diff options
753 files changed, 13669 insertions, 4845 deletions
diff --git a/Documentation/ABI/stable/sysfs-bus-usb b/Documentation/ABI/stable/sysfs-bus-usb index 2be603c52a24..a6b685724740 100644 --- a/Documentation/ABI/stable/sysfs-bus-usb +++ b/Documentation/ABI/stable/sysfs-bus-usb @@ -37,8 +37,8 @@ Description: that the USB device has been connected to the machine. This file is read-only. Users: - PowerTOP <power@bughost.org> - http://www.lesswatts.org/projects/powertop/ + PowerTOP <powertop@lists.01.org> + https://01.org/powertop/ What: /sys/bus/usb/device/.../power/active_duration Date: January 2008 @@ -57,8 +57,8 @@ Description: will give an integer percentage. Note that this does not account for counter wrap. Users: - PowerTOP <power@bughost.org> - http://www.lesswatts.org/projects/powertop/ + PowerTOP <powertop@lists.01.org> + https://01.org/powertop/ What: /sys/bus/usb/devices/<busnum>-<port[.port]>...:<config num>-<interface num>/supports_autosuspend Date: January 2008 diff --git a/Documentation/ABI/testing/sysfs-devices-power b/Documentation/ABI/testing/sysfs-devices-power index 9d43e7670841..efe449bdf811 100644 --- a/Documentation/ABI/testing/sysfs-devices-power +++ b/Documentation/ABI/testing/sysfs-devices-power @@ -1,6 +1,6 @@ What: /sys/devices/.../power/ Date: January 2009 -Contact: Rafael J. Wysocki <rjw@sisk.pl> +Contact: Rafael J. Wysocki <rjw@rjwysocki.net> Description: The /sys/devices/.../power directory contains attributes allowing the user space to check and modify some power @@ -8,7 +8,7 @@ Description: What: /sys/devices/.../power/wakeup Date: January 2009 -Contact: Rafael J. Wysocki <rjw@sisk.pl> +Contact: Rafael J. Wysocki <rjw@rjwysocki.net> Description: The /sys/devices/.../power/wakeup attribute allows the user space to check if the device is enabled to wake up the system @@ -34,7 +34,7 @@ Description: What: /sys/devices/.../power/control Date: January 2009 -Contact: Rafael J. Wysocki <rjw@sisk.pl> +Contact: Rafael J. Wysocki <rjw@rjwysocki.net> Description: The /sys/devices/.../power/control attribute allows the user space to control the run-time power management of the device. @@ -53,7 +53,7 @@ Description: What: /sys/devices/.../power/async Date: January 2009 -Contact: Rafael J. Wysocki <rjw@sisk.pl> +Contact: Rafael J. Wysocki <rjw@rjwysocki.net> Description: The /sys/devices/.../async attribute allows the user space to enable or diasble the device's suspend and resume callbacks to @@ -79,7 +79,7 @@ Description: What: /sys/devices/.../power/wakeup_count Date: September 2010 -Contact: Rafael J. Wysocki <rjw@sisk.pl> +Contact: Rafael J. Wysocki <rjw@rjwysocki.net> Description: The /sys/devices/.../wakeup_count attribute contains the number of signaled wakeup events associated with the device. This @@ -88,7 +88,7 @@ Description: What: /sys/devices/.../power/wakeup_active_count Date: September 2010 -Contact: Rafael J. Wysocki <rjw@sisk.pl> +Contact: Rafael J. Wysocki <rjw@rjwysocki.net> Description: The /sys/devices/.../wakeup_active_count attribute contains the number of times the processing of wakeup events associated with @@ -98,7 +98,7 @@ Description: What: /sys/devices/.../power/wakeup_abort_count Date: February 2012 -Contact: Rafael J. Wysocki <rjw@sisk.pl> +Contact: Rafael J. Wysocki <rjw@rjwysocki.net> Description: The /sys/devices/.../wakeup_abort_count attribute contains the number of times the processing of a wakeup event associated with @@ -109,7 +109,7 @@ Description: What: /sys/devices/.../power/wakeup_expire_count Date: February 2012 -Contact: Rafael J. Wysocki <rjw@sisk.pl> +Contact: Rafael J. Wysocki <rjw@rjwysocki.net> Description: The /sys/devices/.../wakeup_expire_count attribute contains the number of times a wakeup event associated with the device has @@ -119,7 +119,7 @@ Description: What: /sys/devices/.../power/wakeup_active Date: September 2010 -Contact: Rafael J. Wysocki <rjw@sisk.pl> +Contact: Rafael J. Wysocki <rjw@rjwysocki.net> Description: The /sys/devices/.../wakeup_active attribute contains either 1, or 0, depending on whether or not a wakeup event associated with @@ -129,7 +129,7 @@ Description: What: /sys/devices/.../power/wakeup_total_time_ms Date: September 2010 -Contact: Rafael J. Wysocki <rjw@sisk.pl> +Contact: Rafael J. Wysocki <rjw@rjwysocki.net> Description: The /sys/devices/.../wakeup_total_time_ms attribute contains the total time of processing wakeup events associated with the @@ -139,7 +139,7 @@ Description: What: /sys/devices/.../power/wakeup_max_time_ms Date: September 2010 -Contact: Rafael J. Wysocki <rjw@sisk.pl> +Contact: Rafael J. Wysocki <rjw@rjwysocki.net> Description: The /sys/devices/.../wakeup_max_time_ms attribute contains the maximum time of processing a single wakeup event associated @@ -149,7 +149,7 @@ Description: What: /sys/devices/.../power/wakeup_last_time_ms Date: September 2010 -Contact: Rafael J. Wysocki <rjw@sisk.pl> +Contact: Rafael J. Wysocki <rjw@rjwysocki.net> Description: The /sys/devices/.../wakeup_last_time_ms attribute contains the value of the monotonic clock corresponding to the time of @@ -160,7 +160,7 @@ Description: What: /sys/devices/.../power/wakeup_prevent_sleep_time_ms Date: February 2012 -Contact: Rafael J. Wysocki <rjw@sisk.pl> +Contact: Rafael J. Wysocki <rjw@rjwysocki.net> Description: The /sys/devices/.../wakeup_prevent_sleep_time_ms attribute contains the total time the device has been preventing @@ -189,7 +189,7 @@ Description: What: /sys/devices/.../power/pm_qos_latency_us Date: March 2012 -Contact: Rafael J. Wysocki <rjw@sisk.pl> +Contact: Rafael J. Wysocki <rjw@rjwysocki.net> Description: The /sys/devices/.../power/pm_qos_resume_latency_us attribute contains the PM QoS resume latency limit for the given device, @@ -207,7 +207,7 @@ Description: What: /sys/devices/.../power/pm_qos_no_power_off Date: September 2012 -Contact: Rafael J. Wysocki <rjw@sisk.pl> +Contact: Rafael J. Wysocki <rjw@rjwysocki.net> Description: The /sys/devices/.../power/pm_qos_no_power_off attribute is used for manipulating the PM QoS "no power off" flag. If @@ -222,7 +222,7 @@ Description: What: /sys/devices/.../power/pm_qos_remote_wakeup Date: September 2012 -Contact: Rafael J. Wysocki <rjw@sisk.pl> +Contact: Rafael J. Wysocki <rjw@rjwysocki.net> Description: The /sys/devices/.../power/pm_qos_remote_wakeup attribute is used for manipulating the PM QoS "remote wakeup required" diff --git a/Documentation/ABI/testing/sysfs-power b/Documentation/ABI/testing/sysfs-power index 217772615d02..205a73878441 100644 --- a/Documentation/ABI/testing/sysfs-power +++ b/Documentation/ABI/testing/sysfs-power @@ -1,6 +1,6 @@ What: /sys/power/ Date: August 2006 -Contact: Rafael J. Wysocki <rjw@sisk.pl> +Contact: Rafael J. Wysocki <rjw@rjwysocki.net> Description: The /sys/power directory will contain files that will provide a unified interface to the power management @@ -8,7 +8,7 @@ Description: What: /sys/power/state Date: August 2006 -Contact: Rafael J. Wysocki <rjw@sisk.pl> +Contact: Rafael J. Wysocki <rjw@rjwysocki.net> Description: The /sys/power/state file controls the system power state. Reading from this file returns what states are supported, @@ -22,7 +22,7 @@ Description: What: /sys/power/disk Date: September 2006 -Contact: Rafael J. Wysocki <rjw@sisk.pl> +Contact: Rafael J. Wysocki <rjw@rjwysocki.net> Description: The /sys/power/disk file controls the operating mode of the suspend-to-disk mechanism. Reading from this file returns @@ -67,7 +67,7 @@ Description: What: /sys/power/image_size Date: August 2006 -Contact: Rafael J. Wysocki <rjw@sisk.pl> +Contact: Rafael J. Wysocki <rjw@rjwysocki.net> Description: The /sys/power/image_size file controls the size of the image created by the suspend-to-disk mechanism. It can be written a @@ -84,7 +84,7 @@ Description: What: /sys/power/pm_trace Date: August 2006 -Contact: Rafael J. Wysocki <rjw@sisk.pl> +Contact: Rafael J. Wysocki <rjw@rjwysocki.net> Description: The /sys/power/pm_trace file controls the code which saves the last PM event point in the RTC across reboots, so that you can @@ -133,7 +133,7 @@ Description: What: /sys/power/pm_async Date: January 2009 -Contact: Rafael J. Wysocki <rjw@sisk.pl> +Contact: Rafael J. Wysocki <rjw@rjwysocki.net> Description: The /sys/power/pm_async file controls the switch allowing the user space to enable or disable asynchronous suspend and resume @@ -146,7 +146,7 @@ Description: What: /sys/power/wakeup_count Date: July 2010 -Contact: Rafael J. Wysocki <rjw@sisk.pl> +Contact: Rafael J. Wysocki <rjw@rjwysocki.net> Description: The /sys/power/wakeup_count file allows user space to put the system into a sleep state while taking into account the @@ -161,7 +161,7 @@ Description: What: /sys/power/reserved_size Date: May 2011 -Contact: Rafael J. Wysocki <rjw@sisk.pl> +Contact: Rafael J. Wysocki <rjw@rjwysocki.net> Description: The /sys/power/reserved_size file allows user space to control the amount of memory reserved for allocations made by device @@ -175,7 +175,7 @@ Description: What: /sys/power/autosleep Date: April 2012 -Contact: Rafael J. Wysocki <rjw@sisk.pl> +Contact: Rafael J. Wysocki <rjw@rjwysocki.net> Description: The /sys/power/autosleep file can be written one of the strings returned by reads from /sys/power/state. If that happens, a @@ -192,7 +192,7 @@ Description: What: /sys/power/wake_lock Date: February 2012 -Contact: Rafael J. Wysocki <rjw@sisk.pl> +Contact: Rafael J. Wysocki <rjw@rjwysocki.net> Description: The /sys/power/wake_lock file allows user space to create wakeup source objects and activate them on demand (if one of @@ -219,7 +219,7 @@ Description: What: /sys/power/wake_unlock Date: February 2012 -Contact: Rafael J. Wysocki <rjw@sisk.pl> +Contact: Rafael J. Wysocki <rjw@rjwysocki.net> Description: The /sys/power/wake_unlock file allows user space to deactivate wakeup sources created with the help of /sys/power/wake_lock. diff --git a/Documentation/DMA-API-HOWTO.txt b/Documentation/DMA-API-HOWTO.txt index 14129f149a75..5e983031cc11 100644 --- a/Documentation/DMA-API-HOWTO.txt +++ b/Documentation/DMA-API-HOWTO.txt @@ -101,14 +101,23 @@ style to do this even if your device holds the default setting, because this shows that you did think about these issues wrt. your device. -The query is performed via a call to dma_set_mask(): +The query is performed via a call to dma_set_mask_and_coherent(): - int dma_set_mask(struct device *dev, u64 mask); + int dma_set_mask_and_coherent(struct device *dev, u64 mask); -The query for consistent allocations is performed via a call to -dma_set_coherent_mask(): +which will query the mask for both streaming and coherent APIs together. +If you have some special requirements, then the following two separate +queries can be used instead: - int dma_set_coherent_mask(struct device *dev, u64 mask); + The query for streaming mappings is performed via a call to + dma_set_mask(): + + int dma_set_mask(struct device *dev, u64 mask); + + The query for consistent allocations is performed via a call + to dma_set_coherent_mask(): + + int dma_set_coherent_mask(struct device *dev, u64 mask); Here, dev is a pointer to the device struct of your device, and mask is a bit mask describing which bits of an address your device @@ -137,7 +146,7 @@ exactly why. The standard 32-bit addressing device would do something like this: - if (dma_set_mask(dev, DMA_BIT_MASK(32))) { + if (dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32))) { printk(KERN_WARNING "mydev: No suitable DMA available.\n"); goto ignore_this_device; @@ -171,22 +180,20 @@ the case would look like this: int using_dac, consistent_using_dac; - if (!dma_set_mask(dev, DMA_BIT_MASK(64))) { + if (!dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64))) { using_dac = 1; consistent_using_dac = 1; - dma_set_coherent_mask(dev, DMA_BIT_MASK(64)); - } else if (!dma_set_mask(dev, DMA_BIT_MASK(32))) { + } else if (!dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32))) { using_dac = 0; consistent_using_dac = 0; - dma_set_coherent_mask(dev, DMA_BIT_MASK(32)); } else { printk(KERN_WARNING "mydev: No suitable DMA available.\n"); goto ignore_this_device; } -dma_set_coherent_mask() will always be able to set the same or a -smaller mask as dma_set_mask(). However for the rare case that a +The coherent coherent mask will always be able to set the same or a +smaller mask as the streaming mask. However for the rare case that a device driver only uses consistent allocations, one would have to check the return value from dma_set_coherent_mask(). @@ -199,9 +206,9 @@ address you might do something like: goto ignore_this_device; } -When dma_set_mask() is successful, and returns zero, the kernel saves -away this mask you have provided. The kernel will use this -information later when you make DMA mappings. +When dma_set_mask() or dma_set_mask_and_coherent() is successful, and +returns zero, the kernel saves away this mask you have provided. The +kernel will use this information later when you make DMA mappings. There is a case which we are aware of at this time, which is worth mentioning in this documentation. If your device supports multiple diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt index 78a6c569d204..e865279cec58 100644 --- a/Documentation/DMA-API.txt +++ b/Documentation/DMA-API.txt @@ -142,6 +142,14 @@ internal API for use by the platform than an external API for use by driver writers. int +dma_set_mask_and_coherent(struct device *dev, u64 mask) + +Checks to see if the mask is possible and updates the device +streaming and coherent DMA mask parameters if it is. + +Returns: 0 if successful and a negative error if not. + +int dma_set_mask(struct device *dev, u64 mask) Checks to see if the mask is possible and updates the device diff --git a/Documentation/acpi/dsdt-override.txt b/Documentation/acpi/dsdt-override.txt index febbb1ba4d23..784841caa6e6 100644 --- a/Documentation/acpi/dsdt-override.txt +++ b/Documentation/acpi/dsdt-override.txt @@ -4,4 +4,4 @@ CONFIG_ACPI_CUSTOM_DSDT builds the image into the kernel. When to use this method is described in detail on the Linux/ACPI home page: -http://www.lesswatts.org/projects/acpi/overridingDSDT.php +https://01.org/linux-acpi/documentation/overriding-dsdt diff --git a/Documentation/connector/ucon.c b/Documentation/connector/ucon.c index 4848db8c71ff..8a4da64e02a8 100644 --- a/Documentation/connector/ucon.c +++ b/Documentation/connector/ucon.c @@ -71,7 +71,7 @@ static int netlink_send(int s, struct cn_msg *msg) nlh->nlmsg_seq = seq++; nlh->nlmsg_pid = getpid(); nlh->nlmsg_type = NLMSG_DONE; - nlh->nlmsg_len = NLMSG_LENGTH(size - sizeof(*nlh)); + nlh->nlmsg_len = size; nlh->nlmsg_flags = 0; m = NLMSG_DATA(nlh); diff --git a/Documentation/devicetree/bindings/memory.txt b/Documentation/devicetree/bindings/memory.txt deleted file mode 100644 index eb2469365593..000000000000 --- a/Documentation/devicetree/bindings/memory.txt +++ /dev/null @@ -1,168 +0,0 @@ -*** Memory binding *** - -The /memory node provides basic information about the address and size -of the physical memory. This node is usually filled or updated by the -bootloader, depending on the actual memory configuration of the given -hardware. - -The memory layout is described by the following node: - -/ { - #address-cells = <(n)>; - #size-cells = <(m)>; - memory { - device_type = "memory"; - reg = <(baseaddr1) (size1) - (baseaddr2) (size2) - ... - (baseaddrN) (sizeN)>; - }; - ... -}; - -A memory node follows the typical device tree rules for "reg" property: -n: number of cells used to store base address value -m: number of cells used to store size value -baseaddrX: defines a base address of the defined memory bank -sizeX: the size of the defined memory bank - - -More than one memory bank can be defined. - - -*** Reserved memory regions *** - -In /memory/reserved-memory node one can create child nodes describing -particular reserved (excluded from normal use) memory regions. Such -memory regions are usually designed for the special usage by various -device drivers. A good example are contiguous memory allocations or -memory sharing with other operating system on the same hardware board. -Those special memory regions might depend on the board configuration and -devices used on the target system. - -Parameters for each memory region can be encoded into the device tree -with the following convention: - -[(label):] (name) { - compatible = "linux,contiguous-memory-region", "reserved-memory-region"; - reg = <(address) (size)>; - (linux,default-contiguous-region); -}; - -compatible: one or more of: - - "linux,contiguous-memory-region" - enables binding of this - region to Contiguous Memory Allocator (special region for - contiguous memory allocations, shared with movable system - memory, Linux kernel-specific). - - "reserved-memory-region" - compatibility is defined, given - region is assigned for exclusive usage for by the respective - devices. - -reg: standard property defining the base address and size of - the memory region - -linux,default-contiguous-region: property indicating that the region - is the default region for all contiguous memory - allocations, Linux specific (optional) - -It is optional to specify the base address, so if one wants to use -autoconfiguration of the base address, '0' can be specified as a base -address in the 'reg' property. - -The /memory/reserved-memory node must contain the same #address-cells -and #size-cells value as the root node. - - -*** Device node's properties *** - -Once regions in the /memory/reserved-memory node have been defined, they -may be referenced by other device nodes. Bindings that wish to reference -memory regions should explicitly document their use of the following -property: - -memory-region = <&phandle_to_defined_region>; - -This property indicates that the device driver should use the memory -region pointed by the given phandle. - - -*** Example *** - -This example defines a memory consisting of 4 memory banks. 3 contiguous -regions are defined for Linux kernel, one default of all device drivers -(named contig_mem, placed at 0x72000000, 64MiB), one dedicated to the -framebuffer device (labelled display_mem, placed at 0x78000000, 8MiB) -and one for multimedia processing (labelled multimedia_mem, placed at -0x77000000, 64MiB). 'display_mem' region is then assigned to fb@12300000 -device for DMA memory allocations (Linux kernel drivers will use CMA is -available or dma-exclusive usage otherwise). 'multimedia_mem' is -assigned to scaler@12500000 and codec@12600000 devices for contiguous -memory allocations when CMA driver is enabled. - -The reason for creating a separate region for framebuffer device is to -match the framebuffer base address to the one configured by bootloader, -so once Linux kernel drivers starts no glitches on the displayed boot -logo appears. Scaller and codec drivers should share the memory -allocations. - -/ { - #address-cells = <1>; - #size-cells = <1>; - - /* ... */ - - memory { - reg = <0x40000000 0x10000000 - 0x50000000 0x10000000 - 0x60000000 0x10000000 - 0x70000000 0x10000000>; - - reserved-memory { - #address-cells = <1>; - #size-cells = <1>; - - /* - * global autoconfigured region for contiguous allocations - * (used only with Contiguous Memory Allocator) - */ - contig_region@0 { - compatible = "linux,contiguous-memory-region"; - reg = <0x0 0x4000000>; - linux,default-contiguous-region; - }; - - /* - * special region for framebuffer - */ - display_region: region@78000000 { - compatible = "linux,contiguous-memory-region", "reserved-memory-region"; - reg = <0x78000000 0x800000>; - }; - - /* - * special region for multimedia processing devices - */ - multimedia_region: region@77000000 { - compatible = "linux,contiguous-memory-region"; - reg = <0x77000000 0x4000000>; - }; - }; - }; - - /* ... */ - - fb0: fb@12300000 { - status = "okay"; - memory-region = <&display_region>; - }; - - scaler: scaler@12500000 { - status = "okay"; - memory-region = <&multimedia_region>; - }; - - codec: codec@12600000 { - status = "okay"; - memory-region = <&multimedia_region>; - }; -}; diff --git a/Documentation/networking/dccp.txt b/Documentation/networking/dccp.txt index d718bc2ff1cf..bf5dbe3ab8c5 100644 --- a/Documentation/networking/dccp.txt +++ b/Documentation/networking/dccp.txt @@ -18,8 +18,8 @@ Introduction Datagram Congestion Control Protocol (DCCP) is an unreliable, connection oriented protocol designed to solve issues present in UDP and TCP, particularly for real-time and multimedia (streaming) traffic. -It divides into a base protocol (RFC 4340) and plugable congestion control -modules called CCIDs. Like plugable TCP congestion control, at least one CCID +It divides into a base protocol (RFC 4340) and pluggable congestion control +modules called CCIDs. Like pluggable TCP congestion control, at least one CCID needs to be enabled in order for the protocol to function properly. In the Linux implementation, this is the TCP-like CCID2 (RFC 4341). Additional CCIDs, such as the TCP-friendly CCID3 (RFC 4342), are optional. diff --git a/Documentation/networking/e100.txt b/Documentation/networking/e100.txt index 13a32124bca0..f862cf3aff34 100644 --- a/Documentation/networking/e100.txt +++ b/Documentation/networking/e100.txt @@ -103,7 +103,7 @@ Additional Configurations PRO/100 Family of Adapters is e100. As an example, if you install the e100 driver for two PRO/100 adapters - (eth0 and eth1), add the following to a configuraton file in /etc/modprobe.d/ + (eth0 and eth1), add the following to a configuration file in /etc/modprobe.d/ alias eth0 e100 alias eth1 e100 diff --git a/Documentation/networking/ieee802154.txt b/Documentation/networking/ieee802154.txt index 09eb57329f11..22bbc7225f8e 100644 --- a/Documentation/networking/ieee802154.txt +++ b/Documentation/networking/ieee802154.txt @@ -4,7 +4,7 @@ Introduction ============ -The IEEE 802.15.4 working group focuses on standartization of bottom +The IEEE 802.15.4 working group focuses on standardization of bottom two layers: Medium Access Control (MAC) and Physical (PHY). And there are mainly two options available for upper layers: - ZigBee - proprietary protocol from ZigBee Alliance @@ -66,7 +66,7 @@ net_device, with .type = ARPHRD_IEEE802154. Data is exchanged with socket family code via plain sk_buffs. On skb reception skb->cb must contain additional info as described in the struct ieee802154_mac_cb. During packet transmission the skb->cb is used to provide additional data to device's header_ops->create -function. Be aware, that this data can be overriden later (when socket code +function. Be aware that this data can be overridden later (when socket code submits skb to qdisc), so if you need something from that cb later, you should store info in the skb->data on your own. diff --git a/Documentation/networking/l2tp.txt b/Documentation/networking/l2tp.txt index e63fc1f7bf87..c74434de2fa5 100644 --- a/Documentation/networking/l2tp.txt +++ b/Documentation/networking/l2tp.txt @@ -197,7 +197,7 @@ state information because the file format is subject to change. It is implemented to provide extra debug information to help diagnose problems.) Users should use the netlink API. -/proc/net/pppol2tp is also provided for backwards compaibility with +/proc/net/pppol2tp is also provided for backwards compatibility with the original pppol2tp driver. It lists information about L2TPv2 tunnels and sessions only. Its use is discouraged. diff --git a/Documentation/networking/netdev-FAQ.txt b/Documentation/networking/netdev-FAQ.txt index d9112f01c44a..0fe1c6e0dbcd 100644 --- a/Documentation/networking/netdev-FAQ.txt +++ b/Documentation/networking/netdev-FAQ.txt @@ -4,23 +4,23 @@ Information you need to know about netdev Q: What is netdev? -A: It is a mailing list for all network related linux stuff. This includes +A: It is a mailing list for all network-related Linux stuff. This includes anything found under net/ (i.e. core code like IPv6) and drivers/net - (i.e. hardware specific drivers) in the linux source tree. + (i.e. hardware specific drivers) in the Linux source tree. Note that some subsystems (e.g. wireless drivers) which have a high volume of traffic have their own specific mailing lists. - The netdev list is managed (like many other linux mailing lists) through + The netdev list is managed (like many other Linux mailing lists) through VGER ( http://vger.kernel.org/ ) and archives can be found below: http://marc.info/?l=linux-netdev http://www.spinics.net/lists/netdev/ - Aside from subsystems like that mentioned above, all network related linux - development (i.e. RFC, review, comments, etc) takes place on netdev. + Aside from subsystems like that mentioned above, all network-related Linux + development (i.e. RFC, review, comments, etc.) takes place on netdev. -Q: How do the changes posted to netdev make their way into linux? +Q: How do the changes posted to netdev make their way into Linux? A: There are always two trees (git repositories) in play. Both are driven by David Miller, the main network maintainer. There is the "net" tree, @@ -35,7 +35,7 @@ A: There are always two trees (git repositories) in play. Both are driven Q: How often do changes from these trees make it to the mainline Linus tree? A: To understand this, you need to know a bit of background information - on the cadence of linux development. Each new release starts off with + on the cadence of Linux development. Each new release starts off with a two week "merge window" where the main maintainers feed their new stuff to Linus for merging into the mainline tree. After the two weeks, the merge window is closed, and it is called/tagged "-rc1". No new @@ -46,7 +46,7 @@ A: To understand this, you need to know a bit of background information things are in a state of churn), and a week after the last vX.Y-rcN was done, the official "vX.Y" is released. - Relating that to netdev: At the beginning of the 2 week merge window, + Relating that to netdev: At the beginning of the 2-week merge window, the net-next tree will be closed - no new changes/features. The accumulated new content of the past ~10 weeks will be passed onto mainline/Linus via a pull request for vX.Y -- at the same time, @@ -59,16 +59,16 @@ A: To understand this, you need to know a bit of background information IMPORTANT: Do not send new net-next content to netdev during the period during which net-next tree is closed. - Shortly after the two weeks have passed, (and vX.Y-rc1 is released) the + Shortly after the two weeks have passed (and vX.Y-rc1 is released), the tree for net-next reopens to collect content for the next (vX.Y+1) release. If you aren't subscribed to netdev and/or are simply unsure if net-next has re-opened yet, simply check the net-next git repository link above for - any new networking related commits. + any new networking-related commits. The "net" tree continues to collect fixes for the vX.Y content, and is fed back to Linus at regular (~weekly) intervals. Meaning that the - focus for "net" is on stablilization and bugfixes. + focus for "net" is on stabilization and bugfixes. Finally, the vX.Y gets released, and the whole cycle starts over. @@ -217,7 +217,7 @@ A: Attention to detail. Re-read your own work as if you were the to why it happens, and then if necessary, explain why the fix proposed is the best way to get things done. Don't mangle whitespace, and as is common, don't mis-indent function arguments that span multiple lines. - If it is your 1st patch, mail it to yourself so you can test apply + If it is your first patch, mail it to yourself so you can test apply it to an unpatched tree to confirm infrastructure didn't mangle it. Finally, go back and read Documentation/SubmittingPatches to be diff --git a/Documentation/networking/netlink_mmap.txt b/Documentation/networking/netlink_mmap.txt index 533378839546..b26122973525 100644 --- a/Documentation/networking/netlink_mmap.txt +++ b/Documentation/networking/netlink_mmap.txt @@ -45,7 +45,7 @@ processing. Conversion of the reception path involves calling poll() on the file descriptor, once the socket is readable the frames from the ring are -processsed in order until no more messages are available, as indicated by +processed in order until no more messages are available, as indicated by a status word in the frame header. On kernel side, in order to make use of memory mapped I/O on receive, the @@ -56,7 +56,7 @@ Dumps of kernel databases automatically support memory mapped I/O. Conversion of the transmit path involves changing message construction to use memory from the TX ring instead of (usually) a buffer declared on the -stack and setting up the frame header approriately. Optionally poll() can +stack and setting up the frame header appropriately. Optionally poll() can be used to wait for free frames in the TX ring. Structured and definitions for using memory mapped I/O are contained in @@ -231,7 +231,7 @@ Ring setup: if (setsockopt(fd, NETLINK_TX_RING, &req, sizeof(req)) < 0) exit(1) - /* Calculate size of each invididual ring */ + /* Calculate size of each individual ring */ ring_size = req.nm_block_nr * req.nm_block_size; /* Map RX/TX rings. The TX ring is located after the RX ring */ diff --git a/Documentation/networking/operstates.txt b/Documentation/networking/operstates.txt index 97694572338b..355c6d8ef8ad 100644 --- a/Documentation/networking/operstates.txt +++ b/Documentation/networking/operstates.txt @@ -89,8 +89,8 @@ packets. The name 'carrier' and the inversion are historical, think of it as lower layer. Note that for certain kind of soft-devices, which are not managing any -real hardware, there is possible to set this bit from userpsace. -One should use TVL IFLA_CARRIER to do so. +real hardware, it is possible to set this bit from userspace. One +should use TVL IFLA_CARRIER to do so. netif_carrier_ok() can be used to query that bit. diff --git a/Documentation/networking/rxrpc.txt b/Documentation/networking/rxrpc.txt index 60d05eb77c64..b89bc82eed46 100644 --- a/Documentation/networking/rxrpc.txt +++ b/Documentation/networking/rxrpc.txt @@ -144,7 +144,7 @@ An overview of the RxRPC protocol: (*) Calls use ACK packets to handle reliability. Data packets are also explicitly sequenced per call. - (*) There are two types of positive acknowledgement: hard-ACKs and soft-ACKs. + (*) There are two types of positive acknowledgment: hard-ACKs and soft-ACKs. A hard-ACK indicates to the far side that all the data received to a point has been received and processed; a soft-ACK indicates that the data has been received but may yet be discarded and re-requested. The sender may diff --git a/Documentation/networking/stmmac.txt b/Documentation/networking/stmmac.txt index 457b8bbafb08..cdd916da838d 100644 --- a/Documentation/networking/stmmac.txt +++ b/Documentation/networking/stmmac.txt @@ -160,7 +160,7 @@ Where: o pmt: core has the embedded power module (optional). o force_sf_dma_mode: force DMA to use the Store and Forward mode instead of the Threshold. - o force_thresh_dma_mode: force DMA to use the Shreshold mode other than + o force_thresh_dma_mode: force DMA to use the Threshold mode other than the Store and Forward mode. o riwt_off: force to disable the RX watchdog feature and switch to NAPI mode. o fix_mac_speed: this callback is used for modifying some syscfg registers @@ -175,7 +175,7 @@ Where: registers. o custom_cfg/custom_data: this is a custom configuration that can be passed while initializing the resources. - o bsp_priv: another private poiter. + o bsp_priv: another private pointer. For MDIO bus The we have: @@ -271,7 +271,7 @@ reset procedure etc). o dwmac1000_dma.c: dma functions for the GMAC chip; o dwmac1000.h: specific header file for the GMAC; o dwmac100_core: MAC 100 core and dma code; - o dwmac100_dma.c: dma funtions for the MAC chip; + o dwmac100_dma.c: dma functions for the MAC chip; o dwmac1000.h: specific header file for the MAC; o dwmac_lib.c: generic DMA functions shared among chips; o enh_desc.c: functions for handling enhanced descriptors; @@ -364,4 +364,4 @@ Auto-negotiated Link Parter Ability. 10) TODO: o XGMAC is not supported. o Complete the TBI & RTBI support. - o extened VLAN support for 3.70a SYNP GMAC. + o extend VLAN support for 3.70a SYNP GMAC. diff --git a/Documentation/networking/vortex.txt b/Documentation/networking/vortex.txt index 9a8041dcbb53..97282da82b75 100644 --- a/Documentation/networking/vortex.txt +++ b/Documentation/networking/vortex.txt @@ -68,7 +68,7 @@ Module parameters There are several parameters which may be provided to the driver when its module is loaded. These are usually placed in /etc/modprobe.d/*.conf -configuretion files. Example: +configuration files. Example: options 3c59x debug=3 rx_copybreak=300 @@ -178,7 +178,7 @@ max_interrupt_work=N The driver's interrupt service routine can handle many receive and transmit packets in a single invocation. It does this in a loop. - The value of max_interrupt_work governs how mnay times the interrupt + The value of max_interrupt_work governs how many times the interrupt service routine will loop. The default value is 32 loops. If this is exceeded the interrupt service routine gives up and generates a warning message "eth0: Too much work in interrupt". diff --git a/Documentation/networking/x25-iface.txt b/Documentation/networking/x25-iface.txt index 78f662ee0622..7f213b556e85 100644 --- a/Documentation/networking/x25-iface.txt +++ b/Documentation/networking/x25-iface.txt @@ -105,7 +105,7 @@ reduced by the following measures or a combination thereof: later. The lapb module interface was modified to support this. Its data_indication() method should now transparently pass the - netif_rx() return value to the (lapb mopdule) caller. + netif_rx() return value to the (lapb module) caller. (2) Drivers for kernel versions 2.2.x should always check the global variable netdev_dropping when a new frame is received. The driver should only call netif_rx() if netdev_dropping is zero. Otherwise diff --git a/MAINTAINERS b/MAINTAINERS index a4dc305ff7e4..908624892c79 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -237,11 +237,11 @@ F: drivers/platform/x86/acer-wmi.c ACPI M: Len Brown <lenb@kernel.org> -M: Rafael J. Wysocki <rjw@sisk.pl> +M: Rafael J. Wysocki <rjw@rjwysocki.net> L: linux-acpi@vger.kernel.org -W: http://www.lesswatts.org/projects/acpi/ -Q: http://patchwork.kernel.org/project/linux-acpi/list/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux +W: https://01.org/linux-acpi +Q: https://patchwork.kernel.org/project/linux-acpi/list/ +T: git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm S: Supported F: drivers/acpi/ F: drivers/pnp/pnpacpi/ @@ -256,21 +256,21 @@ F: drivers/pci/*/*/*acpi* ACPI FAN DRIVER M: Zhang Rui <rui.zhang@intel.com> L: linux-acpi@vger.kernel.org -W: http://www.lesswatts.org/projects/acpi/ +W: https://01.org/linux-acpi S: Supported F: drivers/acpi/fan.c ACPI THERMAL DRIVER M: Zhang Rui <rui.zhang@intel.com> L: linux-acpi@vger.kernel.org -W: http://www.lesswatts.org/projects/acpi/ +W: https://01.org/linux-acpi S: Supported F: drivers/acpi/*thermal* ACPI VIDEO DRIVER M: Zhang Rui <rui.zhang@intel.com> L: linux-acpi@vger.kernel.org -W: http://www.lesswatts.org/projects/acpi/ +W: https://01.org/linux-acpi S: Supported F: drivers/acpi/video.c @@ -1801,6 +1801,7 @@ F: include/net/bluetooth/ BONDING DRIVER M: Jay Vosburgh <fubar@us.ibm.com> +M: Veaceslav Falico <vfalico@redhat.com> M: Andy Gospodarek <andy@greyhouse.net> L: netdev@vger.kernel.org W: http://sourceforge.net/projects/bonding/ @@ -2310,7 +2311,7 @@ S: Maintained F: drivers/net/ethernet/ti/cpmac.c CPU FREQUENCY DRIVERS -M: Rafael J. Wysocki <rjw@sisk.pl> +M: Rafael J. Wysocki <rjw@rjwysocki.net> M: Viresh Kumar <viresh.kumar@linaro.org> L: cpufreq@vger.kernel.org L: linux-pm@vger.kernel.org @@ -2341,7 +2342,7 @@ S: Maintained F: drivers/cpuidle/cpuidle-big_little.c CPUIDLE DRIVERS -M: Rafael J. Wysocki <rjw@sisk.pl> +M: Rafael J. Wysocki <rjw@rjwysocki.net> M: Daniel Lezcano <daniel.lezcano@linaro.org> L: linux-pm@vger.kernel.org S: Maintained @@ -2728,6 +2729,8 @@ T: git git://git.linaro.org/people/sumitsemwal/linux-dma-buf.git DMA GENERIC OFFLOAD ENGINE SUBSYSTEM M: Vinod Koul <vinod.koul@intel.com> M: Dan Williams <dan.j.williams@intel.com> +L: dmaengine@vger.kernel.org +Q: https://patchwork.kernel.org/project/linux-dmaengine/list/ S: Supported F: drivers/dma/ F: include/linux/dma* @@ -3563,7 +3566,7 @@ F: fs/freevxfs/ FREEZER M: Pavel Machek <pavel@ucw.cz> -M: "Rafael J. Wysocki" <rjw@sisk.pl> +M: "Rafael J. Wysocki" <rjw@rjwysocki.net> L: linux-pm@vger.kernel.org S: Supported F: Documentation/power/freezing-of-tasks.txt @@ -3634,6 +3637,12 @@ L: linux-scsi@vger.kernel.org S: Odd Fixes (e.g., new signatures) F: drivers/scsi/fdomain.* +GCOV BASED KERNEL PROFILING +M: Peter Oberparleiter <oberpar@linux.vnet.ibm.com> +S: Maintained +F: kernel/gcov/ +F: Documentation/gcov.txt + GDT SCSI DISK ARRAY CONTROLLER DRIVER M: Achim Leubner <achim_leubner@adaptec.com> L: linux-scsi@vger.kernel.org @@ -3899,7 +3908,7 @@ F: drivers/video/hgafb.c HIBERNATION (aka Software Suspend, aka swsusp) M: Pavel Machek <pavel@ucw.cz> -M: "Rafael J. Wysocki" <rjw@sisk.pl> +M: "Rafael J. Wysocki" <rjw@rjwysocki.net> L: linux-pm@vger.kernel.org S: Supported F: arch/x86/power/ @@ -4349,7 +4358,7 @@ F: drivers/video/i810/ INTEL MENLOW THERMAL DRIVER M: Sujith Thomas <sujith.thomas@intel.com> L: platform-driver-x86@vger.kernel.org -W: http://www.lesswatts.org/projects/acpi/ +W: https://01.org/linux-acpi S: Supported F: drivers/platform/x86/intel_menlow.c @@ -4361,7 +4370,10 @@ F: arch/x86/kernel/microcode_intel.c INTEL I/OAT DMA DRIVER M: Dan Williams <dan.j.williams@intel.com> -S: Maintained +M: Dave Jiang <dave.jiang@intel.com> +L: dmaengine@vger.kernel.org +Q: https://patchwork.kernel.org/project/linux-dmaengine/list/ +S: Supported F: drivers/dma/ioat* INTEL IOMMU (VT-d) @@ -7832,6 +7844,13 @@ F: Documentation/sound/alsa/soc/ F: sound/soc/ F: include/sound/soc* +SOUND - DMAENGINE HELPERS +M: Lars-Peter Clausen <lars@metafoo.de> +S: Supported +F: include/sound/dmaengine_pcm.h +F: sound/core/pcm_dmaengine.c +F: sound/soc/soc-generic-dmaengine-pcm.c + SPARC + UltraSPARC (sparc/sparc64) M: "David S. Miller" <davem@davemloft.net> L: sparclinux@vger.kernel.org @@ -8111,7 +8130,7 @@ F: drivers/sh/ SUSPEND TO RAM M: Len Brown <len.brown@intel.com> M: Pavel Machek <pavel@ucw.cz> -M: "Rafael J. Wysocki" <rjw@sisk.pl> +M: "Rafael J. Wysocki" <rjw@rjwysocki.net> L: linux-pm@vger.kernel.org S: Supported F: Documentation/power/ @@ -8905,61 +8924,14 @@ W: http://pegasus2.sourceforge.net/ S: Maintained F: drivers/net/usb/rtl8150.c -USB SERIAL BELKIN F5U103 DRIVER -M: William Greathouse <wgreathouse@smva.com> -L: linux-usb@vger.kernel.org -S: Maintained -F: drivers/usb/serial/belkin_sa.* - -USB SERIAL CYPRESS M8 DRIVER -M: Lonnie Mendez <dignome@gmail.com> -L: linux-usb@vger.kernel.org -S: Maintained -W: http://geocities.com/i0xox0i -W: http://firstlight.net/cvs -F: drivers/usb/serial/cypress_m8.* - -USB SERIAL CYBERJACK DRIVER -M: Matthias Bruestle and Harald Welte <support@reiner-sct.com> -W: http://www.reiner-sct.de/support/treiber_cyberjack.php -S: Maintained -F: drivers/usb/serial/cyberjack.c - -USB SERIAL DIGI ACCELEPORT DRIVER -M: Peter Berger <pberger@brimson.com> -M: Al Borchers <alborchers@steinerpoint.com> +USB SERIAL SUBSYSTEM +M: Johan Hovold <jhovold@gmail.com> L: linux-usb@vger.kernel.org S: Maintained -F: drivers/usb/serial/digi_acceleport.c - -USB SERIAL DRIVER -M: Greg Kroah-Hartman <gregkh@linuxfoundation.org> -L: linux-usb@vger.kernel.org -S: Supported F: Documentation/usb/usb-serial.txt -F: drivers/usb/serial/generic.c -F: drivers/usb/serial/usb-serial.c +F: drivers/usb/serial/ F: include/linux/usb/serial.h -USB SERIAL EMPEG EMPEG-CAR MARK I/II DRIVER -M: Gary Brubaker <xavyer@ix.netcom.com> -L: linux-usb@vger.kernel.org -S: Maintained -F: drivers/usb/serial/empeg.c - -USB SERIAL KEYSPAN DRIVER -M: Greg Kroah-Hartman <gregkh@linuxfoundation.org> -L: linux-usb@vger.kernel.org -S: Maintained -F: drivers/usb/serial/*keyspan* - -USB SERIAL WHITEHEAT DRIVER -M: Support Department <support@connecttech.com> -L: linux-usb@vger.kernel.org -W: http://www.connecttech.com -S: Supported -F: drivers/usb/serial/whiteheat* - USB SMSC75XX ETHERNET DRIVER M: Steve Glendinning <steve.glendinning@shawell.net> L: netdev@vger.kernel.org @@ -1,7 +1,7 @@ VERSION = 3 PATCHLEVEL = 12 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = NAME = One Giant Leap for Frogkind # *DOCUMENTATION* diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 91dbb2757afd..fb4177e48260 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -35,6 +35,12 @@ config ARC select PERF_USE_VMALLOC select HAVE_DEBUG_STACKOVERFLOW +config TRACE_IRQFLAGS_SUPPORT + def_bool y + +config LOCKDEP_SUPPORT + def_bool y + config SCHED_OMIT_FRAME_POINTER def_bool y @@ -139,8 +145,8 @@ config ARC_HAS_REENTRANT_IRQ_LV2 endif config NR_CPUS - int "Maximum number of CPUs (2-32)" - range 2 32 + int "Maximum number of CPUs (2-4096)" + range 2 4096 depends on SMP default "2" diff --git a/arch/arc/boot/dts/abilis_tb100.dtsi b/arch/arc/boot/dts/abilis_tb100.dtsi index d9f8249aa66e..3942634f805a 100644 --- a/arch/arc/boot/dts/abilis_tb100.dtsi +++ b/arch/arc/boot/dts/abilis_tb100.dtsi @@ -43,124 +43,124 @@ iomux: iomux@FF10601c { /* Port 1 */ pctl_tsin_s0: pctl-tsin-s0 { /* Serial TS-in 0 */ - pingrp = "mis0_pins"; + abilis,function = "mis0"; }; pctl_tsin_s1: pctl-tsin-s1 { /* Serial TS-in 1 */ - pingrp = "mis1_pins"; + abilis,function = "mis1"; }; pctl_gpio_a: pctl-gpio-a { /* GPIO bank A */ - pingrp = "gpioa_pins"; + abilis,function = "gpioa"; }; pctl_tsin_p1: pctl-tsin-p1 { /* Parallel TS-in 1 */ - pingrp = "mip1_pins"; + abilis,function = "mip1"; }; /* Port 2 */ pctl_tsin_s2: pctl-tsin-s2 { /* Serial TS-in 2 */ - pingrp = "mis2_pins"; + abilis,function = "mis2"; }; pctl_tsin_s3: pctl-tsin-s3 { /* Serial TS-in 3 */ - pingrp = "mis3_pins"; + abilis,function = "mis3"; }; pctl_gpio_c: pctl-gpio-c { /* GPIO bank C */ - pingrp = "gpioc_pins"; + abilis,function = "gpioc"; }; pctl_tsin_p3: pctl-tsin-p3 { /* Parallel TS-in 3 */ - pingrp = "mip3_pins"; + abilis,function = "mip3"; }; /* Port 3 */ pctl_tsin_s4: pctl-tsin-s4 { /* Serial TS-in 4 */ - pingrp = "mis4_pins"; + abilis,function = "mis4"; }; pctl_tsin_s5: pctl-tsin-s5 { /* Serial TS-in 5 */ - pingrp = "mis5_pins"; + abilis,function = "mis5"; }; pctl_gpio_e: pctl-gpio-e { /* GPIO bank E */ - pingrp = "gpioe_pins"; + abilis,function = "gpioe"; }; pctl_tsin_p5: pctl-tsin-p5 { /* Parallel TS-in 5 */ - pingrp = "mip5_pins"; + abilis,function = "mip5"; }; /* Port 4 */ pctl_tsin_s6: pctl-tsin-s6 { /* Serial TS-in 6 */ - pingrp = "mis6_pins"; + abilis,function = "mis6"; }; pctl_tsin_s7: pctl-tsin-s7 { /* Serial TS-in 7 */ - pingrp = "mis7_pins"; + abilis,function = "mis7"; }; pctl_gpio_g: pctl-gpio-g { /* GPIO bank G */ - pingrp = "gpiog_pins"; + abilis,function = "gpiog"; }; pctl_tsin_p7: pctl-tsin-p7 { /* Parallel TS-in 7 */ - pingrp = "mip7_pins"; + abilis,function = "mip7"; }; /* Port 5 */ pctl_gpio_j: pctl-gpio-j { /* GPIO bank J */ - pingrp = "gpioj_pins"; + abilis,function = "gpioj"; }; pctl_gpio_k: pctl-gpio-k { /* GPIO bank K */ - pingrp = "gpiok_pins"; + abilis,function = "gpiok"; }; pctl_ciplus: pctl-ciplus { /* CI+ interface */ - pingrp = "ciplus_pins"; + abilis,function = "ciplus"; }; pctl_mcard: pctl-mcard { /* M-Card interface */ - pingrp = "mcard_pins"; + abilis,function = "mcard"; }; /* Port 6 */ pctl_tsout_p: pctl-tsout-p { /* Parallel TS-out */ - pingrp = "mop_pins"; + abilis,function = "mop"; }; pctl_tsout_s0: pctl-tsout-s0 { /* Serial TS-out 0 */ - pingrp = "mos0_pins"; + abilis,function = "mos0"; }; pctl_tsout_s1: pctl-tsout-s1 { /* Serial TS-out 1 */ - pingrp = "mos1_pins"; + abilis,function = "mos1"; }; pctl_tsout_s2: pctl-tsout-s2 { /* Serial TS-out 2 */ - pingrp = "mos2_pins"; + abilis,function = "mos2"; }; pctl_tsout_s3: pctl-tsout-s3 { /* Serial TS-out 3 */ - pingrp = "mos3_pins"; + abilis,function = "mos3"; }; /* Port 7 */ pctl_uart0: pctl-uart0 { /* UART 0 */ - pingrp = "uart0_pins"; + abilis,function = "uart0"; }; pctl_uart1: pctl-uart1 { /* UART 1 */ - pingrp = "uart1_pins"; + abilis,function = "uart1"; }; pctl_gpio_l: pctl-gpio-l { /* GPIO bank L */ - pingrp = "gpiol_pins"; + abilis,function = "gpiol"; }; pctl_gpio_m: pctl-gpio-m { /* GPIO bank M */ - pingrp = "gpiom_pins"; + abilis,function = "gpiom"; }; /* Port 8 */ pctl_spi3: pctl-spi3 { - pingrp = "spi3_pins"; + abilis,function = "spi3"; }; /* Port 9 */ pctl_spi1: pctl-spi1 { - pingrp = "spi1_pins"; + abilis,function = "spi1"; }; pctl_gpio_n: pctl-gpio-n { - pingrp = "gpion_pins"; + abilis,function = "gpion"; }; /* Unmuxed GPIOs */ pctl_gpio_b: pctl-gpio-b { - pingrp = "gpiob_pins"; + abilis,function = "gpiob"; }; pctl_gpio_d: pctl-gpio-d { - pingrp = "gpiod_pins"; + abilis,function = "gpiod"; }; pctl_gpio_f: pctl-gpio-f { - pingrp = "gpiof_pins"; + abilis,function = "gpiof"; }; pctl_gpio_h: pctl-gpio-h { - pingrp = "gpioh_pins"; + abilis,function = "gpioh"; }; pctl_gpio_i: pctl-gpio-i { - pingrp = "gpioi_pins"; + abilis,function = "gpioi"; }; }; @@ -172,9 +172,10 @@ interrupts = <27 2>; reg = <0xFF140000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <0>; - gpio-pins = <&pctl_gpio_a>; + #gpio-cells = <2>; + abilis,ngpio = <3>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioa"; }; gpiob: gpio@FF141000 { compatible = "abilis,tb10x-gpio"; @@ -184,9 +185,10 @@ interrupts = <27 2>; reg = <0xFF141000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <3>; - gpio-pins = <&pctl_gpio_b>; + #gpio-cells = <2>; + abilis,ngpio = <2>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiob"; }; gpioc: gpio@FF142000 { compatible = "abilis,tb10x-gpio"; @@ -196,9 +198,10 @@ interrupts = <27 2>; reg = <0xFF142000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <5>; - gpio-pins = <&pctl_gpio_c>; + #gpio-cells = <2>; + abilis,ngpio = <3>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioc"; }; gpiod: gpio@FF143000 { compatible = "abilis,tb10x-gpio"; @@ -208,9 +211,10 @@ interrupts = <27 2>; reg = <0xFF143000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <8>; - gpio-pins = <&pctl_gpio_d>; + #gpio-cells = <2>; + abilis,ngpio = <2>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiod"; }; gpioe: gpio@FF144000 { compatible = "abilis,tb10x-gpio"; @@ -220,9 +224,10 @@ interrupts = <27 2>; reg = <0xFF144000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <10>; - gpio-pins = <&pctl_gpio_e>; + #gpio-cells = <2>; + abilis,ngpio = <3>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioe"; }; gpiof: gpio@FF145000 { compatible = "abilis,tb10x-gpio"; @@ -232,9 +237,10 @@ interrupts = <27 2>; reg = <0xFF145000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <13>; - gpio-pins = <&pctl_gpio_f>; + #gpio-cells = <2>; + abilis,ngpio = <2>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiof"; }; gpiog: gpio@FF146000 { compatible = "abilis,tb10x-gpio"; @@ -244,9 +250,10 @@ interrupts = <27 2>; reg = <0xFF146000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <15>; - gpio-pins = <&pctl_gpio_g>; + #gpio-cells = <2>; + abilis,ngpio = <3>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiog"; }; gpioh: gpio@FF147000 { compatible = "abilis,tb10x-gpio"; @@ -256,9 +263,10 @@ interrupts = <27 2>; reg = <0xFF147000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <18>; - gpio-pins = <&pctl_gpio_h>; + #gpio-cells = <2>; + abilis,ngpio = <2>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioh"; }; gpioi: gpio@FF148000 { compatible = "abilis,tb10x-gpio"; @@ -268,9 +276,10 @@ interrupts = <27 2>; reg = <0xFF148000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <20>; - gpio-pins = <&pctl_gpio_i>; + #gpio-cells = <2>; + abilis,ngpio = <12>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioi"; }; gpioj: gpio@FF149000 { compatible = "abilis,tb10x-gpio"; @@ -280,9 +289,10 @@ interrupts = <27 2>; reg = <0xFF149000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <32>; - gpio-pins = <&pctl_gpio_j>; + #gpio-cells = <2>; + abilis,ngpio = <32>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioj"; }; gpiok: gpio@FF14a000 { compatible = "abilis,tb10x-gpio"; @@ -292,9 +302,10 @@ interrupts = <27 2>; reg = <0xFF14A000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <64>; - gpio-pins = <&pctl_gpio_k>; + #gpio-cells = <2>; + abilis,ngpio = <22>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiok"; }; gpiol: gpio@FF14b000 { compatible = "abilis,tb10x-gpio"; @@ -304,9 +315,10 @@ interrupts = <27 2>; reg = <0xFF14B000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <86>; - gpio-pins = <&pctl_gpio_l>; + #gpio-cells = <2>; + abilis,ngpio = <4>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiol"; }; gpiom: gpio@FF14c000 { compatible = "abilis,tb10x-gpio"; @@ -316,9 +328,10 @@ interrupts = <27 2>; reg = <0xFF14C000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <90>; - gpio-pins = <&pctl_gpio_m>; + #gpio-cells = <2>; + abilis,ngpio = <4>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiom"; }; gpion: gpio@FF14d000 { compatible = "abilis,tb10x-gpio"; @@ -328,9 +341,10 @@ interrupts = <27 2>; reg = <0xFF14D000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <94>; - gpio-pins = <&pctl_gpio_n>; + #gpio-cells = <2>; + abilis,ngpio = <5>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpion"; }; }; }; diff --git a/arch/arc/boot/dts/abilis_tb100_dvk.dts b/arch/arc/boot/dts/abilis_tb100_dvk.dts index ebc313a9f5b2..3dd6ed941464 100644 --- a/arch/arc/boot/dts/abilis_tb100_dvk.dts +++ b/arch/arc/boot/dts/abilis_tb100_dvk.dts @@ -64,62 +64,62 @@ compatible = "gpio-leds"; power { label = "Power"; - gpios = <&gpioi 0>; + gpios = <&gpioi 0 0>; linux,default-trigger = "default-on"; }; heartbeat { label = "Heartbeat"; - gpios = <&gpioi 1>; + gpios = <&gpioi 1 0>; linux,default-trigger = "heartbeat"; }; led2 { label = "LED2"; - gpios = <&gpioi 2>; + gpios = <&gpioi 2 0>; default-state = "off"; }; led3 { label = "LED3"; - gpios = <&gpioi 3>; + gpios = <&gpioi 3 0>; default-state = "off"; }; led4 { label = "LED4"; - gpios = <&gpioi 4>; + gpios = <&gpioi 4 0>; default-state = "off"; }; led5 { label = "LED5"; - gpios = <&gpioi 5>; + gpios = <&gpioi 5 0>; default-state = "off"; }; led6 { label = "LED6"; - gpios = <&gpioi 6>; + gpios = <&gpioi 6 0>; default-state = "off"; }; led7 { label = "LED7"; - gpios = <&gpioi 7>; + gpios = <&gpioi 7 0>; default-state = "off"; }; led8 { label = "LED8"; - gpios = <&gpioi 8>; + gpios = <&gpioi 8 0>; default-state = "off"; }; led9 { label = "LED9"; - gpios = <&gpioi 9>; + gpios = <&gpioi 9 0>; default-state = "off"; }; led10 { label = "LED10"; - gpios = <&gpioi 10>; + gpios = <&gpioi 10 0>; default-state = "off"; }; led11 { label = "LED11"; - gpios = <&gpioi 11>; + gpios = <&gpioi 11 0>; default-state = "off"; }; }; diff --git a/arch/arc/boot/dts/abilis_tb101.dtsi b/arch/arc/boot/dts/abilis_tb101.dtsi index da8ca7941e67..b0467229a5c4 100644 --- a/arch/arc/boot/dts/abilis_tb101.dtsi +++ b/arch/arc/boot/dts/abilis_tb101.dtsi @@ -43,133 +43,133 @@ iomux: iomux@FF10601c { /* Port 1 */ pctl_tsin_s0: pctl-tsin-s0 { /* Serial TS-in 0 */ - pingrp = "mis0_pins"; + abilis,function = "mis0"; }; pctl_tsin_s1: pctl-tsin-s1 { /* Serial TS-in 1 */ - pingrp = "mis1_pins"; + abilis,function = "mis1"; }; pctl_gpio_a: pctl-gpio-a { /* GPIO bank A */ - pingrp = "gpioa_pins"; + abilis,function = "gpioa"; }; pctl_tsin_p1: pctl-tsin-p1 { /* Parallel TS-in 1 */ - pingrp = "mip1_pins"; + abilis,function = "mip1"; }; /* Port 2 */ pctl_tsin_s2: pctl-tsin-s2 { /* Serial TS-in 2 */ - pingrp = "mis2_pins"; + abilis,function = "mis2"; }; pctl_tsin_s3: pctl-tsin-s3 { /* Serial TS-in 3 */ - pingrp = "mis3_pins"; + abilis,function = "mis3"; }; pctl_gpio_c: pctl-gpio-c { /* GPIO bank C */ - pingrp = "gpioc_pins"; + abilis,function = "gpioc"; }; pctl_tsin_p3: pctl-tsin-p3 { /* Parallel TS-in 3 */ - pingrp = "mip3_pins"; + abilis,function = "mip3"; }; /* Port 3 */ pctl_tsin_s4: pctl-tsin-s4 { /* Serial TS-in 4 */ - pingrp = "mis4_pins"; + abilis,function = "mis4"; }; pctl_tsin_s5: pctl-tsin-s5 { /* Serial TS-in 5 */ - pingrp = "mis5_pins"; + abilis,function = "mis5"; }; pctl_gpio_e: pctl-gpio-e { /* GPIO bank E */ - pingrp = "gpioe_pins"; + abilis,function = "gpioe"; }; pctl_tsin_p5: pctl-tsin-p5 { /* Parallel TS-in 5 */ - pingrp = "mip5_pins"; + abilis,function = "mip5"; }; /* Port 4 */ pctl_tsin_s6: pctl-tsin-s6 { /* Serial TS-in 6 */ - pingrp = "mis6_pins"; + abilis,function = "mis6"; }; pctl_tsin_s7: pctl-tsin-s7 { /* Serial TS-in 7 */ - pingrp = "mis7_pins"; + abilis,function = "mis7"; }; pctl_gpio_g: pctl-gpio-g { /* GPIO bank G */ - pingrp = "gpiog_pins"; + abilis,function = "gpiog"; }; pctl_tsin_p7: pctl-tsin-p7 { /* Parallel TS-in 7 */ - pingrp = "mip7_pins"; + abilis,function = "mip7"; }; /* Port 5 */ pctl_gpio_j: pctl-gpio-j { /* GPIO bank J */ - pingrp = "gpioj_pins"; + abilis,function = "gpioj"; }; pctl_gpio_k: pctl-gpio-k { /* GPIO bank K */ - pingrp = "gpiok_pins"; + abilis,function = "gpiok"; }; pctl_ciplus: pctl-ciplus { /* CI+ interface */ - pingrp = "ciplus_pins"; + abilis,function = "ciplus"; }; pctl_mcard: pctl-mcard { /* M-Card interface */ - pingrp = "mcard_pins"; + abilis,function = "mcard"; }; pctl_stc0: pctl-stc0 { /* Smart card I/F 0 */ - pingrp = "stc0_pins"; + abilis,function = "stc0"; }; pctl_stc1: pctl-stc1 { /* Smart card I/F 1 */ - pingrp = "stc1_pins"; + abilis,function = "stc1"; }; /* Port 6 */ pctl_tsout_p: pctl-tsout-p { /* Parallel TS-out */ - pingrp = "mop_pins"; + abilis,function = "mop"; }; pctl_tsout_s0: pctl-tsout-s0 { /* Serial TS-out 0 */ - pingrp = "mos0_pins"; + abilis,function = "mos0"; }; pctl_tsout_s1: pctl-tsout-s1 { /* Serial TS-out 1 */ - pingrp = "mos1_pins"; + abilis,function = "mos1"; }; pctl_tsout_s2: pctl-tsout-s2 { /* Serial TS-out 2 */ - pingrp = "mos2_pins"; + abilis,function = "mos2"; }; pctl_tsout_s3: pctl-tsout-s3 { /* Serial TS-out 3 */ - pingrp = "mos3_pins"; + abilis,function = "mos3"; }; /* Port 7 */ pctl_uart0: pctl-uart0 { /* UART 0 */ - pingrp = "uart0_pins"; + abilis,function = "uart0"; }; pctl_uart1: pctl-uart1 { /* UART 1 */ - pingrp = "uart1_pins"; + abilis,function = "uart1"; }; pctl_gpio_l: pctl-gpio-l { /* GPIO bank L */ - pingrp = "gpiol_pins"; + abilis,function = "gpiol"; }; pctl_gpio_m: pctl-gpio-m { /* GPIO bank M */ - pingrp = "gpiom_pins"; + abilis,function = "gpiom"; }; /* Port 8 */ pctl_spi3: pctl-spi3 { - pingrp = "spi3_pins"; + abilis,function = "spi3"; }; pctl_jtag: pctl-jtag { - pingrp = "jtag_pins"; + abilis,function = "jtag"; }; /* Port 9 */ pctl_spi1: pctl-spi1 { - pingrp = "spi1_pins"; + abilis,function = "spi1"; }; pctl_gpio_n: pctl-gpio-n { - pingrp = "gpion_pins"; + abilis,function = "gpion"; }; /* Unmuxed GPIOs */ pctl_gpio_b: pctl-gpio-b { - pingrp = "gpiob_pins"; + abilis,function = "gpiob"; }; pctl_gpio_d: pctl-gpio-d { - pingrp = "gpiod_pins"; + abilis,function = "gpiod"; }; pctl_gpio_f: pctl-gpio-f { - pingrp = "gpiof_pins"; + abilis,function = "gpiof"; }; pctl_gpio_h: pctl-gpio-h { - pingrp = "gpioh_pins"; + abilis,function = "gpioh"; }; pctl_gpio_i: pctl-gpio-i { - pingrp = "gpioi_pins"; + abilis,function = "gpioi"; }; }; @@ -181,9 +181,10 @@ interrupts = <27 2>; reg = <0xFF140000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <0>; - gpio-pins = <&pctl_gpio_a>; + #gpio-cells = <2>; + abilis,ngpio = <3>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioa"; }; gpiob: gpio@FF141000 { compatible = "abilis,tb10x-gpio"; @@ -193,9 +194,10 @@ interrupts = <27 2>; reg = <0xFF141000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <3>; - gpio-pins = <&pctl_gpio_b>; + #gpio-cells = <2>; + abilis,ngpio = <2>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiob"; }; gpioc: gpio@FF142000 { compatible = "abilis,tb10x-gpio"; @@ -205,9 +207,10 @@ interrupts = <27 2>; reg = <0xFF142000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <5>; - gpio-pins = <&pctl_gpio_c>; + #gpio-cells = <2>; + abilis,ngpio = <3>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioc"; }; gpiod: gpio@FF143000 { compatible = "abilis,tb10x-gpio"; @@ -217,9 +220,10 @@ interrupts = <27 2>; reg = <0xFF143000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <8>; - gpio-pins = <&pctl_gpio_d>; + #gpio-cells = <2>; + abilis,ngpio = <2>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiod"; }; gpioe: gpio@FF144000 { compatible = "abilis,tb10x-gpio"; @@ -229,9 +233,10 @@ interrupts = <27 2>; reg = <0xFF144000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <10>; - gpio-pins = <&pctl_gpio_e>; + #gpio-cells = <2>; + abilis,ngpio = <3>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioe"; }; gpiof: gpio@FF145000 { compatible = "abilis,tb10x-gpio"; @@ -241,9 +246,10 @@ interrupts = <27 2>; reg = <0xFF145000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <13>; - gpio-pins = <&pctl_gpio_f>; + #gpio-cells = <2>; + abilis,ngpio = <2>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiof"; }; gpiog: gpio@FF146000 { compatible = "abilis,tb10x-gpio"; @@ -253,9 +259,10 @@ interrupts = <27 2>; reg = <0xFF146000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <15>; - gpio-pins = <&pctl_gpio_g>; + #gpio-cells = <2>; + abilis,ngpio = <3>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiog"; }; gpioh: gpio@FF147000 { compatible = "abilis,tb10x-gpio"; @@ -265,9 +272,10 @@ interrupts = <27 2>; reg = <0xFF147000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <18>; - gpio-pins = <&pctl_gpio_h>; + #gpio-cells = <2>; + abilis,ngpio = <2>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioh"; }; gpioi: gpio@FF148000 { compatible = "abilis,tb10x-gpio"; @@ -277,9 +285,10 @@ interrupts = <27 2>; reg = <0xFF148000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <20>; - gpio-pins = <&pctl_gpio_i>; + #gpio-cells = <2>; + abilis,ngpio = <12>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioi"; }; gpioj: gpio@FF149000 { compatible = "abilis,tb10x-gpio"; @@ -289,9 +298,10 @@ interrupts = <27 2>; reg = <0xFF149000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <32>; - gpio-pins = <&pctl_gpio_j>; + #gpio-cells = <2>; + abilis,ngpio = <32>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpioj"; }; gpiok: gpio@FF14a000 { compatible = "abilis,tb10x-gpio"; @@ -301,9 +311,10 @@ interrupts = <27 2>; reg = <0xFF14A000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <64>; - gpio-pins = <&pctl_gpio_k>; + #gpio-cells = <2>; + abilis,ngpio = <22>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiok"; }; gpiol: gpio@FF14b000 { compatible = "abilis,tb10x-gpio"; @@ -313,9 +324,10 @@ interrupts = <27 2>; reg = <0xFF14B000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <86>; - gpio-pins = <&pctl_gpio_l>; + #gpio-cells = <2>; + abilis,ngpio = <4>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiol"; }; gpiom: gpio@FF14c000 { compatible = "abilis,tb10x-gpio"; @@ -325,9 +337,10 @@ interrupts = <27 2>; reg = <0xFF14C000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <90>; - gpio-pins = <&pctl_gpio_m>; + #gpio-cells = <2>; + abilis,ngpio = <4>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpiom"; }; gpion: gpio@FF14d000 { compatible = "abilis,tb10x-gpio"; @@ -337,9 +350,10 @@ interrupts = <27 2>; reg = <0xFF14D000 0x1000>; gpio-controller; - #gpio-cells = <1>; - gpio-base = <94>; - gpio-pins = <&pctl_gpio_n>; + #gpio-cells = <2>; + abilis,ngpio = <5>; + gpio-ranges = <&iomux 0 0 0>; + gpio-ranges-group-names = "gpion"; }; }; }; diff --git a/arch/arc/boot/dts/abilis_tb101_dvk.dts b/arch/arc/boot/dts/abilis_tb101_dvk.dts index b204657993aa..1cf51c280f28 100644 --- a/arch/arc/boot/dts/abilis_tb101_dvk.dts +++ b/arch/arc/boot/dts/abilis_tb101_dvk.dts @@ -64,62 +64,62 @@ compatible = "gpio-leds"; power { label = "Power"; - gpios = <&gpioi 0>; + gpios = <&gpioi 0 0>; linux,default-trigger = "default-on"; }; heartbeat { label = "Heartbeat"; - gpios = <&gpioi 1>; + gpios = <&gpioi 1 0>; linux,default-trigger = "heartbeat"; }; led2 { label = "LED2"; - gpios = <&gpioi 2>; + gpios = <&gpioi 2 0>; default-state = "off"; }; led3 { label = "LED3"; - gpios = <&gpioi 3>; + gpios = <&gpioi 3 0>; default-state = "off"; }; led4 { label = "LED4"; - gpios = <&gpioi 4>; + gpios = <&gpioi 4 0>; default-state = "off"; }; led5 { label = "LED5"; - gpios = <&gpioi 5>; + gpios = <&gpioi 5 0>; default-state = "off"; }; led6 { label = "LED6"; - gpios = <&gpioi 6>; + gpios = <&gpioi 6 0>; default-state = "off"; }; led7 { label = "LED7"; - gpios = <&gpioi 7>; + gpios = <&gpioi 7 0>; default-state = "off"; }; led8 { label = "LED8"; - gpios = <&gpioi 8>; + gpios = <&gpioi 8 0>; default-state = "off"; }; led9 { label = "LED9"; - gpios = <&gpioi 9>; + gpios = <&gpioi 9 0>; default-state = "off"; }; led10 { label = "LED10"; - gpios = <&gpioi 10>; + gpios = <&gpioi 10 0>; default-state = "off"; }; led11 { label = "LED11"; - gpios = <&gpioi 11>; + gpios = <&gpioi 11 0>; default-state = "off"; }; }; diff --git a/arch/arc/boot/dts/abilis_tb10x.dtsi b/arch/arc/boot/dts/abilis_tb10x.dtsi index edf56f4749e1..a098d7c05e96 100644 --- a/arch/arc/boot/dts/abilis_tb10x.dtsi +++ b/arch/arc/boot/dts/abilis_tb10x.dtsi @@ -62,9 +62,8 @@ }; iomux: iomux@FF10601c { - #address-cells = <1>; - #size-cells = <1>; compatible = "abilis,tb10x-iomux"; + #gpio-range-cells = <3>; reg = <0xFF10601c 0x4>; }; diff --git a/arch/arc/configs/fpga_defconfig b/arch/arc/configs/fpga_defconfig index 4ca50f1f8d05..e283aa586934 100644 --- a/arch/arc/configs/fpga_defconfig +++ b/arch/arc/configs/fpga_defconfig @@ -2,6 +2,8 @@ CONFIG_CROSS_COMPILE="arc-linux-uclibc-" # CONFIG_LOCALVERSION_AUTO is not set CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set +CONFIG_SYSVIPC=y +CONFIG_POSIX_MQUEUE=y CONFIG_HIGH_RES_TIMERS=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y @@ -62,4 +64,5 @@ CONFIG_TMPFS=y CONFIG_NFS_FS=y # CONFIG_ENABLE_WARN_DEPRECATED is not set # CONFIG_ENABLE_MUST_CHECK is not set +# CONFIG_DEBUG_PREEMPT is not set CONFIG_XZ_DEC=y diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h index e4abdaac6f9f..2fd3162ec4df 100644 --- a/arch/arc/include/asm/cache.h +++ b/arch/arc/include/asm/cache.h @@ -17,13 +17,7 @@ #endif #define L1_CACHE_BYTES (1 << L1_CACHE_SHIFT) - -/* For a rare case where customers have differently config I/D */ -#define ARC_ICACHE_LINE_LEN L1_CACHE_BYTES -#define ARC_DCACHE_LINE_LEN L1_CACHE_BYTES - -#define ICACHE_LINE_MASK (~(ARC_ICACHE_LINE_LEN - 1)) -#define DCACHE_LINE_MASK (~(ARC_DCACHE_LINE_LEN - 1)) +#define CACHE_LINE_MASK (~(L1_CACHE_BYTES - 1)) /* * ARC700 doesn't cache any access in top 256M. diff --git a/arch/arc/include/asm/irq.h b/arch/arc/include/asm/irq.h index c0a72105ee0b..291a70db68b8 100644 --- a/arch/arc/include/asm/irq.h +++ b/arch/arc/include/asm/irq.h @@ -18,8 +18,8 @@ #include <asm-generic/irq.h> -extern void __init arc_init_IRQ(void); -extern int __init get_hw_config_num_irq(void); +extern void arc_init_IRQ(void); +extern int get_hw_config_num_irq(void); void arc_local_timer_setup(unsigned int cpu); diff --git a/arch/arc/include/asm/irqflags.h b/arch/arc/include/asm/irqflags.h index b68b53f458d1..cb7efc29f16f 100644 --- a/arch/arc/include/asm/irqflags.h +++ b/arch/arc/include/asm/irqflags.h @@ -151,16 +151,38 @@ static inline void arch_unmask_irq(unsigned int irq) #else +#ifdef CONFIG_TRACE_IRQFLAGS + +.macro TRACE_ASM_IRQ_DISABLE + bl trace_hardirqs_off +.endm + +.macro TRACE_ASM_IRQ_ENABLE + bl trace_hardirqs_on +.endm + +#else + +.macro TRACE_ASM_IRQ_DISABLE +.endm + +.macro TRACE_ASM_IRQ_ENABLE +.endm + +#endif + .macro IRQ_DISABLE scratch lr \scratch, [status32] bic \scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK) flag \scratch + TRACE_ASM_IRQ_DISABLE .endm .macro IRQ_ENABLE scratch lr \scratch, [status32] or \scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK) flag \scratch + TRACE_ASM_IRQ_ENABLE .endm #endif /* __ASSEMBLY__ */ diff --git a/arch/arc/include/asm/mmu.h b/arch/arc/include/asm/mmu.h index c2663b32866b..8c84ae98c337 100644 --- a/arch/arc/include/asm/mmu.h +++ b/arch/arc/include/asm/mmu.h @@ -48,7 +48,7 @@ #ifndef __ASSEMBLY__ typedef struct { - unsigned long asid; /* 8 bit MMU PID + Generation cycle */ + unsigned long asid[NR_CPUS]; /* 8 bit MMU PID + Generation cycle */ } mm_context_t; #ifdef CONFIG_ARC_DBG_TLB_PARANOIA diff --git a/arch/arc/include/asm/mmu_context.h b/arch/arc/include/asm/mmu_context.h index 43a1b51bb8cc..1fd467ef658f 100644 --- a/arch/arc/include/asm/mmu_context.h +++ b/arch/arc/include/asm/mmu_context.h @@ -30,13 +30,13 @@ * "Fast Context Switch" i.e. no TLB flush on ctxt-switch * * Linux assigns each task a unique ASID. A simple round-robin allocation - * of H/w ASID is done using software tracker @asid_cache. + * of H/w ASID is done using software tracker @asid_cpu. * When it reaches max 255, the allocation cycle starts afresh by flushing * the entire TLB and wrapping ASID back to zero. * * A new allocation cycle, post rollover, could potentially reassign an ASID * to a different task. Thus the rule is to refresh the ASID in a new cycle. - * The 32 bit @asid_cache (and mm->asid) have 8 bits MMU PID and rest 24 bits + * The 32 bit @asid_cpu (and mm->asid) have 8 bits MMU PID and rest 24 bits * serve as cycle/generation indicator and natural 32 bit unsigned math * automagically increments the generation when lower 8 bits rollover. */ @@ -47,9 +47,11 @@ #define MM_CTXT_FIRST_CYCLE (MM_CTXT_ASID_MASK + 1) #define MM_CTXT_NO_ASID 0UL -#define hw_pid(mm) (mm->context.asid & MM_CTXT_ASID_MASK) +#define asid_mm(mm, cpu) mm->context.asid[cpu] +#define hw_pid(mm, cpu) (asid_mm(mm, cpu) & MM_CTXT_ASID_MASK) -extern unsigned int asid_cache; +DECLARE_PER_CPU(unsigned int, asid_cache); +#define asid_cpu(cpu) per_cpu(asid_cache, cpu) /* * Get a new ASID if task doesn't have a valid one (unalloc or from prev cycle) @@ -57,6 +59,7 @@ extern unsigned int asid_cache; */ static inline void get_new_mmu_context(struct mm_struct *mm) { + const unsigned int cpu = smp_processor_id(); unsigned long flags; local_irq_save(flags); @@ -71,28 +74,28 @@ static inline void get_new_mmu_context(struct mm_struct *mm) * first need to destroy the context, setting it to invalid * value. */ - if (!