRQ-off regions. blk_mq_raise_softirq() needs a preempt-disable section to ensure the request is enqueued on the same CPU as the softirq is raised. Some callers (USB-storage) invoke this path in preemptible context. Reviewed-by: Christoph Hellwig Reviewed-by: Daniel Wagner Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f94ee3089e01..89a444c5a583 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -153,7 +153,7 @@ struct request { */ union { struct hlist_node hash; /* merge hash */ - struct list_head ipi_list; + struct llist_node ipi_list; }; /* -- cgit v1.2.3 From 731ecea3e5495aa6bd3cb8587f5267cf5e4220e2 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 18 Dec 2020 14:07:58 +0000 Subject: mm: Remove arch_remap() and mm-arch-hooks.h powerpc was the last provider of arch_remap() and the last user of mm-arch-hooks.h. Since commit 526a9c4a7234 ("powerpc/vdso: Provide vdso_remap()"), arch_remap() hence mm-arch-hooks.h are not used anymore. Remove them. Signed-off-by: Christophe Leroy Signed-off-by: Richard Weinberger --- include/linux/mm-arch-hooks.h | 22 ---------------------- 1 file changed, 22 deletions(-) delete mode 100644 include/linux/mm-arch-hooks.h (limited to 'include/linux') diff --git a/include/linux/mm-arch-hooks.h b/include/linux/mm-arch-hooks.h deleted file mode 100644 index 9c4bedc95504..000000000000 --- a/include/linux/mm-arch-hooks.h +++ /dev/null @@ -1,22 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Generic mm no-op hooks. - * - * Copyright (C) 2015, IBM Corporation - * Author: Laurent Dufour - */ -#ifndef _LINUX_MM_ARCH_HOOKS_H -#define _LINUX_MM_ARCH_HOOKS_H - -#include - -#ifndef arch_remap -static inline void arch_remap(struct mm_struct *mm, - unsigned long old_start, unsigned long old_end, - unsigned long new_start, unsigned long new_end) -{ -} -#define arch_remap arch_remap -#endif - -#endif /* _LINUX_MM_ARCH_HOOKS_H */ -- cgit v1.2.3 From 5f7d57280c1982d993d5f4ff0edac310f820f607 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Tue, 9 Feb 2021 14:38:29 +0100 Subject: bpf: Drop MTU check when doing TC-BPF redirect to ingress The use-case for dropping the MTU check when TC-BPF does redirect to ingress, is described by Eyal Birger in email[0]. The summary is the ability to increase packet size (e.g. with IPv6 headers for NAT64) and ingress redirect packet and let normal netstack fragment packet as needed. [0] https://lore.kernel.org/netdev/CAHsH6Gug-hsLGHQ6N0wtixdOa85LDZ3HNRHVd0opR=19Qo4W4Q@mail.gmail.com/ V15: - missing static for function declaration V9: - Make net_device "up" (IFF_UP) check explicit in skb_do_redirect V4: - Keep net_device "up" (IFF_UP) check. - Adjustment to handle bpf_redirect_peer() helper Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/161287790971.790810.11785274340154740591.stgit@firesoul --- include/linux/netdevice.h | 32 ++++++++++++++++++++++++++++++-- 1 file changed, 30 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ef517254367d..b9bcbfde7849 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3931,14 +3931,42 @@ int xdp_umem_query(struct net_device *dev, u16 queue_id); int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); int dev_forward_skb(struct net_device *dev, struct sk_buff *skb); +int dev_forward_skb_nomtu(struct net_device *dev, struct sk_buff *skb); bool is_skb_forwardable(const struct net_device *dev, const struct sk_buff *skb); +static __always_inline bool __is_skb_forwardable(const struct net_device *dev, + const struct sk_buff *skb, + const bool check_mtu) +{ + const u32 vlan_hdr_len = 4; /* VLAN_HLEN */ + unsigned int len; + + if (!(dev->flags & IFF_UP)) + return false; + + if (!check_mtu) + return true; + + len = dev->mtu + dev->hard_header_len + vlan_hdr_len; + if (skb->len <= len) + return true; + + /* if TSO is enabled, we don't care about the length as the packet + * could be forwarded without being segmented before + */ + if (skb_is_gso(skb)) + return true; + + return false; +} + static __always_inline int ____dev_forward_skb(struct net_device *dev, - struct sk_buff *skb) + struct sk_buff *skb, + const bool check_mtu) { if (skb_orphan_frags(skb, GFP_ATOMIC) || - unlikely(!is_skb_forwardable(dev, skb))) { + unlikely(!__is_skb_forwardable(dev, skb, check_mtu))) { atomic_long_inc(&dev->rx_dropped); kfree_skb(skb); return NET_RX_DROP; -- cgit v1.2.3 From 83c4a4eec06a8fc46fc68c437424f9c89e4d9c72 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Thu, 11 Feb 2021 17:27:44 -0600 Subject: of: Remove of_dev_{get,put}() of_dev_get() and of_dev_put are just wrappers for get_device()/put_device() on a platform_device. There's also already platform_device_{get,put}() wrappers for this purpose. Let's update the few users and remove of_dev_{get,put}(). Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Frank Rowand Cc: Patrice Chotard Cc: Felipe Balbi Cc: Julia Lawall Cc: Gilles Muller Cc: Nicolas Palix Cc: Michal Marek Cc: linuxppc-dev@lists.ozlabs.org Cc: netdev@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-usb@vger.kernel.org Cc: cocci@systeme.lip6.fr Signed-off-by: Rob Herring Reviewed-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20210211232745.1498137-2-robh@kernel.org --- include/linux/of_device.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_device.h b/include/linux/of_device.h index 937f32f6aecb..d7a407dfeecb 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -26,9 +26,6 @@ static inline int of_driver_match_device(struct device *dev, return of_match_device(drv->of_match_table, dev) != NULL; } -extern struct platform_device *of_dev_get(struct platform_device *dev); -extern void of_dev_put(struct platform_device *dev); - extern int of_device_add(struct platform_device *pdev); extern int of_device_register(struct platform_device *ofdev); extern void of_device_unregister(struct platform_device *ofdev); -- cgit v1.2.3 From cb8be8b4b27f6eea88268d6991175df1a27e557e Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Thu, 11 Feb 2021 17:27:45 -0600 Subject: driver core: platform: Drop of_device_node_put() wrapper of_device_node_put() is just a wrapper for of_node_put(). The platform driver core is already polluted with of_node pointers and the only 'get' already uses of_node_get() (though typically the get would happen in of_device_alloc()). Cc: "Rafael J. Wysocki" Cc: Frank Rowand Signed-off-by: Rob Herring Reviewed-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20210211232745.1498137-3-robh@kernel.org --- include/linux/of_device.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_device.h b/include/linux/of_device.h index d7a407dfeecb..1d7992a02e36 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -38,11 +38,6 @@ extern int of_device_request_module(struct device *dev); extern void of_device_uevent(struct device *dev, struct kobj_uevent_env *env); extern int of_device_uevent_modalias(struct device *dev, struct kobj_uevent_env *env); -static inline void of_device_node_put(struct device *dev) -{ - of_node_put(dev->of_node); -} - static inline struct device_node *of_cpu_device_node_get(int cpu) { struct device *cpu_dev; @@ -94,8 +89,6 @@ static inline int of_device_uevent_modalias(struct device *dev, return -ENODEV; } -static inline void of_device_node_put(struct device *dev) { } - static inline const struct of_device_id *of_match_device( const struct of_device_id *matches, const struct device *dev) { -- cgit v1.2.3 From e5069b9c23b3857db986c58801bebe450cff3392 Mon Sep 17 00:00:00 2001 From: Dmitrii Banshchikov Date: Sat, 13 Feb 2021 00:56:41 +0400 Subject: bpf: Support pointers in global func args Add an ability to pass a pointer to a type with known size in arguments of a global function. Such pointers may be used to overcome the limit on the maximum number of arguments, avoid expensive and tricky workarounds and to have multiple output arguments. A referenced type may contain pointers but indirect access through them isn't supported. The implementation consists of two parts. If a global function has an argument that is a pointer to a type with known size then: 1) In btf_check_func_arg_match(): check that the corresponding register points to NULL or to a valid memory region that is large enough to contain the expected argument's type. 2) In btf_prepare_func_args(): set the corresponding register type to PTR_TO_MEM_OR_NULL and its size to the size of the expected type. Only global functions are supported because allowance of pointers for static functions might break validation. Consider the following scenario. A static function has a pointer argument. A caller passes pointer to its stack memory. Because the callee can change referenced memory verifier cannot longer assume any particular slot type of the caller's stack memory hence the slot type is changed to SLOT_MISC. If there is an operation that relies on slot type other than SLOT_MISC then verifier won't be able to infer safety of the operation. When verifier sees a static function that has a pointer argument different from PTR_TO_CTX then it skips arguments check and continues with "inline" validation with more information available. The operation that relies on the particular slot type now succeeds. Because global functions were not allowed to have pointer arguments different from PTR_TO_CTX it's not possible to break existing and valid code. Signed-off-by: Dmitrii Banshchikov Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210212205642.620788-4-me@ubique.spb.ru --- include/linux/bpf_verifier.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 532c97836d0d..971b33aca13d 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -471,6 +471,8 @@ bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt); int check_ctx_reg(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno); +int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + u32 regno, u32 mem_size); /* this lives here instead of in bpf.h because it needs to dereference tgt_prog */ static inline u64 bpf_trampoline_compute_key(const struct bpf_prog *tgt_prog, -- cgit v1.2.3 From 6d4e9a8efe3d59f31367d79e970c2f328da139a4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 10 Feb 2021 10:56:39 +0100 Subject: driver core: lift dma_default_coherent into common code Lift the dma_default_coherent variable from the mips architecture code to the driver core. This allows an architecture to sdefault all device to be DMA coherent at run time, even if the kernel is build with support for DMA noncoherent device. By allowing device_initialize to set the ->dma_coherent field to this default the amount of arch hooks required for this behavior can be greatly reduced. Signed-off-by: Christoph Hellwig Acked-by: Greg Kroah-Hartman Signed-off-by: Thomas Bogendoerfer --- include/linux/dma-map-ops.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index 70fcd0f610ea..1e98b8c1e055 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -229,11 +229,10 @@ bool dma_free_from_pool(struct device *dev, void *start, size_t size); int dma_direct_set_offset(struct device *dev, phys_addr_t cpu_start, dma_addr_t dma_start, u64 size); -#ifdef CONFIG_ARCH_HAS_DMA_COHERENCE_H -#include -#elif defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ +#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) +extern bool dma_default_coherent; static inline bool dev_is_dma_coherent(struct device *dev) { return dev->dma_coherent; -- cgit v1.2.3 From 96c0a6a72d181a330db6dc9848ff2e6584b1aa5b Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Wed, 10 Feb 2021 21:51:02 +0100 Subject: s390,alpha: switch to 64-bit ino_t s390 and alpha are the only 64 bit architectures with a 32-bit ino_t. Since this is quite unusual this causes bugs from time to time. See e.g. commit ebce3eb2f7ef ("ceph: fix inode number handling on arches with 32-bit ino_t") for an example. This (obviously) also prevents s390 and alpha to use 64-bit ino_t for tmpfs. See commit b85a7a8bb573 ("tmpfs: disallow CONFIG_TMPFS_INODE64 on s390"). Therefore switch both s390 and alpha to 64-bit ino_t. This should only have an effect on the ustat system call. To prevent ABI breakage define struct ustat compatible to the old layout and change sys_ustat() accordingly. Acked-by: Linus Torvalds Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- include/linux/types.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/types.h b/include/linux/types.h index a147977602b5..ac825ad90e44 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -14,7 +14,7 @@ typedef u32 __kernel_dev_t; typedef __kernel_fd_set fd_set; typedef __kernel_dev_t dev_t; -typedef __kernel_ino_t ino_t; +typedef __kernel_ulong_t ino_t; typedef __kernel_mode_t mode_t; typedef unsigned short umode_t; typedef u32 nlink_t; @@ -189,7 +189,11 @@ struct hlist_node { struct ustat { __kernel_daddr_t f_tfree; - __kernel_ino_t f_tinode; +#ifdef CONFIG_ARCH_32BIT_USTAT_F_TINODE + unsigned int f_tinode; +#else + unsigned long f_tinode; +#endif char f_fname[6]; char f_fpack[6]; }; -- cgit v1.2.3 From fec6e49b63989657bc4076dad99fa51d5ece34da Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Sat, 13 Feb 2021 14:12:02 +0000 Subject: skbuff: remove __kfree_skb_flush() This function isn't much needed as NAPI skb queue gets bulk-freed anyway when there's no more room, and even may reduce the efficiency of bulk operations. It will be even less needed after reusing skb cache on allocation path, so remove it and this way lighten network softirqs a bit. Suggested-by: Eric Dumazet Signed-off-by: Alexander Lobakin Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0a4e91a2f873..0e0707296098 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2919,7 +2919,6 @@ static inline struct sk_buff *napi_alloc_skb(struct napi_struct *napi, } void napi_consume_skb(struct sk_buff *skb, int budget); -void __kfree_skb_flush(void); void __kfree_skb_defer(struct sk_buff *skb); /** -- cgit v1.2.3 From f450d539c05a14c103dd174718f81bb2fe65cb4b Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Sat, 13 Feb 2021 14:12:25 +0000 Subject: skbuff: introduce {,__}napi_build_skb() which reuses NAPI cache heads Instead of just bulk-flushing skbuff_heads queued up through napi_consume_skb() or __kfree_skb_defer(), try to reuse them on allocation path. If the cache is empty on allocation, bulk-allocate the first 16 elements, which is more efficient than per-skb allocation. If the cache is full on freeing, bulk-wipe the second half of the cache (32 elements). This also includes custom KASAN poisoning/unpoisoning to be double sure there are no use-after-free cases. To not change current behaviour, introduce a new function, napi_build_skb(), to optionally use a new approach later in drivers. Note on selected bulk size, 16: - this equals to XDP_BULK_QUEUE_SIZE, DEV_MAP_BULK_SIZE and especially VETH_XDP_BATCH, which is also used to bulk-allocate skbuff_heads and was tested on powerful setups; - this also showed the best performance in the actual test series (from the array of {8, 16, 32}). Suggested-by: Edward Cree # Divide on two halves Suggested-by: Eric Dumazet # KASAN poisoning Cc: Dmitry Vyukov # Help with KASAN Cc: Paolo Abeni # Reduced batch size Signed-off-by: Alexander Lobakin Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0e0707296098..906122eac82a 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1087,6 +1087,8 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size); struct sk_buff *build_skb_around(struct sk_buff *skb, void *data, unsigned int frag_size); +struct sk_buff *napi_build_skb(void *data, unsigned int frag_size); + /** * alloc_skb - allocate a network buffer * @size: size to allocate -- cgit v1.2.3 From 9243adfc311a20371c3f4d8eaf0af4b135e6fac3 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Sat, 13 Feb 2021 14:13:09 +0000 Subject: skbuff: queue NAPI_MERGED_FREE skbs into NAPI cache instead of freeing napi_frags_finish() and napi_skb_finish() can only be called inside NAPI Rx context, so we can feed NAPI cache with skbuff_heads that got NAPI_MERGED_FREE verdict instead of immediate freeing. Replace __kfree_skb() with __kfree_skb_defer() in napi_skb_finish() and move napi_skb_free_stolen_head() to skbuff.c, so it can drop skbs to NAPI cache. As many drivers call napi_alloc_skb()/napi_get_frags() on their receive path, this becomes especially useful. Signed-off-by: Alexander Lobakin Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 906122eac82a..6d0a33d1c0db 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2921,6 +2921,7 @@ static inline struct sk_buff *napi_alloc_skb(struct napi_struct *napi, } void napi_consume_skb(struct sk_buff *skb, int budget); +void napi_skb_free_stolen_head(struct sk_buff *skb); void __kfree_skb_defer(struct sk_buff *skb); /** -- cgit v1.2.3 From 258e0815e2b1706e87c0d874211097aa8a7aa52f Mon Sep 17 00:00:00 2001 From: Dennis Zhou Date: Sun, 14 Feb 2021 17:16:33 +0000 Subject: percpu: fix clang modpost section mismatch pcpu_build_alloc_info() is an __init function that makes a call to cpumask_clear_cpu(). With CONFIG_GCOV_PROFILE_ALL enabled, the inline heuristics are modified and such cpumask_clear_cpu() which is marked inline doesn't get inlined. Because it works on mask in __initdata, modpost throws a section mismatch error. Arnd sent a patch with the flatten attribute as an alternative [2]. I've added it to compiler_attributes.h. modpost complaint: WARNING: modpost: vmlinux.o(.text+0x735425): Section mismatch in reference from the function cpumask_clear_cpu() to the variable .init.data:pcpu_build_alloc_info.mask The function cpumask_clear_cpu() references the variable __initdata pcpu_build_alloc_info.mask. This is often because cpumask_clear_cpu lacks a __initdata annotation or the annotation of pcpu_build_alloc_info.mask is wrong. clang output: mm/percpu.c:2724:5: remark: cpumask_clear_cpu not inlined into pcpu_build_alloc_info because too costly to inline (cost=725, threshold=325) [-Rpass-missed=inline] [1] https://lore.kernel.org/linux-mm/202012220454.9F6Bkz9q-lkp@intel.com/ [2] https://lore.kernel.org/lkml/CAK8P3a2ZWfNeXKSm8K_SUhhwkor17jFo3xApLXjzfPqX0eUDUA@mail.gmail.com/ Reported-by: kernel test robot Cc: Arnd Bergmann Cc: Nick Desaulniers Signed-off-by: Dennis Zhou --- include/linux/compiler_attributes.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index ea5e04e75845..c043b8d2b17b 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -210,6 +210,12 @@ # define fallthrough do {} while (0) /* fallthrough */ #endif +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#Common-Function-Attributes + * clang: https://clang.llvm.org/docs/AttributeReference.html#flatten + */ +# define __flatten __attribute__((flatten)) + /* * Note the missing underscores. * -- cgit v1.2.3 From 0b9266d295cee170509539635b8d572abe5267af Mon Sep 17 00:00:00 2001 From: Daniel Palmer Date: Thu, 11 Feb 2021 14:22:02 +0900 Subject: clk: fixed: add devm helper for clk_hw_register_fixed_factor() Add a devm helper for clk_hw_register_fixed_factor() so that drivers that internally register fixed factor clocks for things like dividers don't need to manually unregister them on remove or if probe fails. Signed-off-by: Daniel Palmer Link: https://lore.kernel.org/r/20210211052206.2955988-4-daniel@0x0f.com Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index e4316890661a..58f6fe866ae9 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -941,7 +941,9 @@ struct clk_hw *clk_hw_register_fixed_factor(struct device *dev, const char *name, const char *parent_name, unsigned long flags, unsigned int mult, unsigned int div); void clk_hw_unregister_fixed_factor(struct clk_hw *hw); - +struct clk_hw *devm_clk_hw_register_fixed_factor(struct device *dev, + const char *name, const char *parent_name, unsigned long flags, + unsigned int mult, unsigned int div); /** * struct clk_fractional_divider - adjustable fractional divider clock * -- cgit v1.2.3 From 40d3f295b5feda409784e569550057b5fbc2a295 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 14 Feb 2021 00:37:56 +0200 Subject: net: mscc: ocelot: use common tag parsing code with DSA The Injection Frame Header and Extraction Frame Header that the switch prepends to frames over the NPI port is also prepended to frames delivered over the CPU port module's queues. Let's unify the handling of the frame headers by making the ocelot driver call some helpers exported by the DSA tagger. Among other things, this allows us to get rid of the strange cpu_to_be32 when transmitting the Injection Frame Header on ocelot, since the packing API uses network byte order natively (when "quirks" is 0). The comments above ocelot_gen_ifh talk about setting pop_cnt to 3, and the cpu extraction queue mask to something, but the code doesn't do it, so we don't do it either. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/dsa/ocelot.h | 208 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 208 insertions(+) create mode 100644 include/linux/dsa/ocelot.h (limited to 'include/linux') diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h new file mode 100644 index 000000000000..763dbbfaff7a --- /dev/null +++ b/include/linux/dsa/ocelot.h @@ -0,0 +1,208 @@ +/* SPDX-License-Identifier: GPL-2.0 + * Copyright 2019-2021 NXP Semiconductors + */ + +#ifndef _NET_DSA_TAG_OCELOT_H +#define _NET_DSA_TAG_OCELOT_H + +#include + +#define OCELOT_TAG_LEN 16 +#define OCELOT_SHORT_PREFIX_LEN 4 +#define OCELOT_LONG_PREFIX_LEN 16 +#define OCELOT_TOTAL_TAG_LEN (OCELOT_SHORT_PREFIX_LEN + OCELOT_TAG_LEN) + +/* The CPU injection header and the CPU extraction header can have 3 types of + * prefixes: long, short and no prefix. The format of the header itself is the + * same in all 3 cases. + * + * Extraction with long prefix: + * + * +-------------------+-------------------+------+------+------------+-------+ + * | ff:ff:ff:ff:ff:ff | fe:ff:ff:ff:ff:ff | 8880 | 000a | extraction | frame | + * | | | | | header | | + * +-------------------+-------------------+------+------+------------+-------+ + * 48 bits 48 bits 16 bits 16 bits 128 bits + * + * Extraction with short prefix: + * + * +------+------+------------+-------+ + * | 8880 | 000a | extraction | frame | + * | | | header | | + * +------+------+------------+-------+ + * 16 bits 16 bits 128 bits + * + * Extraction with no prefix: + * + * +------------+-------+ + * | extraction | frame | + * | header | | + * +------------+-------+ + * 128 bits + * + * + * Injection with long prefix: + * + * +-------------------+-------------------+------+------+------------+-------+ + * | any dmac | any smac | 8880 | 000a | injection | frame | + * | | | | | header | | + * +-------------------+-------------------+------+------+------------+-------+ + * 48 bits 48 bits 16 bits 16 bits 128 bits + * + * Injection with short prefix: + * + * +------+------+------------+-------+ + * | 8880 | 000a | injection | frame | + * | | | header | | + * +------+------+------------+-------+ + * 16 bits 16 bits 128 bits + * + * Injection with no prefix: + * + * +------------+-------+ + * | injection | frame | + * | header | | + * +------------+-------+ + * 128 bits + * + * The injection header looks like this (network byte order, bit 127 + * is part of lowest address byte in memory, bit 0 is part of highest + * address byte): + * + * +------+------+------+------+------+------+------+------+ + * 127:120 |BYPASS| MASQ | MASQ_PORT |REW_OP|REW_OP| + * +------+------+------+------+------+------+------+------+ + * 119:112 | REW_OP | + * +------+------+------+------+------+------+------+------+ + * 111:104 | REW_VAL | + * +------+------+------+------+------+------+------+------+ + * 103: 96 | REW_VAL | + * +------+------+------+------+------+------+------+------+ + * 95: 88 | REW_VAL | + * +------+------+------+------+------+------+------+------+ + * 87: 80 | REW_VAL | + * +------+------+------+------+------+------+------+------+ + * 79: 72 | RSV | + * +------+------+------+------+------+------+------+------+ + * 71: 64 | RSV | DEST | + * +------+------+------+------+------+------+------+------+ + * 63: 56 | DEST | + * +------+------+------+------+------+------+------+------+ + * 55: 48 | RSV | + * +------+------+------+------+------+------+------+------+ + * 47: 40 | RSV | SRC_PORT | RSV |TFRM_TIMER| + * +------+------+------+------+------+------+------+------+ + * 39: 32 | TFRM_TIMER | RSV | + * +------+------+------+------+------+------+------+------+ + * 31: 24 | RSV | DP | POP_CNT | CPUQ | + * +------+------+------+------+------+------+------+------+ + * 23: 16 | CPUQ | QOS_CLASS |TAG_TYPE| + * +------+------+------+------+------+------+------+------+ + * 15: 8 | PCP | DEI | VID | + * +------+------+------+------+------+------+------+------+ + * 7: 0 | VID | + * +------+------+------+------+------+------+------+------+ + * + * And the extraction header looks like this: + * + * +------+------+------+------+------+------+------+------+ + * 127:120 | RSV | REW_OP | + * +------+------+------+------+------+------+------+------+ + * 119:112 | REW_OP | REW_VAL | + * +------+------+------+------+------+------+------+------+ + * 111:104 | REW_VAL | + * +------+------+------+------+------+------+------+------+ + * 103: 96 | REW_VAL | + * +------+------+------+------+------+------+------+------+ + * 95: 88 | REW_VAL | + * +------+------+------+------+------+------+------+------+ + * 87: 80 | REW_VAL | LLEN | + * +------+------+------+------+------+------+------+------+ + * 79: 72 | LLEN | WLEN | + * +------+------+------+------+------+------+------+------+ + * 71: 64 | WLEN | RSV | + * +------+------+------+------+------+------+------+------+ + * 63: 56 | RSV | + * +------+------+------+------+------+------+------+------+ + * 55: 48 | RSV | + * +------+------+------+------+------+------+------+------+ + * 47: 40 | RSV | SRC_PORT | ACL_ID | + * +------+------+------+------+------+------+------+------+ + * 39: 32 | ACL_ID | RSV | SFLOW_ID | + * +------+------+------+------+------+------+------+------+ + * 31: 24 |ACL_HIT| DP | LRN_FLAGS | CPUQ | + * +------+------+------+------+------+------+------+------+ + * 23: 16 | CPUQ | QOS_CLASS |TAG_TYPE| + * +------+------+------+------+------+------+------+------+ + * 15: 8 | PCP | DEI | VID | + * +------+------+------+------+------+------+------+------+ + * 7: 0 | VID | + * +------+------+------+------+------+------+------+------+ + */ + +static inline void ocelot_xfh_get_rew_val(void *extraction, u64 *rew_val) +{ + packing(extraction, rew_val, 116, 85, OCELOT_TAG_LEN, UNPACK, 0); +} + +static inline void ocelot_xfh_get_len(void *extraction, u64 *len) +{ + u64 llen, wlen; + + packing(extraction, &llen, 84, 79, OCELOT_TAG_LEN, UNPACK, 0); + packing(extraction, &wlen, 78, 71, OCELOT_TAG_LEN, UNPACK, 0); + + *len = 60 * wlen + llen - 80; +} + +static inline void ocelot_xfh_get_src_port(void *extraction, u64 *src_port) +{ + packing(extraction, src_port, 46, 43, OCELOT_TAG_LEN, UNPACK, 0); +} + +static inline void ocelot_xfh_get_qos_class(void *extraction, u64 *qos_class) +{ + packing(extraction, qos_class, 19, 17, OCELOT_TAG_LEN, UNPACK, 0); +} + +static inline void ocelot_xfh_get_tag_type(void *extraction, u64 *tag_type) +{ + packing(extraction, tag_type, 16, 16, OCELOT_TAG_LEN, UNPACK, 0); +} + +static inline void ocelot_xfh_get_vlan_tci(void *extraction, u64 *vlan_tci) +{ + packing(extraction, vlan_tci, 15, 0, OCELOT_TAG_LEN, UNPACK, 0); +} + +static inline void ocelot_ifh_set_bypass(void *injection, u64 bypass) +{ + packing(injection, &bypass, 127, 127, OCELOT_TAG_LEN, PACK, 0); +} + +static inline void ocelot_ifh_set_rew_op(void *injection, u64 rew_op) +{ + packing(injection, &rew_op, 125, 117, OCELOT_TAG_LEN, PACK, 0); +} + +static inline void ocelot_ifh_set_dest(void *injection, u64 dest) +{ + packing(injection, &dest, 67, 56, OCELOT_TAG_LEN, PACK, 0); +} + +static inline void ocelot_ifh_set_qos_class(void *injection, u64 qos_class) +{ + packing(injection, &qos_class, 19, 17, OCELOT_TAG_LEN, PACK, 0); +} + +static inline void ocelot_ifh_set_tag_type(void *injection, u64 tag_type) +{ + packing(injection, &tag_type, 16, 16, OCELOT_TAG_LEN, PACK, 0); +} + +static inline void ocelot_ifh_set_vid(void *injection, u64 vid) +{ + packing(injection, &vid, 11, 0, OCELOT_TAG_LEN, PACK, 0); +} + +#endif -- cgit v1.2.3 From 7c4bb540e9173c914c2091fdd9b6aee3c2a3e1e5 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 14 Feb 2021 00:37:58 +0200 Subject: net: dsa: tag_ocelot: create separate tagger for Seville The ocelot tagger is a hot mess currently, it relies on memory initialized by the attached driver for basic frame transmission. This is against all that DSA tagging protocols stand for, which is that the transmission and reception of a DSA-tagged frame, the data path, should be independent from the switch control path, because the tag protocol is in principle hot-pluggable and reusable across switches (even if in practice it wasn't until very recently). But if another driver like dsa_loop wants to make use of tag_ocelot, it couldn't. This was done to have common code between Felix and Ocelot, which have one bit difference in the frame header format. Quoting from commit 67c2404922c2 ("net: dsa: felix: create a template for the DSA tags on xmit"): Other alternatives have been analyzed, such as: - Create a separate tag_seville.c: too much code duplication for just 1 bit field difference. - Create a separate DSA_TAG_PROTO_SEVILLE under tag_ocelot.c, just like tag_brcm.c, which would have a separate .xmit function. Again, too much code duplication for just 1 bit field difference. - Allocate the template from the init function of the tag_ocelot.c module, instead of from the driver: couldn't figure out a method of accessing the correct port template corresponding to the correct tagger in the .xmit function. The really interesting part is that Seville should have had its own tagging protocol defined - it is not compatible on the wire with Ocelot, even for that single bit. In principle, a packet generated by DSA_TAG_PROTO_OCELOT when booted on NXP LS1028A would look in a certain way, but when booted on NXP T1040 it would look differently. The reverse is also true: a packet generated by a Seville switch would be interpreted incorrectly by Wireshark if it was told it was generated by an Ocelot switch. Actually things are a bit more nuanced. If we concentrate only on the DSA tag, what I said above is true, but Ocelot/Seville also support an optional DSA tag prefix, which can be short or long, and it is possible to distinguish the two taggers based on an integer constant put in that prefix. Nonetheless, creating a separate tagger is still justified, since the tag prefix is optional, and without it, there is again no way to distinguish. Claiming backwards binary compatibility is a bit more tough, since I've already changed the format of tag_ocelot once, in commit 5124197ce58b ("net: dsa: tag_ocelot: use a short prefix on both ingress and egress"). Therefore I am not very concerned with treating this as a bugfix and backporting it to stable kernels (which would be another mess due to the fact that there would be lots of conflicts with the other DSA_TAG_PROTO* definitions). It's just simpler to say that the string values of the taggers have ABI value starting with kernel 5.12, which will be when the changing of tag protocol via /sys/class/net//dsa/tagging goes live. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/dsa/ocelot.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h index 763dbbfaff7a..c6bc45ae5e03 100644 --- a/include/linux/dsa/ocelot.h +++ b/include/linux/dsa/ocelot.h @@ -195,6 +195,16 @@ static inline void ocelot_ifh_set_qos_class(void *injection, u64 qos_class) packing(injection, &qos_class, 19, 17, OCELOT_TAG_LEN, PACK, 0); } +static inline void seville_ifh_set_dest(void *injection, u64 dest) +{ + packing(injection, &dest, 67, 57, OCELOT_TAG_LEN, PACK, 0); +} + +static inline void ocelot_ifh_set_src(void *injection, u64 src) +{ + packing(injection, &src, 46, 43, OCELOT_TAG_LEN, PACK, 0); +} + static inline void ocelot_ifh_set_tag_type(void *injection, u64 tag_type) { packing(injection, &tag_type, 16, 16, OCELOT_TAG_LEN, PACK, 0); -- cgit v1.2.3 From b2498cb87c4ba87580e5975e049d589b6786ff75 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 22 Jan 2021 14:38:52 +0200 Subject: gpio: aggregator: Use compound literal from the header Instead of doing it in place, convert GPIO_LOOKUP_IDX() and GPIO_HOG() to be compund literals that's allow to use them as rvalue in assignments. Due to above conversion, use compound literal from the header in the gpio-aggregator.c. Signed-off-by: Andy Shevchenko Reviewed-by: Geert Uytterhoeven --- include/linux/gpio/machine.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/machine.h b/include/linux/gpio/machine.h index 781a053abbb9..d755e529c1e3 100644 --- a/include/linux/gpio/machine.h +++ b/include/linux/gpio/machine.h @@ -75,7 +75,7 @@ struct gpiod_hog { * gpiod_get_index() */ #define GPIO_LOOKUP_IDX(_key, _chip_hwnum, _con_id, _idx, _flags) \ -{ \ +(struct gpiod_lookup) { \ .key = _key, \ .chip_hwnum = _chip_hwnum, \ .con_id = _con_id, \ @@ -87,7 +87,7 @@ struct gpiod_hog { * Simple definition of a single GPIO hog in an array. */ #define GPIO_HOG(_chip_label, _chip_hwnum, _line_name, _lflags, _dflags) \ -{ \ +(struct gpiod_hog) { \ .chip_label = _chip_label, \ .chip_hwnum = _chip_hwnum, \ .line_name = _line_name, \ -- cgit v1.2.3 From 3019270282a175defc02c8331786c73e082cd2a8 Mon Sep 17 00:00:00 2001 From: Wei Liu Date: Mon, 15 Feb 2021 10:44:58 +0000 Subject: Revert "Drivers: hv: vmbus: Copy packets sent by Hyper-V out of the ring buffer" This reverts commit a8c3209998afb5c4941b49e35b513cea9050cb4a. It is reported that the said commit caused regression in netvsc. Reported-by: Andrea Parri (Microsoft) Signed-off-by: Wei Liu --- include/linux/hyperv.h | 48 ++++++++---------------------------------------- 1 file changed, 8 insertions(+), 40 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 9dd22af1b7f6..f1d74dcf0353 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -181,10 +181,6 @@ struct hv_ring_buffer_info { * being freed while the ring buffer is being accessed. */ struct mutex ring_buffer_mutex; - - /* Buffer that holds a copy of an incoming host packet */ - void *pkt_buffer; - u32 pkt_buffer_size; }; @@ -792,8 +788,6 @@ struct vmbus_device { bool allowed_in_isolated; }; -#define VMBUS_DEFAULT_MAX_PKT_SIZE 4096 - struct vmbus_channel { struct list_head listentry; @@ -1016,9 +1010,6 @@ struct vmbus_channel { /* request/transaction ids for VMBus */ struct vmbus_requestor requestor; u32 rqstor_size; - - /* The max size of a packet on this channel */ - u32 max_pkt_size; }; u64 vmbus_next_request_id(struct vmbus_requestor *rqstor, u64 rqst_addr); @@ -1660,44 +1651,15 @@ static inline u32 hv_pkt_datalen(const struct vmpacket_descriptor *desc) } -struct vmpacket_descriptor * -hv_pkt_iter_first_raw(struct vmbus_channel *channel); - struct vmpacket_descriptor * hv_pkt_iter_first(struct vmbus_channel *channel); struct vmpacket_descriptor * __hv_pkt_iter_next(struct vmbus_channel *channel, - const struct vmpacket_descriptor *pkt, - bool copy); + const struct vmpacket_descriptor *pkt); void hv_pkt_iter_close(struct vmbus_channel *channel); -static inline struct vmpacket_descriptor * -hv_pkt_iter_next_pkt(struct vmbus_channel *channel, - const struct vmpacket_descriptor *pkt, - bool copy) -{ - struct vmpacket_descriptor *nxt; - - nxt = __hv_pkt_iter_next(channel, pkt, copy); - if (!nxt) - hv_pkt_iter_close(channel); - - return nxt; -} - -/* - * Get next packet descriptor without copying it out of the ring buffer - * If at end of list, return NULL and update host. - */ -static inline struct vmpacket_descriptor * -hv_pkt_iter_next_raw(struct vmbus_channel *channel, - const struct vmpacket_descriptor *pkt) -{ - return hv_pkt_iter_next_pkt(channel, pkt, false); -} - /* * Get next packet descriptor from iterator * If at end of list, return NULL and update host. @@ -1706,7 +1668,13 @@ static inline struct vmpacket_descriptor * hv_pkt_iter_next(struct vmbus_channel *channel, const struct vmpacket_descriptor *pkt) { - return hv_pkt_iter_next_pkt(channel, pkt, true); + struct vmpacket_descriptor *nxt; + + nxt = __hv_pkt_iter_next(channel, pkt); + if (!nxt) + hv_pkt_iter_close(channel); + + return nxt; } #define foreach_vmbus_pkt(pkt, channel) \ -- cgit v1.2.3 From 2347961b11d4079deace3c81dceed460c08a8fc1 Mon Sep 17 00:00:00 2001 From: Laurent Vivier Date: Tue, 28 Jan 2020 14:25:39 +0100 Subject: binfmt_misc: pass binfmt_misc flags to the interpreter It can be useful to the interpreter to know which flags are in use. For instance, knowing if the preserve-argv[0] is in use would allow to skip the pathname argument. This patch uses an unused auxiliary vector, AT_FLAGS, to add a flag to inform interpreter if the preserve-argv[0] is enabled. Note by Helge Deller: The real-world user of this patch is qemu-user, which needs to know if it has to preserve the argv[0]. See Debian bug #970460. Signed-off-by: Laurent Vivier Reviewed-by: YunQiang Su URL: http://bugs.debian.org/970460 Signed-off-by: Helge Deller --- include/linux/binfmts.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 0571701ab1c5..0abd93efc181 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -73,6 +73,10 @@ struct linux_binprm { #define BINPRM_FLAGS_PATH_INACCESSIBLE_BIT 2 #define BINPRM_FLAGS_PATH_INACCESSIBLE (1 << BINPRM_FLAGS_PATH_INACCESSIBLE_BIT) +/* preserve argv0 for the interpreter */ +#define BINPRM_FLAGS_PRESERVE_ARGV0_BIT 3 +#define BINPRM_FLAGS_PRESERVE_ARGV0 (1 << BINPRM_FLAGS_PRESERVE_ARGV0_BIT) + /* Function parameter for binfmt->coredump */ struct coredump_params { const kernel_siginfo_t *siginfo; -- cgit v1.2.3 From 4590d98f5a4f466d17e5c81d7c9fc796da9a8cee Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 11 Feb 2021 15:40:02 +0200 Subject: sfi: Remove framework for deprecated firmware SFI-based platforms are gone. So does this framework. This removes mention of SFI through the drivers and other code as well. Signed-off-by: Andy Shevchenko Reviewed-by: Hans de Goede Acked-by: Linus Walleij Signed-off-by: Rafael J. Wysocki --- include/linux/sfi.h | 210 ----------------------------------------------- include/linux/sfi_acpi.h | 93 --------------------- 2 files changed, 303 deletions(-) delete mode 100644 include/linux/sfi.h delete mode 100644 include/linux/sfi_acpi.h (limited to 'include/linux') diff --git a/include/linux/sfi.h b/include/linux/sfi.h deleted file mode 100644 index e0e1597ef9e6..000000000000 --- a/include/linux/sfi.h +++ /dev/null @@ -1,210 +0,0 @@ -/* sfi.h Simple Firmware Interface */ - -/* - - This file is provided under a dual BSD/GPLv2 license. When using or - redistributing this file, you may do so under either license. - - GPL LICENSE SUMMARY - - Copyright(c) 2009 Intel Corporation. All rights reserved. - - This program is free software; you can redistribute it and/or modify - it under the terms of version 2 of the GNU General Public License as - published by the Free Software Foundation. - - This program is distributed in the hope that it will be useful, but - WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - General Public License for more details. - - You should have received a copy of the GNU General Public License - along with this program; if not, write to the Free Software - Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - The full GNU General Public License is included in this distribution - in the file called LICENSE.GPL. - - BSD LICENSE - - Copyright(c) 2009 Intel Corporation. All rights reserved. - - Redistribution and use in source and binary forms, with or without - modification, are permitted provided that the following conditions - are met: - - * Redistributions of source code must retain the above copyright - notice, this list of conditions and the following disclaimer. - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in - the documentation and/or other materials provided with the - distribution. - * Neither the name of Intel Corporation nor the names of its - contributors may be used to endorse or promote products derived - from this software without specific prior written permission. - - THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - -*/ - -#ifndef _LINUX_SFI_H -#define _LINUX_SFI_H - -#include -#include - -/* Table signatures reserved by the SFI specification */ -#define SFI_SIG_SYST "SYST" -#define SFI_SIG_FREQ "FREQ" -#define SFI_SIG_IDLE "IDLE" -#define SFI_SIG_CPUS "CPUS" -#define SFI_SIG_MTMR "MTMR" -#define SFI_SIG_MRTC "MRTC" -#define SFI_SIG_MMAP "MMAP" -#define SFI_SIG_APIC "APIC" -#define SFI_SIG_XSDT "XSDT" -#define SFI_SIG_WAKE "WAKE" -#define SFI_SIG_DEVS "DEVS" -#define SFI_SIG_GPIO "GPIO" - -#define SFI_SIGNATURE_SIZE 4 -#define SFI_OEM_ID_SIZE 6 -#define SFI_OEM_TABLE_ID_SIZE 8 - -#define SFI_NAME_LEN 16 - -#define SFI_SYST_SEARCH_BEGIN 0x000E0000 -#define SFI_SYST_SEARCH_END 0x000FFFFF - -#define SFI_GET_NUM_ENTRIES(ptable, entry_type) \ - ((ptable->header.len - sizeof(struct sfi_table_header)) / \ - (sizeof(entry_type))) -/* - * Table structures must be byte-packed to match the SFI specification, - * as they are provided by the BIOS. - */ -struct sfi_table_header { - char sig[SFI_SIGNATURE_SIZE]; - u32 len; - u8 rev; - u8 csum; - char oem_id[SFI_OEM_ID_SIZE]; - char oem_table_id[SFI_OEM_TABLE_ID_SIZE]; -} __packed; - -struct sfi_table_simple { - struct sfi_table_header header; - u64 pentry[1]; -} __packed; - -/* Comply with UEFI spec 2.1 */ -struct sfi_mem_entry { - u32 type; - u64 phys_start; - u64 virt_start; - u64 pages; - u64 attrib; -} __packed; - -struct sfi_cpu_table_entry { - u32 apic_id; -} __packed; - -struct sfi_cstate_table_entry { - u32 hint; /* MWAIT hint */ - u32 latency; /* latency in ms */ -} __packed; - -struct sfi_apic_table_entry { - u64 phys_addr; /* phy base addr for APIC reg */ -} __packed; - -struct sfi_freq_table_entry { - u32 freq_mhz; /* in MHZ */ - u32 latency; /* transition latency in ms */ - u32 ctrl_val; /* value to write to PERF_CTL */ -} __packed; - -struct sfi_wake_table_entry { - u64 phys_addr; /* pointer to where the wake vector locates */ -} __packed; - -struct sfi_timer_table_entry { - u64 phys_addr; /* phy base addr for the timer */ - u32 freq_hz; /* in HZ */ - u32 irq; -} __packed; - -struct sfi_rtc_table_entry { - u64 phys_addr; /* phy base addr for the RTC */ - u32 irq; -} __packed; - -struct sfi_device_table_entry { - u8 type; /* bus type, I2C, SPI or ...*/ -#define SFI_DEV_TYPE_SPI 0 -#define SFI_DEV_TYPE_I2C 1 -#define SFI_DEV_TYPE_UART 2 -#define SFI_DEV_TYPE_HSI 3 -#define SFI_DEV_TYPE_IPC 4 -#define SFI_DEV_TYPE_SD 5 - - u8 host_num; /* attached to host 0, 1...*/ - u16 addr; - u8 irq; - u32 max_freq; - char name[SFI_NAME_LEN]; -} __packed; - -struct sfi_gpio_table_entry { - char controller_name[SFI_NAME_LEN]; - u16 pin_no; - char pin_name[SFI_NAME_LEN]; -} __packed; - -typedef int (*sfi_table_handler) (struct sfi_table_header *table); - -#ifdef CONFIG_SFI -extern void __init sfi_init(void); -extern int __init sfi_platform_init(void); -extern void __init sfi_init_late(void); -extern int sfi_table_parse(char *signature, char *oem_id, char *oem_table_id, - sfi_table_handler handler); - -extern int sfi_disabled; -static inline void disable_sfi(void) -{ - sfi_disabled = 1; -} - -#else /* !CONFIG_SFI */ - -static inline void sfi_init(void) -{ -} - -static inline void sfi_init_late(void) -{ -} - -#define sfi_disabled 0 - -static inline int sfi_table_parse(char *signature, char *oem_id, - char *oem_table_id, - sfi_table_handler handler) -{ - return -1; -} - -#endif /* !CONFIG_SFI */ - -#endif /*_LINUX_SFI_H*/ diff --git a/include/linux/sfi_acpi.h b/include/linux/sfi_acpi.h deleted file mode 100644 index a6e555cbe05c..000000000000 --- a/include/linux/sfi_acpi.h +++ /dev/null @@ -1,93 +0,0 @@ -/* sfi.h Simple Firmware Interface */ - -/* - - This file is provided under a dual BSD/GPLv2 license. When using or - redistributing this file, you may do so under either license. - - GPL LICENSE SUMMARY - - Copyright(c) 2009 Intel Corporation. All rights reserved. - - This program is free software; you can redistribute it and/or modify - it under the terms of version 2 of the GNU General Public License as - published by the Free Software Foundation. - - This program is distributed in the hope that it will be useful, but - WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - General Public License for more details. - - You should have received a copy of the GNU General Public License - along with this program; if not, write to the Free Software - Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - The full GNU General Public License is included in this distribution - in the file called LICENSE.GPL. - - BSD LICENSE - - Copyright(c) 2009 Intel Corporation. All rights reserved. - - Redistribution and use in source and binary forms, with or without - modification, are permitted provided that the following conditions - are met: - - * Redistributions of source code must retain the above copyright - notice, this list of conditions and the following disclaimer. - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in - the documentation and/or other materials provided with the - distribution. - * Neither the name of Intel Corporation nor the names of its - contributors may be used to endorse or promote products derived - from this software without specific prior written permission. - - THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - -*/ - -#ifndef _LINUX_SFI_ACPI_H -#define _LINUX_SFI_ACPI_H - -#include -#include - -#ifdef CONFIG_SFI -extern int sfi_acpi_table_parse(char *signature, char *oem_id, - char *oem_table_id, - int (*handler)(struct acpi_table_header *)); - -static inline int __init acpi_sfi_table_parse(char *signature, - int (*handler)(struct acpi_table_header *)) -{ - if (!acpi_table_parse(signature, handler)) - return 0; - - return sfi_acpi_table_parse(signature, NULL, NULL, handler); -} -#else /* !CONFIG_SFI */ -static inline int sfi_acpi_table_parse(char *signature, char *oem_id, - char *oem_table_id, - int (*handler)(struct acpi_table_header *)) -{ - return -1; -} - -static inline int __init acpi_sfi_table_parse(char *signature, - int (*handler)(struct acpi_table_header *)) -{ - return acpi_table_parse(signature, handler); -} -#endif /* !CONFIG_SFI */ - -#endif /*_LINUX_SFI_ACPI_H*/ -- cgit v1.2.3 From ca66dca5eda6bd16b7b27fed2a034f2396df5627 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Fri, 5 Feb 2021 03:01:18 +0300 Subject: thermal: qcom: add support for adc-tm5 PMIC thermal monitor Add support for Thermal Monitoring part of PMIC5. This part is closely coupled with ADC, using it's channels directly. ADC-TM support generating interrupts on ADC value crossing low or high voltage bounds, which is used to support thermal trip points. Signed-off-by: Dmitry Baryshkov Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20210205000118.493610-3-dmitry.baryshkov@linaro.org --- include/linux/iio/adc/qcom-vadc-common.