((mm->context.asid ^ asid_cache) & MM_CTXT_CYCLE_MASK)) + if (!((asid_mm(mm, cpu) ^ asid_cpu(cpu)) & MM_CTXT_CYCLE_MASK)) goto set_hw; /* move to new ASID and handle rollover */ - if (unlikely(!(++asid_cache & MM_CTXT_ASID_MASK))) { + if (unlikely(!(++asid_cpu(cpu) & MM_CTXT_ASID_MASK))) { - flush_tlb_all(); + local_flush_tlb_all(); /* * Above checke for rollover of 8 bit ASID in 32 bit container. * If the container itself wrapped around, set it to a non zero * "generation" to distinguish from no context */ - if (!asid_cache) - asid_cache = MM_CTXT_FIRST_CYCLE; + if (!asid_cpu(cpu)) + asid_cpu(cpu) = MM_CTXT_FIRST_CYCLE; } /* Assign new ASID to tsk */ - mm->context.asid = asid_cache; + asid_mm(mm, cpu) = asid_cpu(cpu); set_hw: - write_aux_reg(ARC_REG_PID, hw_pid(mm) | MMU_ENABLE); + write_aux_reg(ARC_REG_PID, hw_pid(mm, cpu) | MMU_ENABLE); local_irq_restore(flags); } @@ -104,16 +107,45 @@ set_hw: static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { - mm->context.asid = MM_CTXT_NO_ASID; + int i; + + for_each_possible_cpu(i) + asid_mm(mm, i) = MM_CTXT_NO_ASID; + return 0; } +static inline void destroy_context(struct mm_struct *mm) +{ + unsigned long flags; + + /* Needed to elide CONFIG_DEBUG_PREEMPT warning */ + local_irq_save(flags); + asid_mm(mm, smp_processor_id()) = MM_CTXT_NO_ASID; + local_irq_restore(flags); +} + /* Prepare the MMU for task: setup PID reg with allocated ASID If task doesn't have an ASID (never alloc or stolen, get a new ASID) */ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) { + const int cpu = smp_processor_id(); + + /* + * Note that the mm_cpumask is "aggregating" only, we don't clear it + * for the switched-out task, unlike some other arches. + * It is used to enlist cpus for sending TLB flush IPIs and not sending + * it to CPUs where a task once ran-on, could cause stale TLB entry + * re-use, specially for a multi-threaded task. + * e.g. T1 runs on C1, migrates to C3. T2 running on C2 munmaps. + * For a non-aggregating mm_cpumask, IPI not sent C1, and if T1 + * were to re-migrate to C1, it could access the unmapped region + * via any existing stale TLB entries. + */ + cpumask_set_cpu(cpu, mm_cpumask(next)); + #ifndef CONFIG_SMP /* PGD cached in MMU reg to avoid 3 mem lookups: task->mm->pgd */ write_aux_reg(ARC_REG_SCRATCH_DATA0, next->pgd); @@ -131,11 +163,6 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, */ #define activate_mm(prev, next) switch_mm(prev, next, NULL) -static inline void destroy_context(struct mm_struct *mm) -{ - mm->context.asid = MM_CTXT_NO_ASID; -} - /* it seemed that deactivate_mm( ) is a reasonable place to do book-keeping * for retiring-mm. However destroy_context( ) still needs to do that because * between mm_release( ) = >deactive_mm( ) and diff --git a/arch/arc/include/asm/setup.h b/arch/arc/include/asm/setup.h index 229e50681497..e10f8cef56a8 100644 --- a/arch/arc/include/asm/setup.h +++ b/arch/arc/include/asm/setup.h @@ -31,7 +31,7 @@ struct cpuinfo_data { extern int root_mountflags, end_mem; extern int running_on_hw; -void __init setup_processor(void); +void setup_processor(void); void __init setup_arch_memory(void); #endif /* __ASMARC_SETUP_H */ diff --git a/arch/arc/include/asm/smp.h b/arch/arc/include/asm/smp.h index c4fb211dcd25..eefc29f08cdb 100644 --- a/arch/arc/include/asm/smp.h +++ b/arch/arc/include/asm/smp.h @@ -30,7 +30,7 @@ extern void arch_send_call_function_ipi_mask(const struct cpumask *mask); * APIs provided by arch SMP code to rest of arch code */ extern void __init smp_init_cpus(void); -extern void __init first_lines_of_secondary(void); +extern void first_lines_of_secondary(void); extern const char *arc_platform_smp_cpuinfo(void); /* diff --git a/arch/arc/include/asm/tlbflush.h b/arch/arc/include/asm/tlbflush.h index b2f9bc7f68c8..71c7b2e4b874 100644 --- a/arch/arc/include/asm/tlbflush.h +++ b/arch/arc/include/asm/tlbflush.h @@ -18,11 +18,18 @@ void local_flush_tlb_kernel_range(unsigned long start, unsigned long end); void local_flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); -/* XXX: Revisit for SMP */ +#ifndef CONFIG_SMP #define flush_tlb_range(vma, s, e) local_flush_tlb_range(vma, s, e) #define flush_tlb_page(vma, page) local_flush_tlb_page(vma, page) #define flush_tlb_kernel_range(s, e) local_flush_tlb_kernel_range(s, e) #define flush_tlb_all() local_flush_tlb_all() #define flush_tlb_mm(mm) local_flush_tlb_mm(mm) - +#else +extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end); +extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long page); +extern void flush_tlb_kernel_range(unsigned long start, unsigned long end); +extern void flush_tlb_all(void); +extern void flush_tlb_mm(struct mm_struct *mm); +#endif /* CONFIG_SMP */ #endif diff --git a/arch/arc/include/asm/unaligned.h b/arch/arc/include/asm/unaligned.h index 60702f3751d2..3e5f071bc00c 100644 --- a/arch/arc/include/asm/unaligned.h +++ b/arch/arc/include/asm/unaligned.h @@ -22,7 +22,8 @@ static inline int misaligned_fixup(unsigned long address, struct pt_regs *regs, struct callee_regs *cregs) { - return 0; + /* Not fixed */ + return 1; } #endif diff --git a/arch/arc/kernel/ctx_sw.c b/arch/arc/kernel/ctx_sw.c index 34410eb1a308..c14a5bea0c76 100644 --- a/arch/arc/kernel/ctx_sw.c +++ b/arch/arc/kernel/ctx_sw.c @@ -17,6 +17,8 @@ #include <asm/asm-offsets.h> #include <linux/sched.h> +#define KSP_WORD_OFF ((TASK_THREAD + THREAD_KSP) / 4) + struct task_struct *__sched __switch_to(struct task_struct *prev_task, struct task_struct *next_task) { @@ -45,7 +47,16 @@ __switch_to(struct task_struct *prev_task, struct task_struct *next_task) #endif /* set ksp of outgoing task in tsk->thread.ksp */ +#if KSP_WORD_OFF <= 255 "st.as sp, [%3, %1] \n\t" +#else + /* + * Workaround for NR_CPUS=4k + * %1 is bigger than 255 (S9 offset for st.as) + */ + "add2 r24, %3, %1 \n\t" + "st sp, [r24] \n\t" +#endif "sync \n\t" @@ -97,7 +108,7 @@ __switch_to(struct task_struct *prev_task, struct task_struct *next_task) /* FP/BLINK restore generated by gcc (standard func epilogue */ : "=r"(tmp) - : "n"((TASK_THREAD + THREAD_KSP) / 4), "r"(next), "r"(prev) + : "n"(KSP_WORD_OFF), "r"(next), "r"(prev) : "blink" ); diff --git a/arch/arc/kernel/ctx_sw_asm.S b/arch/arc/kernel/ctx_sw_asm.S index d8972345e4c2..65690e7fcc8c 100644 --- a/arch/arc/kernel/ctx_sw_asm.S +++ b/arch/arc/kernel/ctx_sw_asm.S @@ -14,6 +14,8 @@ #include <asm/asm-offsets.h> #include <asm/linkage.h> +#define KSP_WORD_OFF ((TASK_THREAD + THREAD_KSP) / 4) + ;################### Low Level Context Switch ########################## .section .sched.text,"ax",@progbits @@ -28,8 +30,13 @@ __switch_to: SAVE_CALLEE_SAVED_KERNEL /* Save the now KSP in task->thread.ksp */ - st.as sp, [r0, (TASK_THREAD + THREAD_KSP)/4] - +#if KSP_WORD_OFF <= 255 + st.as sp, [r0, KSP_WORD_OFF] +#else + /* Workaround for NR_CPUS=4k as ST.as can only take s9 offset */ + add2 r24, r0, KSP_WORD_OFF + st sp, [r24] +#endif /* * Return last task in r0 (return reg) * On ARC, Return reg = First Arg reg = r0. diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S index b908dde8a331..47d09d07f093 100644 --- a/arch/arc/kernel/entry.S +++ b/arch/arc/kernel/entry.S @@ -250,6 +250,14 @@ ARC_ENTRY handle_interrupt_level1 lr r0, [icause1] and r0, r0, 0x1f +#ifdef CONFIG_TRACE_IRQFLAGS + ; icause1 needs to be read early, before calling tracing, which + ; can clobber scratch regs, hence use of stack to stash it + push r0 + TRACE_ASM_IRQ_DISABLE + pop r0 +#endif + bl.d @arch_do_IRQ mov r1, sp @@ -337,9 +345,9 @@ ARC_ENTRY EV_TLBProtV ; vineetg: Mar 6th: Random Seg Fault issue #1 ; ecr and efa were not saved in case an Intr sneaks in ; after fake rtie - ; + lr r2, [ecr] - lr r1, [efa] ; Faulting Data address + lr r0, [efa] ; Faulting Data address ; --------(4) Return from CPU Exception Mode --------- ; Fake a rtie, but rtie to next label @@ -348,6 +356,8 @@ ARC_ENTRY EV_TLBProtV FAKE_RET_FROM_EXCPN r9 + mov r1, sp + ;------ (5) Type of Protection Violation? ---------- ; ; ProtV Hardware Exception is triggered for Access Faults of 2 types @@ -358,16 +368,12 @@ ARC_ENTRY EV_TLBProtV bbit1 r2, ECR_C_BIT_PROTV_MISALIG_DATA, 4f ;========= (6a) Access Violation Processing ======== - mov r0, sp ; pt_regs bl do_page_fault b ret_from_exception ;========== (6b) Non aligned access ============ 4: - mov r0, r1 - mov r1, sp ; pt_regs -#ifdef CONFIG_ARC_MISALIGN_ACCESS SAVE_CALLEE_SAVED_USER mov r2, sp ; callee_regs @@ -376,9 +382,6 @@ ARC_ENTRY EV_TLBProtV ; TBD: optimize - do this only if a callee reg was involved ; either a dst of emulated LD/ST or src with address-writeback RESTORE_CALLEE_SAVED_USER -#else - bl do_misaligned_error -#endif b ret_from_exception @@ -575,6 +578,7 @@ resume_user_mode_begin: ; --- (Slow Path #2) pending signal --- mov r0, sp ; pt_regs for arg to do_signal()/do_notify_resume() + GET_CURR_THR_INFO_FLAGS r9 bbit0 r9, TIF_SIGPENDING, .Lchk_notify_resume ; Normal Trap/IRQ entry only saves Scratch (caller-saved) regs @@ -640,6 +644,8 @@ resume_kernel_mode: restore_regs : + TRACE_ASM_IRQ_ENABLE + lr r10, [status32] ; Restore REG File. In case multiple Events outstanding, diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S index 0f944f024513..2c878e964a64 100644 --- a/arch/arc/kernel/head.S +++ b/arch/arc/kernel/head.S @@ -95,7 +95,7 @@ stext: ;---------------------------------------------------------------- ; First lines of code run by secondary before jumping to 'C' ;---------------------------------------------------------------- - .section .init.text, "ax",@progbits + .section .text, "ax",@progbits .type first_lines_of_secondary, @function .globl first_lines_of_secondary diff --git a/arch/arc/kernel/irq.c b/arch/arc/kernel/irq.c index 5fc92455da36..a4b141ee9a6a 100644 --- a/arch/arc/kernel/irq.c +++ b/arch/arc/kernel/irq.c @@ -39,10 +39,14 @@ void arc_init_IRQ(void) level_mask |= IS_ENABLED(CONFIG_ARC_IRQ5_LV2) << 5; level_mask |= IS_ENABLED(CONFIG_ARC_IRQ6_LV2) << 6; - if (level_mask) { + /* + * Write to register, even if no LV2 IRQs configured to reset it + * in case bootloader had mucked with it + */ + write_aux_reg(AUX_IRQ_LEV, level_mask); + + if (level_mask) pr_info("Level-2 interrupts bitset %x\n", level_mask); - write_aux_reg(AUX_IRQ_LEV, level_mask); - } } /* @@ -146,7 +150,7 @@ void arch_do_IRQ(unsigned int irq, struct pt_regs *regs) set_irq_regs(old_regs); } -int __init get_hw_config_num_irq(void) +int get_hw_config_num_irq(void) { uint32_t val = read_aux_reg(ARC_REG_VECBASE_BCR); diff --git a/arch/arc/kernel/kgdb.c b/arch/arc/kernel/kgdb.c index a7698fb14818..a2ff5c5d1450 100644 --- a/arch/arc/kernel/kgdb.c +++ b/arch/arc/kernel/kgdb.c @@ -196,6 +196,18 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long ip) instruction_pointer(regs) = ip; } +static void kgdb_call_nmi_hook(void *ignored) +{ + kgdb_nmicallback(raw_smp_processor_id(), NULL); +} + +void kgdb_roundup_cpus(unsigned long flags) +{ + local_irq_enable(); + smp_call_function(kgdb_call_nmi_hook, NULL, 0); + local_irq_disable(); +} + struct kgdb_arch arch_kgdb_ops = { /* breakpoint instruction: TRAP_S 0x3 */ #ifdef CONFIG_CPU_BIG_ENDIAN diff --git a/arch/arc/kernel/kprobes.c b/arch/arc/kernel/kprobes.c index 72f97822784a..eb1c2ee5eaf0 100644 --- a/arch/arc/kernel/kprobes.c +++ b/arch/arc/kernel/kprobes.c @@ -87,13 +87,13 @@ static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb) static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb) { - __get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp; + __this_cpu_write(current_kprobe, kcb->prev_kprobe.kp); kcb->kprobe_status = kcb->prev_kprobe.status; } static inline void __kprobes set_current_kprobe(struct kprobe *p) { - __get_cpu_var(current_kprobe) = p; + __this_cpu_write(current_kprobe, p); } static void __kprobes resume_execution(struct kprobe *p, unsigned long addr, @@ -237,7 +237,7 @@ int __kprobes arc_kprobe_handler(unsigned long addr, struct pt_regs *regs) return 1; } else if (kprobe_running()) { - p = __get_cpu_var(current_kprobe); + p = __this_cpu_read(current_kprobe); if (p->break_handler && p->break_handler(p, regs)) { setup_singlestep(p, regs); kcb->kprobe_status = KPROBE_HIT_SS; diff --git a/arch/arc/kernel/reset.c b/arch/arc/kernel/reset.c index e227a2b1c943..2768fa1e39b9 100644 --- a/arch/arc/kernel/reset.c +++ b/arch/arc/kernel/reset.c @@ -31,3 +31,4 @@ void machine_power_off(void) } void (*pm_power_off) (void) = NULL; +EXPORT_SYMBOL(pm_power_off); diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index 2c68bc7e6a78..d9e15f16633e 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -37,8 +37,7 @@ struct task_struct *_current_task[NR_CPUS]; /* For stack switching */ struct cpuinfo_arc cpuinfo_arc700[NR_CPUS]; - -void read_arc_build_cfg_regs(void) +static void read_arc_build_cfg_regs(void) { struct bcr_perip uncached_space; struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()]; @@ -106,7 +105,7 @@ static const struct cpuinfo_data arc_cpu_tbl[] = { { {0x00, NULL } } }; -char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len) +static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len) { int n = 0; struct cpuinfo_arc *cpu = &cpuinfo_arc700[cpu_id]; @@ -171,7 +170,7 @@ static const struct id_to_str mac_mul_nm[] = { {0x6, "Dual 16x16 and 32x16"} }; -char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len) +static char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len) { int n = 0; struct cpuinfo_arc *cpu = &cpuinfo_arc700[cpu_id]; @@ -234,7 +233,7 @@ char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len) return buf; } -void arc_chk_ccms(void) +static void arc_chk_ccms(void) { #if defined(CONFIG_ARC_HAS_DCCM) || defined(CONFIG_ARC_HAS_ICCM) struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()]; @@ -269,7 +268,7 @@ void arc_chk_ccms(void) * hardware has dedicated regs which need to be saved/restored on ctx-sw * (Single Precision uses core regs), thus kernel is kind of oblivious to it */ -void arc_chk_fpu(void) +static void arc_chk_fpu(void) { struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()]; diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c index bca3052c956d..c2f9ebbc38f6 100644 --- a/arch/arc/kernel/smp.c +++ b/arch/arc/kernel/smp.c @@ -95,7 +95,7 @@ void __init smp_cpus_done(unsigned int max_cpus) * If it turns out to be elaborate, it's better to code it in assembly * */ -void __attribute__((weak)) arc_platform_smp_wait_to_boot(int cpu) +void __weak arc_platform_smp_wait_to_boot(int cpu) { /* * As a hack for debugging - since debugger will single-step over the @@ -128,6 +128,7 @@ void start_kernel_secondary(void) atomic_inc(&mm->mm_users); atomic_inc(&mm->mm_count); current->active_mm = mm; + cpumask_set_cpu(cpu, mm_cpumask(mm)); notify_cpu_starting(cpu); set_cpu_online(cpu, true); @@ -210,7 +211,6 @@ enum ipi_msg_type { IPI_NOP = 0, IPI_RESCHEDULE = 1, IPI_CALL_FUNC, - IPI_CALL_FUNC_SINGLE, IPI_CPU_STOP }; @@ -254,7 +254,7 @@ void smp_send_stop(void) void arch_send_call_function_single_ipi(int cpu) { - ipi_send_msg(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE); + ipi_send_msg(cpumask_of(cpu), IPI_CALL_FUNC); } void arch_send_call_function_ipi_mask(const struct cpumask *mask) @@ -286,10 +286,6 @@ static inline void __do_IPI(unsigned long *ops, struct ipi_data *ipi, int cpu) generic_smp_call_function_interrupt(); break; - case IPI_CALL_FUNC_SINGLE: - generic_smp_call_function_single_interrupt(); - break; - case IPI_CPU_STOP: ipi_cpu_stop(cpu); break; diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c index f8b7d880304d..9ce47cfe2303 100644 --- a/arch/arc/kernel/stacktrace.c +++ b/arch/arc/kernel/stacktrace.c @@ -237,11 +237,14 @@ unsigned int get_wchan(struct task_struct *tsk) */ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) { + /* Assumes @tsk is sleeping so unwinds from __switch_to */ arc_unwind_core(tsk, NULL, __collect_all_but_sched, trace); } void save_stack_trace(struct stack_trace *trace) { - arc_unwind_core(current, NULL, __collect_all, trace); + /* Pass NULL for task so it unwinds the current call frame */ + arc_unwind_core(NULL, NULL, __collect_all, trace); } +EXPORT_SYMBOL_GPL(save_stack_trace); #endif diff --git a/arch/arc/kernel/time.c b/arch/arc/kernel/time.c index 3fde7de3ea67..0a9b6b289c4f 100644 --- a/arch/arc/kernel/time.c +++ b/arch/arc/kernel/time.c @@ -206,7 +206,7 @@ static DEFINE_PER_CPU(struct clock_event_device, arc_clockevent_device) = { static irqreturn_t timer_irq_handler(int irq, void *dev_id) { - struct clock_event_device *clk = &__get_cpu_var(arc_clockevent_device); + struct clock_event_device *clk = this_cpu_ptr(&arc_clockevent_device); arc_timer_event_ack(clk->mode == CLOCK_EVT_MODE_PERIODIC); clk->event_handler(clk); @@ -223,7 +223,7 @@ static struct irqaction arc_timer_irq = { * Setup the local event timer for @cpu * N.B. weak so that some exotic ARC SoCs can completely override it */ -void __attribute__((weak)) arc_local_timer_setup(unsigned int cpu) +void __weak arc_local_timer_setup(unsigned int cpu) { struct clock_event_device *clk = &per_cpu(arc_clockevent_device, cpu); diff --git a/arch/arc/kernel/traps.c b/arch/arc/kernel/traps.c index e21692d2fdab..3eadfdabc322 100644 --- a/arch/arc/kernel/traps.c +++ b/arch/arc/kernel/traps.c @@ -84,19 +84,18 @@ DO_ERROR_INFO(SIGBUS, "Invalid Mem Access", do_memory_error, BUS_ADRERR) DO_ERROR_INFO(SIGTRAP, "Breakpoint Set", trap_is_brkpt, TRAP_BRKPT) DO_ERROR_INFO(SIGBUS, "Misaligned Access", do_misaligned_error, BUS_ADRALN) -#ifdef CONFIG_ARC_MISALIGN_ACCESS /* * Entry Point for Misaligned Data access Exception, for emulating in software */ int do_misaligned_access(unsigned long address, struct pt_regs *regs, struct callee_regs *cregs) { + /* If emulation not enabled, or failed, kill the task */ if (misaligned_fixup(address, regs, cregs) != 0) return do_misaligned_error(address, regs); return 0; } -#endif /* * Entry point for miscll errors such as Nested Exceptions diff --git a/arch/arc/mm/cache_arc700.c b/arch/arc/mm/cache_arc700.c index 5a1259cd948c..6b58c1de7577 100644 --- a/arch/arc/mm/cache_arc700.c +++ b/arch/arc/mm/cache_arc700.c @@ -182,7 +182,7 @@ void arc_cache_init(void) #ifdef CONFIG_ARC_HAS_ICACHE /* 1. Confirm some of I-cache params which Linux assumes */ - if (ic->line_len != ARC_ICACHE_LINE_LEN) + if (ic->line_len != L1_CACHE_BYTES) panic("Cache H/W doesn't match kernel Config"); if (ic->ver != CONFIG_ARC_MMU_VER) @@ -205,7 +205,7 @@ chk_dc: return; #ifdef CONFIG_ARC_HAS_DCACHE - if (dc->line_len != ARC_DCACHE_LINE_LEN) + if (dc->line_len != L1_CACHE_BYTES) panic("Cache H/W doesn't match kernel Config"); /* check for D-Cache aliasing */ @@ -240,6 +240,67 @@ chk_dc: #define OP_INV 0x1 #define OP_FLUSH 0x2 #define OP_FLUSH_N_INV 0x3 +#define OP_INV_IC 0x4 + +/* + * Common Helper for Line Operations on {I,D}-Cache + */ +static inline void __cache_line_loop(unsigned long paddr, unsigned long vaddr, + unsigned long sz, const int cacheop) +{ + unsigned int aux_cmd, aux_tag; + int num_lines; + const int full_page_op = __builtin_constant_p(sz) && sz == PAGE_SIZE; + + if (cacheop == OP_INV_IC) { + aux_cmd = ARC_REG_IC_IVIL; + aux_tag = ARC_REG_IC_PTAG; + } + else { + /* d$ cmd: INV (discard or wback-n-discard) OR FLUSH (wback) */ + aux_cmd = cacheop & OP_INV ? ARC_REG_DC_IVDL : ARC_REG_DC_FLDL; + aux_tag = ARC_REG_DC_PTAG; + } + + /* Ensure we properly floor/ceil the non-line aligned/sized requests + * and have @paddr - aligned to cache line and integral @num_lines. + * This however can be avoided for page sized since: + * -@paddr will be cache-line aligned already (being page aligned) + * -@sz will be integral multiple of line size (being page sized). + */ + if (!full_page_op) { + sz += paddr & ~CACHE_LINE_MASK; + paddr &= CACHE_LINE_MASK; + vaddr &= CACHE_LINE_MASK; + } + + num_lines = DIV_ROUND_UP(sz, L1_CACHE_BYTES); + +#if (CONFIG_ARC_MMU_VER <= 2) + /* MMUv2 and before: paddr contains stuffed vaddrs bits */ + paddr |= (vaddr >> PAGE_SHIFT) & 0x1F; +#else + /* if V-P const for loop, PTAG can be written once outside loop */ + if (full_page_op) + write_aux_reg(ARC_REG_DC_PTAG, paddr); +#endif + + while (num_lines-- > 0) { +#if (CONFIG_ARC_MMU_VER > 2) + /* MMUv3, cache ops require paddr seperately */ + if (!full_page_op) { + write_aux_reg(aux_tag, paddr); + paddr += L1_CACHE_BYTES; + } + + write_aux_reg(aux_cmd, vaddr); + vaddr += L1_CACHE_BYTES; +#else + write_aux_reg(aux, paddr); + paddr += L1_CACHE_BYTES; +#endif + } +} #ifdef CONFIG_ARC_HAS_DCACHE @@ -289,53 +350,6 @@ static inline void __dc_entire_op(const int cacheop) write_aux_reg(ARC_REG_DC_CTRL, tmp & ~DC_CTRL_INV_MODE_FLUSH); } -/* - * Per Line Operation on D-Cache - * Doesn't deal with type-of-op/IRQ-disabling/waiting-for-flush-to-complete - * It's sole purpose is to help gcc generate ZOL - * (aliasing VIPT dcache flushing needs both vaddr and paddr) - */ -static inline void __dc_line_loop(unsigned long paddr, unsigned long vaddr, - unsigned long sz, const int aux_reg) -{ - int num_lines; - - /* Ensure we properly floor/ceil the non-line aligned/sized requests - * and have @paddr - aligned to cache line and integral @num_lines. - * This however can be avoided for page sized since: - * -@paddr will be cache-line aligned already (being page aligned) - * -@sz will be integral multiple of line size (being page sized). - */ - if (!(__builtin_constant_p(sz) && sz == PAGE_SIZE)) { - sz += paddr & ~DCACHE_LINE_MASK; - paddr &= DCACHE_LINE_MASK; - vaddr &= DCACHE_LINE_MASK; - } - - num_lines = DIV_ROUND_UP(sz, ARC_DCACHE_LINE_LEN); - -#if (CONFIG_ARC_MMU_VER <= 2) - paddr |= (vaddr >> PAGE_SHIFT) & 0x1F; -#endif - - while (num_lines-- > 0) { -#if (CONFIG_ARC_MMU_VER > 2) - /* - * Just as for I$, in MMU v3, D$ ops also require - * "tag" bits in DC_PTAG, "index" bits in FLDL,IVDL ops - */ - write_aux_reg(ARC_REG_DC_PTAG, paddr); - - write_aux_reg(aux_reg, vaddr); - vaddr += ARC_DCACHE_LINE_LEN; -#else - /* paddr contains stuffed vaddrs bits */ - write_aux_reg(aux_reg, paddr); -#endif - paddr += ARC_DCACHE_LINE_LEN; - } -} - /* For kernel mappings cache operation: index is same as paddr */ #define __dc_line_op_k(p, sz, op) __dc_line_op(p, p, sz, op) @@ -346,7 +360,6 @@ static inline void __dc_line_op(unsigned long paddr, unsigned long vaddr, unsigned long sz, const int cacheop) { unsigned long flags, tmp = tmp; - int aux; local_irq_save(flags); @@ -361,12 +374,7 @@ static inline void __dc_line_op(unsigned long paddr, unsigned long vaddr, write_aux_reg(ARC_REG_DC_CTRL, tmp | DC_CTRL_INV_MODE_FLUSH); } - if (cacheop & OP_INV) /* Inv / flush-n-inv use same cmd reg */ - aux = ARC_REG_DC_IVDL; - else - aux = ARC_REG_DC_FLDL; - - __dc_line_loop(paddr, vaddr, sz, aux); + __cache_line_loop(paddr, vaddr, sz, cacheop); if (cacheop & OP_FLUSH) /* flush / flush-n-inv both wait */ wait_for_flush(); @@ -438,42 +446,9 @@ static void __ic_line_inv_vaddr(unsigned long paddr, unsigned long vaddr, unsigned long sz) { unsigned long flags; - int num_lines; - - /* - * Ensure we properly floor/ceil the non-line aligned/sized requests: - * However page sized flushes can be compile time optimised. - * -@paddr will be cache-line aligned already (being page aligned) - * -@sz will be integral multiple of line size (being page sized). - */ - if (!(__builtin_constant_p(sz) && sz == PAGE_SIZE)) { - sz += paddr & ~ICACHE_LINE_MASK; - paddr &= ICACHE_LINE_MASK; - vaddr &= ICACHE_LINE_MASK; - } - - num_lines = DIV_ROUND_UP(sz, ARC_ICACHE_LINE_LEN); - -#if (CONFIG_ARC_MMU_VER <= 2) - /* bits 17:13 of vaddr go as bits 4:0 of paddr */ - paddr |= (vaddr >> PAGE_SHIFT) & 0x1F; -#endif local_irq_save(flags); - while (num_lines-- > 0) { -#if (CONFIG_ARC_MMU_VER > 2) - /* tag comes from phy addr */ - write_aux_reg(ARC_REG_IC_PTAG, paddr); - - /* index bits come from vaddr */ - write_aux_reg(ARC_REG_IC_IVIL, vaddr); - vaddr += ARC_ICACHE_LINE_LEN; -#else - /* paddr contains stuffed vaddrs bits */ - write_aux_reg(ARC_REG_IC_IVIL, paddr); -#endif - paddr += ARC_ICACHE_LINE_LEN; - } + __cache_line_loop(paddr, vaddr, sz, OP_INV_IC); local_irq_restore(flags); } diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c index d63f3de0cd5b..9c69552350c4 100644 --- a/arch/arc/mm/fault.c +++ b/arch/arc/mm/fault.c @@ -17,7 +17,7 @@ #include <asm/pgalloc.h> #include <asm/mmu.h> -static int handle_vmalloc_fault(struct mm_struct *mm, unsigned long address) +static int handle_vmalloc_fault(unsigned long address) { /* * Synchronize this task's top level page-table @@ -27,7 +27,7 @@ static int handle_vmalloc_fault(struct mm_struct *mm, unsigned long address) pud_t *pud, *pud_k; pmd_t *pmd, *pmd_k; - pgd = pgd_offset_fast(mm, address); + pgd = pgd_offset_fast(current->active_mm, address); pgd_k = pgd_offset_k(address); if (!pgd_present(*pgd_k)) @@ -52,7 +52,7 @@ bad_area: return 1; } -void do_page_fault(struct pt_regs *regs, unsigned long address) +void do_page_fault(unsigned long address, struct pt_regs *regs) { struct vm_area_struct *vma = NULL; struct task_struct *tsk = current; @@ -72,7 +72,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long address) * nothing more. */ if (address >= VMALLOC_START && address <= VMALLOC_END) { - ret = handle_vmalloc_fault(mm, address); + ret = handle_vmalloc_fault(address); if (unlikely(ret)) goto bad_area_nosemaphore; else diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c index 71cb26df4255..e1acf0ce5647 100644 --- a/arch/arc/mm/tlb.c +++ b/arch/arc/mm/tlb.c @@ -100,7 +100,7 @@ /* A copy of the ASID from the PID reg is kept in asid_cache */ -unsigned int asid_cache = MM_CTXT_FIRST_CYCLE; +DEFINE_PER_CPU(unsigned int, asid_cache) = MM_CTXT_FIRST_CYCLE; /* * Utility Routine to erase a J-TLB entry @@ -274,6 +274,7 @@ noinline void local_flush_tlb_mm(struct mm_struct *mm) void local_flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { + const unsigned int cpu = smp_processor_id(); unsigned long flags; /* If range @start to @end is more than 32 TLB entries deep, @@ -297,9 +298,9 @@ void local_flush_tlb_range(struct vm_area_struct *vma, unsigned long start, local_irq_save(flags); - if (vma->vm_mm->context.asid != MM_CTXT_NO_ASID) { + if (asid_mm(vma->vm_mm, cpu) != MM_CTXT_NO_ASID) { while (start < end) { - tlb_entry_erase(start | hw_pid(vma->vm_mm)); + tlb_entry_erase(start | hw_pid(vma->vm_mm, cpu)); start += PAGE_SIZE; } } @@ -346,6 +347,7 @@ void local_flush_tlb_kernel_range(unsigned long start, unsigned long end) void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long page) { + const unsigned int cpu = smp_processor_id(); unsigned long flags; /* Note that it is critical that interrupts are DISABLED between @@ -353,14 +355,87 @@ void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long page) */ local_irq_save(flags); - if (vma->vm_mm->context.asid != MM_CTXT_NO_ASID) { - tlb_entry_erase((page & PAGE_MASK) | hw_pid(vma->vm_mm)); + if (asid_mm(vma->vm_mm, cpu) != MM_CTXT_NO_ASID) { + tlb_entry_erase((page & PAGE_MASK) | hw_pid(vma->vm_mm, cpu)); utlb_invalidate(); } local_irq_restore(flags); } +#ifdef CONFIG_SMP + +struct tlb_args { + struct vm_area_struct *ta_vma; + unsigned long ta_start; + unsigned long ta_end; +}; + +static inline void ipi_flush_tlb_page(void *arg) +{ + struct tlb_args *ta = arg; + + local_flush_tlb_page(ta->ta_vma, ta->ta_start); +} + +static inline void ipi_flush_tlb_range(void *arg) +{ + struct tlb_args *ta = arg; + + local_flush_tlb_range(ta->ta_vma, ta->ta_start, ta->ta_end); +} + +static inline void ipi_flush_tlb_kernel_range(void *arg) +{ + struct tlb_args *ta = (struct tlb_args *)arg; + + local_flush_tlb_kernel_range(ta->ta_start, ta->ta_end); +} + +void flush_tlb_all(void) +{ + on_each_cpu((smp_call_func_t)local_flush_tlb_all, NULL, 1); +} + +void flush_tlb_mm(struct mm_struct *mm) +{ + on_each_cpu_mask(mm_cpumask(mm), (smp_call_func_t)local_flush_tlb_mm, + mm, 1); +} + +void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) +{ + struct tlb_args ta = { + .ta_vma = vma, + .ta_start = uaddr + }; + + on_each_cpu_mask(mm_cpumask(vma->vm_mm), ipi_flush_tlb_page, &ta, 1); +} + +void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end) +{ + struct tlb_args ta = { + .ta_vma = vma, + .ta_start = start, + .ta_end = end + }; + + on_each_cpu_mask(mm_cpumask(vma->vm_mm), ipi_flush_tlb_range, &ta, 1); +} + +void flush_tlb_kernel_range(unsigned long start, unsigned long end) +{ + struct tlb_args ta = { + .ta_start = start, + .ta_end = end + }; + + on_each_cpu(ipi_flush_tlb_kernel_range, &ta, 1); +} +#endif + /* * Routine to create a TLB entry */ @@ -400,7 +475,7 @@ void create_tlb(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) local_irq_save(flags); - tlb_paranoid_check(vma->vm_mm->context.asid, address); + tlb_paranoid_check(asid_mm(vma->vm_mm, smp_processor_id()), address); address &= PAGE_MASK; @@ -610,9 +685,9 @@ void do_tlb_overlap_fault(unsigned long cause, unsigned long address, struct pt_regs *regs) { int set, way, n; - unsigned int pd0[4], pd1[4]; /* assume max 4 ways */ unsigned long flags, is_valid; struct cpuinfo_arc_mmu *mmu = &cpuinfo_arc700[smp_processor_id()].mmu; + unsigned int pd0[mmu->ways], pd1[mmu->ways]; local_irq_save(flags); @@ -637,7 +712,7 @@ void do_tlb_overlap_fault(unsigned long cause, unsigned long address, continue; /* Scan the set for duplicate ways: needs a nested loop */ - for (way = 0; way < mmu->ways; way++) { + for (way = 0; way < mmu->ways - 1; way++) { if (!pd0[way]) continue; diff --git a/arch/arc/mm/tlbex.S b/arch/arc/mm/tlbex.S index cf7d7d9ad695..3fcfdb38d242 100644 --- a/arch/arc/mm/tlbex.S +++ b/arch/arc/mm/tlbex.S @@ -369,8 +369,8 @@ do_slow_path_pf: EXCEPTION_PROLOGUE ; ------- setup args for Linux Page fault Hanlder --------- - mov_s r0, sp - lr r1, [efa] + mov_s r1, sp + lr r0, [efa] ; We don't want exceptions to be disabled while the fault is handled. ; Now that we have saved the context we return from exception hence diff --git a/arch/arc/plat-tb10x/Kconfig b/arch/arc/plat-tb10x/Kconfig index 1ab386bb5da8..6994c188dc88 100644 --- a/arch/arc/plat-tb10x/Kconfig +++ b/arch/arc/plat-tb10x/Kconfig @@ -20,8 +20,10 @@ menuconfig ARC_PLAT_TB10X bool "Abilis TB10x" select COMMON_CLK select PINCTRL + select PINCTRL_TB10X select PINMUX select ARCH_REQUIRE_GPIOLIB + select GPIO_TB10X select TB10X_IRQC help Support for platforms based on the TB10x home media gateway SOC by diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 04163fece49f..59c8ae38cb12 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -5,6 +5,7 @@ config ARM select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_HAVE_CUSTOM_GPIO_H + select ARCH_USE_CMPXCHG_LOCKREF select ARCH_WANT_IPC_PARSE_VERSION select BUILDTIME_EXTABLE_SORT if MMU select CLONE_BACKWARDS @@ -51,6 +52,8 @@ config ARM select HAVE_MOD_ARCH_SPECIFIC if ARM_UNWIND select HAVE_OPROFILE if (HAVE_PERF_EVENTS) select HAVE_PERF_EVENTS + select HAVE_PERF_REGS + select HAVE_PERF_USER_STACK_DUMP select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_SYSCALL_TRACEPOINTS select HAVE_UID16 @@ -481,6 +484,7 @@ config ARCH_IXP4XX bool "IXP4xx-based" depends on MMU select ARCH_HAS_DMA_SET_COHERENT_MASK + select ARCH_SUPPORTS_BIG_ENDIAN select ARCH_REQUIRE_GPIOLIB select CLKSRC_MMIO select CPU_XSCALE @@ -690,7 +694,6 @@ config ARCH_SA1100 select GENERIC_CLOCKEVENTS select HAVE_IDE select ISA - select NEED_MACH_GPIO_H select NEED_MACH_MEMORY_H select SPARSE_IRQ help @@ -1066,11 +1069,6 @@ config IWMMXT Enable support for iWMMXt context switching at run time if running on a CPU that supports it. -config XSCALE_PMU - bool - depends on CPU_XSCALE - default y - config MULTI_IRQ_HANDLER bool help @@ -1518,6 +1516,32 @@ config MCPM for (multi-)cluster based systems, such as big.LITTLE based systems. +config BIG_LITTLE + bool "big.LITTLE support (Experimental)" + depends on CPU_V7 && SMP + select MCPM + help + This option enables support selections for the big.LITTLE + system architecture. + +config BL_SWITCHER + bool "big.LITTLE switcher support" + depends on BIG_LITTLE && MCPM && HOTPLUG_CPU + select CPU_PM + select ARM_CPU_SUSPEND + help + The big.LITTLE "switcher" provides the core functionality to + transparently handle transition between a cluster of A15's + and a cluster of A7's in a big.LITTLE system. + +config BL_SWITCHER_DUMMY_IF + tristate "Simple big.LITTLE switcher user interface" + depends on BL_SWITCHER && DEBUG_KERNEL + help + This is a simple and dummy char dev interface to control + the big.LITTLE switcher core code. It is meant for + debugging purposes only. + choice prompt "Memory split" default VMSPLIT_3G diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug index d597c6b8488b..5765abf5ce84 100644 --- a/arch/arm/Kconfig.debug +++ b/arch/arm/Kconfig.debug @@ -318,6 +318,7 @@ choice config DEBUG_MSM_UART1 bool "Kernel low-level debugging messages via MSM UART1" depends on ARCH_MSM7X00A || ARCH_MSM7X30 || ARCH_QSD8X50 + select DEBUG_MSM_UART help Say Y here if you want the debug print routines to direct their output to the first serial port on MSM devices. @@ -325,6 +326,7 @@ choice config DEBUG_MSM_UART2 bool "Kernel low-level debugging messages via MSM UART2" depends on ARCH_MSM7X00A || ARCH_MSM7X30 || ARCH_QSD8X50 + select DEBUG_MSM_UART help Say Y here if you want the debug print routines to direct their output to the second serial port on MSM devices. @@ -332,6 +334,7 @@ choice config DEBUG_MSM_UART3 bool "Kernel low-level debugging messages via MSM UART3" depends on ARCH_MSM7X00A || ARCH_MSM7X30 || ARCH_QSD8X50 + select DEBUG_MSM_UART help Say Y here if you want the debug print routines to direct their output to the third serial port on MSM devices. @@ -340,6 +343,7 @@ choice bool "Kernel low-level debugging messages via MSM 8660 UART" depends on ARCH_MSM8X60 select MSM_HAS_DEBUG_UART_HS + select DEBUG_MSM_UART help Say Y here if you want the debug print routines to direct their output to the serial port on MSM 8660 devices. @@ -348,10 +352,20 @@ choice bool "Kernel low-level debugging messages via MSM 8960 UART" depends on ARCH_MSM8960 select MSM_HAS_DEBUG_UART_HS + select DEBUG_MSM_UART help Say Y here if you want the debug print routines to direct their output to the serial port on MSM 8960 devices. + config DEBUG_MSM8974_UART + bool "Kernel low-level debugging messages via MSM 8974 UART" + depends on ARCH_MSM8974 + select MSM_HAS_DEBUG_UART_HS + select DEBUG_MSM_UART + help + Say Y here if you want the debug print routines to direct + their output to the serial port on MSM 8974 devices. + config DEBUG_MVEBU_UART bool "Kernel low-level debugging messages via MVEBU UART (old bootloaders)" depends on ARCH_MVEBU @@ -841,6 +855,20 @@ choice options; the platform specific options are deprecated and will be soon removed. + config DEBUG_LL_UART_EFM32 + bool "Kernel low-level debugging via efm32 UART" + depends on ARCH_EFM32 + help + Say Y here if you want the debug print routines to direct + their output to an UART or USART port on efm32 based + machines. Use the following addresses for DEBUG_UART_PHYS: + + 0x4000c000 | USART0 + 0x4000c400 | USART1 + 0x4000c800 | USART2 + 0x4000e000 | UART0 + 0x4000e400 | UART1 + config DEBUG_LL_UART_PL01X bool "Kernel low-level debugging via ARM Ltd PL01x Primecell UART" help @@ -887,11 +915,16 @@ config DEBUG_STI_UART bool depends on ARCH_STI +config DEBUG_MSM_UART + bool + depends on ARCH_MSM + config DEBUG_LL_INCLUDE string default "debug/8250.S" if DEBUG_LL_UART_8250 || DEBUG_UART_8250 default "debug/pl01x.S" if DEBUG_LL_UART_PL01X || DEBUG_UART_PL01X default "debug/exynos.S" if DEBUG_EXYNOS_UART + default "debug/efm32.S" if DEBUG_LL_UART_EFM32 default "debug/icedcc.S" if DEBUG_ICEDCC default "debug/imx.S" if DEBUG_IMX1_UART || \ DEBUG_IMX25_UART || \ @@ -902,11 +935,7 @@ config DEBUG_LL_INCLUDE DEBUG_IMX53_UART ||\ DEBUG_IMX6Q_UART || \ DEBUG_IMX6SL_UART - default "debug/msm.S" if DEBUG_MSM_UART1 || \ - DEBUG_MSM_UART2 || \ - DEBUG_MSM_UART3 || \ - DEBUG_MSM8660_UART || \ - DEBUG_MSM8960_UART + default "debug/msm.S" if DEBUG_MSM_UART default "debug/omap2plus.S" if DEBUG_OMAP2PLUS_UART default "debug/sirf.S" if DEBUG_SIRFPRIMA2_UART1 || DEBUG_SIRFMARCO_UART1 default "debug/sti.S" if DEBUG_STI_UART @@ -959,6 +988,7 @@ config DEBUG_UART_PHYS default 0x20064000 if DEBUG_RK29_UART1 || DEBUG_RK3X_UART2 default 0x20068000 if DEBUG_RK29_UART2 || DEBUG_RK3X_UART3 default 0x20201000 if DEBUG_BCM2835 + default 0x4000e400 if DEBUG_LL_UART_EFM32 default 0x40090000 if ARCH_LPC32XX default 0x40100000 if DEBUG_PXA_UART1 default 0x42000000 if ARCH_GEMINI @@ -989,6 +1019,7 @@ config DEBUG_UART_PHYS default 0xfff36000 if DEBUG_HIGHBANK_UART default 0xfffff700 if ARCH_IOP33X depends on DEBUG_LL_UART_8250 || DEBUG_LL_UART_PL01X || \ + DEBUG_LL_UART_EFM32 || \ DEBUG_UART_8250 || DEBUG_UART_PL01X config DEBUG_UART_VIRT diff --git a/arch/arm/Makefile b/arch/arm/Makefile index 8b667132d7b4..c99b1086d83d 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -16,6 +16,7 @@ LDFLAGS := LDFLAGS_vmlinux :=-p --no-undefined -X ifeq ($(CONFIG_CPU_ENDIAN_BE8),y) LDFLAGS_vmlinux += --be8 +LDFLAGS_MODULE += --be8 endif OBJCOPYFLAGS :=-O binary -R .comment -S diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index 75189f13cf54..066b03480b63 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -135,6 +135,7 @@ start: .word _edata @ zImage end address THUMB( .thumb ) 1: + ARM_BE8( setend be ) @ go BE8 if compiled for BE8 mrs r9, cpsr #ifdef CONFIG_ARM_VIRT_EXT bl __hyp_stub_install @ get into SVC mode, reversibly @@ -699,9 +700,7 @@ __armv4_mmu_cache_on: mrc p15, 0, r0, c1, c0, 0 @ read control reg orr r0, r0, #0x5000 @ I-cache enable, RR cache replacement orr r0, r0, #0x0030 -#ifdef CONFIG_CPU_ENDIAN_BE8 - orr r0, r0, #1 << 25 @ big-endian page tables -#endif + ARM_BE8( orr r0, r0, #1 << 25 ) @ big-endian page tables bl __common_mmu_cache_on mov r0, #0 mcr p15, 0, r0, c8, c7, 0 @ flush I,D TLBs @@ -728,9 +727,7 @@ __armv7_mmu_cache_on: orr r0, r0, #1 << 22 @ U (v6 unaligned access model) @ (needed for ARM1176) #ifdef CONFIG_MMU -#ifdef CONFIG_CPU_ENDIAN_BE8 - orr r0, r0, #1 << 25 @ big-endian page tables -#endif + ARM_BE8( orr r0, r0, #1 << 25 ) @ big-endian page tables mrcne p15, 0, r6, c2, c0, 2 @ read ttb control reg orrne r0, r0, #1 @ MMU enabled movne r1, #0xfffffffd @ domain 0 = client diff --git a/arch/arm/common/Makefile b/arch/arm/common/Makefile index eaa9cf4705a7..4bdc41622c36 100644 --- a/arch/arm/common/Makefile +++ b/arch/arm/common/Makefile @@ -16,3 +16,5 @@ obj-$(CONFIG_MCPM) += mcpm_head.o mcpm_entry.o mcpm_platsmp.o vlock.o AFLAGS_mcpm_head.o := -march=armv7-a AFLAGS_vlock.o := -march=armv7-a obj-$(CONFIG_TI_PRIV_EDMA) += edma.o +obj-$(CONFIG_BL_SWITCHER) += bL_switcher.o +obj-$(CONFIG_BL_SWITCHER_DUMMY_IF) += bL_switcher_dummy_if.o diff --git a/arch/arm/common/bL_switcher.c b/arch/arm/common/bL_switcher.c new file mode 100644 index 000000000000..63bbc4f70564 --- /dev/null +++ b/arch/arm/common/bL_switcher.c @@ -0,0 +1,822 @@ +/* + * arch/arm/common/bL_switcher.c -- big.LITTLE cluster switcher core driver + * + * Created by: Nicolas Pitre, March 2012 + * Copyright: (C) 2012-2013 Linaro Limited + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/atomic.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/sched.h> +#include <linux/interrupt.h> +#include <linux/cpu_pm.h> +#include <linux/cpu.h> +#include <linux/cpumask.h> +#include <linux/kthread.h> +#include <linux/wait.h> +#include <linux/time.h> +#include <linux/clockchips.h> +#include <linux/hrtimer.h> +#include <linux/tick.h> +#include <linux/notifier.h> +#include <linux/mm.h> +#include <linux/mutex.h> +#include <linux/smp.h> +#include <linux/spinlock.h> +#include <linux/string.h> +#include <linux/sysfs.h> +#include <linux/irqchip/arm-gic.h> +#include <linux/moduleparam.h> + +#include <asm/smp_plat.h> +#include <asm/cputype.h> +#include <asm/suspend.h> +#include <asm/mcpm.h> +#include <asm/bL_switcher.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/power_cpu_migrate.h> + + +/* + * Use our own MPIDR accessors as the generic ones in asm/cputype.h have + * __attribute_const__ and we don't want the compiler to assume any + * constness here as the value _does_ change along some code paths. + */ + +static int read_mpidr(void) +{ + unsigned int id; + asm volatile ("mrc p15, 0, %0, c0, c0, 5" : "=r" (id)); + return id & MPIDR_HWID_BITMASK; +} + +/* + * Get a global nanosecond time stamp for tracing. + */ +static s64 get_ns(void) +{ + struct timespec ts; + getnstimeofday(&ts); + return timespec_to_ns(&ts); +} + +/* + * bL switcher core code. + */ + +static void bL_do_switch(void *_arg) +{ + unsigned ib_mpidr, ib_cpu, ib_cluster; + long volatile handshake, **handshake_ptr = _arg; + + pr_debug("%s\n", __func__); + + ib_mpidr = cpu_logical_map(smp_processor_id()); + ib_cpu = MPIDR_AFFINITY_LEVEL(ib_mpidr, 0); + ib_cluster = MPIDR_AFFINITY_LEVEL(ib_mpidr, 1); + + /* Advertise our handshake location */ + if (handshake_ptr) { + handshake = 0; + *handshake_ptr = &handshake; + } else + handshake = -1; + + /* + * Our state has been saved at this point. Let's release our + * inbound CPU. + */ + mcpm_set_entry_vector(ib_cpu, ib_cluster, cpu_resume); + sev(); + + /* + * From this point, we must assume that our counterpart CPU might + * have taken over in its parallel world already, as if execution + * just returned from cpu_suspend(). It is therefore important to + * be very careful not to make any change the other guy is not + * expecting. This is why we need stack isolation. + * + * Fancy under cover tasks could be performed here. For now + * we have none. + */ + + /* + * Let's wait until our inbound is alive. + */ + while (!handshake) { + wfe(); + smp_mb(); + } + + /* Let's put ourself down. */ + mcpm_cpu_power_down(); + + /* should never get here */ + BUG(); +} + +/* + * Stack isolation. To ensure 'current' remains valid, we just use another + * piece of our thread's stack space which should be fairly lightly used. + * The selected area starts just above the thread_info structure located + * at the very bottom of the stack, aligned to a cache line, and indexed + * with the cluster number. + */ +#define STACK_SIZE 512 +extern void call_with_stack(void (*fn)(void *), void *arg, void *sp); +static int bL_switchpoint(unsigned long _arg) +{ + unsigned int mpidr = read_mpidr(); + unsigned int clusterid = MPIDR_AFFINITY_LEVEL(mpidr, 1); + void *stack = current_thread_info() + 1; + stack = PTR_ALIGN(stack, L1_CACHE_BYTES); + stack += clusterid * STACK_SIZE + STACK_SIZE; + call_with_stack(bL_do_switch, (void *)_arg, stack); + BUG(); +} + +/* + * Generic switcher interface + */ + +static unsigned int bL_gic_id[MAX_CPUS_PER_CLUSTER][MAX_NR_CLUSTERS]; +static int bL_switcher_cpu_pairing[NR_CPUS]; + +/* + * bL_switch_to - Switch to a specific cluster for the current CPU + * @new_cluster_id: the ID of the cluster to switch to. + * + * This function must be called on the CPU to be switched. + * Returns 0 on success, else a negative status code. + */ +static int bL_switch_to(unsigned int new_cluster_id) +{ + unsigned int mpidr, this_cpu, that_cpu; + unsigned int ob_mpidr, ob_cpu, ob_cluster, ib_mpidr, ib_cpu, ib_cluster; + struct completion inbound_alive; + struct tick_device *tdev; + enum clock_event_mode tdev_mode; + long volatile *handshake_ptr; + int ipi_nr, ret; + + this_cpu = smp_processor_id(); + ob_mpidr = read_mpidr(); + ob_cpu = MPIDR_AFFINITY_LEVEL(ob_mpidr, 0); + ob_cluster = MPIDR_AFFINITY_LEVEL(ob_mpidr, 1); + BUG_ON(cpu_logical_map(this_cpu) != ob_mpidr); + + if (new_cluster_id == ob_cluster) + return 0; + + that_cpu = bL_switcher_cpu_pairing[this_cpu]; + ib_mpidr = cpu_logical_map(that_cpu); + ib_cpu = MPIDR_AFFINITY_LEVEL(ib_mpidr, 0); + ib_cluster = MPIDR_AFFINITY_LEVEL(ib_mpidr, 1); + + pr_debug("before switch: CPU %d MPIDR %#x -> %#x\n", + this_cpu, ob_mpidr, ib_mpidr); + + this_cpu = smp_processor_id(); + + /* Close the gate for our entry vectors */ + mcpm_set_entry_vector(ob_cpu, ob_cluster, NULL); + mcpm_set_entry_vector(ib_cpu, ib_cluster, NULL); + + /* Install our "inbound alive" notifier. */ + init_completion(&inbound_alive); + ipi_nr = register_ipi_completion(&inbound_alive, this_cpu); + ipi_nr |= ((1 << 16) << bL_gic_id[ob_cpu][ob_cluster]); + mcpm_set_early_poke(ib_cpu, ib_cluster, gic_get_sgir_physaddr(), ipi_nr); + + /* + * Let's wake up the inbound CPU now in case it requires some delay + * to come online, but leave it gated in our entry vector code. + */ + ret = mcpm_cpu_power_up(ib_cpu, ib_cluster); + if (ret) { + pr_err("%s: mcpm_cpu_power_up() returned %d\n", __func__, ret); + return ret; + } + + /* + * Raise a SGI on the inbound CPU to make sure it doesn't stall + * in a possible WFI, such as in bL_power_down(). + */ + gic_send_sgi(bL_gic_id[ib_cpu][ib_cluster], 0); + + /* + * Wait for the inbound to come up. This allows for other + * tasks to be scheduled in the mean time. + */ + wait_for_completion(&inbound_alive); + mcpm_set_early_poke(ib_cpu, ib_cluster, 0, 0); + + /* + * From this point we are entering the switch critical zone + * and can't take any interrupts anymore. + */ + local_irq_disable(); + local_fiq_disable(); + trace_cpu_migrate_begin(get_ns(), ob_mpidr); + + /* redirect GIC's SGIs to our counterpart */ + gic_migrate_target(bL_gic_id[ib_cpu][ib_cluster]); + + tdev = tick_get_device(this_cpu); + if (tdev && !cpumask_equal(tdev->evtdev->cpumask, cpumask_of(this_cpu))) + tdev = NULL; + if (tdev) { + tdev_mode = tdev->evtdev->mode; + clockevents_set_mode(tdev->evtdev, CLOCK_EVT_MODE_SHUTDOWN); + } + + ret = cpu_pm_enter(); + + /* we can not tolerate errors at this point */ + if (ret) + panic("%s: cpu_pm_enter() returned %d\n", __func__, ret); + + /* Swap the physical CPUs in the logical map for this logical CPU. */ + cpu_logical_map(this_cpu) = ib_mpidr; + cpu_logical_map(that_cpu) = ob_mpidr; + + /* Let's do the actual CPU switch. */ + ret = cpu_suspend((unsigned long)&handshake_ptr, bL_switchpoint); + if (ret > 0) + panic("%s: cpu_suspend() returned %d\n", __func__, ret); + + /* We are executing on the inbound CPU at this point */ + mpidr = read_mpidr(); + pr_debug("after switch: CPU %d MPIDR %#x\n", this_cpu, mpidr); + BUG_ON(mpidr != ib_mpidr); + + mcpm_cpu_powered_up(); + + ret = cpu_pm_exit(); + + if (tdev) { + clockevents_set_mode(tdev->evtdev, tdev_mode); + clockevents_program_event(tdev->evtdev, + tdev->evtdev->next_event, 1); + } + + trace_cpu_migrate_finish(get_ns(), ib_mpidr); + local_fiq_enable(); + local_irq_enable(); + + *handshake_ptr = 1; + dsb_sev(); + + if (ret) + pr_err("%s exiting with error %d\n", __func__, ret); + return ret; +} + +struct bL_thread { + spinlock_t lock; + struct task_struct *task; + wait_queue_head_t wq; + int wanted_cluster; + struct completion started; + bL_switch_completion_handler completer; + void *completer_cookie; +}; + +static struct bL_thread bL_threads[NR_CPUS]; + +static int bL_switcher_thread(void *arg) +{ + struct bL_thread *t = arg; + struct sched_param param = { .sched_priority = 1 }; + int cluster; + bL_switch_completion_handler completer; + void *completer_cookie; + + sched_setscheduler_nocheck(current, SCHED_FIFO, ¶m); + complete(&t->started); + + do { + if (signal_pending(current)) + flush_signals(current); + wait_event_interruptible(t->wq, + t->wanted_cluster != -1 || + kthread_should_stop()); + + spin_lock(&t->lock); + cluster = t->wanted_cluster; + completer = t->completer; + completer_cookie = t->completer_cookie; + t->wanted_cluster = -1; + t->completer = NULL; + spin_unlock(&t->lock); + + if (cluster != -1) { + bL_switch_to(cluster); + + if (completer) + completer(completer_cookie); + } + } while (!kthread_should_stop()); + + return 0; +} + +static struct task_struct *bL_switcher_thread_create(int cpu, void *arg) +{ + struct task_struct *task; + + task = kthread_create_on_node(bL_switcher_thread, arg, + cpu_to_node(cpu), "kswitcher_%d", cpu); + if (!IS_ERR(task)) { + kthread_bind(task, cpu); + wake_up_process(task); + } else + pr_err("%s failed for CPU %d\n", __func__, cpu); + return task; +} + +/* + * bL_switch_request_cb - Switch to a specific cluster for the given CPU, + * with completion notification via a callback + * + * @cpu: the CPU to switch + * @new_cluster_id: the ID of the cluster to switch to. + * @completer: switch completion callback. if non-NULL, + * @completer(@completer_cookie) will be called on completion of + * the switch, in non-atomic context. + * @completer_cookie: opaque context argument for @completer. + * + * This function causes a cluster switch on the given CPU by waking up + * the appropriate switcher thread. This function may or may not return + * before the switch has occurred. + * + * If a @completer callback function is supplied, it will be called when + * the switch is complete. This can be used to determine asynchronously + * when the switch is complete, regardless of when bL_switch_request() + * returns. When @completer is supplied, no new switch request is permitted + * for the affected CPU until after the switch is complete, and @completer + * has returned. + */ +int bL_switch_request_cb(unsigned int cpu, unsigned int new_cluster_id, + bL_switch_completion_handler completer, + void *completer_cookie) +{ + struct bL_thread *t; + + if (cpu >= ARRAY_SIZE(bL_threads)) { + pr_err("%s: cpu %d out of bounds\n", __func__, cpu); + return -EINVAL; + } + + t = &bL_threads[cpu]; + + if (IS_ERR(t->task)) + return PTR_ERR(t->task); + if (!t->task) + return -ESRCH; + + spin_lock(&t->lock); + if (t->completer) { + spin_unlock(&t->lock); + return -EBUSY; + } + t->completer = completer; + t->completer_cookie = completer_cookie; + t->wanted_cluster = new_cluster_id; + spin_unlock(&t->lock); + wake_up(&t->wq); + return 0; +} +EXPORT_SYMBOL_GPL(bL_switch_request_cb); + +/* + * Activation and configuration code. + */ + +static DEFINE_MUTEX(bL_switcher_activation_lock); +static BLOCKING_NOTIFIER_HEAD(bL_activation_notifier); +static unsigned int bL_switcher_active; +static unsigned int bL_switcher_cpu_original_cluster[NR_CPUS]; +static cpumask_t bL_switcher_removed_logical_cpus; + +int bL_switcher_register_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&bL_activation_notifier, nb); +} +EXPORT_SYMBOL_GPL(bL_switcher_register_notifier); + +int bL_switcher_unregister_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&bL_activation_notifier, nb); +} +EXPORT_SYMBOL_GPL(bL_switcher_unregister_notifier); + +static int bL_activation_notify(unsigned long val) +{ + int ret; + + ret = blocking_notifier_call_chain(&bL_activation_notifier, val, NULL); + if (ret & NOTIFY_STOP_MASK) + pr_err("%s: notifier chain failed with status 0x%x\n", + __func__, ret); + return notifier_to_errno(ret); +} + +static void bL_switcher_restore_cpus(void) +{ + int i; + + for_each_cpu(i, &bL_switcher_removed_logical_cpus) + cpu_up(i); +} + +static int bL_switcher_halve_cpus(void) +{ + int i, j, cluster_0, gic_id, ret; + unsigned int cpu, cluster, mask; + cpumask_t available_cpus; + + /* First pass to validate what we have */ + mask = 0; + for_each_online_cpu(i) { + cpu = MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 0); + cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 1); + if (cluster >= 2) { + pr_err("%s: only dual cluster systems are supported\n", __func__); + return -EINVAL; + } + if (WARN_ON(cpu >= MAX_CPUS_PER_CLUSTER)) + return -EINVAL; + mask |= (1 << cluster); + } + if (mask != 3) { + pr_err("%s: no CPU pairing possible\n", __func__); + return -EINVAL; + } + + /* + * Now let's do the pairing. We match each CPU with another CPU + * from a different cluster. To get a uniform scheduling behavior + * without fiddling with CPU topology and compute capacity data, + * we'll use logical CPUs initially belonging to the same cluster. + */ + memset(bL_switcher_cpu_pairing, -1, sizeof(bL_switcher_cpu_pairing)); + cpumask_copy(&available_cpus, cpu_online_mask); + cluster_0 = -1; + for_each_cpu(i, &available_cpus) { + int match = -1; + cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 1); + if (cluster_0 == -1) + cluster_0 = cluster; + if (cluster != cluster_0) + continue; + cpumask_clear_cpu(i, &available_cpus); + for_each_cpu(j, &available_cpus) { + cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(j), 1); + /* + * Let's remember the last match to create "odd" + * pairings on purpose in order for other code not + * to assume any relation between physical and + * logical CPU numbers. + */ + if (cluster != cluster_0) + match = j; + } + if (match != -1) { + bL_switcher_cpu_pairing[i] = match; + cpumask_clear_cpu(match, &available_cpus); + pr_info("CPU%d paired with CPU%d\n", i, match); + } + } + + /* + * Now we disable the unwanted CPUs i.e. everything that has no + * pairing information (that includes the pairing counterparts). + */ + cpumask_clear(&bL_switcher_removed_logical_cpus); + for_each_online_cpu(i) { + cpu = MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 0); + cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 1); + + /* Let's take note of the GIC ID for this CPU */ + gic_id = gic_get_cpu_id(i); + if (gic_id < 0) { + pr_err("%s: bad GIC ID for CPU %d\n", __func__, i); + bL_switcher_restore_cpus(); + return -EINVAL; + } + bL_gic_id[cpu][cluster] = gic_id; + pr_info("GIC ID for CPU %u cluster %u is %u\n", + cpu, cluster, gic_id); + + if (bL_switcher_cpu_pairing[i] != -1) { + bL_switcher_cpu_original_cluster[i] = cluster; + continue; + } + + ret = cpu_down(i); + if (ret) { + bL_switcher_restore_cpus(); + return ret; + } + cpumask_set_cpu(i, &bL_switcher_removed_logical_cpus); + } + + return 0; +} + +/* Determine the logical CPU a given physical CPU is grouped on. */ +int bL_switcher_get_logical_index(u32 mpidr) +{ + int cpu; + + if (!bL_switcher_active) + return -EUNATCH; + + mpidr &= MPIDR_HWID_BITMASK; + for_each_online_cpu(cpu) { + int pairing = bL_switcher_cpu_pairing[cpu]; + if (pairing == -1) + continue; + if ((mpidr == cpu_logical_map(cpu)) || + (mpidr == cpu_logical_map(pairing))) + return cpu; + } + return -EINVAL; +} + +static void bL_switcher_trace_trigger_cpu(void *__always_unused info) +{ + trace_cpu_migrate_current(get_ns(), read_mpidr()); +} + +int bL_switcher_trace_trigger(void) +{ + int ret; + + preempt_disable(); + + bL_switcher_trace_trigger_cpu(NULL); + ret = smp_call_function(bL_switcher_trace_trigger_cpu, NULL, true); + + preempt_enable(); + + return ret; +} +EXPORT_SYMBOL_GPL(bL_switcher_trace_trigger); + +static int bL_switcher_enable(void) +{ + int cpu, ret; + + mutex_lock(&bL_switcher_activation_lock); + cpu_hotplug_driver_lock(); + if (bL_switcher_active) { + cpu_hotplug_driver_unlock(); + mutex_unlock(&bL_switcher_activation_lock); + return 0; + } + + pr_info("big.LITTLE switcher initializing\n"); + + ret = bL_activation_notify(BL_NOTIFY_PRE_ENABLE); + if (ret) + goto error; + + ret = bL_switcher_halve_cpus(); + if (ret) + goto error; + + bL_switcher_trace_trigger(); + + for_each_online_cpu(cpu) { + struct bL_thread *t = &bL_threads[cpu]; + spin_lock_init(&t->lock); + init_waitqueue_head(&t->wq); + init_completion(&t->started); + t->wanted_cluster = -1; + t->task = bL_switcher_thread_create(cpu, t); + } + + bL_switcher_active = 1; + bL_activation_notify(BL_NOTIFY_POST_ENABLE); + pr_info("big.LITTLE switcher initialized\n"); + goto out; + +error: + pr_warn("big.LITTLE switcher initialization failed\n"); + bL_activation_notify(BL_NOTIFY_POST_DISABLE); + +out: + cpu_hotplug_driver_unlock(); + mutex_unlock(&bL_switcher_activation_lock); + return ret; +} + +#ifdef CONFIG_SYSFS + +static void bL_switcher_disable(void) +{ + unsigned int cpu, cluster; + struct bL_thread *t; + struct task_struct *task; + + mutex_lock(&bL_switcher_activation_lock); + cpu_hotplug_driver_lock(); + + if (!bL_switcher_active) + goto out; + + if (bL_activation_notify(BL_NOTIFY_PRE_DISABLE) != 0) { + bL_activation_notify(BL_NOTIFY_POST_ENABLE); + goto out; + } + + bL_switcher_active = 0; + + /* + * To deactivate the switcher, we must shut down the switcher + * threads to prevent any other requests from being accepted. + * Then, if the final cluster for given logical CPU is not the + * same as the original one, we'll recreate a switcher thread + * just for the purpose of switching the CPU back without any + * possibility for interference from external requests. + */ + for_each_online_cpu(cpu) { + t = &bL_threads[cpu]; + task = t->task; + t->task = NULL; + if (!task || IS_ERR(task)) + continue; + kthread_stop(task); + /* no more switch may happen on this CPU at this point */ + cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(cpu), 1); + if (cluster == bL_switcher_cpu_original_cluster[cpu]) + continue; + init_completion(&t->started); + t->wanted_cluster = bL_switcher_cpu_original_cluster[cpu]; + task = bL_switcher_thread_create(cpu, t); + if (!IS_ERR(task)) { + wait_for_completion(&t->started); + kthread_stop(task); + cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(cpu), 1); + if (cluster == bL_switcher_cpu_original_cluster[cpu]) + continue; + } + /* If execution gets here, we're in trouble. */ + pr_crit("%s: unable to restore original cluster for CPU %d\n", + __func__, cpu); + pr_crit("%s: CPU %d can't be restored\n", + __func__, bL_switcher_cpu_pairing[cpu]); + cpumask_clear_cpu(bL_switcher_cpu_pairing[cpu], + &bL_switcher_removed_logical_cpus); + } + + bL_switcher_restore_cpus(); + bL_switcher_trace_trigger(); + + bL_activation_notify(BL_NOTIFY_POST_DISABLE); + +out: + cpu_hotplug_driver_unlock(); + mutex_unlock(&bL_switcher_activation_lock); +} + +static ssize_t bL_switcher_active_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%u\n", bL_switcher_active); +} + +static ssize_t bL_switcher_active_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + int ret; + + switch (buf[0]) { + case '0': + bL_switcher_disable(); + ret = 0; + break; + case '1': + ret = bL_switcher_enable(); + break; + default: + ret = -EINVAL; + } + + return (ret >= 0) ? count : ret; +} + +static ssize_t bL_switcher_trace_trigger_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t count) +{ + int ret = bL_switcher_trace_trigger(); + + return ret ? ret : count; +} + +static struct kobj_attribute bL_switcher_active_attr = + __ATTR(active, 0644, bL_switcher_active_show, bL_switcher_active_store); + +static struct kobj_attribute bL_switcher_trace_trigger_attr = + __ATTR(trace_trigger, 0200, NULL, bL_switcher_trace_trigger_store); + +static struct attribute *bL_switcher_attrs[] = { + &bL_switcher_active_attr.attr, + &bL_switcher_trace_trigger_attr.attr, + NULL, +}; + +static struct attribute_group bL_switcher_attr_group = { + .attrs = bL_switcher_attrs, +}; + +static struct kobject *bL_switcher_kobj; + +static int __init bL_switcher_sysfs_init(void) +{ + int ret; + + bL_switcher_kobj = kobject_create_and_add("bL_switcher", kernel_kobj); + if (!bL_switcher_kobj) + return -ENOMEM; + ret = sysfs_create_group(bL_switcher_kobj, &bL_switcher_attr_group); + if (ret) + kobject_put(bL_switcher_kobj); + return ret; +} + +#endif /* CONFIG_SYSFS */ + +bool bL_switcher_get_enabled(void) +{ + mutex_lock(&bL_switcher_activation_lock); + + return bL_switcher_active; +} +EXPORT_SYMBOL_GPL(bL_switcher_get_enabled); + +void bL_switcher_put_enabled(void) +{ + mutex_unlock(&bL_switcher_activation_lock); +} +EXPORT_SYMBOL_GPL(bL_switcher_put_enabled); + +/* + * Veto any CPU hotplug operation on those CPUs we've removed + * while the switcher is active. + * We're just not ready to deal with that given the trickery involved. + */ +static int bL_switcher_hotplug_callback(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + if (bL_switcher_active) { + int pairing = bL_switcher_cpu_pairing[(unsigned long)hcpu]; + switch (action & 0xf) { + case CPU_UP_PREPARE: + case CPU_DOWN_PREPARE: + if (pairing == -1) + return NOTIFY_BAD; + } + } + return NOTIFY_DONE; +} + +static bool no_bL_switcher; +core_param(no_bL_switcher, no_bL_switcher, bool, 0644); + +static int __init bL_switcher_init(void) +{ + int ret; + + if (MAX_NR_CLUSTERS != 2) { + pr_err("%s: only dual cluster systems are supported\n", __func__); + return -EINVAL; + } + + cpu_notifier(bL_switcher_hotplug_callback, 0); + + if (!no_bL_switcher) { + ret = bL_switcher_enable(); + if (ret) + return ret; + } + +#ifdef CONFIG_SYSFS + ret = bL_switcher_sysfs_init(); + if (ret) + pr_err("%s: unable to create sysfs entry\n", __func__); +#endif + + return 0; +} + +late_initcall(bL_switcher_init); diff --git a/arch/arm/common/bL_switcher_dummy_if.c b/arch/arm/common/bL_switcher_dummy_if.c new file mode 100644 index 000000000000..3f47f1203c6b --- /dev/null +++ b/arch/arm/common/bL_switcher_dummy_if.c @@ -0,0 +1,71 @@ +/* + * arch/arm/common/bL_switcher_dummy_if.c -- b.L switcher dummy interface + * + * Created by: Nicolas Pitre, November 2012 + * Copyright: (C) 2012-2013 Linaro Limited + * + * Dummy interface to user space for debugging purpose only. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/fs.h> +#include <linux/miscdevice.h> +#include <asm/uaccess.h> +#include <asm/bL_switcher.h> + +static ssize_t bL_switcher_write(struct file *file, const char __user *buf, + size_t len, loff_t *pos) +{ + unsigned char val[3]; + unsigned int cpu, cluster; + int ret; + + pr_debug("%s\n", __func__); + + if (len < 3) + return -EINVAL; + + if (copy_from_user(val, buf, 3)) + return -EFAULT; + + /* format: <cpu#>,<cluster#> */ + if (val[0] < '0' || val[0] > '9' || + val[1] != ',' || + val[2] < '0' || val[2] > '1') + return -EINVAL; + + cpu = val[0] - '0'; + cluster = val[2] - '0'; + ret = bL_switch_request(cpu, cluster); + + return ret ? : len; +} + +static const struct file_operations bL_switcher_fops = { + .write = bL_switcher_write, + .owner = THIS_MODULE, +}; + +static struct miscdevice bL_switcher_device = { + MISC_DYNAMIC_MINOR, + "b.L_switcher", + &bL_switcher_fops +}; + +static int __init bL_switcher_dummy_if_init(void) +{ + return misc_register(&bL_switcher_device); +} + +static void __exit bL_switcher_dummy_if_exit(void) +{ + misc_deregister(&bL_switcher_device); +} + +module_init(bL_switcher_dummy_if_init); +module_exit(bL_switcher_dummy_if_exit); diff --git a/arch/arm/common/mcpm_entry.c b/arch/arm/common/mcpm_entry.c index 370236dd1a03..26020a03f659 100644 --- a/arch/arm/common/mcpm_entry.c +++ b/arch/arm/common/mcpm_entry.c @@ -27,6 +27,18 @@ void mcpm_set_entry_vector(unsigned cpu, unsigned cluster, void *ptr) sync_cache_w(&mcpm_entry_vectors[cluster][cpu]); } +extern unsigned long mcpm_entry_early_pokes[MAX_NR_CLUSTERS][MAX_CPUS_PER_CLUSTER][2]; + +void mcpm_set_early_poke(unsigned cpu, unsigned cluster, + unsigned long poke_phys_addr, unsigned long poke_val) +{ + unsigned long *poke = &mcpm_entry_early_pokes[cluster][cpu][0]; + poke[0] = poke_phys_addr; + poke[1] = poke_val; + __cpuc_flush_dcache_area((void *)poke, 8); + outer_clean_range(__pa(poke), __pa(poke + 2)); +} + static const struct mcpm_platform_ops *platform_ops; int __init mcpm_platform_register(const struct mcpm_platform_ops *ops) @@ -51,7 +63,8 @@ void mcpm_cpu_power_down(void) { phys_reset_t phys_reset; - BUG_ON(!platform_ops); + if (WARN_ON_ONCE(!platform_ops || !platform_ops->power_down)) + return; BUG_ON(!irqs_disabled()); /* @@ -89,11 +102,27 @@ void mcpm_cpu_power_down(void) BUG(); } +int mcpm_cpu_power_down_finish(unsigned int cpu, unsigned int cluster) +{ + int ret; + + if (WARN_ON_ONCE(!platform_ops || !platform_ops->power_down_finish)) + return -EUNATCH; + + ret = platform_ops->power_down_finish(cpu, cluster); + if (ret) + pr_warn("%s: cpu %u, cluster %u failed to power down (%d)\n", + __func__, cpu, cluster, ret); + + return ret; +} + void mcpm_cpu_suspend(u64 expected_residency) { phys_reset_t phys_reset; - BUG_ON(!platform_ops); + if (WARN_ON_ONCE(!platform_ops || !platform_ops->suspend)) + return; BUG_ON(!irqs_disabled()); /* Very similar to mcpm_cpu_power_down() */ diff --git a/arch/arm/common/mcpm_head.S b/arch/arm/common/mcpm_head.S index 39c96df3477a..e02db4b81a66 100644 --- a/arch/arm/common/mcpm_head.S +++ b/arch/arm/common/mcpm_head.S @@ -15,6 +15,7 @@ #include <linux/linkage.h> #include <asm/mcpm.h> +#include <asm/assembler.h> #include "vlock.h" @@ -47,6 +48,7 @@ ENTRY(mcpm_entry_point) + ARM_BE8(setend be) THUMB( adr r12, BSYM(1f) ) THUMB( bx r12 ) THUMB( .thumb ) @@ -71,12 +73,19 @@ ENTRY(mcpm_entry_point) * position independent way. */ adr r5, 3f - ldmia r5, {r6, r7, r8, r11} + ldmia r5, {r0, r6, r7, r8, r11} + add r0, r5, r0 @ r0 = mcpm_entry_early_pokes add r6, r5, r6 @ r6 = mcpm_entry_vectors ldr r7, [r5, r7] @ r7 = mcpm_power_up_setup_phys add r8, r5, r8 @ r8 = mcpm_sync add r11, r5, r11 @ r11 = first_man_locks + @ Perform an early poke, if any + add r0, r0, r4, lsl #3 + ldmia r0, {r0, r1} + teq r0, #0 + strne r1, [r0] + mov r0, #MCPM_SYNC_CLUSTER_SIZE mla r8, r0, r10, r8 @ r8 = sync cluster base @@ -195,7 +204,8 @@ mcpm_entry_gated: .align 2 -3: .word mcpm_entry_vectors - . +3: .word mcpm_entry_early_pokes - . + .word mcpm_entry_vectors - 3b .word mcpm_power_up_setup_phys - 3b .word mcpm_sync - 3b .word first_man_locks - 3b @@ -214,6 +224,10 @@ first_man_locks: ENTRY(mcpm_entry_vectors) .space 4 * MAX_NR_CLUSTERS * MAX_CPUS_PER_CLUSTER + .type mcpm_entry_early_pokes, #object +ENTRY(mcpm_entry_early_pokes) + .space 8 * MAX_NR_CLUSTERS * MAX_CPUS_PER_CLUSTER + .type mcpm_power_up_setup_phys, #object ENTRY(mcpm_power_up_setup_phys) .space 4 @ set by mcpm_sync_init() diff --git a/arch/arm/common/mcpm_platsmp.c b/arch/arm/common/mcpm_platsmp.c index 1bc34c7567fd..177251a4dd9a 100644 --- a/arch/arm/common/mcpm_platsmp.c +++ b/arch/arm/common/mcpm_platsmp.c @@ -19,14 +19,23 @@ #include <asm/smp.h> #include <asm/smp_plat.h> +static void cpu_to_pcpu(unsigned int cpu, + unsigned int *pcpu, unsigned int *pcluster) +{ + unsigned int mpidr; + + mpidr = cpu_logical_map(cpu); + *pcpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); + *pcluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); +} + static int mcpm_boot_secondary(unsigned int cpu, struct task_struct *idle) { - unsigned int mpidr, pcpu, pcluster, ret; + unsigned int pcpu, pcluster, ret; extern void secondary_startup(void); - mpidr = cpu_logical_map(cpu); - pcpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); - pcluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); + cpu_to_pcpu(cpu, &pcpu, &pcluster); + pr_debug("%s: logical CPU %d is physical CPU %d cluster %d\n", __func__, cpu, pcpu, pcluster); @@ -47,6 +56,15 @@ static void mcpm_secondary_init(unsigned int cpu) #ifdef CONFIG_HOTPLUG_CPU +static int mcpm_cpu_kill(unsigned int cpu) +{ + unsigned int pcpu, pcluster; + + cpu_to_pcpu(cpu, &pcpu, &pcluster); + + return !mcpm_cpu_power_down_finish(pcpu, pcluster); +} + static int mcpm_cpu_disable(unsigned int cpu) { /* @@ -73,6 +91,7 @@ static struct smp_operations __initdata mcpm_smp_ops = { .smp_boot_secondary = mcpm_boot_secondary, .smp_secondary_init = mcpm_secondary_init, #ifdef CONFIG_HOTPLUG_CPU + .cpu_kill = mcpm_cpu_kill, .cpu_disable = mcpm_cpu_disable, .cpu_die = mcpm_cpu_die, #endif diff --git a/arch/arm/common/sharpsl_param.c b/arch/arm/common/sharpsl_param.c index d56c932580eb..025f6ce38596 100644 --- a/arch/arm/common/sharpsl_param.c +++ b/arch/arm/common/sharpsl_param.c @@ -15,6 +15,7 @@ #include <linux/module.h> #include <linux/string.h> #include <asm/mach/sharpsl_param.h> +#include <asm/memory.h> /* * Certain hardware parameters determined at the time of device manufacture, @@ -25,8 +26,10 @@ */ #ifdef CONFIG_ARCH_SA1100 #define PARAM_BASE 0xe8ffc000 +#define param_start(x) (void *)(x) #else #define PARAM_BASE 0xa0000a00 +#define param_start(x) __va(x) #endif #define MAGIC_CHG(a,b,c,d) ( ( d << 24 ) | ( c << 16 ) | ( b << 8 ) | a ) @@ -41,7 +44,7 @@ EXPORT_SYMBOL(sharpsl_param); void sharpsl_save_param(void) { - memcpy(&sharpsl_param, (void *)PARAM_BASE, sizeof(struct sharpsl_param_info)); + memcpy(&sharpsl_param, param_start(PARAM_BASE), sizeof(struct sharpsl_param_info)); if (sharpsl_param.comadj_keyword != COMADJ_MAGIC) sharpsl_param.comadj=-1; diff --git a/arch/arm/common/timer-sp.c b/arch/arm/common/timer-sp.c index e901d0f3e0bb..ce922d0ea7aa 100644 --- a/arch/arm/common/timer-sp.c +++ b/arch/arm/common/timer-sp.c @@ -175,7 +175,7 @@ static struct clock_event_device sp804_clockevent = { static struct irqaction sp804_timer_irq = { .name = "timer", - .flags = IRQF_DISABLED | IRQF_TIMER | IRQF_IRQPOLL, + .flags = IRQF_TIMER | IRQF_IRQPOLL, .handler = sp804_timer_interrupt, .dev_id = &sp804_clockevent, }; diff --git a/arch/arm/configs/h3600_defconfig b/arch/arm/configs/h3600_defconfig index 317960f12488..0142ec37e0be 100644 --- a/arch/arm/configs/h3600_defconfig +++ b/arch/arm/configs/h3600_defconfig @@ -1,5 +1,6 @@ -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y +CONFIG_NO_HZ_IDLE=y +CONFIG_HIGH_RES_TIMERS=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_BLK_DEV_INITRD=y CONFIG_MODULES=y @@ -11,11 +12,11 @@ CONFIG_ARCH_SA1100=y CONFIG_SA1100_H3600=y CONFIG_PCCARD=y CONFIG_PCMCIA_SA1100=y +CONFIG_PREEMPT=y CONFIG_ZBOOT_ROM_TEXT=0x0 CONFIG_ZBOOT_ROM_BSS=0x0 # CONFIG_CPU_FREQ_STAT is not set CONFIG_FPE_NWFPE=y -CONFIG_PM=y CONFIG_NET=y CONFIG_UNIX=y CONFIG_INET=y @@ -24,13 +25,10 @@ CONFIG_IRDA=m CONFIG_IRLAN=m CONFIG_IRNET=m CONFIG_IRCOMM=m -CONFIG_SA1100_FIR=m # CONFIG_WIRELESS is not set CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_MTD=y -CONFIG_MTD_PARTITIONS=y CONFIG_MTD_REDBOOT_PARTS=y -CONFIG_MTD_CHAR=y CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y CONFIG_MTD_CFI_ADV_OPTIONS=y @@ -41,19 +39,15 @@ CONFIG_MTD_SA1100=y CONFIG_BLK_DEV_LOOP=m CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=8192 -# CONFIG_MISC_DEVICES is not set CONFIG_IDE=y CONFIG_BLK_DEV_IDECS=y CONFIG_NETDEVICES=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set -# CONFIG_WLAN is not set -CONFIG_NET_PCMCIA=y CONFIG_PCMCIA_PCNET=y CONFIG_PPP=m -CONFIG_PPP_ASYNC=m -CONFIG_PPP_DEFLATE=m CONFIG_PPP_BSDCOMP=m +CONFIG_PPP_DEFLATE=m +CONFIG_PPP_ASYNC=m +# CONFIG_WLAN is not set # CONFIG_KEYBOARD_ATKBD is not set CONFIG_KEYBOARD_GPIO=y # CONFIG_INPUT_MOUSE is not set @@ -64,8 +58,6 @@ CONFIG_SERIAL_SA1100_CONSOLE=y # CONFIG_HWMON is not set CONFIG_FB=y CONFIG_FB_SA1100=y -# CONFIG_VGA_CONSOLE is not set -# CONFIG_HID_SUPPORT is not set # CONFIG_USB_SUPPORT is not set CONFIG_EXT2_FS=y CONFIG_MSDOS_FS=m @@ -74,6 +66,4 @@ CONFIG_JFFS2_FS=y CONFIG_CRAMFS=m CONFIG_NFS_FS=y CONFIG_NFSD=m -CONFIG_SMB_FS=m CONFIG_NLS=y -# CONFIG_RCU_CPU_STALL_DETECTOR is not set diff --git a/arch/arm/crypto/.gitignore b/arch/arm/crypto/.gitignore new file mode 100644 index 000000000000..6231d36b3635 --- /dev/null +++ b/arch/arm/crypto/.gitignore @@ -0,0 +1 @@ +aesbs-core.S diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile index a2c83851bc90..81cda39860c5 100644 --- a/arch/arm/crypto/Makefile +++ b/arch/arm/crypto/Makefile @@ -3,7 +3,17 @@ # obj-$(CONFIG_CRYPTO_AES_ARM) += aes-arm.o +obj-$(CONFIG_CRYPTO_AES_ARM_BS) += aes-arm-bs.o obj-$(CONFIG_CRYPTO_SHA1_ARM) += sha1-arm.o -aes-arm-y := aes-armv4.o aes_glue.o -sha1-arm-y := sha1-armv4-large.o sha1_glue.o +aes-arm-y := aes-armv4.o aes_glue.o +aes-arm-bs-y := aesbs-core.o aesbs-glue.o +sha1-arm-y := sha1-armv4-large.o sha1_glue.o + +quiet_cmd_perl = PERL $@ + cmd_perl = $(PERL) $(<) > $(@) + +$(src)/aesbs-core.S_shipped: $(src)/bsaes-armv7.pl + $(call cmd,perl) + +.PRECIOUS: $(obj)/aesbs-core.S diff --git a/arch/arm/crypto/aes_glue.c b/arch/arm/crypto/aes_glue.c index 59f7877ead6a..3003fa1f6fb4 100644 --- a/arch/arm/crypto/aes_glue.c +++ b/arch/arm/crypto/aes_glue.c @@ -6,22 +6,12 @@ #include <linux/crypto.h> #include <crypto/aes.h> -#define AES_MAXNR 14 +#include "aes_glue.h" -typedef struct { - unsigned int rd_key[4 *(AES_MAXNR + 1)]; - int rounds; -} AES_KEY; - -struct AES_CTX { - AES_KEY enc_key; - AES_KEY dec_key; -}; - -asmlinkage void AES_encrypt(const u8 *in, u8 *out, AES_KEY *ctx); -asmlinkage void AES_decrypt(const u8 *in, u8 *out, AES_KEY *ctx); -asmlinkage int private_AES_set_decrypt_key(const unsigned char *userKey, const int bits, AES_KEY *key); -asmlinkage int private_AES_set_encrypt_key(const unsigned char *userKey, const int bits, AES_KEY *key); +EXPORT_SYMBOL(AES_encrypt); +EXPORT_SYMBOL(AES_decrypt); +EXPORT_SYMBOL(private_AES_set_encrypt_key); +EXPORT_SYMBOL(private_AES_set_decrypt_key); static void aes_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) { @@ -81,7 +71,7 @@ static struct crypto_alg aes_alg = { .cipher = { .cia_min_keysize = AES_MIN_KEY_SIZE, .cia_max_keysize = AES_MAX_KEY_SIZE, - .cia_setkey = aes_set_key, + .cia_setkey = aes_set_key, .cia_encrypt = aes_encrypt, .cia_decrypt = aes_decrypt } diff --git a/arch/arm/crypto/aes_glue.h b/arch/arm/crypto/aes_glue.h new file mode 100644 index 000000000000..cca3e51eb606 --- /dev/null +++ b/arch/arm/crypto/aes_glue.h @@ -0,0 +1,19 @@ + +#define AES_MAXNR 14 + +struct AES_KEY { + unsigned int rd_key[4 * (AES_MAXNR + 1)]; + int rounds; +}; + +struct AES_CTX { + struct AES_KEY enc_key; + struct AES_KEY dec_key; +}; + +asmlinkage void AES_encrypt(const u8 *in, u8 *out, struct AES_KEY *ctx); +asmlinkage void AES_decrypt(const u8 *in, u8 *out, struct AES_KEY *ctx); +asmlinkage int private_AES_set_decrypt_key(const unsigned char *userKey, + const int bits, struct AES_KEY *key); +asmlinkage int private_AES_set_encrypt_key(const unsigned char *userKey, + const int bits, struct AES_KEY *key); diff --git a/arch/arm/crypto/aesbs-core.S_shipped b/arch/arm/crypto/aesbs-core.S_shipped new file mode 100644 index 000000000000..64205d453260 --- /dev/null +++ b/arch/arm/crypto/aesbs-core.S_shipped @@ -0,0 +1,2544 @@ + +@ ==================================================================== +@ Written by Andy Polyakov <appro@openssl.org> for the OpenSSL +@ project. The module is, however, dual licensed under OpenSSL and +@ CRYPTOGAMS licenses depending on where you obtain it. For further +@ details see http://www.openssl.org/~appro/cryptogams/. +@ +@ Specific modes and adaptation for Linux kernel by Ard Biesheuvel +@ <ard.biesheuvel@linaro.org>. Permission to use under GPL terms is +@ granted. +@ ==================================================================== + +@ Bit-sliced AES for ARM NEON +@ +@ February 2012. +@ +@ This implementation is direct adaptation of bsaes-x86_64 module for +@ ARM NEON. Except that this module is endian-neutral [in sense that +@ it can be compiled for either endianness] by courtesy of vld1.8's +@ neutrality. Initial version doesn't implement interface to OpenSSL, +@ only low-level primitives and unsupported entry points, just enough +@ to collect performance results, which for Cortex-A8 core are: +@ +@ encrypt 19.5 cycles per byte processed with 128-bit key +@ decrypt 22.1 cycles per byte processed with 128-bit key +@ key conv. 440 cycles per 128-bit key/0.18 of 8x block +@ +@ Snapdragon S4 encrypts byte in 17.6 cycles and decrypts in 19.7, +@ which is [much] worse than anticipated (for further details see +@ http://www.openssl.org/~appro/Snapdragon-S4.html). +@ +@ Cortex-A15 manages in 14.2/16.1 cycles [when integer-only code +@ manages in 20.0 cycles]. +@ +@ When comparing to x86_64 results keep in mind that NEON unit is +@ [mostly] single-issue and thus can't [fully] benefit from +@ instruction-level parallelism. And when comparing to aes-armv4 +@ results keep in mind key schedule conversion overhead (see +@ bsaes-x86_64.pl for further details)... +@ +@ <appro@openssl.org> + +@ April-August 2013 +@ +@ Add CBC, CTR and XTS subroutines, adapt for kernel use. +@ +@ <ard.biesheuvel@linaro.org> + +#ifndef __KERNEL__ +# include "arm_arch.h" + +# define VFP_ABI_PUSH vstmdb sp!,{d8-d15} +# define VFP_ABI_POP vldmia sp!,{d8-d15} +# define VFP_ABI_FRAME 0x40 +#else +# define VFP_ABI_PUSH +# define VFP_ABI_POP +# define VFP_ABI_FRAME 0 +# define BSAES_ASM_EXTENDED_KEY +# define XTS_CHAIN_TWEAK +# define __ARM_ARCH__ __LINUX_ARM_ARCH__ +#endif + +#ifdef __thumb__ +# define adrl adr +#endif + +#if __ARM_ARCH__>=7 +.text +.syntax unified @ ARMv7-capable assembler is expected to handle this +#ifdef __thumb2__ +.thumb +#else +.code 32 +#endif + +.fpu neon + +.type _bsaes_decrypt8,%function +.align 4 +_bsaes_decrypt8: + adr r6,_bsaes_decrypt8 + vldmia r4!, {q9} @ round 0 key + add r6,r6,#.LM0ISR-_bsaes_decrypt8 + + vldmia r6!, {q8} @ .LM0ISR + veor q10, q0, q9 @ xor with round0 key + veor q11, q1, q9 + vtbl.8 d0, {q10}, d16 + vtbl.8 d1, {q10}, d17 + veor q12, q2, q9 + vtbl.8 d2, {q11}, d16 + vtbl.8 d3, {q11}, d17 + veor q13, q3, q9 + vtbl.8 d4, {q12}, d16 + vtbl.8 d5, {q12}, d17 + veor q14, q4, q9 + vtbl.8 d6, {q13}, d16 + vtbl.8 d7, {q13}, d17 + veor q15, q5, q9 + vtbl.8 d8, {q14}, d16 + vtbl.8 d9, {q14}, d17 + veor q10, q6, q9 + vtbl.8 d10, {q15}, d16 + vtbl.8 d11, {q15}, d17 + veor q11, q7, q9 + vtbl.8 d12, {q10}, d16 + vtbl.8 d13, {q10}, d17 + vtbl.8 d14, {q11}, d16 + vtbl.8 d15, {q11}, d17 + vmov.i8 q8,#0x55 @ compose .LBS0 + vmov.i8 q9,#0x33 @ compose .LBS1 + vshr.u64 q10, q6, #1 + vshr.u64 q11, q4, #1 + veor q10, q10, q7 + veor q11, q11, q5 + vand q10, q10, q8 + vand q11, q11, q8 + veor q7, q7, q10 + vshl.u64 q10, q10, #1 + veor q5, q5, q11 + vshl.u64 q11, q11, #1 + veor q6, q6, q10 + veor q4, q4, q11 + vshr.u64 q10, q2, #1 + vshr.u64 q11, q0, #1 + veor q10, q10, q3 + veor q11, q11, q1 + vand q10, q10, q8 + vand q11, q11, q8 + veor q3, q3, q10 + vshl.u64 q10, q10, #1 + veor q1, q1, q11 + vshl.u64 q11, q11, #1 + veor q2, q2, q10 + veor q0, q0, q11 + vmov.i8 q8,#0x0f @ compose .LBS2 + vshr.u64 q10, q5, #2 + vshr.u64 q11, q4, #2 + veor q10, q10, q7 + veor q11, q11, q6 + vand q10, q10, q9 + vand q11, q11, q9 + veor q7, q7, q10 + vshl.u64 q10, q10, #2 + veor q6, q6, q11 + vshl.u64 q11, q11, #2 + veor q5, q5, q10 + veor q4, q4, q11 + vshr.u64 q10, q1, #2 + vshr.u64 q11, q0, #2 + veor q10, q10, q3 + veor q11, q11, q2 + vand q10, q10, q9 + vand q11, q11, q9 + veor q3, q3, q10 + vshl.u64 q10, q10, #2 + veor q2, q2, q11 + vshl.u64 q11, q11, #2 + veor q1, q1, q10 + veor q0, q0, q11 + vshr.u64 q10, q3, #4 + vshr.u64 q11, q2, #4 + veor q10, q10, q7 + veor q11, q11, q6 + vand q10, q10, q8 + vand q11, q11, q8 + veor q7, q7, q10 + vshl.u64 q10, q10, #4 + veor q6, q6, q11 + vshl.u64 q11, q11, #4 + veor q3, q3, q10 + veor q2, q2, q11 + vshr.u64 q10, q1, #4 + vshr.u64 q11, q0, #4 + veor q10, q10, q5 + veor q11, q11, q4 + vand q10, q10, q8 + vand q11, q11, q8 + veor q5, q5, q10 + vshl.u64 q10, q10, #4 + veor q4, q4, q11 + vshl.u64 q11, q11, #4 + veor q1, q1, q10 + veor q0, q0, q11 + sub r5,r5,#1 + b .Ldec_sbox +.align 4 +.Ldec_loop: + vldmia r4!, {q8-q11} + veor q8, q8, q0 + veor q9, q9, q1 + vtbl.8 d0, {q8}, d24 + vtbl.8 d1, {q8}, d25 + vldmia r4!, {q8} + veor q10, q10, q2 + vtbl.8 d2, {q9}, d24 + vtbl.8 d3, {q9}, d25 + vldmia r4!, {q9} + veor q11, q11, q3 + vtbl.8 d4, {q10}, d24 + vtbl.8 d5, {q10}, d25 + vldmia r4!, {q10} + vtbl.8 d6, {q11}, d24 + vtbl.8 d7, {q11}, d25 + vldmia r4!, {q11} + veor q8, q8, q4 + veor q9, q9, q5 + vtbl.8 d8, {q8}, d24 + vtbl.8 d9, {q8}, d25 + veor q10, q10, q6 + vtbl.8 d10, {q9}, d24 + vtbl.8 d11, {q9}, d25 + veor q11, q11, q7 + vtbl.8 d12, {q10}, d24 + vtbl.8 d13, {q10}, d25 + vtbl.8 d14, {q11}, d24 + vtbl.8 d15, {q11}, d25 +.Ldec_sbox: + veor q1, q1, q4 + veor q3, q3, q4 + + veor q4, q4, q7 + veor q1, q1, q6 + veor q2, q2, q7 + veor q6, q6, q4 + + veor q0, q0, q1 + veor q2, q2, q5 + veor q7, q7, q6 + veor q3, q3, q0 + veor q5, q5, q0 + veor q1, q1, q3 + veor q11, q3, q0 + veor q10, q7, q4 + veor q9, q1, q6 + veor q13, q4, q0 + vmov q8, q10 + veor q12, q5, q2 + + vorr q10, q10, q9 + veor q15, q11, q8 + vand q14, q11, q12 + vorr q11, q11, q12 + veor q12, q12, q9 + vand q8, q8, q9 + veor q9, q6, q2 + vand q15, q15, q12 + vand q13, q13, q9 + veor q9, q3, q7 + veor q12, q1, q5 + veor q11, q11, q13 + veor q10, q10, q13 + vand q13, q9, q12 + vorr q9, q9, q12 + veor q11, q11, q15 + veor q8, q8, q13 + veor q10, q10, q14 + veor q9, q9, q15 + veor q8, q8, q14 + vand q12, q4, q6 + veor q9, q9, q14 + vand q13, q0, q2 + vand q14, q7, q1 + vorr q15, q3, q5 + veor q11, q11, q12 + veor q9, q9, q14 + veor q8, q8, q15 + veor q10, q10, q13 + + @ Inv_GF16 0, 1, 2, 3, s0, s1, s2, s3 + + @ new smaller inversion + + vand q14, q11, q9 + vmov q12, q8 + + veor q13, q10, q14 + veor q15, q8, q14 + veor q14, q8, q14 @ q14=q15 + + vbsl q13, q9, q8 + vbsl q15, q11, q10 + veor q11, q11, q10 + + vbsl q12, q13, q14 + vbsl q8, q14, q13 + + vand q14, q12, q15 + veor q9, q9, q8 + + veor q14, q14, q11 + veor q12, q5, q2 + veor q8, q1, q6 + veor q10, q15, q14 + vand q10, q10, q5 + veor q5, q5, q1 + vand q11, q1, q15 + vand q5, q5, q14 + veor q1, q11, q10 + veor q5, q5, q11 + veor q15, q15, q13 + veor q14, q14, q9 + veor q11, q15, q14 + veor q10, q13, q9 + vand q11, q11, q12 + vand q10, q10, q2 + veor q12, q12, q8 + veor q2, q2, q6 + vand q8, q8, q15 + vand q6, q6, q13 + vand q12, q12, q14 + vand q2, q2, q9 + veor q8, q8, q12 + veor q2, q2, q6 + veor q12, q12, q11 + veor q6, q6, q10 + veor q5, q5, q12 + veor q2, q2, q12 + veor q1, q1, q8 + veor q6, q6, q8 + + veor q12, q3, q0 + veor q8, q7, q4 + veor q11, q15, q14 + veor q10, q13, q9 + vand q11, q11, q12 + vand q10, q10, q0 + veor q12, q12, q8 + veor q0, q0, q4 + vand q8, q8, q15 + vand q4, q4, q13 + vand q12, q12, q14 + vand q0, q0, q9 + veor q8, q8, q12 + veor q0, q0, q4 + veor q12, q12, q11 + veor q4, q4, q10 + veor q15, q15, q13 + veor q14, q14, q9 + veor q10, q15, q14 + vand q10, q10, q3 + veor q3, q3, q7 + vand q11, q7, q15 + vand q3, q3, q14 + veor q7, q11, q10 + veor q3, q3, q11 + veor q3, q3, q12 + veor q0, q0, q12 + veor q7, q7, q8 + veor q4, q4, q8 + veor q1, q1, q7 + veor q6, q6, q5 + + veor q4, q4, q1 + veor q2, q2, q7 + veor q5, q5, q7 + veor q4, q4, q2 + veor q7, q7, q0 + veor q4, q4, q5 + veor q3, q3, q6 + veor q6, q6, q1 + veor q3, q3, q4 + + veor q4, q4, q0 + veor q7, q7, q3 + subs r5,r5,#1 + bcc .Ldec_done + @ multiplication by 0x05-0x00-0x04-0x00 + vext.8 q8, q0, q0, #8 + vext.8 q14, q3, q3, #8 + vext.8 q15, q5, q5, #8 + veor q8, q8, q0 + vext.8 q9, q1, q1, #8 + veor q14, q14, q3 + vext.8 q10, q6, q6, #8 + veor q15, q15, q5 + vext.8 q11, q4, q4, #8 + veor q9, q9, q1 + vext.8 q12, q2, q2, #8 + veor q10, q10, q6 + vext.8 q13, q7, q7, #8 + veor q11, q11, q4 + veor q12, q12, q2 + veor q13, q13, q7 + + veor q0, q0, q14 + veor q1, q1, q14 + veor q6, q6, q8 + veor q2, q2, q10 + veor q4, q4, q9 + veor q1, q1, q15 + veor q6, q6, q15 + veor q2, q2, q14 + veor q7, q7, q11 + veor q4, q4, q14 + veor q3, q3, q12 + veor q2, q2, q15 + veor q7, q7, q15 + veor q5, q5, q13 + vext.8 q8, q0, q0, #12 @ x0 <<< 32 + vext.8 q9, q1, q1, #12 + veor q0, q0, q8 @ x0 ^ (x0 <<< 32) + vext.8 q10, q6, q6, #12 + veor q1, q1, q9 + vext.8 q11, q4, q4, #12 + veor q6, q6, q10 + vext.8 q12, q2, q2, #12 + veor q4, q4, q11 + vext.8 q13, q7, q7, #12 + veor q2, q2, q12 + vext.8 q14, q3, q3, #12 + veor q7, q7, q13 + vext.8 q15, q5, q5, #12 + veor q3, q3, q14 + + veor q9, q9, q0 + veor q5, q5, q15 + vext.8 q0, q0, q0, #8 @ (x0 ^ (x0 <<< 32)) <<< 64) + veor q10, q10, q1 + veor q8, q8, q5 + veor q9, q9, q5 + vext.8 q1, q1, q1, #8 + veor q13, q13, q2 + veor q0, q0, q8 + veor q14, q14, q7 + veor q1, q1, q9 + vext.8 q8, q2, q2, #8 + veor q12, q12, q4 + vext.8 q9, q7, q7, #8 + veor q15, q15, q3 + vext.8 q2, q4, q4, #8 + veor q11, q11, q6 + vext.8 q7, q5, q5, #8 + veor q12, q12, q5 + vext.8 q4, q3, q3, #8 + veor q11, q11, q5 + vext.8 q3, q6, q6, #8 + veor q5, q9, q13 + veor q11, q11, q2 + veor q7, q7, q15 + veor q6, q4, q14 + veor q4, q8, q12 + veor q2, q3, q10 + vmov q3, q11 + @ vmov q5, q9 + vldmia r6, {q12} @ .LISR + ite eq @ Thumb2 thing, sanity check in ARM + addeq r6,r6,#0x10 + bne .Ldec_loop + vldmia r6, {q12} @ .LISRM0 + b .Ldec_loop +.align 4 +.Ldec_done: + vmov.i8 q8,#0x55 @ compose .LBS0 + vmov.i8 q9,#0x33 @ compose .LBS1 + vshr.u64 q10, q3, #1 + vshr.u64 q11, q2, #1 + veor q10, q10, q5 + veor q11, q11, q7 + vand q10, q10, q8 + vand q11, q11, q8 + veor q5, q5, q10 + vshl.u64 q10, q10, #1 + veor q7, q7, q11 + vshl.u64 q11, q11, #1 + veor q3, q3, q10 + veor q2, q2, q11 + vshr.u64 q10, q6, #1 + vshr.u64 q11, q0, #1 + veor q10, q10, q4 + veor q11, q11, q1 + vand q10, q10, q8 + vand q11, q11, q8 + veor q4, q4, q10 + vshl.u64 q10, q10, #1 + veor q1, q1, q11 + vshl.u64 q11, q11, #1 + veor q6, q6, q10 + veor q0, q0, q11 + vmov.i8 q8,#0x0f @ compose .LBS2 + vshr.u64 q10, q7, #2 + vshr.u64 q11, q2, #2 + veor q10, q10, q5 + veor q11, q11, q3 + vand q10, q10, q9 + vand q11, q11, q9 + veor q5, q5, q10 + vshl.u64 q10, q10, #2 + veor q3, q3, q11 + vshl.u64 q11, q11, #2 + veor q7, q7, q10 + veor q2, q2, q11 + vshr.u64 q10, q1, #2 + vshr.u64 q11, q0, #2 + veor q10, q10, q4 + veor q11, q11, q6 + vand q10, q10, q9 + vand q11, q11, q9 + veor q4, q4, q10 + vshl.u64 q10, q10, #2 + veor q6, q6, q11 + vshl.u64 q11, q11, #2 + veor q1, q1, q10 + veor q0, q0, q11 + vshr.u64 q10, q4, #4 + vshr.u64 q11, q6, #4 + veor q10, q10, q5 + veor q11, q11, q3 + vand q10, q10, q8 + vand q11, q11, q8 + veor q5, q5, q10 + vshl.u64 q10, q10, #4 + veor q3, q3, q11 + vshl.u64 q11, q11, #4 + veor q4, q4, q10 + veor q6, q6, q11 + vshr.u64 q10, q1, #4 + vshr.u64 q11, q0, #4 + veor q10, q10, q7 + veor q11, q11, q2 + vand q10, q10, q8 + vand q11, q11, q8 + veor q7, q7, q10 + vshl.u64 q10, q10, #4 + veor q2, q2, q11 + vshl.u64 q11, q11, #4 + veor q1, q1, q10 + veor q0, q0, q11 + vldmia r4, {q8} @ last round key + veor q6, q6, q8 + veor q4, q4, q8 + veor q2, q2, q8 + veor q7, q7, q8 + veor q3, q3, q8 + veor q5, q5, q8 + veor q0, q0, q8 + veor q1, q1, q8 + bx lr +.size _bsaes_decrypt8,.-_bsaes_decrypt8 + +.type _bsaes_const,%object +.align 6 +_bsaes_const: +.LM0ISR: @ InvShiftRows constants + .quad 0x0a0e0206070b0f03, 0x0004080c0d010509 +.LISR: + .quad 0x0504070602010003, 0x0f0e0d0c080b0a09 +.LISRM0: + .quad 0x01040b0e0205080f, 0x0306090c00070a0d +.LM0SR: @ ShiftRows constants + .quad 0x0a0e02060f03070b, 0x0004080c05090d01 +.LSR: + .quad 0x0504070600030201, 0x0f0e0d0c0a09080b +.LSRM0: + .quad 0x0304090e00050a0f, 0x01060b0c0207080d +.LM0: + .quad 0x02060a0e03070b0f, 0x0004080c0105090d +.LREVM0SR: + .quad 0x090d01050c000408, 0x03070b0f060a0e02 +.asciz "Bit-sliced AES for NEON, CRYPTOGAMS by <appro@openssl.org>" +.align 6 +.size _bsaes_const,.-_bsaes_const + +.type _bsaes_encrypt8,%function +.align 4 +_bsaes_encrypt8: + adr r6,_bsaes_encrypt8 + vldmia r4!, {q9} @ round 0 key + sub r6,r6,#_bsaes_encrypt8-.LM0SR + + vldmia r6!, {q8} @ .LM0SR +_bsaes_encrypt8_alt: + veor q10, q0, q9 @ xor with round0 key + veor q11, q1, q9 + vtbl.8 d0, {q10}, d16 + vtbl.8 d1, {q10}, d17 + veor q12, q2, q9 + vtbl.8 d2, {q11}, d16 + vtbl.8 d3, {q11}, d17 + veor q13, q3, q9 + vtbl.8 d4, {q12}, d16 + vtbl.8 d5, {q12}, d17 + veor q14, q4, q9 + vtbl.8 d6, {q13}, d16 + vtbl.8 d7, {q13}, d17 + veor q15, q5, q9 + vtbl.8 d8, {q14}, d16 + vtbl.8 d9, {q14}, d17 + veor q10, q6, q9 + vtbl.8 d10, {q15}, d16 + vtbl.8 d11, {q15}, d17 + veor q11, q7, q9 + vtbl.8 d12, {q10}, d16 + vtbl.8 d13, {q10}, d17 + vtbl.8 d14, {q11}, d16 + vtbl.8 d15, {q11}, d17 +_bsaes_encrypt8_bitslice: + vmov.i8 q8,#0x55 @ compose .LBS0 + vmov.i8 q9,#0x33 @ compose .LBS1 + vshr.u64 q10, q6, #1 + vshr.u64 q11, q4, #1 + veor q10, q10, q7 + veor q11, q11, q5 + vand q10, q10, q8 + vand q11, q11, q8 + veor q7, q7, q10 + vshl.u64 q10, q10, #1 + veor q5, q5, q11 + vshl.u64 q11, q11, #1 + veor q6, q6, q10 + veor q4, q4, q11 + vshr.u64 q10, q2, #1 + vshr.u64 q11, q0, #1 + veor q10, q10, q3 + veor q11, q11, q1 + vand q10, q10, q8 + vand q11, q11, q8 + veor q3, q3, q10 + vshl.u64 q10, q10, #1 + veor q1, q1, q11 + vshl.u64 q11, q11, #1 + veor q2, q2, q10 + veor q0, q0, q11 + vmov.i8 q8,#0x0f @ compose .LBS2 + vshr.u64 q10, q5, #2 + vshr.u64 q11, q4, #2 + veor q10, q10, q7 + veor q11, q11, q6 + vand q10, q10, q9 + vand q11, q11, q9 + veor q7, q7, q10 + vshl.u64 q10, q10, #2 + veor q6, q6, q11 + vshl.u64 q11, q11, #2 + veor q5, q5, q10 + veor q4, q4, q11 + vshr.u64 q10, q1, #2 + vshr.u64 q11, q0, #2 + veor q10, q10, q3 + veor q11, q11, q2 + vand q10, q10, q9 + vand q11, q11, q9 + veor q3, q3, q10 + vshl.u64 q10, q10, #2 + veor q2, q2, q11 + vshl.u64 q11, q11, #2 + veor q1, q1, q10 + veor q0, q0, q11 + vshr.u64 q10, q3, #4 + vshr.u64 q11, q2, #4 + veor q10, q10, q7 + veor q11, q11, q6 + vand q10, q10, q8 + vand q11, q11, q8 + veor q7, q7, q10 + vshl.u64 q10, q10, #4 + veor q6, q6, q11 + vshl.u64 q11, q11, #4 + veor q3, q3, q10 + veor q2, q2, q11 + vshr.u64 q10, q1, #4 + vshr.u64 q11, q0, #4 + veor q10, q10, q5 + veor q11, q11, q4 + vand q10, q10, q8 + vand q11, q11, q8 + veor q5, q5, q10 + vshl.u64 q10, q10, #4 + veor q4, q4, q11 + vshl.u64 q11, q11, #4 + veor q1, q1, q10 + veor q0, q0, q11 + sub r5,r5,#1 + b .Lenc_sbox +.align 4 +.Lenc_loop: + vldmia r4!, {q8-q11} + veor q8, q8, q0 + veor q9, q9, q1 + vtbl.8 d0, {q8}, d24 + vtbl.8 d1, {q8}, d25 + vldmia r4!, {q8} + veor q10, q10, q2 + vtbl.8 d2, {q9}, d24 + vtbl.8 d3, {q9}, d25 + vldmia r4!, {q9} + veor q11, q11, q3 + vtbl.8 d4, {q10}, d24 + vtbl.8 d5, {q10}, d25 + vldmia r4!, {q10} + vtbl.8 d6, {q11}, d24 + vtbl.8 d7, {q11}, d25 + vldmia r4!, {q11} + veor q8, q8, q4 + veor q9, q9, q5 + vtbl.8 d8, {q8}, d24 + vtbl.8 d9, {q8}, d25 + veor q10, q10, q6 + vtbl.8 d10, {q9}, d24 + vtbl.8 d11, {q9}, d25 + veor q11, q11, q7 + vtbl.8 d12, {q10}, d24 + vtbl.8 d13, {q10}, d25 + vtbl.8 d14, {q11}, d24 + vtbl.8 d15, {q11}, d25 +.Lenc_sbox: + veor q2, q2, q1 + veor q5, q5, q6 + veor q3, q3, q0 + veor q6, q6, q2 + veor q5, q5, q0 + + veor q6, q6, q3 + veor q3, q3, q7 + veor q7, q7, q5 + veor q3, q3, q4 + veor q4, q4, q5 + + veor q2, q2, q7 + veor q3, q3, q1 + veor q1, q1, q5 + veor q11, q7, q4 + veor q10, q1, q2 + veor q9, q5, q3 + veor q13, q2, q4 + vmov q8, q10 + veor q12, q6, q0 + + vorr q10, q10, q9 + veor q15, q11, q8 + vand q14, q11, q12 + vorr q11, q11, q12 + veor q12, q12, q9 + vand q8, q8, q9 + veor q9, q3, q0 + vand q15, q15, q12 + vand q13, q13, q9 + veor q9, q7, q1 + veor q12, q5, q6 + veor q11, q11, q13 + veor q10, q10, q13 + vand q13, q9, q12 + vorr q9, q9, q12 + veor q11, q11, q15 + veor q8, q8, q13 + veor q10, q10, q14 + veor q9, q9, q15 + veor q8, q8, q14 + vand q12, q2, q3 + veor q9, q9, q14 + vand q13, q4, q0 + vand q14, q1, q5 + vorr q15, q7, q6 + veor q11, q11, q12 + veor q9, q9, q14 + veor q8, q8, q15 + veor q10, q10, q13 + + @ Inv_GF16 0, 1, 2, 3, s0, s1, s2, s3 + + @ new smaller inversion + + vand q14, q11, q9 + vmov q12, q8 + + veor q13, q10, q14 + veor q15, q8, q14 + veor q14, q8, q14 @ q14=q15 + + vbsl q13, q9, q8 + vbsl q15, q11, q10 + veor q11, q11, q10 + + vbsl q12, q13, q14 + vbsl q8, q14, q13 + + vand q14, q12, q15 + veor q9, q9, q8 + + veor q14, q14, q11 + veor q12, q6, q0 + veor q8, q5, q3 + veor q10, q15, q14 + vand q10, q10, q6 + veor q6, q6, q5 + vand q11, q5, q15 + vand q6, q6, q14 + veor q5, q11, q10 + veor q6, q6, q11 + veor q15, q15, q13 + veor q14, q14, q9 + veor q11, q15, q14 + veor q10, q13, q9 + vand q11, q11, q12 + vand q10, q10, q0 + veor q12, q12, q8 + veor q0, q0, q3 + vand q8, q8, q15 + vand q3, q3, q13 + vand q12, q12, q14 + vand q0, q0, q9 + veor q8, q8, q12 + veor q0, q0, q3 + veor q12, q12, q11 + veor q3, q3, q10 + veor q6, q6, q12 + veor q0, q0, q12 + veor q5, q5, q8 + veor q3, q3, q8 + + veor q12, q7, q4 + veor q8, q1, q2 + veor q11, q15, q14 + veor q10, q13, q9 + vand q11, q11, q12 + vand q10, q10, q4 + veor q12, q12, q8 + veor q4, q4, q2 + vand q8, q8, q15 + vand q2, q2, q13 + vand q12, q12, q14 + vand q4, q4, q9 + veor q8, q8, q12 + veor q4, q4, q2 + veor q12, q12, q11 + veor q2, q2, q10 + veor q15, q15, q13 + veor q14, q14, q9 + veor q10, q15, q14 + vand q10, q10, q7 + veor q7, q7, q1 + vand q11, q1, q15 + vand q7, q7, q14 + veor q1, q11, q10 + veor q7, q7, q11 + veor q7, q7, q12 + veor q4, q4, q12 + veor q1, q1, q8 + veor q2, q2, q8 + veor q7, q7, q0 + veor q1, q1, q6 + veor q6, q6, q0 + veor q4, q4, q7 + veor q0, q0, q1 + + veor q1, q1, q5 + veor q5, q5, q2 + veor q2, q2, q3 + veor q3, q3, q5 + veor q4, q4, q5 + + veor q6, q6, q3 + subs r5,r5,#1 + bcc .Lenc_done + vext.8 q8, q0, q0, #12 @ x0 <<< 32 + vext.8 q9, q1, q1, #12 + veor q0, q0, q8 @ x0 ^ (x0 <<< 32) + vext.8 q10, q4, q4, #12 + veor q1, q1, q9 + vext.8 q11, q6, q6, #12 + veor q4, q4, q10 + vext.8 q12, q3, q3, #12 + veor q6, q6, q11 + vext.8 q13, q7, q7, #12 + veor q3, q3, q12 + vext.8 q14, q2, q2, #12 + veor q7, q7, q13 + vext.8 q15, q5, q5, #12 + veor q2, q2, q14 + + veor q9, q9, q0 + veor q5, q5, q15 + vext.8 q0, q0, q0, #8 @ (x0 ^ (x0 <<< 32)) <<< 64) + veor q10, q10, q1 + veor q8, q8, q5 + veor q9, q9, q5 + vext.8 q1, q1, q1, #8 + veor q13, q13, q3 + veor q0, q0, q8 + veor q14, q14, q7 + veor q1, q1, q9 + vext.8 q8, q3, q3, #8 + veor q12, q12, q6 + vext.8 q9, q7, q7, #8 + veor q15, q15, q2 + vext.8 q3, q6, q6, #8 + veor q11, q11, q4 + vext.8 q7, q5, q5, #8 + veor q12, q12, q5 + vext.8 q6, q2, q2, #8 + veor q11, q11, q5 + vext.8 q2, q4, q4, #8 + veor q5, q9, q13 + veor q4, q8, q12 + veor q3, q3, q11 + veor q7, q7, q15 + veor q6, q6, q14 + @ vmov q4, q8 + veor q2, q2, q10 + @ vmov q5, q9 + vldmia r6, {q12} @ .LSR + ite eq @ Thumb2 thing, samity check in ARM + addeq r6,r6,#0x10 + bne .Lenc_loop + vldmia r6, {q12} @ .LSRM0 + b .Lenc_loop +.align 4 +.Lenc_done: + vmov.i8 q8,#0x55 @ compose .LBS0 + vmov.i8 q9,#0x33 @ compose .LBS1 + vshr.u64 q10, q2, #1 + vshr.u64 q11, q3, #1 + veor q10, q10, q5 + veor q11, q11, q7 + vand q10, q10, q8 + vand q11, q11, q8 + veor q5, q5, q10 + vshl.u64 q10, q10, #1 + veor q7, q7, q11 + vshl.u64 q11, q11, #1 + veor q2, q2, q10 + veor q3, q3, q11 + vshr.u64 q10, q4, #1 + vshr.u64 q11, q0, #1 + veor q10, q10, q6 + veor q11, q11, q1 + vand q10, q10, q8 + vand q11, q11, q8 + veor q6, q6, q10 + vshl.u64 q10, q10, #1 + veor q1, q1, q11 + vshl.u64 q11, q11, #1 + veor q4, q4, q10 + veor q0, q0, q11 + vmov.i8 q8,#0x0f @ compose .LBS2 + vshr.u64 q10, q7, #2 + vshr.u64 q11, q3, #2 + veor q10, q10, q5 + veor q11, q11, q2 + vand q10, q10, q9 + vand q11, q11, q9 + veor q5, q5, q10 + vshl.u64 q10, q10, #2 + veor q2, q2, q11 + vshl.u64 q11, q11, #2 + veor q7, q7, q10 + veor q3, q3, q11 + vshr.u64 q10, q1, #2 + vshr.u64 q11, q0, #2 + veor q10, q10, q6 + veor q11, q11, q4 + vand q10, q10, q9 + vand q11, q11, q9 + veor q6, q6, q10 + vshl.u64 q10, q10, #2 + veor q4, q4, q11 + vshl.u64 q11, q11, #2 + veor q1, q1, q10 + veor q0, q0, q11 + vshr.u64 q10, q6, #4 + vshr.u64 q11, q4, #4 + veor q10, q10, q5 + veor q11, q11, q2 + vand q10, q10, q8 + vand q11, q11, q8 + veor q5, q5, q10 + vshl.u64 q10, q10, #4 + veor q2, q2, q11 + vshl.u64 q11, q11, #4 + veor q6, q6, q10 + veor q4, q4, q11 + vshr.u64 q10, q1, #4 + vshr.u64 q11, q0, #4 + veor q10, q10, q7 + veor q11, q11, q3 + vand q10, q10, q8 + vand q11, q11, q8 + veor q7, q7, q10 + vshl.u64 q10, q10, #4 + veor q3, q3, q11 + vshl.u64 q11, q11, #4 + veor q1, q1, q10 + veor q0, q0, q11 + vldmia r4, {q8} @ last round key + veor q4, q4, q8 + veor q6, q6, q8 + veor q3, q3, q8 + veor q7, q7, q8 + veor q2, q2, q8 + veor q5, q5, q8 + veor q0, q0, q8 + veor q1, q1, q8 + bx lr +.size _bsaes_encrypt8,.-_bsaes_encrypt8 +.type _bsaes_key_convert,%function +.align 4 +_bsaes_key_convert: + adr r6,_bsaes_key_convert + vld1.8 {q7}, [r4]! @ load round 0 key + sub r6,r6,#_bsaes_key_convert-.LM0 + vld1.8 {q15}, [r4]! @ load round 1 key + + vmov.i8 q8, #0x01 @ bit masks + vmov.i8 q9, #0x02 + vmov.i8 q10, #0x04 + vmov.i8 q11, #0x08 + vmov.i8 q12, #0x10 + vmov.i8 q13, #0x20 + vldmia r6, {q14} @ .LM0 + +#ifdef __ARMEL__ + vrev32.8 q7, q7 + vrev32.8 q15, q15 +#endif + sub r5,r5,#1 + vstmia r12!, {q7} @ save round 0 key + b .Lkey_loop + +.align 4 +.Lkey_loop: + vtbl.8 d14,{q15},d28 + vtbl.8 d15,{q15},d29 + vmov.i8 q6, #0x40 + vmov.i8 q15, #0x80 + + vtst.8 q0, q7, q8 + vtst.8 q1, q7, q9 + vtst.8 q2, q7, q10 + vtst.8 q3, q7, q11 + vtst.8 q4, q7, q12 + vtst.8 q5, q7, q13 + vtst.8 q6, q7, q6 + vtst.8 q7, q7, q15 + vld1.8 {q15}, [r4]! @ load next round key + vmvn q0, q0 @ "pnot" + vmvn q1, q1 + vmvn q5, q5 + vmvn q6, q6 +#ifdef __ARMEL__ + vrev32.8 q15, q15 +#endif + subs r5,r5,#1 + vstmia r12!,{q0-q7} @ write bit-sliced round key + bne .Lkey_loop + + vmov.i8 q7,#0x63 @ compose .L63 + @ don't save last round key + bx lr +.size _bsaes_key_convert,.-_bsaes_key_convert +.extern AES_cbc_encrypt +.extern AES_decrypt + +.global bsaes_cbc_encrypt +.type bsaes_cbc_encrypt,%function +.align 5 +bsaes_cbc_encrypt: +#ifndef __KERNEL__ + cmp r2, #128 +#ifndef __thumb__ + blo AES_cbc_encrypt +#else + bhs 1f + b AES_cbc_encrypt +1: +#endif +#endif + + @ it is up to the caller to make sure we are called with enc == 0 + + mov ip, sp + stmdb sp!, {r4-r10, lr} + VFP_ABI_PUSH + ldr r8, [ip] @ IV is 1st arg on the stack + mov r2, r2, lsr#4 @ len in 16 byte blocks + sub sp, #0x10 @ scratch space to carry over the IV + mov r9, sp @ save sp + + ldr r10, [r3, #240] @ get # of rounds +#ifndef BSAES_ASM_EXTENDED_KEY + @ allocate the key schedule on the stack + sub r12, sp, r10, lsl#7 @ 128 bytes per inner round key + add r12, #96 @ sifze of bit-slices key schedule + + @ populate the key schedule + mov r4, r3 @ pass key + mov r5, r10 @ pass # of rounds + mov sp, r12 @ sp is sp + bl _bsaes_key_convert + vldmia sp, {q6} + vstmia r12, {q15} @ save last round key + veor q7, q7, q6 @ fix up round 0 key + vstmia sp, {q7} +#else + ldr r12, [r3, #244] + eors r12, #1 + beq 0f + + @ populate the key schedule + str r12, [r3, #244] + mov r4, r3 @ pass key + mov r5, r10 @ pass # of rounds + add r12, r3, #248 @ pass key schedule + bl _bsaes_key_convert + add r4, r3, #248 + vldmia r4, {q6} + vstmia r12, {q15} @ save last round key + veor q7, q7, q6 @ fix up round 0 key + vstmia r4, {q7} + +.align 2 +0: +#endif + + vld1.8 {q15}, [r8] @ load IV + b .Lcbc_dec_loop + +.align 4 +.Lcbc_dec_loop: + subs r2, r2, #0x8 + bmi .Lcbc_dec_loop_finish + + vld1.8 {q0-q1}, [r0]! @ load input + vld1.8 {q2-q3}, [r0]! +#ifndef BSAES_ASM_EXTENDED_KEY + mov r4, sp @ pass the key +#else + add r4, r3, #248 +#endif + vld1.8 {q4-q5}, [r0]! + mov r5, r10 + vld1.8 {q6-q7}, [r0] + sub r0, r0, #0x60 + vstmia r9, {q15} @ put aside IV + + bl _bsaes_decrypt8 + + vldmia r9, {q14} @ reload IV + vld1.8 {q8-q9}, [r0]! @ reload input + veor q0, q0, q14 @ ^= IV + vld1.8 {q10-q11}, [r0]! + veor q1, q1, q8 + veor q6, q6, q9 + vld1.8 {q12-q13}, [r0]! + veor q4, q4, q10 + veor q2, q2, q11 + vld1.8 {q14-q15}, [r0]! + veor q7, q7, q12 + vst1.8 {q0-q1}, [r1]! @ write output + veor q3, q3, q13 + vst1.8 {q6}, [r1]! + veor q5, q5, q14 + vst1.8 {q4}, [r1]! + vst1.8 {q2}, [r1]! + vst1.8 {q7}, [r1]! + vst1.8 {q3}, [r1]! + vst1.8 {q5}, [r1]! + + b .Lcbc_dec_loop + +.Lcbc_dec_loop_finish: + adds r2, r2, #8 + beq .Lcbc_dec_done + + vld1.8 {q0}, [r0]! @ load input + cmp r2, #2 + blo .Lcbc_dec_one + vld1.8 {q1}, [r0]! +#ifndef BSAES_ASM_EXTENDED_KEY + mov r4, sp @ pass the key +#else + add r4, r3, #248 +#endif + mov r5, r10 + vstmia r9, {q15} @ put aside IV + beq .Lcbc_dec_two + vld1.8 {q2}, [r0]! + cmp r2, #4 + blo .Lcbc_dec_three + vld1.8 {q3}, [r0]! + beq .Lcbc_dec_four + vld1.8 {q4}, [r0]! + cmp r2, #6 + blo .Lcbc_dec_five + vld1.8 {q5}, [r0]! + beq .Lcbc_dec_six + vld1.8 {q6}, [r0]! + sub r0, r0, #0x70 + + bl _bsaes_decrypt8 + + vldmia r9, {q14} @ reload IV + vld1.8 {q8-q9}, [r0]! @ reload input + veor q0, q0, q14 @ ^= IV + vld1.8 {q10-q11}, [r0]! + veor q1, q1, q8 + veor q6, q6, q9 + vld1.8 {q12-q13}, [r0]! + veor q4, q4, q10 + veor q2, q2, q11 + vld1.8 {q15}, [r0]! + veor q7, q7, q12 + vst1.8 {q0-q1}, [r1]! @ write output + veor q3, q3, q13 + vst1.8 {q6}, [r1]! + vst1.8 {q4}, [r1]! + vst1.8 {q2}, [r1]! + vst1.8 {q7}, [r1]! + vst1.8 {q3}, [r1]! + b .Lcbc_dec_done +.align 4 +.Lcbc_dec_six: + sub r0, r0, #0x60 + bl _bsaes_decrypt8 + vldmia r9,{q14} @ reload IV + vld1.8 {q8-q9}, [r0]! @ reload input + veor q0, q0, q14 @ ^= IV + vld1.8 {q10-q11}, [r0]! + veor q1, q1, q8 + veor q6, q6, q9 + vld1.8 {q12}, [r0]! + veor q4, q4, q10 + veor q2, q2, q11 + vld1.8 {q15}, [r0]! + veor q7, q7, q12 + vst1.8 {q0-q1}, [r1]! @ write output + vst1.8 {q6}, [r1]! + vst1.8 {q4}, [r1]! + vst1.8 {q2}, [r1]! + vst1.8 {q7}, [r1]! + b .Lcbc_dec_done +.align 4 +.Lcbc_dec_five: + sub r0, r0, #0x50 + bl _bsaes_decrypt8 + vldmia r9, {q14} @ reload IV + vld1.8 {q8-q9}, [r0]! @ reload input + veor q0, q0, q14 @ ^= IV + vld1.8 {q10-q11}, [r0]! + veor q1, q1, q8 + veor q6, q6, q9 + vld1.8 {q15}, [r0]! + veor q4, q4, q10 + vst1.8 {q0-q1}, [r1]! @ write output + veor q2, q2, q11 + vst1.8 {q6}, [r1]! + vst1.8 {q4}, [r1]! + vst1.8 {q2}, [r1]! + b .Lcbc_dec_done +.align 4 +.Lcbc_dec_four: + sub r0, r0, #0x40 + bl _bsaes_decrypt8 + vldmia r9, {q14} @ reload IV + vld1.8 {q8-q9}, [r0]! @ reload input + veor q0, q0, q14 @ ^= IV + vld1.8 {q10}, [r0]! + veor q1, q1, q8 + veor q6, q6, q9 + vld1.8 {q15}, [r0]! + veor q4, q4, q10 + vst1.8 {q0-q1}, [r1]! @ write output + vst1.8 {q6}, [r1]! + vst1.8 {q4}, [r1]! + b .Lcbc_dec_done +.align 4 +.Lcbc_dec_three: + sub r0, r0, #0x30 + bl _bsaes_decrypt8 + vldmia r9, {q14} @ reload IV + vld1.8 {q8-q9}, [r0]! @ reload input + veor q0, q0, q14 @ ^= IV + vld1.8 {q15}, [r0]! + veor q1, q1, q8 + veor q6, q6, q9 + vst1.8 {q0-q1}, [r1]! @ write output + vst1.8 {q6}, [r1]! + b .Lcbc_dec_done +.align 4 +.Lcbc_dec_two: + sub r0, r0, #0x20 + bl _bsaes_decrypt8 + vldmia r9, {q14} @ reload IV + vld1.8 {q8}, [r0]! @ reload input + veor q0, q0, q14 @ ^= IV + vld1.8 {q15}, [r0]! @ reload input + veor q1, q1, q8 + vst1.8 {q0-q1}, [r1]! @ write output + b .Lcbc_dec_done +.align 4 +.Lcbc_dec_one: + sub r0, r0, #0x10 + mov r10, r1 @ save original out pointer + mov r1, r9 @ use the iv scratch space as out buffer + mov r2, r3 + vmov q4,q15 @ just in case ensure that IV + vmov q5,q0 @ and input are preserved + bl AES_decrypt + vld1.8 {q0}, [r9,:64] @ load result + veor q0, q0, q4 @ ^= IV + vmov q15, q5 @ q5 holds input + vst1.8 {q0}, [r10] @ write output + +.Lcbc_dec_done: +#ifndef BSAES_ASM_EXTENDED_KEY + vmov.i32 q0, #0 + vmov.i32 q1, #0 +.Lcbc_dec_bzero: @ wipe key schedule [if any] + vstmia sp!, {q0-q1} + cmp sp, r9 + bne .Lcbc_dec_bzero +#endif + + mov sp, r9 + add sp, #0x10 @ add sp,r9,#0x10 is no good for thumb + vst1.8 {q15}, [r8] @ return IV + VFP_ABI_POP + ldmia sp!, {r4-r10, pc} +.size bsaes_cbc_encrypt,.-bsaes_cbc_encrypt +.extern AES_encrypt +.global bsaes_ctr32_encrypt_blocks +.type bsaes_ctr32_encrypt_blocks,%function +.align 5 +bsaes_ctr32_encrypt_blocks: + cmp r2, #8 @ use plain AES for + blo .Lctr_enc_short @ small sizes + + mov ip, sp + stmdb sp!, {r4-r10, lr} + VFP_ABI_PUSH + ldr r8, [ip] @ ctr is 1st arg on the stack + sub sp, sp, #0x10 @ scratch space to carry over the ctr + mov r9, sp @ save sp + + ldr r10, [r3, #240] @ get # of rounds +#ifndef BSAES_ASM_EXTENDED_KEY + @ allocate the key schedule on the stack + sub r12, sp, r10, lsl#7 @ 128 bytes per inner round key + add r12, #96 @ size of bit-sliced key schedule + + @ populate the key schedule + mov r4, r3 @ pass key + mov r5, r10 @ pass # of rounds + mov sp, r12 @ sp is sp + bl _bsaes_key_convert + veor q7,q7,q15 @ fix up last round key + vstmia r12, {q7} @ save last round key + + vld1.8 {q0}, [r8] @ load counter + add r8, r6, #.LREVM0SR-.LM0 @ borrow r8 + vldmia sp, {q4} @ load round0 key +#else + ldr r12, [r3, #244] + eors r12, #1 + beq 0f + + @ populate the key schedule + str r12, [r3, #244] + mov r4, r3 @ pass key + mov r5, r10 @ pass # of rounds + add r12, r3, #248 @ pass key schedule + bl _bsaes_key_convert + veor q7,q7,q15 @ fix up last round key + vstmia r12, {q7} @ save last round key + +.align 2 +0: add r12, r3, #248 + vld1.8 {q0}, [r8] @ load counter + adrl r8, .LREVM0SR @ borrow r8 + vldmia r12, {q4} @ load round0 key + sub sp, #0x10 @ place for adjusted round0 key +#endif + + vmov.i32 q8,#1 @ compose 1<<96 + veor q9,q9,q9 + vrev32.8 q0,q0 + vext.8 q8,q9,q8,#4 + vrev32.8 q4,q4 + vadd.u32 q9,q8,q8 @ compose 2<<96 + vstmia sp, {q4} @ save adjusted round0 key + b .Lctr_enc_loop + +.align 4 +.Lctr_enc_loop: + vadd.u32 q10, q8, q9 @ compose 3<<96 + vadd.u32 q1, q0, q8 @ +1 + vadd.u32 q2, q0, q9 @ +2 + vadd.u32 q3, q0, q10 @ +3 + vadd.u32 q4, q1, q10 + vadd.u32 q5, q2, q10 + vadd.u32 q6, q3, q10 + vadd.u32 q7, q4, q10 + vadd.u32 q10, q5, q10 @ next counter + + @ Borrow prologue from _bsaes_encrypt8 to use the opportunity + @ to flip byte order in 32-bit counter + + vldmia sp, {q9} @ load round0 key +#ifndef BSAES_ASM_EXTENDED_KEY + add r4, sp, #0x10 @ pass next round key +#else + add r4, r3, #264 +#endif + vldmia r8, {q8} @ .LREVM0SR + mov r5, r10 @ pass rounds + vstmia r9, {q10} @ save next counter + sub r6, r8, #.LREVM0SR-.LSR @ pass constants + + bl _bsaes_encrypt8_alt + + subs r2, r2, #8 + blo .Lctr_enc_loop_done + + vld1.8 {q8-q9}, [r0]! @ load input + vld1.8 {q10-q11}, [r0]! + veor q0, q8 + veor q1, q9 + vld1.8 {q12-q13}, [r0]! + veor q4, q10 + veor q6, q11 + vld1.8 {q14-q15}, [r0]! + veor q3, q12 + vst1.8 {q0-q1}, [r1]! @ write output + veor q7, q13 + veor q2, q14 + vst1.8 {q4}, [r1]! + veor q5, q15 + vst1.8 {q6}, [r1]! + vmov.i32 q8, #1 @ compose 1<<96 + vst1.8 {q3}, [r1]! + veor q9, q9, q9 + vst1.8 {q7}, [r1]! + vext.8 q8, q9, q8, #4 + vst1.8 {q2}, [r1]! + vadd.u32 q9,q8,q8 @ compose 2<<96 + vst1.8 {q5}, [r1]! + vldmia r9, {q0} @ load counter + + bne .Lctr_enc_loop + b .Lctr_enc_done + +.align 4 +.Lctr_enc_loop_done: + add r2, r2, #8 + vld1.8 {q8}, [r0]! @ load input + veor q0, q8 + vst1.8 {q0}, [r1]! @ write output + cmp r2, #2 + blo .Lctr_enc_done + vld1.8 {q9}, [r0]! + veor q1, q9 + vst1.8 {q1}, [r1]! + beq .Lctr_enc_done + vld1.8 {q10}, [r0]! + veor q4, q10 + vst1.8 {q4}, [r1]! + cmp r2, #4 + blo .Lctr_enc_done + vld1.8 {q11}, [r0]! + veor q6, q11 + vst1.8 {q6}, [r1]! + beq .Lctr_enc_done + vld1.8 {q12}, [r0]! + veor q3, q12 + vst1.8 {q3}, [r1]! + cmp r2, #6 + blo .Lctr_enc_done + vld1.8 {q13}, [r0]! + veor q7, q13 + vst1.8 {q7}, [r1]! + beq .Lctr_enc_done + vld1.8 {q14}, [r0] + veor q2, q14 + vst1.8 {q2}, [r1]! + +.Lctr_enc_done: + vmov.i32 q0, #0 + vmov.i32 q1, #0 +#ifndef BSAES_ASM_EXTENDED_KEY +.Lctr_enc_bzero: @ wipe key schedule [if any] + vstmia sp!, {q0-q1} + cmp sp, r9 + bne .Lctr_enc_bzero +#else + vstmia sp, {q0-q1} +#endif + + mov sp, r9 + add sp, #0x10 @ add sp,r9,#0x10 is no good for thumb + VFP_ABI_POP + ldmia sp!, {r4-r10, pc} @ return + +.align 4 +.Lctr_enc_short: + ldr ip, [sp] @ ctr pointer is passed on stack + stmdb sp!, {r4-r8, lr} + + mov r4, r0 @ copy arguments + mov r5, r1 + mov r6, r2 + mov r7, r3 + ldr r8, [ip, #12] @ load counter LSW + vld1.8 {q1}, [ip] @ load whole counter value +#ifdef __ARMEL__ + rev r8, r8 +#endif + sub sp, sp, #0x10 + vst1.8 {q1}, [sp,:64] @ copy counter value + sub sp, sp, #0x10 + +.Lctr_enc_short_loop: + add r0, sp, #0x10 @ input counter value + mov r1, sp @ output on the stack + mov r2, r7 @ key + + bl AES_encrypt + + vld1.8 {q0}, [r4]! @ load input + vld1.8 {q1}, [sp,:64] @ load encrypted counter + add r8, r8, #1 +#ifdef __ARMEL__ + rev r0, r8 + str r0, [sp, #0x1c] @ next counter value +#else + str r8, [sp, #0x1c] @ next counter value +#endif + veor q0,q0,q1 + vst1.8 {q0}, [r5]! @ store output + subs r6, r6, #1 + bne .Lctr_enc_short_loop + + vmov.i32 q0, #0 + vmov.i32 q1, #0 + vstmia sp!, {q0-q1} + + ldmia sp!, {r4-r8, pc} +.size bsaes_ctr32_encrypt_blocks,.