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/adc/qcom-vadc-common.h b/include/linux/iio/adc/qcom-vadc-common.h index 58216124d89d..33f60f43e1aa 100644 --- a/include/linux/iio/adc/qcom-vadc-common.h +++ b/include/linux/iio/adc/qcom-vadc-common.h @@ -158,6 +158,9 @@ int qcom_adc5_hw_scale(enum vadc_scale_fn_type scaletype, const struct adc5_data *data, u16 adc_code, int *result_mdec); +u16 qcom_adc_tm5_temp_volt_scale(unsigned int prescale_ratio, + u32 full_scale_code_volt, int temp); + int qcom_adc5_prescaling_from_dt(u32 num, u32 den); int qcom_adc5_hw_settle_time_from_dt(u32 value, const unsigned int *hw_settle); -- cgit v1.2.3 From d0a0bbe7b0a181c58bd22d6942146cfa3ab9e49a Mon Sep 17 00:00:00 2001 From: Tong Zhang Date: Sun, 14 Feb 2021 18:43:08 -0500 Subject: atm: idt77252: fix build broken on amd64 idt77252 is broken and wont load on amd64 systems modprobe idt77252 shows the following idt77252_init: skb->cb is too small (48 < 56) Add packed attribute to struct idt77252_skb_prv and struct atm_skb_data so that the total size can be <= sizeof(skb->cb) Also convert runtime size check to buildtime size check in idt77252_init() Signed-off-by: Tong Zhang Signed-off-by: David S. Miller --- include/linux/atmdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h index d7493016cd46..60cd25c0461b 100644 --- a/include/linux/atmdev.h +++ b/include/linux/atmdev.h @@ -207,7 +207,7 @@ struct atm_skb_data { struct atm_vcc *vcc; /* ATM VCC */ unsigned long atm_options; /* ATM layer options */ unsigned int acct_truesize; /* truesize accounted to vcc */ -}; +} __packed; #define VCC_HTABLE_SIZE 32 -- cgit v1.2.3 From 17d3a83afbbff34209d6c3636718fc1abe305ef8 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Fri, 12 Feb 2021 19:46:31 -0800 Subject: net: phy: broadcom: Remove unused flags We have a number of unused flags defined today and since we are scarce on space and may need to introduce new flags in the future remove and shift every existing flag down into a contiguous assignment. PHY_BCM_FLAGS_MODE_1000BX was only used internally for the BCM54616S PHY, so we allocate a driver private structure instead to store that flag instead of canibalizing one from phydev->dev_flags for that purpose. Signed-off-by: Florian Fainelli Reviewed-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 21 ++++++++------------- 1 file changed, 8 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index de9430d55c90..844dcfe789a2 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -61,19 +61,14 @@ #define PHY_BCM_OUI_5 0x03625e00 #define PHY_BCM_OUI_6 0xae025000 -#define PHY_BCM_FLAGS_MODE_COPPER 0x00000001 -#define PHY_BCM_FLAGS_MODE_1000BX 0x00000002 -#define PHY_BCM_FLAGS_INTF_SGMII 0x00000010 -#define PHY_BCM_FLAGS_INTF_XAUI 0x00000020 -#define PHY_BRCM_WIRESPEED_ENABLE 0x00000100 -#define PHY_BRCM_AUTO_PWRDWN_ENABLE 0x00000200 -#define PHY_BRCM_RX_REFCLK_UNUSED 0x00000400 -#define PHY_BRCM_STD_IBND_DISABLE 0x00000800 -#define PHY_BRCM_EXT_IBND_RX_ENABLE 0x00001000 -#define PHY_BRCM_EXT_IBND_TX_ENABLE 0x00002000 -#define PHY_BRCM_CLEAR_RGMII_MODE 0x00004000 -#define PHY_BRCM_DIS_TXCRXC_NOENRGY 0x00008000 -#define PHY_BRCM_EN_MASTER_MODE 0x00010000 +#define PHY_BRCM_AUTO_PWRDWN_ENABLE 0x00000001 +#define PHY_BRCM_RX_REFCLK_UNUSED 0x00000002 +#define PHY_BRCM_STD_IBND_DISABLE 0x00000004 +#define PHY_BRCM_EXT_IBND_RX_ENABLE 0x00000008 +#define PHY_BRCM_EXT_IBND_TX_ENABLE 0x00000010 +#define PHY_BRCM_CLEAR_RGMII_MODE 0x00000020 +#define PHY_BRCM_DIS_TXCRXC_NOENRGY 0x00000040 +#define PHY_BRCM_EN_MASTER_MODE 0x00000080 /* Broadcom BCM7xxx specific workarounds */ #define PHY_BRCM_7XXX_REV(x) (((x) >> 8) & 0xff) -- cgit v1.2.3 From 5d4358ede8ebe2e4ae03a633082f3ce21ec2df3e Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Fri, 12 Feb 2021 19:46:32 -0800 Subject: net: phy: broadcom: Allow BCM54210E to configure APD BCM54210E/BCM50212E has been verified to work correctly with the auto-power down configuration done by bcm54xx_adjust_rxrefclk(), add it to the list of PHYs working. While we are at it, provide an appropriate name for the bit we are changing which disables the RXC and TXC during auto-power down when there is no energy on the cable. Signed-off-by: Florian Fainelli Reviewed-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 844dcfe789a2..16597d3fa011 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -193,6 +193,7 @@ #define BCM54XX_SHD_SCR3_DEF_CLK125 0x0001 #define BCM54XX_SHD_SCR3_DLLAPD_DIS 0x0002 #define BCM54XX_SHD_SCR3_TRDDAPD 0x0004 +#define BCM54XX_SHD_SCR3_RXCTXC_DIS 0x0100 /* 01010: Auto Power-Down */ #define BCM54XX_SHD_APD 0x0a @@ -253,7 +254,6 @@ #define BCM54810_EXP_BROADREACH_LRE_MISC_CTL_EN (1 << 0) #define BCM54810_SHD_CLK_CTL 0x3 #define BCM54810_SHD_CLK_CTL_GTXCLK_EN (1 << 9) -#define BCM54810_SHD_SCR3_TRDDAPD 0x0100 /* BCM54612E Registers */ #define BCM54612E_EXP_SPARE0 (MII_BCM54XX_EXP_SEL_ETC + 0x34) -- cgit v1.2.3 From 93e8990c24bee30696c02e8f6aed043333491a25 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sun, 14 Feb 2021 15:16:23 +0100 Subject: net: phy: rename PHY_IGNORE_INTERRUPT to PHY_MAC_INTERRUPT Some internal PHY's have their events like link change reported by the MAC interrupt. We have PHY_IGNORE_INTERRUPT to deal with this scenario. I'm not too happy with this name. We don't ignore interrupts, typically there is no interrupt exposed at a PHY level. So let's rename it to PHY_MAC_INTERRUPT. This is in line with phy_mac_interrupt(), which is called from the MAC interrupt handler to handle PHY events. Signed-off-by: Heiner Kallweit Reviewed-by: Andrew Lunn Acked-by: Florian Fainelli Reviewed-by: Russell King Signed-off-by: David S. Miller --- include/linux/phy.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index c130788306c8..5d7c4084ade9 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -71,11 +71,11 @@ extern const int phy_10gbit_features_array[1]; /* * Set phydev->irq to PHY_POLL if interrupts are not supported, - * or not desired for this PHY. Set to PHY_IGNORE_INTERRUPT if - * the attached driver handles the interrupt + * or not desired for this PHY. Set to PHY_MAC_INTERRUPT if + * the attached MAC driver handles the interrupt */ #define PHY_POLL -1 -#define PHY_IGNORE_INTERRUPT -2 +#define PHY_MAC_INTERRUPT -2 #define PHY_IS_INTERNAL 0x00000001 #define PHY_RST_AFTER_CLK_EN 0x00000002 @@ -1202,11 +1202,11 @@ static inline int phy_clear_bits_mmd(struct phy_device *phydev, int devad, * @phydev: the phy_device struct * * NOTE: must be kept in sync with addition/removal of PHY_POLL and - * PHY_IGNORE_INTERRUPT + * PHY_MAC_INTERRUPT */ static inline bool phy_interrupt_is_valid(struct phy_device *phydev) { - return phydev->irq != PHY_POLL && phydev->irq != PHY_IGNORE_INTERRUPT; + return phydev->irq != PHY_POLL && phydev->irq != PHY_MAC_INTERRUPT; } /** -- cgit v1.2.3 From aec6c60a01d3a3170242d6a99372a388e1136dc6 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sat, 16 Jan 2021 08:35:42 +0900 Subject: kbuild: check the minimum compiler version in Kconfig Paul Gortmaker reported a regression in the GCC version check. [1] If you use GCC 4.8, the build breaks before showing the error message "error Sorry, your version of GCC is too old - please use 4.9 or newer." I do not want to apply his fix-up since it implies we would not be able to remove any cc-option test. Anyway, I admit checking the GCC version in is too late. Almost at the same time, Linus also suggested to move the compiler version error to Kconfig time. [2] I unified the two similar scripts, gcc-version.sh and clang-version.sh into cc-version.sh. The old scripts invoked the compiler multiple times (3 times for gcc-version.sh, 4 times for clang-version.sh). I refactored the code so the new one invokes the compiler just once, and also tried my best to use shell-builtin commands where possible. The new script runs faster. $ time ./scripts/clang-version.sh clang 120000 real 0m0.029s user 0m0.012s sys 0m0.021s $ time ./scripts/cc-version.sh clang Clang 120000 real 0m0.009s user 0m0.006s sys 0m0.004s cc-version.sh also shows an error message if the compiler is too old: $ make defconfig CC=clang-9 *** Default configuration is based on 'x86_64_defconfig' *** *** Compiler is too old. *** Your Clang version: 9.0.1 *** Minimum Clang version: 10.0.1 *** scripts/Kconfig.include:46: Sorry, this compiler is not supported. make[1]: *** [scripts/kconfig/Makefile:81: defconfig] Error 1 make: *** [Makefile:602: defconfig] Error 2 The new script takes care of ICC because we have although I am not sure if building the kernel with ICC is well-supported. [1]: https://lore.kernel.org/r/20210110190807.134996-1-paul.gortmaker@windriver.com [2]: https://lore.kernel.org/r/CAHk-=wh-+TMHPTFo1qs-MYyK7tZh-OQovA=pP3=e06aCVp6_kA@mail.gmail.com Fixes: 87de84c9140e ("kbuild: remove cc-option test of -Werror=date-time") Reported-by: Paul Gortmaker Suggested-by: Linus Torvalds Reviewed-by: Nick Desaulniers Tested-by: Nick Desaulniers Reviewed-by: Nathan Chancellor Tested-by: Nathan Chancellor Reviewed-by: Miguel Ojeda Tested-by: Miguel Ojeda Tested-by: Sedat Dilek Signed-off-by: Masahiro Yamada --- include/linux/compiler-clang.h | 10 ---------- include/linux/compiler-gcc.h | 11 ----------- 2 files changed, 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 98cff1b4b088..04c0a5a717f7 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -3,16 +3,6 @@ #error "Please don't include directly, include instead." #endif -#define CLANG_VERSION (__clang_major__ * 10000 \ - + __clang_minor__ * 100 \ - + __clang_patchlevel__) - -#if CLANG_VERSION < 100001 -#ifndef __BPF_TRACING__ -# error Sorry, your version of Clang is too old - please use 10.0.1 or newer. -#endif -#endif - /* Compiler specific definitions for Clang compiler */ /* same as gcc, this was present in clang-2.6 so we can assume it works diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 555ab0fddbef..48750243db4c 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -10,17 +10,6 @@ + __GNUC_MINOR__ * 100 \ + __GNUC_PATCHLEVEL__) -/* https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 */ -#if GCC_VERSION < 40900 -# error Sorry, your version of GCC is too old - please use 4.9 or newer. -#elif defined(CONFIG_ARM64) && GCC_VERSION < 50100 -/* - * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63293 - * https://lore.kernel.org/r/20210107111841.GN1551@shell.armlinux.org.uk - */ -# error Sorry, your version of GCC is too old - please use 5.1 or newer. -#endif - /* * This macro obfuscates arithmetic on a variable address so that gcc * shouldn't recognize the original var, and make assumptions about it. -- cgit v1.2.3 From 88a686728b3739d3598851e729c0e81f194e5c53 Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Fri, 12 Feb 2021 11:29:24 -0500 Subject: kbuild: simplify access to the kernel's version Instead of storing the version in a single integer and having various kernel (and userspace) code how it's constructed, export individual (major, patchlevel, sublevel) components and simplify kernel code that uses it. This should also make it easier on userspace. Signed-off-by: Sasha Levin Acked-by: Greg Kroah-Hartman Signed-off-by: Masahiro Yamada --- include/linux/usb/composite.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index a2d229ab63ba..7531ce723374 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -573,8 +573,8 @@ static inline u16 get_default_bcdDevice(void) { u16 bcdDevice; - bcdDevice = bin2bcd((LINUX_VERSION_CODE >> 16 & 0xff)) << 8; - bcdDevice |= bin2bcd((LINUX_VERSION_CODE >> 8 & 0xff)); + bcdDevice = bin2bcd(LINUX_VERSION_MAJOR) << 8; + bcdDevice |= bin2bcd(LINUX_VERSION_PATCHLEVEL); return bcdDevice; } -- cgit v1.2.3 From aab73d9524026caa14aab17fa9b750a6539fd49f Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Wed, 13 Jan 2021 15:26:33 -0800 Subject: tpm: add sysfs exports for all banks of PCR registers Create sysfs per hash groups with 24 PCR files in them one group, named pcr-, for each agile hash of the TPM. The files are plugged in to a PCR read function which is TPM version agnostic, so this works also for TPM 1.2 but the hash is only sha1 in that case. Note: the macros used to create the hashes emit spurious checkpatch warnings. Do not try to "fix" them as checkpatch recommends, otherwise they'll break. Signed-off-by: James Bottomley Reviewed-by: Jerry Snitselaar Tested-by: Thiago Jung Bauermann Tested-by: Jarkko Sakkinen Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen --- include/linux/tpm.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 8f4ff39f51e7..ae2482510f8c 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -31,6 +31,7 @@ struct tpm_chip; struct trusted_key_payload; struct trusted_key_options; +/* if you add a new hash to this, increment TPM_MAX_HASHES below */ enum tpm_algorithms { TPM_ALG_ERROR = 0x0000, TPM_ALG_SHA1 = 0x0004, @@ -42,6 +43,12 @@ enum tpm_algorithms { TPM_ALG_SM3_256 = 0x0012, }; +/* + * maximum number of hashing algorithms a TPM can have. This is + * basically a count of every hash in tpm_algorithms above + */ +#define TPM_MAX_HASHES 5 + struct tpm_digest { u16 alg_id; u8 digest[TPM_MAX_DIGEST_SIZE]; @@ -146,7 +153,7 @@ struct tpm_chip { struct dentry *bios_dir[TPM_NUM_EVENT_LOG_FILES]; - const struct attribute_group *groups[3]; + const struct attribute_group *groups[3 + TPM_MAX_HASHES]; unsigned int groups_cnt; u32 nr_allocated_banks; -- cgit v1.2.3 From 8c657a0590de585b1115847c17b34a58025f2f4b Mon Sep 17 00:00:00 2001 From: Jarkko Sakkinen Date: Fri, 29 Jan 2021 01:56:21 +0200 Subject: KEYS: trusted: Reserve TPM for seal and unseal operations When TPM 2.0 trusted keys code was moved to the trusted keys subsystem, the operations were unwrapped from tpm_try_get_ops() and tpm_put_ops(), which are used to take temporarily the ownership of the TPM chip. The ownership is only taken inside tpm_send(), but this is not sufficient, as in the key load TPM2_CC_LOAD, TPM2_CC_UNSEAL and TPM2_FLUSH_CONTEXT need to be done as a one single atom. Take the TPM chip ownership before sending anything with tpm_try_get_ops() and tpm_put_ops(), and use tpm_transmit_cmd() to send TPM commands instead of tpm_send(), reverting back to the old behaviour. Fixes: 2e19e10131a0 ("KEYS: trusted: Move TPM2 trusted keys code") Reported-by: "James E.J. Bottomley" Cc: stable@vger.kernel.org Cc: David Howells Cc: Mimi Zohar Cc: Sumit Garg Acked-by Sumit Garg Tested-by: Mimi Zohar Signed-off-by: Jarkko Sakkinen --- include/linux/tpm.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tpm.h b/include/linux/tpm.h index ae2482510f8c..543aa3b1dedc 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -404,6 +404,10 @@ static inline u32 tpm2_rc_value(u32 rc) #if defined(CONFIG_TCG_TPM) || defined(CONFIG_TCG_TPM_MODULE) extern int tpm_is_tpm2(struct tpm_chip *chip); +extern __must_check int tpm_try_get_ops(struct tpm_chip *chip); +extern void tpm_put_ops(struct tpm_chip *chip); +extern ssize_t tpm_transmit_cmd(struct tpm_chip *chip, struct tpm_buf *buf, + size_t min_rsp_body_length, const char *desc); extern int tpm_pcr_read(struct tpm_chip *chip, u32 pcr_idx, struct tpm_digest *digest); extern int tpm_pcr_extend(struct tpm_chip *chip, u32 pcr_idx, @@ -417,7 +421,6 @@ static inline int tpm_is_tpm2(struct tpm_chip *chip) { return -ENODEV; } - static inline int tpm_pcr_read(struct tpm_chip *chip, int pcr_idx, struct tpm_digest *digest) { -- cgit v1.2.3 From bfe3911a91047557eb0e620f95a370aee6a248c7 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Fri, 5 Feb 2021 22:00:12 +0000 Subject: kcmp: Support selection of SYS_kcmp without CHECKPOINT_RESTORE Userspace has discovered the functionality offered by SYS_kcmp and has started to depend upon it. In particular, Mesa uses SYS_kcmp for os_same_file_description() in order to identify when two fd (e.g. device or dmabuf) point to the same struct file. Since they depend on it for core functionality, lift SYS_kcmp out of the non-default CONFIG_CHECKPOINT_RESTORE into the selectable syscall category. Rasmus Villemoes also pointed out that systemd uses SYS_kcmp to deduplicate the per-service file descriptor store. Note that some distributions such as Ubuntu are already enabling CHECKPOINT_RESTORE in their configs and so, by extension, SYS_kcmp. References: https://gitlab.freedesktop.org/drm/intel/-/issues/3046 Signed-off-by: Chris Wilson Cc: Kees Cook Cc: Andy Lutomirski Cc: Will Drewry Cc: Andrew Morton Cc: Dave Airlie Cc: Daniel Vetter Cc: Lucas Stach Cc: Rasmus Villemoes Cc: Cyrill Gorcunov Cc: stable@vger.kernel.org Acked-by: Daniel Vetter # DRM depends on kcmp Acked-by: Rasmus Villemoes # systemd uses kcmp Reviewed-by: Cyrill Gorcunov Reviewed-by: Kees Cook Acked-by: Thomas Zimmermann Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210205220012.1983-1-chris@chris-wilson.co.uk --- include/linux/eventpoll.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h index 0350393465d4..593322c946e6 100644 --- a/include/linux/eventpoll.h +++ b/include/linux/eventpoll.h @@ -18,7 +18,7 @@ struct file; #ifdef CONFIG_EPOLL -#ifdef CONFIG_CHECKPOINT_RESTORE +#ifdef CONFIG_KCMP struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, unsigned long toff); #endif -- cgit v1.2.3 From afd56e78dd179d5638333bb407d9f7da2863381a Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Fri, 22 Jan 2021 15:41:14 +0100 Subject: libceph: deprecate [no]cephx_require_signatures options These options were introduced in 3.19 with support for message signing and are rather useless, as explained in commit a51983e4dd2d ("libceph: add nocephx_sign_messages option"). Deprecate them. In case there is someone out there with a cluster that lacks support for MSG_AUTH feature (very unlikely but has to be considered since we haven't formally raised the bar from argonaut to bobtail yet), make nocephx_sign_messages also waive MSG_AUTH requirement. This is probably how it should have been done in the first place -- if we aren't going to sign, requiring the signing feature makes no sense. Signed-off-by: Ilya Dryomov Reviewed-by: Jeff Layton --- include/linux/ceph/libceph.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index eb9008bb3992..409d8c29bc4f 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -32,10 +32,9 @@ #define CEPH_OPT_NOSHARE (1<<1) /* don't share client with other sbs */ #define CEPH_OPT_MYIP (1<<2) /* specified my ip */ #define CEPH_OPT_NOCRC (1<<3) /* no data crc on writes (msgr1) */ -#define CEPH_OPT_NOMSGAUTH (1<<4) /* don't require msg signing feat */ -#define CEPH_OPT_TCP_NODELAY (1<<5) /* TCP_NODELAY on TCP sockets */ -#define CEPH_OPT_NOMSGSIGN (1<<6) /* don't sign msgs (msgr1) */ -#define CEPH_OPT_ABORT_ON_FULL (1<<7) /* abort w/ ENOSPC when full */ +#define CEPH_OPT_TCP_NODELAY (1<<4) /* TCP_NODELAY on TCP sockets */ +#define CEPH_OPT_NOMSGSIGN (1<<5) /* don't sign msgs (msgr1) */ +#define CEPH_OPT_ABORT_ON_FULL (1<<6) /* abort w/ ENOSPC when full */ #define CEPH_OPT_DEFAULT (CEPH_OPT_TCP_NODELAY) -- cgit v1.2.3 From a6a217dddcd544f6b75f0e2a60b6e84c1d494b7e Mon Sep 17 00:00:00 2001 From: Aharon Landau Date: Tue, 9 Feb 2021 15:11:06 +0200 Subject: net/mlx5: Add new timestamp mode bits These fields declare which timestamp mode is supported by the device per RQ/SQ/QP. In addition add the ts_format field to the select the mode for RQ/SQ/QP. Link: https://lore.kernel.org/r/20210209131107.698833-2-leon@kernel.org Signed-off-by: Aharon Landau Signed-off-by: Maor Gottlieb Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 54 +++++++++++++++++++++++++++++++++++++++---- 1 file changed, 49 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index cf692fc17f41..436d6f421dfd 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -932,11 +932,18 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits { u8 reserved_at_200[0x600]; }; +enum { + MLX5_QP_TIMESTAMP_FORMAT_CAP_FREE_RUNNING = 0x0, + MLX5_QP_TIMESTAMP_FORMAT_CAP_REAL_TIME = 0x1, + MLX5_QP_TIMESTAMP_FORMAT_CAP_FREE_RUNNING_AND_REAL_TIME = 0x2, +}; + struct mlx5_ifc_roce_cap_bits { u8 roce_apm[0x1]; u8 reserved_at_1[0x3]; u8 sw_r_roce_src_udp_port[0x1]; - u8 reserved_at_5[0x1b]; + u8 reserved_at_5[0x19]; + u8 qp_ts_format[0x2]; u8 reserved_at_20[0x60]; @@ -1253,6 +1260,18 @@ enum { MLX5_STEERING_FORMAT_CONNECTX_6DX = 1, }; +enum { + MLX5_SQ_TIMESTAMP_FORMAT_CAP_FREE_RUNNING = 0x0, + MLX5_SQ_TIMESTAMP_FORMAT_CAP_REAL_TIME = 0x1, + MLX5_SQ_TIMESTAMP_FORMAT_CAP_FREE_RUNNING_AND_REAL_TIME = 0x2, +}; + +enum { + MLX5_RQ_TIMESTAMP_FORMAT_CAP_FREE_RUNNING = 0x0, + MLX5_RQ_TIMESTAMP_FORMAT_CAP_REAL_TIME = 0x1, + MLX5_RQ_TIMESTAMP_FORMAT_CAP_FREE_RUNNING_AND_REAL_TIME = 0x2, +}; + struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_0[0x1f]; u8 vhca_resource_manager[0x1]; @@ -1564,7 +1583,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 general_obj_types[0x40]; - u8 reserved_at_440[0x4]; + u8 sq_ts_format[0x2]; + u8 rq_ts_format[0x2]; u8 steering_format_version[0x4]; u8 create_qp_start_hint[0x18]; @@ -2868,6 +2888,12 @@ enum { MLX5_QPC_CS_RES_UP_TO_64B = 0x2, }; +enum { + MLX5_QPC_TIMESTAMP_FORMAT_FREE_RUNNING = 0x0, + MLX5_QPC_TIMESTAMP_FORMAT_DEFAULT = 0x1, + MLX5_QPC_TIMESTAMP_FORMAT_REAL_TIME = 0x2, +}; + struct mlx5_ifc_qpc_bits { u8 state[0x4]; u8 lag_tx_port_affinity[0x4]; @@ -2896,7 +2922,9 @@ struct mlx5_ifc_qpc_bits { u8 log_rq_stride[0x3]; u8 no_sq[0x1]; u8 log_sq_size[0x4]; - u8 reserved_at_55[0x6]; + u8 reserved_at_55[0x3]; + u8 ts_format[0x2]; + u8 reserved_at_5a[0x1]; u8 rlky[0x1]; u8 ulp_stateless_offload_mode[0x4]; @@ -3312,6 +3340,12 @@ enum { MLX5_SQC_STATE_ERR = 0x3, }; +enum { + MLX5_SQC_TIMESTAMP_FORMAT_FREE_RUNNING = 0x0, + MLX5_SQC_TIMESTAMP_FORMAT_DEFAULT = 0x1, + MLX5_SQC_TIMESTAMP_FORMAT_REAL_TIME = 0x2, +}; + struct mlx5_ifc_sqc_bits { u8 rlky[0x1]; u8 cd_master[0x1]; @@ -3323,7 +3357,9 @@ struct mlx5_ifc_sqc_bits { u8 reg_umr[0x1]; u8 allow_swp[0x1]; u8 hairpin[0x1]; - u8 reserved_at_f[0x11]; + u8 reserved_at_f[0xb]; + u8 ts_format[0x2]; + u8 reserved_at_1c[0x4]; u8 reserved_at_20[0x8]; u8 user_index[0x18]; @@ -3414,6 +3450,12 @@ enum { MLX5_RQC_STATE_ERR = 0x3, }; +enum { + MLX5_RQC_TIMESTAMP_FORMAT_FREE_RUNNING = 0x0, + MLX5_RQC_TIMESTAMP_FORMAT_DEFAULT = 0x1, + MLX5_RQC_TIMESTAMP_FORMAT_REAL_TIME = 0x2, +}; + struct mlx5_ifc_rqc_bits { u8 rlky[0x1]; u8 delay_drop_en[0x1]; @@ -3424,7 +3466,9 @@ struct mlx5_ifc_rqc_bits { u8 reserved_at_c[0x1]; u8 flush_in_error_en[0x1]; u8 hairpin[0x1]; - u8 reserved_at_f[0x11]; + u8 reserved_at_f[0xb]; + u8 ts_format[0x2]; + u8 reserved_at_1c[0x4]; u8 reserved_at_20[0x8]; u8 user_index[0x18]; -- cgit v1.2.3 From e0a912e8ddbaa0536352dd8318845cdfdbab7bab Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 16 Feb 2021 12:17:22 -0500 Subject: SUNRPC: Use TCP_CORK to optimise send performance on the server Use a counter to keep track of how many requests are queued behind the xprt->xpt_mutex, and keep TCP_CORK set until the queue is empty. Signed-off-by: Trond Myklebust Link: https://lore.kernel.org/linux-nfs/20210213202532.23146-1-trondmy@kernel.org/T/#u Signed-off-by: Chuck Lever --- include/linux/sunrpc/svcsock.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h index b7ac7fe68306..bcc555c7ae9c 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -35,6 +35,8 @@ struct svc_sock { /* Total length of the data (not including fragment headers) * received so far in the fragments making up this rpc: */ u32 sk_datalen; + /* Number of queued send requests */ + atomic_t sk_sendqlen; struct page * sk_pages[RPCSVC_MAXPAGES]; /* received data */ }; -- cgit v1.2.3 From 7232c132d13aafd178ba18c1099b2cb98d104b8c Mon Sep 17 00:00:00 2001 From: Tal Gilboa Date: Thu, 11 Feb 2021 10:55:49 +0200 Subject: RDMA/mlx5: Allow CQ creation without attached EQs The traditional DevX CQ creation flow goes through mlx5_core_create_cq() which checks that the given EQN corresponds to an existing EQ and attaches a devx handler to the EQN for the CQ. In some cases the EQ will not be a kernel EQ, but will be controlled by modify CQ, don't block creating these just because the EQN can't be found in the kernel. Link: https://lore.kernel.org/r/20210211085549.1277674-1-leon@kernel.org Signed-off-by: Tal Gilboa Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/linux/mlx5/mlx5_ifc.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index cf692fc17f41..768e097c633b 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1634,7 +1634,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 sf_set_partition[0x1]; u8 reserved_at_682[0x1]; u8 log_max_sf[0x5]; - u8 reserved_at_688[0x8]; + u8 apu[0x1]; + u8 reserved_at_689[0x7]; u8 log_min_sf_size[0x8]; u8 max_num_sf_partitions[0x8]; @@ -3816,7 +3817,7 @@ struct mlx5_ifc_cqc_bits { u8 status[0x4]; u8 reserved_at_4[0x2]; u8 dbr_umem_valid[0x1]; - u8 reserved_at_7[0x1]; + u8 apu_thread_cq[0x1]; u8 cqe_sz[0x3]; u8 cc[0x1]; u8 reserved_at_c[0x1]; -- cgit v1.2.3 From 75cfb200cd081d23eb7eaa68deba9e0ab9320070 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 12 Feb 2021 16:49:47 -0500 Subject: NFS: 'flags' field should be unsigned in struct nfs_server The mount flags are all unsigned integers, so we should not be storing them in a signed field. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- include/linux/nfs_fs_sb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 38e60ec742df..962e8313f007 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -142,7 +142,7 @@ struct nfs_server { struct nlm_host *nlm_host; /* NLM client handle */ struct nfs_iostats __percpu *io_stats; /* I/O statistics */ atomic_long_t writeback; /* number of writeback pages */ - int flags; /* various flags */ + unsigned int flags; /* various flags */ /* The following are for internal use only. Also see uapi/linux/nfs_mount.h */ #define NFS_MOUNT_LOOKUP_CACHE_NONEG 0x10000 -- cgit v1.2.3 From ed7bcdb374d20fab9e9dc36853a6735c047ad1b1 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 12 Feb 2021 16:49:48 -0500 Subject: NFS: Add support for eager writes Support eager writing to the server, meaning that we write the data to cache on the server, and wait for that to complete. This ensures that we see ENOSPC errors immediately. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- include/linux/nfs_fs_sb.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 962e8313f007..6f76b32a0238 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -153,6 +153,8 @@ struct nfs_server { #define NFS_MOUNT_LOCAL_FCNTL 0x200000 #define NFS_MOUNT_SOFTERR 0x400000 #define NFS_MOUNT_SOFTREVAL 0x800000 +#define NFS_MOUNT_WRITE_EAGER 0x01000000 +#define NFS_MOUNT_WRITE_WAIT 0x02000000 unsigned int caps; /* server capabilities */ unsigned int rsize; /* read size */ -- cgit v1.2.3 From ae02d41551d6f2a035d3e63ce4415e1b2ba3a7e6 Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Fri, 12 Feb 2021 14:30:38 -0800 Subject: net/mlx5: Add register layout to support real-time time-stamp Add needed structure layouts and defines for MTUTC (Management UTC) register. MTUTC will be used for cyc2time HW translation. In addition, add cyc2time modify capability bit and init segment HCA real time address. Finally, add capability bits indicating which time-stamping format is supported per SQ and RQ. Add ts_format in the queue's context layout to allow configuration. Signed-off-by: Eran Ben Elisha Signed-off-by: Aya Levin Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 5 ++++- include/linux/mlx5/driver.h | 1 + include/linux/mlx5/mlx5_ifc.h | 30 ++++++++++++++++++++++++++++-- 3 files changed, 33 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index f1de49d64a98..fd694add6ff0 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -578,7 +578,10 @@ struct mlx5_init_seg { __be32 internal_timer_l; __be32 rsvd3[2]; __be32 health_counter; - __be32 rsvd4[1019]; + __be32 rsvd4[11]; + __be32 real_time_h; + __be32 real_time_l; + __be32 rsvd5[1006]; __be64 ieee1588_clk; __be32 ieee1588_clk_type; __be32 clr_intx; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f93bfe7473aa..2eb7755143d7 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -143,6 +143,7 @@ enum { MLX5_REG_MPCNT = 0x9051, MLX5_REG_MTPPS = 0x9053, MLX5_REG_MTPPSE = 0x9054, + MLX5_REG_MTUTC = 0x9055, MLX5_REG_MPEGC = 0x9056, MLX5_REG_MCQS = 0x9060, MLX5_REG_MCQI = 0x9061, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 436d6f421dfd..7059fcdf54a3 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -9150,6 +9150,28 @@ struct mlx5_ifc_mpegc_reg_bits { u8 reserved_at_60[0x100]; }; +enum { + MLX5_MTUTC_OPERATION_SET_TIME_IMMEDIATE = 0x1, + MLX5_MTUTC_OPERATION_ADJUST_TIME = 0x2, + MLX5_MTUTC_OPERATION_ADJUST_FREQ_UTC = 0x3, +}; + +struct mlx5_ifc_mtutc_reg_bits { + u8 reserved_at_0[0x1c]; + u8 operation[0x4]; + + u8 freq_adjustment[0x20]; + + u8 reserved_at_40[0x40]; + + u8 utc_sec[0x20]; + + u8 reserved_at_a0[0x2]; + u8 utc_nsec[0x1e]; + + u8 time_adjustment[0x20]; +}; + struct mlx5_ifc_pcam_enhanced_features_bits { u8 reserved_at_0[0x68]; u8 fec_50G_per_lane_in_pplm[0x1]; @@ -9208,7 +9230,9 @@ struct mlx5_ifc_pcam_reg_bits { }; struct mlx5_ifc_mcam_enhanced_features_bits { - u8 reserved_at_0[0x6e]; + u8 reserved_at_0[0x6b]; + u8 ptpcyc2realtime_modify[0x1]; + u8 reserved_at_6c[0x2]; u8 pci_status_and_power[0x1]; u8 reserved_at_6f[0x5]; u8 mark_tx_action_cnp[0x1]; @@ -9231,7 +9255,8 @@ struct mlx5_ifc_mcam_access_reg_bits { u8 regs_95_to_87[0x9]; u8 mpegc[0x1]; - u8 regs_85_to_68[0x12]; + u8 mtutc[0x1]; + u8 regs_84_to_68[0x11]; u8 tracer_registers[0x4]; u8 regs_63_to_32[0x20]; @@ -9964,6 +9989,7 @@ union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_mcda_reg_bits mcda_reg; struct mlx5_ifc_mirc_reg_bits mirc_reg; struct mlx5_ifc_mfrl_reg_bits mfrl_reg; + struct mlx5_ifc_mtutc_reg_bits mtutc_reg; u8 reserved_at_0[0x60e0]; }; -- cgit v1.2.3 From d6f3dc8f509ce6288e2537eb4b0614ef444fd84a Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Fri, 12 Feb 2021 14:30:40 -0800 Subject: net/mlx5: Move all internal timer metadata into a dedicated struct Internal timer mode (SW clock) requires some PTP clock related metadata structs. Real time mode (HW clock) will not need these metadata structs. This separation emphasize the different interfaces for HW clock and SW clock. Signed-off-by: Eran Ben Elisha Signed-off-by: Aya Levin Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 2eb7755143d7..2f4d6182df1b 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -662,18 +662,22 @@ struct mlx5_pps { u8 enabled; }; -struct mlx5_clock { - struct mlx5_nb pps_nb; - seqlock_t lock; +struct mlx5_timer { struct cyclecounter cycles; struct timecounter tc; - struct hwtstamp_config hwtstamp_config; u32 nominal_c_mult; unsigned long overflow_period; struct delayed_work overflow_work; +}; + +struct mlx5_clock { + struct mlx5_nb pps_nb; + seqlock_t lock; + struct hwtstamp_config hwtstamp_config; struct ptp_clock *ptp; struct ptp_clock_info ptp_info; struct mlx5_pps pps_info; + struct mlx5_timer timer; }; struct mlx5_dm; -- cgit v1.2.3 From 32aeba1f7a98b0c69d4a5704a7d9cea42ba856ba Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 16 Feb 2021 11:08:37 -0800 Subject: tg3: Remove unused PHY_BRCM flags The tg3 driver tried to communicate towards the PHY driver whether it wanted RGMII in-band signaling enabled or disabled however there is nothing that looks at those flags in drivers/net/phy/broadcom.c so this does do not anything. Suggested-by: Vladimir Oltean Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 16597d3fa011..8fe1d55371ac 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -63,12 +63,9 @@ #define PHY_BRCM_AUTO_PWRDWN_ENABLE 0x00000001 #define PHY_BRCM_RX_REFCLK_UNUSED 0x00000002 -#define PHY_BRCM_STD_IBND_DISABLE 0x00000004 -#define PHY_BRCM_EXT_IBND_RX_ENABLE 0x00000008 -#define PHY_BRCM_EXT_IBND_TX_ENABLE 0x00000010 -#define PHY_BRCM_CLEAR_RGMII_MODE 0x00000020 -#define PHY_BRCM_DIS_TXCRXC_NOENRGY 0x00000040 -#define PHY_BRCM_EN_MASTER_MODE 0x00000080 +#define PHY_BRCM_CLEAR_RGMII_MODE 0x00000004 +#define PHY_BRCM_DIS_TXCRXC_NOENRGY 0x00000008 +#define PHY_BRCM_EN_MASTER_MODE 0x00000010 /* Broadcom BCM7xxx specific workarounds */ #define PHY_BRCM_7XXX_REV(x) (((x) >> 8) & 0xff) -- cgit v1.2.3 From 7331d1d4622ba7e668ec19cfba2ed7feb4a3084e Mon Sep 17 00:00:00 2001 From: Pavana Sharma Date: Tue, 16 Feb 2021 20:20:53 +0100 Subject: net: phy: Add 5GBASER interface mode MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add 5GBASE-R phy interface mode Signed-off-by: Pavana Sharma Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: Marek Behún Signed-off-by: David S. Miller --- include/linux/phy.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 5d7c4084ade9..0d537f59b77f 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -107,6 +107,7 @@ extern const int phy_10gbit_features_array[1]; * @PHY_INTERFACE_MODE_100BASEX: 100 BaseX * @PHY_INTERFACE_MODE_1000BASEX: 1000 BaseX * @PHY_INTERFACE_MODE_2500BASEX: 2500 BaseX + * @PHY_INTERFACE_MODE_5GBASER: 5G BaseR * @PHY_INTERFACE_MODE_RXAUI: Reduced XAUI * @PHY_INTERFACE_MODE_XAUI: 10 Gigabit Attachment Unit Interface * @PHY_INTERFACE_MODE_10GBASER: 10G BaseR @@ -139,6 +140,7 @@ typedef enum { PHY_INTERFACE_MODE_100BASEX, PHY_INTERFACE_MODE_1000BASEX, PHY_INTERFACE_MODE_2500BASEX, + PHY_INTERFACE_MODE_5GBASER, PHY_INTERFACE_MODE_RXAUI, PHY_INTERFACE_MODE_XAUI, /* 10GBASE-R, XFI, SFI - single lane 10G Serdes */ @@ -209,6 +211,8 @@ static inline const char *phy_modes(phy_interface_t interface) return "1000base-x"; case PHY_INTERFACE_MODE_2500BASEX: return "2500base-x"; + case PHY_INTERFACE_MODE_5GBASER: + return "5gbase-r"; case PHY_INTERFACE_MODE_RXAUI: return "rxaui"; case PHY_INTERFACE_MODE_XAUI: -- cgit v1.2.3 From d8ea7ff3995ead5193313c72c0d97c9c16c83be9 Mon Sep 17 00:00:00 2001 From: Horatiu Vultur Date: Tue, 16 Feb 2021 22:42:03 +0100 Subject: net: mscc: ocelot: Add support for MRP Add basic support for MRP. The HW will just trap all MRP frames on the ring ports to CPU and allow the SW to process them. In this way it is possible to for this node to behave both as MRM and MRC. Current limitations are: - it doesn't support Interconnect roles. - it supports only a single ring. - the HW should be able to do forwarding of MRP Test frames so the SW will not need to do this. So it would be able to have the role MRC without SW support. Signed-off-by: Horatiu Vultur Signed-off-by: David S. Miller --- include/linux/dsa/ocelot.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h index c6bc45ae5e03..4265f328681a 100644 --- a/include/linux/dsa/ocelot.h +++ b/include/linux/dsa/ocelot.h @@ -160,6 +160,11 @@ static inline void ocelot_xfh_get_src_port(void *extraction, u64 *src_port) packing(extraction, src_port, 46, 43, OCELOT_TAG_LEN, UNPACK, 0); } +static inline void ocelot_xfh_get_cpuq(void *extraction, u64 *cpuq) +{ + packing(extraction, cpuq, 28, 20, OCELOT_TAG_LEN, UNPACK, 0); +} + static inline void ocelot_xfh_get_qos_class(void *extraction, u64 *qos_class) { packing(extraction, qos_class, 19, 17, OCELOT_TAG_LEN, UNPACK, 0); -- cgit v1.2.3 From 3afd0218992a8d1398e9791d6c2edd4c948ae7ee Mon Sep 17 00:00:00 2001 From: Robert Hancock Date: Tue, 16 Feb 2021 16:54:52 -0600 Subject: net: phy: broadcom: Set proper 1000BaseX/SGMII interface mode for BCM54616S The default configuration for the BCM54616S PHY may not match the desired mode when using 1000BaseX or SGMII interface modes, such as when it is on an SFP module. Add code to explicitly set the correct mode using programming sequences provided by Bel-Fuse: https://www.belfuse.com/resources/datasheets/powersolutions/ds-bps-sfp-1gbt-05-series.pdf https://www.belfuse.com/resources/datasheets/powersolutions/ds-bps-sfp-1gbt-06-series.pdf Signed-off-by: Robert Hancock Acked-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 8fe1d55371ac..c2c2147dfeb8 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -129,6 +129,7 @@ #define MII_BCM54XX_AUXCTL_SHDWSEL_MISC 0x07 #define MII_BCM54XX_AUXCTL_SHDWSEL_MISC_WIRESPEED_EN 0x0010 +#define MII_BCM54XX_AUXCTL_SHDWSEL_MISC_RGMII_EN 0x0080 #define MII_BCM54XX_AUXCTL_SHDWSEL_MISC_RGMII_SKEW_EN 0x0100 #define MII_BCM54XX_AUXCTL_MISC_FORCE_AMDIX 0x0200 #define MII_BCM54XX_AUXCTL_MISC_WREN 0x8000 @@ -216,6 +217,9 @@ /* 11111: Mode Control Register */ #define BCM54XX_SHD_MODE 0x1f #define BCM54XX_SHD_INTF_SEL_MASK GENMASK(2, 1) /* INTERF_SEL[1:0] */ +#define BCM54XX_SHD_INTF_SEL_RGMII 0x02 +#define BCM54XX_SHD_INTF_SEL_SGMII 0x04 +#define BCM54XX_SHD_INTF_SEL_GBIC 0x06 #define BCM54XX_SHD_MODE_1000BX BIT(0) /* Enable 1000-X registers */ /* -- cgit v1.2.3 From b834489bceccc64641684eee5e93275cdf5f465b Mon Sep 17 00:00:00 2001 From: Robert Hancock Date: Tue, 16 Feb 2021 16:54:53 -0600 Subject: net: phy: Add is_on_sfp_module flag and phy_on_sfp helper Add a flag and helper function to indicate that a PHY device is part of an SFP module, which is set on attach. This can be used by PHY drivers to handle SFP-specific quirks or behavior. Signed-off-by: Robert Hancock Signed-off-by: David S. Miller --- include/linux/phy.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 0d537f59b77f..1a12e4436b5b 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -492,6 +492,7 @@ struct macsec_ops; * @sysfs_links: Internal boolean tracking sysfs symbolic links setup/removal. * @loopback_enabled: Set true if this PHY has been loopbacked successfully. * @downshifted_rate: Set true if link speed has been downshifted. + * @is_on_sfp_module: Set true if PHY is located on an SFP module. * @state: State of the PHY for management purposes * @dev_flags: Device-specific flags used by the PHY driver. * @irq: IRQ number of the PHY's interrupt (-1 if none) @@ -565,6 +566,7 @@ struct phy_device { unsigned sysfs_links:1; unsigned loopback_enabled:1; unsigned downshifted_rate:1; + unsigned is_on_sfp_module:1; unsigned autoneg:1; /* The most recently read link state */ @@ -1296,6 +1298,15 @@ static inline bool phy_is_internal(struct phy_device *phydev) return phydev->is_internal; } +/** + * phy_on_sfp - Convenience function for testing if a PHY is on an SFP module + * @phydev: the phy_device struct + */ +static inline bool phy_on_sfp(struct phy_device *phydev) +{ + return phydev->is_on_sfp_module; +} + /** * phy_interface_mode_is_rgmii - Convenience function for testing if a * PHY interface mode is RGMII (all variants) -- cgit v1.2.3 From 1f975074634a63f014e2b7e76852ee6d6005a91d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 12 Feb 2021 18:10:43 +0100 Subject: libnvdimm: Make remove callback return void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit All drivers return 0 in their remove callback and the driver core ignores the return value of nvdimm_bus_remove() anyhow. So simplify by changing the driver remove callback to return void and return 0 unconditionally to the upper layer. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20210212171043.2136580-2-u.kleine-koenig@pengutronix.de Signed-off-by: Dan Williams --- include/linux/nd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nd.h b/include/linux/nd.h index 55c735997805..cec526c8043d 100644 --- a/include/linux/nd.h +++ b/include/linux/nd.h @@ -26,7 +26,7 @@ struct nd_device_driver { struct device_driver drv; unsigned long type; int (*probe)(struct device *dev); - int (*remove)(struct device *dev); + void (*remove)(struct device *dev); void (*shutdown)(struct device *dev); void (*notify)(struct device *dev, enum nvdimm_event event); }; -- cgit v1.2.3 From 4cdadfd5e0a70017fec735b7b6d7f2f731842dc6 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 16 Feb 2021 20:09:50 -0800 Subject: cxl/mem: Introduce a driver for CXL-2.0-Type-3 endpoints The CXL.mem protocol allows a device to act as a provider of "System RAM" and/or "Persistent Memory" that is fully coherent as if the memory was attached to the typical CPU memory controller. With the CXL-2.0 specification a PCI endpoint can implement a "Type-3" device interface and give the operating system control over "Host Managed Device Memory". See section 2.3 Type 3 CXL Device. The memory range exported by the device may optionally be described by the platform firmware memory map, or by infrastructure like LIBNVDIMM to provision persistent memory capacity from one, or more, CXL.mem devices. A pre-requisite for Linux-managed memory-capacity provisioning is this cxl_mem driver that can speak the mailbox protocol defined in section 8.2.8.4 Mailbox Registers. For now just land the initial driver boiler-plate and Documentation/ infrastructure. Signed-off-by: Ben Widawsky Reviewed-by: Jonathan Cameron Acked-by: David Rientjes (v1) Cc: Jonathan Corbet Link: https://www.computeexpresslink.org/download-the-specification Link: https://lore.kernel.org/r/20210217040958.1354670-2-ben.widawsky@intel.com Signed-off-by: Dan Williams --- include/linux/pci_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index d8156a5dbee8..766260a9b247 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -51,6 +51,7 @@ #define PCI_BASE_CLASS_MEMORY 0x05 #define PCI_CLASS_MEMORY_RAM 0x0500 #define PCI_CLASS_MEMORY_FLASH 0x0501 +#define PCI_CLASS_MEMORY_CXL 0x0502 #define PCI_CLASS_MEMORY_OTHER 0x0580 #define PCI_BASE_CLASS_BRIDGE 0x06 -- cgit v1.2.3 From 2d24dd5798d0474d9bf705bfca8725e7d20f9d54 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 29 Apr 2020 17:03:22 +0200 Subject: rbtree: Add generic add and find helpers I've always been bothered by the endless (fragile) boilerplate for rbtree, and I recently wrote some rbtree helpers for objtool and figured I should lift them into the kernel and use them more widely. Provide: partial-order; less() based: - rb_add(): add a new entry to the rbtree - rb_add_cached(): like rb_add(), but for a rb_root_cached total-order; cmp() based: - rb_find(): find an entry in an rbtree - rb_find_add(): find an entry, and add if not found - rb_find_first(): find the first (leftmost) matching entry - rb_next_match(): continue from rb_find_first() - rb_for_each(): iterate a sub-tree using the previous two Inlining and constant propagation should see the compiler inline the whole thing, including the various compare functions. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Reviewed-by: Michel Lespinasse Acked-by: Davidlohr Bueso --- include/linux/rbtree.h | 190 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 190 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h index d7db17996322..e0b300de8f3f 100644 --- a/include/linux/rbtree.h +++ b/include/linux/rbtree.h @@ -158,4 +158,194 @@ static inline void rb_replace_node_cached(struct rb_node *victim, rb_replace_node(victim, new, &root->rb_root); } +/* + * The below helper functions use 2 operators with 3 different + * calling conventions. The operators are related like: + * + * comp(a->key,b) < 0 := less(a,b) + * comp(a->key,b) > 0 := less(b,a) + * comp(a->key,b) == 0 := !less(a,b) && !less(b,a) + * + * If these operators define a partial order on the elements we make no + * guarantee on which of the elements matching the key is found. See + * rb_find(). + * + * The reason for this is to allow the find() interface without requiring an + * on-stack dummy object, which might not be feasible due to object size. + */ + +/** + * rb_add_cached() - insert @node into the leftmost cached tree @tree + * @node: node to insert + * @tree: leftmost cached tree to insert @node into + * @less: operator defining the (partial) node order + */ +static __always_inline void +rb_add_cached(struct rb_node *node, struct rb_root_cached *tree, + bool (*less)(struct rb_node *, const struct rb_node *)) +{ + struct rb_node **link = &tree->rb_root.rb_node; + struct rb_node *parent = NULL; + bool leftmost = true; + + while (*link) { + parent = *link; + if (less(node, parent)) { + link = &parent->rb_left; + } else { + link = &parent->rb_right; + leftmost = false; + } + } + + rb_link_node(node, parent, link); + rb_insert_color_cached(node, tree, leftmost); +} + +/** + * rb_add() - insert @node into @tree + * @node: node to insert + * @tree: tree to insert @node into + * @less: operator defining the (partial) node order + */ +static __always_inline void +rb_add(struct rb_node *node, struct rb_root *tree, + bool (*less)(struct rb_node *, const struct rb_node *)) +{ + struct rb_node **link = &tree->rb_node; + struct rb_node *parent = NULL; + + while (*link) { + parent = *link; + if (less(node, parent)) + link = &parent->rb_left; + else + link = &parent->rb_right; + } + + rb_link_node(node, parent, link); + rb_insert_color(node, tree); +} + +/** + * rb_find_add() - find equivalent @node in @tree, or add @node + * @node: node to look-for / insert + * @tree: tree to search / modify + * @cmp: operator defining the node order + * + * Returns the rb_node matching @node, or NULL when no match is found and @node + * is inserted. + */ +static __always_inline struct rb_node * +rb_find_add(struct rb_node *node, struct rb_root *tree, + int (*cmp)(struct rb_node *, const struct rb_node *)) +{ + struct rb_node **link = &tree->rb_node; + struct rb_node *parent = NULL; + int c; + + while (*link) { + parent = *link; + c = cmp(node, parent); + + if (c < 0) + link = &parent->rb_left; + else if (c > 0) + link = &parent->rb_right; + else + return parent; + } + + rb_link_node(node, parent, link); + rb_insert_color(node, tree); + return NULL; +} + +/** + * rb_find() - find @key in tree @tree + * @key: key to match + * @tree: tree to search + * @cmp: operator defining the node order + * + * Returns the rb_node matching @key or NULL. + */ +static __always_inline struct rb_node * +rb_find(const void *key, const struct rb_root *tree, + int (*cmp)(const void *key, const struct rb_node *)) +{ + struct rb_node *node = tree->rb_node; + + while (node) { + int c = cmp(key, node); + + if (c < 0) + node = node->rb_left; + else if (c > 0) + node = node->rb_right; + else + return node; + } + + return NULL; +} + +/** + * rb_find_first() - find the first @key in @tree + * @key: key to match + * @tree: tree to search + * @cmp: operator defining node order + * + * Returns the leftmost node matching @key, or NULL. + */ +static __always_inline struct rb_node * +rb_find_first(const void *key, const struct rb_root *tree, + int (*cmp)(const void *key, const struct rb_node *)) +{ + struct rb_node *node = tree->rb_node; + struct rb_node *match = NULL; + + while (node) { + int c = cmp(key, node); + + if (c <= 0) { + if (!c) + match = node; + node = node->rb_left; + } else if (c > 0) { + node = node->rb_right; + } + } + + return match; +} + +/** + * rb_next_match() - find the next @key in @tree + * @key: key to match + * @tree: tree to search + * @cmp: operator defining node order + * + * Returns the next node matching @key, or NULL. + */ +static __always_inline struct rb_node * +rb_next_match(const void *key, struct rb_node *node, + int (*cmp)(const void *key, const struct rb_node *)) +{ + node = rb_next(node); + if (node && cmp(key, node)) + node = NULL; + return node; +} + +/** + * rb_for_each() - iterates a subtree matching @key + * @node: iterator + * @key: key to match + * @tree: tree to search + * @cmp: operator defining node order + */ +#define rb_for_each(node, key, tree, cmp) \ + for ((node) = rb_find_first((key), (tree), (cmp)); \ + (node); (node) = rb_next_match((key), (node), (cmp))) + #endif /* _LINUX_RBTREE_H */ -- cgit v1.2.3 From 8ecca39483ed4e4e97096d0d6f8e25fdd323b189 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 29 Apr 2020 17:04:41 +0200 Subject: rbtree, sched/deadline: Use rb_add_cached() Reduce rbtree boiler plate by using the new helpers. Make rb_add_cached() / rb_erase_cached() return a pointer to the leftmost node to aid in updating additional state. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Acked-by: Davidlohr Bueso --- include/linux/rbtree.h | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h index e0b300de8f3f..d31ecaf4fdd3 100644 --- a/include/linux/rbtree.h +++ b/include/linux/rbtree.h @@ -141,12 +141,18 @@ static inline void rb_insert_color_cached(struct rb_node *node, rb_insert_color(node, &root->rb_root); } -static inline void rb_erase_cached(struct rb_node *node, - struct rb_root_cached *root) + +static inline struct rb_node * +rb_erase_cached(struct rb_node *node, struct rb_root_cached *root) { + struct rb_node *leftmost = NULL; + if (root->rb_leftmost == node) - root->rb_leftmost = rb_next(node); + leftmost = root->rb_leftmost = rb_next(node); + rb_erase(node, &root->rb_root); + + return leftmost; } static inline void rb_replace_node_cached(struct rb_node *victim, @@ -179,8 +185,10 @@ static inline void rb_replace_node_cached(struct rb_node *victim, * @node: node to insert * @tree: leftmost cached tree to insert @node into * @less: operator defining the (partial) node order + * + * Returns @node when it is the new leftmost, or NULL. */ -static __always_inline void +static __always_inline struct rb_node * rb_add_cached(struct rb_node *node, struct rb_root_cached *tree, bool (*less)(struct rb_node *, const struct rb_node *)) { @@ -200,6 +208,8 @@ rb_add_cached(struct rb_node *node, struct rb_root_cached *tree, rb_link_node(node, parent, link); rb_insert_color_cached(node, tree, leftmost); + + return leftmost ? node : NULL; } /** -- cgit v1.2.3 From a3b89864554bbce1594b7abdb5739fc708c1ca95 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 29 Apr 2020 17:05:15 +0200 Subject: rbtree, perf: Use new rbtree helpers Reduce rbtree boiler plate by using the new helpers. One noteworthy change is unification of the various (partial) compare functions. We construct a subtree match by forcing the sub-order to always match, see __group_cmp(). Due to 'const' we had to touch cgroup_id(). Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Acked-by: Tejun Heo Acked-by: Davidlohr Bueso --- include/linux/cgroup.