-bsaes_ctr32_encrypt_blocks +.globl bsaes_xts_encrypt +.type bsaes_xts_encrypt,%function +.align 4 +bsaes_xts_encrypt: + mov ip, sp + stmdb sp!, {r4-r10, lr} @ 0x20 + VFP_ABI_PUSH + mov r6, sp @ future r3 + + mov r7, r0 + mov r8, r1 + mov r9, r2 + mov r10, r3 + + sub r0, sp, #0x10 @ 0x10 + bic r0, #0xf @ align at 16 bytes + mov sp, r0 + +#ifdef XTS_CHAIN_TWEAK + ldr r0, [ip] @ pointer to input tweak +#else + @ generate initial tweak + ldr r0, [ip, #4] @ iv[] + mov r1, sp + ldr r2, [ip, #0] @ key2 + bl AES_encrypt + mov r0,sp @ pointer to initial tweak +#endif + + ldr r1, [r10, #240] @ get # of rounds + mov r3, r6 +#ifndef BSAES_ASM_EXTENDED_KEY + @ allocate the key schedule on the stack + sub r12, sp, r1, lsl#7 @ 128 bytes per inner round key + @ add r12, #96 @ size of bit-sliced key schedule + sub r12, #48 @ place for tweak[9] + + @ populate the key schedule + mov r4, r10 @ pass key + mov r5, r1 @ pass # of rounds + mov sp, r12 + add r12, #0x90 @ pass key schedule + bl _bsaes_key_convert + veor q7, q7, q15 @ fix up last round key + vstmia r12, {q7} @ save last round key +#else + ldr r12, [r10, #244] + eors r12, #1 + beq 0f + + str r12, [r10, #244] + mov r4, r10 @ pass key + mov r5, r1 @ pass # of rounds + add r12, r10, #248 @ pass key schedule + bl _bsaes_key_convert + veor q7, q7, q15 @ fix up last round key + vstmia r12, {q7} + +.align 2 +0: sub sp, #0x90 @ place for tweak[9] +#endif + + vld1.8 {q8}, [r0] @ initial tweak + adr r2, .Lxts_magic + + subs r9, #0x80 + blo .Lxts_enc_short + b .Lxts_enc_loop + +.align 4 +.Lxts_enc_loop: + vldmia r2, {q5} @ load XTS magic + vshr.s64 q6, q8, #63 + mov r0, sp + vand q6, q6, q5 + vadd.u64 q9, q8, q8 + vst1.64 {q8}, [r0,:128]! + vswp d13,d12 + vshr.s64 q7, q9, #63 + veor q9, q9, q6 + vand q7, q7, q5 + vadd.u64 q10, q9, q9 + vst1.64 {q9}, [r0,:128]! + vswp d15,d14 + vshr.s64 q6, q10, #63 + veor q10, q10, q7 + vand q6, q6, q5 + vld1.8 {q0}, [r7]! + vadd.u64 q11, q10, q10 + vst1.64 {q10}, [r0,:128]! + vswp d13,d12 + vshr.s64 q7, q11, #63 + veor q11, q11, q6 + vand q7, q7, q5 + vld1.8 {q1}, [r7]! + veor q0, q0, q8 + vadd.u64 q12, q11, q11 + vst1.64 {q11}, [r0,:128]! + vswp d15,d14 + vshr.s64 q6, q12, #63 + veor q12, q12, q7 + vand q6, q6, q5 + vld1.8 {q2}, [r7]! + veor q1, q1, q9 + vadd.u64 q13, q12, q12 + vst1.64 {q12}, [r0,:128]! + vswp d13,d12 + vshr.s64 q7, q13, #63 + veor q13, q13, q6 + vand q7, q7, q5 + vld1.8 {q3}, [r7]! + veor q2, q2, q10 + vadd.u64 q14, q13, q13 + vst1.64 {q13}, [r0,:128]! + vswp d15,d14 + vshr.s64 q6, q14, #63 + veor q14, q14, q7 + vand q6, q6, q5 + vld1.8 {q4}, [r7]! + veor q3, q3, q11 + vadd.u64 q15, q14, q14 + vst1.64 {q14}, [r0,:128]! + vswp d13,d12 + vshr.s64 q7, q15, #63 + veor q15, q15, q6 + vand q7, q7, q5 + vld1.8 {q5}, [r7]! + veor q4, q4, q12 + vadd.u64 q8, q15, q15 + vst1.64 {q15}, [r0,:128]! + vswp d15,d14 + veor q8, q8, q7 + vst1.64 {q8}, [r0,:128] @ next round tweak + + vld1.8 {q6-q7}, [r7]! + veor q5, q5, q13 +#ifndef BSAES_ASM_EXTENDED_KEY + add r4, sp, #0x90 @ pass key schedule +#else + add r4, r10, #248 @ pass key schedule +#endif + veor q6, q6, q14 + mov r5, r1 @ pass rounds + veor q7, q7, q15 + mov r0, sp + + bl _bsaes_encrypt8 + + vld1.64 {q8-q9}, [r0,:128]! + vld1.64 {q10-q11}, [r0,:128]! + veor q0, q0, q8 + vld1.64 {q12-q13}, [r0,:128]! + veor q1, q1, q9 + veor q8, q4, q10 + vst1.8 {q0-q1}, [r8]! + veor q9, q6, q11 + vld1.64 {q14-q15}, [r0,:128]! + veor q10, q3, q12 + vst1.8 {q8-q9}, [r8]! + veor q11, q7, q13 + veor q12, q2, q14 + vst1.8 {q10-q11}, [r8]! + veor q13, q5, q15 + vst1.8 {q12-q13}, [r8]! + + vld1.64 {q8}, [r0,:128] @ next round tweak + + subs r9, #0x80 + bpl .Lxts_enc_loop + +.Lxts_enc_short: + adds r9, #0x70 + bmi .Lxts_enc_done + + vldmia r2, {q5} @ load XTS magic + vshr.s64 q7, q8, #63 + mov r0, sp + vand q7, q7, q5 + vadd.u64 q9, q8, q8 + vst1.64 {q8}, [r0,:128]! + vswp d15,d14 + vshr.s64 q6, q9, #63 + veor q9, q9, q7 + vand q6, q6, q5 + vadd.u64 q10, q9, q9 + vst1.64 {q9}, [r0,:128]! + vswp d13,d12 + vshr.s64 q7, q10, #63 + veor q10, q10, q6 + vand q7, q7, q5 + vld1.8 {q0}, [r7]! + subs r9, #0x10 + bmi .Lxts_enc_1 + vadd.u64 q11, q10, q10 + vst1.64 {q10}, [r0,:128]! + vswp d15,d14 + vshr.s64 q6, q11, #63 + veor q11, q11, q7 + vand q6, q6, q5 + vld1.8 {q1}, [r7]! + subs r9, #0x10 + bmi .Lxts_enc_2 + veor q0, q0, q8 + vadd.u64 q12, q11, q11 + vst1.64 {q11}, [r0,:128]! + vswp d13,d12 + vshr.s64 q7, q12, #63 + veor q12, q12, q6 + vand q7, q7, q5 + vld1.8 {q2}, [r7]! + subs r9, #0x10 + bmi .Lxts_enc_3 + veor q1, q1, q9 + vadd.u64 q13, q12, q12 + vst1.64 {q12}, [r0,:128]! + vswp d15,d14 + vshr.s64 q6, q13, #63 + veor q13, q13, q7 + vand q6, q6, q5 + vld1.8 {q3}, [r7]! + subs r9, #0x10 + bmi .Lxts_enc_4 + veor q2, q2, q10 + vadd.u64 q14, q13, q13 + vst1.64 {q13}, [r0,:128]! + vswp d13,d12 + vshr.s64 q7, q14, #63 + veor q14, q14, q6 + vand q7, q7, q5 + vld1.8 {q4}, [r7]! + subs r9, #0x10 + bmi .Lxts_enc_5 + veor q3, q3, q11 + vadd.u64 q15, q14, q14 + vst1.64 {q14}, [r0,:128]! + vswp d15,d14 + vshr.s64 q6, q15, #63 + veor q15, q15, q7 + vand q6, q6, q5 + vld1.8 {q5}, [r7]! + subs r9, #0x10 + bmi .Lxts_enc_6 + veor q4, q4, q12 + sub r9, #0x10 + vst1.64 {q15}, [r0,:128] @ next round tweak + + vld1.8 {q6}, [r7]! + veor q5, q5, q13 +#ifndef BSAES_ASM_EXTENDED_KEY + add r4, sp, #0x90 @ pass key schedule +#else + add r4, r10, #248 @ pass key schedule +#endif + veor q6, q6, q14 + mov r5, r1 @ pass rounds + mov r0, sp + + bl _bsaes_encrypt8 + + vld1.64 {q8-q9}, [r0,:128]! + vld1.64 {q10-q11}, [r0,:128]! + veor q0, q0, q8 + vld1.64 {q12-q13}, [r0,:128]! + veor q1, q1, q9 + veor q8, q4, q10 + vst1.8 {q0-q1}, [r8]! + veor q9, q6, q11 + vld1.64 {q14}, [r0,:128]! + veor q10, q3, q12 + vst1.8 {q8-q9}, [r8]! + veor q11, q7, q13 + veor q12, q2, q14 + vst1.8 {q10-q11}, [r8]! + vst1.8 {q12}, [r8]! + + vld1.64 {q8}, [r0,:128] @ next round tweak + b .Lxts_enc_done +.align 4 +.Lxts_enc_6: + vst1.64 {q14}, [r0,:128] @ next round tweak + + veor q4, q4, q12 +#ifndef BSAES_ASM_EXTENDED_KEY + add r4, sp, #0x90 @ pass key schedule +#else + add r4, r10, #248 @ pass key schedule +#endif + veor q5, q5, q13 + mov r5, r1 @ pass rounds + mov r0, sp + + bl _bsaes_encrypt8 + + vld1.64 {q8-q9}, [r0,:128]! + vld1.64 {q10-q11}, [r0,:128]! + veor q0, q0, q8 + vld1.64 {q12-q13}, [r0,:128]! + veor q1, q1, q9 + veor q8, q4, q10 + vst1.8 {q0-q1}, [r8]! + veor q9, q6, q11 + veor q10, q3, q12 + vst1.8 {q8-q9}, [r8]! + veor q11, q7, q13 + vst1.8 {q10-q11}, [r8]! + + vld1.64 {q8}, [r0,:128] @ next round tweak + b .Lxts_enc_done + +@ put this in range for both ARM and Thumb mode adr instructions +.align 5 +.Lxts_magic: + .quad 1, 0x87 + +.align 5 +.Lxts_enc_5: + vst1.64 {q13}, [r0,:128] @ next round tweak + + veor q3, q3, q11 +#ifndef BSAES_ASM_EXTENDED_KEY + add r4, sp, #0x90 @ pass key schedule +#else + add r4, r10, #248 @ pass key schedule +#endif + veor q4, q4, q12 + mov r5, r1 @ pass rounds + mov r0, sp + + bl _bsaes_encrypt8 + + vld1.64 {q8-q9}, [r0,:128]! + vld1.64 {q10-q11}, [r0,:128]! + veor q0, q0, q8 + vld1.64 {q12}, [r0,:128]! + veor q1, q1, q9 + veor q8, q4, q10 + vst1.8 {q0-q1}, [r8]! + veor q9, q6, q11 + veor q10, q3, q12 + vst1.8 {q8-q9}, [r8]! + vst1.8 {q10}, [r8]! + + vld1.64 {q8}, [r0,:128] @ next round tweak + b .Lxts_enc_done +.align 4 +.Lxts_enc_4: + vst1.64 {q12}, [r0,:128] @ next round tweak + + veor q2, q2, q10 +#ifndef BSAES_ASM_EXTENDED_KEY + add r4, sp, #0x90 @ pass key schedule +#else + add r4, r10, #248 @ pass key schedule +#endif + veor q3, q3, q11 + mov r5, r1 @ pass rounds + mov r0, sp + + bl _bsaes_encrypt8 + + vld1.64 {q8-q9}, [r0,:128]! + vld1.64 {q10-q11}, [r0,:128]! + veor q0, q0, q8 + veor q1, q1, q9 + veor q8, q4, q10 + vst1.8 {q0-q1}, [r8]! + veor q9, q6, q11 + vst1.8 {q8-q9}, [r8]! + + vld1.64 {q8}, [r0,:128] @ next round tweak + b .Lxts_enc_done +.align 4 +.Lxts_enc_3: + vst1.64 {q11}, [r0,:128] @ next round tweak + + veor q1, q1, q9 +#ifndef BSAES_ASM_EXTENDED_KEY + add r4, sp, #0x90 @ pass key schedule +#else + add r4, r10, #248 @ pass key schedule +#endif + veor q2, q2, q10 + mov r5, r1 @ pass rounds + mov r0, sp + + bl _bsaes_encrypt8 + + vld1.64 {q8-q9}, [r0,:128]! + vld1.64 {q10}, [r0,:128]! + veor q0, q0, q8 + veor q1, q1, q9 + veor q8, q4, q10 + vst1.8 {q0-q1}, [r8]! + vst1.8 {q8}, [r8]! + + vld1.64 {q8}, [r0,:128] @ next round tweak + b .Lxts_enc_done +.align 4 +.Lxts_enc_2: + vst1.64 {q10}, [r0,:128] @ next round tweak + + veor q0, q0, q8 +#ifndef BSAES_ASM_EXTENDED_KEY + add r4, sp, #0x90 @ pass key schedule +#else + add r4, r10, #248 @ pass key schedule +#endif + veor q1, q1, q9 + mov r5, r1 @ pass rounds + mov r0, sp + + bl _bsaes_encrypt8 + + vld1.64 {q8-q9}, [r0,:128]! + veor q0, q0, q8 + veor q1, q1, q9 + vst1.8 {q0-q1}, [r8]! + + vld1.64 {q8}, [r0,:128] @ next round tweak + b .Lxts_enc_done +.align 4 +.Lxts_enc_1: + mov r0, sp + veor q0, q8 + mov r1, sp + vst1.8 {q0}, [sp,:128] + mov r2, r10 + mov r4, r3 @ preserve fp + + bl AES_encrypt + + vld1.8 {q0}, [sp,:128] + veor q0, q0, q8 + vst1.8 {q0}, [r8]! + mov r3, r4 + + vmov q8, q9 @ next round tweak + +.Lxts_enc_done: +#ifndef XTS_CHAIN_TWEAK + adds r9, #0x10 + beq .Lxts_enc_ret + sub r6, r8, #0x10 + +.Lxts_enc_steal: + ldrb r0, [r7], #1 + ldrb r1, [r8, #-0x10] + strb r0, [r8, #-0x10] + strb r1, [r8], #1 + + subs r9, #1 + bhi .Lxts_enc_steal + + vld1.8 {q0}, [r6] + mov r0, sp + veor q0, q0, q8 + mov r1, sp + vst1.8 {q0}, [sp,:128] + mov r2, r10 + mov r4, r3 @ preserve fp + + bl AES_encrypt + + vld1.8 {q0}, [sp,:128] + veor q0, q0, q8 + vst1.8 {q0}, [r6] + mov r3, r4 +#endif + +.Lxts_enc_ret: + bic r0, r3, #0xf + vmov.i32 q0, #0 + vmov.i32 q1, #0 +#ifdef XTS_CHAIN_TWEAK + ldr r1, [r3, #0x20+VFP_ABI_FRAME] @ chain tweak +#endif +.Lxts_enc_bzero: @ wipe key schedule [if any] + vstmia sp!, {q0-q1} + cmp sp, r0 + bne .Lxts_enc_bzero + + mov sp, r3 +#ifdef XTS_CHAIN_TWEAK + vst1.8 {q8}, [r1] +#endif + VFP_ABI_POP + ldmia sp!, {r4-r10, pc} @ return + +.size bsaes_xts_encrypt,.-bsaes_xts_encrypt + +.globl bsaes_xts_decrypt +.type bsaes_xts_decrypt,%function +.align 4 +bsaes_xts_decrypt: + mov ip, sp + stmdb sp!, {r4-r10, lr} @ 0x20 + VFP_ABI_PUSH + mov r6, sp @ future r3 + + mov r7, r0 + mov r8, r1 + mov r9, r2 + mov r10, r3 + + sub r0, sp, #0x10 @ 0x10 + bic r0, #0xf @ align at 16 bytes + mov sp, r0 + +#ifdef XTS_CHAIN_TWEAK + ldr r0, [ip] @ pointer to input tweak +#else + @ generate initial tweak + ldr r0, [ip, #4] @ iv[] + mov r1, sp + ldr r2, [ip, #0] @ key2 + bl AES_encrypt + mov r0, sp @ pointer to initial tweak +#endif + + ldr r1, [r10, #240] @ get # of rounds + mov r3, r6 +#ifndef BSAES_ASM_EXTENDED_KEY + @ allocate the key schedule on the stack + sub r12, sp, r1, lsl#7 @ 128 bytes per inner round key + @ add r12, #96 @ size of bit-sliced key schedule + sub r12, #48 @ place for tweak[9] + + @ populate the key schedule + mov r4, r10 @ pass key + mov r5, r1 @ pass # of rounds + mov sp, r12 + add r12, #0x90 @ pass key schedule + bl _bsaes_key_convert + add r4, sp, #0x90 + vldmia r4, {q6} + vstmia r12, {q15} @ save last round key + veor q7, q7, q6 @ fix up round 0 key + vstmia r4, {q7} +#else + ldr r12, [r10, #244] + eors r12, #1 + beq 0f + + str r12, [r10, #244] + mov r4, r10 @ pass key + mov r5, r1 @ pass # of rounds + add r12, r10, #248 @ pass key schedule + bl _bsaes_key_convert + add r4, r10, #248 + vldmia r4, {q6} + vstmia r12, {q15} @ save last round key + veor q7, q7, q6 @ fix up round 0 key + vstmia r4, {q7} + +.align 2 +0: sub sp, #0x90 @ place for tweak[9] +#endif + vld1.8 {q8}, [r0] @ initial tweak + adr r2, .Lxts_magic + + tst r9, #0xf @ if not multiple of 16 + it ne @ Thumb2 thing, sanity check in ARM + subne r9, #0x10 @ subtract another 16 bytes + subs r9, #0x80 + + blo .Lxts_dec_short + b .Lxts_dec_loop + +.align 4 +.Lxts_dec_loop: + vldmia r2, {q5} @ load XTS magic + vshr.s64 q6, q8, #63 + mov r0, sp + vand q6, q6, q5 + vadd.u64 q9, q8, q8 + vst1.64 {q8}, [r0,:128]! + vswp d13,d12 + vshr.s64 q7, q9, #63 + veor q9, q9, q6 + vand q7, q7, q5 + vadd.u64 q10, q9, q9 + vst1.64 {q9}, [r0,:128]! + vswp d15,d14 + vshr.s64 q6, q10, #63 + veor q10, q10, q7 + vand q6, q6, q5 + vld1.8 {q0}, [r7]! + vadd.u64 q11, q10, q10 + vst1.64 {q10}, [r0,:128]! + vswp d13,d12 + vshr.s64 q7, q11, #63 + veor q11, q11, q6 + vand q7, q7, q5 + vld1.8 {q1}, [r7]! + veor q0, q0, q8 + vadd.u64 q12, q11, q11 + vst1.64 {q11}, [r0,:128]! + vswp d15,d14 + vshr.s64 q6, q12, #63 + veor q12, q12, q7 + vand q6, q6, q5 + vld1.8 {q2}, [r7]! + veor q1, q1, q9 + vadd.u64 q13, q12, q12 + vst1.64 {q12}, [r0,:128]! + vswp d13,d12 + vshr.s64 q7, q13, #63 + veor q13, q13, q6 + vand q7, q7, q5 + vld1.8 {q3}, [r7]! + veor q2, q2, q10 + vadd.u64 q14, q13, q13 + vst1.64 {q13}, [r0,:128]! + vswp d15,d14 + vshr.s64 q6, q14, #63 + veor q14, q14, q7 + vand q6, q6, q5 + vld1.8 {q4}, [r7]! + veor q3, q3, q11 + vadd.u64 q15, q14, q14 + vst1.64 {q14}, [r0,:128]! + vswp d13,d12 + vshr.s64 q7, q15, #63 + veor q15, q15, q6 + vand q7, q7, q5 + vld1.8 {q5}, [r7]! + veor q4, q4, q12 + vadd.u64 q8, q15, q15 + vst1.64 {q15}, [r0,:128]! + vswp d15,d14 + veor q8, q8, q7 + vst1.64 {q8}, [r0,:128] @ next round tweak + + vld1.8 {q6-q7}, [r7]! + veor q5, q5, q13 +#ifndef BSAES_ASM_EXTENDED_KEY + add r4, sp, #0x90 @ pass key schedule +#else + add r4, r10, #248 @ pass key schedule +#endif + veor q6, q6, q14 + mov r5, r1 @ pass rounds + veor q7, q7, q15 + mov r0, sp + + bl _bsaes_decrypt8 + + vld1.64 {q8-q9}, [r0,:128]! + vld1.64 {q10-q11}, [r0,:128]! + veor q0, q0, q8 + vld1.64 {q12-q13}, [r0,:128]! + veor q1, q1, q9 + veor q8, q6, q10 + vst1.8 {q0-q1}, [r8]! + veor q9, q4, q11 + vld1.64 {q14-q15}, [r0,:128]! + veor q10, q2, q12 + vst1.8 {q8-q9}, [r8]! + veor q11, q7, q13 + veor q12, q3, q14 + vst1.8 {q10-q11}, [r8]! + veor q13, q5, q15 + vst1.8 {q12-q13}, [r8]! + + vld1.64 {q8}, [r0,:128] @ next round tweak + + subs r9, #0x80 + bpl .Lxts_dec_loop + +.Lxts_dec_short: + adds r9, #0x70 + bmi .Lxts_dec_done + + vldmia r2, {q5} @ load XTS magic + vshr.s64 q7, q8, #63 + mov r0, sp + vand q7, q7, q5 + vadd.u64 q9, q8, q8 + vst1.64 {q8}, [r0,:128]! + vswp d15,d14 + vshr.s64 q6, q9, #63 + veor q9, q9, q7 + vand q6, q6, q5 + vadd.u64 q10, q9, q9 + vst1.64 {q9}, [r0,:128]! + vswp d13,d12 + vshr.s64 q7, q10, #63 + veor q10, q10, q6 + vand q7, q7, q5 + vld1.8 {q0}, [r7]! + subs r9, #0x10 + bmi .Lxts_dec_1 + vadd.u64 q11, q10, q10 + vst1.64 {q10}, [r0,:128]! + vswp d15,d14 + vshr.s64 q6, q11, #63 + veor q11, q11, q7 + vand q6, q6, q5 + vld1.8 {q1}, [r7]! + subs r9, #0x10 + bmi .Lxts_dec_2 + veor q0, q0, q8 + vadd.u64 q12, q11, q11 + vst1.64 {q11}, [r0,:128]! + vswp d13,d12 + vshr.s64 q7, q12, #63 + veor q12, q12, q6 + vand q7, q7, q5 + vld1.8 {q2}, [r7]! + subs r9, #0x10 + bmi .Lxts_dec_3 + veor q1, q1, q9 + vadd.u64 q13, q12, q12 + vst1.64 {q12}, [r0,:128]! + vswp d15,d14 + vshr.s64 q6, q13, #63 + veor q13, q13, q7 + vand q6, q6, q5 + vld1.8 {q3}, [r7]! + subs r9, #0x10 + bmi .Lxts_dec_4 + veor q2, q2, q10 + vadd.u64 q14, q13, q13 + vst1.64 {q13}, [r0,:128]! + vswp d13,d12 + vshr.s64 q7, q14, #63 + veor q14, q14, q6 + vand q7, q7, q5 + vld1.8 {q4}, [r7]! + subs r9, #0x10 + bmi .Lxts_dec_5 + veor q3, q3, q11 + vadd.u64 q15, q14, q14 + vst1.64 {q14}, [r0,:128]! + vswp d15,d14 + vshr.s64 q6, q15, #63 + veor q15, q15, q7 + vand q6, q6, q5 + vld1.8 {q5}, [r7]! + subs r9, #0x10 + bmi .Lxts_dec_6 + veor q4, q4, q12 + sub r9, #0x10 + vst1.64 {q15}, [r0,:128] @ next round tweak + + vld1.8 {q6}, [r7]! + veor q5, q5, q13 +#ifndef BSAES_ASM_EXTENDED_KEY + add r4, sp, #0x90 @ pass key schedule +#else + add r4, r10, #248 @ pass key schedule +#endif + veor q6, q6, q14 + mov r5, r1 @ pass rounds + mov r0, sp + + bl _bsaes_decrypt8 + + vld1.64 {q8-q9}, [r0,:128]! + vld1.64 {q10-q11}, [r0,:128]! + veor q0, q0, q8 + vld1.64 {q12-q13}, [r0,:128]! + veor q1, q1, q9 + veor q8, q6, q10 + vst1.8 {q0-q1}, [r8]! + veor q9, q4, q11 + vld1.64 {q14}, [r0,:128]! + veor q10, q2, q12 + vst1.8 {q8-q9}, [r8]! + veor q11, q7, q13 + veor q12, q3, q14 + vst1.8 {q10-q11}, [r8]! + vst1.8 {q12}, [r8]! + + vld1.64 {q8}, [r0,:128] @ next round tweak + b .Lxts_dec_done +.align 4 +.Lxts_dec_6: + vst1.64 {q14}, [r0,:128] @ next round tweak + + veor q4, q4, q12 +#ifndef BSAES_ASM_EXTENDED_KEY + add r4, sp, #0x90 @ pass key schedule +#else + add r4, r10, #248 @ pass key schedule +#endif + veor q5, q5, q13 + mov r5, r1 @ pass rounds + mov r0, sp + + bl _bsaes_decrypt8 + + vld1.64 {q8-q9}, [r0,:128]! + vld1.64 {q10-q11}, [r0,:128]! + veor q0, q0, q8 + vld1.64 {q12-q13}, [r0,:128]! + veor q1, q1, q9 + veor q8, q6, q10 + vst1.8 {q0-q1}, [r8]! + veor q9, q4, q11 + veor q10, q2, q12 + vst1.8 {q8-q9}, [r8]! + veor q11, q7, q13 + vst1.8 {q10-q11}, [r8]! + + vld1.64 {q8}, [r0,:128] @ next round tweak + b .Lxts_dec_done +.align 4 +.Lxts_dec_5: + vst1.64 {q13}, [r0,:128] @ next round tweak + + veor q3, q3, q11 +#ifndef BSAES_ASM_EXTENDED_KEY + add r4, sp, #0x90 @ pass key schedule +#else + add r4, r10, #248 @ pass key schedule +#endif + veor q4, q4, q12 + mov r5, r1 @ pass rounds + mov r0, sp + + bl _bsaes_decrypt8 + + vld1.64 {q8-q9}, [r0,:128]! + vld1.64 {q10-q11}, [r0,:128]! + veor q0, q0, q8 + vld1.64 {q12}, [r0,:128]! + veor q1, q1, q9 + veor q8, q6, q10 + vst1.8 {q0-q1}, [r8]! + veor q9, q4, q11 + veor q10, q2, q12 + vst1.8 {q8-q9}, [r8]! + vst1.8 {q10}, [r8]! + + vld1.64 {q8}, [r0,:128] @ next round tweak + b .Lxts_dec_done +.align 4 +.Lxts_dec_4: + vst1.64 {q12}, [r0,:128] @ next round tweak + + veor q2, q2, q10 +#ifndef BSAES_ASM_EXTENDED_KEY + add r4, sp, #0x90 @ pass key schedule +#else + add r4, r10, #248 @ pass key schedule +#endif + veor q3, q3, q11 + mov r5, r1 @ pass rounds + mov r0, sp + + bl _bsaes_decrypt8 + + vld1.64 {q8-q9}, [r0,:128]! + vld1.64 {q10-q11}, [r0,:128]! + veor q0, q0, q8 + veor q1, q1, q9 + veor q8, q6, q10 + vst1.8 {q0-q1}, [r8]! + veor q9, q4, q11 + vst1.8 {q8-q9}, [r8]! + + vld1.64 {q8}, [r0,:128] @ next round tweak + b .Lxts_dec_done +.align 4 +.Lxts_dec_3: + vst1.64 {q11}, [r0,:128] @ next round tweak + + veor q1, q1, q9 +#ifndef BSAES_ASM_EXTENDED_KEY + add r4, sp, #0x90 @ pass key schedule +#else + add r4, r10, #248 @ pass key schedule +#endif + veor q2, q2, q10 + mov r5, r1 @ pass rounds + mov r0, sp + + bl _bsaes_decrypt8 + + vld1.64 {q8-q9}, [r0,:128]! + vld1.64 {q10}, [r0,:128]! + veor q0, q0, q8 + veor q1, q1, q9 + veor q8, q6, q10 + vst1.8 {q0-q1}, [r8]! + vst1.8 {q8}, [r8]! + + vld1.64 {q8}, [r0,:128] @ next round tweak + b .Lxts_dec_done +.align 4 +.Lxts_dec_2: + vst1.64 {q10}, [r0,:128] @ next round tweak + + veor q0, q0, q8 +#ifndef BSAES_ASM_EXTENDED_KEY + add r4, sp, #0x90 @ pass key schedule +#else + add r4, r10, #248 @ pass key schedule +#endif + veor q1, q1, q9 + mov r5, r1 @ pass rounds + mov r0, sp + + bl _bsaes_decrypt8 + + vld1.64 {q8-q9}, [r0,:128]! + veor q0, q0, q8 + veor q1, q1, q9 + vst1.8 {q0-q1}, [r8]! + + vld1.64 {q8}, [r0,:128] @ next round tweak + b .Lxts_dec_done +.align 4 +.Lxts_dec_1: + mov r0, sp + veor q0, q8 + mov r1, sp + vst1.8 {q0}, [sp,:128] + mov r2, r10 + mov r4, r3 @ preserve fp + mov r5, r2 @ preserve magic + + bl AES_decrypt + + vld1.8 {q0}, [sp,:128] + veor q0, q0, q8 + vst1.8 {q0}, [r8]! + mov r3, r4 + mov r2, r5 + + vmov q8, q9 @ next round tweak + +.Lxts_dec_done: +#ifndef XTS_CHAIN_TWEAK + adds r9, #0x10 + beq .Lxts_dec_ret + + @ calculate one round of extra tweak for the stolen ciphertext + vldmia r2, {q5} + vshr.s64 q6, q8, #63 + vand q6, q6, q5 + vadd.u64 q9, q8, q8 + vswp d13,d12 + veor q9, q9, q6 + + @ perform the final decryption with the last tweak value + vld1.8 {q0}, [r7]! + mov r0, sp + veor q0, q0, q9 + mov r1, sp + vst1.8 {q0}, [sp,:128] + mov r2, r10 + mov r4, r3 @ preserve fp + + bl AES_decrypt + + vld1.8 {q0}, [sp,:128] + veor q0, q0, q9 + vst1.8 {q0}, [r8] + + mov r6, r8 +.Lxts_dec_steal: + ldrb r1, [r8] + ldrb r0, [r7], #1 + strb r1, [r8, #0x10] + strb r0, [r8], #1 + + subs r9, #1 + bhi .Lxts_dec_steal + + vld1.8 {q0}, [r6] + mov r0, sp + veor q0, q8 + mov r1, sp + vst1.8 {q0}, [sp,:128] + mov r2, r10 + + bl AES_decrypt + + vld1.8 {q0}, [sp,:128] + veor q0, q0, q8 + vst1.8 {q0}, [r6] + mov r3, r4 +#endif + +.Lxts_dec_ret: + bic r0, r3, #0xf + vmov.i32 q0, #0 + vmov.i32 q1, #0 +#ifdef XTS_CHAIN_TWEAK + ldr r1, [r3, #0x20+VFP_ABI_FRAME] @ chain tweak +#endif +.Lxts_dec_bzero: @ wipe key schedule [if any] + vstmia sp!, {q0-q1} + cmp sp, r0 + bne .Lxts_dec_bzero + + mov sp, r3 +#ifdef XTS_CHAIN_TWEAK + vst1.8 {q8}, [r1] +#endif + VFP_ABI_POP + ldmia sp!, {r4-r10, pc} @ return + +.size bsaes_xts_decrypt,.-bsaes_xts_decrypt +#endif diff --git a/arch/arm/crypto/aesbs-glue.c b/arch/arm/crypto/aesbs-glue.c new file mode 100644 index 000000000000..4522366da759 --- /dev/null +++ b/arch/arm/crypto/aesbs-glue.c @@ -0,0 +1,434 @@ +/* + * linux/arch/arm/crypto/aesbs-glue.c - glue code for NEON bit sliced AES + * + * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <asm/neon.h> +#include <crypto/aes.h> +#include <crypto/ablk_helper.h> +#include <crypto/algapi.h> +#include <linux/module.h> + +#include "aes_glue.h" + +#define BIT_SLICED_KEY_MAXSIZE (128 * (AES_MAXNR - 1) + 2 * AES_BLOCK_SIZE) + +struct BS_KEY { + struct AES_KEY rk; + int converted; + u8 __aligned(8) bs[BIT_SLICED_KEY_MAXSIZE]; +} __aligned(8); + +asmlinkage void bsaes_enc_key_convert(u8 out[], struct AES_KEY const *in); +asmlinkage void bsaes_dec_key_convert(u8 out[], struct AES_KEY const *in); + +asmlinkage void bsaes_cbc_encrypt(u8 const in[], u8 out[], u32 bytes, + struct BS_KEY *key, u8 iv[]); + +asmlinkage void bsaes_ctr32_encrypt_blocks(u8 const in[], u8 out[], u32 blocks, + struct BS_KEY *key, u8 const iv[]); + +asmlinkage void bsaes_xts_encrypt(u8 const in[], u8 out[], u32 bytes, + struct BS_KEY *key, u8 tweak[]); + +asmlinkage void bsaes_xts_decrypt(u8 const in[], u8 out[], u32 bytes, + struct BS_KEY *key, u8 tweak[]); + +struct aesbs_cbc_ctx { + struct AES_KEY enc; + struct BS_KEY dec; +}; + +struct aesbs_ctr_ctx { + struct BS_KEY enc; +}; + +struct aesbs_xts_ctx { + struct BS_KEY enc; + struct BS_KEY dec; + struct AES_KEY twkey; +}; + +static int aesbs_cbc_set_key(struct crypto_tfm *tfm, const u8 *in_key, + unsigned int key_len) +{ + struct aesbs_cbc_ctx *ctx = crypto_tfm_ctx(tfm); + int bits = key_len * 8; + + if (private_AES_set_encrypt_key(in_key, bits, &ctx->enc)) { + tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN; + return -EINVAL; + } + ctx->dec.rk = ctx->enc; + private_AES_set_decrypt_key(in_key, bits, &ctx->dec.rk); + ctx->dec.converted = 0; + return 0; +} + +static int aesbs_ctr_set_key(struct crypto_tfm *tfm, const u8 *in_key, + unsigned int key_len) +{ + struct aesbs_ctr_ctx *ctx = crypto_tfm_ctx(tfm); + int bits = key_len * 8; + + if (private_AES_set_encrypt_key(in_key, bits, &ctx->enc.rk)) { + tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN; + return -EINVAL; + } + ctx->enc.converted = 0; + return 0; +} + +static int aesbs_xts_set_key(struct crypto_tfm *tfm, const u8 *in_key, + unsigned int key_len) +{ + struct aesbs_xts_ctx *ctx = crypto_tfm_ctx(tfm); + int bits = key_len * 4; + + if (private_AES_set_encrypt_key(in_key, bits, &ctx->enc.rk)) { + tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN; + return -EINVAL; + } + ctx->dec.rk = ctx->enc.rk; + private_AES_set_decrypt_key(in_key, bits, &ctx->dec.rk); + private_AES_set_encrypt_key(in_key + key_len / 2, bits, &ctx->twkey); + ctx->enc.converted = ctx->dec.converted = 0; + return 0; +} + +static int aesbs_cbc_encrypt(struct blkcipher_desc *desc, + struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) +{ + struct aesbs_cbc_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + struct blkcipher_walk walk; + int err; + + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt(desc, &walk); + + while (walk.nbytes) { + u32 blocks = walk.nbytes / AES_BLOCK_SIZE; + u8 *src = walk.src.virt.addr; + + if (walk.dst.virt.addr == walk.src.virt.addr) { + u8 *iv = walk.iv; + + do { + crypto_xor(src, iv, AES_BLOCK_SIZE); + AES_encrypt(src, src, &ctx->enc); + iv = src; + src += AES_BLOCK_SIZE; + } while (--blocks); + memcpy(walk.iv, iv, AES_BLOCK_SIZE); + } else { + u8 *dst = walk.dst.virt.addr; + + do { + crypto_xor(walk.iv, src, AES_BLOCK_SIZE); + AES_encrypt(walk.iv, dst, &ctx->enc); + memcpy(walk.iv, dst, AES_BLOCK_SIZE); + src += AES_BLOCK_SIZE; + dst += AES_BLOCK_SIZE; + } while (--blocks); + } + err = blkcipher_walk_done(desc, &walk, 0); + } + return err; +} + +static int aesbs_cbc_decrypt(struct blkcipher_desc *desc, + struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) +{ + struct aesbs_cbc_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + struct blkcipher_walk walk; + int err; + + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt_block(desc, &walk, 8 * AES_BLOCK_SIZE); + + while ((walk.nbytes / AES_BLOCK_SIZE) >= 8) { + kernel_neon_begin(); + bsaes_cbc_encrypt(walk.src.virt.addr, walk.dst.virt.addr, + walk.nbytes, &ctx->dec, walk.iv); + kernel_neon_end(); + err = blkcipher_walk_done(desc, &walk, 0); + } + while (walk.nbytes) { + u32 blocks = walk.nbytes / AES_BLOCK_SIZE; + u8 *dst = walk.dst.virt.addr; + u8 *src = walk.src.virt.addr; + u8 bk[2][AES_BLOCK_SIZE]; + u8 *iv = walk.iv; + + do { + if (walk.dst.virt.addr == walk.src.virt.addr) + memcpy(bk[blocks & 1], src, AES_BLOCK_SIZE); + + AES_decrypt(src, dst, &ctx->dec.rk); + crypto_xor(dst, iv, AES_BLOCK_SIZE); + + if (walk.dst.virt.addr == walk.src.virt.addr) + iv = bk[blocks & 1]; + else + iv = src; + + dst += AES_BLOCK_SIZE; + src += AES_BLOCK_SIZE; + } while (--blocks); + err = blkcipher_walk_done(desc, &walk, 0); + } + return err; +} + +static void inc_be128_ctr(__be32 ctr[], u32 addend) +{ + int i; + + for (i = 3; i >= 0; i--, addend = 1) { + u32 n = be32_to_cpu(ctr[i]) + addend; + + ctr[i] = cpu_to_be32(n); + if (n >= addend) + break; + } +} + +static int aesbs_ctr_encrypt(struct blkcipher_desc *desc, + struct scatterlist *dst, struct scatterlist *src, + unsigned int nbytes) +{ + struct aesbs_ctr_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + struct blkcipher_walk walk; + u32 blocks; + int err; + + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt_block(desc, &walk, 8 * AES_BLOCK_SIZE); + + while ((blocks = walk.nbytes / AES_BLOCK_SIZE)) { + u32 tail = walk.nbytes % AES_BLOCK_SIZE; + __be32 *ctr = (__be32 *)walk.iv; + u32 headroom = UINT_MAX - be32_to_cpu(ctr[3]); + + /* avoid 32 bit counter overflow in the NEON code */ + if (unlikely(headroom < blocks)) { + blocks = headroom + 1; + tail = walk.nbytes - blocks * AES_BLOCK_SIZE; + } + kernel_neon_begin(); + bsaes_ctr32_encrypt_blocks(walk.src.virt.addr, + walk.dst.virt.addr, blocks, + &ctx->enc, walk.iv); + kernel_neon_end(); + inc_be128_ctr(ctr, blocks); + + nbytes -= blocks * AES_BLOCK_SIZE; + if (nbytes && nbytes == tail && nbytes <= AES_BLOCK_SIZE) + break; + + err = blkcipher_walk_done(desc, &walk, tail); + } + if (walk.nbytes) { + u8 *tdst = walk.dst.virt.addr + blocks * AES_BLOCK_SIZE; + u8 *tsrc = walk.src.virt.addr + blocks * AES_BLOCK_SIZE; + u8 ks[AES_BLOCK_SIZE]; + + AES_encrypt(walk.iv, ks, &ctx->enc.rk); + if (tdst != tsrc) + memcpy(tdst, tsrc, nbytes); + crypto_xor(tdst, ks, nbytes); + err = blkcipher_walk_done(desc, &walk, 0); + } + return err; +} + +static int aesbs_xts_encrypt(struct blkcipher_desc *desc, + struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) +{ + struct aesbs_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + struct blkcipher_walk walk; + int err; + + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt_block(desc, &walk, 8 * AES_BLOCK_SIZE); + + /* generate the initial tweak */ + AES_encrypt(walk.iv, walk.iv, &ctx->twkey); + + while (walk.nbytes) { + kernel_neon_begin(); + bsaes_xts_encrypt(walk.src.virt.addr, walk.dst.virt.addr, + walk.nbytes, &ctx->enc, walk.iv); + kernel_neon_end(); + err = blkcipher_walk_done(desc, &walk, 0); + } + return err; +} + +static int aesbs_xts_decrypt(struct blkcipher_desc *desc, + struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) +{ + struct aesbs_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm); + struct blkcipher_walk walk; + int err; + + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt_block(desc, &walk, 8 * AES_BLOCK_SIZE); + + /* generate the initial tweak */ + AES_encrypt(walk.iv, walk.iv, &ctx->twkey); + + while (walk.nbytes) { + kernel_neon_begin(); + bsaes_xts_decrypt(walk.src.virt.addr, walk.dst.virt.addr, + walk.nbytes, &ctx->dec, walk.iv); + kernel_neon_end(); + err = blkcipher_walk_done(desc, &walk, 0); + } + return err; +} + +static struct crypto_alg aesbs_algs[] = { { + .cra_name = "__cbc-aes-neonbs", + .cra_driver_name = "__driver-cbc-aes-neonbs", + .cra_priority = 0, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct aesbs_cbc_ctx), + .cra_alignmask = 7, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_blkcipher = { + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .setkey = aesbs_cbc_set_key, + .encrypt = aesbs_cbc_encrypt, + .decrypt = aesbs_cbc_decrypt, + }, +}, { + .cra_name = "__ctr-aes-neonbs", + .cra_driver_name = "__driver-ctr-aes-neonbs", + .cra_priority = 0, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = 1, + .cra_ctxsize = sizeof(struct aesbs_ctr_ctx), + .cra_alignmask = 7, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_blkcipher = { + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .setkey = aesbs_ctr_set_key, + .encrypt = aesbs_ctr_encrypt, + .decrypt = aesbs_ctr_encrypt, + }, +}, { + .cra_name = "__xts-aes-neonbs", + .cra_driver_name = "__driver-xts-aes-neonbs", + .cra_priority = 0, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct aesbs_xts_ctx), + .cra_alignmask = 7, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_blkcipher = { + .min_keysize = 2 * AES_MIN_KEY_SIZE, + .max_keysize = 2 * AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .setkey = aesbs_xts_set_key, + .encrypt = aesbs_xts_encrypt, + .decrypt = aesbs_xts_decrypt, + }, +}, { + .cra_name = "cbc(aes)", + .cra_driver_name = "cbc-aes-neonbs", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct async_helper_ctx), + .cra_alignmask = 7, + .cra_type = &crypto_ablkcipher_type, + .cra_module = THIS_MODULE, + .cra_init = ablk_init, + .cra_exit = ablk_exit, + .cra_ablkcipher = { + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .setkey = ablk_set_key, + .encrypt = __ablk_encrypt, + .decrypt = ablk_decrypt, + } +}, { + .cra_name = "ctr(aes)", + .cra_driver_name = "ctr-aes-neonbs", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC, + .cra_blocksize = 1, + .cra_ctxsize = sizeof(struct async_helper_ctx), + .cra_alignmask = 7, + .cra_type = &crypto_ablkcipher_type, + .cra_module = THIS_MODULE, + .cra_init = ablk_init, + .cra_exit = ablk_exit, + .cra_ablkcipher = { + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .setkey = ablk_set_key, + .encrypt = ablk_encrypt, + .decrypt = ablk_decrypt, + } +}, { + .cra_name = "xts(aes)", + .cra_driver_name = "xts-aes-neonbs", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct async_helper_ctx), + .cra_alignmask = 7, + .cra_type = &crypto_ablkcipher_type, + .cra_module = THIS_MODULE, + .cra_init = ablk_init, + .cra_exit = ablk_exit, + .cra_ablkcipher = { + .min_keysize = 2 * AES_MIN_KEY_SIZE, + .max_keysize = 2 * AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .setkey = ablk_set_key, + .encrypt = ablk_encrypt, + .decrypt = ablk_decrypt, + } +} }; + +static int __init aesbs_mod_init(void) +{ + if (!cpu_has_neon()) + return -ENODEV; + + return crypto_register_algs(aesbs_algs, ARRAY_SIZE(aesbs_algs)); +} + +static void __exit aesbs_mod_exit(void) +{ + crypto_unregister_algs(aesbs_algs, ARRAY_SIZE(aesbs_algs)); +} + +module_init(aesbs_mod_init); +module_exit(aesbs_mod_exit); + +MODULE_DESCRIPTION("Bit sliced AES in CBC/CTR/XTS modes using NEON"); +MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>"); +MODULE_LICENSE("GPL"); diff --git a/arch/arm/crypto/bsaes-armv7.pl b/arch/arm/crypto/bsaes-armv7.pl new file mode 100644 index 000000000000..f3d96d932573 --- /dev/null +++ b/arch/arm/crypto/bsaes-armv7.pl @@ -0,0 +1,2467 @@ +#!/usr/bin/env perl + +# ==================================================================== +# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL +# project. The module is, however, dual licensed under OpenSSL and +# CRYPTOGAMS licenses depending on where you obtain it. For further +# details see http://www.openssl.org/~appro/cryptogams/. +# +# Specific modes and adaptation for Linux kernel by Ard Biesheuvel +# <ard.biesheuvel@linaro.org>. Permission to use under GPL terms is +# granted. +# ==================================================================== + +# Bit-sliced AES for ARM NEON +# +# February 2012. +# +# This implementation is direct adaptation of bsaes-x86_64 module for +# ARM NEON. Except that this module is endian-neutral [in sense that +# it can be compiled for either endianness] by courtesy of vld1.8's +# neutrality. Initial version doesn't implement interface to OpenSSL, +# only low-level primitives and unsupported entry points, just enough +# to collect performance results, which for Cortex-A8 core are: +# +# encrypt 19.5 cycles per byte processed with 128-bit key +# decrypt 22.1 cycles per byte processed with 128-bit key +# key conv. 440 cycles per 128-bit key/0.18 of 8x block +# +# Snapdragon S4 encrypts byte in 17.6 cycles and decrypts in 19.7, +# which is [much] worse than anticipated (for further details see +# http://www.openssl.org/~appro/Snapdragon-S4.html). +# +# Cortex-A15 manages in 14.2/16.1 cycles [when integer-only code +# manages in 20.0 cycles]. +# +# When comparing to x86_64 results keep in mind that NEON unit is +# [mostly] single-issue and thus can't [fully] benefit from +# instruction-level parallelism. And when comparing to aes-armv4 +# results keep in mind key schedule conversion overhead (see +# bsaes-x86_64.pl for further details)... +# +# <appro@openssl.org> + +# April-August 2013 +# +# Add CBC, CTR and XTS subroutines, adapt for kernel use. +# +# <ard.biesheuvel@linaro.org> + +while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {} +open STDOUT,">$output"; + +my ($inp,$out,$len,$key)=("r0","r1","r2","r3"); +my @XMM=map("q$_",(0..15)); + +{ +my ($key,$rounds,$const)=("r4","r5","r6"); + +sub Dlo() { shift=~m|q([1]?[0-9])|?"d".($1*2):""; } +sub Dhi() { shift=~m|q([1]?[0-9])|?"d".($1*2+1):""; } + +sub Sbox { +# input in lsb > [b0, b1, b2, b3, b4, b5, b6, b7] < msb +# output in lsb > [b0, b1, b4, b6, b3, b7, b2, b5] < msb +my @b=@_[0..7]; +my @t=@_[8..11]; +my @s=@_[12..15]; + &InBasisChange (@b); + &Inv_GF256 (@b[6,5,0,3,7,1,4,2],@t,@s); + &OutBasisChange (@b[7,1,4,2,6,5,0,3]); +} + +sub InBasisChange { +# input in lsb > [b0, b1, b2, b3, b4, b5, b6, b7] < msb +# output in lsb > [b6, b5, b0, b3, b7, b1, b4, b2] < msb +my @b=@_[0..7]; +$code.=<<___; + veor @b[2], @b[2], @b[1] + veor @b[5], @b[5], @b[6] + veor @b[3], @b[3], @b[0] + veor @b[6], @b[6], @b[2] + veor @b[5], @b[5], @b[0] + + veor @b[6], @b[6], @b[3] + veor @b[3], @b[3], @b[7] + veor @b[7], @b[7], @b[5] + veor @b[3], @b[3], @b[4] + veor @b[4], @b[4], @b[5] + + veor @b[2], @b[2], @b[7] + veor @b[3], @b[3], @b[1] + veor @b[1], @b[1], @b[5] +___ +} + +sub OutBasisChange { +# input in lsb > [b0, b1, b2, b3, b4, b5, b6, b7] < msb +# output in lsb > [b6, b1, b2, b4, b7, b0, b3, b5] < msb +my @b=@_[0..7]; +$code.=<<___; + veor @b[0], @b[0], @b[6] + veor @b[1], @b[1], @b[4] + veor @b[4], @b[4], @b[6] + veor @b[2], @b[2], @b[0] + veor @b[6], @b[6], @b[1] + + veor @b[1], @b[1], @b[5] + veor @b[5], @b[5], @b[3] + veor @b[3], @b[3], @b[7] + veor @b[7], @b[7], @b[5] + veor @b[2], @b[2], @b[5] + + veor @b[4], @b[4], @b[7] +___ +} + +sub InvSbox { +# input in lsb > [b0, b1, b2, b3, b4, b5, b6, b7] < msb +# output in lsb > [b0, b1, b6, b4, b2, b7, b3, b5] < msb +my @b=@_[0..7]; +my @t=@_[8..11]; +my @s=@_[12..15]; + &InvInBasisChange (@b); + &Inv_GF256 (@b[5,1,2,6,3,7,0,4],@t,@s); + &InvOutBasisChange (@b[3,7,0,4,5,1,2,6]); +} + +sub InvInBasisChange { # OutBasisChange in reverse (with twist) +my @b=@_[5,1,2,6,3,7,0,4]; +$code.=<<___ + veor @b[1], @b[1], @b[7] + veor @b[4], @b[4], @b[7] + + veor @b[7], @b[7], @b[5] + veor @b[1], @b[1], @b[3] + veor @b[2], @b[2], @b[5] + veor @b[3], @b[3], @b[7] + + veor @b[6], @b[6], @b[1] + veor @b[2], @b[2], @b[0] + veor @b[5], @b[5], @b[3] + veor @b[4], @b[4], @b[6] + veor @b[0], @b[0], @b[6] + veor @b[1], @b[1], @b[4] +___ +} + +sub InvOutBasisChange { # InBasisChange in reverse +my @b=@_[2,5,7,3,6,1,0,4]; +$code.=<<___; + veor @b[1], @b[1], @b[5] + veor @b[2], @b[2], @b[7] + + veor @b[3], @b[3], @b[1] + veor @b[4], @b[4], @b[5] + veor @b[7], @b[7], @b[5] + veor @b[3], @b[3], @b[4] + veor @b[5], @b[5], @b[0] + veor @b[3], @b[3], @b[7] + veor @b[6], @b[6], @b[2] + veor @b[2], @b[2], @b[1] + veor @b[6], @b[6], @b[3] + + veor @b[3], @b[3], @b[0] + veor @b[5], @b[5], @b[6] +___ +} + +sub Mul_GF4 { +#;************************************************************* +#;* Mul_GF4: Input x0-x1,y0-y1 Output x0-x1 Temp t0 (8) * +#;************************************************************* +my ($x0,$x1,$y0,$y1,$t0,$t1)=@_; +$code.=<<___; + veor $t0, $y0, $y1 + vand $t0, $t0, $x0 + veor $x0, $x0, $x1 + vand $t1, $x1, $y0 + vand $x0, $x0, $y1 + veor $x1, $t1, $t0 + veor $x0, $x0, $t1 +___ +} + +sub Mul_GF4_N { # not used, see next subroutine +# multiply and scale by N +my ($x0,$x1,$y0,$y1,$t0)=@_; +$code.=<<___; + veor $t0, $y0, $y1 + vand $t0, $t0, $x0 + veor $x0, $x0, $x1 + vand $x1, $x1, $y0 + vand $x0, $x0, $y1 + veor $x1, $x1, $x0 + veor $x0, $x0, $t0 +___ +} + +sub Mul_GF4_N_GF4 { +# interleaved Mul_GF4_N and Mul_GF4 +my ($x0,$x1,$y0,$y1,$t0, + $x2,$x3,$y2,$y3,$t1)=@_; +$code.=<<___; + veor $t0, $y0, $y1 + veor $t1, $y2, $y3 + vand $t0, $t0, $x0 + vand $t1, $t1, $x2 + veor $x0, $x0, $x1 + veor $x2, $x2, $x3 + vand $x1, $x1, $y0 + vand $x3, $x3, $y2 + vand $x0, $x0, $y1 + vand $x2, $x2, $y3 + veor $x1, $x1, $x0 + veor $x2, $x2, $x3 + veor $x0, $x0, $t0 + veor $x3, $x3, $t1 +___ +} +sub Mul_GF16_2 { +my @x=@_[0..7]; +my @y=@_[8..11]; +my @t=@_[12..15]; +$code.=<<___; + veor @t[0], @x[0], @x[2] + veor @t[1], @x[1], @x[3] +___ + &Mul_GF4 (@x[0], @x[1], @y[0], @y[1], @t[2..3]); +$code.=<<___; + veor @y[0], @y[0], @y[2] + veor @y[1], @y[1], @y[3] +___ + Mul_GF4_N_GF4 (@t[0], @t[1], @y[0], @y[1], @t[3], + @x[2], @x[3], @y[2], @y[3], @t[2]); +$code.=<<___; + veor @x[0], @x[0], @t[0] + veor @x[2], @x[2], @t[0] + veor @x[1], @x[1], @t[1] + veor @x[3], @x[3], @t[1] + + veor @t[0], @x[4], @x[6] + veor @t[1], @x[5], @x[7] +___ + &Mul_GF4_N_GF4 (@t[0], @t[1], @y[0], @y[1], @t[3], + @x[6], @x[7], @y[2], @y[3], @t[2]); +$code.=<<___; + veor @y[0], @y[0], @y[2] + veor @y[1], @y[1], @y[3] +___ + &Mul_GF4 (@x[4], @x[5], @y[0], @y[1], @t[2..3]); +$code.=<<___; + veor @x[4], @x[4], @t[0] + veor @x[6], @x[6], @t[0] + veor @x[5], @x[5], @t[1] + veor @x[7], @x[7], @t[1] +___ +} +sub Inv_GF256 { +#;******************************************************************** +#;* Inv_GF256: Input x0-x7 Output x0-x7 Temp t0-t3,s0-s3 (144) * +#;******************************************************************** +my @x=@_[0..7]; +my @t=@_[8..11]; +my @s=@_[12..15]; +# direct optimizations from hardware +$code.=<<___; + veor @t[3], @x[4], @x[6] + veor @t[2], @x[5], @x[7] + veor @t[1], @x[1], @x[3] + veor @s[1], @x[7], @x[6] + vmov @t[0], @t[2] + veor @s[0], @x[0], @x[2] + + vorr @t[2], @t[2], @t[1] + veor @s[3], @t[3], @t[0] + vand @s[2], @t[3], @s[0] + vorr @t[3], @t[3], @s[0] + veor @s[0], @s[0], @t[1] + vand @t[0], @t[0], @t[1] + veor @t[1], @x[3], @x[2] + vand @s[3], @s[3], @s[0] + vand @s[1], @s[1], @t[1] + veor @t[1], @x[4], @x[5] + veor @s[0], @x[1], @x[0] + veor @t[3], @t[3], @s[1] + veor @t[2], @t[2], @s[1] + vand @s[1], @t[1], @s[0] + vorr @t[1], @t[1], @s[0] + veor @t[3], @t[3], @s[3] + veor @t[0], @t[0], @s[1] + veor @t[2], @t[2], @s[2] + veor @t[1], @t[1], @s[3] + veor @t[0], @t[0], @s[2] + vand @s[0], @x[7], @x[3] + veor @t[1], @t[1], @s[2] + vand @s[1], @x[6], @x[2] + vand @s[2], @x[5], @x[1] + vorr @s[3], @x[4], @x[0] + veor @t[3], @t[3], @s[0] + veor @t[1], @t[1], @s[2] + veor @t[0], @t[0], @s[3] + veor @t[2], @t[2], @s[1] + + @ Inv_GF16 \t0, \t1, \t2, \t3, \s0, \s1, \s2, \s3 + + @ new smaller inversion + + vand @s[2], @t[3], @t[1] + vmov @s[0], @t[0] + + veor @s[1], @t[2], @s[2] + veor @s[3], @t[0], @s[2] + veor @s[2], @t[0], @s[2] @ @s[2]=@s[3] + + vbsl @s[1], @t[1], @t[0] + vbsl @s[3], @t[3], @t[2] + veor @t[3], @t[3], @t[2] + + vbsl @s[0], @s[1], @s[2] + vbsl @t[0], @s[2], @s[1] + + vand @s[2], @s[0], @s[3] + veor @t[1], @t[1], @t[0] + + veor @s[2], @s[2], @t[3] +___ +# output in s3, s2, s1, t1 + +# Mul_GF16_2 \x0, \x1, \x2, \x3, \x4, \x5, \x6, \x7, \t2, \t3, \t0, \t1, \s0, \s1, \s2, \s3 + +# Mul_GF16_2 \x0, \x1, \x2, \x3, \x4, \x5, \x6, \x7, \s3, \s2, \s1, \t1, \s0, \t0, \t2, \t3 + &Mul_GF16_2(@x,@s[3,2,1],@t[1],@s[0],@t[0,2,3]); + +### output msb > [x3,x2,x1,x0,x7,x6,x5,x4] < lsb +} + +# AES linear components + +sub ShiftRows { +my @x=@_[0..7]; +my @t=@_[8..11]; +my $mask=pop; +$code.=<<___; + vldmia $key!, {@t[0]-@t[3]} + veor @t[0], @t[0], @x[0] + veor @t[1], @t[1], @x[1] + vtbl.8 `&Dlo(@x[0])`, {@t[0]}, `&Dlo($mask)` + vtbl.8 `&Dhi(@x[0])`, {@t[0]}, `&Dhi($mask)` + vldmia $key!, {@t[0]} + veor @t[2], @t[2], @x[2] + vtbl.8 `&Dlo(@x[1])`, {@t[1]}, `&Dlo($mask)` + vtbl.8 `&Dhi(@x[1])`, {@t[1]}, `&Dhi($mask)` + vldmia $key!, {@t[1]} + veor @t[3], @t[3], @x[3] + vtbl.8 `&Dlo(@x[2])`, {@t[2]}, `&Dlo($mask)` + vtbl.8 `&Dhi(@x[2])`, {@t[2]}, `&Dhi($mask)` + vldmia $key!, {@t[2]} + vtbl.8 `&Dlo(@x[3])`, {@t[3]}, `&Dlo($mask)` + vtbl.8 `&Dhi(@x[3])`, {@t[3]}, `&Dhi($mask)` + vldmia $key!, {@t[3]} + veor @t[0], @t[0], @x[4] + veor @t[1], @t[1], @x[5] + vtbl.8 `&Dlo(@x[4])`, {@t[0]}, `&Dlo($mask)` + vtbl.8 `&Dhi(@x[4])`, {@t[0]}, `&Dhi($mask)` + veor @t[2], @t[2], @x[6] + vtbl.8 `&Dlo(@x[5])`, {@t[1]}, `&Dlo($mask)` + vtbl.8 `&Dhi(@x[5])`, {@t[1]}, `&Dhi($mask)` + veor @t[3], @t[3], @x[7] + vtbl.8 `&Dlo(@x[6])`, {@t[2]}, `&Dlo($mask)` + vtbl.8 `&Dhi(@x[6])`, {@t[2]}, `&Dhi($mask)` + vtbl.8 `&Dlo(@x[7])`, {@t[3]}, `&Dlo($mask)` + vtbl.8 `&Dhi(@x[7])`, {@t[3]}, `&Dhi($mask)` +___ +} + +sub MixColumns { +# modified to emit output in order suitable for feeding back to aesenc[last] +my @x=@_[0..7]; +my @t=@_[8..15]; +my $inv=@_[16]; # optional +$code.=<<___; + vext.8 @t[0], @x[0], @x[0], #12 @ x0 <<< 32 + vext.8 @t[1], @x[1], @x[1], #12 + veor @x[0], @x[0], @t[0] @ x0 ^ (x0 <<< 32) + vext.8 @t[2], @x[2], @x[2], #12 + veor @x[1], @x[1], @t[1] + vext.8 @t[3], @x[3], @x[3], #12 + veor @x[2], @x[2], @t[2] + vext.8 @t[4], @x[4], @x[4], #12 + veor @x[3], @x[3], @t[3] + vext.8 @t[5], @x[5], @x[5], #12 + veor @x[4], @x[4], @t[4] + vext.8 @t[6], @x[6], @x[6], #12 + veor @x[5], @x[5], @t[5] + vext.8 @t[7], @x[7], @x[7], #12 + veor @x[6], @x[6], @t[6] + + veor @t[1], @t[1], @x[0] + veor @x[7], @x[7], @t[7] + vext.8 @x[0], @x[0], @x[0], #8 @ (x0 ^ (x0 <<< 32)) <<< 64) + veor @t[2], @t[2], @x[1] + veor @t[0], @t[0], @x[7] + veor @t[1], @t[1], @x[7] + vext.8 @x[1], @x[1], @x[1], #8 + veor @t[5], @t[5], @x[4] + veor @x[0], @x[0], @t[0] + veor @t[6], @t[6], @x[5] + veor @x[1], @x[1], @t[1] + vext.8 @t[0], @x[4], @x[4], #8 + veor @t[4], @t[4], @x[3] + vext.8 @t[1], @x[5], @x[5], #8 + veor @t[7], @t[7], @x[6] + vext.8 @x[4], @x[3], @x[3], #8 + veor @t[3], @t[3], @x[2] + vext.8 @x[5], @x[7], @x[7], #8 + veor @t[4], @t[4], @x[7] + vext.8 @x[3], @x[6], @x[6], #8 + veor @t[3], @t[3], @x[7] + vext.8 @x[6], @x[2], @x[2], #8 + veor @x[7], @t[1], @t[5] +___ +$code.=<<___ if (!$inv); + veor @x[2], @t[0], @t[4] + veor @x[4], @x[4], @t[3] + veor @x[5], @x[5], @t[7] + veor @x[3], @x[3], @t[6] + @ vmov @x[2], @t[0] + veor @x[6], @x[6], @t[2] + @ vmov @x[7], @t[1] +___ +$code.=<<___ if ($inv); + veor @t[3], @t[3], @x[4] + veor @x[5], @x[5], @t[7] + veor @x[2], @x[3], @t[6] + veor @x[3], @t[0], @t[4] + veor @x[4], @x[6], @t[2] + vmov @x[6], @t[3] + @ vmov @x[7], @t[1] +___ +} + +sub InvMixColumns_orig { +my @x=@_[0..7]; +my @t=@_[8..15]; + +$code.=<<___; + @ multiplication by 0x0e + vext.8 @t[7], @x[7], @x[7], #12 + vmov @t[2], @x[2] + veor @x[2], @x[2], @x[5] @ 2 5 + veor @x[7], @x[7], @x[5] @ 7 5 + vext.8 @t[0], @x[0], @x[0], #12 + vmov @t[5], @x[5] + veor @x[5], @x[5], @x[0] @ 5 0 [1] + veor @x[0], @x[0], @x[1] @ 0 1 + vext.8 @t[1], @x[1], @x[1], #12 + veor @x[1], @x[1], @x[2] @ 1 25 + veor @x[0], @x[0], @x[6] @ 01 6 [2] + vext.8 @t[3], @x[3], @x[3], #12 + veor @x[1], @x[1], @x[3] @ 125 3 [4] + veor @x[2], @x[2], @x[0] @ 25 016 [3] + veor @x[3], @x[3], @x[7] @ 3 75 + veor @x[7], @x[7], @x[6] @ 75 6 [0] + vext.8 @t[6], @x[6], @x[6], #12 + vmov @t[4], @x[4] + veor @x[6], @x[6], @x[4] @ 6 4 + veor @x[4], @x[4], @x[3] @ 4 375 [6] + veor @x[3], @x[3], @x[7] @ 375 756=36 + veor @x[6], @x[6], @t[5] @ 64 5 [7] + veor @x[3], @x[3], @t[2] @ 36 2 + vext.8 @t[5], @t[5], @t[5], #12 + veor @x[3], @x[3], @t[4] @ 362 4 [5] +___ + my @y = @x[7,5,0,2,1,3,4,6]; +$code.=<<___; + @ multiplication by 0x0b + veor @y[1], @y[1], @y[0] + veor @y[0], @y[0], @t[0] + vext.8 @t[2], @t[2], @t[2], #12 + veor @y[1], @y[1], @t[1] + veor @y[0], @y[0], @t[5] + vext.8 @t[4], @t[4], @t[4], #12 + veor @y[1], @y[1], @t[6] + veor @y[0], @y[0], @t[7] + veor @t[7], @t[7], @t[6] @ clobber t[7] + + veor @y[3], @y[3], @t[0] + veor @y[1], @y[1], @y[0] + vext.8 @t[0], @t[0], @t[0], #12 + veor @y[2], @y[2], @t[1] + veor @y[4], @y[4], @t[1] + vext.8 @t[1], @t[1], @t[1], #12 + veor @y[2], @y[2], @t[2] + veor @y[3], @y[3], @t[2] + veor @y[5], @y[5], @t[2] + veor @y[2], @y[2], @t[7] + vext.8 @t[2], @t[2], @t[2], #12 + veor @y[3], @y[3], @t[3] + veor @y[6], @y[6], @t[3] + veor @y[4], @y[4], @t[3] + veor @y[7], @y[7], @t[4] + vext.8 @t[3], @t[3], @t[3], #12 + veor @y[5], @y[5], @t[4] + veor @y[7], @y[7], @t[7] + veor @t[7], @t[7], @t[5] @ clobber t[7] even more + veor @y[3], @y[3], @t[5] + veor @y[4], @y[4], @t[4] + + veor @y[5], @y[5], @t[7] + vext.8 @t[4], @t[4], @t[4], #12 + veor @y[6], @y[6], @t[7] + veor @y[4], @y[4], @t[7] + + veor @t[7], @t[7], @t[5] + vext.8 @t[5], @t[5], @t[5], #12 + + @ multiplication by 0x0d + veor @y[4], @y[4], @y[7] + veor @t[7], @t[7], @t[6] @ restore t[7] + veor @y[7], @y[7], @t[4] + vext.8 @t[6], @t[6], @t[6], #12 + veor @y[2], @y[2], @t[0] + veor @y[7], @y[7], @t[5] + vext.8 @t[7], @t[7], @t[7], #12 + veor @y[2], @y[2], @t[2] + + veor @y[3], @y[3], @y[1] + veor @y[1], @y[1], @t[1] + veor @y[0], @y[0], @t[0] + veor @y[3], @y[3], @t[0] + veor @y[1], @y[1], @t[5] + veor @y[0], @y[0], @t[5] + vext.8 @t[0], @t[0], @t[0], #12 + veor @y[1], @y[1], @t[7] + veor @y[0], @y[0], @t[6] + veor @y[3], @y[3], @y[1] + veor @y[4], @y[4], @t[1] + vext.8 @t[1], @t[1], @t[1], #12 + + veor @y[7], @y[7], @t[7] + veor @y[4], @y[4], @t[2] + veor @y[5], @y[5], @t[2] + veor @y[2], @y[2], @t[6] + veor @t[6], @t[6], @t[3] @ clobber t[6] + vext.8 @t[2], @t[2], @t[2], #12 + veor @y[4], @y[4], @y[7] + veor @y[3], @y[3], @t[6] + + veor @y[6], @y[6], @t[6] + veor @y[5], @y[5], @t[5] + vext.8 @t[5], @t[5], @t[5], #12 + veor @y[6], @y[6], @t[4] + vext.8 @t[4], @t[4], @t[4], #12 + veor @y[5], @y[5], @t[6] + veor @y[6], @y[6], @t[7] + vext.8 @t[7], @t[7], @t[7], #12 + veor @t[6], @t[6], @t[3] @ restore t[6] + vext.8 @t[3], @t[3], @t[3], #12 + + @ multiplication by 0x09 + veor @y[4], @y[4], @y[1] + veor @t[1], @t[1], @y[1] @ t[1]=y[1] + veor @t[0], @t[0], @t[5] @ clobber t[0] + vext.8 @t[6], @t[6], @t[6], #12 + veor @t[1], @t[1], @t[5] + veor @y[3], @y[3], @t[0] + veor @t[0], @t[0], @y[0] @ t[0]=y[0] + veor @t[1], @t[1], @t[6] + veor @t[6], @t[6], @t[7] @ clobber t[6] + veor @y[4], @y[4], @t[1] + veor @y[7], @y[7], @t[4] + veor @y[6], @y[6], @t[3] + veor @y[5], @y[5], @t[2] + veor @t[4], @t[4], @y[4] @ t[4]=y[4] + veor @t[3], @t[3], @y[3] @ t[3]=y[3] + veor @t[5], @t[5], @y[5] @ t[5]=y[5] + veor @t[2], @t[2], @y[2] @ t[2]=y[2] + veor @t[3], @t[3], @t[7] + veor @XMM[5], @t[5], @t[6] + veor @XMM[6], @t[6], @y[6] @ t[6]=y[6] + veor @XMM[2], @t[2], @t[6] + veor @XMM[7], @t[7], @y[7] @ t[7]=y[7] + + vmov @XMM[0], @t[0] + vmov @XMM[1], @t[1] + @ vmov @XMM[2], @t[2] + vmov @XMM[3], @t[3] + vmov @XMM[4], @t[4] + @ vmov @XMM[5], @t[5] + @ vmov @XMM[6], @t[6] + @ vmov @XMM[7], @t[7] +___ +} + +sub InvMixColumns { +my @x=@_[0..7]; +my @t=@_[8..15]; + +# Thanks to Jussi Kivilinna for providing pointer to +# +# | 0e 0b 0d 09 | | 02 03 01 01 | | 05 00 04 00 | +# | 09 0e 0b 0d | = | 01 02 03 01 | x | 00 05 00 04 | +# | 0d 09 0e 0b | | 01 01 02 03 | | 04 00 05 00 | +# | 0b 0d 09 0e | | 03 01 01 02 | | 00 04 00 05 | + +$code.=<<___; + @ multiplication by 0x05-0x00-0x04-0x00 + vext.8 @t[0], @x[0], @x[0], #8 + vext.8 @t[6], @x[6], @x[6], #8 + vext.8 @t[7], @x[7], @x[7], #8 + veor @t[0], @t[0], @x[0] + vext.8 @t[1], @x[1], @x[1], #8 + veor @t[6], @t[6], @x[6] + vext.8 @t[2], @x[2], @x[2], #8 + veor @t[7], @t[7], @x[7] + vext.8 @t[3], @x[3], @x[3], #8 + veor @t[1], @t[1], @x[1] + vext.8 @t[4], @x[4], @x[4], #8 + veor @t[2], @t[2], @x[2] + vext.8 @t[5], @x[5], @x[5], #8 + veor @t[3], @t[3], @x[3] + veor @t[4], @t[4], @x[4] + veor @t[5], @t[5], @x[5] + + veor @x[0], @x[0], @t[6] + veor @x[1], @x[1], @t[6] + veor @x[2], @x[2], @t[0] + veor @x[4], @x[4], @t[2] + veor @x[3], @x[3], @t[1] + veor @x[1], @x[1], @t[7] + veor @x[2], @x[2], @t[7] + veor @x[4], @x[4], @t[6] + veor @x[5], @x[5], @t[3] + veor @x[3], @x[3], @t[6] + veor @x[6], @x[6], @t[4] + veor @x[4], @x[4], @t[7] + veor @x[5], @x[5], @t[7] + veor @x[7], @x[7], @t[5] +___ + &MixColumns (@x,@t,1); # flipped 2<->3 and 4<->6 +} + +sub swapmove { +my ($a,$b,$n,$mask,$t)=@_; +$code.=<<___; + vshr.u64 $t, $b, #$n + veor $t, $t, $a + vand $t, $t, $mask + veor $a, $a, $t + vshl.u64 $t, $t, #$n + veor $b, $b, $t +___ +} +sub swapmove2x { +my ($a0,$b0,$a1,$b1,$n,$mask,$t0,$t1)=@_; +$code.=<<___; + vshr.u64 $t0, $b0, #$n + vshr.u64 $t1, $b1, #$n + veor $t0, $t0, $a0 + veor $t1, $t1, $a1 + vand $t0, $t0, $mask + vand $t1, $t1, $mask + veor $a0, $a0, $t0 + vshl.u64 $t0, $t0, #$n + veor $a1, $a1, $t1 + vshl.u64 $t1, $t1, #$n + veor $b0, $b0, $t0 + veor $b1, $b1, $t1 +___ +} + +sub bitslice { +my @x=reverse(@_[0..7]); +my ($t0,$t1,$t2,$t3)=@_[8..11]; +$code.=<<___; + vmov.i8 $t0,#0x55 @ compose .LBS0 + vmov.i8 $t1,#0x33 @ compose .LBS1 +___ + &swapmove2x(@x[0,1,2,3],1,$t0,$t2,$t3); + &swapmove2x(@x[4,5,6,7],1,$t0,$t2,$t3); +$code.=<<___; + vmov.i8 $t0,#0x0f @ compose .LBS2 +___ + &swapmove2x(@x[0,2,1,3],2,$t1,$t2,$t3); + &swapmove2x(@x[4,6,5,7],2,$t1,$t2,$t3); + + &swapmove2x(@x[0,4,1,5],4,$t0,$t2,$t3); + &swapmove2x(@x[2,6,3,7],4,$t0,$t2,$t3); +} + +$code.=<<___; +#ifndef __KERNEL__ +# include "arm_arch.h" + +# define VFP_ABI_PUSH vstmdb sp!,{d8-d15} +# define VFP_ABI_POP vldmia sp!,{d8-d15} +# define VFP_ABI_FRAME 0x40 +#else +# define VFP_ABI_PUSH +# define VFP_ABI_POP +# define VFP_ABI_FRAME 0 +# define BSAES_ASM_EXTENDED_KEY +# define XTS_CHAIN_TWEAK +# define __ARM_ARCH__ __LINUX_ARM_ARCH__ +#endif + +#ifdef __thumb__ +# define adrl adr +#endif + +#if __ARM_ARCH__>=7 +.text +.syntax unified @ ARMv7-capable assembler is expected to handle this +#ifdef __thumb2__ +.thumb +#else +.code 32 +#endif + +.fpu neon + +.type _bsaes_decrypt8,%function +.align 4 +_bsaes_decrypt8: + adr $const,_bsaes_decrypt8 + vldmia $key!, {@XMM[9]} @ round 0 key + add $const,$const,#.LM0ISR-_bsaes_decrypt8 + + vldmia $const!, {@XMM[8]} @ .LM0ISR + veor @XMM[10], @XMM[0], @XMM[9] @ xor with round0 key + veor @XMM[11], @XMM[1], @XMM[9] + vtbl.8 `&Dlo(@XMM[0])`, {@XMM[10]}, `&Dlo(@XMM[8])` + vtbl.8 `&Dhi(@XMM[0])`, {@XMM[10]}, `&Dhi(@XMM[8])` + veor @XMM[12], @XMM[2], @XMM[9] + vtbl.8 `&Dlo(@XMM[1])`, {@XMM[11]}, `&Dlo(@XMM[8])` + vtbl.8 `&Dhi(@XMM[1])`, {@XMM[11]}, `&Dhi(@XMM[8])` + veor @XMM[13], @XMM[3], @XMM[9] + vtbl.8 `&Dlo(@XMM[2])`, {@XMM[12]}, `&Dlo(@XMM[8])` + vtbl.8 `&Dhi(@XMM[2])`, {@XMM[12]}, `&Dhi(@XMM[8])` + veor @XMM[14], @XMM[4], @XMM[9] + vtbl.8 `&Dlo(@XMM[3])`, {@XMM[13]}, `&Dlo(@XMM[8])` + vtbl.8 `&Dhi(@XMM[3])`, {@XMM[13]}, `&Dhi(@XMM[8])` + veor @XMM[15], @XMM[5], @XMM[9] + vtbl.8 `&Dlo(@XMM[4])`, {@XMM[14]}, `&Dlo(@XMM[8])` + vtbl.8 `&Dhi(@XMM[4])`, {@XMM[14]}, `&Dhi(@XMM[8])` + veor @XMM[10], @XMM[6], @XMM[9] + vtbl.8 `&Dlo(@XMM[5])`, {@XMM[15]}, `&Dlo(@XMM[8])` + vtbl.8 `&Dhi(@XMM[5])`, {@XMM[15]}, `&Dhi(@XMM[8])` + veor @XMM[11], @XMM[7], @XMM[9] + vtbl.8 `&Dlo(@XMM[6])`, {@XMM[10]}, `&Dlo(@XMM[8])` + vtbl.8 `&Dhi(@XMM[6])`, {@XMM[10]}, `&Dhi(@XMM[8])` + vtbl.8 `&Dlo(@XMM[7])`, {@XMM[11]}, `&Dlo(@XMM[8])` + vtbl.8 `&Dhi(@XMM[7])`, {@XMM[11]}, `&Dhi(@XMM[8])` +___ + &bitslice (@XMM[0..7, 8..11]); +$code.=<<___; + sub $rounds,$rounds,#1 + b .Ldec_sbox +.align 4 +.Ldec_loop: +___ + &ShiftRows (@XMM[0..7, 8..12]); +$code.=".Ldec_sbox:\n"; + &InvSbox (@XMM[0..7, 8..15]); +$code.=<<___; + subs $rounds,$rounds,#1 + bcc .Ldec_done +___ + &InvMixColumns (@XMM[0,1,6,4,2,7,3,5, 8..15]); +$code.=<<___; + vldmia $const, {@XMM[12]} @ .LISR + ite eq @ Thumb2 thing, sanity check in ARM + addeq $const,$const,#0x10 + bne .Ldec_loop + vldmia $const, {@XMM[12]} @ .LISRM0 + b .Ldec_loop +.align 4 +.Ldec_done: +___ + &bitslice (@XMM[0,1,6,4,2,7,3,5, 8..11]); +$code.=<<___; + vldmia $key, {@XMM[8]} @ last round key + veor @XMM[6], @XMM[6], @XMM[8] + veor @XMM[4], @XMM[4], @XMM[8] + veor @XMM[2], @XMM[2], @XMM[8] + veor @XMM[7], @XMM[7], @XMM[8] + veor @XMM[3], @XMM[3], @XMM[8] + veor @XMM[5], @XMM[5], @XMM[8] + veor @XMM[0], @XMM[0], @XMM[8] + veor @XMM[1], @XMM[1], @XMM[8] + bx lr +.size _bsaes_decrypt8,.-_bsaes_decrypt8 + +.type _bsaes_const,%object +.align 6 +_bsaes_const: +.LM0ISR: @ InvShiftRows constants + .quad 0x0a0e0206070b0f03, 0x0004080c0d010509 +.LISR: + .quad 0x0504070602010003, 0x0f0e0d0c080b0a09 +.LISRM0: + .quad 0x01040b0e0205080f, 0x0306090c00070a0d +.LM0SR: @ ShiftRows constants + .quad 0x0a0e02060f03070b, 0x0004080c05090d01 +.LSR: + .quad 0x0504070600030201, 0x0f0e0d0c0a09080b +.LSRM0: + .quad 0x0304090e00050a0f, 0x01060b0c0207080d +.LM0: + .quad 0x02060a0e03070b0f, 0x0004080c0105090d +.LREVM0SR: + .quad 0x090d01050c000408, 0x03070b0f060a0e02 +.asciz "Bit-sliced AES for NEON, CRYPTOGAMS by <appro\@openssl.org>" +.align 6 +.size _bsaes_const,.-_bsaes_const + +.type _bsaes_encrypt8,%function +.align 4 +_bsaes_encrypt8: + adr $const,_bsaes_encrypt8 + vldmia $key!, {@XMM[9]} @ round 0 key + sub $const,$const,#_bsaes_encrypt8-.LM0SR + + vldmia $const!, {@XMM[8]} @ .LM0SR +_bsaes_encrypt8_alt: + veor @XMM[10], @XMM[0], @XMM[9] @ xor with round0 key + veor @XMM[11], @XMM[1], @XMM[9] + vtbl.8 `&Dlo(@XMM[0])`, {@XMM[10]}, `&Dlo(@XMM[8])` + vtbl.8 `&Dhi(@XMM[0])`, {@XMM[10]}, `&Dhi(@XMM[8])` + veor @XMM[12], @XMM[2], @XMM[9] + vtbl.8 `&Dlo(@XMM[1])`, {@XMM[11]}, `&Dlo(@XMM[8])` + vtbl.8 `&Dhi(@XMM[1])`, {@XMM[11]}, `&Dhi(@XMM[8])` + veor @XMM[13], @XMM[3], @XMM[9] + vtbl.8 `&Dlo(@XMM[2])`, {@XMM[12]}, `&Dlo(@XMM[8])` + vtbl.8 `&Dhi(@XMM[2])`, {@XMM[12]}, `&Dhi(@XMM[8])` + veor @XMM[14], @XMM[4], @XMM[9] + vtbl.8 `&Dlo(@XMM[3])`, {@XMM[13]}, `&Dlo(@XMM[8])` + vtbl.8 `&Dhi(@XMM[3])`, {@XMM[13]}, `&Dhi(@XMM[8])` + veor @XMM[15], @XMM[5], @XMM[9] + vtbl.8 `&Dlo(@XMM[4])`, {@XMM[14]}, `&Dlo(@XMM[8])` + vtbl.8 `&Dhi(@XMM[4])`, {@XMM[14]}, `&Dhi(@XMM[8])` + veor @XMM[10], @XMM[6], @XMM[9] + vtbl.8 `&Dlo(@XMM[5])`, {@XMM[15]}, `&Dlo(@XMM[8])` + vtbl.8 `&Dhi(@XMM[5])`, {@XMM[15]}, `&Dhi(@XMM[8])` + veor @XMM[11], @XMM[7], @XMM[9] + vtbl.8 `&Dlo(@XMM[6])`, {@XMM[10]}, `&Dlo(@XMM[8])` + vtbl.8 `&Dhi(@XMM[6])`, {@XMM[10]}, `&Dhi(@XMM[8])` + vtbl.8 `&Dlo(@XMM[7])`, {@XMM[11]}, `&Dlo(@XMM[8])` + vtbl.8 `&Dhi(@XMM[7])`, {@XMM[11]}, `&Dhi(@XMM[8])` +_bsaes_encrypt8_bitslice: +___ + &bitslice (@XMM[0..7, 8..11]); +$code.=<<___; + sub $rounds,$rounds,#1 + b .Lenc_sbox +.align 4 +.Lenc_loop: +___ + &ShiftRows (@XMM[0..7, 8..12]); +$code.=".Lenc_sbox:\n"; + &Sbox (@XMM[0..7, 8..15]); +$code.=<<___; + subs $rounds,$rounds,#1 + bcc .Lenc_done +___ + &MixColumns (@XMM[0,1,4,6,3,7,2,5, 8..15]); +$code.=<<___; + vldmia $const, {@XMM[12]} @ .LSR + ite eq @ Thumb2 thing, samity check in ARM + addeq $const,$const,#0x10 + bne .Lenc_loop + vldmia $const, {@XMM[12]} @ .LSRM0 + b .Lenc_loop +.align 4 +.Lenc_done: +___ + # output in lsb > [t0, t1, t4, t6, t3, t7, t2, t5] < msb + &bitslice (@XMM[0,1,4,6,3,7,2,5, 8..11]); +$code.=<<___; + vldmia $key, {@XMM[8]} @ last round key + veor @XMM[4], @XMM[4], @XMM[8] + veor @XMM[6], @XMM[6], @XMM[8] + veor @XMM[3], @XMM[3], @XMM[8] + veor @XMM[7], @XMM[7], @XMM[8] + veor @XMM[2], @XMM[2], @XMM[8] + veor @XMM[5], @XMM[5], @XMM[8] + veor @XMM[0], @XMM[0], @XMM[8] + veor @XMM[1], @XMM[1], @XMM[8] + bx lr +.size _bsaes_encrypt8,.-_bsaes_encrypt8 +___ +} +{ +my ($out,$inp,$rounds,$const)=("r12","r4","r5","r6"); + +sub bitslice_key { +my @x=reverse(@_[0..7]); +my ($bs0,$bs1,$bs2,$t2,$t3)=@_[8..12]; + + &swapmove (@x[0,1],1,$bs0,$t2,$t3); +$code.=<<___; + @ &swapmove(@x[2,3],1,$t0,$t2,$t3); + vmov @x[2], @x[0] + vmov @x[3], @x[1] +___ + #&swapmove2x(@x[4,5,6,7],1,$t0,$t2,$t3); + + &swapmove2x (@x[0,2,1,3],2,$bs1,$t2,$t3); +$code.=<<___; + @ &swapmove2x(@x[4,6,5,7],2,$t1,$t2,$t3); + vmov @x[4], @x[0] + vmov @x[6], @x[2] + vmov @x[5], @x[1] + vmov @x[7], @x[3] +___ + &swapmove2x (@x[0,4,1,5],4,$bs2,$t2,$t3); + &swapmove2x (@x[2,6,3,7],4,$bs2,$t2,$t3); +} + +$code.=<<___; +.type _bsaes_key_convert,%function +.align 4 +_bsaes_key_convert: + adr $const,_bsaes_key_convert + vld1.8 {@XMM[7]}, [$inp]! @ load round 0 key + sub $const,$const,#_bsaes_key_convert-.LM0 + vld1.8 {@XMM[15]}, [$inp]! @ load round 1 key + + vmov.i8 @XMM[8], #0x01 @ bit masks + vmov.i8 @XMM[9], #0x02 + vmov.i8 @XMM[10], #0x04 + vmov.i8 @XMM[11], #0x08 + vmov.i8 @XMM[12], #0x10 + vmov.i8 @XMM[13], #0x20 + vldmia $const, {@XMM[14]} @ .LM0 + +#ifdef __ARMEL__ + vrev32.8 @XMM[7], @XMM[7] + vrev32.8 @XMM[15], @XMM[15] +#endif + sub $rounds,$rounds,#1 + vstmia $out!, {@XMM[7]} @ save round 0 key + b .Lkey_loop + +.align 4 +.Lkey_loop: + vtbl.8 `&Dlo(@XMM[7])`,{@XMM[15]},`&Dlo(@XMM[14])` + vtbl.8 `&Dhi(@XMM[7])`,{@XMM[15]},`&Dhi(@XMM[14])` + vmov.i8 @XMM[6], #0x40 + vmov.i8 @XMM[15], #0x80 + + vtst.8 @XMM[0], @XMM[7], @XMM[8] + vtst.8 @XMM[1], @XMM[7], @XMM[9] + vtst.8 @XMM[2], @XMM[7], @XMM[10] + vtst.8 @XMM[3], @XMM[7], @XMM[11] + vtst.8 @XMM[4], @XMM[7], @XMM[12] + vtst.8 @XMM[5], @XMM[7], @XMM[13] + vtst.8 @XMM[6], @XMM[7], @XMM[6] + vtst.8 @XMM[7], @XMM[7], @XMM[15] + vld1.8 {@XMM[15]}, [$inp]! @ load next round key + vmvn @XMM[0], @XMM[0] @ "pnot" + vmvn @XMM[1], @XMM[1] + vmvn @XMM[5], @XMM[5] + vmvn @XMM[6], @XMM[6] +#ifdef __ARMEL__ + vrev32.8 @XMM[15], @XMM[15] +#endif + subs $rounds,$rounds,#1 + vstmia $out!,{@XMM[0]-@XMM[7]} @ write bit-sliced round key + bne .Lkey_loop + + vmov.i8 @XMM[7],#0x63 @ compose .L63 + @ don't save last round key + bx lr +.size _bsaes_key_convert,.-_bsaes_key_convert +___ +} + +if (0) { # following four functions are unsupported interface + # used for benchmarking... +$code.=<<___; +.globl bsaes_enc_key_convert +.type bsaes_enc_key_convert,%function +.align 4 +bsaes_enc_key_convert: + stmdb sp!,{r4-r6,lr} + vstmdb sp!,{d8-d15} @ ABI specification says so + + ldr r5,[$inp,#240] @ pass rounds + mov r4,$inp @ pass key + mov r12,$out @ pass key schedule + bl _bsaes_key_convert + veor @XMM[7],@XMM[7],@XMM[15] @ fix up last round key + vstmia r12, {@XMM[7]} @ save last round key + + vldmia sp!,{d8-d15} + ldmia sp!,{r4-r6,pc} +.size bsaes_enc_key_convert,.-bsaes_enc_key_convert + +.globl bsaes_encrypt_128 +.type bsaes_encrypt_128,%function +.align 4 +bsaes_encrypt_128: + stmdb sp!,{r4-r6,lr} + vstmdb sp!,{d8-d15} @ ABI specification says so +.Lenc128_loop: + vld1.8 {@XMM[0]-@XMM[1]}, [$inp]! @ load input + vld1.8 {@XMM[2]-@XMM[3]}, [$inp]! + mov r4,$key @ pass the key + vld1.8 {@XMM[4]-@XMM[5]}, [$inp]! + mov r5,#10 @ pass rounds + vld1.8 {@XMM[6]-@XMM[7]}, [$inp]! + + bl _bsaes_encrypt8 + + vst1.8 {@XMM[0]-@XMM[1]}, [$out]! @ write output + vst1.8 {@XMM[4]}, [$out]! + vst1.8 {@XMM[6]}, [$out]! + vst1.8 {@XMM[3]}, [$out]! + vst1.8 {@XMM[7]}, [$out]! + vst1.8 {@XMM[2]}, [$out]! + subs $len,$len,#0x80 + vst1.8 {@XMM[5]}, [$out]! + bhi .Lenc128_loop + + vldmia sp!,{d8-d15} + ldmia sp!,{r4-r6,pc} +.size bsaes_encrypt_128,.-bsaes_encrypt_128 + +.globl bsaes_dec_key_convert +.type bsaes_dec_key_convert,%function +.align 4 +bsaes_dec_key_convert: + stmdb sp!,{r4-r6,lr} + vstmdb sp!,{d8-d15} @ ABI specification says so + + ldr r5,[$inp,#240] @ pass rounds + mov r4,$inp @ pass key + mov r12,$out @ pass key schedule + bl _bsaes_key_convert + vldmia $out, {@XMM[6]} + vstmia r12, {@XMM[15]} @ save last round key + veor @XMM[7], @XMM[7], @XMM[6] @ fix up round 0 key + vstmia $out, {@XMM[7]} + + vldmia sp!,{d8-d15} + ldmia sp!,{r4-r6,pc} +.size bsaes_dec_key_convert,.-bsaes_dec_key_convert + +.globl bsaes_decrypt_128 +.type bsaes_decrypt_128,%function +.align 4 +bsaes_decrypt_128: + stmdb sp!,{r4-r6,lr} + vstmdb sp!,{d8-d15} @ ABI specification says so +.Ldec128_loop: + vld1.8 {@XMM[0]-@XMM[1]}, [$inp]! @ load input + vld1.8 {@XMM[2]-@XMM[3]}, [$inp]! + mov r4,$key @ pass the key + vld1.8 {@XMM[4]-@XMM[5]}, [$inp]! + mov r5,#10 @ pass rounds + vld1.8 {@XMM[6]-@XMM[7]}, [$inp]! + + bl _bsaes_decrypt8 + + vst1.8 {@XMM[0]-@XMM[1]}, [$out]! @ write output + vst1.8 {@XMM[6]}, [$out]! + vst1.8 {@XMM[4]}, [$out]! + vst1.8 {@XMM[2]}, [$out]! + vst1.8 {@XMM[7]}, [$out]! + vst1.8 {@XMM[3]}, [$out]! + subs $len,$len,#0x80 + vst1.8 {@XMM[5]}, [$out]! + bhi .Ldec128_loop + + vldmia sp!,{d8-d15} + ldmia sp!,{r4-r6,pc} +.size bsaes_decrypt_128,.