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 451c2d26a5db..4f2f79de083e 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -307,7 +307,7 @@ void css_task_iter_end(struct css_task_iter *it); * Inline functions. */ -static inline u64 cgroup_id(struct cgroup *cgrp) +static inline u64 cgroup_id(const struct cgroup *cgrp) { return cgrp->kn->id; } @@ -701,7 +701,7 @@ void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen); struct cgroup_subsys_state; struct cgroup; -static inline u64 cgroup_id(struct cgroup *cgrp) { return 1; } +static inline u64 cgroup_id(const struct cgroup *cgrp) { return 1; } static inline void css_get(struct cgroup_subsys_state *css) {} static inline void css_put(struct cgroup_subsys_state *css) {} static inline int cgroup_attach_task_all(struct task_struct *from, -- cgit v1.2.3 From ae18ad281e825993d190073d0ae2ea35dee27ee1 Mon Sep 17 00:00:00 2001 From: Dietmar Eggemann Date: Thu, 28 Jan 2021 14:10:38 +0100 Subject: sched: Remove MAX_USER_RT_PRIO Commit d46523ea32a7 ("[PATCH] fix MAX_USER_RT_PRIO and MAX_RT_PRIO") was introduced due to a a small time period in which the realtime patch set was using different values for MAX_USER_RT_PRIO and MAX_RT_PRIO. This is no longer true, i.e. now MAX_RT_PRIO == MAX_USER_RT_PRIO. Get rid of MAX_USER_RT_PRIO and make everything use MAX_RT_PRIO instead. Signed-off-by: Dietmar Eggemann Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lkml.kernel.org/r/20210128131040.296856-2-dietmar.eggemann@arm.com --- include/linux/sched/prio.h | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/prio.h b/include/linux/sched/prio.h index 7d64feafc408..d111f2fd77ea 100644 --- a/include/linux/sched/prio.h +++ b/include/linux/sched/prio.h @@ -11,16 +11,9 @@ * priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL/SCHED_BATCH * tasks are in the range MAX_RT_PRIO..MAX_PRIO-1. Priority * values are inverted: lower p->prio value means higher priority. - * - * The MAX_USER_RT_PRIO value allows the actual maximum - * RT priority to be separate from the value exported to - * user-space. This allows kernel threads to set their - * priority to a value higher than any user task. Note: - * MAX_RT_PRIO must not be smaller than MAX_USER_RT_PRIO. */ -#define MAX_USER_RT_PRIO 100 -#define MAX_RT_PRIO MAX_USER_RT_PRIO +#define MAX_RT_PRIO 100 #define MAX_PRIO (MAX_RT_PRIO + NICE_WIDTH) #define DEFAULT_PRIO (MAX_RT_PRIO + NICE_WIDTH / 2) -- cgit v1.2.3 From 9d061ba6bc170045857f3efe0bba5def30188d4d Mon Sep 17 00:00:00 2001 From: Dietmar Eggemann Date: Thu, 28 Jan 2021 14:10:39 +0100 Subject: sched: Remove USER_PRIO, TASK_USER_PRIO and MAX_USER_PRIO The only remaining use of MAX_USER_PRIO (and USER_PRIO) is the SCALE_PRIO() definition in the PowerPC Cell architecture's Synergistic Processor Unit (SPU) scheduler. TASK_USER_PRIO isn't used anymore. Commit fe443ef2ac42 ("[POWERPC] spusched: Dynamic timeslicing for SCHED_OTHER") copied SCALE_PRIO() from the task scheduler in v2.6.23. Commit a4ec24b48dde ("sched: tidy up SCHED_RR") removed it from the task scheduler in v2.6.24. Commit 3ee237dddcd8 ("sched/prio: Add 3 macros of MAX_NICE, MIN_NICE and NICE_WIDTH in prio.h") introduced NICE_WIDTH much later. With: MAX_USER_PRIO = USER_PRIO(MAX_PRIO) = MAX_PRIO - MAX_RT_PRIO MAX_PRIO = MAX_RT_PRIO + NICE_WIDTH MAX_USER_PRIO = MAX_RT_PRIO + NICE_WIDTH - MAX_RT_PRIO MAX_USER_PRIO = NICE_WIDTH MAX_USER_PRIO can be replaced by NICE_WIDTH to be able to remove all the {*_}USER_PRIO defines. Signed-off-by: Dietmar Eggemann Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lkml.kernel.org/r/20210128131040.296856-3-dietmar.eggemann@arm.com --- include/linux/sched/prio.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/prio.h b/include/linux/sched/prio.h index d111f2fd77ea..ab83d85e1183 100644 --- a/include/linux/sched/prio.h +++ b/include/linux/sched/prio.h @@ -26,15 +26,6 @@ #define NICE_TO_PRIO(nice) ((nice) + DEFAULT_PRIO) #define PRIO_TO_NICE(prio) ((prio) - DEFAULT_PRIO) -/* - * 'User priority' is the nice value converted to something we - * can work with better when scaling various scheduler parameters, - * it's a [ 0 ... 39 ] range. - */ -#define USER_PRIO(p) ((p)-MAX_RT_PRIO) -#define TASK_USER_PRIO(p) USER_PRIO((p)->static_prio) -#define MAX_USER_PRIO (USER_PRIO(MAX_PRIO)) - /* * Convert nice value [19,-20] to rlimit style value [1,40]. */ -- cgit v1.2.3 From 880cfed3a012d7863f42251791cea7fe78c39390 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 18 Jan 2021 15:12:18 +0100 Subject: static_call: Pull some static_call declarations to the type headers Some static call declarations are going to be needed on low level header files. Move the necessary material to the dedicated static call types header to avoid inclusion dependency hell. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lkml.kernel.org/r/20210118141223.123667-4-frederic@kernel.org --- include/linux/static_call.h | 21 --------------------- include/linux/static_call_types.h | 27 +++++++++++++++++++++++++++ 2 files changed, 27 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/static_call.h b/include/linux/static_call.h index 695da4c9b338..a2c064585c03 100644 --- a/include/linux/static_call.h +++ b/include/linux/static_call.h @@ -107,26 +107,10 @@ extern void arch_static_call_transform(void *site, void *tramp, void *func, bool #define STATIC_CALL_TRAMP_ADDR(name) &STATIC_CALL_TRAMP(name) -/* - * __ADDRESSABLE() is used to ensure the key symbol doesn't get stripped from - * the symbol table so that objtool can reference it when it generates the - * .static_call_sites section. - */ -#define __static_call(name) \ -({ \ - __ADDRESSABLE(STATIC_CALL_KEY(name)); \ - &STATIC_CALL_TRAMP(name); \ -}) - #else #define STATIC_CALL_TRAMP_ADDR(name) NULL #endif - -#define DECLARE_STATIC_CALL(name, func) \ - extern struct static_call_key STATIC_CALL_KEY(name); \ - extern typeof(func) STATIC_CALL_TRAMP(name); - #define static_call_update(name, func) \ ({ \ BUILD_BUG_ON(!__same_type(*(func), STATIC_CALL_TRAMP(name))); \ @@ -174,7 +158,6 @@ extern int static_call_text_reserved(void *start, void *end); }; \ ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) -#define static_call(name) __static_call(name) #define static_call_cond(name) (void)__static_call(name) #define EXPORT_STATIC_CALL(name) \ @@ -207,7 +190,6 @@ struct static_call_key { }; \ ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) -#define static_call(name) __static_call(name) #define static_call_cond(name) (void)__static_call(name) static inline @@ -252,9 +234,6 @@ struct static_call_key { .func = NULL, \ } -#define static_call(name) \ - ((typeof(STATIC_CALL_TRAMP(name))*)(STATIC_CALL_KEY(name).func)) - static inline void __static_call_nop(void) { } /* diff --git a/include/linux/static_call_types.h b/include/linux/static_call_types.h index 89135bb35bf7..08f78b1b88b4 100644 --- a/include/linux/static_call_types.h +++ b/include/linux/static_call_types.h @@ -4,6 +4,7 @@ #include #include +#include #define STATIC_CALL_KEY_PREFIX __SCK__ #define STATIC_CALL_KEY_PREFIX_STR __stringify(STATIC_CALL_KEY_PREFIX) @@ -32,4 +33,30 @@ struct static_call_site { s32 key; }; +#define DECLARE_STATIC_CALL(name, func) \ + extern struct static_call_key STATIC_CALL_KEY(name); \ + extern typeof(func) STATIC_CALL_TRAMP(name); + +#ifdef CONFIG_HAVE_STATIC_CALL + +/* + * __ADDRESSABLE() is used to ensure the key symbol doesn't get stripped from + * the symbol table so that objtool can reference it when it generates the + * .static_call_sites section. + */ +#define __static_call(name) \ +({ \ + __ADDRESSABLE(STATIC_CALL_KEY(name)); \ + &STATIC_CALL_TRAMP(name); \ +}) + +#define static_call(name) __static_call(name) + +#else + +#define static_call(name) \ + ((typeof(STATIC_CALL_TRAMP(name))*)(STATIC_CALL_KEY(name).func)) + +#endif /* CONFIG_HAVE_STATIC_CALL */ + #endif /* _STATIC_CALL_TYPES_H */ -- cgit v1.2.3 From 3f2a8fc4b15de18644e8a80a09edda168676e22c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 18 Jan 2021 15:12:16 +0100 Subject: static_call/x86: Add __static_call_return0() Provide a stub function that return 0 and wire up the static call site patching to replace the CALL with a single 5 byte instruction that clears %RAX, the return value register. The function can be cast to any function pointer type that has a single %RAX return (including pointers). Also provide a version that returns an int for convenience. We are clearing the entire %RAX register in any case, whether the return value is 32 or 64 bits, since %RAX is always a scratch register anyway. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lkml.kernel.org/r/20210118141223.123667-2-frederic@kernel.org --- include/linux/static_call.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/static_call.h b/include/linux/static_call.h index a2c064585c03..bd6735d10e2e 100644 --- a/include/linux/static_call.h +++ b/include/linux/static_call.h @@ -142,6 +142,8 @@ extern void __static_call_update(struct static_call_key *key, void *tramp, void extern int static_call_mod_init(struct module *mod); extern int static_call_text_reserved(void *start, void *end); +extern long __static_call_return0(void); + #define DEFINE_STATIC_CALL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ struct static_call_key STATIC_CALL_KEY(name) = { \ @@ -206,6 +208,11 @@ static inline int static_call_text_reserved(void *start, void *end) return 0; } +static inline long __static_call_return0(void) +{ + return 0; +} + #define EXPORT_STATIC_CALL(name) \ EXPORT_SYMBOL(STATIC_CALL_KEY(name)); \ EXPORT_SYMBOL(STATIC_CALL_TRAMP(name)) @@ -222,6 +229,11 @@ struct static_call_key { void *func; }; +static inline long __static_call_return0(void) +{ + return 0; +} + #define DEFINE_STATIC_CALL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ struct static_call_key STATIC_CALL_KEY(name) = { \ -- cgit v1.2.3 From 29fd01944b7273bb630c649a2104b7f9e4ef3fa6 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Mon, 18 Jan 2021 15:12:17 +0100 Subject: static_call: Provide DEFINE_STATIC_CALL_RET0() DECLARE_STATIC_CALL() must pass the original function targeted for a given static call. But DEFINE_STATIC_CALL() may want to initialize it as off. In this case we can't pass NULL (for functions without return value) or __static_call_return0 (for functions returning a value) directly to DEFINE_STATIC_CALL() as that may trigger a static call redeclaration with a different function prototype. Type casts neither can work around that as they don't get along with typeof(). The proper way to do that for functions that don't return a value is to use DEFINE_STATIC_CALL_NULL(). But functions returning a actual value don't have an equivalent yet. Provide DEFINE_STATIC_CALL_RET0() to solve this situation. Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lkml.kernel.org/r/20210118141223.123667-3-frederic@kernel.org --- include/linux/static_call.h | 22 ++++++++++++++-------- 1 file changed, 14 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/static_call.h b/include/linux/static_call.h index bd6735d10e2e..d69dd8b976ca 100644 --- a/include/linux/static_call.h +++ b/include/linux/static_call.h @@ -144,13 +144,13 @@ extern int static_call_text_reserved(void *start, void *end); extern long __static_call_return0(void); -#define DEFINE_STATIC_CALL(name, _func) \ +#define __DEFINE_STATIC_CALL(name, _func, _func_init) \ DECLARE_STATIC_CALL(name, _func); \ struct static_call_key STATIC_CALL_KEY(name) = { \ - .func = _func, \ + .func = _func_init, \ .type = 1, \ }; \ - ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func) + ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func_init) #define DEFINE_STATIC_CALL_NULL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ @@ -178,12 +178,12 @@ struct static_call_key { void *func; }; -#define DEFINE_STATIC_CALL(name, _func) \ +#define __DEFINE_STATIC_CALL(name, _func, _func_init) \ DECLARE_STATIC_CALL(name, _func); \ struct static_call_key STATIC_CALL_KEY(name) = { \ - .func = _func, \ + .func = _func_init, \ }; \ - ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func) + ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func_init) #define DEFINE_STATIC_CALL_NULL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ @@ -234,10 +234,10 @@ static inline long __static_call_return0(void) return 0; } -#define DEFINE_STATIC_CALL(name, _func) \ +#define __DEFINE_STATIC_CALL(name, _func, _func_init) \ DECLARE_STATIC_CALL(name, _func); \ struct static_call_key STATIC_CALL_KEY(name) = { \ - .func = _func, \ + .func = _func_init, \ } #define DEFINE_STATIC_CALL_NULL(name, _func) \ @@ -286,4 +286,10 @@ static inline int static_call_text_reserved(void *start, void *end) #endif /* CONFIG_HAVE_STATIC_CALL */ +#define DEFINE_STATIC_CALL(name, _func) \ + __DEFINE_STATIC_CALL(name, _func, _func) + +#define DEFINE_STATIC_CALL_RET0(name, _func) \ + __DEFINE_STATIC_CALL(name, _func, __static_call_return0) + #endif /* _LINUX_STATIC_CALL_H */ -- cgit v1.2.3 From b965f1ddb47daa5b8b2e2bc9c921431236830367 Mon Sep 17 00:00:00 2001 From: "Peter Zijlstra (Intel)" Date: Mon, 18 Jan 2021 15:12:20 +0100 Subject: preempt/dynamic: Provide cond_resched() and might_resched() static calls Provide static calls to control cond_resched() (called in !CONFIG_PREEMPT) and might_resched() (called in CONFIG_PREEMPT_VOLUNTARY) to that we can override their behaviour when preempt= is overriden. Since the default behaviour is full preemption, both their calls are ignored when preempt= isn't passed. [fweisbec: branch might_resched() directly to __cond_resched(), only define static calls when PREEMPT_DYNAMIC] Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lkml.kernel.org/r/20210118141223.123667-6-frederic@kernel.org --- include/linux/kernel.h | 23 +++++++++++++++++++---- include/linux/sched.h | 27 ++++++++++++++++++++++++--- 2 files changed, 43 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index f7902d8c1048..cfd3d349f905 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -15,7 +15,7 @@ #include #include #include - +#include #include #include @@ -81,11 +81,26 @@ struct pt_regs; struct user; #ifdef CONFIG_PREEMPT_VOLUNTARY -extern int _cond_resched(void); -# define might_resched() _cond_resched() + +extern int __cond_resched(void); +# define might_resched() __cond_resched() + +#elif defined(CONFIG_PREEMPT_DYNAMIC) + +extern int __cond_resched(void); + +DECLARE_STATIC_CALL(might_resched, __cond_resched); + +static __always_inline void might_resched(void) +{ + static_call(might_resched)(); +} + #else + # define might_resched() do { } while (0) -#endif + +#endif /* CONFIG_PREEMPT_* */ #ifdef CONFIG_DEBUG_ATOMIC_SLEEP extern void ___might_sleep(const char *file, int line, int preempt_offset); diff --git a/include/linux/sched.h b/include/linux/sched.h index e1152227bb79..2f35594b8b53 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1871,11 +1871,32 @@ static inline int test_tsk_need_resched(struct task_struct *tsk) * value indicates whether a reschedule was done in fact. * cond_resched_lock() will drop the spinlock before scheduling, */ -#ifndef CONFIG_PREEMPTION -extern int _cond_resched(void); +#if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC) +extern int __cond_resched(void); + +#ifdef CONFIG_PREEMPT_DYNAMIC + +DECLARE_STATIC_CALL(cond_resched, __cond_resched); + +static __always_inline int _cond_resched(void) +{ + return static_call(cond_resched)(); +} + #else + +static inline int _cond_resched(void) +{ + return __cond_resched(); +} + +#endif /* CONFIG_PREEMPT_DYNAMIC */ + +#else + static inline int _cond_resched(void) { return 0; } -#endif + +#endif /* !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC) */ #define cond_resched() ({ \ ___might_sleep(__FILE__, __LINE__, 0); \ -- cgit v1.2.3 From 40607ee97e4eec5655cc0f76a720bdc4c63a6434 Mon Sep 17 00:00:00 2001 From: "Peter Zijlstra (Intel)" Date: Mon, 18 Jan 2021 15:12:22 +0100 Subject: preempt/dynamic: Provide irqentry_exit_cond_resched() static call Provide static call to control IRQ preemption (called in CONFIG_PREEMPT) so that we can override its behaviour when preempt= is overriden. Since the default behaviour is full preemption, its call is initialized to provide IRQ preemption when preempt= isn't passed. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lkml.kernel.org/r/20210118141223.123667-8-frederic@kernel.org --- include/linux/entry-common.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index a104b298019a..883acef895bc 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -2,6 +2,7 @@ #ifndef __LINUX_ENTRYCOMMON_H #define __LINUX_ENTRYCOMMON_H +#include #include #include #include @@ -454,6 +455,9 @@ irqentry_state_t noinstr irqentry_enter(struct pt_regs *regs); * Conditional reschedule with additional sanity checks. */ void irqentry_exit_cond_resched(void); +#ifdef CONFIG_PREEMPT_DYNAMIC +DECLARE_STATIC_CALL(irqentry_exit_cond_resched, irqentry_exit_cond_resched); +#endif /** * irqentry_exit - Handle return from exception that used irqentry_enter() -- cgit v1.2.3 From 73f44fe19d359635a607e8e8daa0da4001c1cfc2 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 27 Jan 2021 17:18:37 -0600 Subject: static_call: Allow module use without exposing static_call_key When exporting static_call_key; with EXPORT_STATIC_CALL*(), the module can use static_call_update() to change the function called. This is not desirable in general. Not exporting static_call_key however also disallows usage of static_call(), since objtool needs the key to construct the static_call_site. Solve this by allowing objtool to create the static_call_site using the trampoline address when it builds a module and cannot find the static_call_key symbol. The module loader will then try and map the trampole back to a key before it constructs the normal sites list. Doing this requires a trampoline -> key associsation, so add another magic section that keeps those. Originally-by: Peter Zijlstra (Intel) Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lkml.kernel.org/r/20210127231837.ifddpn7rhwdaepiu@treble --- include/linux/static_call.h | 22 ++++++++++++++++++++-- include/linux/static_call_types.h | 27 +++++++++++++++++++++++++-- 2 files changed, 45 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/static_call.h b/include/linux/static_call.h index d69dd8b976ca..85ecc789f4ff 100644 --- a/include/linux/static_call.h +++ b/include/linux/static_call.h @@ -138,6 +138,12 @@ struct static_call_key { }; }; +/* For finding the key associated with a trampoline */ +struct static_call_tramp_key { + s32 tramp; + s32 key; +}; + extern void __static_call_update(struct static_call_key *key, void *tramp, void *func); extern int static_call_mod_init(struct module *mod); extern int static_call_text_reserved(void *start, void *end); @@ -165,11 +171,18 @@ extern long __static_call_return0(void); #define EXPORT_STATIC_CALL(name) \ EXPORT_SYMBOL(STATIC_CALL_KEY(name)); \ EXPORT_SYMBOL(STATIC_CALL_TRAMP(name)) - #define EXPORT_STATIC_CALL_GPL(name) \ EXPORT_SYMBOL_GPL(STATIC_CALL_KEY(name)); \ EXPORT_SYMBOL_GPL(STATIC_CALL_TRAMP(name)) +/* Leave the key unexported, so modules can't change static call targets: */ +#define EXPORT_STATIC_CALL_TRAMP(name) \ + EXPORT_SYMBOL(STATIC_CALL_TRAMP(name)); \ + ARCH_ADD_TRAMP_KEY(name) +#define EXPORT_STATIC_CALL_TRAMP_GPL(name) \ + EXPORT_SYMBOL_GPL(STATIC_CALL_TRAMP(name)); \ + ARCH_ADD_TRAMP_KEY(name) + #elif defined(CONFIG_HAVE_STATIC_CALL) static inline int static_call_init(void) { return 0; } @@ -216,11 +229,16 @@ static inline long __static_call_return0(void) #define EXPORT_STATIC_CALL(name) \ EXPORT_SYMBOL(STATIC_CALL_KEY(name)); \ EXPORT_SYMBOL(STATIC_CALL_TRAMP(name)) - #define EXPORT_STATIC_CALL_GPL(name) \ EXPORT_SYMBOL_GPL(STATIC_CALL_KEY(name)); \ EXPORT_SYMBOL_GPL(STATIC_CALL_TRAMP(name)) +/* Leave the key unexported, so modules can't change static call targets: */ +#define EXPORT_STATIC_CALL_TRAMP(name) \ + EXPORT_SYMBOL(STATIC_CALL_TRAMP(name)) +#define EXPORT_STATIC_CALL_TRAMP_GPL(name) \ + EXPORT_SYMBOL_GPL(STATIC_CALL_TRAMP(name)) + #else /* Generic implementation */ static inline int static_call_init(void) { return 0; } diff --git a/include/linux/static_call_types.h b/include/linux/static_call_types.h index 08f78b1b88b4..ae5662d368b9 100644 --- a/include/linux/static_call_types.h +++ b/include/linux/static_call_types.h @@ -10,6 +10,7 @@ #define STATIC_CALL_KEY_PREFIX_STR __stringify(STATIC_CALL_KEY_PREFIX) #define STATIC_CALL_KEY_PREFIX_LEN (sizeof(STATIC_CALL_KEY_PREFIX_STR) - 1) #define STATIC_CALL_KEY(name) __PASTE(STATIC_CALL_KEY_PREFIX, name) +#define STATIC_CALL_KEY_STR(name) __stringify(STATIC_CALL_KEY(name)) #define STATIC_CALL_TRAMP_PREFIX __SCT__ #define STATIC_CALL_TRAMP_PREFIX_STR __stringify(STATIC_CALL_TRAMP_PREFIX) @@ -39,17 +40,39 @@ struct static_call_site { #ifdef CONFIG_HAVE_STATIC_CALL +#define __raw_static_call(name) (&STATIC_CALL_TRAMP(name)) + +#ifdef CONFIG_HAVE_STATIC_CALL_INLINE + /* * __ADDRESSABLE() is used to ensure the key symbol doesn't get stripped from * the symbol table so that objtool can reference it when it generates the * .static_call_sites section. */ +#define __STATIC_CALL_ADDRESSABLE(name) \ + __ADDRESSABLE(STATIC_CALL_KEY(name)) + #define __static_call(name) \ ({ \ - __ADDRESSABLE(STATIC_CALL_KEY(name)); \ - &STATIC_CALL_TRAMP(name); \ + __STATIC_CALL_ADDRESSABLE(name); \ + __raw_static_call(name); \ }) +#else /* !CONFIG_HAVE_STATIC_CALL_INLINE */ + +#define __STATIC_CALL_ADDRESSABLE(name) +#define __static_call(name) __raw_static_call(name) + +#endif /* CONFIG_HAVE_STATIC_CALL_INLINE */ + +#ifdef MODULE +#define __STATIC_CALL_MOD_ADDRESSABLE(name) +#define static_call_mod(name) __raw_static_call(name) +#else +#define __STATIC_CALL_MOD_ADDRESSABLE(name) __STATIC_CALL_ADDRESSABLE(name) +#define static_call_mod(name) __static_call(name) +#endif + #define static_call(name) __static_call(name) #else -- cgit v1.2.3 From ef72661e28c64ad610f89acc2832ec67b27ba438 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 25 Jan 2021 16:26:50 +0100 Subject: sched: Harden PREEMPT_DYNAMIC Use the new EXPORT_STATIC_CALL_TRAMP() / static_call_mod() to unexport the static_call_key for the PREEMPT_DYNAMIC calls such that modules can no longer update these calls. Having modules change/hi-jack the preemption calls would be horrible. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar --- include/linux/kernel.h | 2 +- include/linux/sched.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index cfd3d349f905..5b7ed6dc99ac 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -93,7 +93,7 @@ DECLARE_STATIC_CALL(might_resched, __cond_resched); static __always_inline void might_resched(void) { - static_call(might_resched)(); + static_call_mod(might_resched)(); } #else diff --git a/include/linux/sched.h b/include/linux/sched.h index 2f35594b8b53..4d568288abf9 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1880,7 +1880,7 @@ DECLARE_STATIC_CALL(cond_resched, __cond_resched); static __always_inline int _cond_resched(void) { - return static_call(cond_resched)(); + return static_call_mod(cond_resched)(); } #else -- cgit v1.2.3 From 43789ef3f7d61aa7bed0cb2764e588fc990c30ef Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Mon, 1 Feb 2021 00:05:45 +0100 Subject: rcu/nocb: Perform deferred wake up before last idle's need_resched() check Entering RCU idle mode may cause a deferred wake up of an RCU NOCB_GP kthread (rcuog) to be serviced. Usually a local wake up happening while running the idle task is handled in one of the need_resched() checks carefully placed within the idle loop that can break to the scheduler. Unfortunately the call to rcu_idle_enter() is already beyond the last generic need_resched() check and we may halt the CPU with a resched request unhandled, leaving the task hanging. Fix this with splitting the rcuog wakeup handling from rcu_idle_enter() and place it before the last generic need_resched() check in the idle loop. It is then assumed that no call to call_rcu() will be performed after that in the idle loop until the CPU is put in low power mode. Fixes: 96d3fd0d315a (rcu: Break call_rcu() deadlock involving scheduler and perf) Reported-by: Paul E. McKenney Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20210131230548.32970-3-frederic@kernel.org --- include/linux/rcupdate.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index fd02c5fa60cb..36c2119de702 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -110,8 +110,10 @@ static inline void rcu_user_exit(void) { } #ifdef CONFIG_RCU_NOCB_CPU void rcu_init_nohz(void); +void rcu_nocb_flush_deferred_wakeup(void); #else /* #ifdef CONFIG_RCU_NOCB_CPU */ static inline void rcu_init_nohz(void) { } +static inline void rcu_nocb_flush_deferred_wakeup(void) { } #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ /** -- cgit v1.2.3 From 4ae7dc97f726ea95c58ac58af71cc034ad22d7de Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Mon, 1 Feb 2021 00:05:48 +0100 Subject: entry/kvm: Explicitly flush pending rcuog wakeup before last rescheduling point Following the idle loop model, cleanly check for pending rcuog wakeup before the last rescheduling point upon resuming to guest mode. This way we can avoid to do it from rcu_user_enter() with the last resort self-IPI hack that enforces rescheduling. Suggested-by: Peter Zijlstra Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20210131230548.32970-6-frederic@kernel.org --- include/linux/entry-kvm.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/entry-kvm.h b/include/linux/entry-kvm.h index 9b93f8584ff7..8b2b1d68b954 100644 --- a/include/linux/entry-kvm.h +++ b/include/linux/entry-kvm.h @@ -46,6 +46,20 @@ static inline int arch_xfer_to_guest_mode_handle_work(struct kvm_vcpu *vcpu, */ int xfer_to_guest_mode_handle_work(struct kvm_vcpu *vcpu); +/** + * xfer_to_guest_mode_prepare - Perform last minute preparation work that + * need to be handled while IRQs are disabled + * upon entering to guest. + * + * Has to be invoked with interrupts disabled before the last call + * to xfer_to_guest_mode_work_pending(). + */ +static inline void xfer_to_guest_mode_prepare(void) +{ + lockdep_assert_irqs_disabled(); + rcu_nocb_flush_deferred_wakeup(); +} + /** * __xfer_to_guest_mode_work_pending - Check if work is pending * -- cgit v1.2.3 From 96313e1db8e5629cc2217616dca78f03e6463008 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Wed, 17 Feb 2021 12:25:57 -0800 Subject: net: mdio: Remove of_phy_attach() We have no in-tree users, also update the sfp-phylink.rst documentation to indicate that phy_attach_direct() is used instead of of_phy_attach(). Signed-off-by: Florian Fainelli Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/of_mdio.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index cfe8c607a628..2b05e7f7c238 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -26,9 +26,6 @@ of_phy_connect(struct net_device *dev, struct device_node *phy_np, struct phy_device * of_phy_get_and_connect(struct net_device *dev, struct device_node *np, void (*hndlr)(struct net_device *)); -struct phy_device * -of_phy_attach(struct net_device *dev, struct device_node *phy_np, - u32 flags, phy_interface_t iface); struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np); int of_phy_register_fixed_link(struct device_node *np); @@ -100,13 +97,6 @@ of_phy_get_and_connect(struct net_device *dev, struct device_node *np, return NULL; } -static inline struct phy_device *of_phy_attach(struct net_device *dev, - struct device_node *phy_np, - u32 flags, phy_interface_t iface) -{ - return NULL; -} - static inline struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np) { return NULL; -- cgit v1.2.3 From 20e07e2c3cf310578ef19fb4f1e64dc9832abd9d Mon Sep 17 00:00:00 2001 From: Wong Vee Khee Date: Wed, 17 Feb 2021 17:57:05 +0800 Subject: net: stmmac: Add PCI bus info to ethtool driver query output This patch populates the PCI bus info in the ethtool driver query data. Users will be able to view PCI bus info using 'ethtool -i '. Signed-off-by: Wong Vee Khee Signed-off-by: David S. Miller --- include/linux/stmmac.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 15ca6b4167cc..a302982de2d7 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -202,5 +202,6 @@ struct plat_stmmacenet_data { bool vlan_fail_q_en; u8 vlan_fail_q; unsigned int eee_usecs_rate; + struct pci_dev *pdev; }; #endif -- cgit v1.2.3 From fade5cad9339a627c5ad029e3577582b6292df03 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Fri, 15 Jan 2021 13:46:03 +0800 Subject: initrd: Add the preprocessor guard in initrd.h Add the preprocessor guard in initrd.h to prevent possible build error from the multiple inclusion of same header file multiple time. Signed-off-by: Kefeng Wang Signed-off-by: Palmer Dabbelt --- include/linux/initrd.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/initrd.h b/include/linux/initrd.h index 8db6f8c8030b..fc30ac30e10e 100644 --- a/include/linux/initrd.h +++ b/include/linux/initrd.h @@ -1,5 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_INITRD_H +#define __LINUX_INITRD_H + #define INITRD_MINOR 250 /* shouldn't collide with /dev/ram* too soon ... */ /* starting block # of image */ @@ -24,3 +27,5 @@ extern char __initramfs_start[]; extern unsigned long __initramfs_size; void console_on_rootfs(void); + +#endif /* __LINUX_INITRD_H */ -- cgit v1.2.3 From c72160fe05fb978ad859ba053c4462c2bb960b13 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Fri, 15 Jan 2021 13:46:04 +0800 Subject: initramfs: Provide a common initrd reserve function Some architectures(eg, ARM and riscv) have similar logic to check and reserve the memory of initrd, let's provide a common function reserve_initrd_mem() to reduce duplicated code. Signed-off-by: Kefeng Wang Signed-off-by: Palmer Dabbelt --- include/linux/initrd.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/initrd.h b/include/linux/initrd.h index fc30ac30e10e..85c15717af34 100644 --- a/include/linux/initrd.h +++ b/include/linux/initrd.h @@ -18,6 +18,12 @@ extern int initrd_below_start_ok; extern unsigned long initrd_start, initrd_end; extern void free_initrd_mem(unsigned long, unsigned long); +#ifdef CONFIG_BLK_DEV_INITRD +extern void __init reserve_initrd_mem(void); +#else +static inline void __init reserve_initrd_mem(void) {} +#endif + extern phys_addr_t phys_initrd_start; extern unsigned long phys_initrd_size; -- cgit v1.2.3 From af0bfab907a011e146304d20d81dddce4e4d62d0 Mon Sep 17 00:00:00 2001 From: Abanoub Sameh Date: Fri, 11 Dec 2020 22:42:08 +0200 Subject: leds: led-core: Get rid of enum led_brightness This gets rid of enum led_brightness in the main led files, because it is deprecated, and an unsigned int can be used instead. We can get rid of led_brightness completely and patches can also be supplied for the other drivers' files. Signed-off-by: Abanoub Sameh Signed-off-by: Pavel Machek --- include/linux/leds.h | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index 6a8d6409c993..329fd914cf24 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -63,8 +63,8 @@ struct led_hw_trigger_type { struct led_classdev { const char *name; - enum led_brightness brightness; - enum led_brightness max_brightness; + unsigned int brightness; + unsigned int max_brightness; int flags; /* Lower 16 bits reflect status */ @@ -253,8 +253,7 @@ void led_blink_set_oneshot(struct led_classdev *led_cdev, * software blink timer that implements blinking when the * hardware doesn't. This function is guaranteed not to sleep. */ -void led_set_brightness(struct led_classdev *led_cdev, - enum led_brightness brightness); +void led_set_brightness(struct led_classdev *led_cdev, unsigned int brightness); /** * led_set_brightness_sync - set LED brightness synchronously @@ -267,8 +266,7 @@ void led_set_brightness(struct led_classdev *led_cdev, * * Returns: 0 on success or negative error value on failure */ -int led_set_brightness_sync(struct led_classdev *led_cdev, - enum led_brightness value); +int led_set_brightness_sync(struct led_classdev *led_cdev, unsigned int value); /** * led_update_brightness - update LED brightness @@ -565,7 +563,7 @@ static inline void ledtrig_cpu(enum cpu_led_event evt) #ifdef CONFIG_LEDS_BRIGHTNESS_HW_CHANGED void led_classdev_notify_brightness_hw_changed( - struct led_classdev *led_cdev, enum led_brightness brightness); + struct led_classdev *led_cdev, unsigned int brightness); #else static inline void led_classdev_notify_brightness_hw_changed( struct led_classdev *led_cdev, enum led_brightness brightness) { } -- cgit v1.2.3 From 8e5c38a33c84935d66cfcf23c96960b6c4b484ef Mon Sep 17 00:00:00 2001 From: Gene Chen Date: Mon, 21 Dec 2020 18:45:50 +0800 Subject: leds: flash: Add flash registration with undefined CONFIG_LEDS_CLASS_FLASH Add flash registration with undefined CONFIG_LEDS_CLASS_FLASH, and move the same registration functions outside of #ifdef block. Signed-off-by: Gene Chen Acked-by: Jacek Anaszewski Signed-off-by: Pavel Machek --- include/linux/led-class-flash.h | 42 ++++++++++++++++++++++++++++++++--------- 1 file changed, 33 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/led-class-flash.h b/include/linux/led-class-flash.h index 21a3358a1731..612b4cab3819 100644 --- a/include/linux/led-class-flash.h +++ b/include/linux/led-class-flash.h @@ -85,6 +85,7 @@ static inline struct led_classdev_flash *lcdev_to_flcdev( return container_of(lcdev, struct led_classdev_flash, led_cdev); } +#if IS_ENABLED(CONFIG_LEDS_CLASS_FLASH) /** * led_classdev_flash_register_ext - register a new object of LED class with * init data and with support for flash LEDs @@ -98,12 +99,6 @@ int led_classdev_flash_register_ext(struct device *parent, struct led_classdev_flash *fled_cdev, struct led_init_data *init_data); -static inline int led_classdev_flash_register(struct device *parent, - struct led_classdev_flash *fled_cdev) -{ - return led_classdev_flash_register_ext(parent, fled_cdev, NULL); -} - /** * led_classdev_flash_unregister - unregisters an object of led_classdev class * with support for flash LEDs @@ -118,15 +113,44 @@ int devm_led_classdev_flash_register_ext(struct device *parent, struct led_init_data *init_data); +void devm_led_classdev_flash_unregister(struct device *parent, + struct led_classdev_flash *fled_cdev); + +#else + +static inline int led_classdev_flash_register_ext(struct device *parent, + struct led_classdev_flash *fled_cdev, + struct led_init_data *init_data) +{ + return 0; +} + +static inline void led_classdev_flash_unregister(struct led_classdev_flash *fled_cdev) {}; +static inline int devm_led_classdev_flash_register_ext(struct device *parent, + struct led_classdev_flash *fled_cdev, + struct led_init_data *init_data) +{ + return 0; +} + +static inline void devm_led_classdev_flash_unregister(struct device *parent, + struct led_classdev_flash *fled_cdev) +{}; + +#endif /* IS_ENABLED(CONFIG_LEDS_CLASS_FLASH) */ + +static inline int led_classdev_flash_register(struct device *parent, + struct led_classdev_flash *fled_cdev) +{ + return led_classdev_flash_register_ext(parent, fled_cdev, NULL); +} + static inline int devm_led_classdev_flash_register(struct device *parent, struct led_classdev_flash *fled_cdev) { return devm_led_classdev_flash_register_ext(parent, fled_cdev, NULL); } -void devm_led_classdev_flash_unregister(struct device *parent, - struct led_classdev_flash *fled_cdev); - /** * led_set_flash_strobe - setup flash strobe * @fled_cdev: the flash LED to set strobe on -- cgit v1.2.3 From 6039b7e87be0b350a5f8fc135adfb5d1f4ba66ad Mon Sep 17 00:00:00 2001 From: Gene Chen Date: Mon, 21 Dec 2020 18:45:51 +0800 Subject: leds: flash: Fix multicolor no-ops registration by return 0 Fix multicolor no-ops registration by return 0, and move the same registration functions outside of #ifdef block. Signed-off-by: Gene Chen Acked-by: Jacek Anaszewski Signed-off-by: Pavel Machek --- include/linux/led-class-multicolor.h | 42 +++++++++++++----------------------- 1 file changed, 15 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/led-class-multicolor.h b/include/linux/led-class-multicolor.h index 5116f9a866cc..210d57bcd767 100644 --- a/include/linux/led-class-multicolor.h +++ b/include/linux/led-class-multicolor.h @@ -44,12 +44,6 @@ int led_classdev_multicolor_register_ext(struct device *parent, struct led_classdev_mc *mcled_cdev, struct led_init_data *init_data); -static inline int led_classdev_multicolor_register(struct device *parent, - struct led_classdev_mc *mcled_cdev) -{ - return led_classdev_multicolor_register_ext(parent, mcled_cdev, NULL); -} - /** * led_classdev_multicolor_unregister - unregisters an object of led_classdev * class with support for multicolor LEDs @@ -68,13 +62,6 @@ int devm_led_classdev_multicolor_register_ext(struct device *parent, struct led_classdev_mc *mcled_cdev, struct led_init_data *init_data); -static inline int devm_led_classdev_multicolor_register(struct device *parent, - struct led_classdev_mc *mcled_cdev) -{ - return devm_led_classdev_multicolor_register_ext(parent, mcled_cdev, - NULL); -} - void devm_led_classdev_multicolor_unregister(struct device *parent, struct led_classdev_mc *mcled_cdev); #else @@ -83,27 +70,33 @@ static inline int led_classdev_multicolor_register_ext(struct device *parent, struct led_classdev_mc *mcled_cdev, struct led_init_data *init_data) { - return -EINVAL; -} - -static inline int led_classdev_multicolor_register(struct device *parent, - struct led_classdev_mc *mcled_cdev) -{ - return led_classdev_multicolor_register_ext(parent, mcled_cdev, NULL); + return 0; } static inline void led_classdev_multicolor_unregister(struct led_classdev_mc *mcled_cdev) {}; static inline int led_mc_calc_color_components(struct led_classdev_mc *mcled_cdev, enum led_brightness brightness) { - return -EINVAL; + return 0; } static inline int devm_led_classdev_multicolor_register_ext(struct device *parent, struct led_classdev_mc *mcled_cdev, struct led_init_data *init_data) { - return -EINVAL; + return 0; +} + +static inline void devm_led_classdev_multicolor_unregister(struct device *parent, + struct led_classdev_mc *mcled_cdev) +{}; + +#endif /* IS_ENABLED(CONFIG_LEDS_CLASS_MULTICOLOR) */ + +static inline int led_classdev_multicolor_register(struct device *parent, + struct led_classdev_mc *mcled_cdev) +{ + return led_classdev_multicolor_register_ext(parent, mcled_cdev, NULL); } static inline int devm_led_classdev_multicolor_register(struct device *parent, @@ -113,9 +106,4 @@ static inline int devm_led_classdev_multicolor_register(struct device *parent, NULL); } -static inline void devm_led_classdev_multicolor_unregister(struct device *parent, - struct led_classdev_mc *mcled_cdev) -{}; - -#endif /* IS_ENABLED(CONFIG_LEDS_CLASS_MULTICOLOR) */ #endif /* _LINUX_MULTICOLOR_LEDS_H_INCLUDED */ -- cgit v1.2.3 From 36950f2da1ea4cb683be174f6f581e25b2d33e71 Mon Sep 17 00:00:00 2001 From: Jianxiong Gao Date: Mon, 1 Feb 2021 10:30:15 -0800 Subject: driver core: add a min_align_mask field to struct device_dma_parameters Some devices rely on the address offset in a page to function correctly (NVMe driver as an example). These devices may use a different page size than the Linux kernel. The address offset has to be preserved upon mapping, and in order to do so, we need to record the page_offset_mask first. Signed-off-by: Jianxiong Gao Signed-off-by: Christoph Hellwig Acked-by: Greg Kroah-Hartman Signed-off-by: Konrad Rzeszutek Wilk --- include/linux/device.h | 1 + include/linux/dma-mapping.h | 16 ++++++++++++++++ 2 files changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 1779f90eeb4c..7960bf516dd7 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -291,6 +291,7 @@ struct device_dma_parameters { * sg limitations. */ unsigned int max_segment_size; + unsigned int min_align_mask; unsigned long segment_boundary_mask; }; diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 2e49996a8f39..9c26225754e7 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -500,6 +500,22 @@ static inline int dma_set_seg_boundary(struct device *dev, unsigned long mask) return -EIO; } +static inline unsigned int dma_get_min_align_mask(struct device *dev) +{ + if (dev->dma_parms) + return dev->dma_parms->min_align_mask; + return 0; +} + +static inline int dma_set_min_align_mask(struct device *dev, + unsigned int min_align_mask) +{ + if (WARN_ON_ONCE(!dev->dma_parms)) + return -EIO; + dev->dma_parms->min_align_mask = min_align_mask; + return 0; +} + static inline int dma_get_cache_alignment(void) { #ifdef ARCH_DMA_MINALIGN -- cgit v1.2.3 From b5d7ccb7aac3895c2138fe0980a109116ce15eff Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 5 Feb 2021 11:18:40 +0100 Subject: swiotlb: add a IO_TLB_SIZE define Add a new IO_TLB_SIZE define instead open coding it using IO_TLB_SHIFT all over. Signed-off-by: Christoph Hellwig Acked-by: Jianxiong Gao Tested-by: Jianxiong Gao Signed-off-by: Konrad Rzeszutek Wilk --- include/linux/swiotlb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index d9c9fc9ca5d2..5857a937c637 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -29,6 +29,7 @@ enum swiotlb_force { * controllable. */ #define IO_TLB_SHIFT 11 +#define IO_TLB_SIZE (1 << IO_TLB_SHIFT) /* default to 64MB */ #define IO_TLB_DEFAULT_SIZE (64UL<<20) -- cgit v1.2.3 From 5aa75ed5b93f086c455a3c67239b0471ff5a1526 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 16 Feb 2021 12:56:50 -0700 Subject: io_uring: tie async worker side to the task context Move it outside of the io_ring_ctx, and tie it to the io_uring task context. Signed-off-by: Jens Axboe --- include/linux/io_uring.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 2eb6d19de336..0e95398998b6 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -36,6 +36,7 @@ struct io_uring_task { struct xarray xa; struct wait_queue_head wait; struct file *last; + void *io_wq; struct percpu_counter inflight; struct io_identity __identity; struct io_identity *identity; -- cgit v1.2.3 From 3bfe6106693b6b4ba175ad1f929c4660b8f59ca8 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 16 Feb 2021 14:15:30 -0700 Subject: io-wq: fork worker threads from original task Instead of using regular kthread kernel threads, create kernel threads that are like a real thread that the task would create. This ensures that we get all the context that we need, without having to carry that state around. This greatly reduces the code complexity, and the risk of missing state for a given request type. With the move away from kthread, we can also dump everything related to assigned state to the new threads. Signed-off-by: Jens Axboe --- include/linux/sched.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 26f499810dfa..ef00bb22164c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -895,6 +895,9 @@ struct task_struct { /* CLONE_CHILD_CLEARTID: */ int __user *clear_child_tid; + /* PF_IO_WORKER */ + void *pf_io_worker; + u64 utime; u64 stime; #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME -- cgit v1.2.3 From 4379bf8bd70b5de6bba7d53015b0c36c57a634ee Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 15 Feb 2021 13:40:22 -0700 Subject: io_uring: remove io_identity We are no longer grabbing state, so no need to maintain an IO identity that we COW if there are changes. Signed-off-by: Jens Axboe --- include/linux/io_uring.h | 19 ------------------- 1 file changed, 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 0e95398998b6..c48fcbdc2ea8 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -5,23 +5,6 @@ #include #include -struct io_identity { - struct files_struct *files; - struct mm_struct *mm; -#ifdef CONFIG_BLK_CGROUP - struct cgroup_subsys_state *blkcg_css; -#endif - const struct cred *creds; - struct nsproxy *nsproxy; - struct fs_struct *fs; - unsigned long fsize; -#ifdef CONFIG_AUDIT - kuid_t loginuid; - unsigned int sessionid; -#endif - refcount_t count; -}; - struct io_wq_work_node { struct io_wq_work_node *next; }; @@ -38,8 +21,6 @@ struct io_uring_task { struct file *last; void *io_wq; struct percpu_counter inflight; - struct io_identity __identity; - struct io_identity *identity; atomic_t in_idle; bool sqpoll; -- cgit v1.2.3 From 2596b6ae412be3d29632efc63976a2132032e620 Mon Sep 17 00:00:00 2001 From: Pavel Tatashin Date: Fri, 19 Feb 2021 14:51:42 -0500 Subject: kexec: move machine_kexec_post_load() to public interface The kernel test robot reports the following compiler warning: | arch/arm64/kernel/machine_kexec.c:62:5: warning: no previous prototype for | function 'machine_kexec_post_load' [-Wmissing-prototypes] | int machine_kexec_post_load(struct kimage *kimage) Fix it by moving the declaration of machine_kexec_post_load() from kexec_internal.h to the public header instead. Reported-by: kernel test robot Link: https://lore.kernel.org/linux-arm-kernel/202102030727.gqTokACH-lkp@intel.com Signed-off-by: Pavel Tatashin Link: https://lore.kernel.org/r/20210219195142.13571-1-pasha.tatashin@soleen.com Fixes: 4c3c31230c91 ("arm64: kexec: move relocation function setup") Signed-off-by: Will Deacon --- include/linux/kexec.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 9e93bef52968..3671b845cf28 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -309,6 +309,8 @@ extern void machine_kexec_cleanup(struct kimage *image); extern int kernel_kexec(void); extern struct page *kimage_alloc_control_pages(struct kimage *image, unsigned int order); +int machine_kexec_post_load(struct kimage *image); + extern void __crash_kexec(struct pt_regs *); extern void crash_kexec(struct pt_regs *); int kexec_should_crash(struct task_struct *); -- cgit v1.2.3 From 9fb407179c6fd910005040bebb040094ef959b6c Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Sun, 21 Feb 2021 18:28:05 -0800 Subject: block: Remove unused blk_pm_*() function definitions Commit a1ce35fa4985 ("block: remove dead elevator code") removed the last callers of blk_pm_requeue_request(), blk_pm_add_request() and blk_pm_put_request(). Hence remove the definitions of these functions. Removing these functions removes all users of the struct request nr_pending member. Hence also remove 'nr_pending'. Note: 'nr_pending' is no longer used since commit 7cedffec8e75 ("block: Make blk_get_request() block for non-PM requests while suspended"). Cc: Alan Stern Cc: Christoph Hellwig Signed-off-by: Bart Van Assche Reviewed-by: Chaitanya Kulkarni Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 9149f4a5adb3..f2e0697258b8 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -462,7 +462,6 @@ struct request_queue { #ifdef CONFIG_PM struct device *dev; enum rpm_status rpm_status; - unsigned int nr_pending; #endif /* -- cgit v1.2.3 From 179d1600723670dc0d6ae8ce572e0e2c44b64763 Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Sun, 21 Feb 2021 21:29:55 -0800 Subject: block: remove superfluous param in blk_fill_rwbs() The last parameter for the function blk_fill_rwbs() was added in 5782138e47 ("tracing/events: convert block trace points to TRACE_EVENT()") in order to signal read request and use of that parameter was replaced with using switch case REQ_OP_READ with 1b9a9ab78b0 ("blktrace: use op accessors"), but the parameter was never removed. Remove the unused parameter and adjust the respective call sites. Fixes: 1b9a9ab78b0 ("blktrace: use op accessors") Signed-off-by: Chaitanya Kulkarni Reviewed-by: Johannes Thumshirn Reviewed-by: Damien Le Moal Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blktrace_api.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 05556573b896..11484f1d19a1 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -119,7 +119,7 @@ struct compat_blk_user_trace_setup { #endif -extern void blk_fill_rwbs(char *rwbs, unsigned int op, int bytes); +extern void blk_fill_rwbs(char *rwbs, unsigned int op); static inline sector_t blk_rq_trace_sector(struct request *rq) { -- cgit v1.2.3 From 1f83bb4b491472310ae7aeca505ed3725149906c Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Sun, 21 Feb 2021 21:29:56 -0800 Subject: blktrace: add blk_fill_rwbs documentation comment blk_fill_rwbs() is an expoted function, add kernel style documentation comment. Signed-off-by: Chaitanya Kulkarni Reviewed-by: Johannes Thumshirn Reviewed-by: Damien Le Moal Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blktrace_api.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 11484f1d19a1..e17d04abf6a3 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -119,7 +119,7 @@ struct compat_blk_user_trace_setup { #endif -extern void blk_fill_rwbs(char *rwbs, unsigned int op); +void blk_fill_rwbs(char *rwbs, unsigned int op); static inline sector_t blk_rq_trace_sector(struct request *rq) { -- cgit v1.2.3 From 4a42d848db9544e3108875390886dc490d9c101e Mon Sep 17 00:00:00 2001 From: David Stevens Date: Mon, 22 Feb 2021 11:45:22 +0900 Subject: KVM: x86/mmu: Consider the hva in mmu_notifier retry Track the range being invalidated by mmu_notifier and skip page fault retries if the fault address is not affected by the in-progress invalidation. Handle concurrent invalidations by finding the minimal range which includes all ranges being invalidated. Although the combined range may include unrelated addresses and cannot be shrunk as individual invalidation operations complete, it is unlikely the marginal gains of proper range tracking are worth the additional complexity. The primary benefit of this change is the reduction in the likelihood of extreme latency when handing a page fault due to another thread having been preempted while modifying host virtual addresses. Signed-off-by: David Stevens Message-Id: <20210222024522.1751719-3-stevensd@google.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 25 ++++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index e126ebda36d0..1b65e7204344 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -506,6 +507,8 @@ struct kvm { struct mmu_notifier mmu_notifier; unsigned long mmu_notifier_seq; long mmu_notifier_count; + unsigned long mmu_notifier_range_start; + unsigned long mmu_notifier_range_end; #endif long tlbs_dirty; struct list_head devices; @@ -733,7 +736,7 @@ kvm_pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn); kvm_pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn); kvm_pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, bool atomic, bool *async, bool write_fault, - bool *writable); + bool *writable, hva_t *hva); void kvm_release_pfn_clean(kvm_pfn_t pfn); void kvm_release_pfn_dirty(kvm_pfn_t pfn); @@ -1207,6 +1210,26 @@ static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq) return 1; return 0; } + +static inline int mmu_notifier_retry_hva(struct kvm *kvm, + unsigned long mmu_seq, + unsigned long hva) +{ + lockdep_assert_held(&kvm->mmu_lock); + /* + * If mmu_notifier_count is non-zero, then the range maintained by + * kvm_mmu_notifier_invalidate_range_start contains all addresses that + * might be being invalidated. Note that it may include some false + * positives, due to shortcuts when handing concurrent invalidations. + */ + if (unlikely(kvm->mmu_notifier_count) && + hva >= kvm->mmu_notifier_range_start && + hva < kvm->mmu_notifier_range_end) + return 1; + if (kvm->mmu_notifier_seq != mmu_seq) + return 1; + return 0; +} #endif #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING -- cgit v1.2.3 From fd70a406a344e084ac680c3f14e71d37d6023883 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Tue, 5 Jan 2021 12:31:59 +0200 Subject: vdpa: Extend routine to accept vdpa device name In a subsequent patch, when user initiated command creates a vdpa device, the user chooses the name of the vdpa device. To support it, extend the device allocation API to consider this name specified by the caller driver. Signed-off-by: Parav Pandit Reviewed-by: Eli Cohen Acked-by: Jason Wang Link: https://lore.kernel.org/r/20210105103203.82508-3-parav@nvidia.com Signed-off-by: Michael S. Tsirkin --- include/linux/vdpa.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 0fefeb976877..5700baa22356 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -245,15 +245,14 @@ struct vdpa_config_ops { struct vdpa_device *__vdpa_alloc_device(struct device *parent, const struct vdpa_config_ops *config, - int nvqs, - size_t size); + int nvqs, size_t size, const char *name); -#define vdpa_alloc_device(dev_struct, member, parent, config, nvqs) \ +#define vdpa_alloc_device(dev_struct, member, parent, config, nvqs, name) \ container_of(__vdpa_alloc_device( \ parent, config, nvqs, \ sizeof(dev_struct) + \ BUILD_BUG_ON_ZERO(offsetof( \ - dev_struct, member))), \ + dev_struct, member)), name), \ dev_struct, member) int vdpa_register_device(struct vdpa_device *vdev); -- cgit v1.2.3 From 33b347503f014ebf76257327cbc7001c6b721956 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Tue, 5 Jan 2021 12:32:00 +0200 Subject: vdpa: Define vdpa mgmt device, ops and a netlink interface To add one or more VDPA devices, define a management device which allows adding or removing vdpa device. A management device defines set of callbacks to manage vdpa devices. To begin with, it defines add and remove callbacks through which a user defined vdpa device can be added or removed. A unique management device is identified by its unique handle identified by management device name and optionally the bus name. Hence, introduce routine through which driver can register a management device and its callback operations for adding and remove a vdpa device. Introduce vdpa netlink socket family so that user can query management device and its attributes. Example of show vdpa management device which allows creating vdpa device of networking class (device id = 0x1) of virtio specification 1.1 section 5.1.1. $ vdpa mgmtdev show vdpasim_net: supported_classes: net Example of showing vdpa management device in JSON format. $ vdpa mgmtdev show -jp { "show": { "vdpasim_net": { "supported_classes": [ "net" ] } } } Signed-off-by: Parav Pandit Reviewed-by: Eli Cohen Reviewed-by: Jason Wang Link: https://lore.kernel.org/r/20210105103203.82508-4-parav@nvidia.com Signed-off-by: Michael S. Tsirkin Including a bugfix: vpda: correctly size vdpa_nl_policy We need to ensure last entry of vdpa_nl_policy[] is zero, otherwise out-of-bounds access is hurting us. Signed-off-by: Eric Dumazet Reported-by: syzbot Cc: Parav Pandit Cc: Eli Cohen Cc: Jason Wang Cc: Michael S. Tsirkin Link: https://lore.kernel.org/r/20210210134911.4119555-1-eric.dumazet@gmail.com Signed-off-by: Michael S. Tsirkin --- include/linux/vdpa.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 5700baa22356..6b8b4222bca6 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -35,6 +35,8 @@ struct vdpa_vq_state { u16 avail_index; }; +struct vdpa_mgmt_dev; + /** * vDPA device - representation of a vDPA device * @dev: underlying device @@ -335,4 +337,33 @@ static inline void vdpa_get_config(struct vdpa_device *vdev, unsigned offset, ops->get_config(vdev, offset, buf, len); } +/** + * vdpa_mgmtdev_ops - vdpa device ops + * @dev_add: Add a vdpa device using alloc and register + * @mdev: parent device to use for device addition + * @name: name of the new vdpa device + * Driver need to add a new device using _vdpa_register_device() + * after fully initializing the vdpa device. Driver must return 0 + * on success or appropriate error code. + * @dev_del: Remove a vdpa device using unregister + * @mdev: parent device to use for device removal + * @dev: vdpa device to remove + * Driver need to remove the specified device by calling + * _vdpa_unregister_device(). + */ +struct vdpa_mgmtdev_ops { + int (*dev_add)(struct vdpa_mgmt_dev *mdev, const char *name); + void (*dev_del)(struct vdpa_mgmt_dev *mdev, struct vdpa_device *dev); +}; + +struct vdpa_mgmt_dev { + struct device *device; + const struct vdpa_mgmtdev_ops *ops; + const struct virtio_device_id *id_table; /* supported ids */ + struct list_head list; +}; + +int vdpa_mgmtdev_register(struct vdpa_mgmt_dev *mdev); +void vdpa_mgmtdev_unregister(struct vdpa_mgmt_dev *mdev); + #endif /* _LINUX_VDPA_H */ -- cgit v1.2.3 From 903f7bcaedb84ca47998e609015a34ddde93742e Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Tue, 5 Jan 2021 12:32:01 +0200 Subject: vdpa: Enable a user to add and delete a vdpa device Add the ability to add and delete a vdpa device. Examples: Create a vdpa device of type network named "foo2" from the management device vdpasim: $ vdpa dev add mgmtdev vdpasim_net name foo2 Delete the vdpa device after its use: $ vdpa dev del foo2 Signed-off-by: Parav Pandit Reviewed-by: Eli Cohen Reviewed-by: Jason Wang Link: https://lore.kernel.org/r/20210105103203.82508-5-parav@nvidia.com Signed-off-by: Michael S. Tsirkin --- include/linux/vdpa.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 6b8b4222bca6..4ab5494503a8 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -45,6 +45,8 @@ struct vdpa_mgmt_dev; * @index: device index * @features_valid: were features initialized? for legacy guests * @nvqs: maximum number of supported virtqueues + * @mdev: management device pointer; caller must setup when registering device as part + * of dev_add() mgmtdev ops callback before invoking _vdpa_register_device(). */ struct vdpa_device { struct device dev; @@ -53,6 +55,7 @@ struct vdpa_device { unsigned int index; bool features_valid; int nvqs; + struct vdpa_mgmt_dev *mdev; }; /** @@ -260,6 +263,9 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, int vdpa_register_device(struct vdpa_device *vdev); void vdpa_unregister_device(struct vdpa_device *vdev); +int _vdpa_register_device(struct vdpa_device *vdev); +void _vdpa_unregister_device(struct vdpa_device *vdev); + /** * vdpa_driver - operations for a vDPA driver * @driver: underlying device driver -- cgit v1.2.3 From fd502729fbbf6a76fdb7acae4506486bfbb7c4f6 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Mon, 4 Jan 2021 14:55:00 +0800 Subject: virtio-pci: introduce modern device module Signed-off-by: Jason Wang Link: https://lore.kernel.org/r/20210104065503.199631-17-jasowang@redhat.com Including a bugfix: virtio: don't prompt CONFIG_VIRTIO_PCI_MODERN Cc: Arnd Bergmann Cc: Anders Roxell Cc: Guenter Roeck Reported-by: Naresh Kamboju Fixes: 86b87c9d858b6 ("virtio-pci: introduce modern device module") Signed-off-by: Jason Wang Acked-by: Arnd Bergmann Link: https://lore.kernel.org/r/20210223061905.422659-2-jasowang@redhat.com Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_pci_modern.h | 111 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 111 insertions(+) create mode 100644 include/linux/virtio_pci_modern.h (limited to 'include/linux') diff --git a/include/linux/virtio_pci_modern.h b/include/linux/virtio_pci_modern.h new file mode 100644 index 000000000000..f26acbeec965 --- /dev/null +++ b/include/linux/virtio_pci_modern.h @@ -0,0 +1,111 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_VIRTIO_PCI_MODERN_H +#define _LINUX_VIRTIO_PCI_MODERN_H + +#include +#include + +struct virtio_pci_modern_device { + struct pci_dev *pci_dev; + + struct virtio_pci_common_cfg __iomem *common; + /* Device-specific data (non-legacy mode) */ + void __iomem *device; + /* Base of vq notifications (non-legacy mode). */ + void __iomem *notify_base; + /* Where to read and clear interrupt */ + u8 __iomem *isr; + + /* So we can sanity-check accesses. */ + size_t notify_len; + size_t device_len; + + /* Capability for when we need to map notifications per-vq. */ + int notify_map_cap; + + /* Multiply queue_notify_off by this value. (non-legacy mode). */ + u32 notify_offset_multiplier; + + int modern_bars; + + struct virtio_device_id id; +}; + +/* + * Type-safe wrappers for io accesses. + * Use these to enforce at compile time the following spec requirement: + * + * The driver MUST access each field using the “natural” access + * method, i.e. 32-bit accesses for 32-bit fields, 16-bit accesses + * for 16-bit fields and 8-bit accesses for 8-bit fields. + */ +static inline u8 vp_ioread8(const u8 __iomem *addr) +{ + return ioread8(addr); +} +static inline u16 vp_ioread16 (const __le16 __iomem *addr) +{ + return ioread16(addr); +} + +static inline u32 vp_ioread32(const __le32 __iomem *addr) +{ + return ioread32(addr); +} + +static inline void vp_iowrite8(u8 value, u8 __iomem *addr) +{ + iowrite8(value, addr); +} + +static inline void vp_iowrite16(u16 value, __le16 __iomem *addr) +{ + iowrite16(value, addr); +} + +static inline void vp_iowrite32(u32 value, __le32 __iomem *addr) +{ + iowrite32(value, addr); +} + +static inline void vp_iowrite64_twopart(u64 val, + __le32 __iomem *lo, + __le32 __iomem *hi) +{ + vp_iowrite32((u32)val, lo); + vp_iowrite32(val >> 32, hi); +} + +u64 vp_modern_get_features(struct virtio_pci_modern_device *mdev); +void vp_modern_set_features(struct virtio_pci_modern_device *mdev, + u64 features); +u32 vp_modern_generation(struct virtio_pci_modern_device *mdev); +u8 vp_modern_get_status(struct virtio_pci_modern_device *mdev); +void vp_modern_set_status(struct virtio_pci_modern_device *mdev, + u8 status); +u16 vp_modern_queue_vector(struct virtio_pci_modern_device *mdev, + u16 idx, u16 vector); +u16 vp_modern_config_vector(struct virtio_pci_modern_device *mdev, + u16 vector); +void vp_modern_queue_address(struct virtio_pci_modern_device *mdev, + u16 index, u64 desc_addr, u64 driver_addr, + u64 device_addr); +void vp_modern_set_queue_enable(struct virtio_pci_modern_device *mdev, + u16 idx, bool enable); +bool vp_modern_get_queue_enable(struct virtio_pci_modern_device *mdev, + u16 idx); +void vp_modern_set_queue_size(struct virtio_pci_modern_device *mdev, + u16 idx, u16 size); +u16 vp_modern_get_queue_size(struct virtio_pci_modern_device *mdev, + u16 idx); +u16 vp_modern_get_num_queues(struct virtio_pci_modern_device *mdev); +u16 vp_modern_get_queue_notify_off(struct virtio_pci_modern_device *mdev, + u16 idx); +void __iomem *vp_modern_map_capability(struct virtio_pci_modern_device *mdev, int off, + size_t minlen, + u32 align, + u32 start, u32 size, + size_t *len); +int vp_modern_probe(struct virtio_pci_modern_device *mdev); +void vp_modern_remove(struct virtio_pci_modern_device *mdev); +#endif -- cgit v1.2.3 From c0ea57608b691d6cde8aff23e11f9858a86b5918 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 16 Feb 2021 16:52:47 +0100 Subject: blktrace: remove debugfs file dentries from struct blk_trace These debugfs dentries do not need to be saved for anything as the whole directory and everything in it is properly cleaned up when the parent directory is removed. So remove them from struct blk_trace and don't save them when created as it's not necessary. Cc: Jens Axboe Cc: Steven Rostedt Cc: Ingo Molnar Cc: linux-block@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Greg Kroah-Hartman Signed-off-by: Jens Axboe --- include/linux/blktrace_api.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index e17d04abf6a3..a083e15df608 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -23,8 +23,6 @@ struct blk_trace { u32 pid; u32 dev; struct dentry *dir; - struct dentry *dropped_file; - struct dentry *msg_file; struct list_head running_list; atomic_t dropped; }; -- cgit v1.2.3 From ee576c47db60432c37e54b1e2b43a8ca6d3a8dca Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Tue, 23 Feb 2021 14:18:58 +0100 Subject: net: icmp: pass zeroed opts from icmp{,v6}_ndo_send before sending The icmp{,v6}_send functions make all sorts of use of skb->cb, casting it with IPCB or IP6CB, assuming the skb to have come directly from the inet layer. But when the packet comes from the ndo layer, especially when forwarded, there's no telling what might be in skb->cb at that point. As a result, the icmp sending code risks reading bogus memory contents, which can result in nasty stack overflows such as this one reported by a user: panic+0x108/0x2ea __stack_chk_fail+0x14/0x20 __icmp_send+0x5bd/0x5c0 icmp_ndo_send+0x148/0x160 In icmp_send, skb->cb is cast with IPCB and an ip_options struct is read from it. The optlen parameter there is of particular note, as it can induce writes beyond bounds. There are quite a few ways that can happen in __ip_options_echo. For example: // sptr/skb are attacker-controlled skb bytes sptr = skb_network_header(skb); // dptr/dopt points to stack memory allocated by __icmp_send dptr = dopt->__data; // sopt is the corrupt skb->cb in question if (sopt->rr) { optlen = sptr[sopt->rr+1]; // corrupt skb->cb + skb->data soffset = sptr[sopt->rr+2]; // corrupt skb->cb + skb->data // this now writes potentially attacker-controlled data, over // flowing the stack: memcpy(dptr, sptr+sopt->rr, optlen); } In the icmpv6_send case, the story is similar, but not as dire, as only IP6CB(skb)->iif and IP6CB(skb)->dsthao are used. The dsthao case is worse than the iif case, but it is passed to ipv6_find_tlv, which does a bit of bounds checking on the value. This is easy to simulate by doing a `memset(skb->cb, 0x41, sizeof(skb->cb));` before calling icmp{,v6}_ndo_send, and it's only by good fortune and the rarity of icmp sending from that context that we've avoided reports like this until now. For example, in KASAN: BUG: KASAN: stack-out-of-bounds in __ip_options_echo+0xa0e/0x12b0 Write of size 38 at addr ffff888006f1f80e by task ping/89 CPU: 2 PID: 89 Comm: ping Not tainted 5.10.0-rc7-debug+ #5 Call Trace: dump_stack+0x9a/0xcc print_address_description.constprop.0+0x1a/0x160 __kasan_report.cold+0x20/0x38 kasan_report+0x32/0x40 check_memory_region+0x145/0x1a0 memcpy+0x39/0x60 __ip_options_echo+0xa0e/0x12b0 __icmp_send+0x744/0x1700 Actually, out of the 4 drivers that do this, only gtp zeroed the cb for the v4 case, while the rest did not. So this commit actually removes the gtp-specific zeroing, while putting the code where it belongs in the shared infrastructure of icmp{,v6}_ndo_send. This commit fixes the issue by passing an empty IPCB or IP6CB along to the functions that actually do the work. For the icmp_send, this was already trivial, thanks to __icmp_send providing the plumbing function. For icmpv6_send, this required a tiny bit of refactoring to make it behave like the v4 case, after which it was straight forward. Fixes: a2b78e9b2cac ("sunvnet: generate ICMP PTMUD messages for smaller port MTUs") Reported-by: SinYu Reviewed-by: Willem de Bruijn Link: https://lore.kernel.org/netdev/CAF=yD-LOF116aHub6RMe8vB8ZpnrrnoTdqhobEx+bvoA8AsP0w@mail.gmail.com/T/ Signed-off-by: Jason A. Donenfeld Link: https://lore.kernel.org/r/20210223131858.72082-1-Jason@zx2c4.com Signed-off-by: Jakub Kicinski --- include/linux/icmpv6.h | 26 ++++++++++++++++++++------ include/linux/ipv6.h | 1 - 2 files changed, 20 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h index 452d8978ffc7..9055cb380ee2 100644 --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -3,6 +3,7 @@ #define _LINUX_ICMPV6_H #include +#include #include static inline struct icmp6hdr *icmp6_hdr(const struct sk_buff *skb) @@ -15,13 +16,16 @@ static inline struct icmp6hdr *icmp6_hdr(const struct sk_buff *skb) #if IS_ENABLED(CONFIG_IPV6) typedef void ip6_icmp_send_t(struct sk_buff *skb, u8 type, u8 code, __u32 info, - const struct in6_addr *force_saddr); + const struct in6_addr *force_saddr, + const struct inet6_skb_parm *parm); void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, - const struct in6_addr *force_saddr); + const struct in6_addr *force_saddr, + const struct inet6_skb_parm *parm); #if IS_BUILTIN(CONFIG_IPV6) -static inline void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) +static inline void __icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, + const struct inet6_skb_parm *parm) { - icmp6_send(skb, type, code, info, NULL); + icmp6_send(skb, type, code, info, NULL, parm); } static inline int inet6_register_icmp_sender(ip6_icmp_send_t *fn) { @@ -34,18 +38,28 @@ static inline int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn) return 0; } #else -extern void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info); +extern void __icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, + const struct inet6_skb_parm *parm); extern int inet6_register_icmp_sender(ip6_icmp_send_t *fn); extern int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn); #endif +static inline void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) +{ + __icmpv6_send(skb, type, code, info, IP6CB(skb)); +} + int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type, unsigned int data_len); #if IS_ENABLED(CONFIG_NF_NAT) void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info); #else -#define icmpv6_ndo_send icmpv6_send +static inline void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info) +{ + struct inet6_skb_parm parm = { 0 }; + __icmpv6_send(skb_in, type, code, info, &parm); +} #endif #else diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 9d1f29f0c512..70b2ad3b9884 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -85,7 +85,6 @@ struct ipv6_params { __s32 autoconf; }; extern struct ipv6_params ipv6_defaults; -#include #include #include -- cgit v1.2.3 From fa8fef0e104a23efe568b835d9e7e188d1d97610 Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Tue, 2 Feb 2021 01:27:55 +0530 Subject: PCI: endpoint: Add helper API to get the 'next' unreserved BAR Add an API to get the next unreserved BAR starting from a given BAR number that can be used by the endpoint function. Link: https://lore.kernel.org/r/20210201195809.7342-4-kishon@ti.com Signed-off-by: Kishon Vijay Abraham I Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas --- include/linux/pci-epc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h index cc66bec8be90..cfe9b427e6b7 100644 --- a/include/linux/pci-epc.h +++ b/include/linux/pci-epc.h @@ -203,6 +203,8 @@ const struct pci_epc_features *pci_epc_get_features(struct pci_epc *epc, u8 func_no); unsigned int pci_epc_get_first_free_bar(const struct pci_epc_features *epc_features); +unsigned int pci_epc_get_next_free_bar(const struct pci_epc_features + *epc_features, enum pci_barno bar); struct pci_epc *pci_epc_get(const char *epc_name); void pci_epc_put(struct pci_epc *epc); -- cgit v1.2.3 From 0e27aeccfa3d1bab7c6a29fb8e6fcedbad7b09a8 Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Tue, 2 Feb 2021 01:27:56 +0530 Subject: PCI: endpoint: Make *_free_bar() to return error codes on failure Modify pci_epc_get_next_free_bar() and pci_epc_get_first_free_bar() to return error values if there are no free BARs available. Link: https://lore.kernel.org/r/20210201195809.7342-5-kishon@ti.com Signed-off-by: Kishon Vijay Abraham I Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas --- include/linux/pci-epc.h | 8 ++++---- include/linux/pci-epf.h | 1 + 2 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h index cfe9b427e6b7..88d311bad984 100644 --- a/include/linux/pci-epc.h +++ b/include/linux/pci-epc.h @@ -201,10 +201,10 @@ int pci_epc_start(struct pci_epc *epc); void pci_epc_stop(struct pci_epc *epc); const struct pci_epc_features *pci_epc_get_features(struct pci_epc *epc, u8 func_no); -unsigned int pci_epc_get_first_free_bar(const struct pci_epc_features - *epc_features); -unsigned int pci_epc_get_next_free_bar(const struct pci_epc_features - *epc_features, enum pci_barno bar); +enum pci_barno +pci_epc_get_first_free_bar(const struct pci_epc_features *epc_features); +enum pci_barno pci_epc_get_next_free_bar(const struct pci_epc_features + *epc_features, enum pci_barno bar); struct pci_epc *pci_epc_get(const char *epc_name); void pci_epc_put(struct pci_epc *epc); diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h index 6644ff3b0702..fa3aca43eb19 100644 --- a/include/linux/pci-epf.h +++ b/include/linux/pci-epf.h @@ -21,6 +21,7 @@ enum pci_notify_event { }; enum pci_barno { + NO_BAR = -1, BAR_0, BAR_1, BAR_2, -- cgit v1.2.3 From 7e5a51ebb321537c4209cdd0c54c4c19b3ef960d Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Tue, 2 Feb 2021 01:27:57 +0530 Subject: PCI: endpoint: Remove unused pci_epf_match_device() Remove unused pci_epf_match_device() function added in pci-epf-core.c Link: https://lore.kernel.org/r/20210201195809.7342-6-kishon@ti.com Signed-off-by: Kishon Vijay Abraham I Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas --- include/linux/pci-epf.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h index fa3aca43eb19..f373a134ac04 100644 --- a/include/linux/pci-epf.h +++ b/include/linux/pci-epf.h @@ -165,8 +165,6 @@ static inline void *epf_get_drvdata(struct pci_epf *epf) return dev_get_drvdata(&epf->dev); } -const struct pci_epf_device_id * -pci_epf_match_device(const struct pci_epf_device_id *id, struct pci_epf *epf); struct pci_epf *pci_epf_create(const char *name); void pci_epf_destroy(struct pci_epf *epf); int __pci_epf_register_driver(struct pci_epf_driver *driver, -- cgit v1.2.3 From 63840ff5322373d665b2b9c59cd64233d5f0691e Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Tue, 2 Feb 2021 01:27:58 +0530 Subject: PCI: endpoint: Add support to associate secondary EPC with EPF In the case of standard endpoint functions, only one endpoint controller (EPC) will be associated with an endpoint function (EPF). However for providing NTB (non transparent bridge) functionality, two EPCs should be associated with a single EPF. Add support to associate secondary EPC with EPF. This is in preparation for adding NTB endpoint function driver. Link: https://lore.kernel.org/r/20210201195809.7342-7-kishon@ti.com Signed-off-by: Kishon Vijay Abraham I Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas --- include/linux/pci-epc.h | 25 +++++++++++++++++++++++-- include/linux/pci-epf.h | 17 +++++++++++++++-- 2 files changed, 38 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h index 88d311bad984..d9cb3944fb87 100644 --- a/include/linux/pci-epc.h +++ b/include/linux/pci-epc.h @@ -13,6 +13,12 @@ struct pci_epc; +enum pci_epc_interface_type { + UNKNOWN_INTERFACE = -1, + PRIMARY_INTERFACE, + SECONDARY_INTERFACE, +}; + enum pci_epc_irq_type { PCI_EPC_IRQ_UNKNOWN, PCI_EPC_IRQ_LEGACY, @@ -20,6 +26,19 @@ enum pci_epc_irq_type { PCI_EPC_IRQ_MSIX, }; +static inline const char * +pci_epc_interface_string(enum pci_epc_interface_type type) +{ + switch (type) { + case PRIMARY_INTERFACE: + return "primary"; + case SECONDARY_INTERFACE: + return "secondary"; + default: + return "UNKNOWN interface"; + } +} + /** * struct pci_epc_ops - set of function pointers for performing EPC operations * @write_header: ops to populate configuration space header @@ -175,10 +194,12 @@ __pci_epc_create(struct device *dev, const struct pci_epc_ops *ops, struct module *owner); void devm_pci_epc_destroy(struct device *dev, struct pci_epc *epc); void pci_epc_destroy(struct pci_epc *epc); -int pci_epc_add_epf(struct pci_epc *epc, struct pci_epf *epf); +int pci_epc_add_epf(struct pci_epc *epc, struct pci_epf *epf, + enum pci_epc_interface_type type); void pci_epc_linkup(struct pci_epc *epc); void pci_epc_init_notify(struct pci_epc *epc); -void pci_epc_remove_epf(struct pci_epc *epc, struct pci_epf *epf); +void pci_epc_remove_epf(struct pci_epc *epc, struct pci_epf *epf, + enum pci_epc_interface_type type); int pci_epc_write_header(struct pci_epc *epc, u8 func_no, struct pci_epf_header *hdr); int pci_epc_set_bar(struct pci_epc *epc, u8 func_no, diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h index f373a134ac04..1dc66824f5a8 100644 --- a/include/linux/pci-epf.h +++ b/include/linux/pci-epf.h @@ -14,6 +14,7 @@ #include struct pci_epf; +enum pci_epc_interface_type; enum pci_notify_event { CORE_INIT, @@ -119,6 +120,11 @@ struct pci_epf_bar { * @list: to add pci_epf as a list of PCI endpoint functions to pci_epc * @nb: notifier block to notify EPF of any EPC events (like linkup) * @lock: mutex to protect pci_epf_ops + * @sec_epc: the secondary EPC device to which this EPF device is bound + * @sec_epc_list: to add pci_epf as list of PCI endpoint functions to secondary + * EPC device + * @sec_epc_bar: represents the BAR of EPF device associated with secondary EPC + * @sec_epc_func_no: unique (physical) function number within the secondary EPC */ struct pci_epf { struct device dev; @@ -135,6 +141,12 @@ struct pci_epf { struct notifier_block nb; /* mutex to protect against concurrent access of pci_epf_ops */ struct mutex lock; + + /* Below members are to attach secondary EPC to an endpoint function */ + struct pci_epc *sec_epc; + struct list_head sec_epc_list; + struct pci_epf_bar sec_epc_bar[6]; + u8 sec_epc_func_no; }; /** @@ -171,8 +183,9 @@ int __pci_epf_register_driver(struct pci_epf_driver *driver, struct module *owner); void pci_epf_unregister_driver(struct pci_epf_driver *driver); void *pci_epf_alloc_space(struct pci_epf *epf, size_t size, enum pci_barno bar, - size_t align); -void pci_epf_free_space(struct pci_epf *epf, void *addr, enum pci_barno bar); + size_t align, enum pci_epc_interface_type type); +void pci_epf_free_space(struct pci_epf *epf, void *addr, enum pci_barno bar, + enum pci_epc_interface_type type); int pci_epf_bind(struct pci_epf *epf); void pci_epf_unbind(struct pci_epf *epf); #endif /* __LINUX_PCI_EPF_H */ -- cgit v1.2.3 From 87d5972e476f6c4e98a0abce713c54c6f40661b0 Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Tue, 2 Feb 2021 01:28:00 +0530 Subject: PCI: endpoint: Add pci_epc_ops to map MSI IRQ Add pci_epc_ops to map physical address to MSI address and return MSI data. The physical address is an address in the outbound region. This is required to implement doorbell functionality of NTB (non-transparent bridge) wherein EPC on either side of the interface (primary and secondary) can directly write to the physical address (in outbound region) of the other interface to ring doorbell using MSI. Link: https://lore.kernel.org/r/20210201195809.7342-9-kishon@ti.com Signed-off-by: Kishon Vijay Abraham I Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas --- include/linux/pci-epc.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h index d9cb3944fb87..b82c9b100e97 100644 --- a/include/linux/pci-epc.h +++ b/include/linux/pci-epc.h @@ -55,6 +55,7 @@ pci_epc_interface_string(enum pci_epc_interface_type type) * @get_msix: ops to get the number of MSI-X interrupts allocated by the RC * from the MSI-X capability register * @raise_irq: ops to raise a legacy, MSI or MSI-X interrupt + * @map_msi_irq: ops to map physical address to MSI address and return MSI data * @start: ops to start the PCI link * @stop: ops to stop the PCI link * @owner: the module owner containing the ops @@ -77,6 +78,10 @@ struct pci_epc_ops { int (*get_msix)(struct pci_epc *epc, u8 func_no); int (*raise_irq)(struct pci_epc *epc, u8 func_no, enum pci_epc_irq_type type, u16 interrupt_num); + int (*map_msi_irq)(struct pci_epc *epc, u8 func_no, + phys_addr_t phys_addr, u8 interrupt_num, + u32 entry_size, u32 *msi_data, + u32 *msi_addr_offset); int (*start)(struct pci_epc *epc); void (*stop)(struct pci_epc *epc); const struct pci_epc_features* (*get_features)(struct pci_epc *epc, @@ -216,6 +221,9 @@ int pci_epc_get_msi(struct pci_epc *epc, u8 func_no); int pci_epc_set_msix(struct pci_epc *epc, u8 func_no, u16 interrupts, enum pci_barno, u32 offset); int pci_epc_get_msix(struct pci_epc *epc, u8 func_no); +int pci_epc_map_msi_irq(struct pci_epc *epc, u8 func_no, + phys_addr_t phys_addr, u8 interrupt_num, + u32 entry_size, u32 *msi_data, u32 *msi_addr_offset); int pci_epc_raise_irq(struct pci_epc *epc, u8 func_no, enum pci_epc_irq_type type, u16 interrupt_num); int pci_epc_start(struct pci_epc *epc); -- cgit v1.2.3 From 256ae475201b16fd69e00dd6c2d14035e4ea5745 Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Tue, 2 Feb 2021 01:28:01 +0530 Subject: PCI: endpoint: Add pci_epf_ops to expose function-specific attrs In addition to the attributes that are generic across function drivers documented in Documentation/PCI/endpoint/pci-endpoint-cfs.rst, there could be function-specific attributes that has to be exposed by the function driver to be configured by the user. Add ->add_cfs() in pci_epf_ops to be populated by the function driver if it has to expose any function-specific attributes and pci_epf_type_add_cfs() to be invoked by pci-ep-cfs.c when sub-directory to main function directory is created. Link: https://lore.kernel.org/r/20210201195809.7342-10-kishon@ti.com Signed-off-by: Kishon Vijay Abraham I Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas --- include/linux/pci-epf.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h index 1dc66824f5a8..b241e7dd171f 100644 --- a/include/linux/pci-epf.h +++ b/include/linux/pci-epf.h @@ -62,10 +62,13 @@ struct pci_epf_header { * @bind: ops to perform when a EPC device has been bound to EPF device * @unbind: ops to perform when a binding has been lost between a EPC device * and EPF device + * @add_cfs: ops to initialize function specific configfs attributes */ struct pci_epf_ops { int (*bind)(struct pci_epf *epf); void (*unbind)(struct pci_epf *epf); + struct config_group *(*add_cfs)(struct pci_epf *epf, + struct config_group *group); }; /** @@ -188,4 +191,6 @@ void pci_epf_free_space(struct pci_epf *epf, void *addr, enum pci_barno bar, enum pci_epc_interface_type type); int pci_epf_bind(struct pci_epf *epf); void pci_epf_unbind(struct pci_epf *epf); +struct config_group *pci_epf_type_add_cfs(struct pci_epf *epf, + struct config_group *group); #endif /* __LINUX_PCI_EPF_H */ -- cgit v1.2.3 From 38ad827e3bc0f0e94628ee1d8dc31e778d9be40f Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Tue, 2 Feb 2021 01:28:02 +0530 Subject: PCI: endpoint: Allow user to create sub-directory of 'EPF Device' directory Documentation/PCI/endpoint/pci-endpoint-cfs.rst explains how a user has to create a directory in-order to create a 'EPF Device' that can be configured/probed by 'EPF Driver'. Allow user to create a sub-directory of 'EPF Device' directory for any function specific attributes that has to be exposed to the user. Link: https://lore.kernel.org/r/20210201195809.7342-11-kishon@ti.com Signed-off-by: Kishon Vijay Abraham I Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas --- include/linux/pci-epf.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h index b241e7dd171f..6833e2160ef1 100644 --- a/include/linux/pci-epf.h +++ b/include/linux/pci-epf.h @@ -9,6 +9,7 @@ #ifndef __LINUX_PCI_EPF_H #define __LINUX_PCI_EPF_H +#include #include #include #include @@ -128,6 +129,7 @@ struct pci_epf_bar { * EPC device * @sec_epc_bar: represents the BAR of EPF device associated with secondary EPC * @sec_epc_func_no: unique (physical) function number within the secondary EPC + * @group: configfs group associated with the EPF device */ struct pci_epf { struct device dev; @@ -150,6 +152,7 @@ struct pci_epf { struct list_head sec_epc_list; struct pci_epf_bar sec_epc_bar[6]; u8 sec_epc_func_no; + struct config_group *group; }; /** -- cgit v1.2.3 From 599f86872f9ce8a0a0bd111a23442b18e8ee7059 Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Tue, 2 Feb 2021 01:28:06 +0530 Subject: PCI: Add TI J721E device to PCI IDs Add TI J721E device to the PCI ID database. Since this device has a configurable PCIe endpoint, it could be used with different drivers. Link: https://lore.kernel.org/r/20210201195809.7342-15-kishon@ti.com Signed-off-by: Kishon Vijay Abraham I Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas --- include/linux/pci_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index d8156a5dbee8..f968fcda338e 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -881,6 +881,7 @@ #define PCI_DEVICE_ID_TI_X620 0xac8d #define PCI_DEVICE_ID_TI_X420 0xac8e #define PCI_DEVICE_ID_TI_XX20_FM 0xac8f +#define PCI_DEVICE_ID_TI_J721E 0xb00d #define PCI_DEVICE_ID_TI_DRA74x 0xb500 #define PCI_DEVICE_ID_TI_DRA72x 0xb501 -- cgit v1.2.3 From cf6acb8bdb1d829b85a4daa2944bf9e71c93f4b9 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Mon, 22 Feb 2021 18:01:54 +0100 Subject: s390/cpumf: Add support for complete counter set extraction Add support to the CPU Measurement counter facility device driver to extract complete counter sets per CPU and per counter set from user space. This includes a new device named /dev/hwctr and support for the device driver functions open, close and ioctl. Other functions are not supported. The ioctl command supports 3 subcommands: S390_HWCTR_START: enables counter sets on a list of CPUs. S390_HWCTR_STOP: disables counter sets on a list of CPUs. S390_HWCTR_READ: reads counter sets on a list of CPUs. The ioctl(..., S390_HWCTR_READ, ...) is the only subcommand which returns data. It requires member data_bytes to be positive and indicates the maximum amount of data available to store counter set data. The other ioctl() subcommands do not use this member and it should be set to zero. The S390_HWCTR_READ subcommand returns the following data: The cpuset data is flattened using the following scheme, stored in member data: 0x0 0x8 0xc 0x10 0x10 0x18 0x20 0x28 0xU-1 +---------+-----+---------+-----+---------+-----+-----+------+------+ | no_cpus | cpu | no_sets | set | no_cnts | cv1 | cv2 | .... | cv_n | +---------+-----+---------+-----+---------+-----+-----+------+------+ 0xU 0xU+4 0xU+8 0xU+10 0xV-1 +-----+---------+-----+-----+------+------+ | set | no_cnts | cv1 | cv2 | .... | cv_n | +-----+---------+-----+-----+------+------+ 0xV 0xV+4 0xV+8 0xV+c +-----+---------+-----+---------+-----+-----+------+------+ | cpu | no_sets | set | no_cnts | cv1 | cv2 | .... | cv_n | +-----+---------+-----+---------+-----+-----+------+------+ U and V denote arbitrary hexadezimal addresses. The first integer represents the number of CPUs data was extracted from. This is followed by CPU number and number of counter sets extracted. Both are two integer values. This is followed by the set identifer and number of counters extracted. Both are two integer values. This is followed by the counter values, each element is eight bytes in size. The S390_HWCTR_READ ioctl subcommand is also limited to one call per minute. This ensures that an application does not read out the counter sets too often and reduces the overall CPU performance. The complete counter set extraction is an expensive operation. Reviewed-by: Sumanth Korikkar Signed-off-by: Thomas Richter Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index ee09a39627d6..9129ba231423 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -168,6 +168,7 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_CQM_ONLINE, CPUHP_AP_PERF_X86_CSTATE_ONLINE, CPUHP_AP_PERF_S390_CF_ONLINE, + CPUHP_AP_PERF_S390_CFD_ONLINE, CPUHP_AP_PERF_S390_SF_ONLINE, CPUHP_AP_PERF_ARM_CCI_ONLINE, CPUHP_AP_PERF_ARM_CCN_ONLINE, -- cgit v1.2.3 From e54937963fa249595824439dc839c948188dea83 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 17 Feb 2021 10:14:21 -0700 Subject: net: remove cmsg restriction from io_uring based send/recvmsg calls No need to restrict these anymore, as the worker threads are direct clones of the original task. Hence we know for a fact that we can support anything that the regular task can. Since the only user of proto_ops->flags was to flag PROTO_CMSG_DATA_ONLY, kill the member and the flag definition too. Signed-off-by: Jens Axboe --- include/linux/net.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index 9e2324efc26a..ba736b457a06 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -42,8 +42,6 @@ struct net; #define SOCK_PASSCRED 3 #define SOCK_PASSSEC 4 -#define PROTO_CMSG_DATA_ONLY 0x0001 - #ifndef ARCH_HAS_SOCKET_TYPES /** * enum sock_type - Socket types @@ -138,7 +136,6 @@ typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *, struct proto_ops { int family; - unsigned int flags; struct module *owner; int (*release) (struct socket *sock); int (*bind) (struct socket *sock, -- cgit v1.2.3 From 8a378fb096a7f02943c72a428bbfd0029260efb6 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 23 Feb 2021 12:27:49 -0700 Subject: io_uring: ensure io-wq context is always destroyed for tasks If the task ends up doing no IO, the context list is empty and we don't call into __io_uring_files_cancel() when the task exits. This can cause a leak of the io-wq structures. Ensure we always call __io_uring_files_cancel(), even if the task context list is empty. Fixes: 5aa75ed5b93f ("io_uring: tie async worker side to the task context") Signed-off-by: Jens Axboe --- include/linux/io_uring.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index c48fcbdc2ea8..51ede771cd99 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -43,7 +43,7 @@ static inline void io_uring_task_cancel(void) } static inline void io_uring_files_cancel(struct files_struct *files) { - if (current->io_uring && !xa_empty(¤t->io_uring->xa)) + if (current->io_uring) __io_uring_files_cancel(files); } static inline void io_uring_free(struct task_struct *tsk) -- cgit v1.2.3 From 6120484ef2bd4ffea7d2f11d2f06167b8f848349 Mon Sep 17 00:00:00 2001 From: Maximilian Luz Date: Thu, 11 Feb 2021 21:17:01 +0100 Subject: ACPI: platform: Fix file references in comment The referenced files are named slightly different. Replace '-' with '_' and drop the .rst ending. Signed-off-by: Maximilian Luz Reviewed-by: Hans de Goede Signed-off-by: Rafael J. Wysocki --- include/linux/platform_profile.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_profile.h b/include/linux/platform_profile.h index a26542d53058..b4794027e759 100644 --- a/include/linux/platform_profile.h +++ b/include/linux/platform_profile.h @@ -12,9 +12,8 @@ #include /* - * If more options are added please update profile_names - * array in platform-profile.c and sysfs-platform-profile.rst - * documentation. + * If more options are added please update profile_names array in + * platform_profile.c and sysfs-platform_profile documentation. */ enum platform_profile_option { -- cgit v1.2.3 From 6c0b5e3fc6b536b125a66dfee103f3bc26d386f6 Mon Sep 17 00:00:00 2001 From: Maximilian Luz Date: Thu, 11 Feb 2021 21:17:02 +0100 Subject: ACPI: platform: Add balanced-performance platform profile Some devices, including most Microsoft Surface devices, have a platform profile somewhere inbetween balanced and performance. More specifically, adding this profile allows the following mapping on Surface devices: Vendor Name Platform Profile ------------------------------------------ Battery Saver low-power Recommended balanced Better Performance balanced-performance Best Performance performance Suggested-by: Hans de Goede Signed-off-by: Maximilian Luz Reviewed-by: Hans de Goede Signed-off-by: Rafael J. Wysocki --- include/linux/platform_profile.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_profile.h b/include/linux/platform_profile.h index b4794027e759..a6329003aee7 100644 --- a/include/linux/platform_profile.h +++ b/include/linux/platform_profile.h @@ -21,6 +21,7 @@ enum platform_profile_option { PLATFORM_PROFILE_COOL, PLATFORM_PROFILE_QUIET, PLATFORM_PROFILE_BALANCED, + PLATFORM_PROFILE_BALANCED_PERFORMANCE, PLATFORM_PROFILE_PERFORMANCE, PLATFORM_PROFILE_LAST, /*must always be last */ }; -- cgit v1.2.3 From abf4451b340b09f797c87341b3010f95af9215c0 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Tue, 19 Jan 2021 20:45:08 +0000 Subject: dma-buf: heaps: Rework heap allocation hooks to return struct dma_buf instead of fd MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Every heap needs to create a dmabuf and then export it to a fd via dma_buf_fd(), so to consolidate things a bit, have the heaps just return a struct dmabuf * and let the top level dma_heap_buffer_alloc() call handle creating the fd via dma_buf_fd(). Cc: Sumit Semwal Cc: Liam Mark Cc: Laura Abbott Cc: Brian Starkey Cc: Hridya Valsaraju Cc: Suren Baghdasaryan Cc: Sandeep Patil Cc: Daniel Mentz Cc: Chris Goldsworthy Cc: Ørjan Eide Cc: Robin Murphy Cc: Ezequiel Garcia Cc: Simon Ser Cc: James Jones Cc: linux-media@vger.kernel.org Cc: dri-devel@lists.freedesktop.org Signed-off-by: John Stultz Signed-off-by: Sumit Semwal [sumits: minor reword of commit message] Link: https://patchwork.freedesktop.org/patch/msgid/20210119204508.9256-3-john.stultz@linaro.org (cherry picked from commit c7f59e3dd60313071a989227dcb69094f499d310) Signed-off-by: Sumit Semwal --- include/linux/dma-heap.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-heap.h b/include/linux/dma-heap.h index 454e354d1ffb..5bc5c946af58 100644 --- a/include/linux/dma-heap.h +++ b/include/linux/dma-heap.h @@ -16,15 +16,15 @@ struct dma_heap; /** * struct dma_heap_ops - ops to operate on a given heap - * @allocate: allocate dmabuf and return fd + * @allocate: allocate dmabuf and return struct dma_buf ptr * - * allocate returns dmabuf fd on success, -errno on error. + * allocate returns dmabuf on success, ERR_PTR(-errno) on error. */ struct dma_heap_ops { - int (*allocate)(struct dma_heap *heap, - unsigned long len, - unsigned long fd_flags, - unsigned long heap_flags); + struct dma_buf *(*allocate)(struct dma_heap *heap, + unsigned long len, + unsigned long fd_flags, + unsigned long heap_flags); }; /** -- cgit v1.2.3 From f588f0c69e0e645225e4ebc1aff8f9677583a056 Mon Sep 17 00:00:00 2001 From: Veera Sundaram Sankaran Date: Fri, 15 Jan 2021 16:31:46 -0800 Subject: dma-fence: allow signaling drivers to set fence timestamp Some drivers have hardware capability to get the precise HW timestamp of certain events based on which the fences are triggered. The delta between the event HW timestamp & current HW reference timestamp can be used to calculate the timestamp in kernel's CLOCK_MONOTONIC time domain. This allows it to set accurate timestamp factoring out any software and IRQ latencies. Add a timestamp variant of fence signal function, dma_fence_signal_timestamp to allow drivers to update the precise timestamp for fences. Changes in v2: - Add a new fence signal variant instead of modifying fence struct Changes in v3: - Add timestamp domain information to commit-text and dma_fence_signal_timestamp documentation Signed-off-by: Veera Sundaram Sankaran Reviewed-by: John Stultz Signed-off-by: Sumit Semwal [sumits: minor parenthesis alignment] Link: https://patchwork.freedesktop.org/patch/msgid/1610757107-11892-1-git-send-email-veeras@codeaurora.org (cherry picked from commit 5a164ac4dbd21b82bcdc03186d40e455ff467fdc) Signed-off-by: Sumit Semwal --- include/linux/dma-fence.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index 09e23adb351d..9f12efaaa93a 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -372,6 +372,9 @@ static inline void __dma_fence_might_wait(void) {} int dma_fence_signal(struct dma_fence *fence); int dma_fence_signal_locked(struct dma_fence *fence); +int dma_fence_signal_timestamp(struct dma_fence *fence, ktime_t timestamp); +int dma_fence_signal_timestamp_locked(struct dma_fence *fence, + ktime_t timestamp); signed long dma_fence_default_wait(struct dma_fence *fence, bool intr, signed long timeout); int dma_fence_add_callback(struct dma_fence *fence, -- cgit v1.2.3 From 1f7ef657740344541645349a8bece90cbff898f5 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Wed, 24 Feb 2021 12:01:42 -0800 Subject: mm/filemap: remove unused parameter and change to void type for replace_page_cache_page() Since commit 74d609585d8b ("page cache: Add and replace pages using the XArray") was merged, the replace_page_cache_page() can not fail and always return 0, we can remove the redundant return value and void it. Moreover remove the unused gfp_mask. Link: https://lkml.kernel.org/r/609c30e5274ba15d8b90c872fd0d8ac437a9b2bb.1610071401.