-bsaes_decrypt_128 +___ +} +{ +my ($inp,$out,$len,$key, $ivp,$fp,$rounds)=map("r$_",(0..3,8..10)); +my ($keysched)=("sp"); + +$code.=<<___; +.extern AES_cbc_encrypt +.extern AES_decrypt + +.global bsaes_cbc_encrypt +.type bsaes_cbc_encrypt,%function +.align 5 +bsaes_cbc_encrypt: +#ifndef __KERNEL__ + cmp $len, #128 +#ifndef __thumb__ + blo AES_cbc_encrypt +#else + bhs 1f + b AES_cbc_encrypt +1: +#endif +#endif + + @ it is up to the caller to make sure we are called with enc == 0 + + mov ip, sp + stmdb sp!, {r4-r10, lr} + VFP_ABI_PUSH + ldr $ivp, [ip] @ IV is 1st arg on the stack + mov $len, $len, lsr#4 @ len in 16 byte blocks + sub sp, #0x10 @ scratch space to carry over the IV + mov $fp, sp @ save sp + + ldr $rounds, [$key, #240] @ get # of rounds +#ifndef BSAES_ASM_EXTENDED_KEY + @ allocate the key schedule on the stack + sub r12, sp, $rounds, lsl#7 @ 128 bytes per inner round key + add r12, #`128-32` @ sifze of bit-slices key schedule + + @ populate the key schedule + mov r4, $key @ pass key + mov r5, $rounds @ pass # of rounds + mov sp, r12 @ sp is $keysched + bl _bsaes_key_convert + vldmia $keysched, {@XMM[6]} + vstmia r12, {@XMM[15]} @ save last round key + veor @XMM[7], @XMM[7], @XMM[6] @ fix up round 0 key + vstmia $keysched, {@XMM[7]} +#else + ldr r12, [$key, #244] + eors r12, #1 + beq 0f + + @ populate the key schedule + str r12, [$key, #244] + mov r4, $key @ pass key + mov r5, $rounds @ pass # of rounds + add r12, $key, #248 @ pass key schedule + bl _bsaes_key_convert + add r4, $key, #248 + vldmia r4, {@XMM[6]} + vstmia r12, {@XMM[15]} @ save last round key + veor @XMM[7], @XMM[7], @XMM[6] @ fix up round 0 key + vstmia r4, {@XMM[7]} + +.align 2 +0: +#endif + + vld1.8 {@XMM[15]}, [$ivp] @ load IV + b .Lcbc_dec_loop + +.align 4 +.Lcbc_dec_loop: + subs $len, $len, #0x8 + bmi .Lcbc_dec_loop_finish + + vld1.8 {@XMM[0]-@XMM[1]}, [$inp]! @ load input + vld1.8 {@XMM[2]-@XMM[3]}, [$inp]! +#ifndef BSAES_ASM_EXTENDED_KEY + mov r4, $keysched @ pass the key +#else + add r4, $key, #248 +#endif + vld1.8 {@XMM[4]-@XMM[5]}, [$inp]! + mov r5, $rounds + vld1.8 {@XMM[6]-@XMM[7]}, [$inp] + sub $inp, $inp, #0x60 + vstmia $fp, {@XMM[15]} @ put aside IV + + bl _bsaes_decrypt8 + + vldmia $fp, {@XMM[14]} @ reload IV + vld1.8 {@XMM[8]-@XMM[9]}, [$inp]! @ reload input + veor @XMM[0], @XMM[0], @XMM[14] @ ^= IV + vld1.8 {@XMM[10]-@XMM[11]}, [$inp]! + veor @XMM[1], @XMM[1], @XMM[8] + veor @XMM[6], @XMM[6], @XMM[9] + vld1.8 {@XMM[12]-@XMM[13]}, [$inp]! + veor @XMM[4], @XMM[4], @XMM[10] + veor @XMM[2], @XMM[2], @XMM[11] + vld1.8 {@XMM[14]-@XMM[15]}, [$inp]! + veor @XMM[7], @XMM[7], @XMM[12] + vst1.8 {@XMM[0]-@XMM[1]}, [$out]! @ write output + veor @XMM[3], @XMM[3], @XMM[13] + vst1.8 {@XMM[6]}, [$out]! + veor @XMM[5], @XMM[5], @XMM[14] + vst1.8 {@XMM[4]}, [$out]! + vst1.8 {@XMM[2]}, [$out]! + vst1.8 {@XMM[7]}, [$out]! + vst1.8 {@XMM[3]}, [$out]! + vst1.8 {@XMM[5]}, [$out]! + + b .Lcbc_dec_loop + +.Lcbc_dec_loop_finish: + adds $len, $len, #8 + beq .Lcbc_dec_done + + vld1.8 {@XMM[0]}, [$inp]! @ load input + cmp $len, #2 + blo .Lcbc_dec_one + vld1.8 {@XMM[1]}, [$inp]! +#ifndef BSAES_ASM_EXTENDED_KEY + mov r4, $keysched @ pass the key +#else + add r4, $key, #248 +#endif + mov r5, $rounds + vstmia $fp, {@XMM[15]} @ put aside IV + beq .Lcbc_dec_two + vld1.8 {@XMM[2]}, [$inp]! + cmp $len, #4 + blo .Lcbc_dec_three + vld1.8 {@XMM[3]}, [$inp]! + beq .Lcbc_dec_four + vld1.8 {@XMM[4]}, [$inp]! + cmp $len, #6 + blo .Lcbc_dec_five + vld1.8 {@XMM[5]}, [$inp]! + beq .Lcbc_dec_six + vld1.8 {@XMM[6]}, [$inp]! + sub $inp, $inp, #0x70 + + bl _bsaes_decrypt8 + + vldmia $fp, {@XMM[14]} @ reload IV + vld1.8 {@XMM[8]-@XMM[9]}, [$inp]! @ reload input + veor @XMM[0], @XMM[0], @XMM[14] @ ^= IV + vld1.8 {@XMM[10]-@XMM[11]}, [$inp]! + veor @XMM[1], @XMM[1], @XMM[8] + veor @XMM[6], @XMM[6], @XMM[9] + vld1.8 {@XMM[12]-@XMM[13]}, [$inp]! + veor @XMM[4], @XMM[4], @XMM[10] + veor @XMM[2], @XMM[2], @XMM[11] + vld1.8 {@XMM[15]}, [$inp]! + veor @XMM[7], @XMM[7], @XMM[12] + vst1.8 {@XMM[0]-@XMM[1]}, [$out]! @ write output + veor @XMM[3], @XMM[3], @XMM[13] + vst1.8 {@XMM[6]}, [$out]! + vst1.8 {@XMM[4]}, [$out]! + vst1.8 {@XMM[2]}, [$out]! + vst1.8 {@XMM[7]}, [$out]! + vst1.8 {@XMM[3]}, [$out]! + b .Lcbc_dec_done +.align 4 +.Lcbc_dec_six: + sub $inp, $inp, #0x60 + bl _bsaes_decrypt8 + vldmia $fp,{@XMM[14]} @ reload IV + vld1.8 {@XMM[8]-@XMM[9]}, [$inp]! @ reload input + veor @XMM[0], @XMM[0], @XMM[14] @ ^= IV + vld1.8 {@XMM[10]-@XMM[11]}, [$inp]! + veor @XMM[1], @XMM[1], @XMM[8] + veor @XMM[6], @XMM[6], @XMM[9] + vld1.8 {@XMM[12]}, [$inp]! + veor @XMM[4], @XMM[4], @XMM[10] + veor @XMM[2], @XMM[2], @XMM[11] + vld1.8 {@XMM[15]}, [$inp]! + veor @XMM[7], @XMM[7], @XMM[12] + vst1.8 {@XMM[0]-@XMM[1]}, [$out]! @ write output + vst1.8 {@XMM[6]}, [$out]! + vst1.8 {@XMM[4]}, [$out]! + vst1.8 {@XMM[2]}, [$out]! + vst1.8 {@XMM[7]}, [$out]! + b .Lcbc_dec_done +.align 4 +.Lcbc_dec_five: + sub $inp, $inp, #0x50 + bl _bsaes_decrypt8 + vldmia $fp, {@XMM[14]} @ reload IV + vld1.8 {@XMM[8]-@XMM[9]}, [$inp]! @ reload input + veor @XMM[0], @XMM[0], @XMM[14] @ ^= IV + vld1.8 {@XMM[10]-@XMM[11]}, [$inp]! + veor @XMM[1], @XMM[1], @XMM[8] + veor @XMM[6], @XMM[6], @XMM[9] + vld1.8 {@XMM[15]}, [$inp]! + veor @XMM[4], @XMM[4], @XMM[10] + vst1.8 {@XMM[0]-@XMM[1]}, [$out]! @ write output + veor @XMM[2], @XMM[2], @XMM[11] + vst1.8 {@XMM[6]}, [$out]! + vst1.8 {@XMM[4]}, [$out]! + vst1.8 {@XMM[2]}, [$out]! + b .Lcbc_dec_done +.align 4 +.Lcbc_dec_four: + sub $inp, $inp, #0x40 + bl _bsaes_decrypt8 + vldmia $fp, {@XMM[14]} @ reload IV + vld1.8 {@XMM[8]-@XMM[9]}, [$inp]! @ reload input + veor @XMM[0], @XMM[0], @XMM[14] @ ^= IV + vld1.8 {@XMM[10]}, [$inp]! + veor @XMM[1], @XMM[1], @XMM[8] + veor @XMM[6], @XMM[6], @XMM[9] + vld1.8 {@XMM[15]}, [$inp]! + veor @XMM[4], @XMM[4], @XMM[10] + vst1.8 {@XMM[0]-@XMM[1]}, [$out]! @ write output + vst1.8 {@XMM[6]}, [$out]! + vst1.8 {@XMM[4]}, [$out]! + b .Lcbc_dec_done +.align 4 +.Lcbc_dec_three: + sub $inp, $inp, #0x30 + bl _bsaes_decrypt8 + vldmia $fp, {@XMM[14]} @ reload IV + vld1.8 {@XMM[8]-@XMM[9]}, [$inp]! @ reload input + veor @XMM[0], @XMM[0], @XMM[14] @ ^= IV + vld1.8 {@XMM[15]}, [$inp]! + veor @XMM[1], @XMM[1], @XMM[8] + veor @XMM[6], @XMM[6], @XMM[9] + vst1.8 {@XMM[0]-@XMM[1]}, [$out]! @ write output + vst1.8 {@XMM[6]}, [$out]! + b .Lcbc_dec_done +.align 4 +.Lcbc_dec_two: + sub $inp, $inp, #0x20 + bl _bsaes_decrypt8 + vldmia $fp, {@XMM[14]} @ reload IV + vld1.8 {@XMM[8]}, [$inp]! @ reload input + veor @XMM[0], @XMM[0], @XMM[14] @ ^= IV + vld1.8 {@XMM[15]}, [$inp]! @ reload input + veor @XMM[1], @XMM[1], @XMM[8] + vst1.8 {@XMM[0]-@XMM[1]}, [$out]! @ write output + b .Lcbc_dec_done +.align 4 +.Lcbc_dec_one: + sub $inp, $inp, #0x10 + mov $rounds, $out @ save original out pointer + mov $out, $fp @ use the iv scratch space as out buffer + mov r2, $key + vmov @XMM[4],@XMM[15] @ just in case ensure that IV + vmov @XMM[5],@XMM[0] @ and input are preserved + bl AES_decrypt + vld1.8 {@XMM[0]}, [$fp,:64] @ load result + veor @XMM[0], @XMM[0], @XMM[4] @ ^= IV + vmov @XMM[15], @XMM[5] @ @XMM[5] holds input + vst1.8 {@XMM[0]}, [$rounds] @ write output + +.Lcbc_dec_done: +#ifndef BSAES_ASM_EXTENDED_KEY + vmov.i32 q0, #0 + vmov.i32 q1, #0 +.Lcbc_dec_bzero: @ wipe key schedule [if any] + vstmia $keysched!, {q0-q1} + cmp $keysched, $fp + bne .Lcbc_dec_bzero +#endif + + mov sp, $fp + add sp, #0x10 @ add sp,$fp,#0x10 is no good for thumb + vst1.8 {@XMM[15]}, [$ivp] @ return IV + VFP_ABI_POP + ldmia sp!, {r4-r10, pc} +.size bsaes_cbc_encrypt,.-bsaes_cbc_encrypt +___ +} +{ +my ($inp,$out,$len,$key, $ctr,$fp,$rounds)=(map("r$_",(0..3,8..10))); +my $const = "r6"; # shared with _bsaes_encrypt8_alt +my $keysched = "sp"; + +$code.=<<___; +.extern AES_encrypt +.global bsaes_ctr32_encrypt_blocks +.type bsaes_ctr32_encrypt_blocks,%function +.align 5 +bsaes_ctr32_encrypt_blocks: + cmp $len, #8 @ use plain AES for + blo .Lctr_enc_short @ small sizes + + mov ip, sp + stmdb sp!, {r4-r10, lr} + VFP_ABI_PUSH + ldr $ctr, [ip] @ ctr is 1st arg on the stack + sub sp, sp, #0x10 @ scratch space to carry over the ctr + mov $fp, sp @ save sp + + ldr $rounds, [$key, #240] @ get # of rounds +#ifndef BSAES_ASM_EXTENDED_KEY + @ allocate the key schedule on the stack + sub r12, sp, $rounds, lsl#7 @ 128 bytes per inner round key + add r12, #`128-32` @ size of bit-sliced key schedule + + @ populate the key schedule + mov r4, $key @ pass key + mov r5, $rounds @ pass # of rounds + mov sp, r12 @ sp is $keysched + bl _bsaes_key_convert + veor @XMM[7],@XMM[7],@XMM[15] @ fix up last round key + vstmia r12, {@XMM[7]} @ save last round key + + vld1.8 {@XMM[0]}, [$ctr] @ load counter + add $ctr, $const, #.LREVM0SR-.LM0 @ borrow $ctr + vldmia $keysched, {@XMM[4]} @ load round0 key +#else + ldr r12, [$key, #244] + eors r12, #1 + beq 0f + + @ populate the key schedule + str r12, [$key, #244] + mov r4, $key @ pass key + mov r5, $rounds @ pass # of rounds + add r12, $key, #248 @ pass key schedule + bl _bsaes_key_convert + veor @XMM[7],@XMM[7],@XMM[15] @ fix up last round key + vstmia r12, {@XMM[7]} @ save last round key + +.align 2 +0: add r12, $key, #248 + vld1.8 {@XMM[0]}, [$ctr] @ load counter + adrl $ctr, .LREVM0SR @ borrow $ctr + vldmia r12, {@XMM[4]} @ load round0 key + sub sp, #0x10 @ place for adjusted round0 key +#endif + + vmov.i32 @XMM[8],#1 @ compose 1<<96 + veor @XMM[9],@XMM[9],@XMM[9] + vrev32.8 @XMM[0],@XMM[0] + vext.8 @XMM[8],@XMM[9],@XMM[8],#4 + vrev32.8 @XMM[4],@XMM[4] + vadd.u32 @XMM[9],@XMM[8],@XMM[8] @ compose 2<<96 + vstmia $keysched, {@XMM[4]} @ save adjusted round0 key + b .Lctr_enc_loop + +.align 4 +.Lctr_enc_loop: + vadd.u32 @XMM[10], @XMM[8], @XMM[9] @ compose 3<<96 + vadd.u32 @XMM[1], @XMM[0], @XMM[8] @ +1 + vadd.u32 @XMM[2], @XMM[0], @XMM[9] @ +2 + vadd.u32 @XMM[3], @XMM[0], @XMM[10] @ +3 + vadd.u32 @XMM[4], @XMM[1], @XMM[10] + vadd.u32 @XMM[5], @XMM[2], @XMM[10] + vadd.u32 @XMM[6], @XMM[3], @XMM[10] + vadd.u32 @XMM[7], @XMM[4], @XMM[10] + vadd.u32 @XMM[10], @XMM[5], @XMM[10] @ next counter + + @ Borrow prologue from _bsaes_encrypt8 to use the opportunity + @ to flip byte order in 32-bit counter + + vldmia $keysched, {@XMM[9]} @ load round0 key +#ifndef BSAES_ASM_EXTENDED_KEY + add r4, $keysched, #0x10 @ pass next round key +#else + add r4, $key, #`248+16` +#endif + vldmia $ctr, {@XMM[8]} @ .LREVM0SR + mov r5, $rounds @ pass rounds + vstmia $fp, {@XMM[10]} @ save next counter + sub $const, $ctr, #.LREVM0SR-.LSR @ pass constants + + bl _bsaes_encrypt8_alt + + subs $len, $len, #8 + blo .Lctr_enc_loop_done + + vld1.8 {@XMM[8]-@XMM[9]}, [$inp]! @ load input + vld1.8 {@XMM[10]-@XMM[11]}, [$inp]! + veor @XMM[0], @XMM[8] + veor @XMM[1], @XMM[9] + vld1.8 {@XMM[12]-@XMM[13]}, [$inp]! + veor @XMM[4], @XMM[10] + veor @XMM[6], @XMM[11] + vld1.8 {@XMM[14]-@XMM[15]}, [$inp]! + veor @XMM[3], @XMM[12] + vst1.8 {@XMM[0]-@XMM[1]}, [$out]! @ write output + veor @XMM[7], @XMM[13] + veor @XMM[2], @XMM[14] + vst1.8 {@XMM[4]}, [$out]! + veor @XMM[5], @XMM[15] + vst1.8 {@XMM[6]}, [$out]! + vmov.i32 @XMM[8], #1 @ compose 1<<96 + vst1.8 {@XMM[3]}, [$out]! + veor @XMM[9], @XMM[9], @XMM[9] + vst1.8 {@XMM[7]}, [$out]! + vext.8 @XMM[8], @XMM[9], @XMM[8], #4 + vst1.8 {@XMM[2]}, [$out]! + vadd.u32 @XMM[9],@XMM[8],@XMM[8] @ compose 2<<96 + vst1.8 {@XMM[5]}, [$out]! + vldmia $fp, {@XMM[0]} @ load counter + + bne .Lctr_enc_loop + b .Lctr_enc_done + +.align 4 +.Lctr_enc_loop_done: + add $len, $len, #8 + vld1.8 {@XMM[8]}, [$inp]! @ load input + veor @XMM[0], @XMM[8] + vst1.8 {@XMM[0]}, [$out]! @ write output + cmp $len, #2 + blo .Lctr_enc_done + vld1.8 {@XMM[9]}, [$inp]! + veor @XMM[1], @XMM[9] + vst1.8 {@XMM[1]}, [$out]! + beq .Lctr_enc_done + vld1.8 {@XMM[10]}, [$inp]! + veor @XMM[4], @XMM[10] + vst1.8 {@XMM[4]}, [$out]! + cmp $len, #4 + blo .Lctr_enc_done + vld1.8 {@XMM[11]}, [$inp]! + veor @XMM[6], @XMM[11] + vst1.8 {@XMM[6]}, [$out]! + beq .Lctr_enc_done + vld1.8 {@XMM[12]}, [$inp]! + veor @XMM[3], @XMM[12] + vst1.8 {@XMM[3]}, [$out]! + cmp $len, #6 + blo .Lctr_enc_done + vld1.8 {@XMM[13]}, [$inp]! + veor @XMM[7], @XMM[13] + vst1.8 {@XMM[7]}, [$out]! + beq .Lctr_enc_done + vld1.8 {@XMM[14]}, [$inp] + veor @XMM[2], @XMM[14] + vst1.8 {@XMM[2]}, [$out]! + +.Lctr_enc_done: + vmov.i32 q0, #0 + vmov.i32 q1, #0 +#ifndef BSAES_ASM_EXTENDED_KEY +.Lctr_enc_bzero: @ wipe key schedule [if any] + vstmia $keysched!, {q0-q1} + cmp $keysched, $fp + bne .Lctr_enc_bzero +#else + vstmia $keysched, {q0-q1} +#endif + + mov sp, $fp + add sp, #0x10 @ add sp,$fp,#0x10 is no good for thumb + VFP_ABI_POP + ldmia sp!, {r4-r10, pc} @ return + +.align 4 +.Lctr_enc_short: + ldr ip, [sp] @ ctr pointer is passed on stack + stmdb sp!, {r4-r8, lr} + + mov r4, $inp @ copy arguments + mov r5, $out + mov r6, $len + mov r7, $key + ldr r8, [ip, #12] @ load counter LSW + vld1.8 {@XMM[1]}, [ip] @ load whole counter value +#ifdef __ARMEL__ + rev r8, r8 +#endif + sub sp, sp, #0x10 + vst1.8 {@XMM[1]}, [sp,:64] @ copy counter value + sub sp, sp, #0x10 + +.Lctr_enc_short_loop: + add r0, sp, #0x10 @ input counter value + mov r1, sp @ output on the stack + mov r2, r7 @ key + + bl AES_encrypt + + vld1.8 {@XMM[0]}, [r4]! @ load input + vld1.8 {@XMM[1]}, [sp,:64] @ load encrypted counter + add r8, r8, #1 +#ifdef __ARMEL__ + rev r0, r8 + str r0, [sp, #0x1c] @ next counter value +#else + str r8, [sp, #0x1c] @ next counter value +#endif + veor @XMM[0],@XMM[0],@XMM[1] + vst1.8 {@XMM[0]}, [r5]! @ store output + subs r6, r6, #1 + bne .Lctr_enc_short_loop + + vmov.i32 q0, #0 + vmov.i32 q1, #0 + vstmia sp!, {q0-q1} + + ldmia sp!, {r4-r8, pc} +.size bsaes_ctr32_encrypt_blocks,.-bsaes_ctr32_encrypt_blocks +___ +} +{ +###################################################################### +# void bsaes_xts_[en|de]crypt(const char *inp,char *out,size_t len, +# const AES_KEY *key1, const AES_KEY *key2, +# const unsigned char iv[16]); +# +my ($inp,$out,$len,$key,$rounds,$magic,$fp)=(map("r$_",(7..10,1..3))); +my $const="r6"; # returned by _bsaes_key_convert +my $twmask=@XMM[5]; +my @T=@XMM[6..7]; + +$code.=<<___; +.globl bsaes_xts_encrypt +.type bsaes_xts_encrypt,%function +.align 4 +bsaes_xts_encrypt: + mov ip, sp + stmdb sp!, {r4-r10, lr} @ 0x20 + VFP_ABI_PUSH + mov r6, sp @ future $fp + + mov $inp, r0 + mov $out, r1 + mov $len, r2 + mov $key, r3 + + sub r0, sp, #0x10 @ 0x10 + bic r0, #0xf @ align at 16 bytes + mov sp, r0 + +#ifdef XTS_CHAIN_TWEAK + ldr r0, [ip] @ pointer to input tweak +#else + @ generate initial tweak + ldr r0, [ip, #4] @ iv[] + mov r1, sp + ldr r2, [ip, #0] @ key2 + bl AES_encrypt + mov r0,sp @ pointer to initial tweak +#endif + + ldr $rounds, [$key, #240] @ get # of rounds + mov $fp, r6 +#ifndef BSAES_ASM_EXTENDED_KEY + @ allocate the key schedule on the stack + sub r12, sp, $rounds, lsl#7 @ 128 bytes per inner round key + @ add r12, #`128-32` @ size of bit-sliced key schedule + sub r12, #`32+16` @ place for tweak[9] + + @ populate the key schedule + mov r4, $key @ pass key + mov r5, $rounds @ pass # of rounds + mov sp, r12 + add r12, #0x90 @ pass key schedule + bl _bsaes_key_convert + veor @XMM[7], @XMM[7], @XMM[15] @ fix up last round key + vstmia r12, {@XMM[7]} @ save last round key +#else + ldr r12, [$key, #244] + eors r12, #1 + beq 0f + + str r12, [$key, #244] + mov r4, $key @ pass key + mov r5, $rounds @ pass # of rounds + add r12, $key, #248 @ pass key schedule + bl _bsaes_key_convert + veor @XMM[7], @XMM[7], @XMM[15] @ fix up last round key + vstmia r12, {@XMM[7]} + +.align 2 +0: sub sp, #0x90 @ place for tweak[9] +#endif + + vld1.8 {@XMM[8]}, [r0] @ initial tweak + adr $magic, .Lxts_magic + + subs $len, #0x80 + blo .Lxts_enc_short + b .Lxts_enc_loop + +.align 4 +.Lxts_enc_loop: + vldmia $magic, {$twmask} @ load XTS magic + vshr.s64 @T[0], @XMM[8], #63 + mov r0, sp + vand @T[0], @T[0], $twmask +___ +for($i=9;$i<16;$i++) { +$code.=<<___; + vadd.u64 @XMM[$i], @XMM[$i-1], @XMM[$i-1] + vst1.64 {@XMM[$i-1]}, [r0,:128]! + vswp `&Dhi("@T[0]")`,`&Dlo("@T[0]")` + vshr.s64 @T[1], @XMM[$i], #63 + veor @XMM[$i], @XMM[$i], @T[0] + vand @T[1], @T[1], $twmask +___ + @T=reverse(@T); + +$code.=<<___ if ($i>=10); + vld1.8 {@XMM[$i-10]}, [$inp]! +___ +$code.=<<___ if ($i>=11); + veor @XMM[$i-11], @XMM[$i-11], @XMM[$i-3] +___ +} +$code.=<<___; + vadd.u64 @XMM[8], @XMM[15], @XMM[15] + vst1.64 {@XMM[15]}, [r0,:128]! + vswp `&Dhi("@T[0]")`,`&Dlo("@T[0]")` + veor @XMM[8], @XMM[8], @T[0] + vst1.64 {@XMM[8]}, [r0,:128] @ next round tweak + + vld1.8 {@XMM[6]-@XMM[7]}, [$inp]! + veor @XMM[5], @XMM[5], @XMM[13] +#ifndef BSAES_ASM_EXTENDED_KEY + add r4, sp, #0x90 @ pass key schedule +#else + add r4, $key, #248 @ pass key schedule +#endif + veor @XMM[6], @XMM[6], @XMM[14] + mov r5, $rounds @ pass rounds + veor @XMM[7], @XMM[7], @XMM[15] + mov r0, sp + + bl _bsaes_encrypt8 + + vld1.64 {@XMM[ 8]-@XMM[ 9]}, [r0,:128]! + vld1.64 {@XMM[10]-@XMM[11]}, [r0,:128]! + veor @XMM[0], @XMM[0], @XMM[ 8] + vld1.64 {@XMM[12]-@XMM[13]}, [r0,:128]! + veor @XMM[1], @XMM[1], @XMM[ 9] + veor @XMM[8], @XMM[4], @XMM[10] + vst1.8 {@XMM[0]-@XMM[1]}, [$out]! + veor @XMM[9], @XMM[6], @XMM[11] + vld1.64 {@XMM[14]-@XMM[15]}, [r0,:128]! + veor @XMM[10], @XMM[3], @XMM[12] + vst1.8 {@XMM[8]-@XMM[9]}, [$out]! + veor @XMM[11], @XMM[7], @XMM[13] + veor @XMM[12], @XMM[2], @XMM[14] + vst1.8 {@XMM[10]-@XMM[11]}, [$out]! + veor @XMM[13], @XMM[5], @XMM[15] + vst1.8 {@XMM[12]-@XMM[13]}, [$out]! + + vld1.64 {@XMM[8]}, [r0,:128] @ next round tweak + + subs $len, #0x80 + bpl .Lxts_enc_loop + +.Lxts_enc_short: + adds $len, #0x70 + bmi .Lxts_enc_done + + vldmia $magic, {$twmask} @ load XTS magic + vshr.s64 @T[0], @XMM[8], #63 + mov r0, sp + vand @T[0], @T[0], $twmask +___ +for($i=9;$i<16;$i++) { +$code.=<<___; + vadd.u64 @XMM[$i], @XMM[$i-1], @XMM[$i-1] + vst1.64 {@XMM[$i-1]}, [r0,:128]! + vswp `&Dhi("@T[0]")`,`&Dlo("@T[0]")` + vshr.s64 @T[1], @XMM[$i], #63 + veor @XMM[$i], @XMM[$i], @T[0] + vand @T[1], @T[1], $twmask +___ + @T=reverse(@T); + +$code.=<<___ if ($i>=10); + vld1.8 {@XMM[$i-10]}, [$inp]! + subs $len, #0x10 + bmi .Lxts_enc_`$i-9` +___ +$code.=<<___ if ($i>=11); + veor @XMM[$i-11], @XMM[$i-11], @XMM[$i-3] +___ +} +$code.=<<___; + sub $len, #0x10 + vst1.64 {@XMM[15]}, [r0,:128] @ next round tweak + + vld1.8 {@XMM[6]}, [$inp]! + veor @XMM[5], @XMM[5], @XMM[13] +#ifndef BSAES_ASM_EXTENDED_KEY + add r4, sp, #0x90 @ pass key schedule +#else + add r4, $key, #248 @ pass key schedule +#endif + veor @XMM[6], @XMM[6], @XMM[14] + mov r5, $rounds @ pass rounds + mov r0, sp + + bl _bsaes_encrypt8 + + vld1.64 {@XMM[ 8]-@XMM[ 9]}, [r0,:128]! + vld1.64 {@XMM[10]-@XMM[11]}, [r0,:128]! + veor @XMM[0], @XMM[0], @XMM[ 8] + vld1.64 {@XMM[12]-@XMM[13]}, [r0,:128]! + veor @XMM[1], @XMM[1], @XMM[ 9] + veor @XMM[8], @XMM[4], @XMM[10] + vst1.8 {@XMM[0]-@XMM[1]}, [$out]! + veor @XMM[9], @XMM[6], @XMM[11] + vld1.64 {@XMM[14]}, [r0,:128]! + veor @XMM[10], @XMM[3], @XMM[12] + vst1.8 {@XMM[8]-@XMM[9]}, [$out]! + veor @XMM[11], @XMM[7], @XMM[13] + veor @XMM[12], @XMM[2], @XMM[14] + vst1.8 {@XMM[10]-@XMM[11]}, [$out]! + vst1.8 {@XMM[12]}, [$out]! + + vld1.64 {@XMM[8]}, [r0,:128] @ next round tweak + b .Lxts_enc_done +.align 4 +.Lxts_enc_6: + vst1.64 {@XMM[14]}, [r0,:128] @ next round tweak + + veor @XMM[4], @XMM[4], @XMM[12] +#ifndef BSAES_ASM_EXTENDED_KEY + add r4, sp, #0x90 @ pass key schedule +#else + add r4, $key, #248 @ pass key schedule +#endif + veor @XMM[5], @XMM[5], @XMM[13] + mov r5, $rounds @ pass rounds + mov r0, sp + + bl _bsaes_encrypt8 + + vld1.64 {@XMM[ 8]-@XMM[ 9]}, [r0,:128]! + vld1.64 {@XMM[10]-@XMM[11]}, [r0,:128]! + veor @XMM[0], @XMM[0], @XMM[ 8] + vld1.64 {@XMM[12]-@XMM[13]}, [r0,:128]! + veor @XMM[1], @XMM[1], @XMM[ 9] + veor @XMM[8], @XMM[4], @XMM[10] + vst1.8 {@XMM[0]-@XMM[1]}, [$out]! + veor @XMM[9], @XMM[6], @XMM[11] + veor @XMM[10], @XMM[3], @XMM[12] + vst1.8 {@XMM[8]-@XMM[9]}, [$out]! + veor @XMM[11], @XMM[7], @XMM[13] + vst1.8 {@XMM[10]-@XMM[11]}, [$out]! + + vld1.64 {@XMM[8]}, [r0,:128] @ next round tweak + b .Lxts_enc_done + +@ put this in range for both ARM and Thumb mode adr instructions +.align 5 +.Lxts_magic: + .quad 1, 0x87 + +.align 5 +.Lxts_enc_5: + vst1.64 {@XMM[13]}, [r0,:128] @ next round tweak + + veor @XMM[3], @XMM[3], @XMM[11] +#ifndef BSAES_ASM_EXTENDED_KEY + add r4, sp, #0x90 @ pass key schedule +#else + add r4, $key, #248 @ pass key schedule +#endif + veor @XMM[4], @XMM[4], @XMM[12] + mov r5, $rounds @ pass rounds + mov r0, sp + + bl _bsaes_encrypt8 + + vld1.64 {@XMM[ 8]-@XMM[ 9]}, [r0,:128]! + vld1.64 {@XMM[10]-@XMM[11]}, [r0,:128]! + veor @XMM[0], @XMM[0], @XMM[ 8] + vld1.64 {@XMM[12]}, [r0,:128]! + veor @XMM[1], @XMM[1], @XMM[ 9] + veor @XMM[8], @XMM[4], @XMM[10] + vst1.8 {@XMM[0]-@XMM[1]}, [$out]! + veor @XMM[9], @XMM[6], @XMM[11] + veor @XMM[10], @XMM[3], @XMM[12] + vst1.8 {@XMM[8]-@XMM[9]}, [$out]! + vst1.8 {@XMM[10]}, [$out]! + + vld1.64 {@XMM[8]}, [r0,:128] @ next round tweak + b .Lxts_enc_done +.align 4 +.Lxts_enc_4: + vst1.64 {@XMM[12]}, [r0,:128] @ next round tweak + + veor @XMM[2], @XMM[2], @XMM[10] +#ifndef BSAES_ASM_EXTENDED_KEY + add r4, sp, #0x90 @ pass key schedule +#else + add r4, $key, #248 @ pass key schedule +#endif + veor @XMM[3], @XMM[3], @XMM[11] + mov r5, $rounds @ pass rounds + mov r0, sp + + bl _bsaes_encrypt8 + + vld1.64 {@XMM[ 8]-@XMM[ 9]}, [r0,:128]! + vld1.64 {@XMM[10]-@XMM[11]}, [r0,:128]! + veor @XMM[0], @XMM[0], @XMM[ 8] + veor @XMM[1], @XMM[1], @XMM[ 9] + veor @XMM[8], @XMM[4], @XMM[10] + vst1.8 {@XMM[0]-@XMM[1]}, [$out]! + veor @XMM[9], @XMM[6], @XMM[11] + vst1.8 {@XMM[8]-@XMM[9]}, [$out]! + + vld1.64 {@XMM[8]}, [r0,:128] @ next round tweak + b .Lxts_enc_done +.align 4 +.Lxts_enc_3: + vst1.64 {@XMM[11]}, [r0,:128] @ next round tweak + + veor @XMM[1], @XMM[1], @XMM[9] +#ifndef BSAES_ASM_EXTENDED_KEY + add r4, sp, #0x90 @ pass key schedule +#else + add r4, $key, #248 @ pass key schedule +#endif + veor @XMM[2], @XMM[2], @XMM[10] + mov r5, $rounds @ pass rounds + mov r0, sp + + bl _bsaes_encrypt8 + + vld1.64 {@XMM[8]-@XMM[9]}, [r0,:128]! + vld1.64 {@XMM[10]}, [r0,:128]! + veor @XMM[0], @XMM[0], @XMM[ 8] + veor @XMM[1], @XMM[1], @XMM[ 9] + veor @XMM[8], @XMM[4], @XMM[10] + vst1.8 {@XMM[0]-@XMM[1]}, [$out]! + vst1.8 {@XMM[8]}, [$out]! + + vld1.64 {@XMM[8]}, [r0,:128] @ next round tweak + b .Lxts_enc_done +.align 4 +.Lxts_enc_2: + vst1.64 {@XMM[10]}, [r0,:128] @ next round tweak + + veor @XMM[0], @XMM[0], @XMM[8] +#ifndef BSAES_ASM_EXTENDED_KEY + add r4, sp, #0x90 @ pass key schedule +#else + add r4, $key, #248 @ pass key schedule +#endif + veor @XMM[1], @XMM[1], @XMM[9] + mov r5, $rounds @ pass rounds + mov r0, sp + + bl _bsaes_encrypt8 + + vld1.64 {@XMM[8]-@XMM[9]}, [r0,:128]! + veor @XMM[0], @XMM[0], @XMM[ 8] + veor @XMM[1], @XMM[1], @XMM[ 9] + vst1.8 {@XMM[0]-@XMM[1]}, [$out]! + + vld1.64 {@XMM[8]}, [r0,:128] @ next round tweak + b .Lxts_enc_done +.align 4 +.Lxts_enc_1: + mov r0, sp + veor @XMM[0], @XMM[8] + mov r1, sp + vst1.8 {@XMM[0]}, [sp,:128] + mov r2, $key + mov r4, $fp @ preserve fp + + bl AES_encrypt + + vld1.8 {@XMM[0]}, [sp,:128] + veor @XMM[0], @XMM[0], @XMM[8] + vst1.8 {@XMM[0]}, [$out]! + mov $fp, r4 + + vmov @XMM[8], @XMM[9] @ next round tweak + +.Lxts_enc_done: +#ifndef XTS_CHAIN_TWEAK + adds $len, #0x10 + beq .Lxts_enc_ret + sub r6, $out, #0x10 + +.Lxts_enc_steal: + ldrb r0, [$inp], #1 + ldrb r1, [$out, #-0x10] + strb r0, [$out, #-0x10] + strb r1, [$out], #1 + + subs $len, #1 + bhi .Lxts_enc_steal + + vld1.8 {@XMM[0]}, [r6] + mov r0, sp + veor @XMM[0], @XMM[0], @XMM[8] + mov r1, sp + vst1.8 {@XMM[0]}, [sp,:128] + mov r2, $key + mov r4, $fp @ preserve fp + + bl AES_encrypt + + vld1.8 {@XMM[0]}, [sp,:128] + veor @XMM[0], @XMM[0], @XMM[8] + vst1.8 {@XMM[0]}, [r6] + mov $fp, r4 +#endif + +.Lxts_enc_ret: + bic r0, $fp, #0xf + vmov.i32 q0, #0 + vmov.i32 q1, #0 +#ifdef XTS_CHAIN_TWEAK + ldr r1, [$fp, #0x20+VFP_ABI_FRAME] @ chain tweak +#endif +.Lxts_enc_bzero: @ wipe key schedule [if any] + vstmia sp!, {q0-q1} + cmp sp, r0 + bne .Lxts_enc_bzero + + mov sp, $fp +#ifdef XTS_CHAIN_TWEAK + vst1.8 {@XMM[8]}, [r1] +#endif + VFP_ABI_POP + ldmia sp!, {r4-r10, pc} @ return + +.size bsaes_xts_encrypt,.-bsaes_xts_encrypt + +.globl bsaes_xts_decrypt +.type bsaes_xts_decrypt,%function +.align 4 +bsaes_xts_decrypt: + mov ip, sp + stmdb sp!, {r4-r10, lr} @ 0x20 + VFP_ABI_PUSH + mov r6, sp @ future $fp + + mov $inp, r0 + mov $out, r1 + mov $len, r2 + mov $key, r3 + + sub r0, sp, #0x10 @ 0x10 + bic r0, #0xf @ align at 16 bytes + mov sp, r0 + +#ifdef XTS_CHAIN_TWEAK + ldr r0, [ip] @ pointer to input tweak +#else + @ generate initial tweak + ldr r0, [ip, #4] @ iv[] + mov r1, sp + ldr r2, [ip, #0] @ key2 + bl AES_encrypt + mov r0, sp @ pointer to initial tweak +#endif + + ldr $rounds, [$key, #240] @ get # of rounds + mov $fp, r6 +#ifndef BSAES_ASM_EXTENDED_KEY + @ allocate the key schedule on the stack + sub r12, sp, $rounds, lsl#7 @ 128 bytes per inner round key + @ add r12, #`128-32` @ size of bit-sliced key schedule + sub r12, #`32+16` @ place for tweak[9] + + @ populate the key schedule + mov r4, $key @ pass key + mov r5, $rounds @ pass # of rounds + mov sp, r12 + add r12, #0x90 @ pass key schedule + bl _bsaes_key_convert + add r4, sp, #0x90 + vldmia r4, {@XMM[6]} + vstmia r12, {@XMM[15]} @ save last round key + veor @XMM[7], @XMM[7], @XMM[6] @ fix up round 0 key + vstmia r4, {@XMM[7]} +#else + ldr r12, [$key, #244] + eors r12, #1 + beq 0f + + str r12, [$key, #244] + mov r4, $key @ pass key + mov r5, $rounds @ pass # of rounds + add r12, $key, #248 @ pass key schedule + bl _bsaes_key_convert + add r4, $key, #248 + vldmia r4, {@XMM[6]} + vstmia r12, {@XMM[15]} @ save last round key + veor @XMM[7], @XMM[7], @XMM[6] @ fix up round 0 key + vstmia r4, {@XMM[7]} + +.align 2 +0: sub sp, #0x90 @ place for tweak[9] +#endif + vld1.8 {@XMM[8]}, [r0] @ initial tweak + adr $magic, .Lxts_magic + + tst $len, #0xf @ if not multiple of 16 + it ne @ Thumb2 thing, sanity check in ARM + subne $len, #0x10 @ subtract another 16 bytes + subs $len, #0x80 + + blo .Lxts_dec_short + b .Lxts_dec_loop + +.align 4 +.Lxts_dec_loop: + vldmia $magic, {$twmask} @ load XTS magic + vshr.s64 @T[0], @XMM[8], #63 + mov r0, sp + vand @T[0], @T[0], $twmask +___ +for($i=9;$i<16;$i++) { +$code.=<<___; + vadd.u64 @XMM[$i], @XMM[$i-1], @XMM[$i-1] + vst1.64 {@XMM[$i-1]}, [r0,:128]! + vswp `&Dhi("@T[0]")`,`&Dlo("@T[0]")` + vshr.s64 @T[1], @XMM[$i], #63 + veor @XMM[$i], @XMM[$i], @T[0] + vand @T[1], @T[1], $twmask +___ + @T=reverse(@T); + +$code.=<<___ if ($i>=10); + vld1.8 {@XMM[$i-10]}, [$inp]! +___ +$code.=<<___ if ($i>=11); + veor @XMM[$i-11], @XMM[$i-11], @XMM[$i-3] +___ +} +$code.=<<___; + vadd.u64 @XMM[8], @XMM[15], @XMM[15] + vst1.64 {@XMM[15]}, [r0,:128]! + vswp `&Dhi("@T[0]")`,`&Dlo("@T[0]")` + veor @XMM[8], @XMM[8], @T[0] + vst1.64 {@XMM[8]}, [r0,:128] @ next round tweak + + vld1.8 {@XMM[6]-@XMM[7]}, [$inp]! + veor @XMM[5], @XMM[5], @XMM[13] +#ifndef BSAES_ASM_EXTENDED_KEY + add r4, sp, #0x90 @ pass key schedule +#else + add r4, $key, #248 @ pass key schedule +#endif + veor @XMM[6], @XMM[6], @XMM[14] + mov r5, $rounds @ pass rounds + veor @XMM[7], @XMM[7], @XMM[15] + mov r0, sp + + bl _bsaes_decrypt8 + + vld1.64 {@XMM[ 8]-@XMM[ 9]}, [r0,:128]! + vld1.64 {@XMM[10]-@XMM[11]}, [r0,:128]! + veor @XMM[0], @XMM[0], @XMM[ 8] + vld1.64 {@XMM[12]-@XMM[13]}, [r0,:128]! + veor @XMM[1], @XMM[1], @XMM[ 9] + veor @XMM[8], @XMM[6], @XMM[10] + vst1.8 {@XMM[0]-@XMM[1]}, [$out]! + veor @XMM[9], @XMM[4], @XMM[11] + vld1.64 {@XMM[14]-@XMM[15]}, [r0,:128]! + veor @XMM[10], @XMM[2], @XMM[12] + vst1.8 {@XMM[8]-@XMM[9]}, [$out]! + veor @XMM[11], @XMM[7], @XMM[13] + veor @XMM[12], @XMM[3], @XMM[14] + vst1.8 {@XMM[10]-@XMM[11]}, [$out]! + veor @XMM[13], @XMM[5], @XMM[15] + vst1.8 {@XMM[12]-@XMM[13]}, [$out]! + + vld1.64 {@XMM[8]}, [r0,:128] @ next round tweak + + subs $len, #0x80 + bpl .Lxts_dec_loop + +.Lxts_dec_short: + adds $len, #0x70 + bmi .Lxts_dec_done + + vldmia $magic, {$twmask} @ load XTS magic + vshr.s64 @T[0], @XMM[8], #63 + mov r0, sp + vand @T[0], @T[0], $twmask +___ +for($i=9;$i<16;$i++) { +$code.=<<___; + vadd.u64 @XMM[$i], @XMM[$i-1], @XMM[$i-1] + vst1.64 {@XMM[$i-1]}, [r0,:128]! + vswp `&Dhi("@T[0]")`,`&Dlo("@T[0]")` + vshr.s64 @T[1], @XMM[$i], #63 + veor @XMM[$i], @XMM[$i], @T[0] + vand @T[1], @T[1], $twmask +___ + @T=reverse(@T); + +$code.=<<___ if ($i>=10); + vld1.8 {@XMM[$i-10]}, [$inp]! + subs $len, #0x10 + bmi .Lxts_dec_`$i-9` +___ +$code.=<<___ if ($i>=11); + veor @XMM[$i-11], @XMM[$i-11], @XMM[$i-3] +___ +} +$code.=<<___; + sub $len, #0x10 + vst1.64 {@XMM[15]}, [r0,:128] @ next round tweak + + vld1.8 {@XMM[6]}, [$inp]! + veor @XMM[5], @XMM[5], @XMM[13] +#ifndef BSAES_ASM_EXTENDED_KEY + add r4, sp, #0x90 @ pass key schedule +#else + add r4, $key, #248 @ pass key schedule +#endif + veor @XMM[6], @XMM[6], @XMM[14] + mov r5, $rounds @ pass rounds + mov r0, sp + + bl _bsaes_decrypt8 + + vld1.64 {@XMM[ 8]-@XMM[ 9]}, [r0,:128]! + vld1.64 {@XMM[10]-@XMM[11]}, [r0,:128]! + veor @XMM[0], @XMM[0], @XMM[ 8] + vld1.64 {@XMM[12]-@XMM[13]}, [r0,:128]! + veor @XMM[1], @XMM[1], @XMM[ 9] + veor @XMM[8], @XMM[6], @XMM[10] + vst1.8 {@XMM[0]-@XMM[1]}, [$out]! + veor @XMM[9], @XMM[4], @XMM[11] + vld1.64 {@XMM[14]}, [r0,:128]! + veor @XMM[10], @XMM[2], @XMM[12] + vst1.8 {@XMM[8]-@XMM[9]}, [$out]! + veor @XMM[11], @XMM[7], @XMM[13] + veor @XMM[12], @XMM[3], @XMM[14] + vst1.8 {@XMM[10]-@XMM[11]}, [$out]! + vst1.8 {@XMM[12]}, [$out]! + + vld1.64 {@XMM[8]}, [r0,:128] @ next round tweak + b .Lxts_dec_done +.align 4 +.Lxts_dec_6: + vst1.64 {@XMM[14]}, [r0,:128] @ next round tweak + + veor @XMM[4], @XMM[4], @XMM[12] +#ifndef BSAES_ASM_EXTENDED_KEY + add r4, sp, #0x90 @ pass key schedule +#else + add r4, $key, #248 @ pass key schedule +#endif + veor @XMM[5], @XMM[5], @XMM[13] + mov r5, $rounds @ pass rounds + mov r0, sp + + bl _bsaes_decrypt8 + + vld1.64 {@XMM[ 8]-@XMM[ 9]}, [r0,:128]! + vld1.64 {@XMM[10]-@XMM[11]}, [r0,:128]! + veor @XMM[0], @XMM[0], @XMM[ 8] + vld1.64 {@XMM[12]-@XMM[13]}, [r0,:128]! + veor @XMM[1], @XMM[1], @XMM[ 9] + veor @XMM[8], @XMM[6], @XMM[10] + vst1.8 {@XMM[0]-@XMM[1]}, [$out]! + veor @XMM[9], @XMM[4], @XMM[11] + veor @XMM[10], @XMM[2], @XMM[12] + vst1.8 {@XMM[8]-@XMM[9]}, [$out]! + veor @XMM[11], @XMM[7], @XMM[13] + vst1.8 {@XMM[10]-@XMM[11]}, [$out]! + + vld1.64 {@XMM[8]}, [r0,:128] @ next round tweak + b .Lxts_dec_done +.align 4 +.Lxts_dec_5: + vst1.64 {@XMM[13]}, [r0,:128] @ next round tweak + + veor @XMM[3], @XMM[3], @XMM[11] +#ifndef BSAES_ASM_EXTENDED_KEY + add r4, sp, #0x90 @ pass key schedule +#else + add r4, $key, #248 @ pass key schedule +#endif + veor @XMM[4], @XMM[4], @XMM[12] + mov r5, $rounds @ pass rounds + mov r0, sp + + bl _bsaes_decrypt8 + + vld1.64 {@XMM[ 8]-@XMM[ 9]}, [r0,:128]! + vld1.64 {@XMM[10]-@XMM[11]}, [r0,:128]! + veor @XMM[0], @XMM[0], @XMM[ 8] + vld1.64 {@XMM[12]}, [r0,:128]! + veor @XMM[1], @XMM[1], @XMM[ 9] + veor @XMM[8], @XMM[6], @XMM[10] + vst1.8 {@XMM[0]-@XMM[1]}, [$out]! + veor @XMM[9], @XMM[4], @XMM[11] + veor @XMM[10], @XMM[2], @XMM[12] + vst1.8 {@XMM[8]-@XMM[9]}, [$out]! + vst1.8 {@XMM[10]}, [$out]! + + vld1.64 {@XMM[8]}, [r0,:128] @ next round tweak + b .Lxts_dec_done +.align 4 +.Lxts_dec_4: + vst1.64 {@XMM[12]}, [r0,:128] @ next round tweak + + veor @XMM[2], @XMM[2], @XMM[10] +#ifndef BSAES_ASM_EXTENDED_KEY + add r4, sp, #0x90 @ pass key schedule +#else + add r4, $key, #248 @ pass key schedule +#endif + veor @XMM[3], @XMM[3], @XMM[11] + mov r5, $rounds @ pass rounds + mov r0, sp + + bl _bsaes_decrypt8 + + vld1.64 {@XMM[ 8]-@XMM[ 9]}, [r0,:128]! + vld1.64 {@XMM[10]-@XMM[11]}, [r0,:128]! + veor @XMM[0], @XMM[0], @XMM[ 8] + veor @XMM[1], @XMM[1], @XMM[ 9] + veor @XMM[8], @XMM[6], @XMM[10] + vst1.8 {@XMM[0]-@XMM[1]}, [$out]! + veor @XMM[9], @XMM[4], @XMM[11] + vst1.8 {@XMM[8]-@XMM[9]}, [$out]! + + vld1.64 {@XMM[8]}, [r0,:128] @ next round tweak + b .Lxts_dec_done +.align 4 +.Lxts_dec_3: + vst1.64 {@XMM[11]}, [r0,:128] @ next round tweak + + veor @XMM[1], @XMM[1], @XMM[9] +#ifndef BSAES_ASM_EXTENDED_KEY + add r4, sp, #0x90 @ pass key schedule +#else + add r4, $key, #248 @ pass key schedule +#endif + veor @XMM[2], @XMM[2], @XMM[10] + mov r5, $rounds @ pass rounds + mov r0, sp + + bl _bsaes_decrypt8 + + vld1.64 {@XMM[8]-@XMM[9]}, [r0,:128]! + vld1.64 {@XMM[10]}, [r0,:128]! + veor @XMM[0], @XMM[0], @XMM[ 8] + veor @XMM[1], @XMM[1], @XMM[ 9] + veor @XMM[8], @XMM[6], @XMM[10] + vst1.8 {@XMM[0]-@XMM[1]}, [$out]! + vst1.8 {@XMM[8]}, [$out]! + + vld1.64 {@XMM[8]}, [r0,:128] @ next round tweak + b .Lxts_dec_done +.align 4 +.Lxts_dec_2: + vst1.64 {@XMM[10]}, [r0,:128] @ next round tweak + + veor @XMM[0], @XMM[0], @XMM[8] +#ifndef BSAES_ASM_EXTENDED_KEY + add r4, sp, #0x90 @ pass key schedule +#else + add r4, $key, #248 @ pass key schedule +#endif + veor @XMM[1], @XMM[1], @XMM[9] + mov r5, $rounds @ pass rounds + mov r0, sp + + bl _bsaes_decrypt8 + + vld1.64 {@XMM[8]-@XMM[9]}, [r0,:128]! + veor @XMM[0], @XMM[0], @XMM[ 8] + veor @XMM[1], @XMM[1], @XMM[ 9] + vst1.8 {@XMM[0]-@XMM[1]}, [$out]! + + vld1.64 {@XMM[8]}, [r0,:128] @ next round tweak + b .Lxts_dec_done +.align 4 +.Lxts_dec_1: + mov r0, sp + veor @XMM[0], @XMM[8] + mov r1, sp + vst1.8 {@XMM[0]}, [sp,:128] + mov r2, $key + mov r4, $fp @ preserve fp + mov r5, $magic @ preserve magic + + bl AES_decrypt + + vld1.8 {@XMM[0]}, [sp,:128] + veor @XMM[0], @XMM[0], @XMM[8] + vst1.8 {@XMM[0]}, [$out]! + mov $fp, r4 + mov $magic, r5 + + vmov @XMM[8], @XMM[9] @ next round tweak + +.Lxts_dec_done: +#ifndef XTS_CHAIN_TWEAK + adds $len, #0x10 + beq .Lxts_dec_ret + + @ calculate one round of extra tweak for the stolen ciphertext + vldmia $magic, {$twmask} + vshr.s64 @XMM[6], @XMM[8], #63 + vand @XMM[6], @XMM[6], $twmask + vadd.u64 @XMM[9], @XMM[8], @XMM[8] + vswp `&Dhi("@XMM[6]")`,`&Dlo("@XMM[6]")` + veor @XMM[9], @XMM[9], @XMM[6] + + @ perform the final decryption with the last tweak value + vld1.8 {@XMM[0]}, [$inp]! + mov r0, sp + veor @XMM[0], @XMM[0], @XMM[9] + mov r1, sp + vst1.8 {@XMM[0]}, [sp,:128] + mov r2, $key + mov r4, $fp @ preserve fp + + bl AES_decrypt + + vld1.8 {@XMM[0]}, [sp,:128] + veor @XMM[0], @XMM[0], @XMM[9] + vst1.8 {@XMM[0]}, [$out] + + mov r6, $out +.Lxts_dec_steal: + ldrb r1, [$out] + ldrb r0, [$inp], #1 + strb r1, [$out, #0x10] + strb r0, [$out], #1 + + subs $len, #1 + bhi .Lxts_dec_steal + + vld1.8 {@XMM[0]}, [r6] + mov r0, sp + veor @XMM[0], @XMM[8] + mov r1, sp + vst1.8 {@XMM[0]}, [sp,:128] + mov r2, $key + + bl AES_decrypt + + vld1.8 {@XMM[0]}, [sp,:128] + veor @XMM[0], @XMM[0], @XMM[8] + vst1.8 {@XMM[0]}, [r6] + mov $fp, r4 +#endif + +.Lxts_dec_ret: + bic r0, $fp, #0xf + vmov.i32 q0, #0 + vmov.i32 q1, #0 +#ifdef XTS_CHAIN_TWEAK + ldr r1, [$fp, #0x20+VFP_ABI_FRAME] @ chain tweak +#endif +.Lxts_dec_bzero: @ wipe key schedule [if any] + vstmia sp!, {q0-q1} + cmp sp, r0 + bne .Lxts_dec_bzero + + mov sp, $fp +#ifdef XTS_CHAIN_TWEAK + vst1.8 {@XMM[8]}, [r1] +#endif + VFP_ABI_POP + ldmia sp!, {r4-r10, pc} @ return + +.size bsaes_xts_decrypt,.-bsaes_xts_decrypt +___ +} +$code.=<<___; +#endif +___ + +$code =~ s/\`([^\`]*)\`/eval($1)/gem; + +open SELF,$0; +while(<SELF>) { + next if (/^#!/); + last if (!s/^#/@/ and !/^$/); + print; +} +close SELF; + +print $code; + +close STDOUT; diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild index d3db39860b9c..a6395c027715 100644 --- a/arch/arm/include/asm/Kbuild +++ b/arch/arm/include/asm/Kbuild @@ -24,6 +24,7 @@ generic-y += sembuf.h generic-y += serial.h generic-y += shmbuf.h generic-y += siginfo.h +generic-y += simd.h generic-y += sizes.h generic-y += socket.h generic-y += sockios.h @@ -31,5 +32,4 @@ generic-y += termbits.h generic-y += termios.h generic-y += timex.h generic-y += trace_clock.h -generic-y += types.h generic-y += unaligned.h diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h index fcc1b5bf6979..5c2285160575 100644 --- a/arch/arm/include/asm/assembler.h +++ b/arch/arm/include/asm/assembler.h @@ -53,6 +53,13 @@ #define put_byte_3 lsl #0 #endif +/* Select code for any configuration running in BE8 mode */ +#ifdef CONFIG_CPU_ENDIAN_BE8 +#define ARM_BE8(code...) code +#else +#define ARM_BE8(code...) +#endif + /* * Data preload for architectures that support it */ diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h index da1c77d39327..134aa28b6f64 100644 --- a/arch/arm/include/asm/atomic.h +++ b/arch/arm/include/asm/atomic.h @@ -12,6 +12,7 @@ #define __ASM_ARM_ATOMIC_H #include <linux/compiler.h> +#include <linux/prefetch.h> #include <linux/types.h> #include <linux/irqflags.h> #include <asm/barrier.h> @@ -41,6 +42,7 @@ static inline void atomic_add(int i, atomic_t *v) unsigned long tmp; int result; + prefetchw(&v->counter); __asm__ __volatile__("@ atomic_add\n" "1: ldrex %0, [%3]\n" " add %0, %0, %4\n" @@ -79,6 +81,7 @@ static inline void atomic_sub(int i, atomic_t *v) unsigned long tmp; int result; + prefetchw(&v->counter); __asm__ __volatile__("@ atomic_sub\n" "1: ldrex %0, [%3]\n" " sub %0, %0, %4\n" @@ -138,6 +141,7 @@ static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr) { unsigned long tmp, tmp2; + prefetchw(addr); __asm__ __volatile__("@ atomic_clear_mask\n" "1: ldrex %0, [%3]\n" " bic %0, %0, %4\n" @@ -283,6 +287,7 @@ static inline void atomic64_set(atomic64_t *v, u64 i) { u64 tmp; + prefetchw(&v->counter); __asm__ __volatile__("@ atomic64_set\n" "1: ldrexd %0, %H0, [%2]\n" " strexd %0, %3, %H3, [%2]\n" @@ -299,10 +304,11 @@ static inline void atomic64_add(u64 i, atomic64_t *v) u64 result; unsigned long tmp; + prefetchw(&v->counter); __asm__ __volatile__("@ atomic64_add\n" "1: ldrexd %0, %H0, [%3]\n" -" adds %0, %0, %4\n" -" adc %H0, %H0, %H4\n" +" adds %Q0, %Q0, %Q4\n" +" adc %R0, %R0, %R4\n" " strexd %1, %0, %H0, [%3]\n" " teq %1, #0\n" " bne 1b" @@ -320,8 +326,8 @@ static inline u64 atomic64_add_return(u64 i, atomic64_t *v) __asm__ __volatile__("@ atomic64_add_return\n" "1: ldrexd %0, %H0, [%3]\n" -" adds %0, %0, %4\n" -" adc %H0, %H0, %H4\n" +" adds %Q0, %Q0, %Q4\n" +" adc %R0, %R0, %R4\n" " strexd %1, %0, %H0, [%3]\n" " teq %1, #0\n" " bne 1b" @@ -339,10 +345,11 @@ static inline void atomic64_sub(u64 i, atomic64_t *v) u64 result; unsigned long tmp; + prefetchw(&v->counter); __asm__ __volatile__("@ atomic64_sub\n" "1: ldrexd %0, %H0, [%3]\n" -" subs %0, %0, %4\n" -" sbc %H0, %H0, %H4\n" +" subs %Q0, %Q0, %Q4\n" +" sbc %R0, %R0, %R4\n" " strexd %1, %0, %H0, [%3]\n" " teq %1, #0\n" " bne 1b" @@ -360,8 +367,8 @@ static inline u64 atomic64_sub_return(u64 i, atomic64_t *v) __asm__ __volatile__("@ atomic64_sub_return\n" "1: ldrexd %0, %H0, [%3]\n" -" subs %0, %0, %4\n" -" sbc %H0, %H0, %H4\n" +" subs %Q0, %Q0, %Q4\n" +" sbc %R0, %R0, %R4\n" " strexd %1, %0, %H0, [%3]\n" " teq %1, #0\n" " bne 1b" @@ -428,9 +435,9 @@ static inline u64 atomic64_dec_if_positive(atomic64_t *v) __asm__ __volatile__("@ atomic64_dec_if_positive\n" "1: ldrexd %0, %H0, [%3]\n" -" subs %0, %0, #1\n" -" sbc %H0, %H0, #0\n" -" teq %H0, #0\n" +" subs %Q0, %Q0, #1\n" +" sbc %R0, %R0, #0\n" +" teq %R0, #0\n" " bmi 2f\n" " strexd %1, %0, %H0, [%3]\n" " teq %1, #0\n" @@ -459,8 +466,8 @@ static inline int atomic64_add_unless(atomic64_t *v, u64 a, u64 u) " teqeq %H0, %H5\n" " moveq %1, #0\n" " beq 2f\n" -" adds %0, %0, %6\n" -" adc %H0, %H0, %H6\n" +" adds %Q0, %Q0, %Q6\n" +" adc %R0, %R0, %R6\n" " strexd %2, %0, %H0, [%4]\n" " teq %2, #0\n" " bne 1b\n" diff --git a/arch/arm/include/asm/bL_switcher.h b/arch/arm/include/asm/bL_switcher.h new file mode 100644 index 000000000000..1714800fa113 --- /dev/null +++ b/arch/arm/include/asm/bL_switcher.h @@ -0,0 +1,77 @@ +/* + * arch/arm/include/asm/bL_switcher.h + * + * Created by: Nicolas Pitre, April 2012 + * Copyright: (C) 2012-2013 Linaro Limited + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef ASM_BL_SWITCHER_H +#define ASM_BL_SWITCHER_H + +#include <linux/compiler.h> +#include <linux/types.h> + +typedef void (*bL_switch_completion_handler)(void *cookie); + +int bL_switch_request_cb(unsigned int cpu, unsigned int new_cluster_id, + bL_switch_completion_handler completer, + void *completer_cookie); +static inline int bL_switch_request(unsigned int cpu, unsigned int new_cluster_id) +{ + return bL_switch_request_cb(cpu, new_cluster_id, NULL, NULL); +} + +/* + * Register here to be notified about runtime enabling/disabling of + * the switcher. + * + * The notifier chain is called with the switcher activation lock held: + * the switcher will not be enabled or disabled during callbacks. + * Callbacks must not call bL_switcher_{get,put}_enabled(). + */ +#define BL_NOTIFY_PRE_ENABLE 0 +#define BL_NOTIFY_POST_ENABLE 1 +#define BL_NOTIFY_PRE_DISABLE 2 +#define BL_NOTIFY_POST_DISABLE 3 + +#ifdef CONFIG_BL_SWITCHER + +int bL_switcher_register_notifier(struct notifier_block *nb); +int bL_switcher_unregister_notifier(struct notifier_block *nb); + +/* + * Use these functions to temporarily prevent enabling/disabling of + * the switcher. + * bL_switcher_get_enabled() returns true if the switcher is currently + * enabled. Each call to bL_switcher_get_enabled() must be followed + * by a call to bL_switcher_put_enabled(). These functions are not + * recursive. + */ +bool bL_switcher_get_enabled(void); +void bL_switcher_put_enabled(void); + +int bL_switcher_trace_trigger(void); +int bL_switcher_get_logical_index(u32 mpidr); + +#else +static inline int bL_switcher_register_notifier(struct notifier_block *nb) +{ + return 0; +} + +static inline int bL_switcher_unregister_notifier(struct notifier_block *nb) +{ + return 0; +} + +static inline bool bL_switcher_get_enabled(void) { return false; } +static inline void bL_switcher_put_enabled(void) { } +static inline int bL_switcher_trace_trigger(void) { return 0; } +static inline int bL_switcher_get_logical_index(u32 mpidr) { return -EUNATCH; } +#endif /* CONFIG_BL_SWITCHER */ + +#endif diff --git a/arch/arm/include/asm/bug.h b/arch/arm/include/asm/bug.h index 7af5c6c3653a..b274bde24905 100644 --- a/arch/arm/include/asm/bug.h +++ b/arch/arm/include/asm/bug.h @@ -2,6 +2,8 @@ #define _ASMARM_BUG_H #include <linux/linkage.h> +#include <linux/types.h> +#include <asm/opcodes.h> #ifdef CONFIG_BUG @@ -12,10 +14,10 @@ */ #ifdef CONFIG_THUMB2_KERNEL #define BUG_INSTR_VALUE 0xde02 -#define BUG_INSTR_TYPE ".hword " +#define BUG_INSTR(__value) __inst_thumb16(__value) #else #define BUG_INSTR_VALUE 0xe7f001f2 -#define BUG_INSTR_TYPE ".word " +#define BUG_INSTR(__value) __inst_arm(__value) #endif @@ -33,7 +35,7 @@ #define __BUG(__file, __line, __value) \ do { \ - asm volatile("1:\t" BUG_INSTR_TYPE #__value "\n" \ + asm volatile("1:\t" BUG_INSTR(__value) "\n" \ ".pushsection .rodata.str, \"aMS\", %progbits, 1\n" \ "2:\t.asciz " #__file "\n" \ ".popsection\n" \ @@ -48,7 +50,7 @@ do { \ #define __BUG(__file, __line, __value) \ do { \ - asm volatile(BUG_INSTR_TYPE #__value); \ + asm volatile(BUG_INSTR(__value) "\n"); \ unreachable(); \ } while (0) #endif /* CONFIG_DEBUG_BUGVERBOSE */ diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index 15f2d5bf8875..ee753f1749cd 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -435,4 +435,50 @@ static inline void __sync_cache_range_r(volatile void *p, size_t size) #define sync_cache_w(ptr) __sync_cache_range_w(ptr, sizeof *(ptr)) #define sync_cache_r(ptr) __sync_cache_range_r(ptr, sizeof *(ptr)) +/* + * Disabling cache access for one CPU in an ARMv7 SMP system is tricky. + * To do so we must: + * + * - Clear the SCTLR.C bit to prevent further cache allocations + * - Flush the desired level of cache + * - Clear the ACTLR "SMP" bit to disable local coherency + * + * ... and so without any intervening memory access in between those steps, + * not even to the stack. + * + * WARNING -- After this has been called: + * + * - No ldrex/strex (and similar) instructions must be used. + * - The CPU is obviously no longer coherent with the other CPUs. + * - This is unlikely to work as expected if Linux is running non-secure. + * + * Note: + * + * - This is known to apply to several ARMv7 processor implementations, + * however some exceptions may exist. Caveat emptor. + * + * - The clobber list is dictated by the call to v7_flush_dcache_*. + * fp is preserved to the stack explicitly prior disabling the cache + * since adding it to the clobber list is incompatible with having + * CONFIG_FRAME_POINTER=y. ip is saved as well if ever r12-clobbering + * trampoline are inserted by the linker and to keep sp 64-bit aligned. + */ +#define v7_exit_coherency_flush(level) \ + asm volatile( \ + "stmfd sp!, {fp, ip} \n\t" \ + "mrc p15, 0, r0, c1, c0, 0 @ get SCTLR \n\t" \ + "bic r0, r0, #"__stringify(CR_C)" \n\t" \ + "mcr p15, 0, r0, c1, c0, 0 @ set SCTLR \n\t" \ + "isb \n\t" \ + "bl v7_flush_dcache_"__stringify(level)" \n\t" \ + "clrex \n\t" \ + "mrc p15, 0, r0, c1, c0, 1 @ get ACTLR \n\t" \ + "bic r0, r0, #(1 << 6) @ disable local coherency \n\t" \ + "mcr p15, 0, r0, c1, c0, 1 @ set ACTLR \n\t" \ + "isb \n\t" \ + "dsb \n\t" \ + "ldmfd sp!, {fp, ip}" \ + : : : "r0","r1","r2","r3","r4","r5","r6","r7", \ + "r9","r10","lr","memory" ) + #endif diff --git a/arch/arm/include/asm/cmpxchg.h b/arch/arm/include/asm/cmpxchg.h index 4f009c10540d..df2fbba7efc8 100644 --- a/arch/arm/include/asm/cmpxchg.h +++ b/arch/arm/include/asm/cmpxchg.h @@ -223,6 +223,42 @@ static inline unsigned long __cmpxchg_local(volatile void *ptr, return ret; } +static inline unsigned long long __cmpxchg64(unsigned long long *ptr, + unsigned long long old, + unsigned long long new) +{ + unsigned long long oldval; + unsigned long res; + + __asm__ __volatile__( +"1: ldrexd %1, %H1, [%3]\n" +" teq %1, %4\n" +" teqeq %H1, %H4\n" +" bne 2f\n" +" strexd %0, %5, %H5, [%3]\n" +" teq %0, #0\n" +" bne 1b\n" +"2:" + : "=&r" (res), "=&r" (oldval), "+Qo" (*ptr) + : "r" (ptr), "r" (old), "r" (new) + : "cc"); + + return oldval; +} + +static inline unsigned long long __cmpxchg64_mb(unsigned long long *ptr, + unsigned long long old, + unsigned long long new) +{ + unsigned long long ret; + + smp_mb(); + ret = __cmpxchg64(ptr, old, new); + smp_mb(); + + return ret; +} + #define cmpxchg_local(ptr,o,n) \ ((__typeof__(*(ptr)))__cmpxchg_local((ptr), \ (unsigned long)(o), \ @@ -230,18 +266,16 @@ static inline unsigned long __cmpxchg_local(volatile void *ptr, sizeof(*(ptr)))) #define cmpxchg64(ptr, o, n) \ - ((__typeof__(*(ptr)))atomic64_cmpxchg(container_of((ptr), \ - atomic64_t, \ - counter), \ - (unsigned long long)(o), \ - (unsigned long long)(n))) - -#define cmpxchg64_local(ptr, o, n) \ - ((__typeof__(*(ptr)))local64_cmpxchg(container_of((ptr), \ - local64_t, \ - a), \ - (unsigned long long)(o), \ - (unsigned long long)(n))) + ((__typeof__(*(ptr)))__cmpxchg64_mb((ptr), \ + (unsigned long long)(o), \ + (unsigned long long)(n))) + +#define cmpxchg64_relaxed(ptr, o, n) \ + ((__typeof__(*(ptr)))__cmpxchg64((ptr), \ + (unsigned long long)(o), \ + (unsigned long long)(n))) + +#define cmpxchg64_local(ptr, o, n) cmpxchg64_relaxed((ptr), (o), (n)) #endif /* __LINUX_ARM_ARCH__ >= 6 */ diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h index 9672e978d50d..acdde76b39bb 100644 --- a/arch/arm/include/asm/cputype.h +++ b/arch/arm/include/asm/cputype.h @@ -10,6 +10,7 @@ #define CPUID_TLBTYPE 3 #define CPUID_MPUIR 4 #define CPUID_MPIDR 5 +#define CPUID_REVIDR 6 #ifdef CONFIG_CPU_V7M #define CPUID_EXT_PFR0 0x40 diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h index 5b579b951503..863cd84eb1a2 100644 --- a/arch/arm/include/asm/dma-mapping.h +++ b/arch/arm/include/asm/dma-mapping.h @@ -64,6 +64,7 @@ static inline dma_addr_t virt_to_dma(struct device *dev, void *addr) { return (dma_addr_t)__virt_to_bus((unsigned long)(addr)); } + #else static inline dma_addr_t pfn_to_dma(struct device *dev, unsigned long pfn) { @@ -86,6 +87,13 @@ static inline dma_addr_t virt_to_dma(struct device *dev, void *addr) } #endif +/* The ARM override for dma_max_pfn() */ +static inline unsigned long dma_max_pfn(struct device *dev) +{ + return PHYS_PFN_OFFSET + dma_to_pfn(dev, *dev->dma_mask); +} +#define dma_max_pfn(dev) dma_max_pfn(dev) + /* * DMA errors are defined by all-bits-set in the DMA address. */ diff --git a/arch/arm/include/asm/hardirq.h b/arch/arm/include/asm/hardirq.h index 2740c2a2df63..3d7351c844aa 100644 --- a/arch/arm/include/asm/hardirq.h +++ b/arch/arm/include/asm/hardirq.h @@ -5,7 +5,7 @@ #include <linux/threads.h> #include <asm/irq.h> -#define NR_IPI 6 +#define NR_IPI 7 typedef struct { unsigned int __softirq_pending; diff --git a/arch/arm/include/asm/hardware/coresight.h b/arch/arm/include/asm/hardware/coresight.h index 0cf7a6b842ff..ad774f37c47c 100644 --- a/arch/arm/include/asm/hardware/coresight.h +++ b/arch/arm/include/asm/hardware/coresight.h @@ -24,8 +24,8 @@ #define TRACER_TIMEOUT 10000 #define etm_writel(t, v, x) \ - (__raw_writel((v), (t)->etm_regs + (x))) -#define etm_readl(t, x) (__raw_readl((t)->etm_regs + (x))) + (writel_relaxed((v), (t)->etm_regs + (x))) +#define etm_readl(t, x) (readl_relaxed((t)->etm_regs + (x))) /* CoreSight Management Registers */ #define CSMR_LOCKACCESS 0xfb0 @@ -142,8 +142,8 @@ #define ETBFF_TRIGFL BIT(10) #define etb_writel(t, v, x) \ - (__raw_writel((v), (t)->etb_regs + (x))) -#define etb_readl(t, x) (__raw_readl((t)->etb_regs + (x))) + (writel_relaxed((v), (t)->etb_regs + (x))) +#define etb_readl(t, x) (readl_relaxed((t)->etb_regs + (x))) #define etm_lock(t) do { etm_writel((t), 0, CSMR_LOCKACCESS); } while (0) #define etm_unlock(t) \ diff --git a/arch/arm/include/asm/kgdb.h b/arch/arm/include/asm/kgdb.h index 48066ce9ea34..0a9d5dd93294 100644 --- a/arch/arm/include/asm/kgdb.h +++ b/arch/arm/include/asm/kgdb.h @@ -11,6 +11,7 @@ #define __ARM_KGDB_H__ #include <linux/ptrace.h> +#include <asm/opcodes.h> /* * GDB assumes that we're a user process being debugged, so @@ -41,7 +42,7 @@ static inline void arch_kgdb_breakpoint(void) { - asm(".word 0xe7ffdeff"); + asm(__inst_arm(0xe7ffdeff)); } extern void kgdb_handle_bus_error(void); diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h index 402a2bc6aa68..17a3fa2979e8 100644 --- a/arch/arm/include/asm/mach/arch.h +++ b/arch/arm/include/asm/mach/arch.h @@ -49,6 +49,7 @@ struct machine_desc { bool (*smp_init)(void); void (*fixup)(struct tag *, char **, struct meminfo *); + void (*init_meminfo)(void); void (*reserve)(void);/* reserve mem blocks */ void (*map_io)(void);/* IO mapping function */ void (*init_early)(void); diff --git a/arch/arm/include/asm/mcpm.h b/arch/arm/include/asm/mcpm.h index 0f7b7620e9a5..608516ebabfe 100644 --- a/arch/arm/include/asm/mcpm.h +++ b/arch/arm/include/asm/mcpm.h @@ -42,6 +42,14 @@ extern void mcpm_entry_point(void); void mcpm_set_entry_vector(unsigned cpu, unsigned cluster, void *ptr); /* + * This sets an early poke i.e a value to be poked into some address + * from very early assembly code before the CPU is ungated. The + * address must be physical, and if 0 then nothing will happen. + */ +void mcpm_set_early_poke(unsigned cpu, unsigned cluster, + unsigned long poke_phys_addr, unsigned long poke_val); + +/* * CPU/cluster power operations API for higher subsystems to use. */ @@ -76,12 +84,45 @@ int mcpm_cpu_power_up(unsigned int cpu, unsigned int cluster); * * This must be called with interrupts disabled. * - * This does not return. Re-entry in the kernel is expected via - * mcpm_entry_point. + * On success this does not return. Re-entry in the kernel is expected + * via mcpm_entry_point. + * + * This will return if mcpm_platform_register() has not been called + * previously in which case the caller should take appropriate action. + * + * On success, the CPU is not guaranteed to be truly halted until + * mcpm_cpu_power_down_finish() subsequently returns non-zero for the + * specified cpu. Until then, other CPUs should make sure they do not + * trash memory the target CPU might be executing/accessing. */ void mcpm_cpu_power_down(void); /** + * mcpm_cpu_power_down_finish - wait for a specified CPU to halt, and + * make sure it is powered off + * + * @cpu: CPU number within given cluster + * @cluster: cluster number for the CPU + * + * Call this function to ensure that a pending powerdown has taken + * effect and the CPU is safely parked before performing non-mcpm + * operations that may affect the CPU (such as kexec trashing the + * kernel text). + * + * It is *not* necessary to call this function if you only need to + * serialise a pending powerdown with mcpm_cpu_power_up() or a wakeup + * event. + * + * Do not call this function unless the specified CPU has already + * called mcpm_cpu_power_down() or has committed to doing so. + * + * @return: + * - zero if the CPU is in a safely parked state + * - nonzero otherwise (e.g., timeout) + */ +int mcpm_cpu_power_down_finish(unsigned int cpu, unsigned int cluster); + +/** * mcpm_cpu_suspend - bring the calling CPU in a suspended state * * @expected_residency: duration in microseconds the CPU is expected @@ -98,8 +139,11 @@ void mcpm_cpu_power_down(void); * * This must be called with interrupts disabled. * - * This does not return. Re-entry in the kernel is expected via - * mcpm_entry_point. + * On success this does not return. Re-entry in the kernel is expected + * via mcpm_entry_point. + * + * This will return if mcpm_platform_register() has not been called + * previously in which case the caller should take appropriate action. */ void mcpm_cpu_suspend(u64 expected_residency); @@ -120,6 +164,7 @@ int mcpm_cpu_powered_up(void); struct mcpm_platform_ops { int (*power_up)(unsigned int cpu, unsigned int cluster); void (*power_down)(void); + int (*power_down_finish)(unsigned int cpu, unsigned int cluster); void (*suspend)(u64); void (*powered_up)(void); }; diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h index e750a938fd3c..4dd21457ef9d 100644 --- a/arch/arm/include/asm/memory.h +++ b/arch/arm/include/asm/memory.h @@ -172,8 +172,13 @@ * so that all we need to do is modify the 8-bit constant field. */ #define __PV_BITS_31_24 0x81000000 +#define __PV_BITS_7_0 0x81 + +extern u64 __pv_phys_offset; +extern u64 __pv_offset; +extern void fixup_pv_table(const void *, unsigned long); +extern const void *__pv_table_begin, *__pv_table_end; -extern unsigned long __pv_phys_offset; #define PHYS_OFFSET __pv_phys_offset #define __pv_stub(from,to,instr,type) \ @@ -185,22 +190,58 @@ extern unsigned long __pv_phys_offset; : "=r" (to) \ : "r" (from), "I" (type)) -static inline unsigned long __virt_to_phys(unsigned long x) +#define __pv_stub_mov_hi(t) \ + __asm__ volatile("@ __pv_stub_mov\n" \ + "1: mov %R0, %1\n" \ + " .pushsection .pv_table,\"a\"\n" \ + " .long 1b\n" \ + " .popsection\n" \ + : "=r" (t) \ + : "I" (__PV_BITS_7_0)) + +#define __pv_add_carry_stub(x, y) \ + __asm__ volatile("@ __pv_add_carry_stub\n" \ + "1: adds %Q0, %1, %2\n" \ + " adc %R0, %R0, #0\n" \ + " .pushsection .pv_table,\"a\"\n" \ + " .long 1b\n" \ + " .popsection\n" \ + : "+r" (y) \ + : "r" (x), "I" (__PV_BITS_31_24) \ + : "cc") + +static inline phys_addr_t __virt_to_phys(unsigned long x) { - unsigned long t; - __pv_stub(x, t, "add", __PV_BITS_31_24); + phys_addr_t t; + + if (sizeof(phys_addr_t) == 4) { + __pv_stub(x, t, "add", __PV_BITS_31_24); + } else { + __pv_stub_mov_hi(t); + __pv_add_carry_stub(x, t); + } return t; } -static inline unsigned long __phys_to_virt(unsigned long x) +static inline unsigned long __phys_to_virt(phys_addr_t x) { unsigned long t; __pv_stub(x, t, "sub", __PV_BITS_31_24); return t; } + #else -#define __virt_to_phys(x) ((x) - PAGE_OFFSET + PHYS_OFFSET) -#define __phys_to_virt(x) ((x) - PHYS_OFFSET + PAGE_OFFSET) + +static inline phys_addr_t __virt_to_phys(unsigned long x) +{ + return (phys_addr_t)x - PAGE_OFFSET + PHYS_OFFSET; +} + +static inline unsigned long __phys_to_virt(phys_addr_t x) +{ + return x - PHYS_OFFSET + PAGE_OFFSET; +} + #endif #endif #endif /* __ASSEMBLY__ */ @@ -238,16 +279,33 @@ static inline phys_addr_t virt_to_phys(const volatile void *x) static inline void *phys_to_virt(phys_addr_t x) { - return (void *)(__phys_to_virt((unsigned long)(x))); + return (void *)__phys_to_virt(x); } /* * Drivers should NOT use these either. */ #define __pa(x) __virt_to_phys((unsigned long)(x)) -#define __va(x) ((void *)__phys_to_virt((unsigned long)(x))) +#define __va(x) ((void *)__phys_to_virt((phys_addr_t)(x))) #define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) +extern phys_addr_t (*arch_virt_to_idmap)(unsigned long x); + +/* + * These are for systems that have a hardware interconnect supported alias of + * physical memory for idmap purposes. Most cases should leave these + * untouched. + */ +static inline phys_addr_t __virt_to_idmap(unsigned long x) +{ + if (arch_virt_to_idmap) + return arch_virt_to_idmap(x); + else + return __virt_to_phys(x); +} + +#define virt_to_idmap(x) __virt_to_idmap((unsigned long)(x)) + /* * Virtual <-> DMA view memory address translations * Again, these are *only* valid on the kernel direct mapped RAM diff --git a/arch/arm/include/asm/mmu.h b/arch/arm/include/asm/mmu.h index 6f18da09668b..64fd15159b7d 100644 --- a/arch/arm/include/asm/mmu.h +++ b/arch/arm/include/asm/mmu.h @@ -16,7 +16,7 @@ typedef struct { #ifdef CONFIG_CPU_HAS_ASID #define ASID_BITS 8 #define ASID_MASK ((~0ULL) << ASID_BITS) -#define ASID(mm) ((mm)->context.id.counter & ~ASID_MASK) +#define ASID(mm) ((unsigned int)((mm)->context.id.counter & ~ASID_MASK)) #else #define ASID(mm) (0) #endif diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h index f97ee02386ee..86a659a19526 100644 --- a/arch/arm/include/asm/pgtable-2level.h +++ b/arch/arm/include/asm/pgtable-2level.h @@ -181,6 +181,13 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr) #define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,pte,ext) +/* + * We don't have huge page support for short descriptors, for the moment + * define empty stubs for use by pin_page_for_write. + */ +#define pmd_hugewillfault(pmd) (0) +#define pmd_thp_or_huge(pmd) (0) + #endif /* __ASSEMBLY__ */ #endif /* _ASM_PGTABLE_2LEVEL_H */ diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h index 5689c18c85f5..39c54cfa03e9 100644 --- a/arch/arm/include/asm/pgtable-3level.h +++ b/arch/arm/include/asm/pgtable-3level.h @@ -206,6 +206,9 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr) #define __HAVE_ARCH_PMD_WRITE #define pmd_write(pmd) (!(pmd_val(pmd) & PMD_SECT_RDONLY)) +#define pmd_hugewillfault(pmd) (!pmd_young(pmd) || !pmd_write(pmd)) +#define pmd_thp_or_huge(pmd) (pmd_huge(pmd) || pmd_trans_huge(pmd)) + #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define pmd_trans_huge(pmd) (pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT)) #define pmd_trans_splitting(pmd) (pmd_val(pmd) & PMD_SECT_SPLITTING) diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h index 413f3876341c..c3d5fc124a05 100644 --- a/arch/arm/include/asm/processor.h +++ b/arch/arm/include/asm/processor.h @@ -22,6 +22,7 @@ #include <asm/hw_breakpoint.h> #include <asm/ptrace.h> #include <asm/types.h> +#include <asm/unified.h> #ifdef __KERNEL__ #define STACK_TOP ((current->personality & ADDR_LIMIT_32BIT) ? \ @@ -87,6 +88,17 @@ unsigned long get_wchan(struct task_struct *p); #define KSTK_EIP(tsk) task_pt_regs(tsk)->ARM_pc #define KSTK_ESP(tsk) task_pt_regs(tsk)->ARM_sp +#ifdef CONFIG_SMP +#define __ALT_SMP_ASM(smp, up) \ + "9998: " smp "\n" \ + " .pushsection \".alt.smp.init\", \"a\"\n" \ + " .long 9998b\n" \ + " " up "\n" \ + " .popsection\n" +#else +#define __ALT_SMP_ASM(smp, up) up +#endif + /* * Prefetching support - only ARMv5. */ @@ -97,17 +109,22 @@ static inline void prefetch(const void *ptr) { __asm__ __volatile__( "pld\t%a0" - : - : "p" (ptr) - : "cc"); + :: "p" (ptr)); } +#if __LINUX_ARM_ARCH__ >= 7 && defined(CONFIG_SMP) #define ARCH_HAS_PREFETCHW -#define prefetchw(ptr) prefetch(ptr) - -#define ARCH_HAS_SPINLOCK_PREFETCH -#define spin_lock_prefetch(x) do { } while (0) - +static inline void prefetchw(const void *ptr) +{ + __asm__ __volatile__( + ".arch_extension mp\n" + __ALT_SMP_ASM( + WASM(pldw) "\t%a0", + WASM(pld) "\t%a0" + ) + :: "p" (ptr)); +} +#endif #endif #define HAVE_ARCH_PICK_MMAP_LAYOUT diff --git a/arch/arm/include/asm/setup.h b/arch/arm/include/asm/setup.h index c50f05609501..8d6a089dfb76 100644 --- a/arch/arm/include/asm/setup.h +++ b/arch/arm/include/asm/setup.h @@ -49,7 +49,7 @@ extern struct meminfo meminfo; #define bank_phys_end(bank) ((bank)->start + (bank)->size) #define bank_phys_size(bank) (bank)->size -extern int arm_add_memory(phys_addr_t start, phys_addr_t size); +extern int arm_add_memory(u64 start, u64 size); extern void early_print(const char *str, ...); extern void dump_machine_table(void); diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h index a8cae71caceb..22a3b9b5d4a1 100644 --- a/arch/arm/include/asm/smp.h +++ b/arch/arm/include/asm/smp.h @@ -84,6 +84,8 @@ extern void arch_send_call_function_single_ipi(int cpu); extern void arch_send_call_function_ipi_mask(const struct cpumask *mask); extern void arch_send_wakeup_ipi_mask(const struct cpumask *mask); +extern int register_ipi_completion(struct completion *completion, int cpu); + struct smp_operations { #ifdef CONFIG_SMP /* diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h index 4f2c28060c9a..ef3c6072aa45 100644 --- a/arch/arm/include/asm/spinlock.h +++ b/arch/arm/include/asm/spinlock.h @@ -5,21 +5,13 @@ #error SMP not supported on pre-ARMv6 CPUs #endif -#include <asm/processor.h> +#include <linux/prefetch.h> /* * sev and wfe are ARMv6K extensions. Uniprocessor ARMv6 may not have the K * extensions, so when running on UP, we have to patch these instructions away. */ -#define ALT_SMP(smp, up) \ - "9998: " smp "\n" \ - " .pushsection \".alt.smp.init\", \"a\"\n" \ - " .long 9998b\n" \ - " " up "\n" \ - " .popsection\n" - #ifdef CONFIG_THUMB2_KERNEL -#define SEV ALT_SMP("sev.w", "nop.w") /* * For Thumb-2, special care is needed to ensure that the conditional WFE * instruction really does assemble to exactly 4 bytes (as required by @@ -31,17 +23,18 @@ * the assembler won't change IT instructions which are explicitly present * in the input. */ -#define WFE(cond) ALT_SMP( \ +#define WFE(cond) __ALT_SMP_ASM( \ "it " cond "\n\t" \ "wfe" cond ".n", \ \ "nop.w" \ ) #else -#define SEV ALT_SMP("sev", "nop") -#define WFE(cond) ALT_SMP("wfe" cond, "nop") +#define WFE(cond) __ALT_SMP_ASM("wfe" cond, "nop") #endif +#define SEV __ALT_SMP_ASM(WASM(sev), WASM(nop)) + static inline void dsb_sev(void) { #if __LINUX_ARM_ARCH__ >= 7 @@ -77,6 +70,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock) u32 newval; arch_spinlock_t lockval; + prefetchw(&lock->slock); __asm__ __volatile__( "1: ldrex %0, [%3]\n" " add %1, %0, %4\n" @@ -100,6 +94,7 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock) unsigned long contended, res; u32 slock; + prefetchw(&lock->slock); do { __asm__ __volatile__( " ldrex %0, [%3]\n" @@ -127,10 +122,14 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock) dsb_sev(); } +static inline int arch_spin_value_unlocked(arch_spinlock_t lock) +{ + return lock.tickets.owner == lock.tickets.next; +} + static inline int arch_spin_is_locked(arch_spinlock_t *lock) { - struct __raw_tickets tickets = ACCESS_ONCE(lock->tickets); - return tickets.owner != tickets.next; + return !arch_spin_value_unlocked(ACCESS_ONCE(*lock)); } static inline int arch_spin_is_contended(arch_spinlock_t *lock) @@ -152,6 +151,7 @@ static inline void arch_write_lock(arch_rwlock_t *rw) { unsigned long tmp; + prefetchw(&rw->lock); __asm__ __volatile__( "1: ldrex %0, [%1]\n" " teq %0, #0\n" @@ -170,6 +170,7 @@ static inline int arch_write_trylock(arch_rwlock_t *rw) { unsigned long contended, res; + prefetchw(&rw->lock); do { __asm__ __volatile__( " ldrex %0, [%2]\n" @@ -203,7 +204,7 @@ static inline void arch_write_unlock(arch_rwlock_t *rw) } /* write_can_lock - would write_trylock() succeed? */ -#define arch_write_can_lock(x) ((x)->lock == 0) +#define arch_write_can_lock(x) (ACCESS_ONCE((x)->lock) == 0) /* * Read locks are a bit more hairy: @@ -221,6 +222,7 @@ static inline void arch_read_lock(arch_rwlock_t *rw) { unsigned long tmp, tmp2; + prefetchw(&rw->lock); __asm__ __volatile__( "1: ldrex %0, [%2]\n" " adds %0, %0, #1\n" @@ -241,6 +243,7 @@ static inline void arch_read_unlock(arch_rwlock_t *rw) smp_mb(); + prefetchw(&rw->lock); __asm__ __volatile__( "1: ldrex %0, [%2]\n" " sub %0, %0, #1\n" @@ -259,6 +262,7 @@ static inline int arch_read_trylock(arch_rwlock_t *rw) { unsigned long contended, res; + prefetchw(&rw->lock); do { __asm__ __volatile__( " ldrex %0, [%2]\n" @@ -280,7 +284,7 @@ static inline int arch_read_trylock(arch_rwlock_t *rw) } /* read_can_lock - would read_trylock() succeed? */ -#define arch_read_can_lock(x) ((x)->lock < 0x80000000) +#define arch_read_can_lock(x) (ACCESS_ONCE((x)->lock) < 0x80000000) #define arch_read_lock_flags(lock, flags) arch_read_lock(lock) #define arch_write_lock_flags(lock, flags) arch_write_lock(lock) diff --git a/arch/arm/include/asm/spinlock_types.h b/arch/arm/include/asm/spinlock_types.h index b262d2f8b478..47663fcb10ad 100644 --- a/arch/arm/include/asm/spinlock_types.h +++ b/arch/arm/include/asm/spinlock_types.h @@ -25,7 +25,7 @@ typedef struct { #define __ARCH_SPIN_LOCK_UNLOCKED { { 0 } } typedef struct { - volatile unsigned int lock; + u32 lock; } arch_rwlock_t; #define __ARCH_RW_LOCK_UNLOCKED { 0 } diff --git a/arch/arm/include/asm/syscall.h b/arch/arm/include/asm/syscall.h index f1d96d4e8092..73ddd7239b33 100644 --- a/arch/arm/include/asm/syscall.h +++ b/arch/arm/include/asm/syscall.h @@ -57,6 +57,9 @@ static inline void syscall_get_arguments(struct task_struct *task, unsigned int i, unsigned int n, unsigned long *args) { + if (n == 0) + return; + if (i + n > SYSCALL_MAX_ARGS) { unsigned long *args_bad = args + SYSCALL_MAX_ARGS - i; unsigned int n_bad = n + i - SYSCALL_MAX_ARGS; @@ -81,6 +84,9 @@ static inline void syscall_set_arguments(struct task_struct *task, unsigned int i, unsigned int n, const unsigned long *args) { + if (n == 0) + return; + if (i + n > SYSCALL_MAX_ARGS) { pr_warning("%s called with max args %d, handling only %d\n", __func__, i + n, SYSCALL_MAX_ARGS); diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h index 38960264040c..def9e570199f 100644 --- a/arch/arm/include/asm/tlbflush.h +++ b/arch/arm/include/asm/tlbflush.h @@ -560,37 +560,6 @@ static inline void __flush_bp_all(void) asm("mcr p15, 0, %0, c7, c1, 6" : : "r" (zero)); } -#include <asm/cputype.h> -#ifdef CONFIG_ARM_ERRATA_798181 -static inline int erratum_a15_798181(void) -{ - unsigned int midr = read_cpuid_id(); - - /* Cortex-A15 r0p0..r3p2 affected */ - if ((midr & 0xff0ffff0) != 0x410fc0f0 || midr > 0x413fc0f2) - return 0; - return 1; -} - -static inline void dummy_flush_tlb_a15_erratum(void) -{ - /* - * Dummy TLBIMVAIS. Using the unmapped address 0 and ASID 0. - */ - asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (0)); - dsb(ish); -} -#else -static inline int erratum_a15_798181(void) -{ - return 0; -} - -static inline void dummy_flush_tlb_a15_erratum(void) -{ -} -#endif - /* * flush_pmd_entry * @@ -697,4 +666,21 @@ extern void flush_bp_all(void); #endif +#ifndef __ASSEMBLY__ +#ifdef CONFIG_ARM_ERRATA_798181 +extern void erratum_a15_798181_init(void); +#else +static inline void erratum_a15_798181_init(void) {} +#endif +extern bool (*erratum_a15_798181_handler)(void); + +static inline bool erratum_a15_798181(void) +{ + if (unlikely(IS_ENABLED(CONFIG_ARM_ERRATA_798181) && + erratum_a15_798181_handler)) + return erratum_a15_798181_handler(); + return false; +} +#endif + #endif diff --git a/arch/arm/include/asm/unified.h b/arch/arm/include/asm/unified.h index f5989f46b4d2..b88beaba6b4a 100644 --- a/arch/arm/include/asm/unified.h +++ b/arch/arm/include/asm/unified.h @@ -38,6 +38,8 @@ #ifdef __ASSEMBLY__ #define W(instr) instr.w #define BSYM(sym) sym + 1 +#else +#define WASM(instr) #instr ".w" #endif #else /* !CONFIG_THUMB2_KERNEL */ @@ -50,6 +52,8 @@ #ifdef __ASSEMBLY__ #define W(instr) instr #define BSYM(sym) sym +#else +#define WASM(instr) #instr #endif #endif /* CONFIG_THUMB2_KERNEL */ diff --git a/arch/arm/include/debug/efm32.S b/arch/arm/include/debug/efm32.S new file mode 100644 index 000000000000..2265a199280c --- /dev/null +++ b/arch/arm/include/debug/efm32.S @@ -0,0 +1,45 @@ +/* + * Copyright (C) 2013 Pengutronix + * Uwe Kleine-Koenig <u.kleine-koenig@pengutronix.de> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#define UARTn_CMD 0x000c +#define UARTn_CMD_TXEN 0x0004 + +#define UARTn_STATUS 0x0010 +#define UARTn_STATUS_TXC 0x0020 +#define UARTn_STATUS_TXBL 0x0040 + +#define UARTn_TXDATA 0x0034 + + .macro addruart, rx, tmp + ldr \rx, =(CONFIG_DEBUG_UART_PHYS) + + /* + * enable TX. The driver might disable it to save energy. We + * don't care about disabling at the end as during debug power + * consumption isn't that important. + */ + ldr \tmp, =(UARTn_CMD_TXEN) + str \tmp, [\rx, #UARTn_CMD] + .endm + + .macro senduart,rd,rx + strb \rd, [\rx, #UARTn_TXDATA] + .endm + + .macro waituart,rd,rx +1001: ldr \rd, [\rx, #UARTn_STATUS] + tst \rd, #UARTn_STATUS_TXBL + beq 1001b + .endm + + .macro busyuart,rd,rx +1001: ldr \rd, [\rx, UARTn_STATUS] + tst \rd, #UARTn_STATUS_TXC + bne 1001b + .endm diff --git a/arch/arm/include/debug/msm.S b/arch/arm/include/debug/msm.S index 9166e1bc470e..9d653d475903 100644 --- a/arch/arm/include/debug/msm.S +++ b/arch/arm/include/debug/msm.S @@ -46,6 +46,11 @@ #define MSM_DEBUG_UART_PHYS 0x16440000 #endif +#ifdef CONFIG_DEBUG_MSM8974_UART +#define MSM_DEBUG_UART_BASE 0xFA71E000 +#define MSM_DEBUG_UART_PHYS 0xF991E000 +#endif + .macro addruart, rp, rv, tmp #ifdef MSM_DEBUG_UART_PHYS ldr \rp, =MSM_DEBUG_UART_PHYS diff --git a/arch/arm/include/debug/pl01x.S b/arch/arm/include/debug/pl01x.S index 37c6895b87e6..92ef808a2337 100644 --- a/arch/arm/include/debug/pl01x.S +++ b/arch/arm/include/debug/pl01x.S @@ -25,12 +25,14 @@ .macro waituart,rd,rx 1001: ldr \rd, [\rx, #UART01x_FR] + ARM_BE8( rev \rd, \rd ) tst \rd, #UART01x_FR_TXFF bne 1001b .endm .macro busyuart,rd,rx 1001: ldr \rd, [\rx, #UART01x_FR] + ARM_BE8( rev \rd, \rd ) tst \rd, #UART01x_FR_BUSY bne 1001b .endm diff --git a/arch/arm/include/uapi/asm/Kbuild b/arch/arm/include/uapi/asm/Kbuild index 18d76fd5a2af..70a1c9da30ca 100644 --- a/arch/arm/include/uapi/asm/Kbuild +++ b/arch/arm/include/uapi/asm/Kbuild @@ -7,6 +7,7 @@ header-y += hwcap.h header-y += ioctls.h header-y += kvm_para.h header-y += mman.h +header-y += perf_regs.h header-y += posix_types.h header-y += ptrace.h header-y += setup.h diff --git a/arch/arm/include/uapi/asm/perf_regs.h b/arch/arm/include/uapi/asm/perf_regs.h new file mode 100644 index 000000000000..ce59448458b2 --- /dev/null +++ b/arch/arm/include/uapi/asm/perf_regs.h @@ -0,0 +1,23 @@ +#ifndef _ASM_ARM_PERF_REGS_H +#define _ASM_ARM_PERF_REGS_H + +enum perf_event_arm_regs { + PERF_REG_ARM_R0, + PERF_REG_ARM_R1, + PERF_REG_ARM_R2, + PERF_REG_ARM_R3, + PERF_REG_ARM_R4, + PERF_REG_ARM_R5, + PERF_REG_ARM_R6, + PERF_REG_ARM_R7, + PERF_REG_ARM_R8, + PERF_REG_ARM_R9, + PERF_REG_ARM_R10, + PERF_REG_ARM_FP, + PERF_REG_ARM_IP, + PERF_REG_ARM_SP, + PERF_REG_ARM_LR, + PERF_REG_ARM_PC, + PERF_REG_ARM_MAX, +}; +#endif /* _ASM_ARM_PERF_REGS_H */ diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index 5140df5f23aa..a30fc9be9e9e 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -17,7 +17,8 @@ CFLAGS_REMOVE_return_address.o = -pg obj-y := elf.o entry-common.o irq.o opcodes.o \ process.o ptrace.o return_address.o \ - setup.o signal.o stacktrace.o sys_arm.o time.o traps.o + setup.o signal.o sigreturn_codes.o \ + stacktrace.o sys_arm.o time.o traps.o obj-$(CONFIG_ATAGS) += atags_parse.o obj-$(CONFIG_ATAGS_PROC) += atags_proc.o @@ -78,6 +79,7 @@ obj-$(CONFIG_CPU_XSC3) += xscale-cp0.o obj-$(CONFIG_CPU_MOHAWK) += xscale-cp0.o obj-$(CONFIG_CPU_PJ4) += pj4-cp0.o obj-$(CONFIG_IWMMXT) += iwmmxt.o +obj-$(CONFIG_PERF_EVENTS) += perf_regs.o obj-$(CONFIG_HW_PERF_EVENTS) += perf_event.o perf_event_cpu.o AFLAGS_iwmmxt.o := -Wa,-mcpu=iwmmxt obj-$(CONFIG_ARM_CPU_TOPOLOGY) += topology.o diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c index 60d3b738d420..1f031ddd0667 100644 --- a/arch/arm/kernel/armksyms.c +++ b/arch/arm/kernel/armksyms.c @@ -155,4 +155,5 @@ EXPORT_SYMBOL(__gnu_mcount_nc); #ifdef CONFIG_ARM_PATCH_PHYS_VIRT EXPORT_SYMBOL(__pv_phys_offset); +EXPORT_SYMBOL(__pv_offset); #endif diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 9cbe70c8b0ef..55090fbb81a2 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -416,9 +416,8 @@ __und_usr: bne __und_usr_thumb sub r4, r2, #4 @ ARM instr at LR - 4 1: ldrt r0, [r4] -#ifdef CONFIG_CPU_ENDIAN_BE8 - rev r0, r0 @ little endian instruction -#endif + ARM_BE8(rev r0, r0) @ little endian instruction + @ r0 = 32-bit ARM instruction which caused the exception @ r2 = PC value for the following instruction (:= regs->ARM_pc) @ r4 = PC value for the faulting instruction diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index bc6bd9683ba4..a2dcafdf1bc8 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -393,9 +393,7 @@ ENTRY(vector_swi) #else USER( ldr r10, [lr, #-4] ) @ get SWI instruction #endif -#ifdef CONFIG_CPU_ENDIAN_BE8 - rev r10, r10 @ little endian instruction -#endif + ARM_BE8(rev r10, r10) @ little endian instruction #elif defined(CONFIG_AEABI) diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index 2c7cc1e03473..7801866e626a 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -77,6 +77,7 @@ __HEAD ENTRY(stext) + ARM_BE8(setend be ) @ ensure we are in BE8 mode THUMB( adr r9, BSYM(1f) ) @ Kernel is always entered in ARM. THUMB( bx r9 ) @ If this is a Thumb-2 kernel, @@ -352,6 +353,9 @@ ENTRY(secondary_startup) * the processor type - there is no need to check the machine type * as it has already been validated by the primary processor. */ + + ARM_BE8(setend be) @ ensure we are in BE8 mode + #ifdef CONFIG_ARM_VIRT_EXT bl __hyp_stub_install_secondary #endif @@ -487,7 +491,26 @@ __fixup_smp: mrc p15, 0, r0, c0, c0, 5 @ read MPIDR and r0, r0, #0xc0000000 @ multiprocessing extensions and teq r0, #0x80000000 @ not part of a uniprocessor system? - moveq pc, lr @ yes, assume SMP + bne __fixup_smp_on_up @ no, assume UP + + @ Core indicates it is SMP. Check for Aegis SOC where a single + @ Cortex-A9 CPU is present but SMP operations fault. + mov r4, #0x41000000 + orr r4, r4, #0x0000c000 + orr r4, r4, #0x00000090 + teq r3, r4 @ Check for ARM Cortex-A9 + movne pc, lr @ Not ARM Cortex-A9, + + @ If a future SoC *does* use 0x0 as the PERIPH_BASE, then the + @ below address check will need to be #ifdef'd or equivalent + @ for the Aegis platform. + mrc p15, 4, r0, c15, c0 @ get SCU base address + teq r0, #0x0 @ '0' on actual UP A9 hardware + beq __fixup_smp_on_up @ So its an A9 UP + ldr r0, [r0, #4] @ read SCU Config + and r0, r0, #0x3 @ number of CPUs + teq r0, #0x0 @ is 1? + movne pc, lr __fixup_smp_on_up: adr r0, 1f @@ -536,6 +559,14 @@ ENTRY(fixup_smp) ldmfd sp!, {r4 - r6, pc} ENDPROC(fixup_smp) +#ifdef __ARMEB__ +#define LOW_OFFSET 0x4 +#define HIGH_OFFSET 0x0 +#else +#define LOW_OFFSET 0x0 +#define HIGH_OFFSET 0x4 +#endif + #ifdef CONFIG_ARM_PATCH_PHYS_VIRT /* __fixup_pv_table - patch the stub instructions with the delta between @@ -546,17 +577,20 @@ ENDPROC(fixup_smp) __HEAD __fixup_pv_table: adr r0, 1f - ldmia r0, {r3-r5, r7} - sub r3, r0, r3 @ PHYS_OFFSET - PAGE_OFFSET + ldmia r0, {r3-r7} + mvn ip, #0 + subs r3, r0, r3 @ PHYS_OFFSET - PAGE_OFFSET add r4, r4, r3 @ adjust table start address add r5, r5, r3 @ adjust table end address - add r7, r7, r3 @ adjust __pv_phys_offset address - str r8, [r7] @ save computed PHYS_OFFSET to __pv_phys_offset + add r6, r6, r3 @ adjust __pv_phys_offset address + add r7, r7, r3 @ adjust __pv_offset address + str r8, [r6, #LOW_OFFSET] @ save computed PHYS_OFFSET to __pv_phys_offset + strcc ip, [r7, #HIGH_OFFSET] @ save to __pv_offset high bits mov r6, r3, lsr #24 @ constant for add/sub instructions teq r3, r6, lsl #24 @ must be 16MiB aligned THUMB( it ne @ cross section branch ) bne __error - str r6, [r7, #4] @ save to __pv_offset + str r3, [r7, #LOW_OFFSET] @ save to __pv_offset low bits b __fixup_a_pv_table ENDPROC(__fixup_pv_table) @@ -565,10 +599,19 @@ ENDPROC(__fixup_pv_table) .long __pv_table_begin .long __pv_table_end 2: .long __pv_phys_offset + .long __pv_offset .text __fixup_a_pv_table: + adr r0, 3f + ldr r6, [r0] + add r6, r6, r3 + ldr r0, [r6, #HIGH_OFFSET] @ pv_offset high word + ldr r6, [r6, #LOW_OFFSET] @ pv_offset low word + mov r6, r6, lsr #24 + cmn r0, #1 #ifdef CONFIG_THUMB2_KERNEL + moveq r0, #0x200000 @ set bit 21, mov to mvn instruction lsls r6, #24 beq 2f clz r7, r6 @@ -582,18 +625,42 @@ __fixup_a_pv_table: b 2f 1: add r7, r3 ldrh ip, [r7, #2] - and ip, 0x8f00 - orr ip, r6 @ mask in offset bits 31-24 +ARM_BE8(rev16 ip, ip) + tst ip, #0x4000 + and ip, #0x8f00 + orrne ip, r6 @ mask in offset bits 31-24 + orreq ip, r0 @ mask in offset bits 7-0 +ARM_BE8(rev16 ip, ip) strh ip, [r7, #2] + bne 2f + ldrh ip, [r7] +ARM_BE8(rev16 ip, ip) + bic ip, #0x20 + orr ip, ip, r0, lsr #16 +ARM_BE8(rev16 ip, ip) + strh ip, [r7] 2: cmp r4, r5 ldrcc r7, [r4], #4 @ use branch for delay slot bcc 1b bx lr #else + moveq r0, #0x400000 @ set bit 22, mov to mvn instruction b 2f 1: ldr ip, [r7, r3] +#ifdef CONFIG_CPU_ENDIAN_BE8 + @ in BE8, we load data in BE, but instructions still in LE + bic ip, ip, #0xff000000 + tst ip, #0x000f0000 @ check the rotation field + orrne ip, ip, r6, lsl #24 @ mask in offset bits 31-24 + biceq ip, ip, #0x00004000 @ clear bit 22 + orreq ip, ip, r0, lsl #24 @ mask in offset bits 7-0 +#else bic ip, ip, #0x000000ff - orr ip, ip, r6 @ mask in offset bits 31-24 + tst ip, #0xf00 @ check the rotation field + orrne ip, ip, r6 @ mask in offset bits 31-24 + biceq ip, ip, #0x400000 @ clear bit 22 + orreq ip, ip, r0 @ mask in offset bits 7-0 +#endif str ip, [r7, r3] 2: cmp r4, r5 ldrcc r7, [r4], #4 @ use branch for delay slot @@ -602,28 +669,30 @@ __fixup_a_pv_table: #endif ENDPROC(__fixup_a_pv_table) + .align +3: .long __pv_offset + ENTRY(fixup_pv_table) stmfd sp!, {r4 - r7, lr} - ldr r2, 2f @ get address of __pv_phys_offset mov r3, #0 @ no offset mov r4, r0 @ r0 = table start add r5, r0, r1 @ r1 = table size - ldr r6, [r2, #4] @ get __pv_offset bl __fixup_a_pv_table ldmfd sp!, {r4 - r7, pc} ENDPROC(fixup_pv_table) - .align -2: .long __pv_phys_offset - .data .globl __pv_phys_offset .type __pv_phys_offset, %object __pv_phys_offset: - .long 0 - .size __pv_phys_offset, . - __pv_phys_offset + .quad 0 + .size __pv_phys_offset, . -__pv_phys_offset + + .globl __pv_offset + .type __pv_offset, %object __pv_offset: - .long 0 + .quad 0 + .size __pv_offset, . -__pv_offset #endif #include "head-common.S" diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c index 7b95de601357..3d446605cbf8 100644 --- a/arch/arm/kernel/hw_breakpoint.c +++ b/arch/arm/kernel/hw_breakpoint.c @@ -344,13 +344,13 @@ int arch_install_hw_breakpoint(struct perf_event *bp) /* Breakpoint */ ctrl_base = ARM_BASE_BCR; val_base = ARM_BASE_BVR; - slots = (struct perf_event **)__get_cpu_var(bp_on_reg); + slots = this_cpu_ptr(bp_on_reg); max_slots = core_num_brps; } else { /* Watchpoint */ ctrl_base = ARM_BASE_WCR; val_base = ARM_BASE_WVR; - slots = (struct perf_event **)__get_cpu_var(wp_on_reg); + slots = this_cpu_ptr(wp_on_reg); max_slots = core_num_wrps; } @@ -396,12 +396,12 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp) if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) { /* Breakpoint */ base = ARM_BASE_BCR; - slots = (struct perf_event **)__get_cpu_var(bp_on_reg); + slots = this_cpu_ptr(bp_on_reg); max_slots = core_num_brps; } else { /* Watchpoint */ base = ARM_BASE_WCR; - slots = (struct perf_event **)__get_cpu_var(wp_on_reg); + slots = this_cpu_ptr(wp_on_reg); max_slots = core_num_wrps; } @@ -697,7 +697,7 @@ static void watchpoint_handler(unsigned long addr, unsigned int fsr, struct arch_hw_breakpoint *info; struct arch_hw_breakpoint_ctrl ctrl; - slots = (struct perf_event **)__get_cpu_var(wp_on_reg); + slots = this_cpu_ptr(wp_on_reg); for (i = 0; i < core_num_wrps; ++i) { rcu_read_lock(); @@ -768,7 +768,7 @@ static void watchpoint_single_step_handler(unsigned long pc) struct perf_event *wp, **slots; struct arch_hw_breakpoint *info; - slots = (struct perf_event **)__get_cpu_var(wp_on_reg); + slots = this_cpu_ptr(wp_on_reg); for (i = 0; i < core_num_wrps; ++i) { rcu_read_lock(); @@ -802,7 +802,7 @@ static void breakpoint_handler(unsigned long unknown, struct pt_regs *regs) struct arch_hw_breakpoint *info; struct arch_hw_breakpoint_ctrl ctrl; - slots = (struct perf_event **)__get_cpu_var(bp_on_reg); + slots = this_cpu_ptr(bp_on_reg); /* The exception entry code places the amended lr in the PC. */ addr = regs->ARM_pc; diff --git a/arch/arm/kernel/kprobes.c b/arch/arm/kernel/kprobes.c index 170e9f34003f..a7b621ece23d 100644 --- a/arch/arm/kernel/kprobes.c +++ b/arch/arm/kernel/kprobes.c @@ -171,13 +171,13 @@ static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb) static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb) { - __get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp; + __this_cpu_write(current_kprobe, kcb->prev_kprobe.kp); kcb->kprobe_status = kcb->prev_kprobe.status; } static void __kprobes set_current_kprobe(struct kprobe *p) { - __get_cpu_var(current_kprobe) = p; + __this_cpu_write(current_kprobe, p); } static void __kprobes @@ -421,10 +421,10 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs) continue; if (ri->rp && ri->rp->handler) { - __get_cpu_var(current_kprobe) = &ri->rp->kp; + __this_cpu_write(current_kprobe, &ri->rp->kp); get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE; ri->rp->handler(ri, regs); - __get_cpu_var(current_kprobe) = NULL; + __this_cpu_write(current_kprobe, NULL); } orig_ret_address = (unsigned long)ri->ret_addr; diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c index 084dc8896986..5fdb4038f969 100644 --- a/arch/arm/kernel/module.c +++ b/arch/arm/kernel/module.c @@ -24,6 +24,7 @@ #include <asm/sections.h> #include <asm/smp_plat.h> #include <asm/unwind.h> +#include <asm/opcodes.h> #ifdef CONFIG_XIP_KERNEL /* @@ -60,6 +61,7 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, Elf32_Sym *sym; const char *symname; s32 offset; + u32 tmp; #ifdef CONFIG_THUMB2_KERNEL u32 upper, lower, sign, j1, j2; #endif @@ -95,7 +97,8 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, case R_ARM_PC24: case R_ARM_CALL: case R_ARM_JUMP24: - offset = (*(u32 *)loc & 0x00ffffff) << 2; + offset = __mem_to_opcode_arm(*(u32 *)loc); + offset = (offset & 0x00ffffff) << 2; if (offset & 0x02000000) offset -= 0x04000000; @@ -111,9 +114,10 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, } offset >>= 2; + offset &= 0x00ffffff; - *(u32 *)loc &= 0xff000000; - *(u32 *)loc |= offset & 0x00ffffff; + *(u32 *)loc &= __opcode_to_mem_arm(0xff000000); + *(u32 *)loc |= __opcode_to_mem_arm(offset); break; case R_ARM_V4BX: @@ -121,8 +125,8 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, * other bits to re-code instruction as * MOV PC,Rm. */ - *(u32 *)loc &= 0xf000000f; - *(u32 *)loc |= 0x01a0f000; + *(u32 *)loc &= __opcode_to_mem_arm(0xf000000f); + *(u32 *)loc |= __opcode_to_mem_arm(0x01a0f000); break; case R_ARM_PREL31: @@ -132,7 +136,7 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, case R_ARM_MOVW_ABS_NC: case R_ARM_MOVT_ABS: - offset = *(u32 *)loc; + offset = tmp = __mem_to_opcode_arm(*(u32 *)loc); offset = ((offset & 0xf0000) >> 4) | (offset & 0xfff); offset = (offset ^ 0x8000) - 0x8000; @@ -140,16 +144,18 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, if (ELF32_R_TYPE(rel->r_info) == R_ARM_MOVT_ABS) offset >>= 16; - *(u32 *)loc &= 0xfff0f000; - *(u32 *)loc |= ((offset & 0xf000) << 4) | - (offset & 0x0fff); + tmp &= 0xfff0f000; + tmp |= ((offset & 0xf000) << 4) | + (offset & 0x0fff); + + *(u32 *)loc = __opcode_to_mem_arm(tmp); break; #ifdef CONFIG_THUMB2_KERNEL case R_ARM_THM_CALL: case R_ARM_THM_JUMP24: - upper = *(u16 *)loc; - lower = *(u16 *)(loc + 2); + upper = __mem_to_opcode_thumb16(*(u16 *)loc); + lower = __mem_to_opcode_thumb16(*(u16 *)(loc + 2)); /* * 25 bit signed address range (Thumb-2 BL and B.W @@ -198,17 +204,20 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, sign = (offset >> 24) & 1; j1 = sign ^ (~(offset >> 23) & 1); j2 = sign ^ (~(offset >> 22) & 1); - *(u16 *)loc = (u16)((upper & 0xf800) | (sign << 10) | + upper = (u16)((upper & 0xf800) | (sign << 10) | ((offset >> 12) & 0x03ff)); - *(u16 *)(loc + 2) = (u16)((lower & 0xd000) | - (j1 << 13) | (j2 << 11) | - ((offset >> 1) & 0x07ff)); + lower = (u16)((lower & 0xd000) | + (j1 << 13) | (j2 << 11) | + ((offset >> 1) & 0x07ff)); + + *(u16 *)loc = __opcode_to_mem_thumb16(upper); + *(u16 *)(loc + 2) = __opcode_to_mem_thumb16(lower); break; case R_ARM_THM_MOVW_ABS_NC: case R_ARM_THM_MOVT_ABS: - upper = *(u16 *)loc; - lower = *(u16 *)(loc + 2); + upper = __mem_to_opcode_thumb16(*(u16 *)loc); + lower = __mem_to_opcode_thumb16(*(u16 *)(loc + 2)); /* * MOVT/MOVW instructions encoding in Thumb-2: @@ -229,12 +238,14 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, if (ELF32_R_TYPE(rel->r_info) == R_ARM_THM_MOVT_ABS) offset >>= 16; - *(u16 *)loc = (u16)((upper & 0xfbf0) | - ((offset & 0xf000) >> 12) | - ((offset & 0x0800) >> 1)); - *(u16 *)(loc + 2) = (u16)((lower & 0x8f00) | - ((offset & 0x0700) << 4) | - (offset & 0x00ff)); + upper = (u16)((upper & 0xfbf0) | + ((offset & 0xf000) >> 12) | + ((offset & 0x0800) >> 1)); + lower = (u16)((lower & 0x8f00) | + ((offset & 0x0700) << 4) | + (offset & 0x00ff)); + *(u16 *)loc = __opcode_to_mem_thumb16(upper); + *(u16 *)(loc + 2) = __opcode_to_mem_thumb16(lower); break; #endif diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index e186ee1e63f6..bc3f2efa0d86 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -256,12 +256,11 @@ validate_event(struct pmu_hw_events *hw_events, struct perf_event *event) { struct arm_pmu *armpmu = to_arm_pmu(event->pmu); - struct pmu *leader_pmu = event->group_leader->pmu; if (is_software_event(event)) return 1; - if (event->pmu != leader_pmu || event->state < PERF_EVENT_STATE_OFF) + if (event->state < PERF_EVENT_STATE_OFF) return 1; if (event->state == PERF_EVENT_STATE_OFF && !event->attr.enable_on_exec) diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c index 8d6147b2001f..d85055cd24ba 100644 --- a/arch/arm/kernel/perf_event_cpu.c +++ b/arch/arm/kernel/perf_event_cpu.c @@ -68,7 +68,7 @@ EXPORT_SYMBOL_GPL(perf_num_counters); static struct pmu_hw_events *cpu_pmu_get_cpu_events(void) { - return &__get_cpu_var(cpu_hw_events); + return this_cpu_ptr(&cpu_hw_events); } static void cpu_pmu_free_irq(struct arm_pmu *cpu_pmu) diff --git a/arch/arm/kernel/perf_regs.c b/arch/arm/kernel/perf_regs.c new file mode 100644 index 000000000000..6e4379c67cbc --- /dev/null +++ b/arch/arm/kernel/perf_regs.c @@ -0,0 +1,30 @@ + +#include <linux/errno.h> +#include <linux/kernel.h> +#include <linux/perf_event.h> +#include <linux/bug.h> +#include <asm/perf_regs.h> +#include <asm/ptrace.h> + +u64 perf_reg_value(struct pt_regs *regs, int idx) +{ + if (WARN_ON_ONCE((u32)idx >= PERF_REG_ARM_MAX)) + return 0; + + return regs->uregs[idx]; +} + +#define REG_RESERVED (~((1ULL << PERF_REG_ARM_MAX) - 1)) + +int perf_reg_validate(u64 mask) +{ + if (!mask || mask & REG_RESERVED) + return -EINVAL; + + return 0; +} + +u64 perf_reg_abi(struct task_struct *task) +{ + return PERF_SAMPLE_REGS_ABI_32; +} diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 0e1e2b3afa45..f52150d2ec00 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -73,6 +73,8 @@ __setup("fpe=", fpe_setup); #endif extern void paging_init(const struct machine_desc *desc); +extern void early_paging_init(const struct machine_desc *, + struct proc_info_list *); extern void sanity_check_meminfo(void); extern enum reboot_mode reboot_mode; extern void setup_dma_zone(const struct machine_desc *desc); @@ -599,6 +601,8 @@ static void __init setup_processor(void) elf_hwcap &= ~(HWCAP_THUMB | HWCAP_IDIVT); #endif + erratum_a15_798181_init(); + feat_v6_fixup(); cacheid_init(); @@ -619,9 +623,10 @@ void __init dump_machine_table(void) /* can't use cpu_relax() here as it may require MMU setup */; } -int __init arm_add_memory(phys_addr_t start, phys_addr_t size) +int __init arm_add_memory(u64 start, u64 size) { struct membank *bank = &meminfo.bank[meminfo.nr_banks]; + u64 aligned_start; if (meminfo.nr_banks >= NR_BANKS) { printk(KERN_CRIT "NR_BANKS too low, " @@ -634,10 +639,16 @@ int __init arm_add_memory(phys_addr_t start, phys_addr_t size) * Size is appropriately rounded down, start is rounded up. */ size -= start & ~PAGE_MASK; - bank->start = PAGE_ALIGN(start); + aligned_start = PAGE_ALIGN(start); -#ifndef CONFIG_ARM_LPAE - if (bank->start + size < bank->start) { +#ifndef CONFIG_ARCH_PHYS_ADDR_T_64BIT + if (aligned_start > ULONG_MAX) { + printk(KERN_CRIT "Ignoring memory at 0x%08llx outside " + "32-bit physical address space\n", (long long)start); + return -EINVAL; + } + + if (aligned_start + size > ULONG_MAX) { printk(KERN_CRIT "Truncating memory at 0x%08llx to fit in " "32-bit physical address space\n", (long long)start); /* @@ -645,10 +656,11 @@ int __init arm_add_memory(phys_addr_t start, phys_addr_t size) * 32 bits, we use ULONG_MAX as the upper limit rather than 4GB. * This means we lose a page after masking. */ - size = ULONG_MAX - bank->start; + size = ULONG_MAX - aligned_start; } #endif + bank->start = aligned_start; bank->size = size & ~(phys_addr_t)(PAGE_SIZE - 1); /* @@ -669,8 +681,8 @@ int __init arm_add_memory(phys_addr_t start, phys_addr_t size) static int __init early_mem(char *p) { static int usermem __initdata = 0; - phys_addr_t size; - phys_addr_t start; + u64 size; + u64 start; char *endp; /* @@ -878,6 +890,8 @@ void __init setup_arch(char **cmdline_p) parse_early_param(); sort(&meminfo.bank, meminfo.nr_banks, sizeof(meminfo.bank[0]), meminfo_cmp, NULL); + + early_paging_init(mdesc, lookup_processor_type(read_cpuid_id())); sanity_check_meminfo(); arm_memblock_init(&meminfo, mdesc); diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index ab3304225272..64845fc4152a 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -21,29 +21,7 @@ #include <asm/unistd.h> #include <asm/vfp.h> -/* - * For ARM syscalls, we encode the syscall number into the instruction. - */ -#define SWI_SYS_SIGRETURN (0xef000000|(__NR_sigreturn)|(__NR_OABI_SYSCALL_BASE)) -#define SWI_SYS_RT_SIGRETURN (0xef000000|(__NR_rt_sigreturn)|(__NR_OABI_SYSCALL_BASE)) - -/* - * With EABI, the syscall number has to be loaded into r7. - */ -#define MOV_R7_NR_SIGRETURN (0xe3a07000 | (__NR_sigreturn - __NR_SYSCALL_BASE)) -#define MOV_R7_NR_RT_SIGRETURN (0xe3a07000 | (__NR_rt_sigreturn - __NR_SYSCALL_BASE)) - -/* - * For Thumb syscalls, we pass the syscall number via r7. We therefore - * need two 16-bit instructions. - */ -#define SWI_THUMB_SIGRETURN (0xdf00 << 16 | 0x2700 | (__NR_sigreturn - __NR_SYSCALL_BASE)) -#define SWI_THUMB_RT_SIGRETURN (0xdf00 << 16 | 0x2700 | (__NR_rt_sigreturn - __NR_SYSCALL_BASE)) - -static const unsigned long sigreturn_codes[7] = { - MOV_R7_NR_SIGRETURN, SWI_SYS_SIGRETURN, SWI_THUMB_SIGRETURN, - MOV_R7_NR_RT_SIGRETURN, SWI_SYS_RT_SIGRETURN, SWI_THUMB_RT_SIGRETURN, -}; +extern const unsigned long sigreturn_codes[7]; static unsigned long signal_return_offset; diff --git a/arch/arm/kernel/sigreturn_codes.S b/arch/arm/kernel/sigreturn_codes.S new file mode 100644 index 000000000000..3c5d0f2170fd --- /dev/null +++ b/arch/arm/kernel/sigreturn_codes.S @@ -0,0 +1,80 @@ +/* + * sigreturn_codes.S - code sinpets for sigreturn syscalls + * + * Created by: Victor Kamensky, 2013-08-13 + * Copyright: (C) 2013 Linaro Limited + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <asm/unistd.h> + +/* + * For ARM syscalls, we encode the syscall number into the instruction. + * With EABI, the syscall number has to be loaded into r7. As result + * ARM syscall sequence snippet will have move and svc in .arm encoding + * + * For Thumb syscalls, we pass the syscall number via r7. We therefore + * need two 16-bit instructions in .thumb encoding + * + * Please note sigreturn_codes code are not executed in place. Instead + * they just copied by kernel into appropriate places. Code inside of + * arch/arm/kernel/signal.c is very sensitive to layout of these code + * snippets. + */ + +#if __LINUX_ARM_ARCH__ <= 4 + /* + * Note we manually set minimally required arch that supports + * required thumb opcodes for early arch versions. It is OK + * for this file to be used in combination with other + * lower arch variants, since these code snippets are only + * used as input data. + */ + .arch armv4t +#endif + + .section .rodata + .global sigreturn_codes + .type sigreturn_codes, #object + + .arm + +sigreturn_codes: + + /* ARM sigreturn syscall code snippet */ + mov r7, #(__NR_sigreturn - __NR_SYSCALL_BASE) + swi #(__NR_sigreturn)|(__NR_OABI_SYSCALL_BASE) + + /* Thumb sigreturn syscall code snippet */ + .thumb + movs r7, #(__NR_sigreturn - __NR_SYSCALL_BASE) + swi #0 + + /* ARM sigreturn_rt syscall code snippet */ + .arm + mov r7, #(__NR_rt_sigreturn - __NR_SYSCALL_BASE) + swi #(__NR_rt_sigreturn)|(__NR_OABI_SYSCALL_BASE) + + /* Thumb sigreturn_rt syscall code snippet */ + .thumb + movs r7, #(__NR_rt_sigreturn - __NR_SYSCALL_BASE) + swi #0 + + /* + * Note on addtional space: setup_return in signal.c + * algorithm uses two words copy regardless whether + * it is thumb case or not, so we need additional + * word after real last entry. + */ + .arm + .space 4 + + .size sigreturn_codes, . - sigreturn_codes diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S index db1536b8b30b..b907d9b790ab 100644 --- a/arch/arm/kernel/sleep.S +++ b/arch/arm/kernel/sleep.S @@ -55,6 +55,7 @@ * specific registers and some other data for resume. * r0 = suspend function arg0 * r1 = suspend function + * r2 = MPIDR value the resuming CPU will use */ ENTRY(__cpu_suspend) stmfd sp!, {r4 - r11, lr} @@ -67,23 +68,18 @@ ENTRY(__cpu_suspend) mov r5, sp @ current virtual SP add r4, r4, #12 @ Space for pgd, virt sp, phys resume fn sub sp, sp, r4 @ allocate CPU state on stack - stmfd sp!, {r0, r1} @ save suspend func arg and pointer - add r0, sp, #8 @ save pointer to save block - mov r1, r4 @ size of save block - mov r2, r5 @ virtual SP ldr r3, =sleep_save_sp + stmfd sp!, {r0, r1} @ save suspend func arg and pointer ldr r3, [r3, #SLEEP_SAVE_SP_VIRT] - ALT_SMP(mrc p15, 0, r9, c0, c0, 5) - ALT_UP_B(1f) - ldr r8, =mpidr_hash - /* - * This ldmia relies on the memory layout of the mpidr_hash - * struct mpidr_hash. - */ - ldmia r8, {r4-r7} @ r4 = mpidr mask (r5,r6,r7) = l[0,1,2] shifts - compute_mpidr_hash lr, r5, r6, r7, r9, r4 - add r3, r3, lr, lsl #2 -1: + ALT_SMP(ldr r0, =mpidr_hash) + ALT_UP_B(1f) + /* This ldmia relies on the memory layout of the mpidr_hash struct */ + ldmia r0, {r1, r6-r8} @ r1 = mpidr mask (r6,r7,r8) = l[0,1,2] shifts + compute_mpidr_hash r0, r6, r7, r8, r2, r1 + add r3, r3, r0, lsl #2 +1: mov r2, r5 @ virtual SP + mov r1, r4 @ size of save block + add r0, sp, #8 @ pointer to save block bl __cpu_suspend_save adr lr, BSYM(cpu_suspend_abort) ldmfd sp!, {r0, pc} @ call suspend fn @@ -130,6 +126,7 @@ ENDPROC(cpu_resume_after_mmu) .data .align ENTRY(cpu_resume) +ARM_BE8(setend be) @ ensure we are in BE mode mov r1, #0 ALT_SMP(mrc p15, 0, r0, c0, c0, 5) ALT_UP_B(1f) diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 72024ea8a3a6..5c820cbcf918 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -66,6 +66,7 @@ enum ipi_msg_type { IPI_CALL_FUNC, IPI_CALL_FUNC_SINGLE, IPI_CPU_STOP, + IPI_COMPLETION, }; static DECLARE_COMPLETION(cpu_running); @@ -80,7 +81,7 @@ void __init smp_set_ops(struct smp_operations *ops) static unsigned long get_arch_pgd(pgd_t *pgd) { - phys_addr_t pgdir = virt_to_phys(pgd); + phys_addr_t pgdir = virt_to_idmap(pgd); BUG_ON(pgdir & ARCH_PGD_MASK); return pgdir >> ARCH_PGD_SHIFT; } @@ -456,6 +457,7 @@ static const char *ipi_types[NR_IPI] = { S(IPI_CALL_FUNC, "Function call interrupts"), S(IPI_CALL_FUNC_SINGLE, "Single function call interrupts"), S(IPI_CPU_STOP, "CPU stop interrupts"), + S(IPI_COMPLETION, "completion interrupts"), }; void show_ipi_list(struct seq_file *p, int prec) @@ -515,6 +517,19 @@ static void ipi_cpu_stop(unsigned int cpu) cpu_relax(); } +static DEFINE_PER_CPU(struct completion *, cpu_completion); + +int register_ipi_completion(struct completion *completion, int cpu) +{ + per_cpu(cpu_completion, cpu) = completion; + return IPI_COMPLETION; +} + +static void ipi_complete(unsigned int cpu) +{ + complete(per_cpu(cpu_completion, cpu)); +} + /* * Main handler for inter-processor interrupts */ @@ -565,6 +580,12 @@ void handle_IPI(int ipinr, struct pt_regs *regs) irq_exit(); break; + case IPI_COMPLETION: + irq_enter(); + ipi_complete(cpu); + irq_exit(); + break; + default: printk(KERN_CRIT "CPU%u: Unknown IPI message 0x%x\n", cpu, ipinr); diff --git a/arch/arm/kernel/smp_scu.c b/arch/arm/kernel/smp_scu.c index 5bc1a63284e3..1aafa0d785eb 100644 --- a/arch/arm/kernel/smp_scu.c +++ b/arch/arm/kernel/smp_scu.c @@ -28,7 +28,7 @@ */ unsigned int __init scu_get_core_count(void __iomem *scu_base) { - unsigned int ncores = __raw_readl(scu_base + SCU_CONFIG); + unsigned int ncores = readl_relaxed(scu_base + SCU_CONFIG); return (ncores & 0x03) + 1; } @@ -42,19 +42,19 @@ void scu_enable(void __iomem *scu_base) #ifdef CONFIG_ARM_ERRATA_764369 /* Cortex-A9 only */ if ((read_cpuid_id() & 0xff0ffff0) == 0x410fc090) { - scu_ctrl = __raw_readl(scu_base + 0x30); + scu_ctrl = readl_relaxed(scu_base + 0x30); if (!(scu_ctrl & 1)) - __raw_writel(scu_ctrl | 0x1, scu_base + 0x30); + writel_relaxed(scu_ctrl | 0x1, scu_base + 0x30); } #endif - scu_ctrl = __raw_readl(scu_base + SCU_CTRL); + scu_ctrl = readl_relaxed(scu_base + SCU_CTRL); /* already enabled? */ if (scu_ctrl & 1) return; scu_ctrl |= 1; - __raw_writel(scu_ctrl, scu_base + SCU_CTRL); + writel_relaxed(scu_ctrl, scu_base + SCU_CTRL); /* * Ensure that the data accessed by CPU0 before the SCU was @@ -80,9 +80,9 @@ int scu_power_mode(void __iomem *scu_base, unsigned int mode) if (mode > 3 || mode == 1 || cpu > 3) return -EINVAL; - val = __raw_readb(scu_base + SCU_CPU_STATUS + cpu) & ~0x03; + val = readb_relaxed(scu_base + SCU_CPU_STATUS + cpu) & ~0x03; val |= mode; - __raw_writeb(val, scu_base + SCU_CPU_STATUS + cpu); + writeb_relaxed(val, scu_base + SCU_CPU_STATUS + cpu); return 0; } diff --git a/arch/arm/kernel/smp_tlb.c b/arch/arm/kernel/smp_tlb.c index 83ccca303df8..95d063620b76 100644 --- a/arch/arm/kernel/smp_tlb.c +++ b/arch/arm/kernel/smp_tlb.c @@ -70,6 +70,40 @@ static inline void ipi_flush_bp_all(void *ignored) local_flush_bp_all(); } +#ifdef CONFIG_ARM_ERRATA_798181 +bool (*erratum_a15_798181_handler)(void); + +static bool erratum_a15_798181_partial(void) +{ + asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (0)); + dsb(ish); + return false; +} + +static bool erratum_a15_798181_broadcast(void) +{ + asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (0)); + dsb(ish); + return true; +} + +void erratum_a15_798181_init(void) +{ + unsigned int midr = read_cpuid_id(); + unsigned int revidr = read_cpuid(CPUID_REVIDR); + + /* Cortex-A15 r0p0..r3p2 w/o ECO fix affected */ + if ((midr & 0xff0ffff0) != 0x410fc0f0 || midr > 0x413fc0f2 || + (revidr & 0x210) == 0x210) { + return; + } + if (revidr & 0x10) + erratum_a15_798181_handler = erratum_a15_798181_partial; + else + erratum_a15_798181_handler = erratum_a15_798181_broadcast; +} +#endif + static void ipi_flush_tlb_a15_erratum(void *arg) { dmb(); @@ -80,7 +114,6 @@ static void broadcast_tlb_a15_erratum(void) if (!erratum_a15_798181()) return; - dummy_flush_tlb_a15_erratum(); smp_call_function(ipi_flush_tlb_a15_erratum, NULL, 1); } @@ -92,7 +125,6 @@ static void broadcast_tlb_mm_a15_erratum(struct mm_struct *mm) if (!erratum_a15_798181()) return; - dummy_flush_tlb_a15_erratum(); this_cpu = get_cpu(); a15_erratum_get_cpumask(this_cpu, mm, &mask); smp_call_function_many(&mask, ipi_flush_tlb_a15_erratum, NULL, 1); diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c index 2985c9f0905d..6591e26fc13f 100644 --- a/arch/arm/kernel/smp_twd.c +++ b/arch/arm/kernel/smp_twd.c @@ -45,7 +45,7 @@ static void twd_set_mode(enum clock_event_mode mode, case CLOCK_EVT_MODE_PERIODIC: ctrl = TWD_TIMER_CONTROL_ENABLE | TWD_TIMER_CONTROL_IT_ENABLE | TWD_TIMER_CONTROL_PERIODIC; - __raw_writel(DIV_ROUND_CLOSEST(twd_timer_rate, HZ), + writel_relaxed(DIV_ROUND_CLOSEST(twd_timer_rate, HZ), twd_base + TWD_TIMER_LOAD); break; case CLOCK_EVT_MODE_ONESHOT: @@ -58,18 +58,18 @@ static void twd_set_mode(enum clock_event_mode mode, ctrl = 0; } - __raw_writel(ctrl, twd_base + TWD_TIMER_CONTROL); + writel_relaxed(ctrl, twd_base + TWD_TIMER_CONTROL); } static int twd_set_next_event(unsigned long evt, struct clock_event_device *unused) { - unsigned long ctrl = __raw_readl(twd_base + TWD_TIMER_CONTROL); + unsigned long ctrl = readl_relaxed(twd_base + TWD_TIMER_CONTROL); ctrl |= TWD_TIMER_CONTROL_ENABLE; - __raw_writel(evt, twd_base + TWD_TIMER_COUNTER); - __raw_writel(ctrl, twd_base + TWD_TIMER_CONTROL); + writel_relaxed(evt, twd_base + TWD_TIMER_COUNTER); + writel_relaxed(ctrl, twd_base + TWD_TIMER_CONTROL); return 0; } @@ -82,8 +82,8 @@ static int twd_set_next_event(unsigned long evt, */ static int twd_timer_ack(void) { - if (__raw_readl(twd_base + TWD_TIMER_INTSTAT)) { - __raw_writel(1, twd_base + TWD_TIMER_INTSTAT); + if (readl_relaxed(twd_base + TWD_TIMER_INTSTAT)) { + writel_relaxed(1, twd_base + TWD_TIMER_INTSTAT); return 1; } @@ -211,15 +211,15 @@ static void twd_calibrate_rate(void) waitjiffies += 5; /* enable, no interrupt or reload */ - __raw_writel(0x1, twd_base + TWD_TIMER_CONTROL); + writel_relaxed(0x1, twd_base + TWD_TIMER_CONTROL); /* maximum value */ - __raw_writel(0xFFFFFFFFU, twd_base + TWD_TIMER_COUNTER); + writel_relaxed(0xFFFFFFFFU, twd_base + TWD_TIMER_COUNTER); while (get_jiffies_64() < waitjiffies) udelay(10); - count = __raw_readl(twd_base + TWD_TIMER_COUNTER); + count = readl_relaxed(twd_base + TWD_TIMER_COUNTER); twd_timer_rate = (0xFFFFFFFFU - count) * (HZ / 5); @@ -277,7 +277,7 @@ static void twd_timer_setup(void) * bother with the below. */ if (per_cpu(percpu_setup_called, cpu)) { - __raw_writel(0, twd_base + TWD_TIMER_CONTROL); + writel_relaxed(0, twd_base + TWD_TIMER_CONTROL); clockevents_register_device(clk); enable_percpu_irq(clk->irq, 0); return; @@ -290,7 +290,7 @@ static void twd_timer_setup(void) * The following is done once per CPU the first time .setup() is * called. */ - __raw_writel(0, twd_base + TWD_TIMER_CONTROL); + writel_relaxed(0, twd_base + TWD_TIMER_CONTROL); clk->name = "local_timer"; clk->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT | diff --git a/arch/arm/kernel/suspend.c b/arch/arm/kernel/suspend.c index 41cf3cbf756d..2835d35234ca 100644 --- a/arch/arm/kernel/suspend.c +++ b/arch/arm/kernel/suspend.c @@ -10,7 +10,7 @@ #include <asm/suspend.h> #include <asm/tlbflush.h> -extern int __cpu_suspend(unsigned long, int (*)(unsigned long)); +extern int __cpu_suspend(unsigned long, int (*)(unsigned long), u32 cpuid); extern void cpu_resume_mmu(void); #ifdef CONFIG_MMU @@ -21,6 +21,7 @@ extern void cpu_resume_mmu(void); int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) { struct mm_struct *mm = current->active_mm; + u32 __mpidr = cpu_logical_map(smp_processor_id()); int ret; if (!idmap_pgd) @@ -32,7 +33,7 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) * resume (indicated by a zero return code), we need to switch * back to the correct page tables. */ - ret = __cpu_suspend(arg, fn); + ret = __cpu_suspend(arg, fn, __mpidr); if (ret == 0) { cpu_switch_mm(mm->pgd, mm); local_flush_bp_all(); @@ -44,7 +45,8 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) #else int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) { - return __cpu_suspend(arg, fn); + u32 __mpidr = cpu_logical_map(smp_processor_id()); + return __cpu_suspend(arg, fn, __mpidr); } #define idmap_pgd NULL #endif diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index 8fcda140358d..6125f259b7b5 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -34,6 +34,7 @@ #include <asm/unwind.h> #include <asm/tls.h> #include <asm/system_misc.h> +#include <asm/opcodes.h> static const char *handler[]= { "prefetch abort", "data abort", "address exception", "interrupt" }; @@ -341,15 +342,17 @@ void arm_notify_die(const char *str, struct pt_regs *regs, int is_valid_bugaddr(unsigned long pc) { #ifdef CONFIG_THUMB2_KERNEL - unsigned short bkpt; + u16 bkpt; + u16 insn = __opcode_to_mem_thumb16(BUG_INSTR_VALUE); #else - unsigned long bkpt; + u32 bkpt; + u32 insn = __opcode_to_mem_arm(BUG_INSTR_VALUE); #endif if (probe_kernel_address((unsigned *)pc, bkpt)) return 0; - return bkpt == BUG_INSTR_VALUE; + return bkpt == insn; } #endif @@ -402,25 +405,28 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs) if (processor_mode(regs) == SVC_MODE) { #ifdef CONFIG_THUMB2_KERNEL if (thumb_mode(regs)) { - instr = ((u16 *)pc)[0]; + instr = __mem_to_opcode_thumb16(((u16 *)pc)[0]); if (is_wide_instruction(instr)) { - instr <<= 16; - instr |= ((u16 *)pc)[1]; + u16 inst2; + inst2 = __mem_to_opcode_thumb16(((u16 *)pc)[1]); + instr = __opcode_thumb32_compose(instr, inst2); } } else #endif - instr = *(u32 *) pc; + instr = __mem_to_opcode_arm(*(u32 *) pc); } else if (thumb_mode(regs)) { if (get_user(instr, (u16 __user *)pc)) goto die_sig; + instr = __mem_to_opcode_thumb16(instr); if (is_wide_instruction(instr)) { unsigned int instr2; if (get_user(instr2, (u16 __user *)pc+1)) goto die_sig; - instr <<= 16; - instr |= instr2; + instr2 = __mem_to_opcode_thumb16(instr2); + instr = __opcode_thumb32_compose(instr, instr2); } } else if (get_user(instr, (u32 __user *)pc)) { + instr = __mem_to_opcode_arm(instr); goto die_sig; } diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index 9c697db2787e..aea7ccb8d397 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -65,7 +65,7 @@ static bool vgic_present; static void kvm_arm_set_running_vcpu(struct kvm_vcpu *vcpu) { BUG_ON(preemptible()); - __get_cpu_var(kvm_arm_running_vcpu) = vcpu; + __this_cpu_write(kvm_arm_running_vcpu, vcpu); } /** @@ -75,7 +75,7 @@ static void kvm_arm_set_running_vcpu(struct kvm_vcpu *vcpu) struct kvm_vcpu *kvm_arm_get_running_vcpu(void) { BUG_ON(preemptible()); - return __get_cpu_var(kvm_arm_running_vcpu); + return __this_cpu_read(kvm_arm_running_vcpu); } /** @@ -815,7 +815,7 @@ static void cpu_init_hyp_mode(void *dummy) boot_pgd_ptr = kvm_mmu_get_boot_httbr(); pgd_ptr = kvm_mmu_get_httbr(); - stack_page = __get_cpu_var(kvm_arm_hyp_stack_page); + stack_page = __this_cpu_read(kvm_arm_hyp_stack_page); hyp_stack_ptr = stack_page + PAGE_SIZE; vector_ptr = (unsigned long)__kvm_hyp_vector; diff --git a/arch/arm/lib/bitops.h b/arch/arm/lib/bitops.h index d6408d1ee543..e0c68d5bb7dc 100644 --- a/arch/arm/lib/bitops.h +++ b/arch/arm/lib/bitops.h @@ -10,6 +10,11 @@ UNWIND( .fnstart ) and r3, r0, #31 @ Get bit offset mov r0, r0, lsr #5 add r1, r1, r0, lsl #2 @ Get word offset +#if __LINUX_ARM_ARCH__ >= 7 + .arch_extension mp + ALT_SMP(W(pldw) [r1]) + ALT_UP(W(nop)) +#endif mov r3, r2, lsl r3 1: ldrex r2, [r1] \instr r2, r2, r3 diff --git a/arch/arm/lib/uaccess_with_memcpy.c b/arch/arm/lib/uaccess_with_memcpy.c index 025f742dd4df..3e58d710013c 100644 --- a/arch/arm/lib/uaccess_with_memcpy.c +++ b/arch/arm/lib/uaccess_with_memcpy.c @@ -18,6 +18,7 @@ #include <linux/hardirq.h> /* for in_atomic() */ #include <linux/gfp.h> #include <linux/highmem.h> +#include <linux/hugetlb.h> #include <asm/current.h> #include <asm/page.h> @@ -40,7 +41,35 @@ pin_page_for_write(const void __user *_addr, pte_t **ptep, spinlock_t **ptlp) return 0; pmd = pmd_offset(pud, addr); - if (unlikely(pmd_none(*pmd) || pmd_bad(*pmd))) + if (unlikely(pmd_none(*pmd))) + return 0; + + /* + * A pmd can be bad if it refers to a HugeTLB or THP page. + * + * Both THP and HugeTLB pages have the same pmd layout + * and should not be manipulated by the pte functions. + * + * Lock the page table for the destination and check + * to see that it's still huge and whether or not we will + * need to fault on write, or if we have a splitting THP. + */ + if (unlikely(pmd_thp_or_huge(*pmd))) { + ptl = ¤t->mm->page_table_lock; + spin_lock(ptl); + if (unlikely(!pmd_thp_or_huge(*pmd) + || pmd_hugewillfault(*pmd) + || pmd_trans_splitting(*pmd))) { + spin_unlock(ptl); + return 0; + } + + *ptep = NULL; + *ptlp = ptl; + return 1; + } + + if (unlikely(pmd_bad(*pmd))) return 0; pte = pte_offset_map_lock(current->mm, pmd, addr, &ptl); @@ -94,7 +123,10 @@ __copy_to_user_memcpy(void __user *to, const void *from, unsigned long n) from += tocopy; n -= tocopy; - pte_unmap_unlock(pte, ptl); + if (pte) + pte_unmap_unlock(pte, ptl); + else + spin_unlock(ptl); } if (!atomic) up_read(¤t->mm->mmap_sem); @@ -147,7 +179,10 @@ __clear_user_memset(void __user *addr, unsigned long n) addr += tocopy; n -= tocopy; - pte_unmap_unlock(pte, ptl); + if (pte) + pte_unmap_unlock(pte, ptl); + else + spin_unlock(ptl); } up_read(¤t->mm->mmap_sem); diff --git a/arch/arm/mach-highbank/Kconfig b/arch/arm/mach-highbank/Kconfig index fe98df44579c..08332d841440 100644 --- a/arch/arm/mach-highbank/Kconfig +++ b/arch/arm/mach-highbank/Kconfig @@ -4,11 +4,12 @@ config ARCH_HIGHBANK select ARCH_HAS_CPUFREQ select ARCH_HAS_HOLES_MEMORYMODEL select ARCH_HAS_OPP + select ARCH_SUPPORTS_BIG_ENDIAN select ARCH_WANT_OPTIONAL_GPIOLIB select ARM_AMBA select ARM_ERRATA_764369 select ARM_ERRATA_775420 - select ARM_ERRATA_798181 + select ARM_ERRATA_798181 if SMP select ARM_GIC select ARM_PSCI select ARM_TIMER_SP804 diff --git a/arch/arm/mach-ixp4xx/Kconfig b/arch/arm/mach-ixp4xx/Kconfig index 30e1ebe3a891..c342dc4e8a45 100644 --- a/arch/arm/mach-ixp4xx/Kconfig +++ b/arch/arm/mach-ixp4xx/Kconfig @@ -1,9 +1,5 @@ if ARCH_IXP4XX -config ARCH_SUPPORTS_BIG_ENDIAN - bool - default y - menu "Intel IXP4xx Implementation Options" comment "IXP4xx Platforms" diff --git a/arch/arm/mach-mvebu/Kconfig b/arch/arm/mach-mvebu/Kconfig index 9eb63d724602..5e269d7263ce 100644 --- a/arch/arm/mach-mvebu/Kconfig +++ b/arch/arm/mach-mvebu/Kconfig @@ -1,5 +1,6 @@ config ARCH_MVEBU bool "Marvell SOCs with Device Tree support" if ARCH_MULTI_V7 + select ARCH_SUPPORTS_BIG_ENDIAN select CLKSRC_MMIO select COMMON_CLK select GENERIC_CLOCKEVENTS diff --git a/arch/arm/mach-mvebu/coherency_ll.S b/arch/arm/mach-mvebu/coherency_ll.S index 5476669ba905..ee7598fe75db 100644 --- a/arch/arm/mach-mvebu/coherency_ll.S +++ b/arch/arm/mach-mvebu/coherency_ll.S @@ -20,6 +20,8 @@ #define ARMADA_XP_CFB_CTL_REG_OFFSET 0x0 #define ARMADA_XP_CFB_CFG_REG_OFFSET 0x4 +#include <asm/assembler.h> + .text /* * r0: Coherency fabric base register address @@ -29,6 +31,7 @@ ENTRY(ll_set_cpu_coherent) /* Create bit by cpu index */ mov r3, #(1 << 24) lsl r1, r3, r1 +ARM_BE8(rev r1, r1) /* Add CPU to SMP group - Atomic */ add r3, r0, #ARMADA_XP_CFB_CTL_REG_OFFSET diff --git a/arch/arm/mach-mvebu/headsmp.S b/arch/arm/mach-mvebu/headsmp.S index 8a1b0c96e9ec..3dd80df428f7 100644 --- a/arch/arm/mach-mvebu/headsmp.S +++ b/arch/arm/mach-mvebu/headsmp.S @@ -21,12 +21,16 @@ #include <linux/linkage.h> #include <linux/init.h> +#include <asm/assembler.h> + /* * Armada XP specific entry point for secondary CPUs. * We add the CPU to the coherency fabric and then jump to secondary * startup */ ENTRY(armada_xp_secondary_startup) + ARM_BE8(setend be ) @ go BE8 if entered LE + /* Get coherency fabric base physical address */ adr r0, 1f ldr r1, [r0] diff --git a/arch/arm/mach-sa1100/assabet.c b/arch/arm/mach-sa1100/assabet.c index e838ba27e443..c9808c684152 100644 --- a/arch/arm/mach-sa1100/assabet.c +++ b/arch/arm/mach-sa1100/assabet.c @@ -512,6 +512,9 @@ static void __init assabet_map_io(void) * Its called GPCLKR0 in my SA1110 manual. */ Ser1SDCR0 |= SDCR0_SUS; + MSC1 = (MSC1 & ~0xffff) | + MSC_NonBrst | MSC_32BitStMem | + MSC_RdAcc(2) | MSC_WrAcc(2) | MSC_Rec(0); if (!machine_has_neponset()) sa1100_register_uart_fns(&assabet_port_fns); diff --git a/arch/arm/mach-sa1100/include/mach/gpio.h b/arch/arm/mach-sa1100/include/mach/gpio.h deleted file mode 100644 index 6a9eecf3137e..000000000000 --- a/arch/arm/mach-sa1100/include/mach/gpio.h +++ /dev/null @@ -1,55 +0,0 @@ -/* - * arch/arm/mach-sa1100/include/mach/gpio.h - * - * SA1100 GPIO wrappers for arch-neutral GPIO calls - * - * Written by Philipp Zabel <philipp.zabel@gmail.