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang Cc: Matthew Wilcox Cc: Miklos Szeredi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index d5570deff400..74e466e5a2ba 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -757,7 +757,7 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); extern void delete_from_page_cache(struct page *page); extern void __delete_from_page_cache(struct page *page, void *shadow); -int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask); +void replace_page_cache_page(struct page *old, struct page *new); void delete_from_page_cache_batch(struct address_space *mapping, struct pagevec *pvec); -- cgit v1.2.3 From 4805462598113f350838d612d0895db2dbb3992b Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 24 Feb 2021 12:02:02 -0800 Subject: mm/filemap: pass a sleep state to put_and_wait_on_page_locked This is prep work for the next patch, but I think at least one of the current callers would prefer a killable sleep to an uninterruptible one. Link: https://lkml.kernel.org/r/20210122160140.223228-6-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Kent Overstreet Reviewed-by: Christoph Hellwig Cc: Miaohe Lin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 74e466e5a2ba..bd629d676a27 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -681,8 +681,7 @@ static inline int wait_on_page_locked_killable(struct page *page) return wait_on_page_bit_killable(compound_head(page), PG_locked); } -extern void put_and_wait_on_page_locked(struct page *page); - +int put_and_wait_on_page_locked(struct page *page, int state); void wait_on_page_writeback(struct page *page); extern void end_page_writeback(struct page *page); void wait_for_stable_page(struct page *page); -- cgit v1.2.3 From 87fa0f3eb267eed966ee194907bc15376c1b758f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 24 Feb 2021 12:02:42 -0800 Subject: mm/filemap: rename generic_file_buffered_read to filemap_read Rename generic_file_buffered_read to match the naming of filemap_fault, also update the written parameter to a more descriptive name and improve the kerneldoc comment. Link: https://lkml.kernel.org/r/20210122160140.223228-18-willy@infradead.org Signed-off-by: Christoph Hellwig Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Kent Overstreet Cc: Miaohe Lin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 418b772d6eca..ec8f3ddf4a6a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3080,8 +3080,8 @@ extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); extern int generic_write_check_limits(struct file *file, loff_t pos, loff_t *count); extern int generic_file_rw_checks(struct file *file_in, struct file *file_out); -extern ssize_t generic_file_buffered_read(struct kiocb *iocb, - struct iov_iter *to, ssize_t already_read); +ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *to, + ssize_t already_read); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); -- cgit v1.2.3 From 2e9bd483159939ed2c0704b914294653c8341d25 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Wed, 24 Feb 2021 12:03:11 -0800 Subject: mm: memcg/slab: pre-allocate obj_cgroups for slab caches with SLAB_ACCOUNT In general it's unknown in advance if a slab page will contain accounted objects or not. In order to avoid memory waste, an obj_cgroup vector is allocated dynamically when a need to account of a new object arises. Such approach is memory efficient, but requires an expensive cmpxchg() to set up the memcg/objcgs pointer, because an allocation can race with a different allocation on another cpu. But in some common cases it's known for sure that a slab page will contain accounted objects: if the page belongs to a slab cache with a SLAB_ACCOUNT flag set. It includes such popular objects like vm_area_struct, anon_vma, task_struct, etc. In such cases we can pre-allocate the objcgs vector and simple assign it to the page without any atomic operations, because at this early stage the page is not visible to anyone else. A very simplistic benchmark (allocating 10000000 64-bytes objects in a row) shows ~15% win. In the real life it seems that most workloads are not very sensitive to the speed of (accounted) slab allocations. [guro@fb.com: open-code set_page_objcgs() and add some comments, by Johannes] Link: https://lkml.kernel.org/r/20201113001926.GA2934489@carbon.dhcp.thefacebook.com [akpm@linux-foundation.org: fix it for mm-slub-call-account_slab_page-after-slab-page-initialization-fix.patch] Link: https://lkml.kernel.org/r/20201110195753.530157-2-guro@fb.com Signed-off-by: Roman Gushchin Acked-by: Johannes Weiner Reviewed-by: Shakeel Butt Cc: Michal Hocko Cc: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 19 ------------------- 1 file changed, 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index eeb0b52203e9..7a4dd1cb19fe 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -475,19 +475,6 @@ static inline struct obj_cgroup **page_objcgs_check(struct page *page) return (struct obj_cgroup **)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); } -/* - * set_page_objcgs - associate a page with a object cgroups vector - * @page: a pointer to the page struct - * @objcgs: a pointer to the object cgroups vector - * - * Atomically associates a page with a vector of object cgroups. - */ -static inline bool set_page_objcgs(struct page *page, - struct obj_cgroup **objcgs) -{ - return !cmpxchg(&page->memcg_data, 0, (unsigned long)objcgs | - MEMCG_DATA_OBJCGS); -} #else static inline struct obj_cgroup **page_objcgs(struct page *page) { @@ -498,12 +485,6 @@ static inline struct obj_cgroup **page_objcgs_check(struct page *page) { return NULL; } - -static inline bool set_page_objcgs(struct page *page, - struct obj_cgroup **objcgs) -{ - return true; -} #endif static __always_inline bool memcg_stat_item_in_bytes(int idx) -- cgit v1.2.3 From f3344adf38bdb3107d40483dd9501215ad40edce Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Wed, 24 Feb 2021 12:03:15 -0800 Subject: mm: memcontrol: optimize per-lruvec stats counter memory usage The vmstat threshold is 32 (MEMCG_CHARGE_BATCH), Actually the threshold can be as big as MEMCG_CHARGE_BATCH * PAGE_SIZE. It still fits into s32. So introduce struct batched_lruvec_stat to optimize memory usage. The size of struct lruvec_stat is 304 bytes on 64 bit systems. As it is a per-cpu structure. So with this patch, we can save 304 / 2 * ncpu bytes per-memcg per-node where ncpu is the number of the possible CPU. If there are c memory cgroup (include dying cgroup) and n NUMA node in the system. Finally, we can save (152 * ncpu * c * n) bytes. [akpm@linux-foundation.org: fix typo in comment] Link: https://lkml.kernel.org/r/20201210042121.39665-1-songmuchun@bytedance.com Signed-off-by: Muchun Song Reviewed-by: Shakeel Butt Cc: Johannes Weiner Cc: Michal Hocko Cc: Vladimir Davydov Cc: Shakeel Butt Cc: Roman Gushchin Cc: Stephen Rothwell Cc: Chris Down Cc: Yafang Shao Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 7a4dd1cb19fe..41bbf71edd9f 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -92,6 +92,10 @@ struct lruvec_stat { long count[NR_VM_NODE_STAT_ITEMS]; }; +struct batched_lruvec_stat { + s32 count[NR_VM_NODE_STAT_ITEMS]; +}; + /* * Bitmap of shrinker::id corresponding to memcg-aware shrinkers, * which have elements charged to this memcg. @@ -107,11 +111,17 @@ struct memcg_shrinker_map { struct mem_cgroup_per_node { struct lruvec lruvec; - /* Legacy local VM stats */ + /* + * Legacy local VM stats. This should be struct lruvec_stat and + * cannot be optimized to struct batched_lruvec_stat. Because + * the threshold of the lruvec_stat_cpu can be as big as + * MEMCG_CHARGE_BATCH * PAGE_SIZE. It can fit into s32. But this + * filed has no upper limit. + */ struct lruvec_stat __percpu *lruvec_stat_local; /* Subtree VM stats (batched updates) */ - struct lruvec_stat __percpu *lruvec_stat_cpu; + struct batched_lruvec_stat __percpu *lruvec_stat_cpu; atomic_long_t lruvec_stat[NR_VM_NODE_STAT_ITEMS]; unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS]; -- cgit v1.2.3 From 69473e5de87389be6c0fa4a5d574a50c8f904fb3 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Wed, 24 Feb 2021 12:03:23 -0800 Subject: mm: memcontrol: convert NR_ANON_THPS account to pages Currently we use struct per_cpu_nodestat to cache the vmstat counters, which leads to inaccurate statistics especially THP vmstat counters. In the systems with hundreds of processors it can be GBs of memory. For example, for a 96 CPUs system, the threshold is the maximum number of 125. And the per cpu counters can cache 23.4375 GB in total. The THP page is already a form of batched addition (it will add 512 worth of memory in one go) so skipping the batching seems like sensible. Although every THP stats update overflows the per-cpu counter, resorting to atomic global updates. But it can make the statistics more accuracy for the THP vmstat counters. So we convert the NR_ANON_THPS account to pages. This patch is consistent with 8f182270dfec ("mm/swap.c: flush lru pvecs on compound page arrival"). Doing this also can make the unit of vmstat counters more unified. Finally, the unit of the vmstat counters are pages, kB and bytes. The B/KB suffix can tell us that the unit is bytes or kB. The rest which is without suffix are pages. Link: https://lkml.kernel.org/r/20201228164110.2838-3-songmuchun@bytedance.com Signed-off-by: Muchun Song Cc: Greg Kroah-Hartman Cc: Rafael. J. Wysocki Cc: Alexey Dobriyan Cc: Johannes Weiner Cc: Vladimir Davydov Cc: Hugh Dickins Cc: Shakeel Butt Cc: Roman Gushchin Cc: Sami Tolvanen Cc: Feng Tang Cc: NeilBrown Cc: Joonsoo Kim Cc: Randy Dunlap Cc: Michal Hocko Cc: Pankaj Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index b593316bff3d..67d50ef5dd20 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -209,6 +209,19 @@ enum node_stat_item { NR_VM_NODE_STAT_ITEMS }; +/* + * Returns true if the item should be printed in THPs (/proc/vmstat + * currently prints number of anon, file and shmem THPs. But the item + * is charged in pages). + */ +static __always_inline bool vmstat_item_print_in_thp(enum node_stat_item item) +{ + if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) + return false; + + return item == NR_ANON_THPS; +} + /* * Returns true if the value is measured in bytes (most vmstat values are * measured in pages). This defines the API part, the internal representation -- cgit v1.2.3 From bf9ecead53c89d3d2cf60acbc460174ebbcf0027 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Wed, 24 Feb 2021 12:03:27 -0800 Subject: mm: memcontrol: convert NR_FILE_THPS account to pages Currently we use struct per_cpu_nodestat to cache the vmstat counters, which leads to inaccurate statistics especially THP vmstat counters. In the systems with if hundreds of processors it can be GBs of memory. For example, for a 96 CPUs system, the threshold is the maximum number of 125. And the per cpu counters can cache 23.4375 GB in total. The THP page is already a form of batched addition (it will add 512 worth of memory in one go) so skipping the batching seems like sensible. Although every THP stats update overflows the per-cpu counter, resorting to atomic global updates. But it can make the statistics more accuracy for the THP vmstat counters. So we convert the NR_FILE_THPS account to pages. This patch is consistent with 8f182270dfec ("mm/swap.c: flush lru pvecs on compound page arrival"). Doing this also can make the unit of vmstat counters more unified. Finally, the unit of the vmstat counters are pages, kB and bytes. The B/KB suffix can tell us that the unit is bytes or kB. The rest which is without suffix are pages. Link: https://lkml.kernel.org/r/20201228164110.2838-4-songmuchun@bytedance.com Signed-off-by: Muchun Song Cc: Alexey Dobriyan Cc: Feng Tang Cc: Greg Kroah-Hartman Cc: Hugh Dickins Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Michal Hocko Cc: NeilBrown Cc: Pankaj Gupta Cc: Rafael. J. Wysocki Cc: Randy Dunlap Cc: Roman Gushchin Cc: Sami Tolvanen Cc: Shakeel Butt Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 67d50ef5dd20..b751a9898bb6 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -219,7 +219,8 @@ static __always_inline bool vmstat_item_print_in_thp(enum node_stat_item item) if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return false; - return item == NR_ANON_THPS; + return item == NR_ANON_THPS || + item == NR_FILE_THPS; } /* -- cgit v1.2.3 From 57b2847d3c1dc154923578efb47a12302a57d700 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Wed, 24 Feb 2021 12:03:31 -0800 Subject: mm: memcontrol: convert NR_SHMEM_THPS account to pages Currently we use struct per_cpu_nodestat to cache the vmstat counters, which leads to inaccurate statistics especially THP vmstat counters. In the systems with hundreds of processors it can be GBs of memory. For example, for a 96 CPUs system, the threshold is the maximum number of 125. And the per cpu counters can cache 23.4375 GB in total. The THP page is already a form of batched addition (it will add 512 worth of memory in one go) so skipping the batching seems like sensible. Although every THP stats update overflows the per-cpu counter, resorting to atomic global updates. But it can make the statistics more accuracy for the THP vmstat counters. So we convert the NR_SHMEM_THPS account to pages. This patch is consistent with 8f182270dfec ("mm/swap.c: flush lru pvecs on compound page arrival"). Doing this also can make the unit of vmstat counters more unified. Finally, the unit of the vmstat counters are pages, kB and bytes. The B/KB suffix can tell us that the unit is bytes or kB. The rest which is without suffix are pages. Link: https://lkml.kernel.org/r/20201228164110.2838-5-songmuchun@bytedance.com Signed-off-by: Muchun Song Cc: Alexey Dobriyan Cc: Feng Tang Cc: Greg Kroah-Hartman Cc: Hugh Dickins Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Michal Hocko Cc: NeilBrown Cc: Pankaj Gupta Cc: Rafael. J. Wysocki Cc: Randy Dunlap Cc: Roman Gushchin Cc: Sami Tolvanen Cc: Shakeel Butt Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index b751a9898bb6..788837f40b38 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -220,7 +220,8 @@ static __always_inline bool vmstat_item_print_in_thp(enum node_stat_item item) return false; return item == NR_ANON_THPS || - item == NR_FILE_THPS; + item == NR_FILE_THPS || + item == NR_SHMEM_THPS; } /* -- cgit v1.2.3 From a1528e21f8915e16252cda1137fe29672c918361 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Wed, 24 Feb 2021 12:03:35 -0800 Subject: mm: memcontrol: convert NR_SHMEM_PMDMAPPED account to pages Currently we use struct per_cpu_nodestat to cache the vmstat counters, which leads to inaccurate statistics especially THP vmstat counters. In the systems with hundreds of processors it can be GBs of memory. For example, for a 96 CPUs system, the threshold is the maximum number of 125. And the per cpu counters can cache 23.4375 GB in total. The THP page is already a form of batched addition (it will add 512 worth of memory in one go) so skipping the batching seems like sensible. Although every THP stats update overflows the per-cpu counter, resorting to atomic global updates. But it can make the statistics more accuracy for the THP vmstat counters. So we convert the NR_SHMEM_PMDMAPPED account to pages. This patch is consistent with 8f182270dfec ("mm/swap.c: flush lru pvecs on compound page arrival"). Doing this also can make the unit of vmstat counters more unified. Finally, the unit of the vmstat counters are pages, kB and bytes. The B/KB suffix can tell us that the unit is bytes or kB. The rest which is without suffix are pages. Link: https://lkml.kernel.org/r/20201228164110.2838-6-songmuchun@bytedance.com Signed-off-by: Muchun Song Cc: Alexey Dobriyan Cc: Feng Tang Cc: Greg Kroah-Hartman Cc: Hugh Dickins Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Michal Hocko Cc: NeilBrown Cc: Pankaj Gupta Cc: Rafael. J. Wysocki Cc: Randy Dunlap Cc: Roman Gushchin Cc: Sami Tolvanen Cc: Shakeel Butt Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 788837f40b38..7bdbfeeb5c8c 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -221,7 +221,8 @@ static __always_inline bool vmstat_item_print_in_thp(enum node_stat_item item) return item == NR_ANON_THPS || item == NR_FILE_THPS || - item == NR_SHMEM_THPS; + item == NR_SHMEM_THPS || + item == NR_SHMEM_PMDMAPPED; } /* -- cgit v1.2.3 From 380780e71895ae301505ffcec8f954ab3666a4c7 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Wed, 24 Feb 2021 12:03:39 -0800 Subject: mm: memcontrol: convert NR_FILE_PMDMAPPED account to pages Currently we use struct per_cpu_nodestat to cache the vmstat counters, which leads to inaccurate statistics especially THP vmstat counters. In the systems with hundreds of processors it can be GBs of memory. For example, for a 96 CPUs system, the threshold is the maximum number of 125. And the per cpu counters can cache 23.4375 GB in total. The THP page is already a form of batched addition (it will add 512 worth of memory in one go) so skipping the batching seems like sensible. Although every THP stats update overflows the per-cpu counter, resorting to atomic global updates. But it can make the statistics more accuracy for the THP vmstat counters. So we convert the NR_FILE_PMDMAPPED account to pages. This patch is consistent with 8f182270dfec ("mm/swap.c: flush lru pvecs on compound page arrival"). Doing this also can make the unit of vmstat counters more unified. Finally, the unit of the vmstat counters are pages, kB and bytes. The B/KB suffix can tell us that the unit is bytes or kB. The rest which is without suffix are pages. Link: https://lkml.kernel.org/r/20201228164110.2838-7-songmuchun@bytedance.com Signed-off-by: Muchun Song Cc: Alexey Dobriyan Cc: Feng Tang Cc: Greg Kroah-Hartman Cc: Hugh Dickins Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Michal Hocko Cc: NeilBrown Cc: Pankaj Gupta Cc: Rafael. J. Wysocki Cc: Randy Dunlap Cc: Roman Gushchin Cc: Sami Tolvanen Cc: Shakeel Butt Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 7bdbfeeb5c8c..66d68e5d5a0f 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -222,7 +222,8 @@ static __always_inline bool vmstat_item_print_in_thp(enum node_stat_item item) return item == NR_ANON_THPS || item == NR_FILE_THPS || item == NR_SHMEM_THPS || - item == NR_SHMEM_PMDMAPPED; + item == NR_SHMEM_PMDMAPPED || + item == NR_FILE_PMDMAPPED; } /* -- cgit v1.2.3 From b6038942480e574c697ea1a80019bbe586c1d654 Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Wed, 24 Feb 2021 12:03:55 -0800 Subject: mm: memcg: add swapcache stat for memcg v2 This patch adds swapcache stat for the cgroup v2. The swapcache represents the memory that is accounted against both the memory and the swap limit of the cgroup. The main motivation behind exposing the swapcache stat is for enabling users to gracefully migrate from cgroup v1's memsw counter to cgroup v2's memory and swap counters. Cgroup v1's memsw limit allows users to limit the memory+swap usage of a workload but without control on the exact proportion of memory and swap. Cgroup v2 provides separate limits for memory and swap which enables more control on the exact usage of memory and swap individually for the workload. With some little subtleties, the v1's memsw limit can be switched with the sum of the v2's memory and swap limits. However the alternative for memsw usage is not yet available in cgroup v2. Exposing per-cgroup swapcache stat enables that alternative. Adding the memory usage and swap usage and subtracting the swapcache will approximate the memsw usage. This will help in the transparent migration of the workloads depending on memsw usage and limit to v2' memory and swap counters. The reasons these applications are still interested in this approximate memsw usage are: (1) these applications are not really interested in two separate memory and swap usage metrics. A single usage metric is more simple to use and reason about for them. (2) The memsw usage metric hides the underlying system's swap setup from the applications. Applications with multiple instances running in a datacenter with heterogeneous systems (some have swap and some don't) will keep seeing a consistent view of their usage. [akpm@linux-foundation.org: fix CONFIG_SWAP=n build] Link: https://lkml.kernel.org/r/20210108155813.2914586-3-shakeelb@google.com Signed-off-by: Shakeel Butt Acked-by: Michal Hocko Reviewed-by: Roman Gushchin Cc: Johannes Weiner Cc: Muchun Song Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 3 +++ include/linux/swap.h | 6 +++++- 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 66d68e5d5a0f..fc99e9241846 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -206,6 +206,9 @@ enum node_stat_item { NR_KERNEL_SCS_KB, /* measured in KiB */ #endif NR_PAGETABLE, /* used for pagetables */ +#ifdef CONFIG_SWAP + NR_SWAPCACHE, +#endif NR_VM_NODE_STAT_ITEMS }; diff --git a/include/linux/swap.h b/include/linux/swap.h index 3f1f7ae0fbe9..0d64a2bc7e00 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -408,7 +408,11 @@ extern struct address_space *swapper_spaces[]; #define swap_address_space(entry) \ (&swapper_spaces[swp_type(entry)][swp_offset(entry) \ >> SWAP_ADDRESS_SPACE_SHIFT]) -extern unsigned long total_swapcache_pages(void); +static inline unsigned long total_swapcache_pages(void) +{ + return global_node_page_state(NR_SWAPCACHE); +} + extern void show_swap_cache_info(void); extern int add_to_swap(struct page *page); extern void *get_shadow_from_swap_cache(swp_entry_t entry); -- cgit v1.2.3 From c1a660dea3fa616420606f1e206e6d22f7e05c30 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Wed, 24 Feb 2021 12:03:58 -0800 Subject: mm: kmem: make __memcg_kmem_(un)charge static I've noticed that __memcg_kmem_charge() and __memcg_kmem_uncharge() are not used anywhere except memcontrol.c. Yet they are not declared as non-static and are declared in memcontrol.h. This patch makes them static. Link: https://lkml.kernel.org/r/20210108020332.4096911-1-guro@fb.com Signed-off-by: Roman Gushchin Reviewed-by: Shakeel Butt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 41bbf71edd9f..7a38a1517a05 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1592,9 +1592,6 @@ static inline void memcg_set_shrinker_bit(struct mem_cgroup *memcg, #endif #ifdef CONFIG_MEMCG_KMEM -int __memcg_kmem_charge(struct mem_cgroup *memcg, gfp_t gfp, - unsigned int nr_pages); -void __memcg_kmem_uncharge(struct mem_cgroup *memcg, unsigned int nr_pages); int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order); void __memcg_kmem_uncharge_page(struct page *page, int order); -- cgit v1.2.3 From 802f1d522d5fdaefc2b935141bc8fe03d43a99ab Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Wed, 24 Feb 2021 12:04:01 -0800 Subject: mm: page_counter: re-layout structure to reduce false sharing MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When checking a memory cgroup related performance regression [1], from the perf c2c profiling data, we found high false sharing for accessing 'usage' and 'parent'. On 64 bit system, the 'usage' and 'parent' are close to each other, and easy to be in one cacheline (for cacheline size == 64+ B). 'usage' is usally written, while 'parent' is usually read as the cgroup's hierarchical counting nature. So move the 'parent' to the end of the structure to make sure they are in different cache lines. Following are some performance data with the patch, against v5.11-rc1. [ In the data, A means a platform with 2 sockets 48C/96T, B is a platform of 4 sockests 72C/144T, and if a %stddev will be shown bigger than 2%, P100/P50 means number of test tasks equals to 100%/50% of nr_cpu] will-it-scale/malloc1 --------------------- v5.11-rc1 v5.11-rc1+patch A-P100 15782 ± 2% -0.1% 15765 ± 3% will-it-scale.per_process_ops A-P50 21511 +8.9% 23432 will-it-scale.per_process_ops B-P100 9155 +2.2% 9357 will-it-scale.per_process_ops B-P50 10967 +7.1% 11751 ± 2% will-it-scale.per_process_ops will-it-scale/pagefault2 ------------------------ v5.11-rc1 v5.11-rc1+patch A-P100 79028 +3.0% 81411 will-it-scale.per_process_ops A-P50 183960 ± 2% +4.4% 192078 ± 2% will-it-scale.per_process_ops B-P100 85966 +9.9% 94467 ± 3% will-it-scale.per_process_ops B-P50 198195 +9.8% 217526 will-it-scale.per_process_ops fio (4k/1M is block size) ------------------------- v5.11-rc1 v5.11-rc1+patch A-P50-r-4k 16881 ± 2% +1.2% 17081 ± 2% fio.read_bw_MBps A-P50-w-4k 3931 +4.5% 4111 ± 2% fio.write_bw_MBps A-P50-r-1M 15178 -0.2% 15154 fio.read_bw_MBps A-P50-w-1M 3924 +0.1% 3929 fio.write_bw_MBps [1].https://lore.kernel.org/lkml/20201102091543.GM31092@shao2-debian/ Link: https://lkml.kernel.org/r/1611040814-33449-1-git-send-email-feng.tang@intel.com Signed-off-by: Feng Tang Reviewed-by: Roman Gushchin Reviewed-by: Shakeel Butt Acked-by: Johannes Weiner Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_counter.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h index 85bd413e784e..679591301994 100644 --- a/include/linux/page_counter.h +++ b/include/linux/page_counter.h @@ -12,7 +12,6 @@ struct page_counter { unsigned long low; unsigned long high; unsigned long max; - struct page_counter *parent; /* effective memory.min and memory.min usage tracking */ unsigned long emin; @@ -27,6 +26,14 @@ struct page_counter { /* legacy */ unsigned long watermark; unsigned long failcnt; + + /* + * 'parent' is placed here to be far from 'usage' to reduce + * cache false sharing, as 'usage' is written mostly while + * parent is frequently read for cgroup's hierarchical + * counting nature. + */ + struct page_counter *parent; }; #if BITS_PER_LONG == 32 -- cgit v1.2.3 From 6eeb104e114cb6b7391c2d69ff873403858c1f35 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 24 Feb 2021 12:04:15 -0800 Subject: fs: buffer: use raw page_memcg() on locked page alloc_page_buffers() currently uses get_mem_cgroup_from_page() for charging the buffers to the page owner, which does an rcu-protected page->memcg lookup and acquires a reference. But buffer allocation has the page lock held throughout, which pins the page to the memcg and thereby the memcg - neither rcu nor holding an extra reference during the allocation are necessary. Use a raw page_memcg() instead. This was the last user of get_mem_cgroup_from_page(), delete it. Link: https://lkml.kernel.org/r/20210209190126.97842-1-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Reported-by: Muchun Song Reviewed-by: Shakeel Butt Acked-by: Roman Gushchin Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 7a38a1517a05..e6dc793d587d 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -680,8 +680,6 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm); -struct mem_cgroup *get_mem_cgroup_from_page(struct page *page); - struct lruvec *lock_page_lruvec(struct page *page); struct lruvec *lock_page_lruvec_irq(struct page *page); struct lruvec *lock_page_lruvec_irqsave(struct page *page, @@ -1191,11 +1189,6 @@ static inline struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) return NULL; } -static inline struct mem_cgroup *get_mem_cgroup_from_page(struct page *page) -{ - return NULL; -} - static inline void mem_cgroup_put(struct mem_cgroup *memcg) { } -- cgit v1.2.3 From 027b37b552f326aa94ef06c7ea77088b16c41e6e Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Wed, 24 Feb 2021 12:05:46 -0800 Subject: kasan: move _RET_IP_ to inline wrappers Generic mm functions that call KASAN annotations that might report a bug pass _RET_IP_ to them as an argument. This allows KASAN to include the name of the function that called the mm function in its report's header. Now that KASAN has inline wrappers for all of its annotations, move _RET_IP_ to those wrappers to simplify annotation call sites. Link: https://linux-review.googlesource.com/id/I8fb3c06d49671305ee184175a39591bc26647a67 Link: https://lkml.kernel.org/r/5c1490eddf20b436b8c4eeea83fce47687d5e4a4.1610733117.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Reviewed-by: Marco Elver Reviewed-by: Alexander Potapenko Cc: Andrey Ryabinin Cc: Branislav Rankov Cc: Catalin Marinas Cc: Dmitry Vyukov Cc: Evgenii Stepanov Cc: Kevin Brodsky Cc: Peter Collingbourne Cc: Vincenzo Frascino Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 20 +++++++++----------- 1 file changed, 9 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 0aea9e2a2a01..a7254186558a 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -185,19 +185,18 @@ static __always_inline void * __must_check kasan_init_slab_obj( } bool __kasan_slab_free(struct kmem_cache *s, void *object, unsigned long ip); -static __always_inline bool kasan_slab_free(struct kmem_cache *s, void *object, - unsigned long ip) +static __always_inline bool kasan_slab_free(struct kmem_cache *s, void *object) { if (kasan_enabled()) - return __kasan_slab_free(s, object, ip); + return __kasan_slab_free(s, object, _RET_IP_); return false; } void __kasan_slab_free_mempool(void *ptr, unsigned long ip); -static __always_inline void kasan_slab_free_mempool(void *ptr, unsigned long ip) +static __always_inline void kasan_slab_free_mempool(void *ptr) { if (kasan_enabled()) - __kasan_slab_free_mempool(ptr, ip); + __kasan_slab_free_mempool(ptr, _RET_IP_); } void * __must_check __kasan_slab_alloc(struct kmem_cache *s, @@ -241,10 +240,10 @@ static __always_inline void * __must_check kasan_krealloc(const void *object, } void __kasan_kfree_large(void *ptr, unsigned long ip); -static __always_inline void kasan_kfree_large(void *ptr, unsigned long ip) +static __always_inline void kasan_kfree_large(void *ptr) { if (kasan_enabled()) - __kasan_kfree_large(ptr, ip); + __kasan_kfree_large(ptr, _RET_IP_); } bool kasan_save_enable_multi_shot(void); @@ -277,12 +276,11 @@ static inline void *kasan_init_slab_obj(struct kmem_cache *cache, { return (void *)object; } -static inline bool kasan_slab_free(struct kmem_cache *s, void *object, - unsigned long ip) +static inline bool kasan_slab_free(struct kmem_cache *s, void *object) { return false; } -static inline void kasan_slab_free_mempool(void *ptr, unsigned long ip) {} +static inline void kasan_slab_free_mempool(void *ptr) {} static inline void *kasan_slab_alloc(struct kmem_cache *s, void *object, gfp_t flags) { @@ -302,7 +300,7 @@ static inline void *kasan_krealloc(const void *object, size_t new_size, { return (void *)object; } -static inline void kasan_kfree_large(void *ptr, unsigned long ip) {} +static inline void kasan_kfree_large(void *ptr) {} #endif /* CONFIG_KASAN */ -- cgit v1.2.3 From 611806b4bf8dd97a4f3d73f5cf3c2c7730c51eb2 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Wed, 24 Feb 2021 12:05:50 -0800 Subject: kasan: fix bug detection via ksize for HW_TAGS mode The currently existing kasan_check_read/write() annotations are intended to be used for kernel modules that have KASAN compiler instrumentation disabled. Thus, they are only relevant for the software KASAN modes that rely on compiler instrumentation. However there's another use case for these annotations: ksize() checks that the object passed to it is indeed accessible before unpoisoning the whole object. This is currently done via __kasan_check_read(), which is compiled away for the hardware tag-based mode that doesn't rely on compiler instrumentation. This leads to KASAN missing detecting some memory corruptions. Provide another annotation called kasan_check_byte() that is available for all KASAN modes. As the implementation rename and reuse kasan_check_invalid_free(). Use this new annotation in ksize(). To avoid having ksize() as the top frame in the reported stack trace pass _RET_IP_ to __kasan_check_byte(). Also add a new ksize_uaf() test that checks that a use-after-free is detected via ksize() itself, and via plain accesses that happen later. Link: https://linux-review.googlesource.com/id/Iaabf771881d0f9ce1b969f2a62938e99d3308ec5 Link: https://lkml.kernel.org/r/f32ad74a60b28d8402482a38476f02bb7600f620.1610733117.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Reviewed-by: Marco Elver Reviewed-by: Alexander Potapenko Cc: Andrey Ryabinin Cc: Branislav Rankov Cc: Catalin Marinas Cc: Dmitry Vyukov Cc: Evgenii Stepanov Cc: Kevin Brodsky Cc: Peter Collingbourne Cc: Vincenzo Frascino Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan-checks.h | 6 ++++++ include/linux/kasan.h | 17 +++++++++++++++++ 2 files changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kasan-checks.h b/include/linux/kasan-checks.h index ca5e89fb10d3..3d6d22a25bdc 100644 --- a/include/linux/kasan-checks.h +++ b/include/linux/kasan-checks.h @@ -4,6 +4,12 @@ #include +/* + * The annotations present in this file are only relevant for the software + * KASAN modes that rely on compiler instrumentation, and will be optimized + * away for the hardware tag-based KASAN mode. Use kasan_check_byte() instead. + */ + /* * __kasan_check_*: Always available when KASAN is enabled. This may be used * even in compilation units that selectively disable KASAN, but must use KASAN diff --git a/include/linux/kasan.h b/include/linux/kasan.h index a7254186558a..7eaf2d9effb4 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -246,6 +246,19 @@ static __always_inline void kasan_kfree_large(void *ptr) __kasan_kfree_large(ptr, _RET_IP_); } +/* + * Unlike kasan_check_read/write(), kasan_check_byte() is performed even for + * the hardware tag-based mode that doesn't rely on compiler instrumentation. + */ +bool __kasan_check_byte(const void *addr, unsigned long ip); +static __always_inline bool kasan_check_byte(const void *addr) +{ + if (kasan_enabled()) + return __kasan_check_byte(addr, _RET_IP_); + return true; +} + + bool kasan_save_enable_multi_shot(void); void kasan_restore_multi_shot(bool enabled); @@ -301,6 +314,10 @@ static inline void *kasan_krealloc(const void *object, size_t new_size, return (void *)object; } static inline void kasan_kfree_large(void *ptr) {} +static inline bool kasan_check_byte(const void *address) +{ + return true; +} #endif /* CONFIG_KASAN */ -- cgit v1.2.3 From 93f503c3fcd168a43e4a6c875fe2cfafaf8439dc Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Wed, 24 Feb 2021 12:06:10 -0800 Subject: mm: fix prototype warning from kernel test robot Patch series "mm: clean up names and parameters of memmap_init_xxxx functions", v5. This patchset corrects inappropriate function names of memmap_init_xxx, and simplify parameters of functions in the code flow. And also fix a prototype warning reported by lkp. This patch (of 5); Kernel test robot calling make with 'W=1' is triggering warning like below for memmap_init_zone() function. mm/page_alloc.c:6259:23: warning: no previous prototype for 'memmap_init_zone' [-Wmissing-prototypes] 6259 | void __meminit __weak memmap_init_zone(unsigned long size, int nid, | ^~~~~~~~~~~~~~~~ Fix it by adding the function declaration in include/linux/mm.h. Since memmap_init_zone() has a generic version with '__weak', the declaratoin in ia64 header file can be simply removed. Link: https://lkml.kernel.org/r/20210122135956.5946-1-bhe@redhat.com Link: https://lkml.kernel.org/r/20210122135956.5946-2-bhe@redhat.com Signed-off-by: Baoquan He Reported-by: kernel test robot Reviewed-by: Mike Rapoport Reviewed-by: David Hildenbrand Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 7deb7168104d..1c1eabdf112c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2408,6 +2408,8 @@ extern void set_dma_reserve(unsigned long new_dma_reserve); extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long, unsigned long, enum meminit_context, struct vmem_altmap *, int migratetype); +extern void memmap_init(unsigned long size, int nid, + unsigned long zone, unsigned long range_start_pfn); extern void setup_per_zone_wmarks(void); extern int __meminit init_per_zone_wmark_min(void); extern void mem_init(void); -- cgit v1.2.3 From ab28cb6e1e5e59eb8bf3ad399133617414301d3a Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Wed, 24 Feb 2021 12:06:14 -0800 Subject: mm: rename memmap_init() and memmap_init_zone() The current memmap_init_zone() only handles memory region inside one zone, actually memmap_init() does the memmap init of one zone. So rename both of them accordingly. Link: https://lkml.kernel.org/r/20210122135956.5946-3-bhe@redhat.com Signed-off-by: Baoquan He Reviewed-by: Mike Rapoport Reviewed-by: David Hildenbrand Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 1c1eabdf112c..56d0eeae0ce3 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2405,10 +2405,10 @@ extern int __meminit early_pfn_to_nid(unsigned long pfn); #endif extern void set_dma_reserve(unsigned long new_dma_reserve); -extern void memmap_init_zone(unsigned long, int, unsigned long, +extern void memmap_init_range(unsigned long, int, unsigned long, unsigned long, unsigned long, enum meminit_context, struct vmem_altmap *, int migratetype); -extern void memmap_init(unsigned long size, int nid, +extern void memmap_init_zone(unsigned long size, int nid, unsigned long zone, unsigned long range_start_pfn); extern void setup_per_zone_wmarks(void); extern int __meminit init_per_zone_wmark_min(void); -- cgit v1.2.3 From 3256ff83c566235e812498ee1dc806c45a5d5af7 Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Wed, 24 Feb 2021 12:06:17 -0800 Subject: mm: simplify parater of function memmap_init_zone() As David suggested, simply passing 'struct zone *zone' is enough. We can get all needed information from 'struct zone*' easily. Link: https://lkml.kernel.org/r/20210122135956.5946-4-bhe@redhat.com Signed-off-by: Baoquan He Suggested-by: David Hildenbrand Reviewed-by: Mike Rapoport Reviewed-by: David Hildenbrand Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 56d0eeae0ce3..2601a5cce0ef 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2408,8 +2408,7 @@ extern void set_dma_reserve(unsigned long new_dma_reserve); extern void memmap_init_range(unsigned long, int, unsigned long, unsigned long, unsigned long, enum meminit_context, struct vmem_altmap *, int migratetype); -extern void memmap_init_zone(unsigned long size, int nid, - unsigned long zone, unsigned long range_start_pfn); +extern void memmap_init_zone(struct zone *zone); extern void setup_per_zone_wmarks(void); extern int __meminit init_per_zone_wmark_min(void); extern void mem_init(void); -- cgit v1.2.3 From a0cd7a7c4bc004587d1f4785a320f58e72d880eb Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Wed, 24 Feb 2021 12:06:32 -0800 Subject: mm: simplify free_highmem_page() and free_reserved_page() adjust_managed_page_count() as called by free_reserved_page() properly handles pages in a highmem zone, so we can reuse it for free_highmem_page(). We can now get rid of totalhigh_pages_inc() and simplify free_reserved_page(). Link: https://lkml.kernel.org/r/20210126182113.19892-3-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Oscar Salvador Reviewed-by: Anshuman Khandual Cc: Thomas Gleixner Cc: "Peter Zijlstra (Intel)" Cc: Mike Rapoport Cc: Michal Hocko Cc: Wei Yang Cc: "Gustavo A. R. Silva" Cc: Sam Ravnborg Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/highmem-internal.h | 5 ----- include/linux/mm.h | 16 ++-------------- 2 files changed, 2 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h index 1bbe96dc8be6..7902c7d8b55f 100644 --- a/include/linux/highmem-internal.h +++ b/include/linux/highmem-internal.h @@ -127,11 +127,6 @@ static inline unsigned long totalhigh_pages(void) return (unsigned long)atomic_long_read(&_totalhigh_pages); } -static inline void totalhigh_pages_inc(void) -{ - atomic_long_inc(&_totalhigh_pages); -} - static inline void totalhigh_pages_add(long count) { atomic_long_add(count, &_totalhigh_pages); diff --git a/include/linux/mm.h b/include/linux/mm.h index 2601a5cce0ef..76cab132c295 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2310,32 +2310,20 @@ extern void free_initmem(void); extern unsigned long free_reserved_area(void *start, void *end, int poison, const char *s); -#ifdef CONFIG_HIGHMEM -/* - * Free a highmem page into the buddy system, adjusting totalhigh_pages - * and totalram_pages. - */ -extern void free_highmem_page(struct page *page); -#endif - extern void adjust_managed_page_count(struct page *page, long count); extern void mem_init_print_info(const char *str); extern void reserve_bootmem_region(phys_addr_t start, phys_addr_t end); /* Free the reserved page into the buddy system, so it gets managed. */ -static inline void __free_reserved_page(struct page *page) +static inline void free_reserved_page(struct page *page) { ClearPageReserved(page); init_page_count(page); __free_page(page); -} - -static inline void free_reserved_page(struct page *page) -{ - __free_reserved_page(page); adjust_managed_page_count(page, 1); } +#define free_highmem_page(page) free_reserved_page(page) static inline void mark_page_reserved(struct page *page) { -- cgit v1.2.3 From 3b2ebeaf98a028d5dd4ec63095855ef507920276 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 24 Feb 2021 12:06:35 -0800 Subject: mm/gfp: add kernel-doc for gfp_t The generated html will link to the definition of the gfp_t automatically once we define it. Move the one-paragraph overview of GFP flags from the documentation directory into gfp.h and pull gfp.h into the documentation. This generates warnings with clang (https://lkml.kernel.org/r/20210219195509.GA59987@24bbad8f3778), so use a #if 0 to hide it from the compiler for now. Link: https://lkml.kernel.org/r/20210215204909.3824509-1-willy@infradead.org Link: https://lkml.kernel.org/r/20210220003049.GZ2858050@casper.infradead.org Signed-off-by: Matthew Wilcox (Oracle) Acked-by: Mike Rapoport Cc: Nathan Chancellor Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 80544d5c08e7..220cd553a9e7 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -8,6 +8,20 @@ #include #include +/* The typedef is in types.h but we want the documentation here */ +#if 0 +/** + * typedef gfp_t - Memory allocation flags. + * + * GFP flags are commonly used throughout Linux to indicate how memory + * should be allocated. The GFP acronym stands for get_free_pages(), + * the underlying memory allocation function. Not every GFP flag is + * supported by every function which may allocate memory. Most users + * will want to use a plain ``GFP_KERNEL``. + */ +typedef unsigned int __bitwise gfp_t; +#endif + struct vm_area_struct; /* -- cgit v1.2.3 From 0fa5bc4023c188082024833b3deffd5543b93bc9 Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Wed, 24 Feb 2021 12:07:12 -0800 Subject: mm/hugetlb: grab head page refcount once for group of subpages Patch series "mm/hugetlb: follow_hugetlb_page() improvements", v2. While looking at ZONE_DEVICE struct page reuse particularly the last patch[0], I found two possible improvements for follow_hugetlb_page() which is solely used for get_user_pages()/pin_user_pages(). The first patch batches page refcount updates while the second tidies up storing the subpages/vmas. Both together bring the cost of slow variant of gup() cost from ~87.6k usecs to ~5.8k usecs. libhugetlbfs tests seem to pass as well gup_test benchmarks with hugetlbfs vmas. This patch (of 2): follow_hugetlb_page() once it locks the pmd/pud, checks all its N subpages in a huge page and grabs a reference for each one. Similar to gup-fast, have follow_hugetlb_page() grab the head page refcount only after counting all its subpages that are part of the just faulted huge page. Consequently we reduce the number of atomics necessary to pin said huge page, which improves non-fast gup() considerably: - 16G with 1G huge page size gup_test -f /mnt/huge/file -m 16384 -r 10 -L -S -n 512 -w PIN_LONGTERM_BENCHMARK: ~87.6k us -> ~12.8k us Link: https://lkml.kernel.org/r/20210128182632.24562-1-joao.m.martins@oracle.com Link: https://lkml.kernel.org/r/20210128182632.24562-2-joao.m.martins@oracle.com Signed-off-by: Joao Martins Reviewed-by: Mike Kravetz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 76cab132c295..77e64e3eac80 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1187,6 +1187,9 @@ static inline void get_page(struct page *page) } bool __must_check try_grab_page(struct page *page, unsigned int flags); +__maybe_unused struct page *try_grab_compound_head(struct page *page, int refs, + unsigned int flags); + static inline __must_check bool try_get_page(struct page *page) { -- cgit v1.2.3 From 6c26d3108393211ecfd44d89404cfb744027bafd Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Wed, 24 Feb 2021 12:07:19 -0800 Subject: mm/hugetlb: fix some comment typos Fix typos sasitfy to satisfy, reservtion to reservation, hugegpage to hugepage and uniprocesor to uniprocessor in comments. Link: https://lkml.kernel.org/r/20210128112028.64831-1-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Reviewed-by: Souptick Joarder Cc: Mike Kravetz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index b5807f23caf8..ac3cb239a7ec 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -37,7 +37,7 @@ struct hugepage_subpool { struct hstate *hstate; long min_hpages; /* Minimum huge pages or -1 if no minimum. */ long rsv_hpages; /* Pages reserved against global pool to */ - /* sasitfy minimum size. */ + /* satisfy minimum size. */ }; struct resv_map { -- cgit v1.2.3 From bae84953815793f68ddd8edeadd3f4e32676a2c8 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 24 Feb 2021 12:07:32 -0800 Subject: mm/pmem: avoid inserting hugepage PTE entry with fsdax if hugepage support is disabled Differentiate between hardware not supporting hugepages and user disabling THP via 'echo never > /sys/kernel/mm/transparent_hugepage/enabled' For the devdax namespace, the kernel handles the above via the supported_alignment attribute and failing to initialize the namespace if the namespace align value is not supported on the platform. For the fsdax namespace, the kernel will continue to initialize the namespace. This can result in the kernel creating a huge pte entry even though the hardware don't support the same. We do want hugepage support with pmem even if the end-user disabled THP via sysfs file (/sys/kernel/mm/transparent_hugepage/enabled). Hence differentiate between hardware/firmware lacking support vs user-controlled disable of THP and prevent a huge fault if the hardware lacks hugepage support. Link: https://lkml.kernel.org/r/20210205023956.417587-1-aneesh.kumar@linux.ibm.com Signed-off-by: Aneesh Kumar K.V Reviewed-by: Dan Williams Cc: "Kirill A . Shutemov" Cc: Jan Kara Cc: David Hildenbrand Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 6a19f35f836b..ba973efcd369 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -78,6 +78,7 @@ static inline vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, } enum transparent_hugepage_flag { + TRANSPARENT_HUGEPAGE_NEVER_DAX, TRANSPARENT_HUGEPAGE_FLAG, TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, @@ -123,6 +124,13 @@ extern unsigned long transparent_hugepage_flags; */ static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) { + + /* + * If the hardware/firmware marked hugepage support disabled. + */ + if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_NEVER_DAX)) + return false; + if (vma->vm_flags & VM_NOHUGEPAGE) return false; @@ -134,12 +142,7 @@ static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_FLAG)) return true; - /* - * For dax vmas, try to always use hugepage mappings. If the kernel does - * not support hugepages, fsdax mappings will fallback to PAGE_SIZE - * mappings, and device-dax namespaces, that try to guarantee a given - * mapping size, will fail to enable - */ + if (vma_is_dax(vma)) return true; -- cgit v1.2.3 From c2135f7c570bc274035834848d9bf46ea89ba763 Mon Sep 17 00:00:00 2001 From: Alex Shi Date: Wed, 24 Feb 2021 12:08:01 -0800 Subject: mm/vmscan: __isolate_lru_page_prepare() cleanup The function just returns 2 results, so using a 'switch' to deal with its result is unnecessary. Also simplify it to a bool func as Vlastimil suggested. Also remove 'goto' by reusing list_move(), and take Matthew Wilcox's suggestion to update comments in function. Link: https://lkml.kernel.org/r/728874d7-2d93-4049-68c1-dcc3b2d52ccd@linux.alibaba.com Signed-off-by: Alex Shi Reviewed-by: Andrew Morton Acked-by: Vlastimil Babka Cc: Matthew Wilcox Cc: Hugh Dickins Cc: Yu Zhao Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 0d64a2bc7e00..32f665b1ee85 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -356,7 +356,7 @@ extern void lru_cache_add_inactive_or_unevictable(struct page *page, extern unsigned long zone_reclaimable_pages(struct zone *zone); extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask); -extern int __isolate_lru_page_prepare(struct page *page, isolate_mode_t mode); +extern bool __isolate_lru_page_prepare(struct page *page, isolate_mode_t mode); extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, -- cgit v1.2.3 From f90d8191ac864df33b1898bc7edc54eaa24e22bc Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Wed, 24 Feb 2021 12:08:13 -0800 Subject: include/linux/mm_inline.h: shuffle lru list addition and deletion functions These functions will call page_lru() in the following patches. Move them below page_lru() to avoid the forward declaration. Link: https://lore.kernel.org/linux-mm/20201207220949.830352-3-yuzhao@google.com/ Link: https://lkml.kernel.org/r/20210122220600.906146-3-yuzhao@google.com Signed-off-by: Yu Zhao Acked-by: Vlastimil Babka Reviewed-by: Miaohe Lin Cc: Alex Shi Cc: Hugh Dickins Cc: Johannes Weiner Cc: Matthew Wilcox Cc: Michal Hocko Cc: Roman Gushchin Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_inline.h | 42 +++++++++++++++++++++--------------------- 1 file changed, 21 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 8fc71e9d7bb0..2889741f450a 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -45,27 +45,6 @@ static __always_inline void update_lru_size(struct lruvec *lruvec, #endif } -static __always_inline void add_page_to_lru_list(struct page *page, - struct lruvec *lruvec, enum lru_list lru) -{ - update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page)); - list_add(&page->lru, &lruvec->lists[lru]); -} - -static __always_inline void add_page_to_lru_list_tail(struct page *page, - struct lruvec *lruvec, enum lru_list lru) -{ - update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page)); - list_add_tail(&page->lru, &lruvec->lists[lru]); -} - -static __always_inline void del_page_from_lru_list(struct page *page, - struct lruvec *lruvec, enum lru_list lru) -{ - list_del(&page->lru); - update_lru_size(lruvec, lru, page_zonenum(page), -thp_nr_pages(page)); -} - /** * page_lru_base_type - which LRU list type should a page be on? * @page: the page to test @@ -125,4 +104,25 @@ static __always_inline enum lru_list page_lru(struct page *page) } return lru; } + +static __always_inline void add_page_to_lru_list(struct page *page, + struct lruvec *lruvec, enum lru_list lru) +{ + update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page)); + list_add(&page->lru, &lruvec->lists[lru]); +} + +static __always_inline void add_page_to_lru_list_tail(struct page *page, + struct lruvec *lruvec, enum lru_list lru) +{ + update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page)); + list_add_tail(&page->lru, &lruvec->lists[lru]); +} + +static __always_inline void del_page_from_lru_list(struct page *page, + struct lruvec *lruvec, enum lru_list lru) +{ + list_del(&page->lru); + update_lru_size(lruvec, lru, page_zonenum(page), -thp_nr_pages(page)); +} #endif -- cgit v1.2.3 From 3a9c9788a3149d9745b7eb2eae811e57ef3b127c Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Wed, 24 Feb 2021 12:08:17 -0800 Subject: mm: don't pass "enum lru_list" to lru list addition functions The "enum lru_list" parameter to add_page_to_lru_list() and add_page_to_lru_list_tail() is redundant in the sense that it can be extracted from the "struct page" parameter by page_lru(). A caveat is that we need to make sure PageActive() or PageUnevictable() is correctly set or cleared before calling these two functions. And they are indeed. Link: https://lore.kernel.org/linux-mm/20201207220949.830352-4-yuzhao@google.com/ Link: https://lkml.kernel.org/r/20210122220600.906146-4-yuzhao@google.com Signed-off-by: Yu Zhao Cc: Alex Shi Cc: Hugh Dickins Cc: Johannes Weiner Cc: Matthew Wilcox Cc: Michal Hocko Cc: Roman Gushchin Cc: Vladimir Davydov Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_inline.