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * - */ - -#ifndef __ASM_ARCH_SA1100_GPIO_H -#define __ASM_ARCH_SA1100_GPIO_H - -#include <linux/io.h> -#include <mach/hardware.h> -#include <asm/irq.h> -#include <asm-generic/gpio.h> - -#define __ARM_GPIOLIB_COMPLEX - -static inline int gpio_get_value(unsigned gpio) -{ - if (__builtin_constant_p(gpio) && (gpio <= GPIO_MAX)) - return GPLR & GPIO_GPIO(gpio); - else - return __gpio_get_value(gpio); -} - -static inline void gpio_set_value(unsigned gpio, int value) -{ - if (__builtin_constant_p(gpio) && (gpio <= GPIO_MAX)) - if (value) - GPSR = GPIO_GPIO(gpio); - else - GPCR = GPIO_GPIO(gpio); - else - __gpio_set_value(gpio, value); -} - -#define gpio_cansleep __gpio_cansleep - -#endif diff --git a/arch/arm/mach-sa1100/include/mach/h3xxx.h b/arch/arm/mach-sa1100/include/mach/h3xxx.h index 7d9df16f04a2..c810620db53d 100644 --- a/arch/arm/mach-sa1100/include/mach/h3xxx.h +++ b/arch/arm/mach-sa1100/include/mach/h3xxx.h @@ -13,6 +13,8 @@ #ifndef _INCLUDE_H3XXX_H_ #define _INCLUDE_H3XXX_H_ +#include "hardware.h" /* Gives GPIO_MAX */ + /* Physical memory regions corresponding to chip selects */ #define H3600_EGPIO_PHYS (SA1100_CS5_PHYS + 0x01000000) #define H3600_BANK_2_PHYS SA1100_CS2_PHYS diff --git a/arch/arm/mach-sa1100/simpad.c b/arch/arm/mach-sa1100/simpad.c index bcbc94540e45..41e476e571d7 100644 --- a/arch/arm/mach-sa1100/simpad.c +++ b/arch/arm/mach-sa1100/simpad.c @@ -19,6 +19,7 @@ #include <mach/hardware.h> #include <asm/setup.h> +#include <asm/irq.h> #include <asm/mach-types.h> #include <asm/mach/arch.h> diff --git a/arch/arm/mach-tegra/Kconfig b/arch/arm/mach-tegra/Kconfig index 0bf04a0bca9d..09e740f58b27 100644 --- a/arch/arm/mach-tegra/Kconfig +++ b/arch/arm/mach-tegra/Kconfig @@ -51,7 +51,7 @@ config ARCH_TEGRA_3x_SOC config ARCH_TEGRA_114_SOC bool "Enable support for Tegra114 family" - select ARM_ERRATA_798181 + select ARM_ERRATA_798181 if SMP select ARM_L1_CACHE_SHIFT_6 select HAVE_ARM_ARCH_TIMER select PINCTRL_TEGRA114 diff --git a/arch/arm/mach-vexpress/Kconfig b/arch/arm/mach-vexpress/Kconfig index d7e7422527ca..cbbb81e0e509 100644 --- a/arch/arm/mach-vexpress/Kconfig +++ b/arch/arm/mach-vexpress/Kconfig @@ -1,6 +1,7 @@ config ARCH_VEXPRESS bool "ARM Ltd. Versatile Express family" if ARCH_MULTI_V7 select ARCH_REQUIRE_GPIOLIB + select ARCH_SUPPORTS_BIG_ENDIAN select ARM_AMBA select ARM_GIC select ARM_TIMER_SP804 diff --git a/arch/arm/mach-vexpress/dcscb.c b/arch/arm/mach-vexpress/dcscb.c index 3a6384c6c435..14d499688736 100644 --- a/arch/arm/mach-vexpress/dcscb.c +++ b/arch/arm/mach-vexpress/dcscb.c @@ -133,38 +133,8 @@ static void dcscb_power_down(void) if (last_man && __mcpm_outbound_enter_critical(cpu, cluster)) { arch_spin_unlock(&dcscb_lock); - /* - * Flush all cache levels for this cluster. - * - * To do so we do: - * - Clear the SCTLR.C bit to prevent further cache allocations - * - Flush the whole cache - * - Clear the ACTLR "SMP" bit to disable local coherency - * - * Let's do it in the safest possible way i.e. with - * no memory access within the following sequence - * including to the stack. - * - * Note: fp is preserved to the stack explicitly prior doing - * this since adding it to the clobber list is incompatible - * with having CONFIG_FRAME_POINTER=y. - */ - asm volatile( - "str fp, [sp, #-4]! \n\t" - "mrc p15, 0, r0, c1, c0, 0 @ get CR \n\t" - "bic r0, r0, #"__stringify(CR_C)" \n\t" - "mcr p15, 0, r0, c1, c0, 0 @ set CR \n\t" - "isb \n\t" - "bl v7_flush_dcache_all \n\t" - "clrex \n\t" - "mrc p15, 0, r0, c1, c0, 1 @ get AUXCR \n\t" - "bic r0, r0, #(1 << 6) @ disable local coherency \n\t" - "mcr p15, 0, r0, c1, c0, 1 @ set AUXCR \n\t" - "isb \n\t" - "dsb \n\t" - "ldr fp, [sp], #4" - : : : "r0","r1","r2","r3","r4","r5","r6","r7", - "r9","r10","lr","memory"); + /* Flush all cache levels for this cluster. */ + v7_exit_coherency_flush(all); /* * This is a harmless no-op. On platforms with a real @@ -183,26 +153,8 @@ static void dcscb_power_down(void) } else { arch_spin_unlock(&dcscb_lock); - /* - * Flush the local CPU cache. - * Let's do it in the safest possible way as above. - */ - asm volatile( - "str fp, [sp, #-4]! \n\t" - "mrc p15, 0, r0, c1, c0, 0 @ get CR \n\t" - "bic r0, r0, #"__stringify(CR_C)" \n\t" - "mcr p15, 0, r0, c1, c0, 0 @ set CR \n\t" - "isb \n\t" - "bl v7_flush_dcache_louis \n\t" - "clrex \n\t" - "mrc p15, 0, r0, c1, c0, 1 @ get AUXCR \n\t" - "bic r0, r0, #(1 << 6) @ disable local coherency \n\t" - "mcr p15, 0, r0, c1, c0, 1 @ set AUXCR \n\t" - "isb \n\t" - "dsb \n\t" - "ldr fp, [sp], #4" - : : : "r0","r1","r2","r3","r4","r5","r6","r7", - "r9","r10","lr","memory"); + /* Disable and flush the local CPU cache. */ + v7_exit_coherency_flush(louis); } __mcpm_cpu_down(cpu, cluster); diff --git a/arch/arm/mach-vexpress/tc2_pm.c b/arch/arm/mach-vexpress/tc2_pm.c index e6eb48192912..4eb92ebfd953 100644 --- a/arch/arm/mach-vexpress/tc2_pm.c +++ b/arch/arm/mach-vexpress/tc2_pm.c @@ -156,32 +156,7 @@ static void tc2_pm_down(u64 residency) : : "r" (0x400) ); } - /* - * We need to disable and flush the whole (L1 and L2) cache. - * Let's do it in the safest possible way i.e. with - * no memory access within the following sequence - * including the stack. - * - * Note: fp is preserved to the stack explicitly prior doing - * this since adding it to the clobber list is incompatible - * with having CONFIG_FRAME_POINTER=y. - */ - asm volatile( - "str fp, [sp, #-4]! \n\t" - "mrc p15, 0, r0, c1, c0, 0 @ get CR \n\t" - "bic r0, r0, #"__stringify(CR_C)" \n\t" - "mcr p15, 0, r0, c1, c0, 0 @ set CR \n\t" - "isb \n\t" - "bl v7_flush_dcache_all \n\t" - "clrex \n\t" - "mrc p15, 0, r0, c1, c0, 1 @ get AUXCR \n\t" - "bic r0, r0, #(1 << 6) @ disable local coherency \n\t" - "mcr p15, 0, r0, c1, c0, 1 @ set AUXCR \n\t" - "isb \n\t" - "dsb \n\t" - "ldr fp, [sp], #4" - : : : "r0","r1","r2","r3","r4","r5","r6","r7", - "r9","r10","lr","memory"); + v7_exit_coherency_flush(all); cci_disable_port_by_cpu(mpidr); @@ -197,26 +172,7 @@ static void tc2_pm_down(u64 residency) arch_spin_unlock(&tc2_pm_lock); - /* - * We need to disable and flush only the L1 cache. - * Let's do it in the safest possible way as above. - */ - asm volatile( - "str fp, [sp, #-4]! \n\t" - "mrc p15, 0, r0, c1, c0, 0 @ get CR \n\t" - "bic r0, r0, #"__stringify(CR_C)" \n\t" - "mcr p15, 0, r0, c1, c0, 0 @ set CR \n\t" - "isb \n\t" - "bl v7_flush_dcache_louis \n\t" - "clrex \n\t" - "mrc p15, 0, r0, c1, c0, 1 @ get AUXCR \n\t" - "bic r0, r0, #(1 << 6) @ disable local coherency \n\t" - "mcr p15, 0, r0, c1, c0, 1 @ set AUXCR \n\t" - "isb \n\t" - "dsb \n\t" - "ldr fp, [sp], #4" - : : : "r0","r1","r2","r3","r4","r5","r6","r7", - "r9","r10","lr","memory"); + v7_exit_coherency_flush(louis); } __mcpm_cpu_down(cpu, cluster); diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index cd2c88e7a8f7..1f8fed94c2a4 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -952,3 +952,9 @@ config ARCH_HAS_BARRIERS help This option allows the use of custom mandatory barriers included via the mach/barriers.h file. + +config ARCH_SUPPORTS_BIG_ENDIAN + bool + help + This option specifies the architecture can support big endian + operation. diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S index 80741992a9fc..3815a8262af0 100644 --- a/arch/arm/mm/abort-ev6.S +++ b/arch/arm/mm/abort-ev6.S @@ -38,9 +38,8 @@ ENTRY(v6_early_abort) bne do_DataAbort bic r1, r1, #1 << 11 @ clear bit 11 of FSR ldr r3, [r4] @ read aborted ARM instruction -#ifdef CONFIG_CPU_ENDIAN_BE8 - rev r3, r3 -#endif + ARM_BE8(rev r3, r3) + do_ldrd_abort tmp=ip, insn=r3 tst r3, #1 << 20 @ L = 0 -> write orreq r1, r1, #1 << 11 @ yes. diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index 6f4585b89078..924036473b16 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -25,6 +25,7 @@ #include <asm/cp15.h> #include <asm/system_info.h> #include <asm/unaligned.h> +#include <asm/opcodes.h> #include "fault.h" @@ -762,21 +763,25 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) if (thumb_mode(regs)) { u16 *ptr = (u16 *)(instrptr & ~1); fault = probe_kernel_address(ptr, tinstr); + tinstr = __mem_to_opcode_thumb16(tinstr); if (!fault) { if (cpu_architecture() >= CPU_ARCH_ARMv7 && IS_T32(tinstr)) { /* Thumb-2 32-bit */ u16 tinst2 = 0; fault = probe_kernel_address(ptr + 1, tinst2); - instr = (tinstr << 16) | tinst2; + tinst2 = __mem_to_opcode_thumb16(tinst2); + instr = __opcode_thumb32_compose(tinstr, tinst2); thumb2_32b = 1; } else { isize = 2; instr = thumb2arm(tinstr); } } - } else + } else { fault = probe_kernel_address(instrptr, instr); + instr = __mem_to_opcode_arm(instr); + } if (fault) { type = TYPE_FAULT; diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index f5e1a8471714..79f8b39801a8 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -159,7 +159,7 @@ EXPORT_SYMBOL(arm_coherent_dma_ops); static u64 get_coherent_dma_mask(struct device *dev) { - u64 mask = (u64)arm_dma_limit; + u64 mask = (u64)DMA_BIT_MASK(32); if (dev) { mask = dev->coherent_dma_mask; @@ -173,10 +173,30 @@ static u64 get_coherent_dma_mask(struct device *dev) return 0; } - if ((~mask) & (u64)arm_dma_limit) { - dev_warn(dev, "coherent DMA mask %#llx is smaller " - "than system GFP_DMA mask %#llx\n", - mask, (u64)arm_dma_limit); + /* + * If the mask allows for more memory than we can address, + * and we actually have that much memory, then fail the + * allocation. + */ + if (sizeof(mask) != sizeof(dma_addr_t) && + mask > (dma_addr_t)~0 && + dma_to_pfn(dev, ~0) > arm_dma_pfn_limit) { + dev_warn(dev, "Coherent DMA mask %#llx is larger than dma_addr_t allows\n", + mask); + dev_warn(dev, "Driver did not use or check the return value from dma_set_coherent_mask()?\n"); + return 0; + } + + /* + * Now check that the mask, when translated to a PFN, + * fits within the allowable addresses which we can + * allocate. + */ + if (dma_to_pfn(dev, mask) < arm_dma_pfn_limit) { + dev_warn(dev, "Coherent DMA mask %#llx (pfn %#lx-%#lx) covers a smaller range of system memory than the DMA zone pfn 0x0-%#lx\n", + mask, + dma_to_pfn(dev, 0), dma_to_pfn(dev, mask) + 1, + arm_dma_pfn_limit + 1); return 0; } } @@ -687,7 +707,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs) { - pgprot_t prot = __get_dma_pgprot(attrs, pgprot_kernel); + pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL); void *memory; if (dma_alloc_from_coherent(dev, size, handle, &memory)) @@ -700,7 +720,7 @@ void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, static void *arm_coherent_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs) { - pgprot_t prot = __get_dma_pgprot(attrs, pgprot_kernel); + pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL); void *memory; if (dma_alloc_from_coherent(dev, size, handle, &memory)) @@ -1007,8 +1027,27 @@ void arm_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, */ int dma_supported(struct device *dev, u64 mask) { - if (mask < (u64)arm_dma_limit) + unsigned long limit; + + /* + * If the mask allows for more memory than we can address, + * and we actually have that much memory, then we must + * indicate that DMA to this device is not supported. + */ + if (sizeof(mask) != sizeof(dma_addr_t) && + mask > (dma_addr_t)~0 && + dma_to_pfn(dev, ~0) > arm_dma_pfn_limit) + return 0; + + /* + * Translate the device's DMA mask to a PFN limit. This + * PFN number includes the page which we can DMA to. + */ + limit = dma_to_pfn(dev, mask); + + if (limit < arm_dma_pfn_limit) return 0; + return 1; } EXPORT_SYMBOL(dma_supported); @@ -1232,7 +1271,8 @@ __iommu_create_mapping(struct device *dev, struct page **pages, size_t size) break; len = (j - i) << PAGE_SHIFT; - ret = iommu_map(mapping->domain, iova, phys, len, 0); + ret = iommu_map(mapping->domain, iova, phys, len, + IOMMU_READ|IOMMU_WRITE); if (ret < 0) goto fail; iova += len; @@ -1431,6 +1471,27 @@ static int arm_iommu_get_sgtable(struct device *dev, struct sg_table *sgt, GFP_KERNEL); } +static int __dma_direction_to_prot(enum dma_data_direction dir) +{ + int prot; + + switch (dir) { + case DMA_BIDIRECTIONAL: + prot = IOMMU_READ | IOMMU_WRITE; + break; + case DMA_TO_DEVICE: + prot = IOMMU_READ; + break; + case DMA_FROM_DEVICE: + prot = IOMMU_WRITE; + break; + default: + prot = 0; + } + + return prot; +} + /* * Map a part of the scatter-gather list into contiguous io address space */ @@ -1444,6 +1505,7 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg, int ret = 0; unsigned int count; struct scatterlist *s; + int prot; size = PAGE_ALIGN(size); *handle = DMA_ERROR_CODE; @@ -1460,7 +1522,9 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg, !dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) __dma_page_cpu_to_dev(sg_page(s), s->offset, s->length, dir); - ret = iommu_map(mapping->domain, iova, phys, len, 0); + prot = __dma_direction_to_prot(dir); + + ret = iommu_map(mapping->domain, iova, phys, len, prot); if (ret < 0) goto fail; count += len >> PAGE_SHIFT; @@ -1665,19 +1729,7 @@ static dma_addr_t arm_coherent_iommu_map_page(struct device *dev, struct page *p if (dma_addr == DMA_ERROR_CODE) return dma_addr; - switch (dir) { - case DMA_BIDIRECTIONAL: - prot = IOMMU_READ | IOMMU_WRITE; - break; - case DMA_TO_DEVICE: - prot = IOMMU_READ; - break; - case DMA_FROM_DEVICE: - prot = IOMMU_WRITE; - break; - default: - prot = 0; - } + prot = __dma_direction_to_prot(dir); ret = iommu_map(mapping->domain, dma_addr, page_to_phys(page), len, prot); if (ret < 0) diff --git a/arch/arm/mm/idmap.c b/arch/arm/mm/idmap.c index 83cb3ac27095..8e0e52eb76b5 100644 --- a/arch/arm/mm/idmap.c +++ b/arch/arm/mm/idmap.c @@ -10,6 +10,7 @@ #include <asm/system_info.h> pgd_t *idmap_pgd; +phys_addr_t (*arch_virt_to_idmap) (unsigned long x); #ifdef CONFIG_ARM_LPAE static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end, @@ -67,8 +68,9 @@ static void identity_mapping_add(pgd_t *pgd, const char *text_start, unsigned long addr, end; unsigned long next; - addr = virt_to_phys(text_start); - end = virt_to_phys(text_end); + addr = virt_to_idmap(text_start); + end = virt_to_idmap(text_end); + pr_info("Setting up static identity map for 0x%lx - 0x%lx\n", addr, end); prot |= PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_AF; @@ -90,8 +92,6 @@ static int __init init_static_idmap(void) if (!idmap_pgd) return -ENOMEM; - pr_info("Setting up static identity map for 0x%p - 0x%p\n", - __idmap_text_start, __idmap_text_end); identity_mapping_add(idmap_pgd, __idmap_text_start, __idmap_text_end, 0); diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index febaee7ca57b..2a3fa425c52c 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -17,7 +17,6 @@ #include <linux/nodemask.h> #include <linux/initrd.h> #include <linux/of_fdt.h> -#include <linux/of_reserved_mem.h> #include <linux/highmem.h> #include <linux/gfp.h> #include <linux/memblock.h> @@ -218,6 +217,7 @@ EXPORT_SYMBOL(arm_dma_zone_size); * so a successful GFP_DMA allocation will always satisfy this. */ phys_addr_t arm_dma_limit; +unsigned long arm_dma_pfn_limit; static void __init arm_adjust_dma_zone(unsigned long *size, unsigned long *hole, unsigned long dma_size) @@ -240,6 +240,7 @@ void __init setup_dma_zone(const struct machine_desc *mdesc) arm_dma_limit = PHYS_OFFSET + arm_dma_zone_size - 1; } else arm_dma_limit = 0xffffffff; + arm_dma_pfn_limit = arm_dma_limit >> PAGE_SHIFT; #endif } @@ -379,8 +380,6 @@ void __init arm_memblock_init(struct meminfo *mi, if (mdesc->reserve) mdesc->reserve(); - early_init_dt_scan_reserved_mem(); - /* * reserve memory for DMA contigouos allocations, * must come from DMA area inside low memory @@ -424,12 +423,10 @@ void __init bootmem_init(void) * This doesn't seem to be used by the Linux memory manager any * more, but is used by ll_rw_block. If we can get rid of it, we * also get rid of some of the stuff above as well. - * - * Note: max_low_pfn and max_pfn reflect the number of _pages_ in - * the system, not the maximum PFN. */ - max_low_pfn = max_low - PHYS_PFN_OFFSET; - max_pfn = max_high - PHYS_PFN_OFFSET; + min_low_pfn = min; + max_low_pfn = max_low; + max_pfn = max_high; } /* @@ -535,7 +532,7 @@ static inline void free_area_high(unsigned long pfn, unsigned long end) static void __init free_highpages(void) { #ifdef CONFIG_HIGHMEM - unsigned long max_low = max_low_pfn + PHYS_PFN_OFFSET; + unsigned long max_low = max_low_pfn; struct memblock_region *mem, *res; /* set highmem page free */ diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h index d5a4e9ad8f0f..d5a982d15a88 100644 --- a/arch/arm/mm/mm.h +++ b/arch/arm/mm/mm.h @@ -81,8 +81,10 @@ extern __init void add_static_vm_early(struct static_vm *svm); #ifdef CONFIG_ZONE_DMA extern phys_addr_t arm_dma_limit; +extern unsigned long arm_dma_pfn_limit; #else #define arm_dma_limit ((phys_addr_t)~0) +#define arm_dma_pfn_limit (~0ul >> PAGE_SHIFT) #endif extern phys_addr_t arm_lowmem_limit; diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c index 0c6356255fe3..d27158c38eb0 100644 --- a/arch/arm/mm/mmap.c +++ b/arch/arm/mm/mmap.c @@ -202,13 +202,11 @@ int valid_phys_addr_range(phys_addr_t addr, size_t size) } /* - * We don't use supersection mappings for mmap() on /dev/mem, which - * means that we can't map the memory area above the 4G barrier into - * userspace. + * Do not allow /dev/mem mappings beyond the supported physical range. */ int valid_mmap_phys_addr_range(unsigned long pfn, size_t size) { - return !(pfn + (size >> PAGE_SHIFT) > 0x00100000); + return (pfn + (size >> PAGE_SHIFT)) <= (1 + (PHYS_MASK >> PAGE_SHIFT)); } #ifdef CONFIG_STRICT_DEVMEM diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index b1d17eeb59b8..78eeeca78f5a 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -28,6 +28,8 @@ #include <asm/highmem.h> #include <asm/system_info.h> #include <asm/traps.h> +#include <asm/procinfo.h> +#include <asm/memory.h> #include <asm/mach/arch.h> #include <asm/mach/map.h> @@ -1315,6 +1317,86 @@ static void __init map_lowmem(void) } } +#ifdef CONFIG_ARM_LPAE +/* + * early_paging_init() recreates boot time page table setup, allowing machines + * to switch over to a high (>4G) address space on LPAE systems + */ +void __init early_paging_init(const struct machine_desc *mdesc, + struct proc_info_list *procinfo) +{ + pmdval_t pmdprot = procinfo->__cpu_mm_mmu_flags; + unsigned long map_start, map_end; + pgd_t *pgd0, *pgdk; + pud_t *pud0, *pudk, *pud_start; + pmd_t *pmd0, *pmdk; + phys_addr_t phys; + int i; + + if (!(mdesc->init_meminfo)) + return; + + /* remap kernel code and data */ + map_start = init_mm.start_code; + map_end = init_mm.brk; + + /* get a handle on things... */ + pgd0 = pgd_offset_k(0); + pud_start = pud0 = pud_offset(pgd0, 0); + pmd0 = pmd_offset(pud0, 0); + + pgdk = pgd_offset_k(map_start); + pudk = pud_offset(pgdk, map_start); + pmdk = pmd_offset(pudk, map_start); + + mdesc->init_meminfo(); + + /* Run the patch stub to update the constants */ + fixup_pv_table(&__pv_table_begin, + (&__pv_table_end - &__pv_table_begin) << 2); + + /* + * Cache cleaning operations for self-modifying code + * We should clean the entries by MVA but running a + * for loop over every pv_table entry pointer would + * just complicate the code. + */ + flush_cache_louis(); + dsb(); + isb(); + + /* remap level 1 table */ + for (i = 0; i < PTRS_PER_PGD; pud0++, i++) { + set_pud(pud0, + __pud(__pa(pmd0) | PMD_TYPE_TABLE | L_PGD_SWAPPER)); + pmd0 += PTRS_PER_PMD; + } + + /* remap pmds for kernel mapping */ + phys = __pa(map_start) & PMD_MASK; + do { + *pmdk++ = __pmd(phys | pmdprot); + phys += PMD_SIZE; + } while (phys < map_end); + + flush_cache_all(); + cpu_switch_mm(pgd0, &init_mm); + cpu_set_ttbr(1, __pa(pgd0) + TTBR1_OFFSET); + local_flush_bp_all(); + local_flush_tlb_all(); +} + +#else + +void __init early_paging_init(const struct machine_desc *mdesc, + struct proc_info_list *procinfo) +{ + if (mdesc->init_meminfo) + mdesc->init_meminfo(); +} + +#endif + /* * paging_init() sets up the page tables, initialises the zone memory * maps, and sets up the zero page, bad page and bad page tables. diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S index 1128064fddcb..45dc29f85d56 100644 --- a/arch/arm/mm/proc-v6.S +++ b/arch/arm/mm/proc-v6.S @@ -220,9 +220,7 @@ __v6_setup: #endif /* CONFIG_MMU */ adr r5, v6_crval ldmia r5, {r5, r6} -#ifdef CONFIG_CPU_ENDIAN_BE8 - orr r6, r6, #1 << 25 @ big-endian page tables -#endif + ARM_BE8(orr r6, r6, #1 << 25) @ big-endian page tables mrc p15, 0, r0, c1, c0, 0 @ read control register bic r0, r0, r5 @ clear bits them orr r0, r0, r6 @ set them diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index c63d9bdee51e..60920f62fdf5 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -367,9 +367,7 @@ __v7_setup: #endif adr r5, v7_crval ldmia r5, {r5, r6} -#ifdef CONFIG_CPU_ENDIAN_BE8 - orr r6, r6, #1 << 25 @ big-endian page tables -#endif + ARM_BE8(orr r6, r6, #1 << 25) @ big-endian page tables #ifdef CONFIG_SWP_EMULATE orr r5, r5, #(1 << 10) @ set SW bit in "clear" bic r6, r6, #(1 << 10) @ clear it in "mmuset" diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index f50d223a0bd3..9ed155ad0f97 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -19,6 +19,7 @@ #include <linux/if_vlan.h> #include <asm/cacheflush.h> #include <asm/hwcap.h> +#include <asm/opcodes.h> #include "bpf_jit_32.h" @@ -113,8 +114,11 @@ static u32 jit_udiv(u32 dividend, u32 divisor) static inline void _emit(int cond, u32 inst, struct jit_ctx *ctx) { + inst |= (cond << 28); + inst = __opcode_to_mem_arm(inst); + if (ctx->target != NULL) - ctx->target[ctx->idx] = inst | (cond << 28); + ctx->target[ctx->idx] = inst; ctx->idx++; } @@ -930,4 +934,5 @@ void bpf_jit_free(struct sk_filter *fp) { if (fp->bpf_func != sk_run_filter) module_free(NULL, fp->bpf_func); + kfree(fp); } diff --git a/arch/arm/plat-versatile/headsmp.S b/arch/arm/plat-versatile/headsmp.S index 2677bc3762d7..40f27e52de75 100644 --- a/arch/arm/plat-versatile/headsmp.S +++ b/arch/arm/plat-versatile/headsmp.S @@ -10,6 +10,7 @@ */ #include <linux/linkage.h> #include <linux/init.h> +#include <asm/assembler.h> /* * Realview/Versatile Express specific entry point for secondary CPUs. @@ -17,6 +18,7 @@ * until we're ready for them to initialise. */ ENTRY(versatile_secondary_startup) + ARM_BE8(setend be) mrc p15, 0, r0, c0, c0, 5 bic r0, #0xff000000 adr r4, 1f diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c index 52b8f40b1c73..2f37e1d6cb45 100644 --- a/arch/arm/vfp/vfpmodule.c +++ b/arch/arm/vfp/vfpmodule.c @@ -642,9 +642,9 @@ int vfp_restore_user_hwstate(struct user_vfp __user *ufp, static int vfp_hotplug(struct notifier_block *b, unsigned long action, void *hcpu) { - if (action == CPU_DYING || action == CPU_DYING_FROZEN) { - vfp_force_reload((long)hcpu, current_thread_info()); - } else if (action == CPU_STARTING || action == CPU_STARTING_FROZEN) + if (action == CPU_DYING || action == CPU_DYING_FROZEN) + vfp_current_hw_state[(long)hcpu] = NULL; + else if (action == CPU_STARTING || action == CPU_STARTING_FROZEN) vfp_enable(NULL); return NOTIFY_OK; } diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c index cbfacf7fb438..6a0a9b132d7a 100644 --- a/arch/arm64/kernel/debug-monitors.c +++ b/arch/arm64/kernel/debug-monitors.c @@ -27,7 +27,6 @@ #include <linux/uaccess.h> #include <asm/debug-monitors.h> -#include <asm/local.h> #include <asm/cputype.h> #include <asm/system_misc.h> @@ -89,8 +88,8 @@ early_param("nodebugmon", early_debug_disable); * Keep track of debug users on each core. * The ref counts are per-cpu so we use a local_t type. */ -static DEFINE_PER_CPU(local_t, mde_ref_count); -static DEFINE_PER_CPU(local_t, kde_ref_count); +static DEFINE_PER_CPU(int, mde_ref_count); +static DEFINE_PER_CPU(int, kde_ref_count); void enable_debug_monitors(enum debug_el el) { @@ -98,11 +97,11 @@ void enable_debug_monitors(enum debug_el el) WARN_ON(preemptible()); - if (local_inc_return(&__get_cpu_var(mde_ref_count)) == 1) + if (this_cpu_inc_return(mde_ref_count) == 1) enable = DBG_MDSCR_MDE; if (el == DBG_ACTIVE_EL1 && - local_inc_return(&__get_cpu_var(kde_ref_count)) == 1) + this_cpu_inc_return(kde_ref_count) == 1) enable |= DBG_MDSCR_KDE; if (enable && debug_enabled) { @@ -118,11 +117,11 @@ void disable_debug_monitors(enum debug_el el) WARN_ON(preemptible()); - if (local_dec_and_test(&__get_cpu_var(mde_ref_count))) + if (this_cpu_dec_return(mde_ref_count) == 0) disable = ~DBG_MDSCR_MDE; if (el == DBG_ACTIVE_EL1 && - local_dec_and_test(&__get_cpu_var(kde_ref_count))) + this_cpu_dec_return(kde_ref_count) == 0) disable &= ~DBG_MDSCR_KDE; if (disable) { diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index 329218ca9ffb..ff516f6691e4 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -184,14 +184,14 @@ int arch_install_hw_breakpoint(struct perf_event *bp) /* Breakpoint */ ctrl_reg = AARCH64_DBG_REG_BCR; val_reg = AARCH64_DBG_REG_BVR; - slots = __get_cpu_var(bp_on_reg); + slots = this_cpu_ptr(bp_on_reg); max_slots = core_num_brps; reg_enable = !debug_info->bps_disabled; } else { /* Watchpoint */ ctrl_reg = AARCH64_DBG_REG_WCR; val_reg = AARCH64_DBG_REG_WVR; - slots = __get_cpu_var(wp_on_reg); + slots = this_cpu_ptr(wp_on_reg); max_slots = core_num_wrps; reg_enable = !debug_info->wps_disabled; } @@ -230,12 +230,12 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp) if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) { /* Breakpoint */ base = AARCH64_DBG_REG_BCR; - slots = __get_cpu_var(bp_on_reg); + slots = this_cpu_ptr(bp_on_reg); max_slots = core_num_brps; } else { /* Watchpoint */ base = AARCH64_DBG_REG_WCR; - slots = __get_cpu_var(wp_on_reg); + slots = this_cpu_ptr(wp_on_reg); max_slots = core_num_wrps; } @@ -505,11 +505,11 @@ static void toggle_bp_registers(int reg, enum debug_el el, int enable) switch (reg) { case AARCH64_DBG_REG_BCR: - slots = __get_cpu_var(bp_on_reg); + slots = this_cpu_ptr(bp_on_reg); max_slots = core_num_brps; break; case AARCH64_DBG_REG_WCR: - slots = __get_cpu_var(wp_on_reg); + slots = this_cpu_ptr(wp_on_reg); max_slots = core_num_wrps; break; default: @@ -546,7 +546,7 @@ static int breakpoint_handler(unsigned long unused, unsigned int esr, struct debug_info *debug_info; struct arch_hw_breakpoint_ctrl ctrl; - slots = (struct perf_event **)__get_cpu_var(bp_on_reg); + slots = this_cpu_ptr(bp_on_reg); addr = instruction_pointer(regs); debug_info = ¤t->thread.debug; @@ -596,7 +596,7 @@ unlock: user_enable_single_step(current); } else { toggle_bp_registers(AARCH64_DBG_REG_BCR, DBG_ACTIVE_EL1, 0); - kernel_step = &__get_cpu_var(stepping_kernel_bp); + kernel_step = this_cpu_ptr(&stepping_kernel_bp); if (*kernel_step != ARM_KERNEL_STEP_NONE) return 0; @@ -623,7 +623,7 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr, struct arch_hw_breakpoint *info; struct arch_hw_breakpoint_ctrl ctrl; - slots = (struct perf_event **)__get_cpu_var(wp_on_reg); + slots = this_cpu_ptr(wp_on_reg); debug_info = ¤t->thread.debug; for (i = 0; i < core_num_wrps; ++i) { @@ -698,7 +698,7 @@ unlock: user_enable_single_step(current); } else { toggle_bp_registers(AARCH64_DBG_REG_WCR, DBG_ACTIVE_EL1, 0); - kernel_step = &__get_cpu_var(stepping_kernel_bp); + kernel_step = this_cpu_ptr(&stepping_kernel_bp); if (*kernel_step != ARM_KERNEL_STEP_NONE) return 0; @@ -722,7 +722,7 @@ int reinstall_suspended_bps(struct pt_regs *regs) struct debug_info *debug_info = ¤t->thread.debug; int handled_exception = 0, *kernel_step; - kernel_step = &__get_cpu_var(stepping_kernel_bp); + kernel_step = this_cpu_ptr(&stepping_kernel_bp); /* * Called from single-step exception handler. diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index cea1594ff933..6983ed5a351a 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -1044,7 +1044,7 @@ static irqreturn_t armv8pmu_handle_irq(int irq_num, void *dev) */ regs = get_irq_regs(); - cpuc = &__get_cpu_var(cpu_hw_events); + cpuc = this_cpu_ptr(&cpu_hw_events); for (idx = 0; idx < cpu_pmu->num_events; ++idx) { struct perf_event *event = cpuc->events[idx]; struct hw_perf_event *hwc; @@ -1257,7 +1257,7 @@ device_initcall(register_pmu_driver); static struct pmu_hw_events *armpmu_get_cpu_events(void) { - return &__get_cpu_var(cpu_hw_events); + return this_cpu_ptr(&cpu_hw_events); } static void __init cpu_pmu_init(struct arm_pmu *armpmu) diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c index 45f1ffcf1a4b..24cdf64789c3 100644 --- a/arch/mips/kernel/perf_event_mipsxx.c +++ b/arch/mips/kernel/perf_event_mipsxx.c @@ -971,11 +971,11 @@ static const struct mips_perf_event mipsxx74Kcore_cache_map [C(LL)] = { [C(OP_READ)] = { [C(RESULT_ACCESS)] = { 0x1c, CNTR_ODD, P }, - [C(RESULT_MISS)] = { 0x1d, CNTR_EVEN | CNTR_ODD, P }, + [C(RESULT_MISS)] = { 0x1d, CNTR_EVEN, P }, }, [C(OP_WRITE)] = { [C(RESULT_ACCESS)] = { 0x1c, CNTR_ODD, P }, - [C(RESULT_MISS)] = { 0x1d, CNTR_EVEN | CNTR_ODD, P }, + [C(RESULT_MISS)] = { 0x1d, CNTR_EVEN, P }, }, }, [C(ITLB)] = { diff --git a/arch/mips/mti-malta/malta-int.c b/arch/mips/mti-malta/malta-int.c index c69da3734699..5b28e81d94a0 100644 --- a/arch/mips/mti-malta/malta-int.c +++ b/arch/mips/mti-malta/malta-int.c @@ -473,7 +473,7 @@ static void __init fill_ipi_map(void) { int cpu; - for (cpu = 0; cpu < NR_CPUS; cpu++) { + for (cpu = 0; cpu < nr_cpu_ids; cpu++) { fill_ipi_map1(gic_resched_int_base, cpu, GIC_CPU_INT1); fill_ipi_map1(gic_call_int_base, cpu, GIC_CPU_INT2); } @@ -574,8 +574,9 @@ void __init arch_init_irq(void) /* FIXME */ int i; #if defined(CONFIG_MIPS_MT_SMP) - gic_call_int_base = GIC_NUM_INTRS - NR_CPUS; - gic_resched_int_base = gic_call_int_base - NR_CPUS; + gic_call_int_base = GIC_NUM_INTRS - + (NR_CPUS - nr_cpu_ids) * 2 - nr_cpu_ids; + gic_resched_int_base = gic_call_int_base - nr_cpu_ids; fill_ipi_map(); #endif gic_init(GIC_BASE_ADDR, GIC_ADDRSPACE_SZ, gic_intr_map, @@ -599,7 +600,7 @@ void __init arch_init_irq(void) printk("CPU%d: status register now %08x\n", smp_processor_id(), read_c0_status()); write_c0_status(0x1100dc00); printk("CPU%d: status register frc %08x\n", smp_processor_id(), read_c0_status()); - for (i = 0; i < NR_CPUS; i++) { + for (i = 0; i < nr_cpu_ids; i++) { arch_init_ipiirq(MIPS_GIC_IRQ_BASE + GIC_RESCHED_INT(i), &irq_resched); arch_init_ipiirq(MIPS_GIC_IRQ_BASE + diff --git a/arch/mips/ralink/timer.c b/arch/mips/ralink/timer.c index e49241a2c39a..202785709441 100644 --- a/arch/mips/ralink/timer.c +++ b/arch/mips/ralink/timer.c @@ -126,7 +126,7 @@ static int rt_timer_probe(struct platform_device *pdev) return -ENOENT; } - rt->membase = devm_request_and_ioremap(&pdev->dev, res); + rt->membase = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(rt->membase)) return PTR_ERR(rt->membase); diff --git a/arch/parisc/configs/712_defconfig b/arch/parisc/configs/712_defconfig index 0f90569b9d85..9387cc2693f6 100644 --- a/arch/parisc/configs/712_defconfig +++ b/arch/parisc/configs/712_defconfig @@ -40,6 +40,8 @@ CONFIG_IP_NF_QUEUE=m CONFIG_LLC2=m CONFIG_NET_PKTGEN=m CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set CONFIG_PARPORT=y diff --git a/arch/parisc/configs/a500_defconfig b/arch/parisc/configs/a500_defconfig index b647b182dacc..90025322b75e 100644 --- a/arch/parisc/configs/a500_defconfig +++ b/arch/parisc/configs/a500_defconfig @@ -79,6 +79,8 @@ CONFIG_IP_DCCP=m CONFIG_LLC2=m CONFIG_NET_PKTGEN=m CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set CONFIG_BLK_DEV_UMEM=m diff --git a/arch/parisc/configs/b180_defconfig b/arch/parisc/configs/b180_defconfig index e289f5bf3148..f1a0c25bef8d 100644 --- a/arch/parisc/configs/b180_defconfig +++ b/arch/parisc/configs/b180_defconfig @@ -4,6 +4,7 @@ CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=16 CONFIG_SYSFS_DEPRECATED_V2=y +CONFIG_BLK_DEV_INITRD=y CONFIG_SLAB=y CONFIG_MODULES=y CONFIG_MODVERSIONS=y @@ -27,6 +28,8 @@ CONFIG_IP_PNP_BOOTP=y # CONFIG_INET_LRO is not set CONFIG_IPV6=y CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y # CONFIG_PREVENT_FIRMWARE_BUILD is not set CONFIG_PARPORT=y CONFIG_PARPORT_PC=y diff --git a/arch/parisc/configs/c3000_defconfig b/arch/parisc/configs/c3000_defconfig index 311ca367b622..ec1b014952b6 100644 --- a/arch/parisc/configs/c3000_defconfig +++ b/arch/parisc/configs/c3000_defconfig @@ -5,6 +5,7 @@ CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=16 CONFIG_SYSFS_DEPRECATED_V2=y +CONFIG_BLK_DEV_INITRD=y # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set CONFIG_EXPERT=y CONFIG_KALLSYMS_ALL=y @@ -39,6 +40,8 @@ CONFIG_NETFILTER_DEBUG=y CONFIG_IP_NF_QUEUE=m CONFIG_NET_PKTGEN=m CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set CONFIG_BLK_DEV_UMEM=m diff --git a/arch/parisc/configs/c8000_defconfig b/arch/parisc/configs/c8000_defconfig index f11006361297..e1c8d2015c89 100644 --- a/arch/parisc/configs/c8000_defconfig +++ b/arch/parisc/configs/c8000_defconfig @@ -62,6 +62,8 @@ CONFIG_TIPC=m CONFIG_LLC2=m CONFIG_DNS_RESOLVER=y CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y # CONFIG_STANDALONE is not set CONFIG_PARPORT=y CONFIG_PARPORT_PC=y diff --git a/arch/parisc/configs/default_defconfig b/arch/parisc/configs/default_defconfig index dfe88f6c95c4..ba61495e1fa4 100644 --- a/arch/parisc/configs/default_defconfig +++ b/arch/parisc/configs/default_defconfig @@ -49,6 +49,8 @@ CONFIG_INET6_ESP=y CONFIG_INET6_IPCOMP=y CONFIG_LLC2=m CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set CONFIG_PARPORT=y diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index b521c0adf4ec..c035673209f7 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -602,7 +602,6 @@ flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long __flush_cache_page(vma, vmaddr, PFN_PHYS(pfn)); } } -EXPORT_SYMBOL_GPL(flush_cache_page); #ifdef CONFIG_PARISC_TMPALIAS diff --git a/arch/parisc/kernel/head.S b/arch/parisc/kernel/head.S index 37aabd772fbb..d2d58258aea6 100644 --- a/arch/parisc/kernel/head.S +++ b/arch/parisc/kernel/head.S @@ -195,6 +195,8 @@ common_stext: ldw MEM_PDC_HI(%r0),%r6 depd %r6, 31, 32, %r3 /* move to upper word */ + mfctl %cr30,%r6 /* PCX-W2 firmware bug */ + ldo PDC_PSW(%r0),%arg0 /* 21 */ ldo PDC_PSW_SET_DEFAULTS(%r0),%arg1 /* 2 */ ldo PDC_PSW_WIDE_BIT(%r0),%arg2 /* 2 */ @@ -203,6 +205,8 @@ common_stext: copy %r0,%arg3 stext_pdc_ret: + mtctl %r6,%cr30 /* restore task thread info */ + /* restore rfi target address*/ ldd TI_TASK-THREAD_SZ_ALGN(%sp), %r10 tophys_r1 %r10 diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index d38cc08b16c7..089de12b9ab0 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -1413,8 +1413,7 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node) /* needed to ensure proper operation of coherent allocations * later, in case driver doesn't set it explicitly */ - dma_set_mask(&viodev->dev, DMA_BIT_MASK(64)); - dma_set_coherent_mask(&viodev->dev, DMA_BIT_MASK(64)); + dma_set_mask_and_coherent(&viodev->dev, DMA_BIT_MASK(64)); } /* register with generic device framework */ diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index bf56e33f8257..2345bdb4d917 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -691,4 +691,5 @@ void bpf_jit_free(struct sk_filter *fp) { if (fp->bpf_func != sk_run_filter) module_free(NULL, fp->bpf_func); + kfree(fp); } diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 9b60a36c348d..2204400d0bd5 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -748,7 +748,9 @@ static inline void pgste_set_key(pte_t *ptep, pgste_t pgste, pte_t entry) static inline void pgste_set_pte(pte_t *ptep, pte_t entry) { - if (!MACHINE_HAS_ESOP && (pte_val(entry) & _PAGE_WRITE)) { + if (!MACHINE_HAS_ESOP && + (pte_val(entry) & _PAGE_PRESENT) && + (pte_val(entry) & _PAGE_WRITE)) { /* * Without enhanced suppression-on-protection force * the dirty bit on for all writable ptes. diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h index 8ad8af915032..819b94d22720 100644 --- a/arch/s390/include/asm/timex.h +++ b/arch/s390/include/asm/timex.h @@ -71,30 +71,30 @@ static inline void local_tick_enable(unsigned long long comp) typedef unsigned long long cycles_t; -static inline unsigned long long get_tod_clock(void) -{ - unsigned long long clk; - -#ifdef CONFIG_HAVE_MARCH_Z9_109_FEATURES - asm volatile(".insn s,0xb27c0000,%0" : "=Q" (clk) : : "cc"); -#else - asm volatile("stck %0" : "=Q" (clk) : : "cc"); -#endif - return clk; -} - static inline void get_tod_clock_ext(char *clk) { asm volatile("stcke %0" : "=Q" (*clk) : : "cc"); } -static inline unsigned long long get_tod_clock_xt(void) +static inline unsigned long long get_tod_clock(void) { unsigned char clk[16]; get_tod_clock_ext(clk); return *((unsigned long long *)&clk[1]); } +static inline unsigned long long get_tod_clock_fast(void) +{ +#ifdef CONFIG_HAVE_MARCH_Z9_109_FEATURES + unsigned long long clk; + + asm volatile("stckf %0" : "=Q" (clk) : : "cc"); + return clk; +#else + return get_tod_clock(); +#endif +} + static inline cycles_t get_cycles(void) { return (cycles_t) get_tod_clock() >> 2; @@ -125,7 +125,7 @@ extern u64 sched_clock_base_cc; */ static inline unsigned long long get_tod_clock_monotonic(void) { - return get_tod_clock_xt() - sched_clock_base_cc; + return get_tod_clock() - sched_clock_base_cc; } /** diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c index 1389b637dae5..adaa9e9478d8 100644 --- a/arch/s390/kernel/compat_signal.c +++ b/arch/s390/kernel/compat_signal.c @@ -99,7 +99,7 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from) break; } } - return err; + return err ? -EFAULT : 0; } int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) @@ -148,7 +148,7 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) break; } } - return err; + return err ? -EFAULT : 0; } static int save_sigregs32(struct pt_regs *regs, _sigregs32 __user *sregs) diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index f1279dc2e1bc..17d62fe5d7b7 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -867,7 +867,7 @@ static inline void debug_finish_entry(debug_info_t * id, debug_entry_t* active, int level, int exception) { - active->id.stck = get_tod_clock(); + active->id.stck = get_tod_clock_fast(); active->id.fields.cpuid = smp_processor_id(); active->caller = __builtin_return_address(0); active->id.fields.exception = exception; diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 7f35cb33e510..7f1f7ac5cf7f 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -385,7 +385,7 @@ static int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu) } if ((!rc) && (vcpu->arch.sie_block->ckc < - get_tod_clock() + vcpu->arch.sie_block->epoch)) { + get_tod_clock_fast() + vcpu->arch.sie_block->epoch)) { if ((!psw_extint_disabled(vcpu)) && (vcpu->arch.sie_block->gcr[0] & 0x800ul)) rc = 1; @@ -425,7 +425,7 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu) goto no_timer; } - now = get_tod_clock() + vcpu->arch.sie_block->epoch; + now = get_tod_clock_fast() + vcpu->arch.sie_block->epoch; if (vcpu->arch.sie_block->ckc < now) { __unset_cpu_idle(vcpu); return 0; @@ -515,7 +515,7 @@ void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu) } if ((vcpu->arch.sie_block->ckc < - get_tod_clock() + vcpu->arch.sie_block->epoch)) + get_tod_clock_fast() + vcpu->arch.sie_block->epoch)) __try_deliver_ckc_interrupt(vcpu); if (atomic_read(&fi->active)) { diff --git a/arch/s390/lib/delay.c b/arch/s390/lib/delay.c index 57c87d7d7ede..a9f3d0042d58 100644 --- a/arch/s390/lib/delay.c +++ b/arch/s390/lib/delay.c @@ -44,7 +44,7 @@ static void __udelay_disabled(unsigned long long usecs) do { set_clock_comparator(end); vtime_stop_cpu(); - } while (get_tod_clock() < end); + } while (get_tod_clock_fast() < end); lockdep_on(); __ctl_load(cr0, 0, 0); __ctl_load(cr6, 6, 6); @@ -55,7 +55,7 @@ static void __udelay_enabled(unsigned long long usecs) { u64 clock_saved, end; - end = get_tod_clock() + (usecs << 12); + end = get_tod_clock_fast() + (usecs << 12); do { clock_saved = 0; if (end < S390_lowcore.clock_comparator) { @@ -65,7 +65,7 @@ static void __udelay_enabled(unsigned long long usecs) vtime_stop_cpu(); if (clock_saved) local_tick_enable(clock_saved); - } while (get_tod_clock() < end); + } while (get_tod_clock_fast() < end); } /* @@ -109,8 +109,8 @@ void udelay_simple(unsigned long long usecs) { u64 end; - end = get_tod_clock() + (usecs << 12); - while (get_tod_clock() < end) + end = get_tod_clock_fast() + (usecs << 12); + while (get_tod_clock_fast() < end) cpu_relax(); } @@ -120,10 +120,10 @@ void __ndelay(unsigned long long nsecs) nsecs <<= 9; do_div(nsecs, 125); - end = get_tod_clock() + nsecs; + end = get_tod_clock_fast() + nsecs; if (nsecs & ~0xfffUL) __udelay(nsecs >> 12); - while (get_tod_clock() < end) + while (get_tod_clock_fast() < end) barrier(); } EXPORT_SYMBOL(__ndelay); diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 709239285869..a5df511e27a2 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -881,7 +881,9 @@ void bpf_jit_free(struct sk_filter *fp) struct bpf_binary_header *header = (void *)addr; if (fp->bpf_func == sk_run_filter) - return; + goto free_filter; set_memory_rw(addr, header->pages); module_free(NULL, header); +free_filter: + kfree(fp); } diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c index 9c7be59e6f5a..218b6b23c378 100644 --- a/arch/sparc/net/bpf_jit_comp.c +++ b/arch/sparc/net/bpf_jit_comp.c @@ -808,4 +808,5 @@ void bpf_jit_free(struct sk_filter *fp) { if (fp->bpf_func != sk_run_filter) module_free(NULL, fp->bpf_func); + kfree(fp); } diff --git a/arch/um/kernel/exitcode.c b/arch/um/kernel/exitcode.c index 829df49dee99..41ebbfebb333 100644 --- a/arch/um/kernel/exitcode.c +++ b/arch/um/kernel/exitcode.c @@ -40,9 +40,11 @@ static ssize_t exitcode_proc_write(struct file *file, const char __user *buffer, size_t count, loff_t *pos) { char *end, buf[sizeof("nnnnn\0")]; + size_t size; int tmp; - if (copy_from_user(buf, buffer, count)) + size = min(count, sizeof(buf)); + if (copy_from_user(buf, buffer, size)) return -EFAULT; tmp = simple_strtol(buf, &end, 0); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 145d703227bf..f67e839f06c8 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1033,6 +1033,7 @@ config X86_REBOOTFIXUPS config MICROCODE tristate "CPU microcode loading support" + depends on CPU_SUP_AMD || CPU_SUP_INTEL select FW_LOADER ---help--- diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index 0da5200ee79d..b3e18f800302 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -128,7 +128,8 @@ do { \ do { \ typedef typeof(var) pao_T__; \ const int pao_ID__ = (__builtin_constant_p(val) && \ - ((val) == 1 || (val) == -1)) ? (val) : 0; \ + ((val) == 1 || (val) == -1)) ? \ + (int)(val) : 0; \ if (0) { \ pao_T__ pao_tmp__; \ pao_tmp__ = (val); \ diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 1191ac1c9d25..a419814cea57 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -113,7 +113,7 @@ static int __init early_get_pnodeid(void) break; case UV3_HUB_PART_NUMBER: case UV3_HUB_PART_NUMBER_X: - uv_min_hub_revision_id += UV3_HUB_REVISION_BASE - 1; + uv_min_hub_revision_id += UV3_HUB_REVISION_BASE; break; } diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 9d8449158cf9..8a87a3224121 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1276,16 +1276,16 @@ void perf_events_lapic_init(void) static int __kprobes perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs) { - int ret; u64 start_clock; u64 finish_clock; + int ret; if (!atomic_read(&active_events)) return NMI_DONE; - start_clock = local_clock(); + start_clock = sched_clock(); ret = x86_pmu.handle_irq(regs); - finish_clock = local_clock(); + finish_clock = sched_clock(); perf_sample_event_took(finish_clock - start_clock); diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 697b93af02dd..b2046e4d0b59 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -609,7 +609,7 @@ static struct dentry *d_kvm_debug; struct dentry *kvm_init_debugfs(void) { - d_kvm_debug = debugfs_create_dir("kvm", NULL); + d_kvm_debug = debugfs_create_dir("kvm-guest", NULL); if (!d_kvm_debug) printk(KERN_WARNING "Could not create 'kvm' debugfs directory\n"); @@ -775,11 +775,22 @@ void __init kvm_spinlock_init(void) if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT)) return; - printk(KERN_INFO "KVM setup paravirtual spinlock\n"); + pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(kvm_lock_spinning); + pv_lock_ops.unlock_kick = kvm_unlock_kick; +} + +static __init int kvm_spinlock_init_jump(void) +{ + if (!kvm_para_available()) + return 0; + if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT)) + return 0; static_key_slow_inc(¶virt_ticketlocks_enabled); + printk(KERN_INFO "KVM setup paravirtual spinlock\n"); - pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(kvm_lock_spinning); - pv_lock_ops.unlock_kick = kvm_unlock_kick; + return 0; } +early_initcall(kvm_spinlock_init_jump); + #endif /* CONFIG_PARAVIRT_SPINLOCKS */ diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index ba77ebc2c353..6fcb49ce50a1 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -113,10 +113,10 @@ static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2 u64 before, delta, whole_msecs; int remainder_ns, decimal_msecs, thishandled; - before = local_clock(); + before = sched_clock(); thishandled = a->handler(type, regs); handled += thishandled; - delta = local_clock() - before; + delta = sched_clock() - before; trace_nmi_handler(a->handler, (int)delta, thishandled); if (delta < nmi_longest_ns) diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 79c216aa0e2b..516593e1ce33 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -772,13 +772,21 @@ out: return; } +static void bpf_jit_free_deferred(struct work_struct *work) +{ + struct sk_filter *fp = container_of(work, struct sk_filter, work); + unsigned long addr = (unsigned long)fp->bpf_func & PAGE_MASK; + struct bpf_binary_header *header = (void *)addr; + + set_memory_rw(addr, header->pages); + module_free(NULL, header); + kfree(fp); +} + void bpf_jit_free(struct sk_filter *fp) { if (fp->bpf_func != sk_run_filter) { - unsigned long addr = (unsigned long)fp->bpf_func & PAGE_MASK; - struct bpf_binary_header *header = (void *)addr; - - set_memory_rw(addr, header->pages); - module_free(NULL, header); + INIT_WORK(&fp->work, bpf_jit_free_deferred); + schedule_work(&fp->work); } } diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index d1e4777b4e75..31d04758b76f 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -278,6 +278,15 @@ static void __init xen_smp_prepare_boot_cpu(void) old memory can be recycled */ make_lowmem_page_readwrite(xen_initial_gdt); +#ifdef CONFIG_X86_32 + /* + * Xen starts us with XEN_FLAT_RING1_DS, but linux code + * expects __USER_DS + */ + loadsegment(ds, __USER_DS); + loadsegment(es, __USER_DS); +#endif + xen_filter_cpu_maps(); xen_setup_vcpu_info_placement(); } diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S index de1dfa18d0a1..21dbe6bdb8ed 100644 --- a/arch/xtensa/kernel/entry.S +++ b/arch/xtensa/kernel/entry.S @@ -1122,7 +1122,7 @@ ENDPROC(fast_syscall_spill_registers) * a3: exctable, original value in excsave1 */ -fast_syscall_spill_registers_fixup: +ENTRY(fast_syscall_spill_registers_fixup) rsr a2, windowbase # get current windowbase (a2 is saved) xsr a0, depc # restore depc and a0 @@ -1134,22 +1134,26 @@ fast_syscall_spill_registers_fixup: */ xsr a3, excsave1 # get spill-mask - slli a2, a3, 1 # shift left by one + slli a3, a3, 1 # shift left by one - slli a3, a2, 32-WSBITS - src a2, a2, a3 # a1 = xxwww1yyxxxwww1yy...... + slli a2, a3, 32-WSBITS + src a2, a3, a2 # a2 = xxwww1yyxxxwww1yy...... wsr a2, windowstart # set corrected windowstart - rsr a3, excsave1 - l32i a2, a3, EXC_TABLE_DOUBLE_SAVE # restore a2 - l32i a3, a3, EXC_TABLE_PARAM # original WB (in user task) + srli a3, a3, 1 + rsr a2, excsave1 + l32i a2, a2, EXC_TABLE_DOUBLE_SAVE # restore a2 + xsr a2, excsave1 + s32i a3, a2, EXC_TABLE_DOUBLE_SAVE # save a3 + l32i a3, a2, EXC_TABLE_PARAM # original WB (in user task) + xsr a2, excsave1 /* Return to the original (user task) WINDOWBASE. * We leave the following frame behind: * a0, a1, a2 same - * a3: trashed (saved in excsave_1) + * a3: trashed (saved in EXC_TABLE_DOUBLE_SAVE) * depc: depc (we have to return to that address) - * excsave_1: a3 + * excsave_1: exctable */ wsr a3, windowbase @@ -1159,9 +1163,9 @@ fast_syscall_spill_registers_fixup: * a0: return address * a1: used, stack pointer * a2: kernel stack pointer - * a3: available, saved in EXCSAVE_1 + * a3: available * depc: exception address - * excsave: a3 + * excsave: exctable * Note: This frame might be the same as above. */ @@ -1181,9 +1185,12 @@ fast_syscall_spill_registers_fixup: rsr a0, exccause addx4 a0, a0, a3 # find entry in table l32i a0, a0, EXC_TABLE_FAST_USER # load handler + l32i a3, a3, EXC_TABLE_DOUBLE_SAVE jx a0 -fast_syscall_spill_registers_fixup_return: +ENDPROC(fast_syscall_spill_registers_fixup) + +ENTRY(fast_syscall_spill_registers_fixup_return) /* When we return here, all registers have been restored (a2: DEPC) */ @@ -1191,13 +1198,13 @@ fast_syscall_spill_registers_fixup_return: /* Restore fixup handler. */ - xsr a3, excsave1 - movi a2, fast_syscall_spill_registers_fixup - s32i a2, a3, EXC_TABLE_FIXUP - s32i a0, a3, EXC_TABLE_DOUBLE_SAVE - rsr a2, windowbase - s32i a2, a3, EXC_TABLE_PARAM - l32i a2, a3, EXC_TABLE_KSTK + rsr a2, excsave1 + s32i a3, a2, EXC_TABLE_DOUBLE_SAVE + movi a3, fast_syscall_spill_registers_fixup + s32i a3, a2, EXC_TABLE_FIXUP + rsr a3, windowbase + s32i a3, a2, EXC_TABLE_PARAM + l32i a2, a2, EXC_TABLE_KSTK /* Load WB at the time the exception occurred. */ @@ -1206,8 +1213,12 @@ fast_syscall_spill_registers_fixup_return: wsr a3, windowbase rsync + rsr a3, excsave1 + l32i a3, a3, EXC_TABLE_DOUBLE_SAVE + rfde +ENDPROC(fast_syscall_spill_registers_fixup_return) /* * spill all registers. diff --git a/arch/xtensa/kernel/signal.c b/arch/xtensa/kernel/signal.c index 718eca1850bd..98b67d5f1514 100644 --- a/arch/xtensa/kernel/signal.c +++ b/arch/xtensa/kernel/signal.c @@ -341,7 +341,7 @@ static int setup_frame(int sig, struct k_sigaction *ka, siginfo_t *info, sp = regs->areg[1]; - if ((ka->sa.sa_flags & SA_ONSTACK) != 0 && ! on_sig_stack(sp)) { + if ((ka->sa.sa_flags & SA_ONSTACK) != 0 && sas_ss_flags(sp) == 0) { sp = current->sas_ss_sp + current->sas_ss_size; } diff --git a/arch/xtensa/platforms/iss/network.c b/arch/xtensa/platforms/iss/network.c index 56f88b7afe2f..e9e1aad8c271 100644 --- a/arch/xtensa/platforms/iss/network.c +++ b/arch/xtensa/platforms/iss/network.c @@ -737,7 +737,8 @@ static int __init iss_net_setup(char *str) return 1; } - if ((new = alloc_bootmem(sizeof new)) == NULL) { + new = alloc_bootmem(sizeof(*new)); + if (new == NULL) { printk("Alloc_bootmem failed\n"); return 1; } diff --git a/block/blk-settings.c b/block/blk-settings.c index c50ecf0ea3b1..026c1517505f 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -195,17 +195,17 @@ EXPORT_SYMBOL(blk_queue_make_request); /** * blk_queue_bounce_limit - set bounce buffer limit for queue * @q: the request queue for the device - * @dma_mask: the maximum address the device can handle + * @max_addr: the maximum address the device can handle * * Description: * Different hardware can have different requirements as to what pages * it can do I/O directly to. A low level driver can call * blk_queue_bounce_limit to have lower memory pages allocated as bounce - * buffers for doing I/O to pages residing above @dma_mask. + * buffers for doing I/O to pages residing above @max_addr. **/ -void blk_queue_bounce_limit(struct request_queue *q, u64 dma_mask) +void blk_queue_bounce_limit(struct request_queue *q, u64 max_addr) { - unsigned long b_pfn = dma_mask >> PAGE_SHIFT; + unsigned long b_pfn = max_addr >> PAGE_SHIFT; int dma = 0; q->bounce_gfp = GFP_NOIO; diff --git a/block/partitions/efi.c b/block/partitions/efi.c index 1eb09ee5311b..a8287b49d062 100644 --- a/block/partitions/efi.c +++ b/block/partitions/efi.c @@ -222,11 +222,16 @@ check_hybrid: * the disk size. * * Hybrid MBRs do not necessarily comply with this. + * + * Consider a bad value here to be a warning to support dd'ing + * an image from a smaller disk to a larger disk. */ if (ret == GPT_MBR_PROTECTIVE) { sz = le32_to_cpu(mbr->partition_record[part].size_in_lba); if (sz != (uint32_t) total_sectors - 1 && sz != 0xFFFFFFFF) - ret = 0; + pr_debug("GPT: mbr size in lba (%u) different than whole disk (%u).\n", + sz, min_t(uint32_t, + total_sectors - 1, 0xFFFFFFFF)); } done: return ret; diff --git a/crypto/Kconfig b/crypto/Kconfig index 69ce573f1224..71f337aefa39 100644 --- a/crypto/Kconfig +++ b/crypto/Kconfig @@ -776,6 +776,22 @@ config CRYPTO_AES_ARM See <http://csrc.nist.gov/encryption/aes/> for more information. +config CRYPTO_AES_ARM_BS + tristate "Bit sliced AES using NEON instructions" + depends on ARM && KERNEL_MODE_NEON + select CRYPTO_ALGAPI + select CRYPTO_AES_ARM + select CRYPTO_ABLK_HELPER + help + Use a faster and more secure NEON based implementation of AES in CBC, + CTR and XTS modes + + Bit sliced AES gives around 45% speedup on Cortex-A15 for CTR mode + and for XTS mode encryption, CBC and XTS mode decryption speedup is + around 25%. (CBC encryption speed is not affected by this driver.) + This implementation does not rely on any lookup tables so it is + believed to be invulnerable to cache timing attacks. + config CRYPTO_ANUBIS tristate "Anubis cipher algorithm" select CRYPTO_ALGAPI diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index 22327e6a7236..6efe2ac6902f 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -24,7 +24,7 @@ menuconfig ACPI are configured, ACPI is used. The project home page for the Linux ACPI subsystem is here: - <http://www.lesswatts.org/projects/acpi/> + <https://01.org/linux-acpi> Linux support for ACPI is based on Intel Corporation's ACPI Component Architecture (ACPI CA). For more information on the @@ -123,9 +123,9 @@ config ACPI_BUTTON default y help This driver handles events on the power, sleep, and lid buttons. - A daemon reads /proc/acpi/event and perform user-defined actions - such as shutting down the system. This is necessary for - software-controlled poweroff. + A daemon reads events from input devices or via netlink and + performs user-defined actions such as shutting down the system. + This is necessary for software-controlled poweroff. To compile this driver as a module, choose M here: the module will be called button. diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c index 59d3202f6b36..a94383d1f350 100644 --- a/drivers/acpi/device_pm.c +++ b/drivers/acpi/device_pm.c @@ -1025,60 +1025,4 @@ void acpi_dev_pm_detach(struct device *dev, bool power_off) } } EXPORT_SYMBOL_GPL(acpi_dev_pm_detach); - -/** - * acpi_dev_pm_add_dependent - Add physical device depending for PM. - * @handle: Handle of ACPI device node. - * @depdev: Device depending on that node for PM. - */ -void acpi_dev_pm_add_dependent(acpi_handle handle, struct device *depdev) -{ - struct acpi_device_physical_node *dep; - struct acpi_device *adev; - - if (!depdev || acpi_bus_get_device(handle, &adev)) - return; - - mutex_lock(&adev->physical_node_lock); - - list_for_each_entry(dep, &adev->power_dependent, node) - if (dep->dev == depdev) - goto out; - - dep = kzalloc(sizeof(*dep), GFP_KERNEL); - if (dep) { - dep->dev = depdev; - list_add_tail(&dep->node, &adev->power_dependent); - } - - out: - mutex_unlock(&adev->physical_node_lock); -} -EXPORT_SYMBOL_GPL(acpi_dev_pm_add_dependent); - -/** - * acpi_dev_pm_remove_dependent - Remove physical device depending for PM. - * @handle: Handle of ACPI device node. - * @depdev: Device depending on that node for PM. - */ -void acpi_dev_pm_remove_dependent(acpi_handle handle, struct device *depdev) -{ - struct acpi_device_physical_node *dep; - struct acpi_device *adev; - - if (!depdev || acpi_bus_get_device(handle, &adev)) - return; - - mutex_lock(&adev->physical_node_lock); - - list_for_each_entry(dep, &adev->power_dependent, node) - if (dep->dev == depdev) { - list_del(&dep->node); - kfree(dep); - break; - } - - mutex_unlock(&adev->physical_node_lock); -} -EXPORT_SYMBOL_GPL(acpi_dev_pm_remove_dependent); #endif /* CONFIG_PM */ diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c index 0dbe5cdf3396..c2ad391d8041 100644 --- a/drivers/acpi/power.c +++ b/drivers/acpi/power.c @@ -59,16 +59,9 @@ ACPI_MODULE_NAME("power"); #define ACPI_POWER_RESOURCE_STATE_ON 0x01 #define ACPI_POWER_RESOURCE_STATE_UNKNOWN 0xFF -struct acpi_power_dependent_device { - struct list_head node; - struct acpi_device *adev; - struct work_struct work; -}; - struct acpi_power_resource { struct acpi_device device; struct list_head list_node; - struct list_head dependent; char *name; u32 system_level; u32 order; @@ -233,32 +226,6 @@ static int acpi_power_get_list_state(struct list_head *list, int *state) return 0; } -static void acpi_power_resume_dependent(struct work_struct *work) -{ - struct acpi_power_dependent_device *dep; - struct acpi_device_physical_node *pn; - struct acpi_device *adev; - int state; - - dep = container_of(work, struct acpi_power_dependent_device, work); - adev = dep->adev; - if (acpi_power_get_inferred_state(adev, &state)) - return; - - if (state > ACPI_STATE_D0) - return; - - mutex_lock(&adev->physical_node_lock); - - list_for_each_entry(pn, &adev->physical_node_list, node) - pm_request_resume(pn->dev); - - list_for_each_entry(pn, &adev->power_dependent, node) - pm_request_resume(pn->dev); - - mutex_unlock(&adev->physical_node_lock); -} - static int __acpi_power_on(struct acpi_power_resource *resource) { acpi_status status = AE_OK; @@ -283,14 +250,8 @@ static int acpi_power_on_unlocked(struct acpi_power_resource *resource) resource->name)); } else { result = __acpi_power_on(resource); - if (result) { + if (result) resource->ref_count--; - } else { - struct acpi_power_dependent_device *dep; - - list_for_each_entry(dep, &resource->dependent, node) - schedule_work(&dep->work); - } } return result; } @@ -390,52 +351,6 @@ static int acpi_power_on_list(struct list_head *list) return result; } -static void acpi_power_add_dependent(struct acpi_power_resource *resource, - struct acpi_device *adev) -{ - struct acpi_power_dependent_device *dep; - - mutex_lock(&resource->resource_lock); - - list_for_each_entry(dep, &resource->dependent, node) - if (dep->adev == adev) - goto out; - - dep = kzalloc(sizeof(*dep), GFP_KERNEL); - if (!dep) - goto out; - - dep->adev = adev; - INIT_WORK(&dep->work, acpi_power_resume_dependent); - list_add_tail(&dep->node, &resource->dependent); - - out: - mutex_unlock(&resource->resource_lock); -} - -static void acpi_power_remove_dependent(struct acpi_power_resource *resource, - struct acpi_device *adev) -{ - struct acpi_power_dependent_device *dep; - struct work_struct *work = NULL; - - mutex_lock(&resource->resource_lock); - - list_for_each_entry(dep, &resource->dependent, node) - if (dep->adev == adev) { - list_del(&dep->node); - work = &dep->work; - break; - } - - mutex_unlock(&resource->resource_lock); - - if (work) { - cancel_work_sync(work); - kfree(dep); - } -} - static struct attribute *attrs[] = { NULL, }; @@ -524,8 +439,6 @@ static void acpi_power_expose_hide(struct acpi_device *adev, void acpi_power_add_remove_device(struct acpi_device *adev, bool add) { - struct acpi_device_power_state *ps; - struct acpi_power_resource_entry *entry; int state; if (adev->wakeup.flags.valid) @@ -535,16 +448,6 @@ void acpi_power_add_remove_device(struct acpi_device *adev, bool add) if (!adev->power.flags.power_resources) return; - ps = &adev->power.states[ACPI_STATE_D0]; - list_for_each_entry(entry, &ps->resources, node) { - struct acpi_power_resource *resource = entry->resource; - - if (add) - acpi_power_add_dependent(resource, adev); - else - acpi_power_remove_dependent(resource, adev); - } - for (state = ACPI_STATE_D0; state <= ACPI_STATE_D3_HOT; state++) acpi_power_expose_hide(adev, &adev->power.states[state].resources, @@ -882,7 +785,6 @@ int acpi_add_power_resource(acpi_handle handle) acpi_init_device_object(device, handle, ACPI_BUS_TYPE_POWER, ACPI_STA_DEFAULT); mutex_init(&resource->resource_lock); - INIT_LIST_HEAD(&resource->dependent); INIT_LIST_HEAD(&resource->list_node); resource->name = device->pnp.bus_id; strcpy(acpi_device_name(device), ACPI_POWER_DEVICE_NAME); @@ -936,8 +838,10 @@ void acpi_resume_power_resources(void) mutex_lock(&resource->resource_lock); result = acpi_power_get_state(resource->device.handle, &state); - if (result) + if (result) { + mutex_unlock(&resource->resource_lock); continue; + } if (state == ACPI_POWER_RESOURCE_STATE_OFF && resource->ref_count) { diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 407ad13cac2f..fee8a297c7d9 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -999,7 +999,6 @@ int acpi_device_add(struct acpi_device *device, INIT_LIST_HEAD(&device->wakeup_list); INIT_LIST_HEAD(&device->physical_node_list); mutex_init(&device->physical_node_lock); - INIT_LIST_HEAD(&device->power_dependent); new_bus_id = kzalloc(sizeof(struct acpi_device_bus_id), GFP_KERNEL); if (!new_bus_id) { diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c index c6707278a6bb..c4876ac9151a 100644 --- a/drivers/amba/bus.c +++ b/drivers/amba/bus.c @@ -552,7 +552,6 @@ amba_aphb_device_add(struct device *parent, const char *name, if (!dev) return ERR_PTR(-ENOMEM); - dev->dma_mask = dma_mask; dev->dev.coherent_dma_mask = dma_mask; dev->irq[0] = irq1; dev->irq[1] = irq2; @@ -619,7 +618,7 @@ static void amba_device_initialize(struct amba_device *dev, const char *name) dev_set_name(&dev->dev, "%s", name); dev->dev.release = amba_device_release; dev->dev.bus = &amba_bustype; - dev->dev.dma_mask = &dev->dma_mask; + dev->dev.dma_mask = &dev->dev.coherent_dma_mask; dev->res.name = dev_name(&dev->dev); } @@ -663,9 +662,6 @@ int amba_device_register(struct amba_device *dev, struct resource *parent) amba_device_initialize(dev, dev->dev.init_name); dev->dev.init_name = NULL; - if (!dev->dev.coherent_dma_mask && dev->dma_mask) - dev_warn(&dev->dev, "coherent dma mask is unset\n"); - return amba_device_add(dev, parent); } diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 9d715ae5ff6b..8e28f923cf7f 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -1343,7 +1343,7 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (!(hpriv->cap & HOST_CAP_SSS) || ahci_ignore_sss) host->flags |= ATA_HOST_PARALLEL_SCAN; else - printk(KERN_INFO "ahci: SSS flag set, parallel bus scan disabled\n"); + dev_info(&pdev->dev, "SSS flag set, parallel bus scan disabled\n"); if (pi.flags & ATA_FLAG_EM) ahci_reset_em(host); diff --git a/drivers/ata/ahci_platform.c b/drivers/ata/ahci_platform.c index 2daaee05cab1..7d3b85385bfc 100644 --- a/drivers/ata/ahci_platform.c +++ b/drivers/ata/ahci_platform.c @@ -184,7 +184,7 @@ static int ahci_probe(struct platform_device *pdev) if (!