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 2889741f450a..130ba3201d3f 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -106,15 +106,19 @@ static __always_inline enum lru_list page_lru(struct page *page) } static __always_inline void add_page_to_lru_list(struct page *page, - struct lruvec *lruvec, enum lru_list lru) + struct lruvec *lruvec) { + enum lru_list lru = page_lru(page); + update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page)); list_add(&page->lru, &lruvec->lists[lru]); } static __always_inline void add_page_to_lru_list_tail(struct page *page, - struct lruvec *lruvec, enum lru_list lru) + struct lruvec *lruvec) { + enum lru_list lru = page_lru(page); + update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page)); list_add_tail(&page->lru, &lruvec->lists[lru]); } -- cgit v1.2.3 From 46ae6b2cc2a47904a368d238425531ea91f3a2a5 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Wed, 24 Feb 2021 12:08:25 -0800 Subject: mm/swap.c: don't pass "enum lru_list" to del_page_from_lru_list() The parameter is redundant in the sense that it can be potentially extracted from the "struct page" parameter by page_lru(). We need to make sure that existing PageActive() or PageUnevictable() remains until the function returns. A few places don't conform, and simple reordering fixes them. This patch may have left page_off_lru() seemingly odd, and we'll take care of it in the next patch. Link: https://lore.kernel.org/linux-mm/20201207220949.830352-6-yuzhao@google.com/ Link: https://lkml.kernel.org/r/20210122220600.906146-6-yuzhao@google.com Signed-off-by: Yu Zhao Cc: Alex Shi Cc: Hugh Dickins Cc: Johannes Weiner Cc: Matthew Wilcox Cc: Michal Hocko Cc: Roman Gushchin Cc: Vladimir Davydov Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_inline.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 130ba3201d3f..ffacc6273678 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -124,9 +124,10 @@ static __always_inline void add_page_to_lru_list_tail(struct page *page, } static __always_inline void del_page_from_lru_list(struct page *page, - struct lruvec *lruvec, enum lru_list lru) + struct lruvec *lruvec) { list_del(&page->lru); - update_lru_size(lruvec, lru, page_zonenum(page), -thp_nr_pages(page)); + update_lru_size(lruvec, page_lru(page), page_zonenum(page), + -thp_nr_pages(page)); } #endif -- cgit v1.2.3 From 875601796267214f286d3581fe74f2805d060fe8 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Wed, 24 Feb 2021 12:08:28 -0800 Subject: mm: add __clear_page_lru_flags() to replace page_off_lru() Similar to page_off_lru(), the new function does non-atomic clearing of PageLRU() in addition to PageActive() and PageUnevictable(), on a page that has no references left. If PageActive() and PageUnevictable() are both set, refuse to clear either and leave them to bad_page(). This is a behavior change that is meant to help debug. Link: https://lore.kernel.org/linux-mm/20201207220949.830352-7-yuzhao@google.com/ Link: https://lkml.kernel.org/r/20210122220600.906146-7-yuzhao@google.com Signed-off-by: Yu Zhao Cc: Alex Shi Cc: Hugh Dickins Cc: Johannes Weiner Cc: Matthew Wilcox Cc: Michal Hocko Cc: Roman Gushchin Cc: Vladimir Davydov Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_inline.h | 28 ++++++++++------------------ 1 file changed, 10 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index ffacc6273678..ef3fd79222e5 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -61,27 +61,19 @@ static inline enum lru_list page_lru_base_type(struct page *page) } /** - * page_off_lru - which LRU list was page on? clearing its lru flags. - * @page: the page to test - * - * Returns the LRU list a page was on, as an index into the array of LRU - * lists; and clears its Unevictable or Active flags, ready for freeing. + * __clear_page_lru_flags - clear page lru flags before releasing a page + * @page: the page that was on lru and now has a zero reference */ -static __always_inline enum lru_list page_off_lru(struct page *page) +static __always_inline void __clear_page_lru_flags(struct page *page) { - enum lru_list lru; + __ClearPageLRU(page); - if (PageUnevictable(page)) { - __ClearPageUnevictable(page); - lru = LRU_UNEVICTABLE; - } else { - lru = page_lru_base_type(page); - if (PageActive(page)) { - __ClearPageActive(page); - lru += LRU_ACTIVE; - } - } - return lru; + /* this shouldn't happen, so leave the flags to bad_page() */ + if (PageActive(page) && PageUnevictable(page)) + return; + + __ClearPageActive(page); + __ClearPageUnevictable(page); } /** -- cgit v1.2.3 From bc7112719e1e80e4208eef3fc9bd8d2b6c263e7d Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Wed, 24 Feb 2021 12:08:32 -0800 Subject: mm: VM_BUG_ON lru page flags Move scattered VM_BUG_ONs to two essential places that cover all lru list additions and deletions. Link: https://lore.kernel.org/linux-mm/20201207220949.830352-8-yuzhao@google.com/ Link: https://lkml.kernel.org/r/20210122220600.906146-8-yuzhao@google.com Signed-off-by: Yu Zhao Cc: Alex Shi Cc: Hugh Dickins Cc: Johannes Weiner Cc: Matthew Wilcox Cc: Michal Hocko Cc: Roman Gushchin Cc: Vladimir Davydov Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_inline.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index ef3fd79222e5..6d907a4dd6ad 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -66,6 +66,8 @@ static inline enum lru_list page_lru_base_type(struct page *page) */ static __always_inline void __clear_page_lru_flags(struct page *page) { + VM_BUG_ON_PAGE(!PageLRU(page), page); + __ClearPageLRU(page); /* this shouldn't happen, so leave the flags to bad_page() */ @@ -87,6 +89,8 @@ static __always_inline enum lru_list page_lru(struct page *page) { enum lru_list lru; + VM_BUG_ON_PAGE(PageActive(page) && PageUnevictable(page), page); + if (PageUnevictable(page)) lru = LRU_UNEVICTABLE; else { -- cgit v1.2.3 From c1770e34f3e7640887d8129fc05d13fe17101301 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Wed, 24 Feb 2021 12:08:36 -0800 Subject: include/linux/mm_inline.h: fold page_lru_base_type() into its sole caller We've removed all other references to this function. Link: https://lore.kernel.org/linux-mm/20201207220949.830352-9-yuzhao@google.com/ Link: https://lkml.kernel.org/r/20210122220600.906146-9-yuzhao@google.com Signed-off-by: Yu Zhao Reviewed-by: Alex Shi Cc: Hugh Dickins Cc: Johannes Weiner Cc: Matthew Wilcox Cc: Michal Hocko Cc: Roman Gushchin Cc: Vladimir Davydov Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_inline.h | 27 ++++++--------------------- 1 file changed, 6 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 6d907a4dd6ad..7183c7a03f09 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -45,21 +45,6 @@ static __always_inline void update_lru_size(struct lruvec *lruvec, #endif } -/** - * page_lru_base_type - which LRU list type should a page be on? - * @page: the page to test - * - * Used for LRU list index arithmetic. - * - * Returns the base LRU type - file or anon - @page should be on. - */ -static inline enum lru_list page_lru_base_type(struct page *page) -{ - if (page_is_file_lru(page)) - return LRU_INACTIVE_FILE; - return LRU_INACTIVE_ANON; -} - /** * __clear_page_lru_flags - clear page lru flags before releasing a page * @page: the page that was on lru and now has a zero reference @@ -92,12 +77,12 @@ static __always_inline enum lru_list page_lru(struct page *page) VM_BUG_ON_PAGE(PageActive(page) && PageUnevictable(page), page); if (PageUnevictable(page)) - lru = LRU_UNEVICTABLE; - else { - lru = page_lru_base_type(page); - if (PageActive(page)) - lru += LRU_ACTIVE; - } + return LRU_UNEVICTABLE; + + lru = page_is_file_lru(page) ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON; + if (PageActive(page)) + lru += LRU_ACTIVE; + return lru; } -- cgit v1.2.3 From 289ccba18af436f2b65ec69b2be1b086ec9f24a4 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Wed, 24 Feb 2021 12:08:40 -0800 Subject: include/linux/mm_inline.h: fold __update_lru_size() into its sole caller All other references to the function were removed after commit a892cb6b977f ("mm/vmscan.c: use update_lru_size() in update_lru_sizes()"). Link: https://lore.kernel.org/linux-mm/20201207220949.830352-10-yuzhao@google.com/ Link: https://lkml.kernel.org/r/20210122220600.906146-10-yuzhao@google.com Signed-off-by: Yu Zhao Reviewed-by: Alex Shi Cc: Hugh Dickins Cc: Johannes Weiner Cc: Matthew Wilcox Cc: Michal Hocko Cc: Roman Gushchin Cc: Vladimir Davydov Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_inline.h | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 7183c7a03f09..355ea1ee32bd 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -24,7 +24,7 @@ static inline int page_is_file_lru(struct page *page) return !PageSwapBacked(page); } -static __always_inline void __update_lru_size(struct lruvec *lruvec, +static __always_inline void update_lru_size(struct lruvec *lruvec, enum lru_list lru, enum zone_type zid, int nr_pages) { @@ -33,13 +33,6 @@ static __always_inline void __update_lru_size(struct lruvec *lruvec, __mod_lruvec_state(lruvec, NR_LRU_BASE + lru, nr_pages); __mod_zone_page_state(&pgdat->node_zones[zid], NR_ZONE_LRU_BASE + lru, nr_pages); -} - -static __always_inline void update_lru_size(struct lruvec *lruvec, - enum lru_list lru, enum zone_type zid, - int nr_pages) -{ - __update_lru_size(lruvec, lru, zid, nr_pages); #ifdef CONFIG_MEMCG mem_cgroup_update_lru_size(lruvec, lru, zid, nr_pages); #endif -- cgit v1.2.3 From 2091339d59e7808e9b39a79f48e3d17ef7389b97 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Wed, 24 Feb 2021 12:08:44 -0800 Subject: mm/vmscan.c: make lruvec_lru_size() static All other references to the function were removed after commit b910718a948a ("mm: vmscan: detect file thrashing at the reclaim root"). Link: https://lore.kernel.org/linux-mm/20201207220949.830352-11-yuzhao@google.com/ Link: https://lkml.kernel.org/r/20210122220600.906146-11-yuzhao@google.com Signed-off-by: Yu Zhao Reviewed-by: Alex Shi Cc: Hugh Dickins Cc: Johannes Weiner Cc: Matthew Wilcox Cc: Michal Hocko Cc: Roman Gushchin Cc: Vladimir Davydov Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index fc99e9241846..9198b7ade85f 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -892,8 +892,6 @@ static inline struct pglist_data *lruvec_pgdat(struct lruvec *lruvec) #endif } -extern unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx); - #ifdef CONFIG_HAVE_MEMORYLESS_NODES int local_memory_node(int node_id); #else -- cgit v1.2.3 From d6995da311221a05c8aef3bda2629e5cb14c7302 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Wed, 24 Feb 2021 12:08:51 -0800 Subject: hugetlb: use page.private for hugetlb specific page flags Patch series "create hugetlb flags to consolidate state", v3. While discussing a series of hugetlb fixes in [1], it became evident that the hugetlb specific page state information is stored in a somewhat haphazard manner. Code dealing with state information would be easier to read, understand and maintain if this information was stored in a consistent manner. This series uses page.private of the hugetlb head page for storing a set of hugetlb specific page flags. Routines are priovided for test, set and clear of the flags. [1] https://lore.kernel.org/r/20210106084739.63318-1-songmuchun@bytedance.com This patch (of 4): As hugetlbfs evolved, state information about hugetlb pages was added. One 'convenient' way of doing this was to use available fields in tail pages. Over time, it has become difficult to know the meaning or contents of fields simply by looking at a small bit of code. Sometimes, the naming is just confusing. For example: The PagePrivate flag indicates a huge page reservation was consumed and needs to be restored if an error is encountered and the page is freed before it is instantiated. The page.private field contains the pointer to a subpool if the page is associated with one. In an effort to make the code more readable, use page.private to contain hugetlb specific page flags. These flags will have test, set and clear functions similar to those used for 'normal' page flags. More importantly, an enum of flag values will be created with names that actually reflect their purpose. In this patch, - Create infrastructure for hugetlb specific page flag functions - Move subpool pointer to page[1].private to make way for flags Create routines with meaningful names to modify subpool field - Use new HPageRestoreReserve flag instead of PagePrivate Conversion of other state information will happen in subsequent patches. Link: https://lkml.kernel.org/r/20210122195231.324857-1-mike.kravetz@oracle.com Link: https://lkml.kernel.org/r/20210122195231.324857-2-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Reviewed-by: Oscar Salvador Acked-by: Michal Hocko Cc: Naoya Horiguchi Cc: Muchun Song Cc: David Hildenbrand Cc: Matthew Wilcox Cc: Miaohe Lin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 68 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 68 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index ac3cb239a7ec..249c65e1d8ca 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -472,6 +472,60 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long flags); #endif /* HAVE_ARCH_HUGETLB_UNMAPPED_AREA */ +/* + * huegtlb page specific state flags. These flags are located in page.private + * of the hugetlb head page. Functions created via the below macros should be + * used to manipulate these flags. + * + * HPG_restore_reserve - Set when a hugetlb page consumes a reservation at + * allocation time. Cleared when page is fully instantiated. Free + * routine checks flag to restore a reservation on error paths. + */ +enum hugetlb_page_flags { + HPG_restore_reserve = 0, + __NR_HPAGEFLAGS, +}; + +/* + * Macros to create test, set and clear function definitions for + * hugetlb specific page flags. + */ +#ifdef CONFIG_HUGETLB_PAGE +#define TESTHPAGEFLAG(uname, flname) \ +static inline int HPage##uname(struct page *page) \ + { return test_bit(HPG_##flname, &(page->private)); } + +#define SETHPAGEFLAG(uname, flname) \ +static inline void SetHPage##uname(struct page *page) \ + { set_bit(HPG_##flname, &(page->private)); } + +#define CLEARHPAGEFLAG(uname, flname) \ +static inline void ClearHPage##uname(struct page *page) \ + { clear_bit(HPG_##flname, &(page->private)); } +#else +#define TESTHPAGEFLAG(uname, flname) \ +static inline int HPage##uname(struct page *page) \ + { return 0; } + +#define SETHPAGEFLAG(uname, flname) \ +static inline void SetHPage##uname(struct page *page) \ + { } + +#define CLEARHPAGEFLAG(uname, flname) \ +static inline void ClearHPage##uname(struct page *page) \ + { } +#endif + +#define HPAGEFLAG(uname, flname) \ + TESTHPAGEFLAG(uname, flname) \ + SETHPAGEFLAG(uname, flname) \ + CLEARHPAGEFLAG(uname, flname) \ + +/* + * Create functions associated with hugetlb page flags + */ +HPAGEFLAG(RestoreReserve, restore_reserve) + #ifdef CONFIG_HUGETLB_PAGE #define HSTATE_NAME_LEN 32 @@ -531,6 +585,20 @@ extern unsigned int default_hstate_idx; #define default_hstate (hstates[default_hstate_idx]) +/* + * hugetlb page subpool pointer located in hpage[1].private + */ +static inline struct hugepage_subpool *hugetlb_page_subpool(struct page *hpage) +{ + return (struct hugepage_subpool *)(hpage+1)->private; +} + +static inline void hugetlb_set_page_subpool(struct page *hpage, + struct hugepage_subpool *subpool) +{ + set_page_private(hpage+1, (unsigned long)subpool); +} + static inline struct hstate *hstate_file(struct file *f) { return hstate_inode(file_inode(f)); -- cgit v1.2.3 From 8f251a3d5ce3bdea73bd045ed35db64f32e0d0d9 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Wed, 24 Feb 2021 12:08:56 -0800 Subject: hugetlb: convert page_huge_active() HPageMigratable flag Use the new hugetlb page specific flag HPageMigratable to replace the page_huge_active interfaces. By it's name, page_huge_active implied that a huge page was on the active list. However, that is not really what code checking the flag wanted to know. It really wanted to determine if the huge page could be migrated. This happens when the page is actually added to the page cache and/or task page table. This is the reasoning behind the name change. The VM_BUG_ON_PAGE() calls in the *_huge_active() interfaces are not really necessary as we KNOW the page is a hugetlb page. Therefore, they are removed. The routine page_huge_active checked for PageHeadHuge before testing the active bit. This is unnecessary in the case where we hold a reference or lock and know it is a hugetlb head page. page_huge_active is also called without holding a reference or lock (scan_movable_pages), and can race with code freeing the page. The extra check in page_huge_active shortened the race window, but did not prevent the race. Offline code calling scan_movable_pages already deals with these races, so removing the check is acceptable. Add comment to racy code. [songmuchun@bytedance.com: remove set_page_huge_active() declaration from include/linux/hugetlb.h] Link: https://lkml.kernel.org/r/CAMZfGtUda+KoAZscU0718TN61cSFwp4zy=y2oZ=+6Z2TAZZwng@mail.gmail.com Link: https://lkml.kernel.org/r/20210122195231.324857-3-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Reviewed-by: Oscar Salvador Reviewed-by: Muchun Song Reviewed-by: Miaohe Lin Acked-by: Michal Hocko Cc: David Hildenbrand Cc: Matthew Wilcox Cc: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 7 +++++-- include/linux/page-flags.h | 6 ------ 2 files changed, 5 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 249c65e1d8ca..77f2a032fe32 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -480,9 +480,13 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, * HPG_restore_reserve - Set when a hugetlb page consumes a reservation at * allocation time. Cleared when page is fully instantiated. Free * routine checks flag to restore a reservation on error paths. + * HPG_migratable - Set after a newly allocated page is added to the page + * cache and/or page tables. Indicates the page is a candidate for + * migration. */ enum hugetlb_page_flags { HPG_restore_reserve = 0, + HPG_migratable, __NR_HPAGEFLAGS, }; @@ -525,6 +529,7 @@ static inline void ClearHPage##uname(struct page *page) \ * Create functions associated with hugetlb page flags */ HPAGEFLAG(RestoreReserve, restore_reserve) +HPAGEFLAG(Migratable, migratable) #ifdef CONFIG_HUGETLB_PAGE @@ -838,8 +843,6 @@ static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, } #endif -void set_page_huge_active(struct page *page); - #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index ec5d0290e0ee..db914477057b 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -592,15 +592,9 @@ static inline void ClearPageCompound(struct page *page) #ifdef CONFIG_HUGETLB_PAGE int PageHuge(struct page *page); int PageHeadHuge(struct page *page); -bool page_huge_active(struct page *page); #else TESTPAGEFLAG_FALSE(Huge) TESTPAGEFLAG_FALSE(HeadHuge) - -static inline bool page_huge_active(struct page *page) -{ - return 0; -} #endif -- cgit v1.2.3 From 9157c31186c358c5750dea50ac5705d61d7fc917 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Wed, 24 Feb 2021 12:09:00 -0800 Subject: hugetlb: convert PageHugeTemporary() to HPageTemporary flag Use new hugetlb specific HPageTemporary flag to replace the PageHugeTemporary() interfaces. PageHugeTemporary does contain a PageHuge() check. However, this interface is only used within hugetlb code where we know we are dealing with a hugetlb page. Therefore, the check can be eliminated. Link: https://lkml.kernel.org/r/20210122195231.324857-5-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Reviewed-by: Oscar Salvador Reviewed-by: Muchun Song Acked-by: Michal Hocko Cc: David Hildenbrand Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 77f2a032fe32..e97498a21010 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -483,10 +483,15 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, * HPG_migratable - Set after a newly allocated page is added to the page * cache and/or page tables. Indicates the page is a candidate for * migration. + * HPG_temporary - - Set on a page that is temporarily allocated from the buddy + * allocator. Typically used for migration target pages when no pages + * are available in the pool. The hugetlb free page path will + * immediately free pages with this flag set to the buddy allocator. */ enum hugetlb_page_flags { HPG_restore_reserve = 0, HPG_migratable, + HPG_temporary, __NR_HPAGEFLAGS, }; @@ -530,6 +535,7 @@ static inline void ClearHPage##uname(struct page *page) \ */ HPAGEFLAG(RestoreReserve, restore_reserve) HPAGEFLAG(Migratable, migratable) +HPAGEFLAG(Temporary, temporary) #ifdef CONFIG_HUGETLB_PAGE -- cgit v1.2.3 From 6c037149014027d50175da5be4ae4531374dcbe0 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Wed, 24 Feb 2021 12:09:04 -0800 Subject: hugetlb: convert PageHugeFreed to HPageFreed flag Use new hugetlb specific HPageFreed flag to replace the PageHugeFreed interfaces. Link: https://lkml.kernel.org/r/20210122195231.324857-6-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Reviewed-by: Oscar Salvador Reviewed-by: Muchun Song Acked-by: Michal Hocko Cc: David Hildenbrand Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Michal Hocko Cc: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index e97498a21010..eb2682fd97b6 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -487,11 +487,13 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, * allocator. Typically used for migration target pages when no pages * are available in the pool. The hugetlb free page path will * immediately free pages with this flag set to the buddy allocator. + * HPG_freed - Set when page is on the free lists. */ enum hugetlb_page_flags { HPG_restore_reserve = 0, HPG_migratable, HPG_temporary, + HPG_freed, __NR_HPAGEFLAGS, }; @@ -536,6 +538,7 @@ static inline void ClearHPage##uname(struct page *page) \ HPAGEFLAG(RestoreReserve, restore_reserve) HPAGEFLAG(Migratable, migratable) HPAGEFLAG(Temporary, temporary) +HPAGEFLAG(Freed, freed) #ifdef CONFIG_HUGETLB_PAGE -- cgit v1.2.3 From d95c0337774b1dc74d271e7475a96fe8838332ea Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Wed, 24 Feb 2021 12:09:08 -0800 Subject: include/linux/hugetlb.h: add synchronization information for new hugetlb specific flags Add comments, no functional change. Link: https://lkml.kernel.org/r/62a80585-2a73-10cc-4a2d-5721540d4ad2@oracle.com Signed-off-by: Mike Kravetz Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index eb2682fd97b6..3a541c6cf5c3 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -480,14 +480,24 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, * HPG_restore_reserve - Set when a hugetlb page consumes a reservation at * allocation time. Cleared when page is fully instantiated. Free * routine checks flag to restore a reservation on error paths. + * Synchronization: Examined or modified by code that knows it has + * the only reference to page. i.e. After allocation but before use + * or when the page is being freed. * HPG_migratable - Set after a newly allocated page is added to the page * cache and/or page tables. Indicates the page is a candidate for * migration. + * Synchronization: Initially set after new page allocation with no + * locking. When examined and modified during migration processing + * (isolate, migrate, putback) the hugetlb_lock is held. * HPG_temporary - - Set on a page that is temporarily allocated from the buddy * allocator. Typically used for migration target pages when no pages * are available in the pool. The hugetlb free page path will * immediately free pages with this flag set to the buddy allocator. + * Synchronization: Can be set after huge page allocation from buddy when + * code knows it has only reference. All other examinations and + * modifications require hugetlb_lock. * HPG_freed - Set when page is on the free lists. + * Synchronization: hugetlb_lock held for examination and modification. */ enum hugetlb_page_flags { HPG_restore_reserve = 0, -- cgit v1.2.3 From 33b8f84a4ee78491a8f4f9e4c5520c9da4a10983 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Wed, 24 Feb 2021 12:09:54 -0800 Subject: mm/hugetlb: change hugetlb_reserve_pages() to type bool While reviewing a bug in hugetlb_reserve_pages, it was noticed that all callers ignore the return value. Any failure is considered an ENOMEM error by the callers. Change the function to be of type bool. The function will return true if the reservation was successful, false otherwise. Callers currently assume a zero return code indicates success. Change the callers to look for true to indicate success. No functional change, only code cleanup. Link: https://lkml.kernel.org/r/20201221192542.15732-1-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Reviewed-by: Matthew Wilcox (Oracle) Cc: David Hildenbrand Cc: Dan Carpenter Cc: Michal Hocko Cc: Davidlohr Bueso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 3a541c6cf5c3..cccd1aab69dd 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -139,7 +139,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, pte_t *dst_pte, unsigned long dst_addr, unsigned long src_addr, struct page **pagep); -int hugetlb_reserve_pages(struct inode *inode, long from, long to, +bool hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, vm_flags_t vm_flags); long hugetlb_unreserve_pages(struct inode *inode, long start, long end, -- cgit v1.2.3 From a553e3cd2053501b658feec2be9a3b662eb1b22b Mon Sep 17 00:00:00 2001 From: Chengyang Fan Date: Wed, 24 Feb 2021 12:10:28 -0800 Subject: mm/migrate: remove unneeded semicolons Remove superfluous semicolons after function definitions. Link: https://lkml.kernel.org/r/20210115110131.2359683-1-cy.fan@huawei.com Signed-off-by: Chengyang Fan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 4594838a0f7c..3a389633b68f 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -89,7 +89,7 @@ extern int PageMovable(struct page *page); extern void __SetPageMovable(struct page *page, struct address_space *mapping); extern void __ClearPageMovable(struct page *page); #else -static inline int PageMovable(struct page *page) { return 0; }; +static inline int PageMovable(struct page *page) { return 0; } static inline void __SetPageMovable(struct page *page, struct address_space *mapping) { -- cgit v1.2.3 From 4e096a18867a5a989b510f6999d9c6b6622e8f7b Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Tue, 23 Feb 2021 08:01:26 +0100 Subject: net: introduce CAN specific pointer in the struct net_device Since 20dd3850bcf8 ("can: Speed up CAN frame receiption by using ml_priv") the CAN framework uses per device specific data in the AF_CAN protocol. For this purpose the struct net_device->ml_priv is used. Later the ml_priv usage in CAN was extended for other users, one of them being CAN_J1939. Later in the kernel ml_priv was converted to an union, used by other drivers. E.g. the tun driver started storing it's stats pointer. Since tun devices can claim to be a CAN device, CAN specific protocols will wrongly interpret this pointer, which will cause system crashes. Mostly this issue is visible in the CAN_J1939 stack. To fix this issue, we request a dedicated CAN pointer within the net_device struct. Reported-by: syzbot+5138c4dd15a0401bec7b@syzkaller.appspotmail.com Fixes: 20dd3850bcf8 ("can: Speed up CAN frame receiption by using ml_priv") Fixes: ffd956eef69b ("can: introduce CAN midlayer private and allocate it automatically") Fixes: 9d71dd0c7009 ("can: add support of SAE J1939 protocol") Fixes: 497a5757ce4e ("tun: switch to net core provided statistics counters") Signed-off-by: Oleksij Rempel Link: https://lore.kernel.org/r/20210223070127.4538-1-o.rempel@pengutronix.de Signed-off-by: Jakub Kicinski --- include/linux/can/can-ml.h | 12 ++++++++++++ include/linux/netdevice.h | 34 +++++++++++++++++++++++++++++++++- 2 files changed, 45 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/can/can-ml.h b/include/linux/can/can-ml.h index 2f5d731ae251..8afa92d15a66 100644 --- a/include/linux/can/can-ml.h +++ b/include/linux/can/can-ml.h @@ -44,6 +44,7 @@ #include #include +#include #define CAN_SFF_RCV_ARRAY_SZ (1 << CAN_SFF_ID_BITS) #define CAN_EFF_RCV_HASH_BITS 10 @@ -65,4 +66,15 @@ struct can_ml_priv { #endif }; +static inline struct can_ml_priv *can_get_ml_priv(struct net_device *dev) +{ + return netdev_get_ml_priv(dev, ML_PRIV_CAN); +} + +static inline void can_set_ml_priv(struct net_device *dev, + struct can_ml_priv *ml_priv) +{ + netdev_set_ml_priv(dev, ml_priv, ML_PRIV_CAN); +} + #endif /* CAN_ML_H */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ddf4cfc12615..f06fbee8638e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1584,6 +1584,12 @@ enum netdev_priv_flags { #define IFF_L3MDEV_RX_HANDLER IFF_L3MDEV_RX_HANDLER #define IFF_LIVE_RENAME_OK IFF_LIVE_RENAME_OK +/* Specifies the type of the struct net_device::ml_priv pointer */ +enum netdev_ml_priv_type { + ML_PRIV_NONE, + ML_PRIV_CAN, +}; + /** * struct net_device - The DEVICE structure. * @@ -1779,6 +1785,7 @@ enum netdev_priv_flags { * @nd_net: Network namespace this network device is inside * * @ml_priv: Mid-layer private + * @ml_priv_type: Mid-layer private type * @lstats: Loopback statistics * @tstats: Tunnel statistics * @dstats: Dummy statistics @@ -2094,8 +2101,10 @@ struct net_device { possible_net_t nd_net; /* mid-layer private */ + void *ml_priv; + enum netdev_ml_priv_type ml_priv_type; + union { - void *ml_priv; struct pcpu_lstats __percpu *lstats; struct pcpu_sw_netstats __percpu *tstats; struct pcpu_dstats __percpu *dstats; @@ -2286,6 +2295,29 @@ static inline void netdev_reset_rx_headroom(struct net_device *dev) netdev_set_rx_headroom(dev, -1); } +static inline void *netdev_get_ml_priv(struct net_device *dev, + enum netdev_ml_priv_type type) +{ + if (dev->ml_priv_type != type) + return NULL; + + return dev->ml_priv; +} + +static inline void netdev_set_ml_priv(struct net_device *dev, + void *ml_priv, + enum netdev_ml_priv_type type) +{ + WARN(dev->ml_priv_type && dev->ml_priv_type != type, + "Overwriting already set ml_priv_type (%u) with different ml_priv_type (%u)!\n", + dev->ml_priv_type, type); + WARN(!dev->ml_priv_type && dev->ml_priv, + "Overwriting already set ml_priv and ml_priv_type is ML_PRIV_NONE!\n"); + + dev->ml_priv = ml_priv; + dev->ml_priv_type = type; +} + /* * Net namespace inlines */ -- cgit v1.2.3 From 44835d20b2a0c9b4c0c3fb96e90f4e2fd4a4e41d Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 25 Feb 2021 17:15:36 -0800 Subject: mm: add FGP_ENTRY The functionality of find_lock_entry() and find_get_entry() can be provided by pagecache_get_page(), which lets us delete find_lock_entry() and make find_get_entry() static. Link: https://lkml.kernel.org/r/20201112212641.27837-5-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Cc: Dave Chinner Cc: Hugh Dickins Cc: Jan Kara Cc: Johannes Weiner Cc: Kirill A. Shutemov Cc: William Kucharski Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index bd629d676a27..b379b2388202 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -315,6 +315,7 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping, #define FGP_NOWAIT 0x00000020 #define FGP_FOR_MMAP 0x00000040 #define FGP_HEAD 0x00000080 +#define FGP_ENTRY 0x00000100 struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset, int fgp_flags, gfp_t cache_gfp_mask); -- cgit v1.2.3 From 41139aa4c3a31ee7e072fc63353c74035aade2ff Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 25 Feb 2021 17:15:48 -0800 Subject: mm/filemap: add mapping_seek_hole_data Rewrite shmem_seek_hole_data() and move it to filemap.c. [willy@infradead.org: don't put an xa_is_value() page] Link: https://lkml.kernel.org/r/20201124041507.28996-4-willy@infradead.org Link: https://lkml.kernel.org/r/20201112212641.27837-8-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: William Kucharski Reviewed-by: Christoph Hellwig Cc: Dave Chinner Cc: Hugh Dickins Cc: Jan Kara Cc: Johannes Weiner Cc: Kirill A. Shutemov Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index b379b2388202..3608993428d9 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -760,6 +760,8 @@ extern void __delete_from_page_cache(struct page *page, void *shadow); void replace_page_cache_page(struct page *old, struct page *new); void delete_from_page_cache_batch(struct address_space *mapping, struct pagevec *pvec); +loff_t mapping_seek_hole_data(struct address_space *, loff_t start, loff_t end, + int whence); /* * Like add_to_page_cache_locked, but used to add newly allocated pages: -- cgit v1.2.3 From ca122fe40eb463c8c11c3bfc1914f0048ca5c268 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 25 Feb 2021 17:16:00 -0800 Subject: mm: add an 'end' parameter to find_get_entries This simplifies the callers and leads to a more efficient implementation since the XArray has this functionality already. Link: https://lkml.kernel.org/r/20201112212641.27837-11-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Jan Kara Reviewed-by: William Kucharski Reviewed-by: Christoph Hellwig Cc: Dave Chinner Cc: Hugh Dickins Cc: Johannes Weiner Cc: Kirill A. Shutemov Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 3608993428d9..fdb2c4e44851 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -451,8 +451,8 @@ static inline struct page *find_subpage(struct page *head, pgoff_t index) } unsigned find_get_entries(struct address_space *mapping, pgoff_t start, - unsigned int nr_entries, struct page **entries, - pgoff_t *indices); + pgoff_t end, unsigned int nr_entries, struct page **entries, + pgoff_t *indices); unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start, pgoff_t end, unsigned int nr_pages, struct page **pages); -- cgit v1.2.3 From 31d270fd98d196578223e5b568a0bd3bc6028b09 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 25 Feb 2021 17:16:03 -0800 Subject: mm: add an 'end' parameter to pagevec_lookup_entries Simplifies the callers and uses the existing functionality in find_get_entries(). We can also drop the final argument of truncate_exceptional_pvec_entries() and simplify the logic in that function. Link: https://lkml.kernel.org/r/20201112212641.27837-12-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Jan Kara Reviewed-by: William Kucharski Reviewed-by: Christoph Hellwig Cc: Dave Chinner Cc: Hugh Dickins Cc: Johannes Weiner Cc: Kirill A. Shutemov Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagevec.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index ad4ddc17d403..f70a9dc81504 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -26,9 +26,8 @@ struct pagevec { void __pagevec_release(struct pagevec *pvec); void __pagevec_lru_add(struct pagevec *pvec); unsigned pagevec_lookup_entries(struct pagevec *pvec, - struct address_space *mapping, - pgoff_t start, unsigned nr_entries, - pgoff_t *indices); + struct address_space *mapping, pgoff_t start, pgoff_t end, + unsigned nr_entries, pgoff_t *indices); void pagevec_remove_exceptionals(struct pagevec *pvec); unsigned pagevec_lookup_range(struct pagevec *pvec, struct address_space *mapping, -- cgit v1.2.3 From 38cefeb33749992ceaad6ea40e12f92aa8f8e28f Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 25 Feb 2021 17:16:07 -0800 Subject: mm: remove nr_entries parameter from pagevec_lookup_entries All callers want to fetch the full size of the pvec. Link: https://lkml.kernel.org/r/20201112212641.27837-13-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Jan Kara Reviewed-by: William Kucharski Reviewed-by: Christoph Hellwig Cc: Dave Chinner Cc: Hugh Dickins Cc: Johannes Weiner Cc: Kirill A. Shutemov Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagevec.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index f70a9dc81504..72c5ea2e708d 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -27,7 +27,7 @@ void __pagevec_release(struct pagevec *pvec); void __pagevec_lru_add(struct pagevec *pvec); unsigned pagevec_lookup_entries(struct pagevec *pvec, struct address_space *mapping, pgoff_t start, pgoff_t end, - unsigned nr_entries, pgoff_t *indices); + pgoff_t *indices); void pagevec_remove_exceptionals(struct pagevec *pvec); unsigned pagevec_lookup_range(struct pagevec *pvec, struct address_space *mapping, -- cgit v1.2.3 From cf2039af1a2eee58fdbfa68bc0c9123e77477645 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 25 Feb 2021 17:16:11 -0800 Subject: mm: pass pvec directly to find_get_entries All callers of find_get_entries() use a pvec, so pass it directly instead of manipulating it in the caller. Link: https://lkml.kernel.org/r/20201112212641.27837-14-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Jan Kara Reviewed-by: William Kucharski Cc: Christoph Hellwig Cc: Dave Chinner Cc: Hugh Dickins Cc: Johannes Weiner Cc: Kirill A. Shutemov Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index fdb2c4e44851..20225b067583 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -451,8 +451,7 @@ static inline struct page *find_subpage(struct page *head, pgoff_t index) } unsigned find_get_entries(struct address_space *mapping, pgoff_t start, - pgoff_t end, unsigned int nr_entries, struct page **entries, - pgoff_t *indices); + pgoff_t end, struct pagevec *pvec, pgoff_t *indices); unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start, pgoff_t end, unsigned int nr_pages, struct page **pages); -- cgit v1.2.3 From a656a20241f08be532539c7d5bd82df741c2d487 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 25 Feb 2021 17:16:14 -0800 Subject: mm: remove pagevec_lookup_entries pagevec_lookup_entries() is now just a wrapper around find_get_entries() so remove it and convert all its callers. Link: https://lkml.kernel.org/r/20201112212641.27837-15-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Jan Kara Reviewed-by: William Kucharski Reviewed-by: Christoph Hellwig Cc: Dave Chinner Cc: Hugh Dickins Cc: Johannes Weiner Cc: Kirill A. Shutemov Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagevec.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index 72c5ea2e708d..7f3f19065a9f 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -25,9 +25,6 @@ struct pagevec { void __pagevec_release(struct pagevec *pvec); void __pagevec_lru_add(struct pagevec *pvec); -unsigned pagevec_lookup_entries(struct pagevec *pvec, - struct address_space *mapping, pgoff_t start, pgoff_t end, - pgoff_t *indices); void pagevec_remove_exceptionals(struct pagevec *pvec); unsigned pagevec_lookup_range(struct pagevec *pvec, struct address_space *mapping, -- cgit v1.2.3 From 164cc4fef4456727466f8e35bb654c3994748070 Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Thu, 25 Feb 2021 17:16:18 -0800 Subject: mm,thp,shmem: limit shmem THP alloc gfp_mask Patch series "mm,thp,shm: limit shmem THP alloc gfp_mask", v6. The allocation flags of anonymous transparent huge pages can be controlled through the files in /sys/kernel/mm/transparent_hugepage/defrag, which can help the system from getting bogged down in the page reclaim and compaction code when many THPs are getting allocated simultaneously. However, the gfp_mask for shmem THP allocations were not limited by those configuration settings, and some workloads ended up with all CPUs stuck on the LRU lock in the page reclaim code, trying to allocate dozens of THPs simultaneously. This patch applies the same configurated limitation of THPs to shmem hugepage allocations, to prevent that from happening. This way a THP defrag setting of "never" or "defer+madvise" will result in quick allocation failures without direct reclaim when no 2MB free pages are available. With this patch applied, THP allocations for tmpfs will be a little more aggressive than today for files mmapped with MADV_HUGEPAGE, and a little less aggressive for files that are not mmapped or mapped without that flag. This patch (of 4): The allocation flags of anonymous transparent huge pages can be controlled through the files in /sys/kernel/mm/transparent_hugepage/defrag, which can help the system from getting bogged down in the page reclaim and compaction code when many THPs are getting allocated simultaneously. However, the gfp_mask for shmem THP allocations were not limited by those configuration settings, and some workloads ended up with all CPUs stuck on the LRU lock in the page reclaim code, trying to allocate dozens of THPs simultaneously. This patch applies the same configurated limitation of THPs to shmem hugepage allocations, to prevent that from happening. Controlling the gfp_mask of THP allocations through the knobs in sysfs allows users to determine the balance between how aggressively the system tries to allocate THPs at fault time, and how much the application may end up stalling attempting those allocations. This way a THP defrag setting of "never" or "defer+madvise" will result in quick allocation failures without direct reclaim when no 2MB free pages are available. With this patch applied, THP allocations for tmpfs will be a little more aggressive than today for files mmapped with MADV_HUGEPAGE, and a little less aggressive for files that are not mmapped or mapped without that flag. Link: https://lkml.kernel.org/r/20201124194925.623931-1-riel@surriel.com Link: https://lkml.kernel.org/r/20201124194925.623931-2-riel@surriel.com Signed-off-by: Rik van Riel Acked-by: Michal Hocko Acked-by: Vlastimil Babka Cc: Xu Yu Cc: Mel Gorman Cc: Andrea Arcangeli Cc: Matthew Wilcox (Oracle) Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 220cd553a9e7..8572a1474e16 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -634,6 +634,8 @@ bool gfp_pfmemalloc_allowed(gfp_t gfp_mask); extern void pm_restrict_gfp_mask(void); extern void pm_restore_gfp_mask(void); +extern gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma); + #ifdef CONFIG_PM_SLEEP extern bool pm_suspended_storage(void); #else -- cgit v1.2.3 From cd89fb06509903f942a0ffe97ffa63034671ed0c Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Thu, 25 Feb 2021 17:16:25 -0800 Subject: mm,thp,shmem: make khugepaged obey tmpfs mount flags Currently if thp enabled=[madvise], mounting a tmpfs filesystem with huge=always and mmapping files from that tmpfs does not result in khugepaged collapsing those mappings, despite the mount flag indicating that it should. Fix that by breaking up the blocks of tests in hugepage_vma_check a little bit, and testing things in the correct order. Link: https://lkml.kernel.org/r/20201124194925.623931-4-riel@surriel.com Fixes: c2231020ea7b ("mm: thp: register mm for khugepaged when merging vma for shmem") Signed-off-by: Rik van Riel Cc: Andrea Arcangeli Cc: Hugh Dickins Cc: Matthew Wilcox (Oracle) Cc: Mel Gorman Cc: Michal Hocko Cc: Vlastimil Babka Cc: Xu Yu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/khugepaged.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h index c941b7377321..2fcc01891b47 100644 --- a/include/linux/khugepaged.h +++ b/include/linux/khugepaged.h @@ -3,6 +3,7 @@ #define _LINUX_KHUGEPAGED_H #include /* MMF_VM_HUGEPAGE */ +#include #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -57,6 +58,7 @@ static inline int khugepaged_enter(struct vm_area_struct *vma, { if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags)) if ((khugepaged_always() || + (shmem_file(vma->vm_file) && shmem_huge_enabled(vma)) || (khugepaged_req_madv() && (vm_flags & VM_HUGEPAGE))) && !(vm_flags & VM_NOHUGEPAGE) && !test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) -- cgit v1.2.3 From 3c381db1fac80373f2cc0d8c1d0bcfbf8bd4fb57 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 25 Feb 2021 17:16:40 -0800 Subject: mm/page_alloc: count CMA pages per zone and print them in /proc/zoneinfo Let's count the number of CMA pages per zone and print them in /proc/zoneinfo. Having access to the total number of CMA pages per zone is helpful for debugging purposes to know where exactly the CMA pages ended up, and to figure out how many pages of a zone might behave differently, even after some of these pages might already have been allocated. As one example, CMA pages part of a kernel zone cannot be used for ordinary kernel allocations but instead behave more like ZONE_MOVABLE. For now, we are only able to get the global nr+free cma pages from /proc/meminfo and the free cma pages per zone from /proc/zoneinfo. Example after this patch when booting a 6 GiB QEMU VM with "hugetlb_cma=2G": # cat /proc/zoneinfo | grep cma cma 0 nr_free_cma 0 cma 0 nr_free_cma 0 cma 524288 nr_free_cma 493016 cma 0 cma 0 # cat /proc/meminfo | grep Cma CmaTotal: 2097152 kB CmaFree: 1972064 kB Note: We print even without CONFIG_CMA, just like "nr_free_cma"; this way, one can be sure when spotting "cma 0", that there are definetly no CMA pages located in a zone. [david@redhat.com: v2] Link: https://lkml.kernel.org/r/20210128164533.18566-1-david@redhat.com [david@redhat.com: v3] Link: https://lkml.kernel.org/r/20210129113451.22085-1-david@redhat.com Link: https://lkml.kernel.org/r/20210127101813.6370-3-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Oscar Salvador Acked-by: David Rientjes Cc: Thomas Gleixner Cc: "Peter Zijlstra (Intel)" Cc: Mike Rapoport Cc: Michal Hocko Cc: Wei Yang Cc: Zi Yan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 9198b7ade85f..5f9c4dad73ed 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -503,6 +503,9 @@ struct zone { * bootmem allocator): * managed_pages = present_pages - reserved_pages; * + * cma pages is present pages that are assigned for CMA use + * (MIGRATE_CMA). + * * So present_pages may be used by memory hotplug or memory power * management logic to figure out unmanaged pages by checking * (present_pages - managed_pages). And managed_pages should be used @@ -527,6 +530,9 @@ struct zone { atomic_long_t managed_pages; unsigned long spanned_pages; unsigned long present_pages; +#ifdef CONFIG_CMA + unsigned long cma_pages; +#endif const char *name; @@ -624,6 +630,15 @@ static inline unsigned long zone_managed_pages(struct zone *zone) return (unsigned long)atomic_long_read(&zone->managed_pages); } +static inline unsigned long zone_cma_pages(struct zone *zone) +{ +#ifdef CONFIG_CMA + return zone->cma_pages; +#else + return 0; +#endif +} + static inline unsigned long zone_end_pfn(const struct zone *zone) { return zone->zone_start_pfn + zone->spanned_pages; -- cgit v1.2.3 From 629484ae73754243917e06d8d5e5f37c26e99399 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 25 Feb 2021 17:16:51 -0800 Subject: mm: vmstat: add some comments on internal storage of byte items Byte-accounted items are used for slab object accounting at the cgroup level, because the objects in a slab page can belong to different cgroups. At the global level these items always change in multiples of whole slab pages. The vmstat code exploits this and stores these items as pages internally, which allows for more compact per-cpu data. This optimization isn't self-evident from the asserts and the division in the stat update functions. Provide the reader with some context. Link: https://lkml.kernel.org/r/20210202184411.118614-1-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmstat.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 773135fc6e19..506d625163a1 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -313,6 +313,12 @@ static inline void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, int delta) { if (vmstat_item_in_bytes(item)) { + /* + * Only cgroups use subpage accounting right now; at + * the global level, these items still change in + * multiples of whole pages. Store them as pages + * internally to keep the per-cpu counters compact. + */ VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1)); delta >>= PAGE_SHIFT; } -- cgit v1.2.3 From 9f605f260594f99b950062fd62244251e85dbd2b Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 25 Feb 2021 17:16:57 -0800 Subject: mm: move pfn_to_online_page() out of line Patch series "mm: Fix pfn_to_online_page() with respect to ZONE_DEVICE", v4. A pfn-walker that uses pfn_to_online_page() may inadvertently translate a pfn as online and in the page allocator, when it is offline managed by a ZONE_DEVICE mapping (details in Patch 3: ("mm: Teach pfn_to_online_page() about ZONE_DEVICE section collisions")). The 2 proposals under consideration are teach pfn_to_online_page() to be precise in the presence of mixed-zone sections, or teach the memory-add code to drop the System RAM associated with ZONE_DEVICE collisions. In order to not regress memory capacity by a few 10s to 100s of MiB the approach taken in this set is to add precision to pfn_to_online_page(). In the course of validating pfn_to_online_page() a couple other fixes fell out: 1/ soft_offline_page() fails to drop the reference taken in the madvise(..., MADV_SOFT_OFFLINE) case. 2/ memory_failure() uses get_dev_pagemap() to lookup ZONE_DEVICE pages, however that mapping may contain data pages and metadata raw pfns. Introduce pgmap_pfn_valid() to delineate the 2 types and fail the handling of raw metadata pfns. This patch (of 4); pfn_to_online_page() is already too large to be a macro or an inline function. In anticipation of further logic changes / growth, move it out of line. No functional change, just code movement. Link: https://lkml.kernel.org/r/161058499000.1840162.702316708443239771.stgit@dwillia2-desk3.amr.corp.intel.com Link: https://lkml.kernel.org/r/161058499608.1840162.10165648147615238793.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams Reported-by: Michal Hocko Acked-by: Michal Hocko Reviewed-by: David Hildenbrand Reviewed-by: Oscar Salvador Cc: Naoya Horiguchi Cc: Qian Cai Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 17 +---------------- 1 file changed, 1 insertion(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 15acce5ab106..3d99de0db2dd 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -16,22 +16,7 @@ struct resource; struct vmem_altmap; #ifdef CONFIG_MEMORY_HOTPLUG -/* - * Return page for the valid pfn only if the page is online. All pfn - * walkers which rely on the fully initialized page->flags and others - * should use this rather than pfn_valid && pfn_to_page - */ -#define pfn_to_online_page(pfn) \ -({ \ - struct page *___page = NULL; \ - unsigned long ___pfn = pfn; \ - unsigned long ___nr = pfn_to_section_nr(___pfn); \ - \ - if (___nr < NR_MEM_SECTIONS && online_section_nr(___nr) && \ - pfn_valid_within(___pfn)) \ - ___page = pfn_to_page(___pfn); \ - ___page; \ -}) +struct page *pfn_to_online_page(unsigned long pfn); /* * Types for free bootmem stored in page->lru.next. These have to be in -- cgit v1.2.3 From 1f90a3477df3ff1a91e064af554cdc887c8f9e5e Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 25 Feb 2021 17:17:05 -0800 Subject: mm: teach pfn_to_online_page() about ZONE_DEVICE section collisions While pfn_to_online_page() is able to determine pfn_valid() at subsection granularity it is not able to reliably determine if a given pfn is also online if the section is mixes ZONE_{NORMAL,MOVABLE} with ZONE_DEVICE. This means that pfn_to_online_page() may return invalid @page objects. For example with a memory map like: 100000000-1fbffffff : System RAM 142000000-143002e16 : Kernel code 143200000-143713fff : Kernel rodata 143800000-143b15b7f : Kernel data 144227000-144ffffff : Kernel bss 1fc000000-2fbffffff : Persistent Memory (legacy) 1fc000000-2fbffffff : namespace0.0 This command: echo 0x1fc000000 > /sys/devices/system/memory/soft_offline_page ...succeeds when it should fail. When it succeeds it touches an uninitialized page and may crash or cause other damage (see dissolve_free_huge_page()). While the memory map above is contrived via the memmap=ss!nn kernel command line option, the collision happens in practice on shipping platforms. The memory controller resources that decode spans of physical address space are a limited resource. One technique platform-firmware uses to conserve those resources is to share a decoder across 2 devices to keep the address range contiguous. Unfortunately the unit of operation of a decoder is 64MiB while the Linux section size is 128MiB. This results in situations where, without subsection hotplug memory mappings with different lifetimes collide into one object that can only express one lifetime. Update move_pfn_range_to_zone() to flag (SECTION_TAINT_ZONE_DEVICE) a section that mixes ZONE_DEVICE pfns with other online pfns. With SECTION_TAINT_ZONE_DEVICE to delineate, pfn_to_online_page() can fall back to a slow-path check for ZONE_DEVICE pfns in an online section. In the fast path online_section() for a full ZONE_DEVICE section returns false. Because the collision case is rare, and for simplicity, the SECTION_TAINT_ZONE_DEVICE flag is never cleared once set. [dan.j.williams@intel.com: fix CONFIG_ZONE_DEVICE=n build] Link: https://lkml.kernel.org/r/CAPcyv4iX+7LAgAeSqx7Zw-Zd=ZV9gBv8Bo7oTbwCOOqJoZ3+Yg@mail.gmail.com Link: https://lkml.kernel.org/r/161058500675.1840162.7887862152161279354.stgit@dwillia2-desk3.amr.corp.intel.com Fixes: ba72b4c8cf60 ("mm/sparsemem: support sub-section hotplug") Signed-off-by: Dan Williams Reported-by: Michal Hocko Acked-by: Michal Hocko Reported-by: David Hildenbrand Reviewed-by: David Hildenbrand Reviewed-by: Oscar Salvador Cc: Naoya Horiguchi Cc: Qian Cai Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 34 +++++++++++++++++++++++++++------- 1 file changed, 27 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 5f9c4dad73ed..47946cec7584 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -918,6 +918,18 @@ static inline int local_memory_node(int node_id) { return node_id; }; */ #define zone_idx(zone) ((zone) - (zone)->zone_pgdat->node_zones) +#ifdef CONFIG_ZONE_DEVICE +static inline bool zone_is_zone_device(struct zone *zone) +{ + return zone_idx(zone) == ZONE_DEVICE; +} +#else +static inline bool zone_is_zone_device(struct zone *zone) +{ + return false; +} +#endif + /* * Returns true if a zone has pages managed by the buddy allocator. * All the reclaim decisions have to use this function rather than @@ -1306,13 +1318,14 @@ extern size_t mem_section_usage_size(void); * which results in PFN_SECTION_SHIFT equal 6. * To sum it up, at least 6 bits are available. */ -#define SECTION_MARKED_PRESENT (1UL<<0) -#define SECTION_HAS_MEM_MAP (1UL<<1) -#define SECTION_IS_ONLINE (1UL<<2) -#define SECTION_IS_EARLY (1UL<<3) -#define SECTION_MAP_LAST_BIT (1UL<<4) -#define SECTION_MAP_MASK (~(SECTION_MAP_LAST_BIT-1)) -#define SECTION_NID_SHIFT 3 +#define SECTION_MARKED_PRESENT (1UL<<0) +#define SECTION_HAS_MEM_MAP (1UL<<1) +#define SECTION_IS_ONLINE (1UL<<2) +#define SECTION_IS_EARLY (1UL<<3) +#define SECTION_TAINT_ZONE_DEVICE (1UL<<4) +#define SECTION_MAP_LAST_BIT (1UL<<5) +#define SECTION_MAP_MASK (~(SECTION_MAP_LAST_BIT-1)) +#define SECTION_NID_SHIFT 3 static inline struct page *__section_mem_map_addr(struct mem_section *section) { @@ -1351,6 +1364,13 @@ static inline int online_section(struct mem_section *section) return (section && (section->section_mem_map & SECTION_IS_ONLINE)); } +static inline int online_device_section(struct mem_section *section) +{ + unsigned long flags = SECTION_IS_ONLINE | SECTION_TAINT_ZONE_DEVICE; + + return section && ((section->section_mem_map & flags) == flags); +} + static inline int online_section_nr(unsigned long nr) { return online_section(__nr_to_section(nr)); -- cgit v1.2.3 From 34dc45be4563f344d59ba0428416d0d265aa4f4d Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 25 Feb 2021 17:17:08 -0800 Subject: mm: fix memory_failure() handling of dax-namespace metadata Given 'struct dev_pagemap' spans both data pages and metadata pages be careful to consult the altmap if present to delineate metadata. In fact the pfn_first() helper already identifies the first valid data pfn, so export that helper for other code paths via pgmap_pfn_valid(). Other usage of get_dev_pagemap() are not a concern because those are operating on known data pfns having been looked up by get_user_pages(). I.e. metadata pfns are never user mapped. Link: https://lkml.kernel.org/r/161058501758.1840162.4239831989762604527.stgit@dwillia2-desk3.amr.corp.intel.com Fixes: 6100e34b2526 ("mm, memory_failure: Teach memory_failure() about dev_pagemap pages") Signed-off-by: Dan Williams Reported-by: David Hildenbrand Reviewed-by: David Hildenbrand Reviewed-by: Naoya Horiguchi Cc: Michal Hocko Cc: Oscar Salvador Cc: Qian Cai Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memremap.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 79c49e7f5c30..f5b464daeeca 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -137,6 +137,7 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap); void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap); struct dev_pagemap *get_dev_pagemap(unsigned long pfn, struct dev_pagemap *pgmap); +bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn); unsigned long vmem_altmap_offset(struct vmem_altmap *altmap); void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns); @@ -165,6 +166,11 @@ static inline struct dev_pagemap *get_dev_pagemap(unsigned long pfn, return NULL; } +static inline bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn) +{ + return false; +} + static inline unsigned long vmem_altmap_offset(struct vmem_altmap *altmap) { return 0; -- cgit v1.2.3 From 1adf8b468ff6bc64ba01ce3848da4bcf409215b4 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Thu, 25 Feb 2021 17:17:13 -0800 Subject: mm/memory_hotplug: rename all existing 'memhp' into 'mhp' This renames all 'memhp' instances to 'mhp' except for memhp_default_state for being a kernel command line option. This is just a clean up and should not cause a functional change. Let's make it consistent rater than mixing the two prefixes. In preparation for more users of the 'mhp' terminology. Link: https://lkml.kernel.org/r/1611554093-27316-1-git-send-email-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual Suggested-by: David Hildenbrand Reviewed-by: David Hildenbrand Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 3d99de0db2dd..ca5e8d137726 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -116,10 +116,10 @@ extern int arch_add_memory(int nid, u64 start, u64 size, struct mhp_params *params); extern u64 max_mem_size; -extern int memhp_online_type_from_str(const char *str); +extern int mhp_online_type_from_str(const char *str); /* Default online_type (MMOP_*) when new memory blocks are added. */ -extern int memhp_default_online_type; +extern int mhp_default_online_type; /* If movable_node boot option specified */ extern bool movable_node_enabled; static inline bool movable_node_is_enabled(void) -- cgit v1.2.3 From 26011267e1a7ddaab50b5f81b402ca3e7fc2887c Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 25 Feb 2021 17:17:17 -0800 Subject: mm/memory_hotplug: MEMHP_MERGE_RESOURCE -> MHP_MERGE_RESOURCE Let's make "MEMHP_MERGE_RESOURCE" consistent with "MHP_NONE", "mhp_t" and "mhp_flags". As discussed recently [1], "mhp" is our internal acronym for memory hotplug now. [1] https://lore.kernel.org/linux-mm/c37de2d0-28a1-4f7d-f944-cfd7d81c334d@redhat.com/ Link: https://lkml.kernel.org/r/20210126115829.10909-1-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Miaohe Lin Acked-by: Michael S. Tsirkin Reviewed-by: Oscar Salvador Acked-by: Wei Liu Reviewed-by: Pankaj Gupta Cc: "K. Y. Srinivasan" Cc: Haiyang Zhang Cc: Stephen Hemminger Cc: Jason Wang Cc: Boris Ostrovsky Cc: Juergen Gross Cc: Stefano Stabellini Cc: Michal Hocko Cc: Anshuman Khandual Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index ca5e8d137726..08eeef679ab7 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -53,7 +53,7 @@ typedef int __bitwise mhp_t; * with this flag set, the resource pointer must no longer be used as it * might be stale, or the resource might have changed. */ -#define MEMHP_MERGE_RESOURCE ((__force mhp_t)BIT(0)) +#define MHP_MERGE_RESOURCE ((__force mhp_t)BIT(0)) /* * Extended parameters for memory hotplug: -- cgit v1.2.3 From e9a2e48e8704c9d20a625c6f2357147d03ea7b97 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 25 Feb 2021 17:17:24 -0800 Subject: drivers/base/memory: don't store phys_device in memory blocks No need to store the value for each and every memory block, as we can easily query the value at runtime. Reshuffle the members to optimize the memory layout. Also, let's clarify what the interface once was used for and why it's legacy nowadays. "phys_device" was used on s390x in older versions of lsmem[2]/chmem[3], back when they were still part of s390x-tools. They were later replaced by the variants in linux-utils. For example, RHEL6 and RHEL7 contain lsmem/chmem from s390-utils. RHEL8 switched to versions from util-linux on s390x [4]. "phys_device" was added with sysfs support for memory hotplug in commit 3947be1969a9 ("[PATCH] memory hotplug: sysfs and add/remove functions") in 2005. It always returned 0. s390x started returning something != 0 on some setups (if sclp.rzm is set by HW) in 2010 via commit 57b552ba0b2f ("memory hotplug/s390: set phys_device"). For s390x, it allowed for identifying which memory block devices belong to the same storage increment (RZM). Only if all memory block devices comprising a single storage increment were offline, the memory could actually be removed in the hypervisor. Since commit e5d709bb5fb7 ("s390/memory hotplug: provide memory_block_size_bytes() function") in 2013 a memory block device spans at least one storage increment - which is why the interface isn't really helpful/used anymore (except by old lsmem/chmem tools). There were once RFC patches to make use of "phys_device" in ACPI context; however, the underlying problem could be solved using different interfaces [1]. [1] https://patchwork.kernel.org/patch/2163871/ [2] https://github.com/ibm-s390-tools/s390-tools/blob/v2.1.0/zconf/lsmem [3] https://github.com/ibm-s390-tools/s390-tools/blob/v2.1.0/zconf/chmem [4] https://bugzilla.redhat.com/show_bug.cgi?id=1504134 Link: https://lkml.kernel.org/r/20210201181347.13262-2-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Michal Hocko Reviewed-by: Oscar Salvador Cc: Dave Hansen Cc: Greg Kroah-Hartman Cc: Gerald Schaefer Cc: Jonathan Corbet Cc: "Rafael J. Wysocki" Cc: Mauro Carvalho Chehab Cc: Ilya Dryomov Cc: Vaibhav Jain Cc: Tom Rix Cc: Geert Uytterhoeven Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory.h b/include/linux/memory.h index 439a89e758d8..4da95e684e20 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -27,9 +27,8 @@ struct memory_block { unsigned long start_section_nr; unsigned long state; /* serialized by the dev->lock */ int online_type; /* for passing data to online routine */ - int phys_device; /* to which fru does this belong? */ - struct device dev; int nid; /* NID for this memory block */ + struct device dev; }; int arch_get_memory_phys_device(unsigned long start_pfn); -- cgit v1.2.3 From bca3feaa0764ab5a4cbe6817871601f1d00c059d Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Thu, 25 Feb 2021 17:17:33 -0800 Subject: mm/memory_hotplug: prevalidate the address range being added with platform Patch series "mm/memory_hotplug: Pre-validate the address range with platform", v5. This series adds a mechanism allowing platforms to weigh in and prevalidate incoming address range before proceeding further with the memory hotplug. This helps prevent potential platform errors for the given address range, down the hotplug call chain, which inevitably fails the hotplug itself. This mechanism was suggested by David Hildenbrand during another discussion with respect to a memory hotplug fix on arm64 platform. https://lore.kernel.org/linux-arm-kernel/1600332402-30123-1-git-send-email-anshuman.khandual@arm.com/ This mechanism focuses on the addressibility aspect and not [sub] section alignment aspect. Hence check_hotplug_memory_range() and check_pfn_span() have been left unchanged. This patch (of 4): This introduces mhp_range_allowed() which can be called in various memory hotplug paths to prevalidate the address range which is being added, with the platform. Then mhp_range_allowed() calls mhp_get_pluggable_range() which provides applicable address range depending on whether linear mapping is required or not. For ranges that require linear mapping, it calls a new arch callback arch_get_mappable_range() which the platform can override. So the new callback, in turn provides the platform an opportunity to configure acceptable memory hotplug address ranges in case there are constraints. This mechanism will help prevent platform specific errors deep down during hotplug calls. This drops now redundant check_hotplug_memory_addressable() check in __add_pages() but instead adds a VM_BUG_ON() check which would ensure that the range has been validated with mhp_range_allowed() earlier in the call chain. Besides mhp_get_pluggable_range() also can be used by potential memory hotplug callers to avail the allowed physical range which would go through on a given platform. This does not really add any new range check in generic memory hotplug but instead compensates for lost checks in arch_add_memory() where applicable and check_hotplug_memory_addressable(), with unified mhp_range_allowed(). [akpm@linux-foundation.org: make pagemap_range() return -EINVAL when mhp_range_allowed() fails] Link: https://lkml.kernel.org/r/1612149902-7867-1-git-send-email-anshuman.khandual@arm.com Link: https://lkml.kernel.org/r/1612149902-7867-2-git-send-email-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual Suggested-by: David Hildenbrand Reviewed-by: David Hildenbrand Reviewed-by: Oscar Salvador Cc: Heiko Carstens Cc: Catalin Marinas Cc: Vasily Gorbik # s390 Cc: Will Deacon Cc: Ard Biesheuvel Cc: Mark Rutland Cc: Jason Wang Cc: Jonathan Cameron Cc: "Michael S. Tsirkin" Cc: Michal Hocko Cc: Pankaj Gupta Cc: Pankaj Gupta Cc: teawater Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 08eeef679ab7..7288aa5ef73b 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -66,6 +66,9 @@ struct mhp_params { pgprot_t pgprot; }; +bool mhp_range_allowed(u64 start, u64 size, bool need_mapping); +struct range mhp_get_pluggable_range(bool need_mapping); + /* * Zone resizing functions * @@ -266,6 +269,13 @@ static inline bool movable_node_is_enabled(void) } #endif /* ! CONFIG_MEMORY_HOTPLUG */ +/* + * Keep this declaration outside CONFIG_MEMORY_HOTPLUG as some + * platforms might override and use arch_get_mappable_range() + * for internal non memory hotplug purposes. + */ +struct range arch_get_mappable_range(void); + #if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT) /* * pgdat resizing functions -- cgit v1.2.3 From 5d5d19eda6b0ee790af89c45e3f678345be6f50f Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Thu, 25 Feb 2021 17:18:09 -0800 Subject: mm/rmap: fix potential pte_unmap on an not mapped pte For PMD-mapped page (usually THP), pvmw->pte is NULL. For PTE-mapped THP, pvmw->pte is mapped. But for HugeTLB pages, pvmw->pte is not mapped and set to the relevant page table entry. So in page_vma_mapped_walk_done(), we may do pte_unmap() for HugeTLB pte which is not mapped. Fix this by checking pvmw->page against PageHuge before trying to do pte_unmap(). Link: https://lkml.kernel.org/r/20210127093349.39081-1-linmiaohe@huawei.com Fixes: ace71a19cec5 ("mm: introduce page_vma_mapped_walk()") Signed-off-by: Hongxiang Lou Signed-off-by: Miaohe Lin Tested-by: Sedat Dilek Cc: Kees Cook Cc: Nathan Chancellor Cc: Mike Kravetz Cc: Shakeel Butt Cc: Johannes Weiner Cc: Vlastimil Babka Cc: Michel Lespinasse Cc: Nick Desaulniers Cc: "Kirill A. Shutemov" Cc: Wei Yang Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Brian Geffon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rmap.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 70085ca1a3fc..def5c62c93b3 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -213,7 +213,8 @@ struct page_vma_mapped_walk { static inline void page_vma_mapped_walk_done(struct page_vma_mapped_walk *pvmw) { - if (pvmw->pte) + /* HugeTLB pte is set to the relevant page table entry without pte_mapped. */ + if (pvmw->pte && !PageHuge(pvmw->page)) pte_unmap(pvmw->pte); if (pvmw->ptl) spin_unlock(pvmw->ptl); -- cgit v1.2.3 From fc6697a89f56d9773b2fbff718d4cf2a6d63379d Mon Sep 17 00:00:00 2001 From: Tian Tao Date: Thu, 25 Feb 2021 17:18:17 -0800 Subject: mm/zswap: add the flag can_sleep_mapped Patch series "Fix the compatibility of zsmalloc and zswap". Patch #1 adds a flag to zpool, then zswap used to determine if zpool drivers such as zbud/z3fold/zsmalloc will enter an atomic context after mapping. The difference between zbud/z3fold and zsmalloc is that zsmalloc requires an atomic context that since its map function holds a preempt-disabled, but zbud/z3fold don't require an atomic context. So patch #2 sets flag sleep_mapped to true indicating that zbud/z3fold can sleep after mapping. zsmalloc didn't support sleep after mapping, so don't set that flag to true. This patch (of 2): Add a flag to zpool, named is "can_sleep_mapped", and have it set true for zbud/z3fold, not set this flag for zsmalloc, so its default value is false. Then zswap could go the current path if the flag is true; and if it's false, copy data from src to a temporary buffer, then unmap the handle, take the mutex, process the buffer instead of src to avoid sleeping function called from atomic context. [natechancellor@gmail.com: add return value in zswap_frontswap_load] Link: https://lkml.kernel.org/r/20210121214804.926843-1-natechancellor@gmail.com [tiantao6@hisilicon.com: fix potential memory leak] Link: https://lkml.kernel.org/r/1611538365-51811-1-git-send-email-tiantao6@hisilicon.com [colin.king@canonical.com: fix potential uninitialized pointer read on tmp] Link: https://lkml.kernel.org/r/20210128141728.639030-1-colin.king@canonical.com [tiantao6@hisilicon.com: fix variable 'entry' is uninitialized when used] Link: https://lkml.kernel.org/r/1611223030-58346-1-git-send-email-tiantao6@hisilicon.comLink: https://lkml.kernel.org/r/1611035683-12732-1-git-send-email-tiantao6@hisilicon.com Link: https://lkml.kernel.org/r/1611035683-12732-2-git-send-email-tiantao6@hisilicon.com Signed-off-by: Tian Tao Signed-off-by: Nathan Chancellor Signed-off-by: Colin Ian King Reviewed-by: Vitaly Wool Acked-by: Sebastian Andrzej Siewior Reported-by: Mike Galbraith Cc: Barry Song Cc: Dan Streetman Cc: Seth Jennings Cc: Dan Carpenter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/zpool.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/zpool.h b/include/linux/zpool.h index 51bf43076165..e8997010612a 100644 --- a/include/linux/zpool.h +++ b/include/linux/zpool.h @@ -73,6 +73,7 @@ u64 zpool_get_total_size(struct zpool *pool); * @malloc: allocate mem from a pool. * @free: free mem from a pool. * @shrink: shrink the pool. + * @sleep_mapped: whether zpool driver can sleep during map. * @map: map a handle. * @unmap: unmap a handle. * @total_size: get total size of a pool. @@ -100,6 +101,7 @@ struct zpool_driver { int (*shrink)(void *pool, unsigned int pages, unsigned int *reclaimed); + bool sleep_mapped; void *(*map)(void *pool, unsigned long handle, enum zpool_mapmode mm); void (*unmap)(void *pool, unsigned long handle); @@ -112,5 +114,6 @@ void zpool_register_driver(struct zpool_driver *driver); int zpool_unregister_driver(struct zpool_driver *driver); bool zpool_evictable(struct zpool *pool); +bool zpool_can_sleep_mapped(struct zpool *pool); #endif -- cgit v1.2.3 From 2395928158059b8f9858365fce7713ce7fef62e4 Mon Sep 17 00:00:00 2001 From: Rokudo Yan Date: Thu, 25 Feb 2021 17:18:31 -0800 Subject: zsmalloc: account the number of compacted pages correctly There exists multiple path may do zram compaction concurrently. 1. auto-compaction triggered during memory reclaim 2. userspace utils write zram/compaction node So, multiple threads may call zs_shrinker_scan/zs_compact concurrently. But pages_compacted is a per zsmalloc pool variable and modification of the variable is not serialized(through under class->lock). There are two issues here: 1. the pages_compacted may not equal to total number of pages freed(due to concurrently add). 2. zs_shrinker_scan may not return the correct number of pages freed(issued by current shrinker). The fix is simple: 1. account the number of pages freed in zs_compact locally. 2. use actomic variable pages_compacted to accumulate total number. Link: https://lkml.kernel.org/r/20210202122235.26885-1-wu-yan@tcl.com Fixes: 860c707dca155a56 ("zsmalloc: account the number of compacted pages") Signed-off-by: Rokudo Yan Cc: Minchan Kim Cc: Sergey Senozhatsky Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/zsmalloc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h index 4807ca4d52e0..2a430e713ce5 100644 --- a/include/linux/zsmalloc.h +++ b/include/linux/zsmalloc.h @@ -35,7 +35,7 @@ enum zs_mapmode { struct zs_pool_stats { /* How many pages were migrated (freed) */ - unsigned long pages_compacted; + atomic_long_t pages_compacted; }; struct zs_pool; -- cgit v1.2.3 From 4be408cec257d1156d35647db57726f5ef977630 Mon Sep 17 00:00:00 2001 From: Guo Ren Date: Thu, 25 Feb 2021 17:18:38 -0800 Subject: mm: page-flags.h: Typo fix (It -> If) The "If" was wrongly spelled as "It". Link: https://lkml.kernel.org/r/1608959036-91409-1-git-send-email-guoren@kernel.org Signed-off-by: Guo Ren Cc: Oscar Salvador Cc: Alexander Duyck Cc: David Hildenbrand Cc: Steven Price Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index db914477057b..04a34c08e0a6 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -810,7 +810,7 @@ static inline void ClearPageSlabPfmemalloc(struct page *page) /* * Flags checked when a page is freed. Pages being freed should not have - * these flags set. It they are, there is a problem. + * these flags set. If they are, there is a problem. */ #define PAGE_FLAGS_CHECK_AT_FREE \ (1UL << PG_lru | 1UL << PG_locked | \ @@ -821,7 +821,7 @@ static inline void ClearPageSlabPfmemalloc(struct page *page) /* * Flags checked when a page is prepped for return by the page allocator. - * Pages being prepped should not have these flags set. It they are set, + * Pages being prepped should not have these flags set. If they are set, * there has been a kernel bug or struct page corruption. * * __PG_HWPOISON is exceptional because it needs to be kept beyond page's -- cgit v1.2.3 From 0ce20dd840897b12ae70869c69f1ba34d6d16965 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 25 Feb 2021 17:18:53 -0800 Subject: mm: add Kernel Electric-Fence infrastructure Patch series "KFENCE: A low-overhead sampling-based memory safety error detector", v7. This adds the Kernel Electric-Fence (KFENCE) infrastructure. KFENCE is a low-overhead sampling-based memory safety error detector of heap use-after-free, invalid-free, and out-of-bounds access errors. This series enables KFENCE for the x86 and arm64 architectures, and adds KFENCE hooks to the SLAB and SLUB allocators. KFENCE is designed to be enabled in production kernels, and has near zero performance overhead. Compared to KASAN, KFENCE trades performance for precision. The main motivation behind KFENCE's design, is that with enough total uptime KFENCE will detect bugs in code paths not typically exercised by non-production test workloads. One way to quickly achieve a large enough total uptime is when the tool is deployed across a large fleet of machines. KFENCE objects each reside on a dedicated page, at either the left or right page boundaries. The pages to the left and right of the object page are "guard pages", whose attributes are changed to a protected state, and cause page faults on any attempted access to them. Such page faults are then intercepted by KFENCE, which handles the fault gracefully by reporting a memory access error. Guarded allocations are set up based on a sample interval (can be set via kfence.sample_interval). After expiration of the sample interval, the next allocation through the main allocator (SLAB or SLUB) returns a guarded allocation from the KFENCE object pool. At this point, the timer is reset, and the next allocation is set up after the expiration of the interval. To enable/disable a KFENCE allocation through the main allocator's fast-path without overhead, KFENCE relies on static branches via the static keys infrastructure. The static branch is toggled to redirect the allocation to KFENCE. The KFENCE memory pool is of fixed size, and if the pool is exhausted no further KFENCE allocations occur. The default config is conservative with only 255 objects, resulting in a pool size of 2 MiB (with 4 KiB pages). We have verified by running synthetic benchmarks (sysbench I/O, hackbench) and production server-workload benchmarks that a kernel with KFENCE (using sample intervals 100-500ms) is performance-neutral compared to a non-KFENCE baseline kernel. KFENCE is inspired by GWP-ASan [1], a userspace tool with similar properties. The name "KFENCE" is a homage to the Electric Fence Malloc Debugger [2]. For more details, see Documentation/dev-tools/kfence.rst added in the series -- also viewable here: https://raw.githubusercontent.com/google/kasan/kfence/Documentation/dev-tools/kfence.rst [1] http://llvm.org/docs/GwpAsan.html [2] https://linux.die.net/man/3/efence This patch (of 9): This adds the Kernel Electric-Fence (KFENCE) infrastructure. KFENCE is a low-overhead sampling-based memory safety error detector of heap use-after-free, invalid-free, and out-of-bounds access errors. KFENCE is designed to be enabled in production kernels, and has near zero performance overhead. Compared to KASAN, KFENCE trades performance for precision. The main motivation behind KFENCE's design, is that with enough total uptime KFENCE will detect bugs in code paths not typically exercised by non-production test workloads. One way to quickly achieve a large enough total uptime is when the tool is deployed across a large fleet of machines. KFENCE objects each reside on a dedicated page, at either the left or right page boundaries. The pages to the left and right of the object page are "guard pages", whose attributes are changed to a protected state, and cause page faults on any attempted access to them. Such page faults are then intercepted by KFENCE, which handles the fault gracefully by reporting a memory access error. To detect out-of-bounds writes to memory within the object's page itself, KFENCE also uses pattern-based redzones. The following figure illustrates the page layout: ---+-----------+-----------+-----------+-----------+-----------+--- | xxxxxxxxx | O : | xxxxxxxxx | : O | xxxxxxxxx | | xxxxxxxxx | B : | xxxxxxxxx | : B | xxxxxxxxx | | x GUARD x | J : RED- | x GUARD x | RED- : J | x GUARD x | | xxxxxxxxx | E : ZONE | xxxxxxxxx | ZONE : E | xxxxxxxxx | | xxxxxxxxx | C : | xxxxxxxxx | : C | xxxxxxxxx | | xxxxxxxxx | T : | xxxxxxxxx | : T | xxxxxxxxx | ---+-----------+-----------+-----------+-----------+-----------+--- Guarded allocations are set up based on a sample interval (can be set via kfence.sample_interval). After expiration of the sample interval, a guarded allocation from the KFENCE object pool is returned to the main allocator (SLAB or SLUB). At this point, the timer is reset, and the next allocation is set up after the expiration of the interval. To enable/disable a KFENCE allocation through the main allocator's fast-path without overhead, KFENCE relies on static branches via the static keys infrastructure. The static branch is toggled to redirect the allocation to KFENCE. To date, we have verified by running synthetic benchmarks (sysbench I/O, hackbench) that a kernel compiled with KFENCE is performance-neutral compared to the non-KFENCE baseline. For more details, see Documentation/dev-tools/kfence.rst (added later in the series). [elver@google.com: fix parameter description for kfence_object_start()] Link: https://lkml.kernel.org/r/20201106092149.GA2851373@elver.google.com [elver@google.com: avoid stalling work queue task without allocations] Link: https://lkml.kernel.org/r/CADYN=9J0DQhizAGB0-jz4HOBBh+05kMBXb4c0cXMS7Qi5NAJiw@mail.gmail.com Link: https://lkml.kernel.org/r/20201110135320.3309507-1-elver@google.com [elver@google.com: fix potential deadlock due to wake_up()] Link: https://lkml.kernel.org/r/000000000000c0645805b7f982e4@google.com Link: https://lkml.kernel.org/r/20210104130749.1768991-1-elver@google.com [elver@google.com: add option to use KFENCE without static keys] Link: https://lkml.kernel.org/r/20210111091544.3287013-1-elver@google.com [elver@google.com: add missing copyright and description headers] Link: https://lkml.kernel.org/r/20210118092159.145934-1-elver@google.com Link: https://lkml.kernel.org/r/20201103175841.3495947-2-elver@google.com Signed-off-by: Marco Elver Signed-off-by: Alexander Potapenko Reviewed-by: Dmitry Vyukov Reviewed-by: SeongJae Park Co-developed-by: Marco Elver Reviewed-by: Jann Horn Cc: "H. Peter Anvin" Cc: Paul E. McKenney Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christopher Lameter Cc: Dave Hansen Cc: David Rientjes Cc: Eric Dumazet Cc: Greg Kroah-Hartman Cc: Hillf Danton Cc: Ingo Molnar Cc: Jonathan Corbet Cc: Joonsoo Kim Cc: Joern Engel Cc: Kees Cook Cc: Mark Rutland Cc: Pekka Enberg Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kfence.h | 216 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 216 insertions(+) create mode 100644 include/linux/kfence.h (limited to 'include/linux') diff --git a/include/linux/kfence.h b/include/linux/kfence.h new file mode 100644 index 000000000000..81f3911cb298 --- /dev/null +++ b/include/linux/kfence.h @@ -0,0 +1,216 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Kernel Electric-Fence (KFENCE). Public interface for allocator and fault + * handler integration. For more info see Documentation/dev-tools/kfence.rst. + * + * Copyright (C) 2020, Google LLC. + */ + +#ifndef _LINUX_KFENCE_H +#define _LINUX_KFENCE_H + +#include +#include + +#ifdef CONFIG_KFENCE + +/* + * We allocate an even number of pages, as it simplifies calculations to map + * address to metadata indices; effectively, the very first page serves as an + * extended guard page, but otherwise has no special purpose. + */ +#define KFENCE_POOL_SIZE ((CONFIG_KFENCE_NUM_OBJECTS + 1) * 2 * PAGE_SIZE) +extern char *__kfence_pool; + +#ifdef CONFIG_KFENCE_STATIC_KEYS +#include +DECLARE_STATIC_KEY_FALSE(kfence_allocation_key); +#else +#include +extern atomic_t kfence_allocation_gate; +#endif + +/** + * is_kfence_address() - check if an address belongs to KFENCE pool + * @addr: address to check + * + * Return: true or false depending on whether the address is within the KFENCE + * object range. + * + * KFENCE objects live in a separate page range and are not to be intermixed + * with regular heap objects (e.g. KFENCE objects must never be added to the + * allocator freelists). Failing to do so may and will result in heap + * corruptions, therefore is_kfence_address() must be used to check whether + * an object requires specific handling. + * + * Note: This function may be used in fast-paths, and is performance critical. + * Future changes should take this into account; for instance, we want to avoid + * introducing another load and therefore need to keep KFENCE_POOL_SIZE a + * constant (until immediate patching support is added to the kernel). + */ +static __always_inline bool is_kfence_address(const void *addr) +{ + /* + * The non-NULL check is required in case the __kfence_pool pointer was + * never initialized; keep it in the slow-path after the range-check. + */ + return unlikely((unsigned long)((char *)addr - __kfence_pool) < KFENCE_POOL_SIZE && addr); +} + +/** + * kfence_alloc_pool() - allocate the KFENCE pool via memblock + */ +void __init kfence_alloc_pool(void); + +/** + * kfence_init() - perform KFENCE initialization at boot time + * + * Requires that kfence_alloc_pool() was called before. This sets up the + * allocation gate timer, and requires that workqueues are available. + */ +void __init kfence_init(void); + +/** + * kfence_shutdown_cache() - handle shutdown_cache() for KFENCE objects + * @s: cache being shut down + * + * Before shutting down a cache, one must ensure there are no remaining objects + * allocated from it. Because KFENCE objects are not referenced from the cache + * directly, we need to check them here. + * + * Note that shutdown_cache() is internal to SL*B, and kmem_cache_destroy() does + * not return if allocated objects still exist: it prints an error message and + * simply aborts destruction of a cache, leaking memory. + * + * If the only such objects are KFENCE objects, we will not leak the entire + * cache, but instead try to provide more useful debug info by making allocated + * objects "zombie allocations". Objects may then still be used or freed (which + * is handled gracefully), but usage will result in showing KFENCE error reports + * which include stack traces to the user of the object, the original allocation + * site, and caller to shutdown_cache(). + */ +void kfence_shutdown_cache(struct kmem_cache *s); + +/* + * Allocate a KFENCE object. Allocators must not call this function directly, + * use kfence_alloc() instead. + */ +void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags); + +/** + * kfence_alloc() - allocate a KFENCE object with a low probability + * @s: struct kmem_cache with object requirements + * @size: exact size of the object to allocate (can be less than @s->size + * e.g. for kmalloc caches) + * @flags: GFP flags + * + * Return: + * * NULL - must proceed with allocating as usual, + * * non-NULL - pointer to a KFENCE object. + * + * kfence_alloc() should be inserted into the heap allocation fast path, + * allowing it to transparently return KFENCE-allocated objects with a low + * probability using a static branch (the probability is controlled by the + * kfence.sample_interval boot parameter). + */ +static __always_inline void *kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) +{ +#ifdef CONFIG_KFENCE_STATIC_KEYS + if (static_branch_unlikely(&kfence_allocation_key)) +#else + if (unlikely(!atomic_read(&kfence_allocation_gate))) +#endif + return __kfence_alloc(s, size, flags); + return NULL; +} + +/** + * kfence_ksize() - get actual amount of memory allocated for a KFENCE object + * @addr: pointer to a heap object + * + * Return: + * * 0 - not a KFENCE object, must call __ksize() instead, + * * non-0 - this many bytes can be accessed without causing a memory error. + * + * kfence_ksize() returns the number of bytes requested for a KFENCE object at + * allocation time. This number may be less than the object size of the + * corresponding struct kmem_cache. + */ +size_t kfence_ksize(const void *addr); + +/** + * kfence_object_start() - find the beginning of a KFENCE object + * @addr: address within a KFENCE-allocated object + * + * Return: address of the beginning of the object. + * + * SL[AU]B-allocated objects are laid out within a page one by one, so it is + * easy to calculate the beginning of an object given a pointer inside it and + * the object size. The same is not true for KFENCE, which places a single + * object at either end of the page. This helper function is used to find the + * beginning of a KFENCE-allocated object. + */ +void *kfence_object_start(const void *addr); + +/** + * __kfence_free() - release a KFENCE heap object to KFENCE pool + * @addr: object to be freed + * + * Requires: is_kfence_address(addr) + * + * Release a KFENCE object and mark it as freed. + */ +void __kfence_free(void *addr); + +/** + * kfence_free() - try to release an arbitrary heap object to KFENCE pool + * @addr: object to be freed + * + * Return: + * * false - object doesn't belong to KFENCE pool and was ignored, + * * true - object was released to KFENCE pool. + * + * Release a KFENCE object and mark it as freed. May be called on any object, + * even non-KFENCE objects, to simplify integration of the hooks into the + * allocator's free codepath. The allocator must check the return value to + * determine if it was a KFENCE object or not. + */ +static __always_inline __must_check bool kfence_free(void *addr) +{ + if (!is_kfence_address(addr)) + return false; + __kfence_free(addr); + return true; +} + +/** + * kfence_handle_page_fault() - perform page fault handling for KFENCE pages + * @addr: faulting address + * + * Return: + * * false - address outside KFENCE pool, + * * true - page fault handled by KFENCE, no additional handling required. + * + * A page fault inside KFENCE pool indicates a memory error, such as an + * out-of-bounds access, a use-after-free or an invalid memory access. In these + * cases KFENCE prints an error message and marks the offending page as + * present, so that the kernel can proceed. + */ +bool __must_check kfence_handle_page_fault(unsigned long addr); + +#else /* CONFIG_KFENCE */ + +static inline bool is_kfence_address(const void *addr) { return false; } +static inline void kfence_alloc_pool(void) { } +static inline void kfence_init(void) { } +static inline void kfence_shutdown_cache(struct kmem_cache *s) { } +static inline void *kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) { return NULL; } +static inline size_t kfence_ksize(const void *addr) { return 0; } +static inline void *kfence_object_start(const void *addr) { return NULL; } +static inline void __kfence_free(void *addr) { } +static inline bool __must_check kfence_free(void *addr) { return false; } +static inline bool __must_check kfence_handle_page_fault(unsigned long addr) { return false; } + +#endif + +#endif /* _LINUX_KFENCE_H */ -- cgit v1.2.3 From d438fabce7860df3cb9337776be6f90b59ced8ed Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Thu, 25 Feb 2021 17:19:08 -0800 Subject: kfence: use pt_regs to generate stack trace on faults Instead of removing the fault handling portion of the stack trace based on the fault handler's name, just use struct pt_regs directly. Change kfence_handle_page_fault() to take a struct pt_regs, and plumb it through to kfence_report_error() for out-of-bounds, use-after-free, or invalid access errors, where pt_regs is used to generate the stack trace. If the kernel is a DEBUG_KERNEL, also show registers for more information. Link: https://lkml.kernel.org/r/20201105092133.2075331-1-elver@google.com Signed-off-by: Marco Elver Suggested-by: Mark Rutland Acked-by: Mark Rutland Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Jann Horn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kfence.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kfence.h b/include/linux/kfence.h index 81f3911cb298..5a56bcf5606c 100644 --- a/include/linux/kfence.h +++ b/include/linux/kfence.h @@ -186,6 +186,7 @@ static __always_inline __must_check bool kfence_free(void *addr) /** * kfence_handle_page_fault() - perform page fault handling for KFENCE pages * @addr: faulting address + * @regs: current struct pt_regs (can be NULL, but shows full stack trace) * * Return: * * false - address outside KFENCE pool, @@ -196,7 +197,7 @@ static __always_inline __must_check bool kfence_free(void *addr) * cases KFENCE prints an error message and marks the offending page as * present, so that the kernel can proceed. */ -bool __must_check kfence_handle_page_fault(unsigned long addr); +bool __must_check kfence_handle_page_fault(unsigned long addr, struct pt_regs *regs); #else /* CONFIG_KFENCE */ @@ -209,7 +210,7 @@ static inline size_t kfence_ksize(const void *addr) { return 0; } static inline void *kfence_object_start(const void *addr) { return NULL; } static inline void __kfence_free(void *addr) { } static inline bool __must_check kfence_free(void *addr) { return false; } -static inline bool __must_check kfence_handle_page_fault(unsigned long addr) { return false; } +static inline bool __must_check kfence_handle_page_fault(unsigned long addr, struct pt_regs *regs) { return false; } #endif -- cgit v1.2.3 From d3fb45f370d927224af35d22d34ea465884afec8 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 25 Feb 2021 17:19:11 -0800 Subject: mm, kfence: insert KFENCE hooks for SLAB Inserts KFENCE hooks into the SLAB allocator. To pass the originally requested size to KFENCE, add an argument 'orig_size' to slab_alloc*(). The additional argument is required to preserve the requested original size for kmalloc() allocations, which uses size classes (e.g. an allocation of 272 bytes will return an object of size 512). Therefore, kmem_cache::size does not represent the kmalloc-caller's requested size, and we must introduce the argument 'orig_size' to propagate the originally requested size to KFENCE. Without the originally requested size, we would not be able to detect out-of-bounds accesses for objects placed at the end of a KFENCE object page if that object is not equal to the kmalloc-size class it was bucketed into. When KFENCE is disabled, there is no additional overhead, since slab_alloc*() functions are __always_inline. Link: https://lkml.kernel.org/r/20201103175841.3495947-5-elver@google.com Signed-off-by: Marco Elver Signed-off-by: Alexander Potapenko Reviewed-by: Dmitry Vyukov Co-developed-by: Marco Elver Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Catalin Marinas Cc: Dave Hansen Cc: Eric Dumazet Cc: Greg Kroah-Hartman Cc: Hillf Danton Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jann Horn Cc: Joern Engel Cc: Jonathan Corbet Cc: Kees Cook Cc: Mark Rutland Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: SeongJae Park Cc: Thomas Gleixner Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab_def.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index 9eb430c163c2..3aa5e1e73ab6 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -2,6 +2,7 @@ #ifndef _LINUX_SLAB_DEF_H #define _LINUX_SLAB_DEF_H +#include #include /* @@ -114,6 +115,8 @@ static inline unsigned int obj_to_index(const struct kmem_cache *cache, static inline int objs_per_slab_page(const struct kmem_cache *cache, const struct page *page) { + if (is_kfence_address(page_address(page))) + return 1; return cache->num; } -- cgit v1.2.3 From b89fb5ef0ce611b5db8eb9d3a5a7fcaab2cbe9e4 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 25 Feb 2021 17:19:16 -0800 Subject: mm, kfence: insert KFENCE hooks for SLUB Inserts KFENCE hooks into the SLUB allocator. To pass the originally requested size to KFENCE, add an argument 'orig_size' to slab_alloc*(). The additional argument is required to preserve the requested original size for kmalloc() allocations, which uses size classes (e.g. an allocation of 272 bytes will return an object of size 512). Therefore, kmem_cache::size does not represent the kmalloc-caller's requested size, and we must introduce the argument 'orig_size' to propagate the originally requested size to KFENCE. Without the originally requested size, we would not be able to detect out-of-bounds accesses for objects placed at the end of a KFENCE object page if that object is not equal to the kmalloc-size class it was bucketed into. When KFENCE is disabled, there is no additional overhead, since slab_alloc*() functions are __always_inline. Link: https://lkml.kernel.org/r/20201103175841.3495947-6-elver@google.com Signed-off-by: Marco Elver Signed-off-by: Alexander Potapenko Reviewed-by: Dmitry Vyukov Reviewed-by: Jann Horn Co-developed-by: Marco Elver Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christopher Lameter Cc: Dave Hansen Cc: David Rientjes Cc: Eric Dumazet Cc: Greg Kroah-Hartman Cc: Hillf Danton Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Joern Engel Cc: Jonathan Corbet Cc: Joonsoo Kim Cc: Kees Cook Cc: Mark Rutland Cc: Paul E. McKenney Cc: Pekka Enberg Cc: Peter Zijlstra Cc: SeongJae Park Cc: Thomas Gleixner Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slub_def.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 1be0ed5befa1..dcde82a4434c 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -7,6 +7,7 @@ * * (C) 2007 SGI, Christoph Lameter */ +#include #include #include @@ -185,6 +186,8 @@ static inline unsigned int __obj_to_index(const struct kmem_cache *cache, static inline unsigned int obj_to_index(const struct kmem_cache *cache, const struct page *page, void *obj) { + if (is_kfence_address(obj)) + return 0; return __obj_to_index(cache, page_address(page), obj); } -- cgit v1.2.3 From bc8fbc5f305aecf63423da91e5faf4c0ce40bf38 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Thu, 25 Feb 2021 17:19:31 -0800 Subject: kfence: add test suite Add KFENCE test suite, testing various error detection scenarios. Makes use of KUnit for test organization. Since KFENCE's interface to obtain error reports is via the console, the test verifies that KFENCE outputs expected reports to the console. [elver@google.com: fix typo in test] Link: https://lkml.kernel.org/r/X9lHQExmHGvETxY4@elver.google.com [elver@google.com: show access type in report] Link: https://lkml.kernel.org/r/20210111091544.3287013-2-elver@google.com Link: https://lkml.kernel.org/r/20201103175841.3495947-9-elver@google.com Signed-off-by: Alexander Potapenko Signed-off-by: Marco Elver Reviewed-by: Dmitry Vyukov Co-developed-by: Alexander Potapenko Reviewed-by: Jann Horn Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christopher Lameter Cc: Dave Hansen Cc: David Rientjes Cc: Eric Dumazet Cc: Greg Kroah-Hartman Cc: Hillf Danton Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Joern Engel Cc: Jonathan Corbet Cc: Joonsoo Kim Cc: Kees Cook Cc: Mark Rutland Cc: Paul E. McKenney Cc: Pekka Enberg Cc: Peter Zijlstra Cc: SeongJae Park Cc: Thomas Gleixner Cc: Vlastimil Babka Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kfence.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kfence.h b/include/linux/kfence.h index 5a56bcf5606c..a70d1ea03532 100644 --- a/include/linux/kfence.h +++ b/include/linux/kfence.h @@ -186,6 +186,7 @@ static __always_inline __must_check bool kfence_free(void *addr) /** * kfence_handle_page_fault() - perform page fault handling for KFENCE pages * @addr: faulting address + * @is_write: is access a write * @regs: current struct pt_regs (can be NULL, but shows full stack trace) * * Return: @@ -197,7 +198,7 @@ static __always_inline __must_check bool kfence_free(void *addr) * cases KFENCE prints an error message and marks the offending page as * present, so that the kernel can proceed. */ -bool __must_check kfence_handle_page_fault(unsigned long addr, struct pt_regs *regs); +bool __must_check kfence_handle_page_fault(unsigned long addr, bool is_write, struct pt_regs *regs); #else /* CONFIG_KFENCE */ @@ -210,7 +211,11 @@ static inline size_t kfence_ksize(const void *addr) { return 0; } static inline void *kfence_object_start(const void *addr) { return NULL; } static inline void __kfence_free(void *addr) { } static inline bool __must_check kfence_free(void *addr) { return false; } -static inline bool __must_check kfence_handle_page_fault(unsigned long addr, struct pt_regs *regs) { return false; } +static inline bool __must_check kfence_handle_page_fault(unsigned long addr, bool is_write, + struct pt_regs *regs) +{ + return false; +} #endif -- cgit v1.2.3 From 928501344fc645f80390afc12708c81b3595745d Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Thu, 25 Feb 2021 17:19:55 -0800 Subject: kasan, mm: don't save alloc stacks twice Patch series "kasan: optimizations and fixes for HW_TAGS", v4. This patchset makes the HW_TAGS mode more efficient, mostly by reworking poisoning approaches and simplifying/inlining some internal helpers. With this change, the overhead of HW_TAGS annotations excluding setting and checking memory tags is ~3%. The performance impact caused by tags will be unknown until we have hardware that supports MTE. As a side-effect, this patchset speeds up generic KASAN by ~15%. This patch (of 13): Currently KASAN saves allocation stacks in both kasan_slab_alloc() and kasan_kmalloc() annotations. This patch changes KASAN to save allocation stacks for slab objects from kmalloc caches in kasan_kmalloc() only, and stacks for other slab objects in kasan_slab_alloc() only. This change requires ____kasan_kmalloc() knowing whether the object belongs to a kmalloc cache. This is implemented by adding a flag field to the kasan_info structure. That flag is only set for kmalloc caches via a new kasan_cache_create_kmalloc() annotation. Link: https://lkml.kernel.org/r/cover.1612546384.git.andreyknvl@google.com Link: https://lkml.kernel.org/r/7c673ebca8d00f40a7ad6f04ab9a2bddeeae2097.1612546384.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Reviewed-by: Marco Elver Cc: Catalin Marinas Cc: Vincenzo Frascino Cc: Dmitry Vyukov Cc: Alexander Potapenko Cc: Will Deacon Cc: Andrey Ryabinin Cc: Peter Collingbourne Cc: Evgenii Stepanov Cc: Branislav Rankov Cc: Kevin Brodsky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 7eaf2d9effb4..3fb31e8a353e 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -83,6 +83,7 @@ static inline void kasan_disable_current(void) {} struct kasan_cache { int alloc_meta_offset; int free_meta_offset; + bool is_kmalloc; }; #ifdef CONFIG_KASAN_HW_TAGS @@ -143,6 +144,13 @@ static __always_inline void kasan_cache_create(struct kmem_cache *cache, __kasan_cache_create(cache, size, flags); } +void __kasan_cache_create_kmalloc(struct kmem_cache *cache); +static __always_inline void kasan_cache_create_kmalloc(struct kmem_cache *cache) +{ + if (kasan_enabled()) + __kasan_cache_create_kmalloc(cache); +} + size_t __kasan_metadata_size(struct kmem_cache *cache); static __always_inline size_t kasan_metadata_size(struct kmem_cache *cache) { @@ -278,6 +286,7 @@ static inline void kasan_free_pages(struct page *page, unsigned int order) {} static inline void kasan_cache_create(struct kmem_cache *cache, unsigned int *size, slab_flags_t *flags) {} +static inline void kasan_cache_create_kmalloc(struct kmem_cache *cache) {} static inline size_t kasan_metadata_size(struct kmem_cache *cache) { return 0; } static inline void kasan_poison_slab(struct page *page) {} static inline void kasan_unpoison_object_data(struct kmem_cache *cache, -- cgit v1.2.3 From 200072ce33b298cf14d3ed2a570f5eb27609677d Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Thu, 25 Feb 2021 17:20:11 -0800 Subject: kasan: unify large kfree checks Unify checks in kasan_kfree_large() and in kasan_slab_free_mempool() for large allocations as it's done for small kfree() allocations. With this change, kasan_slab_free_mempool() starts checking that the first byte of the memory that's being freed is accessible. Link: https://lkml.kernel.org/r/14ffc4cd867e0b1ed58f7527e3b748a1b4ad08aa.1612546384.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Reviewed-by: Marco Elver Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Branislav Rankov Cc: Catalin Marinas Cc: Dmitry Vyukov Cc: Evgenii Stepanov Cc: Kevin Brodsky Cc: Peter Collingbourne Cc: Vincenzo Frascino Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 3fb31e8a353e..b91732bd05d7 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -200,6 +200,13 @@ static __always_inline bool kasan_slab_free(struct kmem_cache *s, void *object) return false; } +void __kasan_kfree_large(void *ptr, unsigned long ip); +static __always_inline void kasan_kfree_large(void *ptr) +{ + if (kasan_enabled()) + __kasan_kfree_large(ptr, _RET_IP_); +} + void __kasan_slab_free_mempool(void *ptr, unsigned long ip); static __always_inline void kasan_slab_free_mempool(void *ptr) { @@ -247,13 +254,6 @@ static __always_inline void * __must_check kasan_krealloc(const void *object, return (void *)object; } -void __kasan_kfree_large(void *ptr, unsigned long ip); -static __always_inline void kasan_kfree_large(void *ptr) -{ - if (kasan_enabled()) - __kasan_kfree_large(ptr, _RET_IP_); -} - /* * Unlike kasan_check_read/write(), kasan_check_byte() is performed even for * the hardware tag-based mode that doesn't rely on compiler instrumentation. @@ -302,6 +302,7 @@ static inline bool kasan_slab_free(struct kmem_cache *s, void *object) { return false; } +static inline void kasan_kfree_large(void *ptr) {} static inline void kasan_slab_free_mempool(void *ptr) {} static inline void *kasan_slab_alloc(struct kmem_cache *s, void *object, gfp_t flags) @@ -322,7 +323,6 @@ static inline void *kasan_krealloc(const void *object, size_t new_size, { return (void *)object; } -static inline void kasan_kfree_large(void *ptr) {} static inline bool kasan_check_byte(const void *address) { return true; -- cgit v1.2.3 From df54714f579a77662054132161612ce3da876b0d Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 25 Feb 2021 17:20:56 -0800 Subject: include/linux: remove repeated words Drop the doubled word "for" in a comment. {firewire-cdev.h} Drop the doubled word "in" in a comment. {input.h} Drop the doubled word "a" in a comment. {mdev.h} Drop the doubled word "the" in a comment. {ptrace.h} Link: https://lkml.kernel.org/r/20210126232444.22861-1-rdunlap@infradead.org Signed-off-by: Randy Dunlap Cc: Stefan Richter Cc: Dmitry Torokhov Cc: Kirti Wankhede Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mdev.h | 2 +- include/linux/ptrace.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mdev.h b/include/linux/mdev.h index 9004375c462e..27eb383cb95d 100644 --- a/include/linux/mdev.h +++ b/include/linux/mdev.h @@ -42,7 +42,7 @@ struct device *mdev_get_iommu_device(struct device *dev); * @mdev: mdev_device structure on of mediated device * that is being created * Returns integer: success (0) or error (< 0) - * @remove: Called to free resources in parent device's driver for a + * @remove: Called to free resources in parent device's driver for * a mediated device. It is mandatory to provide 'remove' * ops. * @mdev: mdev_device device structure which is being diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 2a9df80ea887..b5ebf6c01292 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -171,7 +171,7 @@ static inline void ptrace_event(int event, unsigned long message) * * Check whether @event is enabled and, if so, report @event and @pid * to the ptrace parent. @pid is reported as the pid_t seen from the - * the ptrace parent's pid namespace. + * ptrace parent's pid namespace. * * Called without locks. */ -- cgit v1.2.3 From c131bd0b5448bb577b7a9ed48c4e528807e8d5af Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Thu, 25 Feb 2021 17:21:00 -0800 Subject: treewide: Miguel has moved Update contact info. Link: https://lkml.kernel.org/r/20210206162524.GA11520@kernel.org Signed-off-by: Miguel Ojeda Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cfag12864b.h | 2 +- include/linux/ks0108.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cfag12864b.h b/include/linux/cfag12864b.h index 4060004968c8..6617d9c68d86 100644 --- a/include/linux/cfag12864b.h +++ b/include/linux/cfag12864b.h @@ -4,7 +4,7 @@ * Version: 0.1.0 * Description: cfag12864b LCD driver header * - * Author: Copyright (C) Miguel Ojeda Sandonis + * Author: Copyright (C) Miguel Ojeda * Date: 2006-10-12 */ diff --git a/include/linux/ks0108.h b/include/linux/ks0108.h index 0738389b42b6..1a37a664f915 100644 --- a/include/linux/ks0108.h +++ b/include/linux/ks0108.h @@ -4,7 +4,7 @@ * Version: 0.1.0 * Description: ks0108 LCD Controller driver header * - * Author: Copyright (C) Miguel Ojeda Sandonis + * Author: Copyright (C) Miguel Ojeda * Date: 2006-10-31 */ -- cgit v1.2.3 From c1f26493ed7f363c63e0e9d91e50d4db26df6603 Mon Sep 17 00:00:00 2001 From: Hubert Jasudowicz Date: Thu, 25 Feb 2021 17:21:03 -0800 Subject: groups: use flexible-array member in struct group_info Replace zero-size array with flexible array member, as recommended by the docs. Link: https://lkml.kernel.org/r/155995eed35c3c1bdcc56e69d8997c8e4c46740a.1611620846.git.hubert.jasudowicz@gmail.com Signed-off-by: Hubert Jasudowicz Cc: "Peter Zijlstra (Intel)" Cc: Micah Morton Cc: Gao Xiang Cc: Michael Kelley Cc: Thomas Cedeno Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cred.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cred.h b/include/linux/cred.h index 18639c069263..4c6350503697 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -25,7 +25,7 @@ struct inode; struct group_info { atomic_t usage; int ngroups; - kgid_t gid[0]; + kgid_t gid[]; } __randomize_layout; /** -- cgit v1.2.3 From a28a6e860c6cf231cf3c5171c75c342adcd00406 Mon Sep 17 00:00:00 2001 From: Francis Laniel Date: Thu, 25 Feb 2021 17:21:20 -0800 Subject: string.h: move fortified functions definitions in a dedicated header. This patch adds fortify-string.h to contain fortified functions definitions. Thus, the code is more separated and compile time is approximately 1% faster for people who do not set CONFIG_FORTIFY_SOURCE. Link: https://lkml.kernel.org/r/20210111092141.22946-1-laniel_francis@privacyrequired.com Link: https://lkml.kernel.org/r/20210111092141.22946-2-laniel_francis@privacyrequired.com Signed-off-by: Francis Laniel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fortify-string.h | 302 +++++++++++++++++++++++++++++++++++++++++ include/linux/string.h | 282 +------------------------------------- 2 files changed, 303 insertions(+), 281 deletions(-) create mode 100644 include/linux/fortify-string.h (limited to 'include/linux') diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h new file mode 100644 index 000000000000..c1be37437e77 --- /dev/null +++ b/include/linux/fortify-string.h @@ -0,0 +1,302 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_FORTIFY_STRING_H_ +#define _LINUX_FORTIFY_STRING_H_ + + +#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) +extern void *__underlying_memchr(const void *p, int c, __kernel_size_t size) __RENAME(memchr); +extern int __underlying_memcmp(const void *p, const void *q, __kernel_size_t size) __RENAME(memcmp); +extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy); +extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(memmove); +extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(memset); +extern char *__underlying_strcat(char *p, const char *q) __RENAME(strcat); +extern char *__underlying_strcpy(char *p, const char *q) __RENAME(strcpy); +extern __kernel_size_t __underlying_strlen(const char *p) __RENAME(strlen); +extern char *__underlying_strncat(char *p, const char *q, __kernel_size_t count) __RENAME(strncat); +extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) __RENAME(strncpy); +#else +#define __underlying_memchr __builtin_memchr +#define __underlying_memcmp __builtin_memcmp +#define __underlying_memcpy __builtin_memcpy +#define __underlying_memmove __builtin_memmove +#define __underlying_memset __builtin_memset +#define __underlying_strcat __builtin_strcat +#define __underlying_strcpy __builtin_strcpy +#define __underlying_strlen __builtin_strlen +#define __underlying_strncat __builtin_strncat +#define __underlying_strncpy __builtin_strncpy +#endif + +__FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 1); + + if (__builtin_constant_p(size) && p_size < size) + __write_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __underlying_strncpy(p, q, size); +} + +__FORTIFY_INLINE char *strcat(char *p, const char *q) +{ + size_t p_size = __builtin_object_size(p, 1); + + if (p_size == (size_t)-1) + return __underlying_strcat(p, q); + if (strlcat(p, q, p_size) >= p_size) + fortify_panic(__func__); + return p; +} + +__FORTIFY_INLINE __kernel_size_t strlen(const char *p) +{ + __kernel_size_t ret; + size_t p_size = __builtin_object_size(p, 1); + + /* Work around gcc excess stack consumption issue */ + if (p_size == (size_t)-1 || + (__builtin_constant_p(p[p_size - 1]) && p[p_size - 1] == '\0')) + return __underlying_strlen(p); + ret = strnlen(p, p_size); + if (p_size <= ret) + fortify_panic(__func__); + return ret; +} + +extern __kernel_size_t __real_strnlen(const char *, __kernel_size_t) __RENAME(strnlen); +__FORTIFY_INLINE __kernel_size_t strnlen(const char *p, __kernel_size_t maxlen) +{ + size_t p_size = __builtin_object_size(p, 1); + __kernel_size_t ret = __real_strnlen(p, maxlen < p_size ? maxlen : p_size); + + if (p_size <= ret && maxlen != ret) + fortify_panic(__func__); + return ret; +} + +/* defined after fortified strlen to reuse it */ +extern size_t __real_strlcpy(char *, const char *, size_t) __RENAME(strlcpy); +__FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size) +{ + size_t ret; + size_t p_size = __builtin_object_size(p, 1); + size_t q_size = __builtin_object_size(q, 1); + + if (p_size == (size_t)-1 && q_size == (size_t)-1) + return __real_strlcpy(p, q, size); + ret = strlen(q); + if (size) { + size_t len = (ret >= size) ? size - 1 : ret; + + if (__builtin_constant_p(len) && len >= p_size) + __write_overflow(); + if (len >= p_size) + fortify_panic(__func__); + __underlying_memcpy(p, q, len); + p[len] = '\0'; + } + return ret; +} + +/* defined after fortified strnlen to reuse it */ +extern ssize_t __real_strscpy(char *, const char *, size_t) __RENAME(strscpy); +__FORTIFY_INLINE ssize_t strscpy(char *p, const char *q, size_t size) +{ + size_t len; + /* Use string size rather than possible enclosing struct size. */ + size_t p_size = __builtin_object_size(p, 1); + size_t q_size = __builtin_object_size(q, 1); + + /* If we cannot get size of p and q default to call strscpy. */ + if (p_size == (size_t) -1 && q_size == (size_t) -1) + return __real_strscpy(p, q, size); + + /* + * If size can be known at compile time and is greater than + * p_size, generate a compile time write overflow error. + */ + if (__builtin_constant_p(size) && size > p_size) + __write_overflow(); + + /* + * This call protects from read overflow, because len will default to q + * length if it smaller than size. + */ + len = strnlen(q, size); + /* + * If len equals size, we will copy only size bytes which leads to + * -E2BIG being returned. + * Otherwise we will copy len + 1 because of the final '\O'. + */ + len = len == size ? size : len + 1; + + /* + * Generate a runtime write overflow error if len is greater than + * p_size. + */ + if (len > p_size) + fortify_panic(__func__); + + /* + * We can now safely call vanilla strscpy because we are protected from: + * 1. Read overflow thanks to call to strnlen(). + * 2. Write overflow thanks to above ifs. + */ + return __real_strscpy(p, q, len); +} + +/* defined after fortified strlen and strnlen to reuse them */ +__FORTIFY_INLINE char *strncat(char *p, const char *q, __kernel_size_t count) +{ + size_t p_len, copy_len; + size_t p_size = __builtin_object_size(p, 1); + size_t q_size = __builtin_object_size(q, 1); + + if (p_size == (size_t)-1 && q_size == (size_t)-1) + return __underlying_strncat(p, q, count); + p_len = strlen(p); + copy_len = strnlen(q, count); + if (p_size < p_len + copy_len + 1) + fortify_panic(__func__); + __underlying_memcpy(p + p_len, q, copy_len); + p[p_len + copy_len] = '\0'; + return p; +} + +__FORTIFY_INLINE void *memset(void *p, int c, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + + if (__builtin_constant_p(size) && p_size < size) + __write_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __underlying_memset(p, c, size); +} + +__FORTIFY_INLINE void *memcpy(void *p, const void *q, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + + if (__builtin_constant_p(size)) { + if (p_size < size) + __write_overflow(); + if (q_size < size) + __read_overflow2(); + } + if (p_size < size || q_size < size) + fortify_panic(__func__); + return __underlying_memcpy(p, q, size); +} + +__FORTIFY_INLINE void *memmove(void *p, const void *q, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + + if (__builtin_constant_p(size)) { + if (p_size < size) + __write_overflow(); + if (q_size < size) + __read_overflow2(); + } + if (p_size < size || q_size < size) + fortify_panic(__func__); + return __underlying_memmove(p, q, size); +} + +extern void *__real_memscan(void *, int, __kernel_size_t) __RENAME(memscan); +__FORTIFY_INLINE void *memscan(void *p, int c, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + + if (__builtin_constant_p(size) && p_size < size) + __read_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __real_memscan(p, c, size); +} + +__FORTIFY_INLINE int memcmp(const void *p, const void *q, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + + if (__builtin_constant_p(size)) { + if (p_size < size) + __read_overflow(); + if (q_size < size) + __read_overflow2(); + } + if (p_size < size || q_size < size) + fortify_panic(__func__); + return __underlying_memcmp(p, q, size); +} + +__FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + + if (__builtin_constant_p(size) && p_size < size) + __read_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __underlying_memchr(p, c, size); +} + +void *__real_memchr_inv(const void *s, int c, size_t n) __RENAME(memchr_inv); +__FORTIFY_INLINE void *memchr_inv(const void *p, int c, size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + + if (__builtin_constant_p(size) && p_size < size) + __read_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __real_memchr_inv(p, c, size); +} + +extern void *__real_kmemdup(const void *src, size_t len, gfp_t gfp) __RENAME(kmemdup); +__FORTIFY_INLINE void *kmemdup(const void *p, size_t size, gfp_t gfp) +{ + size_t p_size = __builtin_object_size(p, 0); + + if (__builtin_constant_p(size) && p_size < size) + __read_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __real_kmemdup(p, size, gfp); +} + +/* defined after fortified strlen and memcpy to reuse them */ +__FORTIFY_INLINE char *strcpy(char *p, const char *q) +{ + size_t p_size = __builtin_object_size(p, 1); + size_t q_size = __builtin_object_size(q, 1); + size_t size; + + if (p_size == (size_t)-1 && q_size == (size_t)-1) + return __underlying_strcpy(p, q); + size = strlen(q) + 1; + /* test here to use the more stringent object size */ + if (p_size < size) + fortify_panic(__func__); + memcpy(p, q, size); + return p; +} + +/* Don't use these outside the FORITFY_SOURCE implementation */ +#undef __underlying_memchr +#undef __underlying_memcmp +#undef __underlying_memcpy +#undef __underlying_memmove +#undef __underlying_memset +#undef __underlying_strcat +#undef __underlying_strcpy +#undef __underlying_strlen +#undef __underlying_strncat +#undef __underlying_strncpy + +#endif /* _LINUX_FORTIFY_STRING_H_ */ diff --git a/include/linux/string.h b/include/linux/string.h index 4fcfb56abcf5..9521d8cab18e 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -266,287 +266,7 @@ void __read_overflow3(void) __compiletime_error("detected read beyond size of ob void __write_overflow(void) __compiletime_error("detected write beyond size of object passed as 1st parameter"); #if !defined(__NO_FORTIFY) && defined(__OPTIMIZE__) && defined(CONFIG_FORTIFY_SOURCE) - -#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) -extern void *__underlying_memchr(const void *p, int c, __kernel_size_t size) __RENAME(memchr); -extern int __underlying_memcmp(const void *p, const void *q, __kernel_size_t size) __RENAME(memcmp); -extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy); -extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(memmove); -extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(memset); -extern char *__underlying_strcat(char *p, const char *q) __RENAME(strcat); -extern char *__underlying_strcpy(char *p, const char *q) __RENAME(strcpy); -extern __kernel_size_t __underlying_strlen(const char *p) __RENAME(strlen); -extern char *__underlying_strncat(char *p, const char *q, __kernel_size_t count) __RENAME(strncat); -extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) __RENAME(strncpy); -#else -#define __underlying_memchr __builtin_memchr -#define __underlying_memcmp __builtin_memcmp -#define __underlying_memcpy __builtin_memcpy -#define __underlying_memmove __builtin_memmove -#define __underlying_memset __builtin_memset -#define __underlying_strcat __builtin_strcat -#define __underlying_strcpy __builtin_strcpy -#define __underlying_strlen __builtin_strlen -#define __underlying_strncat __builtin_strncat -#define __underlying_strncpy __builtin_strncpy -#endif - -__FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size) -{ - size_t p_size = __builtin_object_size(p, 1); - if (__builtin_constant_p(size) && p_size < size) - __write_overflow(); - if (p_size < size) - fortify_panic(__func__); - return __underlying_strncpy(p, q, size); -} - -__FORTIFY_INLINE char *strcat(char *p, const char *q) -{ - size_t p_size = __builtin_object_size(p, 1); - if (p_size == (size_t)-1) - return __underlying_strcat(p, q); - if (strlcat(p, q, p_size) >= p_size) - fortify_panic(__func__); - return p; -} - -__FORTIFY_INLINE __kernel_size_t strlen(const char *p) -{ - __kernel_size_t ret; - size_t p_size = __builtin_object_size(p, 1); - - /* Work around gcc excess stack consumption issue */ - if (p_size == (size_t)-1 || - (__builtin_constant_p(p[p_size - 1]) && p[p_size - 1] == '\0')) - return __underlying_strlen(p); - ret = strnlen(p, p_size); - if (p_size <= ret) - fortify_panic(__func__); - return ret; -} - -extern __kernel_size_t __real_strnlen(const char *, __kernel_size_t) __RENAME(strnlen); -__FORTIFY_INLINE __kernel_size_t strnlen(const char *p, __kernel_size_t maxlen) -{ - size_t p_size = __builtin_object_size(p, 1); - __kernel_size_t ret = __real_strnlen(p, maxlen < p_size ? maxlen : p_size); - if (p_size <= ret && maxlen != ret) - fortify_panic(__func__); - return ret; -} - -/* defined after fortified strlen to reuse it */ -extern size_t __real_strlcpy(char *, const char *, size_t) __RENAME(strlcpy); -__FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size) -{ - size_t ret; - size_t p_size = __builtin_object_size(p, 1); - size_t q_size = __builtin_object_size(q, 1); - if (p_size == (size_t)-1 && q_size == (size_t)-1) - return __real_strlcpy(p, q, size); - ret = strlen(q); - if (size) { - size_t len = (ret >= size) ? size - 1 : ret; - if (__builtin_constant_p(len) && len >= p_size) - __write_overflow(); - if (len >= p_size) - fortify_panic(__func__); - __underlying_memcpy(p, q, len); - p[len] = '\0'; - } - return ret; -} - -/* defined after fortified strnlen to reuse it */ -extern ssize_t __real_strscpy(char *, const char *, size_t) __RENAME(strscpy); -__FORTIFY_INLINE ssize_t strscpy(char *p, const char *q, size_t size) -{ - size_t len; - /* Use string size rather than possible enclosing struct size. */ - size_t p_size = __builtin_object_size(p, 1); - size_t q_size = __builtin_object_size(q, 1); - - /* If we cannot get size of p and q default to call strscpy. */ - if (p_size == (size_t) -1 && q_size == (size_t) -1) - return __real_strscpy(p, q, size); - - /* - * If size can be known at compile time and is greater than - * p_size, generate a compile time write overflow error. - */ - if (__builtin_constant_p(size) && size > p_size) - __write_overflow(); - - /* - * This call protects from read overflow, because len will default to q - * length if it smaller than size. - */ - len = strnlen(q, size); - /* - * If len equals size, we will copy only size bytes which leads to - * -E2BIG being returned. - * Otherwise we will copy len + 1 because of the final '\O'. - */ - len = len == size ? size : len + 1; - - /* - * Generate a runtime write overflow error if len is greater than - * p_size. - */ - if (len > p_size) - fortify_panic(__func__); - - /* - * We can now safely call vanilla strscpy because we are protected from: - * 1. Read overflow thanks to call to strnlen(). - * 2. Write overflow thanks to above ifs. - */ - return __real_strscpy(p, q, len); -} - -/* defined after fortified strlen and strnlen to reuse them */ -__FORTIFY_INLINE char *strncat(char *p, const char *q, __kernel_size_t count) -{ - size_t p_len, copy_len; - size_t p_size = __builtin_object_size(p, 1); - size_t q_size = __builtin_object_size(q, 1); - if (p_size == (size_t)-1 && q_size == (size_t)-1) - return __underlying_strncat(p, q, count); - p_len = strlen(p); - copy_len = strnlen(q, count); - if (p_size < p_len + copy_len + 1) - fortify_panic(__func__); - __underlying_memcpy(p + p_len, q, copy_len); - p[p_len + copy_len] = '\0'; - return p; -} - -__FORTIFY_INLINE void *memset(void *p, int c, __kernel_size_t size) -{ - size_t p_size = __builtin_object_size(p, 0); - if (__builtin_constant_p(size) && p_size < size) - __write_overflow(); - if (p_size < size) - fortify_panic(__func__); - return __underlying_memset(p, c, size); -} - -__FORTIFY_INLINE void *memcpy(void *p, const void *q, __kernel_size_t size) -{ - size_t p_size = __builtin_object_size(p, 0); - size_t q_size = __builtin_object_size(q, 0); - if (__builtin_constant_p(size)) { - if (p_size < size) - __write_overflow(); - if (q_size < size) - __read_overflow2(); - } - if (p_size < size || q_size < size) - fortify_panic(__func__); - return __underlying_memcpy(p, q, size); -} - -__FORTIFY_INLINE void *memmove(void *p, const void *q, __kernel_size_t size) -{ - size_t p_size = __builtin_object_size(p, 0); - size_t q_size = __builtin_object_size(q, 0); - if (__builtin_constant_p(size)) { - if (p_size < size) - __write_overflow(); - if (q_size < size) - __read_overflow2(); - } - if (p_size < size || q_size < size) - fortify_panic(__func__); - return __underlying_memmove(p, q, size); -} - -extern void *__real_memscan(void *, int, __kernel_size_t) __RENAME(memscan); -__FORTIFY_INLINE void *memscan(void *p, int c, __kernel_size_t size) -{ - size_t p_size = __builtin_object_size(p, 0); - if (__builtin_constant_p(size) && p_size < size) - __read_overflow(); - if (p_size < size) - fortify_panic(__func__); - return __real_memscan(p, c, size); -} - -__FORTIFY_INLINE int memcmp(const void *p, const void *q, __kernel_size_t size) -{ - size_t p_size = __builtin_object_size(p, 0); - size_t q_size = __builtin_object_size(q, 0); - if (__builtin_constant_p(size)) { - if (p_size < size) - __read_overflow(); - if (q_size < size) - __read_overflow2(); - } - if (p_size < size || q_size < size) - fortify_panic(__func__); - return __underlying_memcmp(p, q, size); -} - -__FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size) -{ - size_t p_size = __builtin_object_size(p, 0); - if (__builtin_constant_p(size) && p_size < size) - __read_overflow(); - if (p_size < size) - fortify_panic(__func__); - return __underlying_memchr(p, c, size); -} - -void *__real_memchr_inv(const void *s, int c, size_t n) __RENAME(memchr_inv); -__FORTIFY_INLINE void *memchr_inv(const void *p, int c, size_t size) -{ - size_t p_size = __builtin_object_size(p, 0); - if (__builtin_constant_p(size) && p_size < size) - __read_overflow(); - if (p_size < size) - fortify_panic(__func__); - return __real_memchr_inv(p, c, size); -} - -extern void *__real_kmemdup(const void *src, size_t len, gfp_t gfp) __RENAME(kmemdup); -__FORTIFY_INLINE void *kmemdup(const void *p, size_t size, gfp_t gfp) -{ - size_t p_size = __builtin_object_size(p, 0); - if (__builtin_constant_p(size) && p_size < size) - __read_overflow(); - if (p_size < size) - fortify_panic(__func__); - return __real_kmemdup(p, size, gfp); -} - -/* defined after fortified strlen and memcpy to reuse them */ -__FORTIFY_INLINE char *strcpy(char *p, const char *q) -{ - size_t p_size = __builtin_object_size(p, 1); - size_t q_size = __builtin_object_size(q, 1); - size_t size; - if (p_size == (size_t)-1 && q_size == (size_t)-1) - return __underlying_strcpy(p, q); - size = strlen(q) + 1; - /* test here to use the more stringent object size */ - if (p_size < size) - fortify_panic(__func__); - memcpy(p, q, size); - return p; -} - -/* Don't use these outside the FORITFY_SOURCE implementation */ -#undef __underlying_memchr -#undef __underlying_memcmp -#undef __underlying_memcpy -#undef __underlying_memmove -#undef __underlying_memset -#undef __underlying_strcat -#undef __underlying_strcpy -#undef __underlying_strlen -#undef __underlying_strncat -#undef __underlying_strncpy +#include #endif /** -- cgit v1.2.3 From e1fdc403349c64fa58f4c163f4bf9b860b4db808 Mon Sep 17 00:00:00 2001 From: Vijayanand Jitta Date: Thu, 25 Feb 2021 17:21:27 -0800 Subject: lib: stackdepot: add support to disable stack depot Add a kernel parameter stack_depot_disable to disable stack depot. So that stack hash table doesn't consume any memory when stack depot is disabled. The use case is CONFIG_PAGE_OWNER without page_owner=on. Without this patch, stackdepot will consume the memory for the hashtable. By default, it's 8M which is never trivial. With this option, in CONFIG_PAGE_OWNER configured system, page_owner=off, stack_depot_disable in kernel command line, we could save the wasted memory for the hashtable. [akpm@linux-foundation.org: fix CONFIG_STACKDEPOT=n build] Link: https://lkml.kernel.org/r/1611749198-24316-2-git-send-email-vjitta@codeaurora.org Signed-off-by: Vinayak Menon Signed-off-by: Vijayanand Jitta Cc: Alexander Potapenko Cc: Minchan Kim Cc: Yogesh Lal Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/stackdepot.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index 24d49c732341..6bb4bc1a5f54 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -21,4 +21,13 @@ unsigned int stack_depot_fetch(depot_stack_handle_t handle, unsigned int filter_irq_stacks(unsigned long *entries, unsigned int nr_entries); +#ifdef CONFIG_STACKDEPOT +int stack_depot_init(void); +#else +static inline int stack_depot_init(void) +{ + return 0; +} +#endif /* CONFIG_STACKDEPOT */ + #endif -- cgit v1.2.3 From 4945cca232ce8bc699b8743f2436af664c471b96 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 25 Feb 2021 17:21:37 -0800 Subject: include/linux/bitops.h: spelling s/synomyn/synonym/ Fix a misspelling of "synonym". Link: https://lkml.kernel.org/r/20210108105305.2028120-1-geert+renesas@glider.be Signed-off-by: Geert Uytterhoeven Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitops.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index a61f192c096b..a5a48303b0f1 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -214,7 +214,7 @@ static inline int get_count_order_long(unsigned long l) * __ffs64 - find first set bit in a 64 bit word * @word: The 64 bit word * - * On 64 bit arches this is a synomyn for __ffs + * On 64 bit arches this is a synonym for __ffs * The result is not defined if no bits are set, so check that @word * is non-zero before calling this. */ -- cgit v1.2.3 From a5a673f7312253a842f3da8c60c980461cc269ec Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 25 Feb 2021 17:22:15 -0800 Subject: init: clean up early_param_on_off() macro Use early_param() to define early_param_on_off(). Link: https://lkml.kernel.org/r/20210201041532.4025025-1-masahiroy@kernel.org Signed-off-by: Masahiro Yamada Reviewed-by: Johan Hovold Reviewed-by: Miguel Ojeda Cc: Masahiro Yamada Cc: Joe Perches Cc: Nick Desaulniers Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/init.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init.h b/include/linux/init.h index a01f01c1a5c5..31f54de58429 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -338,14 +338,14 @@ struct obs_kernel_param { var = 1; \ return 0; \ } \ - __setup_param(str_on, parse_##var##_on, parse_##var##_on, 1); \ + early_param(str_on, parse_##var##_on); \ \ static int __init parse_##var##_off(char *arg) \ { \ var = 0; \ return 0; \ } \ - __setup_param(str_off, parse_##var##_off, parse_##var##_off, 1) + early_param(str_off, parse_##var##_off) /* Relies on boot_command_line being set */ void __init parse_early_param(void); -- cgit v1.2.3 From d54ce6158e354f5358a547b96299ecd7f3725393 Mon Sep 17 00:00:00 2001 From: Sumit Garg Date: Thu, 25 Feb 2021 17:22:38 -0800 Subject: kgdb: fix to kill breakpoints on initmem after boot Currently breakpoints in kernel .init.text section are not handled correctly while allowing to remove them even after corresponding pages have been freed. Fix it via killing .init.text section breakpoints just prior to initmem pages being freed. Doug: "HW breakpoints aren't handled by this patch but it's probably not such a big deal". Link: https://lkml.kernel.org/r/20210224081652.587785-1-sumit.garg@linaro.org Signed-off-by: Sumit Garg Suggested-by: Doug Anderson Acked-by: Doug Anderson Acked-by: Daniel Thompson Tested-by: Daniel Thompson Cc: Masami Hiramatsu Cc: Steven Rostedt (VMware) Cc: Jason Wessel Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kgdb.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index 0444b44bd156..392a3670944c 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -359,9 +359,11 @@ extern atomic_t kgdb_active; extern bool dbg_is_early; extern void __init dbg_late_init(void); extern void kgdb_panic(const char *msg); +extern void kgdb_free_init_mem(void); #else /* ! CONFIG_KGDB */ #define in_dbg_master() (0) #define dbg_late_init() static inline void kgdb_panic(const char *msg) {} +static inline void kgdb_free_init_mem(void) { } #endif /* ! CONFIG_KGDB */ #endif /* _KGDB_H_ */ -- cgit v1.2.3 From f685a533a7fab35c5d069dcd663f59c8e4171a75 Mon Sep 17 00:00:00 2001 From: Huang Pei Date: Thu, 25 Feb 2021 17:22:49 -0800 Subject: MIPS: make userspace mapping young by default MIPS page fault path(except huge page) takes 3 exceptions (1 TLB Miss + 2 TLB Invalid), butthe second TLB Invalid exception is just triggered by __update_tlb from do_page_fault writing tlb without _PAGE_VALID set. With this patch, user space mapping prot is made young by default (with both _PAGE_VALID and _PAGE_YOUNG set), and it only take 1 TLB Miss + 1 TLB Invalid exception Remove pte_sw_mkyoung without polluting MM code and make page fault delay of MIPS on par with other architecture Link: https://lkml.kernel.org/r/20210204013942.8398-1-huangpei@loongson.cn Signed-off-by: Huang Pei Reviewed-by: Nicholas Piggin Acked-by: Acked-by: Thomas Bogendoerfer Cc: Christophe Leroy Cc: Cc: Bibo Mao Cc: Jiaxun Yang Cc: Paul Burton Cc: Li Xuefeng Cc: Yang Tiezhu Cc: Gao Juxin Cc: Fuxin Zhang Cc: Huacai Chen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pgtable.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 36eb748f3c97..cdfc4e9f253e 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -432,14 +432,6 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addres * To be differentiate with macro pte_mkyoung, this macro is used on platforms * where software maintains page access bit. */ -#ifndef pte_sw_mkyoung -static inline pte_t pte_sw_mkyoung(pte_t pte) -{ - return pte; -} -#define pte_sw_mkyoung pte_sw_mkyoung -#endif - #ifndef pte_savedwrite #define pte_savedwrite pte_write #endif -- cgit v1.2.3 From 5f7136db82996089cdfb2939c7664b29e9da141d Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 29 Jan 2021 04:38:57 +0000 Subject: block: Add bio_max_segs It's often inconvenient to use BIO_MAX_PAGES due to min() requiring the sign to be the same. Introduce bio_max_segs() and change BIO_MAX_PAGES to be unsigned to make it easier for the users. Reviewed-by: Chaitanya Kulkarni Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Jens Axboe --- include/linux/bio.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 5b468f2242ff..983ed2fe7c85 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -20,7 +20,12 @@ #define BIO_BUG_ON #endif -#define BIO_MAX_PAGES 256 +#define BIO_MAX_PAGES 256U + +static inline unsigned int bio_max_segs(unsigned int nr_segs) +{ + return min(nr_segs, BIO_MAX_PAGES); +} #define bio_prio(bio) (bio)->bi_ioprio #define bio_set_prio(bio, prio) ((bio)->bi_ioprio = prio) -- cgit v1.2.3 From 5218e12e9f3a324f41c05da4874d76d7ea3677cb Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Mon, 1 Mar 2021 17:23:25 +0100 Subject: block: Drop leftover references to RQF_SORTED Commit a1ce35fa49852db60fc6e268038530be533c5b15 ("block: remove dead elevator code") removed all users of RQF_SORTED. However it is still defined, and there is one reference left to it (which in effect is dead code). Clear it all up. Signed-off-by: Jean Delvare Cc: Jens Axboe Cc: Ming Lei Cc: Omar Sandoval Cc: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c032cfe133c7..bc6bc8383b43 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -65,8 +65,6 @@ typedef void (rq_end_io_fn)(struct request *, blk_status_t); * request flags */ typedef __u32 __bitwise req_flags_t; -/* elevator knows about this request */ -#define RQF_SORTED ((__force req_flags_t)(1 << 0)) /* drive already may have started this one */ #define RQF_STARTED ((__force req_flags_t)(1 << 1)) /* may not be passed by ioscheduler */ -- cgit v1.2.3 From 08c2a4bc9f2acaefbd0158866db5cb3238a68674 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Mon, 1 Mar 2021 18:31:24 -0600 Subject: ALSA: hda: move Intel SoundWire ACPI scan to dedicated module The ACPI scan capabilities is called from the intel-dspconfig as well as the SOF/HDaudio drivers. This creates dependencies and randconfig issues when HDaudio and SOF/SoundWire are not all configured as modules. To simplify Kconfig dependencies between HDAudio, SoundWire, SOF and intel-dspconfig, move the ACPI scan helpers to a dedicated module. This follows the same idea as NHLT helpers which are already handled as a dedicated module. The only functional change is that the kernel parameter to filter links is now handled by a different module, but that was only provided for developers needing work-arounds for early BIOS releases. Reported-by: Arnd Bergmann Signed-off-by: Pierre-Louis Bossart Reviewed-by: Kai Vehmanen Reviewed-by: Guennadi Liakhovetski Reviewed-by: Bard Liao Acked-by: Mark Brown Acked-by: Vinod Koul Link: https://lore.kernel.org/r/20210302003125.1178419-7-pierre-louis.bossart@linux.intel.com Signed-off-by: Takashi Iwai --- include/linux/soundwire/sdw_intel.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index 120ffddc03d2..3a5446ac014a 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -187,4 +187,6 @@ void sdw_intel_enable_irq(void __iomem *mmio_base, bool enable); irqreturn_t sdw_intel_thread(int irq, void *dev_id); +#define SDW_INTEL_QUIRK_MASK_BUS_DISABLE BIT(1) + #endif -- cgit v1.2.3 From caf6912f3f4af7232340d500a4a2008f81b93f14 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 2 Mar 2021 14:53:21 -0700 Subject: swap: fix swapfile read/write offset We're not factoring in the start of the file for where to write and read the swapfile, which leads to very unfortunate side effects of writing where we should not be... Fixes: 48d15436fde6 ("mm: remove get_swap_bio") Signed-off-by: Jens Axboe --- include/linux/swap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 32f665b1ee85..4cc6ec3bf0ab 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -485,6 +485,7 @@ struct backing_dev_info; extern int init_swap_address_space(unsigned int type, unsigned long nr_pages); extern void exit_swap_address_space(unsigned int type); extern struct swap_info_struct *get_swap_device(swp_entry_t entry); +sector_t swap_page_sector(struct page *page); static inline void put_swap_device(struct swap_info_struct *si) { -- cgit v1.2.3 From ff70784ab9f89e78e67d5d172bf7644de673f61f Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 2 Mar 2021 15:35:48 +0200 Subject: ACPI: bus: Constify is_acpi_node() and friends (part 2) Commit 8b9d6802583a ("ACPI: Constify acpi_bus helper functions, switch to macros") only changed functions for CONFIG_ACPI=y case. This part adjusts the rest. Fixes: 8b9d6802583a ("ACPI: Constify acpi_bus helper functions, switch to macros") Signed-off-by: Andy Shevchenko Reviewed-by: Sakari Ailus Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 3c5757d539ab..9f432411e988 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -746,12 +746,12 @@ acpi_dev_get_first_match_dev(const char *hid, const char *uid, s64 hrv) static inline void acpi_dev_put(struct acpi_device *adev) {} -static inline bool is_acpi_node(struct fwnode_handle *fwnode) +static inline bool is_acpi_node(const struct fwnode_handle *fwnode) { return false; } -static inline bool is_acpi_device_node(struct fwnode_handle *fwnode) +static inline bool is_acpi_device_node(const struct fwnode_handle *fwnode) { return false; } @@ -761,7 +761,7 @@ static inline struct acpi_device *to_acpi_device_node(struct fwnode_handle *fwno return NULL; } -static inline bool is_acpi_data_node(struct fwnode_handle *fwnode) +static inline bool is_acpi_data_node(const struct fwnode_handle *fwnode) { return false; } -- cgit v1.2.3 From 8452d4a674b0e59bd53baef0b30b018690dde594 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Sat, 27 Feb 2021 11:16:46 +0000 Subject: io_uring: destroy io-wq on exec Destroy current's io-wq backend and tctx on __io_uring_task_cancel(), aka exec(). Looks it's not strictly necessary, because it will be done at some point when the task dies and changes of creds/files/etc. are handled, but better to do that earlier to free io-wq and not potentially lock previous mm and other resources for the time being. It's safe to do because we wait for all requests of the current task to complete, so no request will use tctx afterwards. Note, that io_uring_files_cancel() may leave some requests for later reaping, so it leaves tctx intact, that's ok as the task is dying anyway. Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe --- include/linux/io_uring.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 51ede771cd99..7cb7bd0e334c 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -38,7 +38,7 @@ void __io_uring_free(struct task_struct *tsk); static inline void io_uring_task_cancel(void) { - if (current->io_uring && !xa_empty(¤t->io_uring->xa)) + if (current->io_uring) __io_uring_task_cancel(); } static inline void io_uring_files_cancel(struct files_struct *files) -- cgit v1.2.3 From f9f344479d8b40b3b001c913fb992d85d19261d0 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Fri, 26 Feb 2021 14:09:15 -0500 Subject: tracing: Fix comment about the trace_event_call flags In the declaration of the struct trace_event_call, the flags has the bits defined in the comment above it. But these bits are also defined by the TRACE_EVENT_FL_* enums just above the declaration of the struct. As the comment about the flags in the struct has become stale and incorrect, just replace it with a reference to the TRACE_EVENT_FL_* enum above. Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 7077fec653bb..28e7af1406f2 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -349,15 +349,8 @@ struct trace_event_call { struct event_filter *filter; void *mod; void *data; - /* - * bit 0: filter_active - * bit 1: allow trace by non root (cap any) - * bit 2: failed to apply filter - * bit 3: trace internal event (do not enable) - * bit 4: Event was enabled by module - * bit 5: use call filter rather than file filter - * bit 6: Event is a tracepoint - */ + + /* See the TRACE_EVENT_FL_* flags above */ int flags; /* static flags of different events */ #ifdef CONFIG_PERF_EVENTS -- cgit v1.2.3 From cc440e8738e5c875297ac0e90316745093be7e28 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 4 Mar 2021 12:21:05 -0700 Subject: kernel: provide create_io_thread() helper Provide a generic helper for setting up an io_uring worker. Returns a task_struct so that the caller can do whatever setup is needed, then call wake_up_new_task() to kick it into gear. Add a kernel_clone_args member, io_thread, which tells copy_process() to mark the task with PF_IO_WORKER. Signed-off-by: Jens Axboe --- include/linux/sched/task.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index c0f71f2e7160..ef02be869cf2 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -31,6 +31,7 @@ struct kernel_clone_args { /* Number of elements in *set_tid */ size_t set_tid_size; int cgroup; + int io_thread; struct cgroup *cgrp; struct css_set *cset; }; @@ -82,6 +83,7 @@ extern void exit_files(struct task_struct *); extern void exit_itimers(struct signal_struct *); extern pid_t kernel_clone(struct kernel_clone_args *kargs); +struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node); struct task_struct *fork_idle(int); struct mm_struct *copy_init_mm(void); extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); -- cgit v1.2.3