(hpriv->cap & HOST_CAP_SSS) || ahci_ignore_sss) host->flags |= ATA_HOST_PARALLEL_SCAN; else - printk(KERN_INFO "ahci: SSS flag set, parallel bus scan disabled\n"); + dev_info(dev, "SSS flag set, parallel bus scan disabled\n"); if (pi.flags & ATA_FLAG_EM) ahci_reset_em(host); diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index acfd0f711069..aaac4fb0d564 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -778,8 +778,16 @@ static void ahci_start_port(struct ata_port *ap) rc = ap->ops->transmit_led_message(ap, emp->led_state, 4); + /* + * If busy, give a breather but do not + * release EH ownership by using msleep() + * instead of ata_msleep(). EM Transmit + * bit is busy for the whole host and + * releasing ownership will cause other + * ports to fail the same way. + */ if (rc == -EBUSY) - ata_msleep(ap, 1); + msleep(1); else break; } diff --git a/drivers/ata/libata-acpi.c b/drivers/ata/libata-acpi.c index 4ba8b0405572..ab714d2ad978 100644 --- a/drivers/ata/libata-acpi.c +++ b/drivers/ata/libata-acpi.c @@ -1035,17 +1035,3 @@ void ata_acpi_on_disable(struct ata_device *dev) { ata_acpi_clear_gtf(dev); } - -void ata_scsi_acpi_bind(struct ata_device *dev) -{ - acpi_handle handle = ata_dev_acpi_handle(dev); - if (handle) - acpi_dev_pm_add_dependent(handle, &dev->sdev->sdev_gendev); -} - -void ata_scsi_acpi_unbind(struct ata_device *dev) -{ - acpi_handle handle = ata_dev_acpi_handle(dev); - if (handle) - acpi_dev_pm_remove_dependent(handle, &dev->sdev->sdev_gendev); -} diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index c69fcce505c0..370462fa8e01 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -1322,14 +1322,14 @@ void ata_eh_qc_complete(struct ata_queued_cmd *qc) * should be retried. To be used from EH. * * SCSI midlayer limits the number of retries to scmd->allowed. - * scmd->retries is decremented for commands which get retried + * scmd->allowed is incremented for commands which get retried * due to unrelated failures (qc->err_mask is zero). */ void ata_eh_qc_retry(struct ata_queued_cmd *qc) { struct scsi_cmnd *scmd = qc->scsicmd; - if (!qc->err_mask && scmd->retries) - scmd->retries--; + if (!qc->err_mask) + scmd->allowed++; __ata_eh_qc_complete(qc); } diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 97a0cef12959..db6dfcfa3e2e 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -3679,7 +3679,6 @@ void ata_scsi_scan_host(struct ata_port *ap, int sync) if (!IS_ERR(sdev)) { dev->sdev = sdev; scsi_device_put(sdev); - ata_scsi_acpi_bind(dev); } else { dev->sdev = NULL; } @@ -3767,8 +3766,6 @@ static void ata_scsi_remove_dev(struct ata_device *dev) struct scsi_device *sdev; unsigned long flags; - ata_scsi_acpi_unbind(dev); - /* Alas, we need to grab scan_mutex to ensure SCSI device * state doesn't change underneath us and thus * scsi_device_get() always succeeds. The mutex locking can diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h index eeeb77845d48..45b5ab3a95d5 100644 --- a/drivers/ata/libata.h +++ b/drivers/ata/libata.h @@ -121,8 +121,6 @@ extern void ata_acpi_set_state(struct ata_port *ap, pm_message_t state); extern void ata_acpi_bind_port(struct ata_port *ap); extern void ata_acpi_bind_dev(struct ata_device *dev); extern acpi_handle ata_dev_acpi_handle(struct ata_device *dev); -extern void ata_scsi_acpi_bind(struct ata_device *dev); -extern void ata_scsi_acpi_unbind(struct ata_device *dev); #else static inline void ata_acpi_dissociate(struct ata_host *host) { } static inline int ata_acpi_on_suspend(struct ata_port *ap) { return 0; } @@ -133,8 +131,6 @@ static inline void ata_acpi_set_state(struct ata_port *ap, pm_message_t state) { } static inline void ata_acpi_bind_port(struct ata_port *ap) {} static inline void ata_acpi_bind_dev(struct ata_device *dev) {} -static inline void ata_scsi_acpi_bind(struct ata_device *dev) {} -static inline void ata_scsi_acpi_unbind(struct ata_device *dev) {} #endif /* libata-scsi.c */ diff --git a/drivers/ata/pata_isapnp.c b/drivers/ata/pata_isapnp.c index 4bceb8803a10..b33d1f99b3a4 100644 --- a/drivers/ata/pata_isapnp.c +++ b/drivers/ata/pata_isapnp.c @@ -78,7 +78,7 @@ static int isapnp_init_one(struct pnp_dev *idev, const struct pnp_device_id *dev ap->ioaddr.cmd_addr = cmd_addr; - if (pnp_port_valid(idev, 1) == 0) { + if (pnp_port_valid(idev, 1)) { ctl_addr = devm_ioport_map(&idev->dev, pnp_port_start(idev, 1), 1); ap->ioaddr.altstatus_addr = ctl_addr; diff --git a/drivers/ata/pata_ixp4xx_cf.c b/drivers/ata/pata_ixp4xx_cf.c index 1ec53f8ca96f..ddf470c2341d 100644 --- a/drivers/ata/pata_ixp4xx_cf.c +++ b/drivers/ata/pata_ixp4xx_cf.c @@ -144,6 +144,7 @@ static int ixp4xx_pata_probe(struct platform_device *pdev) struct ata_host *host; struct ata_port *ap; struct ixp4xx_pata_data *data = dev_get_platdata(&pdev->dev); + int ret; cs0 = platform_get_resource(pdev, IORESOURCE_MEM, 0); cs1 = platform_get_resource(pdev, IORESOURCE_MEM, 1); @@ -157,7 +158,9 @@ static int ixp4xx_pata_probe(struct platform_device *pdev) return -ENOMEM; /* acquire resources and fill host */ - pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32); + ret = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)); + if (ret) + return ret; data->cs0 = devm_ioremap(&pdev->dev, cs0->start, 0x1000); data->cs1 = devm_ioremap(&pdev->dev, cs1->start, 0x1000); diff --git a/drivers/ata/pata_octeon_cf.c b/drivers/ata/pata_octeon_cf.c index c51bbb9ea8e8..83c4ddb1bc7f 100644 --- a/drivers/ata/pata_octeon_cf.c +++ b/drivers/ata/pata_octeon_cf.c @@ -1014,8 +1014,9 @@ static int octeon_cf_probe(struct platform_device *pdev) } cf_port->c0 = ap->ioaddr.ctl_addr; - pdev->dev.coherent_dma_mask = DMA_BIT_MASK(64); - pdev->dev.dma_mask = &pdev->dev.coherent_dma_mask; + rv = dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + if (rv) + return rv; ata_port_desc(ap, "cmd %p ctl %p", base, ap->ioaddr.ctl_addr); diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 9e59f6535c44..bece691cb5d9 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -333,8 +333,10 @@ store_mem_state(struct device *dev, online_type = ONLINE_KEEP; else if (!strncmp(buf, "offline", min_t(int, count, 7))) online_type = -1; - else - return -EINVAL; + else { + ret = -EINVAL; + goto err; + } switch (online_type) { case ONLINE_KERNEL: @@ -357,6 +359,7 @@ store_mem_state(struct device *dev, ret = -EINVAL; /* should never happen */ } +err: unlock_device_hotplug(); if (ret) diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c index da52092980e2..26d03fa0bf26 100644 --- a/drivers/block/nvme-core.c +++ b/drivers/block/nvme-core.c @@ -1949,12 +1949,9 @@ static int nvme_dev_map(struct nvme_dev *dev) if (pci_request_selected_regions(pdev, bars, "nvme")) goto disable_pci; - if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(64))) - dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64)); - else if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(32))) - dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)); - else - goto disable_pci; + if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)) && + dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32))) + goto disable; pci_set_drvdata(pdev, dev); dev->bar = ioremap(pci_resource_start(pdev, 0), 8192); @@ -2168,6 +2165,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) INIT_LIST_HEAD(&dev->namespaces); dev->pci_dev = pdev; + result = nvme_set_instance(dev); if (result) goto free; diff --git a/drivers/bus/arm-cci.c b/drivers/bus/arm-cci.c index bb5b90e8e768..b6739cb78e32 100644 --- a/drivers/bus/arm-cci.c +++ b/drivers/bus/arm-cci.c @@ -852,7 +852,7 @@ asmlinkage void __naked cci_enable_port_for_self(void) /* Enable the CCI port */ " ldr r0, [r0, %[offsetof_port_phys]] \n" -" mov r3, #"__stringify(CCI_ENABLE_REQ)" \n" +" mov r3, %[cci_enable_req]\n" " str r3, [r0, #"__stringify(CCI_PORT_CTRL)"] \n" /* poll the status reg for completion */ @@ -860,7 +860,7 @@ asmlinkage void __naked cci_enable_port_for_self(void) " ldr r0, [r1] \n" " ldr r0, [r0, r1] @ cci_ctrl_base \n" "4: ldr r1, [r0, #"__stringify(CCI_CTRL_STATUS)"] \n" -" tst r1, #1 \n" +" tst r1, %[cci_control_status_bits] \n" " bne 4b \n" " mov r0, #0 \n" @@ -873,6 +873,8 @@ asmlinkage void __naked cci_enable_port_for_self(void) "7: .word cci_ctrl_phys - . \n" : : [sizeof_cpu_port] "i" (sizeof(cpu_port)), + [cci_enable_req] "i" cpu_to_le32(CCI_ENABLE_REQ), + [cci_control_status_bits] "i" cpu_to_le32(1), #ifndef __ARMEB__ [offsetof_cpu_port_mpidr_lsb] "i" (offsetof(struct cpu_port, mpidr)), #else diff --git a/drivers/char/tpm/xen-tpmfront.c b/drivers/char/tpm/xen-tpmfront.c index 06189e55b4e5..94c280d36e8b 100644 --- a/drivers/char/tpm/xen-tpmfront.c +++ b/drivers/char/tpm/xen-tpmfront.c @@ -10,6 +10,7 @@ #include <linux/errno.h> #include <linux/err.h> #include <linux/interrupt.h> +#include <xen/xen.h> #include <xen/events.h> #include <xen/interface/io/tpmif.h> #include <xen/grant_table.h> diff --git a/drivers/clk/mvebu/armada-370.c b/drivers/clk/mvebu/armada-370.c index fc777bdc1886..81a202d12a7a 100644 --- a/drivers/clk/mvebu/armada-370.c +++ b/drivers/clk/mvebu/armada-370.c @@ -39,8 +39,8 @@ static const struct coreclk_ratio a370_coreclk_ratios[] __initconst = { }; static const u32 a370_tclk_freqs[] __initconst = { - 16600000, - 20000000, + 166000000, + 200000000, }; static u32 __init a370_get_tclk_freq(void __iomem *sar) diff --git a/drivers/clk/socfpga/clk.c b/drivers/clk/socfpga/clk.c index 5bb848cac6ec..81dd31a686df 100644 --- a/drivers/clk/socfpga/clk.c +++ b/drivers/clk/socfpga/clk.c @@ -49,7 +49,7 @@ #define SOCFPGA_L4_SP_CLK "l4_sp_clk" #define SOCFPGA_NAND_CLK "nand_clk" #define SOCFPGA_NAND_X_CLK "nand_x_clk" -#define SOCFPGA_MMC_CLK "mmc_clk" +#define SOCFPGA_MMC_CLK "sdmmc_clk" #define SOCFPGA_DB_CLK "gpio_db_clk" #define div_mask(width) ((1 << (width)) - 1) diff --git a/drivers/clk/versatile/clk-icst.c b/drivers/clk/versatile/clk-icst.c index 67ccf4aa7277..f5e4c21b301f 100644 --- a/drivers/clk/versatile/clk-icst.c +++ b/drivers/clk/versatile/clk-icst.c @@ -107,7 +107,7 @@ static int icst_set_rate(struct clk_hw *hw, unsigned long rate, vco = icst_hz_to_vco(icst->params, rate); icst->rate = icst_hz(icst->params, vco); - vco_set(icst->vcoreg, icst->lockreg, vco); + vco_set(icst->lockreg, icst->vcoreg, vco); return 0; } diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c index 08ae128cce9b..c73fc2b74de2 100644 --- a/drivers/connector/cn_proc.c +++ b/drivers/connector/cn_proc.c @@ -65,6 +65,7 @@ void proc_fork_connector(struct task_struct *task) msg = (struct cn_msg *)buffer; ev = (struct proc_event *)msg->data; + memset(&ev->event_data, 0, sizeof(ev->event_data)); get_seq(&msg->seq, &ev->cpu); ktime_get_ts(&ts); /* get high res monotonic timestamp */ put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns); @@ -80,6 +81,7 @@ void proc_fork_connector(struct task_struct *task) memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); + msg->flags = 0; /* not used */ /* If cn_netlink_send() failed, the data is not sent */ cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL); } @@ -96,6 +98,7 @@ void proc_exec_connector(struct task_struct *task) msg = (struct cn_msg *)buffer; ev = (struct proc_event *)msg->data; + memset(&ev->event_data, 0, sizeof(ev->event_data)); get_seq(&msg->seq, &ev->cpu); ktime_get_ts(&ts); /* get high res monotonic timestamp */ put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns); @@ -106,6 +109,7 @@ void proc_exec_connector(struct task_struct *task) memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); + msg->flags = 0; /* not used */ cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL); } @@ -122,6 +126,7 @@ void proc_id_connector(struct task_struct *task, int which_id) msg = (struct cn_msg *)buffer; ev = (struct proc_event *)msg->data; + memset(&ev->event_data, 0, sizeof(ev->event_data)); ev->what = which_id; ev->event_data.id.process_pid = task->pid; ev->event_data.id.process_tgid = task->tgid; @@ -145,6 +150,7 @@ void proc_id_connector(struct task_struct *task, int which_id) memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); + msg->flags = 0; /* not used */ cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL); } @@ -160,6 +166,7 @@ void proc_sid_connector(struct task_struct *task) msg = (struct cn_msg *)buffer; ev = (struct proc_event *)msg->data; + memset(&ev->event_data, 0, sizeof(ev->event_data)); get_seq(&msg->seq, &ev->cpu); ktime_get_ts(&ts); /* get high res monotonic timestamp */ put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns); @@ -170,6 +177,7 @@ void proc_sid_connector(struct task_struct *task) memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); + msg->flags = 0; /* not used */ cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL); } @@ -185,6 +193,7 @@ void proc_ptrace_connector(struct task_struct *task, int ptrace_id) msg = (struct cn_msg *)buffer; ev = (struct proc_event *)msg->data; + memset(&ev->event_data, 0, sizeof(ev->event_data)); get_seq(&msg->seq, &ev->cpu); ktime_get_ts(&ts); /* get high res monotonic timestamp */ put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns); @@ -203,6 +212,7 @@ void proc_ptrace_connector(struct task_struct *task, int ptrace_id) memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); + msg->flags = 0; /* not used */ cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL); } @@ -218,6 +228,7 @@ void proc_comm_connector(struct task_struct *task) msg = (struct cn_msg *)buffer; ev = (struct proc_event *)msg->data; + memset(&ev->event_data, 0, sizeof(ev->event_data)); get_seq(&msg->seq, &ev->cpu); ktime_get_ts(&ts); /* get high res monotonic timestamp */ put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns); @@ -229,6 +240,7 @@ void proc_comm_connector(struct task_struct *task) memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); + msg->flags = 0; /* not used */ cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL); } @@ -244,6 +256,7 @@ void proc_coredump_connector(struct task_struct *task) msg = (struct cn_msg *)buffer; ev = (struct proc_event *)msg->data; + memset(&ev->event_data, 0, sizeof(ev->event_data)); get_seq(&msg->seq, &ev->cpu); ktime_get_ts(&ts); /* get high res monotonic timestamp */ put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns); @@ -254,6 +267,7 @@ void proc_coredump_connector(struct task_struct *task) memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); + msg->flags = 0; /* not used */ cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL); } @@ -269,6 +283,7 @@ void proc_exit_connector(struct task_struct *task) msg = (struct cn_msg *)buffer; ev = (struct proc_event *)msg->data; + memset(&ev->event_data, 0, sizeof(ev->event_data)); get_seq(&msg->seq, &ev->cpu); ktime_get_ts(&ts); /* get high res monotonic timestamp */ put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns); @@ -281,6 +296,7 @@ void proc_exit_connector(struct task_struct *task) memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); + msg->flags = 0; /* not used */ cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL); } @@ -304,6 +320,7 @@ static void cn_proc_ack(int err, int rcvd_seq, int rcvd_ack) msg = (struct cn_msg *)buffer; ev = (struct proc_event *)msg->data; + memset(&ev->event_data, 0, sizeof(ev->event_data)); msg->seq = rcvd_seq; ktime_get_ts(&ts); /* get high res monotonic timestamp */ put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns); @@ -313,6 +330,7 @@ static void cn_proc_ack(int err, int rcvd_seq, int rcvd_ack) memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = rcvd_ack + 1; msg->len = sizeof(*ev); + msg->flags = 0; /* not used */ cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL); } diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c index 6ecfa758942c..a36749f1e44a 100644 --- a/drivers/connector/connector.c +++ b/drivers/connector/connector.c @@ -109,7 +109,7 @@ int cn_netlink_send(struct cn_msg *msg, u32 __group, gfp_t gfp_mask) data = nlmsg_data(nlh); - memcpy(data, msg, sizeof(*data) + msg->len); + memcpy(data, msg, size); NETLINK_CB(skb).dst_group = group; @@ -157,17 +157,18 @@ static int cn_call_callback(struct sk_buff *skb) static void cn_rx_skb(struct sk_buff *__skb) { struct nlmsghdr *nlh; - int err; struct sk_buff *skb; + int len, err; skb = skb_get(__skb); if (skb->len >= NLMSG_HDRLEN) { nlh = nlmsg_hdr(skb); + len = nlmsg_len(nlh); - if (nlh->nlmsg_len < sizeof(struct cn_msg) || + if (len < (int)sizeof(struct cn_msg) || skb->len < nlh->nlmsg_len || - nlh->nlmsg_len > CONNECTOR_MAX_MSG_SIZE) { + len > CONNECTOR_MAX_MSG_SIZE) { kfree_skb(skb); return; } diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index d2c3253e015e..506fd23c7550 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -986,12 +986,12 @@ static int __init acpi_cpufreq_init(void) { int ret; + if (acpi_disabled) + return -ENODEV; + /* don't keep reloading if cpufreq_driver exists */ if (cpufreq_get_current_driver()) - return 0; - - if (acpi_disabled) - return 0; + return -EEXIST; pr_debug("acpi_cpufreq_init\n"); diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 32b3479a2405..eb3fdc755000 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -48,7 +48,7 @@ static inline int32_t div_fp(int32_t x, int32_t y) } struct sample { - int core_pct_busy; + int32_t core_pct_busy; u64 aperf; u64 mperf; int freq; @@ -68,7 +68,7 @@ struct _pid { int32_t i_gain; int32_t d_gain; int deadband; - int last_err; + int32_t last_err; }; struct cpudata { @@ -153,16 +153,15 @@ static inline void pid_d_gain_set(struct _pid *pid, int percent) pid->d_gain = div_fp(int_tofp(percent), int_tofp(100)); } -static signed int pid_calc(struct _pid *pid, int busy) +static signed int pid_calc(struct _pid *pid, int32_t busy) { - signed int err, result; + signed int result; int32_t pterm, dterm, fp_error; int32_t integral_limit; - err = pid->setpoint - busy; - fp_error = int_tofp(err); + fp_error = int_tofp(pid->setpoint) - busy; - if (abs(err) <= pid->deadband) + if (abs(fp_error) <= int_tofp(pid->deadband)) return 0; pterm = mul_fp(pid->p_gain, fp_error); @@ -176,8 +175,8 @@ static signed int pid_calc(struct _pid *pid, int busy) if (pid->integral < -integral_limit) pid->integral = -integral_limit; - dterm = mul_fp(pid->d_gain, (err - pid->last_err)); - pid->last_err = err; + dterm = mul_fp(pid->d_gain, fp_error - pid->last_err); + pid->last_err = fp_error; result = pterm + mul_fp(pid->integral, pid->i_gain) + dterm; @@ -367,12 +366,13 @@ static int intel_pstate_turbo_pstate(void) static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max) { int max_perf = cpu->pstate.turbo_pstate; + int max_perf_adj; int min_perf; if (limits.no_turbo) max_perf = cpu->pstate.max_pstate; - max_perf = fp_toint(mul_fp(int_tofp(max_perf), limits.max_perf)); - *max = clamp_t(int, max_perf, + max_perf_adj = fp_toint(mul_fp(int_tofp(max_perf), limits.max_perf)); + *max = clamp_t(int, max_perf_adj, cpu->pstate.min_pstate, cpu->pstate.turbo_pstate); min_perf = fp_toint(mul_fp(int_tofp(max_perf), limits.min_perf)); @@ -383,6 +383,7 @@ static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max) static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate) { int max_perf, min_perf; + u64 val; intel_pstate_get_min_max(cpu, &min_perf, &max_perf); @@ -394,11 +395,11 @@ static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate) trace_cpu_frequency(pstate * 100000, cpu->cpu); cpu->pstate.current_pstate = pstate; + val = pstate << 8; if (limits.no_turbo) - wrmsrl(MSR_IA32_PERF_CTL, BIT(32) | (pstate << 8)); - else - wrmsrl(MSR_IA32_PERF_CTL, pstate << 8); + val |= (u64)1 << 32; + wrmsrl(MSR_IA32_PERF_CTL, val); } static inline void intel_pstate_pstate_increase(struct cpudata *cpu, int steps) @@ -435,8 +436,9 @@ static inline void intel_pstate_calc_busy(struct cpudata *cpu, struct sample *sample) { u64 core_pct; - core_pct = div64_u64(sample->aperf * 100, sample->mperf); - sample->freq = cpu->pstate.max_pstate * core_pct * 1000; + core_pct = div64_u64(int_tofp(sample->aperf * 100), + sample->mperf); + sample->freq = fp_toint(cpu->pstate.max_pstate * core_pct * 1000); sample->core_pct_busy = core_pct; } @@ -468,22 +470,19 @@ static inline void intel_pstate_set_sample_time(struct cpudata *cpu) mod_timer_pinned(&cpu->timer, jiffies + delay); } -static inline int intel_pstate_get_scaled_busy(struct cpudata *cpu) +static inline int32_t intel_pstate_get_scaled_busy(struct cpudata *cpu) { - int32_t busy_scaled; int32_t core_busy, max_pstate, current_pstate; - core_busy = int_tofp(cpu->samples[cpu->sample_ptr].core_pct_busy); + core_busy = cpu->samples[cpu->sample_ptr].core_pct_busy; max_pstate = int_tofp(cpu->pstate.max_pstate); current_pstate = int_tofp(cpu->pstate.current_pstate); - busy_scaled = mul_fp(core_busy, div_fp(max_pstate, current_pstate)); - - return fp_toint(busy_scaled); + return mul_fp(core_busy, div_fp(max_pstate, current_pstate)); } static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu) { - int busy_scaled; + int32_t busy_scaled; struct _pid *pid; signed int ctl = 0; int steps; @@ -637,8 +636,8 @@ static int intel_pstate_cpu_exit(struct cpufreq_policy *policy) static int intel_pstate_cpu_init(struct cpufreq_policy *policy) { - int rc, min_pstate, max_pstate; struct cpudata *cpu; + int rc; rc = intel_pstate_init_cpu(policy->cpu); if (rc) @@ -652,9 +651,8 @@ static int intel_pstate_cpu_init(struct cpufreq_policy *policy) else policy->policy = CPUFREQ_POLICY_POWERSAVE; - intel_pstate_get_min_max(cpu, &min_pstate, &max_pstate); - policy->min = min_pstate * 100000; - policy->max = max_pstate * 100000; + policy->min = cpu->pstate.min_pstate * 100000; + policy->max = cpu->pstate.turbo_pstate * 100000; /* cpuinfo and default policy values */ policy->cpuinfo.min_freq = cpu->pstate.min_pstate * 100000; diff --git a/drivers/cpufreq/s3c64xx-cpufreq.c b/drivers/cpufreq/s3c64xx-cpufreq.c index 8a72b0c555f8..15631f92ab7d 100644 --- a/drivers/cpufreq/s3c64xx-cpufreq.c +++ b/drivers/cpufreq/s3c64xx-cpufreq.c @@ -166,7 +166,7 @@ static void __init s3c64xx_cpufreq_config_regulator(void) if (freq->frequency == CPUFREQ_ENTRY_INVALID) continue; - dvfs = &s3c64xx_dvfs_table[freq->index]; + dvfs = &s3c64xx_dvfs_table[freq->driver_data]; found = 0; for (i = 0; i < count; i++) { diff --git a/drivers/crypto/ixp4xx_crypto.c b/drivers/crypto/ixp4xx_crypto.c index 21180d6cad6e..214357e12dc0 100644 --- a/drivers/crypto/ixp4xx_crypto.c +++ b/drivers/crypto/ixp4xx_crypto.c @@ -218,23 +218,9 @@ static dma_addr_t crypt_phys; static int support_aes = 1; -static void dev_release(struct device *dev) -{ - return; -} - #define DRIVER_NAME "ixp4xx_crypto" -static struct platform_device pseudo_dev = { - .name = DRIVER_NAME, - .id = 0, - .num_resources = 0, - .dev = { - .coherent_dma_mask = DMA_BIT_MASK(32), - .release = dev_release, - } -}; -static struct device *dev = &pseudo_dev.dev; +static struct platform_device *pdev; static inline dma_addr_t crypt_virt2phys(struct crypt_ctl *virt) { @@ -263,6 +249,7 @@ static inline const struct ix_hash_algo *ix_hash(struct crypto_tfm *tfm) static int setup_crypt_desc(void) { + struct device *dev = &pdev->dev; BUILD_BUG_ON(sizeof(struct crypt_ctl) != 64); crypt_virt = dma_alloc_coherent(dev, NPE_QLEN * sizeof(struct crypt_ctl), @@ -363,6 +350,7 @@ static void finish_scattered_hmac(struct crypt_ctl *crypt) static void one_packet(dma_addr_t phys) { + struct device *dev = &pdev->dev; struct crypt_ctl *crypt; struct ixp_ctx *ctx; int failed; @@ -432,7 +420,7 @@ static void crypto_done_action(unsigned long arg) tasklet_schedule(&crypto_done_tasklet); } -static int init_ixp_crypto(void) +static int init_ixp_crypto(struct device *dev) { int ret = -ENODEV; u32 msg[2] = { 0, 0 }; @@ -519,7 +507,7 @@ err: return ret; } -static void release_ixp_crypto(void) +static void release_ixp_crypto(struct device *dev) { qmgr_disable_irq(RECV_QID); tasklet_kill(&crypto_done_tasklet); @@ -886,6 +874,7 @@ static int ablk_perform(struct ablkcipher_request *req, int encrypt) enum dma_data_direction src_direction = DMA_BIDIRECTIONAL; struct ablk_ctx *req_ctx = ablkcipher_request_ctx(req); struct buffer_desc src_hook; + struct device *dev = &pdev->dev; gfp_t flags = req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL : GFP_ATOMIC; @@ -1010,6 +999,7 @@ static int aead_perform(struct aead_request *req, int encrypt, unsigned int cryptlen; struct buffer_desc *buf, src_hook; struct aead_ctx *req_ctx = aead_request_ctx(req); + struct device *dev = &pdev->dev; gfp_t flags = req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL : GFP_ATOMIC; @@ -1418,20 +1408,30 @@ static struct ixp_alg ixp4xx_algos[] = { } }; #define IXP_POSTFIX "-ixp4xx" + +static const struct platform_device_info ixp_dev_info __initdata = { + .name = DRIVER_NAME, + .id = 0, + .dma_mask = DMA_BIT_MASK(32), +}; + static int __init ixp_module_init(void) { int num = ARRAY_SIZE(ixp4xx_algos); - int i,err ; + int i, err ; - if (platform_device_register(&pseudo_dev)) - return -ENODEV; + pdev = platform_device_register_full(&ixp_dev_info); + if (IS_ERR(pdev)) + return PTR_ERR(pdev); + + dev = &pdev->dev; spin_lock_init(&desc_lock); spin_lock_init(&emerg_lock); - err = init_ixp_crypto(); + err = init_ixp_crypto(&pdev->dev); if (err) { - platform_device_unregister(&pseudo_dev); + platform_device_unregister(pdev); return err; } for (i=0; i< num; i++) { @@ -1495,8 +1495,8 @@ static void __exit ixp_module_exit(void) if (ixp4xx_algos[i].registered) crypto_unregister_alg(&ixp4xx_algos[i].crypto); } - release_ixp_crypto(); - platform_device_unregister(&pseudo_dev); + release_ixp_crypto(&pdev->dev); + platform_device_unregister(pdev); } module_init(ixp_module_init); diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c index fce46c5bf1c7..e51a9832ef0d 100644 --- a/drivers/dma/amba-pl08x.c +++ b/drivers/dma/amba-pl08x.c @@ -2055,6 +2055,11 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id) if (ret) return ret; + /* Ensure that we can do DMA */ + ret = dma_set_mask_and_coherent(&adev->dev, DMA_BIT_MASK(32)); + if (ret) + goto out_no_pl08x; + /* Create the driver state holder */ pl08x = kzalloc(sizeof(*pl08x), GFP_KERNEL); if (!pl08x) { diff --git a/drivers/dma/dw/platform.c b/drivers/dma/dw/platform.c index e35d97590311..453822cc4f9d 100644 --- a/drivers/dma/dw/platform.c +++ b/drivers/dma/dw/platform.c @@ -191,11 +191,9 @@ static int dw_probe(struct platform_device *pdev) if (IS_ERR(chip->regs)) return PTR_ERR(chip->regs); - /* Apply default dma_mask if needed */ - if (!dev->dma_mask) { - dev->dma_mask = &dev->coherent_dma_mask; - dev->coherent_dma_mask = DMA_BIT_MASK(32); - } + err = dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (err) + return err; pdata = dev_get_platdata(dev); if (!pdata) diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c index 3519111c566b..bef8a368c8dd 100644 --- a/drivers/dma/edma.c +++ b/drivers/dma/edma.c @@ -305,6 +305,7 @@ static struct dma_async_tx_descriptor *edma_prep_slave_sg( edma_alloc_slot(EDMA_CTLR(echan->ch_num), EDMA_SLOT_ANY); if (echan->slot[i] < 0) { + kfree(edesc); dev_err(dev, "Failed to allocate slot\n"); kfree(edesc); return NULL; @@ -346,6 +347,7 @@ static struct dma_async_tx_descriptor *edma_prep_slave_sg( ccnt = sg_dma_len(sg) / (acnt * bcnt); if (ccnt > (SZ_64K - 1)) { dev_err(dev, "Exceeded max SG segment size\n"); + kfree(edesc); return NULL; } cidx = acnt * bcnt; @@ -632,6 +634,10 @@ static int edma_probe(struct platform_device *pdev) struct edma_cc *ecc; int ret; + ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (ret) + return ret; + ecc = devm_kzalloc(&pdev->dev, sizeof(*ecc), GFP_KERNEL); if (!ecc) { dev_err(&pdev->dev, "Can't allocate controller\n"); @@ -703,11 +709,13 @@ static struct platform_device *pdev0, *pdev1; static const struct platform_device_info edma_dev_info0 = { .name = "edma-dma-engine", .id = 0, + .dma_mask = DMA_BIT_MASK(32), }; static const struct platform_device_info edma_dev_info1 = { .name = "edma-dma-engine", .id = 1, + .dma_mask = DMA_BIT_MASK(32), }; static int edma_init(void) @@ -721,8 +729,6 @@ static int edma_init(void) ret = PTR_ERR(pdev0); goto out; } - pdev0->dev.dma_mask = &pdev0->dev.coherent_dma_mask; - pdev0->dev.coherent_dma_mask = DMA_BIT_MASK(32); } if (EDMA_CTLRS == 2) { @@ -732,8 +738,6 @@ static int edma_init(void) platform_device_unregister(pdev0); ret = PTR_ERR(pdev1); } - pdev1->dev.dma_mask = &pdev1->dev.coherent_dma_mask; - pdev1->dev.coherent_dma_mask = DMA_BIT_MASK(32); } out: diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c index fc43603cf0bb..c1fd504cae28 100644 --- a/drivers/dma/imx-sdma.c +++ b/drivers/dma/imx-sdma.c @@ -1432,6 +1432,10 @@ static int __init sdma_probe(struct platform_device *pdev) return -EINVAL; } + ret = dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (ret) + return ret; + sdma = kzalloc(sizeof(*sdma), GFP_KERNEL); if (!sdma) return -ENOMEM; diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index a562d24d20bf..df8b10fd1726 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -2903,6 +2903,10 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id) pdat = dev_get_platdata(&adev->dev); + ret = dma_set_mask_and_coherent(&adev->dev, DMA_BIT_MASK(32)); + if (ret) + return ret; + /* Allocate a new DMAC and its Channels */ pdmac = devm_kzalloc(&adev->dev, sizeof(*pdmac), GFP_KERNEL); if (!pdmac) { diff --git a/drivers/firmware/dcdbas.c b/drivers/firmware/dcdbas.c index ff080ee20197..1b5e8e46226d 100644 --- a/drivers/firmware/dcdbas.c +++ b/drivers/firmware/dcdbas.c @@ -545,12 +545,15 @@ static int dcdbas_probe(struct platform_device *dev) host_control_action = HC_ACTION_NONE; host_control_smi_type = HC_SMITYPE_NONE; + dcdbas_pdev = dev; + /* * BIOS SMI calls require buffer addresses be in 32-bit address space. * This is done by setting the DMA mask below. */ - dcdbas_pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32); - dcdbas_pdev->dev.dma_mask = &dcdbas_pdev->dev.coherent_dma_mask; + error = dma_set_coherent_mask(&dcdbas_pdev->dev, DMA_BIT_MASK(32)); + if (error) + return error; error = sysfs_create_group(&dev->dev.kobj, &dcdbas_attr_group); if (error) @@ -581,6 +584,14 @@ static struct platform_driver dcdbas_driver = { .remove = dcdbas_remove, }; +static const struct platform_device_info dcdbas_dev_info __initdata = { + .name = DRIVER_NAME, + .id = -1, + .dma_mask = DMA_BIT_MASK(32), +}; + +static struct platform_device *dcdbas_pdev_reg; + /** * dcdbas_init: initialize driver */ @@ -592,20 +603,14 @@ static int __init dcdbas_init(void) if (error) return error; - dcdbas_pdev = platform_device_alloc(DRIVER_NAME, -1); - if (!dcdbas_pdev) { - error = -ENOMEM; + dcdbas_pdev_reg = platform_device_register_full(&dcdbas_dev_info); + if (IS_ERR(dcdbas_pdev_reg)) { + error = PTR_ERR(dcdbas_pdev_reg); goto err_unregister_driver; } - error = platform_device_add(dcdbas_pdev); - if (error) - goto err_free_device; - return 0; - err_free_device: - platform_device_put(dcdbas_pdev); err_unregister_driver: platform_driver_unregister(&dcdbas_driver); return error; @@ -628,8 +633,9 @@ static void __exit dcdbas_exit(void) * all sysfs attributes belonging to this module have been * released. */ - smi_data_buf_free(); - platform_device_unregister(dcdbas_pdev); + if (dcdbas_pdev) + smi_data_buf_free(); + platform_device_unregister(dcdbas_pdev_reg); platform_driver_unregister(&dcdbas_driver); } diff --git a/drivers/firmware/google/gsmi.c b/drivers/firmware/google/gsmi.c index 6eb535ffeddc..e5a67b24587a 100644 --- a/drivers/firmware/google/gsmi.c +++ b/drivers/firmware/google/gsmi.c @@ -764,6 +764,13 @@ static __init int gsmi_system_valid(void) static struct kobject *gsmi_kobj; static struct efivars efivars; +static const struct platform_device_info gsmi_dev_info = { + .name = "gsmi", + .id = -1, + /* SMI callbacks require 32bit addresses */ + .dma_mask = DMA_BIT_MASK(32), +}; + static __init int gsmi_init(void) { unsigned long flags; @@ -776,7 +783,7 @@ static __init int gsmi_init(void) gsmi_dev.smi_cmd = acpi_gbl_FADT.smi_command; /* register device */ - gsmi_dev.pdev = platform_device_register_simple("gsmi", -1, NULL, 0); + gsmi_dev.pdev = platform_device_register_full(&gsmi_dev_info); if (IS_ERR(gsmi_dev.pdev)) { printk(KERN_ERR "gsmi: unable to register platform device\n"); return PTR_ERR(gsmi_dev.pdev); @@ -785,10 +792,6 @@ static __init int gsmi_init(void) /* SMI access needs to be serialized */ spin_lock_init(&gsmi_dev.lock); - /* SMI callbacks require 32bit addresses */ - gsmi_dev.pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32); - gsmi_dev.pdev->dev.dma_mask = - &gsmi_dev.pdev->dev.coherent_dma_mask; ret = -ENOMEM; gsmi_dev.dma_pool = dma_pool_create("gsmi", &gsmi_dev.pdev->dev, GSMI_BUF_SIZE, GSMI_BUF_ALIGN, 0); diff --git a/drivers/gpio/gpio-lynxpoint.c b/drivers/gpio/gpio-lynxpoint.c index 2d9ca6055e5e..41b5913ddabe 100644 --- a/drivers/gpio/gpio-lynxpoint.c +++ b/drivers/gpio/gpio-lynxpoint.c @@ -248,14 +248,15 @@ static void lp_gpio_irq_handler(unsigned irq, struct irq_desc *desc) struct lp_gpio *lg = irq_data_get_irq_handler_data(data); struct irq_chip *chip = irq_data_get_irq_chip(data); u32 base, pin, mask; - unsigned long reg, pending; + unsigned long reg, ena, pending; unsigned virq; /* check from GPIO controller which pin triggered the interrupt */ for (base = 0; base < lg->chip.ngpio; base += 32) { reg = lp_gpio_reg(&lg->chip, base, LP_INT_STAT); + ena = lp_gpio_reg(&lg->chip, base, LP_INT_ENABLE); - while ((pending = inl(reg))) { + while ((pending = (inl(reg) & inl(ena)))) { pin = __ffs(pending); mask = BIT(pin); /* Clear before handling so we don't lose an edge */ diff --git a/drivers/gpio/gpio-sa1100.c b/drivers/gpio/gpio-sa1100.c index 8ea3b33d4b40..a90be34e4d5c 100644 --- a/drivers/gpio/gpio-sa1100.c +++ b/drivers/gpio/gpio-sa1100.c @@ -10,7 +10,7 @@ #include <linux/gpio.h> #include <linux/init.h> #include <linux/module.h> - +#include <linux/io.h> #include <mach/hardware.h> #include <mach/irqs.h> diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 86ef3461ec06..0dee0e0c247a 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -136,7 +136,7 @@ static struct gpio_desc *gpio_to_desc(unsigned gpio) */ static int desc_to_gpio(const struct gpio_desc *desc) { - return desc->chip->base + gpio_chip_hwgpio(desc); + return desc - &gpio_desc[0]; } @@ -1398,7 +1398,7 @@ static int gpiod_request(struct gpio_desc *desc, const char *label) int status = -EPROBE_DEFER; unsigned long flags; - if (!desc || !desc->chip) { + if (!desc) { pr_warn("%s: invalid GPIO\n", __func__); return -EINVAL; } @@ -1406,6 +1406,8 @@ static int gpiod_request(struct gpio_desc *desc, const char *label) spin_lock_irqsave(&gpio_lock, flags); chip = desc->chip; + if (chip == NULL) + goto done; if (!try_module_get(chip->owner)) goto done; diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c index e572dd20bdee..fe58d0833a11 100644 --- a/drivers/gpu/drm/drm_drv.c +++ b/drivers/gpu/drm/drm_drv.c @@ -61,7 +61,7 @@ static int drm_version(struct drm_device *dev, void *data, /** Ioctl table */ static const struct drm_ioctl_desc drm_ioctls[] = { - DRM_IOCTL_DEF(DRM_IOCTL_VERSION, drm_version, DRM_UNLOCKED), + DRM_IOCTL_DEF(DRM_IOCTL_VERSION, drm_version, DRM_UNLOCKED|DRM_RENDER_ALLOW), DRM_IOCTL_DEF(DRM_IOCTL_GET_UNIQUE, drm_getunique, 0), DRM_IOCTL_DEF(DRM_IOCTL_GET_MAGIC, drm_getmagic, 0), DRM_IOCTL_DEF(DRM_IOCTL_IRQ_BUSID, drm_irq_by_busid, DRM_MASTER|DRM_ROOT_ONLY), @@ -402,9 +402,16 @@ long drm_ioctl(struct file *filp, cmd = ioctl->cmd_drv; } else if ((nr >= DRM_COMMAND_END) || (nr < DRM_COMMAND_BASE)) { + u32 drv_size; + ioctl = &drm_ioctls[nr]; - cmd = ioctl->cmd; + + drv_size = _IOC_SIZE(ioctl->cmd); usize = asize = _IOC_SIZE(cmd); + if (drv_size > asize) + asize = drv_size; + + cmd = ioctl->cmd; } else goto err_i1; diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c index bb82ef78ca85..81192d00b39e 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_drv.c +++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c @@ -286,7 +286,11 @@ static struct drm_driver exynos_drm_driver = { static int exynos_drm_platform_probe(struct platform_device *pdev) { - pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32); + int ret; + + ret = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)); + if (ret) + return ret; return drm_platform_init(&exynos_drm_driver, pdev); } diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 69d8ed5416c3..2ad27880cd04 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -505,6 +505,8 @@ static int i915_drm_freeze(struct drm_device *dev) intel_modeset_suspend_hw(dev); } + i915_gem_suspend_gtt_mappings(dev); + i915_save_state(dev); intel_opregion_fini(dev); @@ -648,7 +650,8 @@ static int i915_drm_thaw(struct drm_device *dev) mutex_lock(&dev->struct_mutex); i915_gem_restore_gtt_mappings(dev); mutex_unlock(&dev->struct_mutex); - } + } else if (drm_core_check_feature(dev, DRIVER_MODESET)) + i915_check_and_clear_faults(dev); __i915_drm_thaw(dev); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 35874b3a86dc..ab0f2c0a440c 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -497,10 +497,12 @@ struct i915_address_space { /* FIXME: Need a more generic return type */ gen6_gtt_pte_t (*pte_encode)(dma_addr_t addr, - enum i915_cache_level level); + enum i915_cache_level level, + bool valid); /* Create a valid PTE */ void (*clear_range)(struct i915_address_space *vm, unsigned int first_entry, - unsigned int num_entries); + unsigned int num_entries, + bool use_scratch); void (*insert_entries)(struct i915_address_space *vm, struct sg_table *st, unsigned int first_entry, @@ -2065,6 +2067,8 @@ void i915_ppgtt_bind_object(struct i915_hw_ppgtt *ppgtt, void i915_ppgtt_unbind_object(struct i915_hw_ppgtt *ppgtt, struct drm_i915_gem_object *obj); +void i915_check_and_clear_faults(struct drm_device *dev); +void i915_gem_suspend_gtt_mappings(struct drm_device *dev); void i915_gem_restore_gtt_mappings(struct drm_device *dev); int __must_check i915_gem_gtt_prepare_object(struct drm_i915_gem_object *obj); void i915_gem_gtt_bind_object(struct drm_i915_gem_object *obj, diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 212f6d8c35ec..1f7b4caefb6e 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -58,9 +58,10 @@ #define HSW_WT_ELLC_LLC_AGE0 HSW_CACHEABILITY_CONTROL(0x6) static gen6_gtt_pte_t snb_pte_encode(dma_addr_t addr, - enum i915_cache_level level) + enum i915_cache_level level, + bool valid) { - gen6_gtt_pte_t pte = GEN6_PTE_VALID; + gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0; pte |= GEN6_PTE_ADDR_ENCODE(addr); switch (level) { @@ -79,9 +80,10 @@ static gen6_gtt_pte_t snb_pte_encode(dma_addr_t addr, } static gen6_gtt_pte_t ivb_pte_encode(dma_addr_t addr, - enum i915_cache_level level) + enum i915_cache_level level, + bool valid) { - gen6_gtt_pte_t pte = GEN6_PTE_VALID; + gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0; pte |= GEN6_PTE_ADDR_ENCODE(addr); switch (level) { @@ -105,9 +107,10 @@ static gen6_gtt_pte_t ivb_pte_encode(dma_addr_t addr, #define BYT_PTE_SNOOPED_BY_CPU_CACHES (1 << 2) static gen6_gtt_pte_t byt_pte_encode(dma_addr_t addr, - enum i915_cache_level level) + enum i915_cache_level level, + bool valid) { - gen6_gtt_pte_t pte = GEN6_PTE_VALID; + gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0; pte |= GEN6_PTE_ADDR_ENCODE(addr); /* Mark the page as writeable. Other platforms don't have a @@ -122,9 +125,10 @@ static gen6_gtt_pte_t byt_pte_encode(dma_addr_t addr, } static gen6_gtt_pte_t hsw_pte_encode(dma_addr_t addr, - enum i915_cache_level level) + enum i915_cache_level level, + bool valid) { - gen6_gtt_pte_t pte = GEN6_PTE_VALID; + gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0; pte |= HSW_PTE_ADDR_ENCODE(addr); if (level != I915_CACHE_NONE) @@ -134,9 +138,10 @@ static gen6_gtt_pte_t hsw_pte_encode(dma_addr_t addr, } static gen6_gtt_pte_t iris_pte_encode(dma_addr_t addr, - enum i915_cache_level level) + enum i915_cache_level level, + bool valid) { - gen6_gtt_pte_t pte = GEN6_PTE_VALID; + gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0; pte |= HSW_PTE_ADDR_ENCODE(addr); switch (level) { @@ -236,7 +241,8 @@ static int gen6_ppgtt_enable(struct drm_device *dev) /* PPGTT support for Sandybdrige/Gen6 and later */ static void gen6_ppgtt_clear_range(struct i915_address_space *vm, unsigned first_entry, - unsigned num_entries) + unsigned num_entries, + bool use_scratch) { struct i915_hw_ppgtt *ppgtt = container_of(vm, struct i915_hw_ppgtt, base); @@ -245,7 +251,7 @@ static void gen6_ppgtt_clear_range(struct i915_address_space *vm, unsigned first_pte = first_entry % I915_PPGTT_PT_ENTRIES; unsigned last_pte, i; - scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC); + scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC, true); while (num_entries) { last_pte = first_pte + num_entries; @@ -282,7 +288,7 @@ static void gen6_ppgtt_insert_entries(struct i915_address_space *vm, dma_addr_t page_addr; page_addr = sg_page_iter_dma_address(&sg_iter); - pt_vaddr[act_pte] = vm->pte_encode(page_addr, cache_level); + pt_vaddr[act_pte] = vm->pte_encode(page_addr, cache_level, true); if (++act_pte == I915_PPGTT_PT_ENTRIES) { kunmap_atomic(pt_vaddr); act_pt++; @@ -367,7 +373,7 @@ static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt) } ppgtt->base.clear_range(&ppgtt->base, 0, - ppgtt->num_pd_entries * I915_PPGTT_PT_ENTRIES); + ppgtt->num_pd_entries * I915_PPGTT_PT_ENTRIES, true); ppgtt->pd_offset = first_pd_entry_in_global_pt * sizeof(gen6_gtt_pte_t); @@ -444,7 +450,8 @@ void i915_ppgtt_unbind_object(struct i915_hw_ppgtt *ppgtt, { ppgtt->base.clear_range(&ppgtt->base, i915_gem_obj_ggtt_offset(obj) >> PAGE_SHIFT, - obj->base.size >> PAGE_SHIFT); + obj->base.size >> PAGE_SHIFT, + true); } extern int intel_iommu_gfx_mapped; @@ -485,15 +492,65 @@ static void undo_idling(struct drm_i915_private *dev_priv, bool interruptible) dev_priv->mm.interruptible = interruptible; } +void i915_check_and_clear_faults(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_ring_buffer *ring; + int i; + + if (INTEL_INFO(dev)->gen < 6) + return; + + for_each_ring(ring, dev_priv, i) { + u32 fault_reg; + fault_reg = I915_READ(RING_FAULT_REG(ring)); + if (fault_reg & RING_FAULT_VALID) { + DRM_DEBUG_DRIVER("Unexpected fault\n" + "\tAddr: 0x%08lx\\n" + "\tAddress space: %s\n" + "\tSource ID: %d\n" + "\tType: %d\n", + fault_reg & PAGE_MASK, + fault_reg & RING_FAULT_GTTSEL_MASK ? "GGTT" : "PPGTT", + RING_FAULT_SRCID(fault_reg), + RING_FAULT_FAULT_TYPE(fault_reg)); + I915_WRITE(RING_FAULT_REG(ring), + fault_reg & ~RING_FAULT_VALID); + } + } + POSTING_READ(RING_FAULT_REG(&dev_priv->ring[RCS])); +} + +void i915_gem_suspend_gtt_mappings(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + /* Don't bother messing with faults pre GEN6 as we have little + * documentation supporting that it's a good idea. + */ + if (INTEL_INFO(dev)->gen < 6) + return; + + i915_check_and_clear_faults(dev); + + dev_priv->gtt.base.clear_range(&dev_priv->gtt.base, + dev_priv->gtt.base.start / PAGE_SIZE, + dev_priv->gtt.base.total / PAGE_SIZE, + false); +} + void i915_gem_restore_gtt_mappings(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; struct drm_i915_gem_object *obj; + i915_check_and_clear_faults(dev); + /* First fill our portion of the GTT with scratch pages */ dev_priv->gtt.base.clear_range(&dev_priv->gtt.base, dev_priv->gtt.base.start / PAGE_SIZE, - dev_priv->gtt.base.total / PAGE_SIZE); + dev_priv->gtt.base.total / PAGE_SIZE, + true); list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) { i915_gem_clflush_object(obj, obj->pin_display); @@ -536,7 +593,7 @@ static void gen6_ggtt_insert_entries(struct i915_address_space *vm, for_each_sg_page(st->sgl, &sg_iter, st->nents, 0) { addr = sg_page_iter_dma_address(&sg_iter); - iowrite32(vm->pte_encode(addr, level), >t_entries[i]); + iowrite32(vm->pte_encode(addr, level, true), >t_entries[i]); i++; } @@ -548,7 +605,7 @@ static void gen6_ggtt_insert_entries(struct i915_address_space *vm, */ if (i != 0) WARN_ON(readl(>t_entries[i-1]) != - vm->pte_encode(addr, level)); + vm->pte_encode(addr, level, true)); /* This next bit makes the above posting read even more important. We * want to flush the TLBs only after we're certain all the PTE updates @@ -560,7 +617,8 @@ static void gen6_ggtt_insert_entries(struct i915_address_space *vm, static void gen6_ggtt_clear_range(struct i915_address_space *vm, unsigned int first_entry, - unsigned int num_entries) + unsigned int num_entries, + bool use_scratch) { struct drm_i915_private *dev_priv = vm->dev->dev_private; gen6_gtt_pte_t scratch_pte, __iomem *gtt_base = @@ -573,7 +631,8 @@ static void gen6_ggtt_clear_range(struct i915_address_space *vm, first_entry, num_entries, max_entries)) num_entries = max_entries; - scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC); + scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC, use_scratch); + for (i = 0; i < num_entries; i++) iowrite32(scratch_pte, >t_base[i]); readl(gtt_base); @@ -594,7 +653,8 @@ static void i915_ggtt_insert_entries(struct i915_address_space *vm, static void i915_ggtt_clear_range(struct i915_address_space *vm, unsigned int first_entry, - unsigned int num_entries) + unsigned int num_entries, + bool unused) { intel_gtt_clear_range(first_entry, num_entries); } @@ -622,7 +682,8 @@ void i915_gem_gtt_unbind_object(struct drm_i915_gem_object *obj) dev_priv->gtt.base.clear_range(&dev_priv->gtt.base, entry, - obj->base.size >> PAGE_SHIFT); + obj->base.size >> PAGE_SHIFT, + true); obj->has_global_gtt_mapping = 0; } @@ -709,11 +770,11 @@ void i915_gem_setup_global_gtt(struct drm_device *dev, const unsigned long count = (hole_end - hole_start) / PAGE_SIZE; DRM_DEBUG_KMS("clearing unused GTT space: [%lx, %lx]\n", hole_start, hole_end); - ggtt_vm->clear_range(ggtt_vm, hole_start / PAGE_SIZE, count); + ggtt_vm->clear_range(ggtt_vm, hole_start / PAGE_SIZE, count, true); } /* And finally clear the reserved guard page */ - ggtt_vm->clear_range(ggtt_vm, end / PAGE_SIZE - 1, 1); + ggtt_vm->clear_range(ggtt_vm, end / PAGE_SIZE - 1, 1, true); } static bool diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 38f96f65d87a..ef9b35479f01 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -604,6 +604,10 @@ #define ARB_MODE_SWIZZLE_IVB (1<<5) #define RENDER_HWS_PGA_GEN7 (0x04080) #define RING_FAULT_REG(ring) (0x4094 + 0x100*(ring)->id) +#define RING_FAULT_GTTSEL_MASK (1<<11) +#define RING_FAULT_SRCID(x) ((x >> 3) & 0xff) +#define RING_FAULT_FAULT_TYPE(x) ((x >> 1) & 0x3) +#define RING_FAULT_VALID (1<<0) #define DONE_REG 0x40b0 #define BSD_HWS_PGA_GEN7 (0x04180) #define BLT_HWS_PGA_GEN7 (0x04280) @@ -4279,7 +4283,9 @@ #define FDI_RX_CHICKEN(pipe) _PIPE(pipe, _FDI_RXA_CHICKEN, _FDI_RXB_CHICKEN) #define SOUTH_DSPCLK_GATE_D 0xc2020 +#define PCH_DPLUNIT_CLOCK_GATE_DISABLE (1<<30) #define PCH_DPLSUNIT_CLOCK_GATE_DISABLE (1<<29) +#define PCH_CPUNIT_CLOCK_GATE_DISABLE (1<<14) #define PCH_LP_PARTITION_LEVEL_DISABLE (1<<12) /* CPU: FDI_TX */ diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c index ea9022ef15d5..10d1de5bce6f 100644 --- a/drivers/gpu/drm/i915/intel_crt.c +++ b/drivers/gpu/drm/i915/intel_crt.c @@ -83,8 +83,7 @@ static bool intel_crt_get_hw_state(struct intel_encoder *encoder, return true; } -static void intel_crt_get_config(struct intel_encoder *encoder, - struct intel_crtc_config *pipe_config) +static unsigned int intel_crt_get_flags(struct intel_encoder *encoder) { struct drm_i915_private *dev_priv = encoder->base.dev->dev_private; struct intel_crt *crt = intel_encoder_to_crt(encoder); @@ -102,7 +101,25 @@ static void intel_crt_get_config(struct intel_encoder *encoder, else flags |= DRM_MODE_FLAG_NVSYNC; - pipe_config->adjusted_mode.flags |= flags; + return flags; +} + +static void intel_crt_get_config(struct intel_encoder *encoder, + struct intel_crtc_config *pipe_config) +{ + pipe_config->adjusted_mode.flags |= intel_crt_get_flags(encoder); +} + +static void hsw_crt_get_config(struct intel_encoder *encoder, + struct intel_crtc_config *pipe_config) +{ + intel_ddi_get_config(encoder, pipe_config); + + pipe_config->adjusted_mode.flags &= ~(DRM_MODE_FLAG_PHSYNC | + DRM_MODE_FLAG_NHSYNC | + DRM_MODE_FLAG_PVSYNC | + DRM_MODE_FLAG_NVSYNC); + pipe_config->adjusted_mode.flags |= intel_crt_get_flags(encoder); } /* Note: The caller is required to filter out dpms modes not supported by the @@ -799,7 +816,10 @@ void intel_crt_init(struct drm_device *dev) crt->base.mode_set = intel_crt_mode_set; crt->base.disable = intel_disable_crt; crt->base.enable = intel_enable_crt; - crt->base.get_config = intel_crt_get_config; + if (IS_HASWELL(dev)) + crt->base.get_config = hsw_crt_get_config; + else + crt->base.get_config = intel_crt_get_config; if (I915_HAS_HOTPLUG(dev)) crt->base.hpd_pin = HPD_CRT; if (HAS_DDI(dev)) diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index 63de2701b974..b53fff84a7d5 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -1249,8 +1249,8 @@ static void intel_ddi_hot_plug(struct intel_encoder *intel_encoder) intel_dp_check_link_status(intel_dp); } -static void intel_ddi_get_config(struct intel_encoder *encoder, - struct intel_crtc_config *pipe_config) +void intel_ddi_get_config(struct intel_encoder *encoder, + struct intel_crtc_config *pipe_config) { struct drm_i915_private *dev_priv = encoder->base.dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc); @@ -1268,6 +1268,23 @@ static void intel_ddi_get_config(struct intel_encoder *encoder, flags |= DRM_MODE_FLAG_NVSYNC; pipe_config->adjusted_mode.flags |= flags; + + switch (temp & TRANS_DDI_BPC_MASK) { + case TRANS_DDI_BPC_6: + pipe_config->pipe_bpp = 18; + break; + case TRANS_DDI_BPC_8: + pipe_config->pipe_bpp = 24; + break; + case TRANS_DDI_BPC_10: + pipe_config->pipe_bpp = 30; + break; + case TRANS_DDI_BPC_12: + pipe_config->pipe_bpp = 36; + break; + default: + break; + } } static void intel_ddi_destroy(struct drm_encoder *encoder) diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 581fb4b2f766..d78d33f9337d 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -2327,9 +2327,10 @@ static void intel_fdi_normal_train(struct drm_crtc *crtc) FDI_FE_ERRC_ENABLE); } -static bool pipe_has_enabled_pch(struct intel_crtc *intel_crtc) +static bool pipe_has_enabled_pch(struct intel_crtc *crtc) { - return intel_crtc->base.enabled && intel_crtc->config.has_pch_encoder; + return crtc->base.enabled && crtc->active && + crtc->config.has_pch_encoder; } static void ivb_modeset_global_resources(struct drm_device *dev) @@ -2979,6 +2980,48 @@ static void ironlake_pch_transcoder_set_timings(struct intel_crtc *crtc, I915_READ(VSYNCSHIFT(cpu_transcoder))); } +static void cpt_enable_fdi_bc_bifurcation(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + uint32_t temp; + + temp = I915_READ(SOUTH_CHICKEN1); + if (temp & FDI_BC_BIFURCATION_SELECT) + return; + + WARN_ON(I915_READ(FDI_RX_CTL(PIPE_B)) & FDI_RX_ENABLE); + WARN_ON(I915_READ(FDI_RX_CTL(PIPE_C)) & FDI_RX_ENABLE); + + temp |= FDI_BC_BIFURCATION_SELECT; + DRM_DEBUG_KMS("enabling fdi C rx\n"); + I915_WRITE(SOUTH_CHICKEN1, temp); + POSTING_READ(SOUTH_CHICKEN1); +} + +static void ivybridge_update_fdi_bc_bifurcation(struct intel_crtc *intel_crtc) +{ + struct drm_device *dev = intel_crtc->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + + switch (intel_crtc->pipe) { + case PIPE_A: + break; + case PIPE_B: + if (intel_crtc->config.fdi_lanes > 2) + WARN_ON(I915_READ(SOUTH_CHICKEN1) & FDI_BC_BIFURCATION_SELECT); + else + cpt_enable_fdi_bc_bifurcation(dev); + + break; + case PIPE_C: + cpt_enable_fdi_bc_bifurcation(dev); + + break; + default: + BUG(); + } +} + /* * Enable PCH resources required for PCH ports: * - PCH PLLs @@ -2997,6 +3040,9 @@ static void ironlake_pch_enable(struct drm_crtc *crtc) assert_pch_transcoder_disabled(dev_priv, pipe); + if (IS_IVYBRIDGE(dev)) + ivybridge_update_fdi_bc_bifurcation(intel_crtc); + /* Write the TU size bits before fdi link training, so that error * detection works. */ I915_WRITE(FDI_RX_TUSIZE1(pipe), @@ -4983,6 +5029,22 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc, if (!(tmp & PIPECONF_ENABLE)) return false; + if (IS_G4X(dev) || IS_VALLEYVIEW(dev)) { + switch (tmp & PIPECONF_BPC_MASK) { + case PIPECONF_6BPC: + pipe_config->pipe_bpp = 18; + break; + case PIPECONF_8BPC: + pipe_config->pipe_bpp = 24; + break; + case PIPECONF_10BPC: + pipe_config->pipe_bpp = 30; + break; + default: + break; + } + } + intel_get_pipe_timings(crtc, pipe_config); i9xx_get_pfit_config(crtc, pipe_config); @@ -5576,48 +5638,6 @@ static bool ironlake_compute_clocks(struct drm_crtc *crtc, return true; } -static void cpt_enable_fdi_bc_bifurcation(struct drm_device *dev) -{ - struct drm_i915_private *dev_priv = dev->dev_private; - uint32_t temp; - - temp = I915_READ(SOUTH_CHICKEN1); - if (temp & FDI_BC_BIFURCATION_SELECT) - return; - - WARN_ON(I915_READ(FDI_RX_CTL(PIPE_B)) & FDI_RX_ENABLE); - WARN_ON(I915_READ(FDI_RX_CTL(PIPE_C)) & FDI_RX_ENABLE); - - temp |= FDI_BC_BIFURCATION_SELECT; - DRM_DEBUG_KMS("enabling fdi C rx\n"); - I915_WRITE(SOUTH_CHICKEN1, temp); - POSTING_READ(SOUTH_CHICKEN1); -} - -static void ivybridge_update_fdi_bc_bifurcation(struct intel_crtc *intel_crtc) -{ - struct drm_device *dev = intel_crtc->base.dev; - struct drm_i915_private *dev_priv = dev->dev_private; - - switch (intel_crtc->pipe) { - case PIPE_A: - break; - case PIPE_B: - if (intel_crtc->config.fdi_lanes > 2) - WARN_ON(I915_READ(SOUTH_CHICKEN1) & FDI_BC_BIFURCATION_SELECT); - else - cpt_enable_fdi_bc_bifurcation(dev); - - break; - case PIPE_C: - cpt_enable_fdi_bc_bifurcation(dev); - - break; - default: - BUG(); - } -} - int ironlake_get_lanes_required(int target_clock, int link_bw, int bpp) { /* @@ -5811,9 +5831,6 @@ static int ironlake_crtc_mode_set(struct drm_crtc *crtc, &intel_crtc->config.fdi_m_n); } - if (IS_IVYBRIDGE(dev)) - ivybridge_update_fdi_bc_bifurcation(intel_crtc); - ironlake_set_pipeconf(crtc); /* Set up the display plane register */ @@ -5881,6 +5898,23 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc, if (!(tmp & PIPECONF_ENABLE)) return false; + switch (tmp & PIPECONF_BPC_MASK) { + case PIPECONF_6BPC: + pipe_config->pipe_bpp = 18; + break; + case PIPECONF_8BPC: + pipe_config->pipe_bpp = 24; + break; + case PIPECONF_10BPC: + pipe_config->pipe_bpp = 30; + break; + case PIPECONF_12BPC: + pipe_config->pipe_bpp = 36; + break; + default: + break; + } + if (I915_READ(PCH_TRANSCONF(crtc->pipe)) & TRANS_ENABLE) { struct intel_shared_dpll *pll; @@ -8612,6 +8646,9 @@ intel_pipe_config_compare(struct drm_device *dev, PIPE_CONF_CHECK_X(dpll_hw_state.fp0); PIPE_CONF_CHECK_X(dpll_hw_state.fp1); + if (IS_G4X(dev) || INTEL_INFO(dev)->gen >= 5) + PIPE_CONF_CHECK_I(pipe_bpp); + #undef PIPE_CONF_CHECK_X #undef PIPE_CONF_CHECK_I #undef PIPE_CONF_CHECK_FLAGS diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 2c555f91bfae..1a431377d83b 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -1401,6 +1401,26 @@ static void intel_dp_get_config(struct intel_encoder *encoder, else pipe_config->port_clock = 270000; } + + if (is_edp(intel_dp) && dev_priv->vbt.edp_bpp && + pipe_config->pipe_bpp > dev_priv->vbt.edp_bpp) { + /* + * This is a big fat ugly hack. + * + * Some machines in UEFI boot mode provide us a VBT that has 18 + * bpp and 1.62 GHz link bandwidth for eDP, which for reasons + * unknown we fail to light up. Yet the same BIOS boots up with + * 24 bpp and 2.7 GHz link. Use the same bpp as the BIOS uses as + * max, not what it tells us to use. + * + * Note: This will still be broken if the eDP panel is not lit + * up by the BIOS, and thus we can't get the mode at module + * load. + */ + DRM_DEBUG_KMS("pipe has %d bpp for eDP panel, overriding BIOS-provided max %d bpp\n", + pipe_config->pipe_bpp, dev_priv->vbt.edp_bpp); + dev_priv->vbt.edp_bpp = pipe_config->pipe_bpp; + } } static bool is_edp_psr(struct intel_dp *intel_dp) diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index 9b7b68fd5d47..7f2b384ac939 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -765,6 +765,8 @@ extern void intel_ddi_prepare_link_retrain(struct drm_encoder *encoder); extern bool intel_ddi_connector_get_hw_state(struct intel_connector *intel_connector); extern void intel_ddi_fdi_disable(struct drm_crtc *crtc); +extern void intel_ddi_get_config(struct intel_encoder *encoder, + struct intel_crtc_config *pipe_config); extern void intel_display_handle_reset(struct drm_device *dev); extern bool intel_set_cpu_fifo_underrun_reporting(struct drm_device *dev, diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index 831a5c021c4b..b8af94a5be39 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -700,6 +700,22 @@ static const struct dmi_system_id intel_no_lvds[] = { }, { .callback = intel_no_lvds_dmi_callback, + .ident = "Intel D410PT", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Intel"), + DMI_MATCH(DMI_BOARD_NAME, "D410PT"), + }, + }, + { + .callback = intel_no_lvds_dmi_callback, + .ident = "Intel D425KT", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Intel"), + DMI_EXACT_MATCH(DMI_BOARD_NAME, "D425KT"), + }, + }, + { + .callback = intel_no_lvds_dmi_callback, .ident = "Intel D510MO", .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "Intel"), diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index f4c5e95b2d6f..26c2ea3e985c 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -4759,7 +4759,9 @@ static void cpt_init_clock_gating(struct drm_device *dev) * gating for the panel power sequencer or it will fail to * start up when no ports are active. */ - I915_WRITE(SOUTH_DSPCLK_GATE_D, PCH_DPLSUNIT_CLOCK_GATE_DISABLE); + I915_WRITE(SOUTH_DSPCLK_GATE_D, PCH_DPLSUNIT_CLOCK_GATE_DISABLE | + PCH_DPLUNIT_CLOCK_GATE_DISABLE | + PCH_CPUNIT_CLOCK_GATE_DISABLE); I915_WRITE(SOUTH_CHICKEN2, I915_READ(SOUTH_CHICKEN2) | DPLS_EDP_PPS_FIX_DIS); /* The below fixes the weird display corruption, a few pixels shifted diff --git a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c index acf667859cb6..701c4c10e08b 100644 --- a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c +++ b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c @@ -664,8 +664,9 @@ static int omap_dmm_probe(struct platform_device *dev) } /* set dma mask for device */ - /* NOTE: this is a workaround for the hwmod not initializing properly */ - dev->dev.coherent_dma_mask = DMA_BIT_MASK(32); + ret = dma_set_coherent_mask(&dev->dev, DMA_BIT_MASK(32)); + if (ret) + goto fail; omap_dmm->dummy_pa = page_to_phys(omap_dmm->dummy_page); diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c index 32923d2f6002..5e891b226acf 100644 --- a/drivers/gpu/drm/radeon/atombios_encoders.c +++ b/drivers/gpu/drm/radeon/atombios_encoders.c @@ -707,24 +707,37 @@ atombios_get_encoder_mode(struct drm_encoder *encoder) switch (connector->connector_type) { case DRM_MODE_CONNECTOR_DVII: case DRM_MODE_CONNECTOR_HDMIB: /* HDMI-B is basically DL-DVI; analog works fine */ - if ((radeon_connector->audio == RADEON_AUDIO_ENABLE) || - (drm_detect_hdmi_monitor(radeon_connector->edid) && - (radeon_connector->audio == RADEON_AUDIO_AUTO))) - return ATOM_ENCODER_MODE_HDMI; - else if (radeon_connector->use_digital) + if (radeon_audio != 0) { + if (radeon_connector->use_digital && + (radeon_connector->audio == RADEON_AUDIO_ENABLE)) + return ATOM_ENCODER_MODE_HDMI; + else if (drm_detect_hdmi_monitor(radeon_connector->edid) && + (radeon_connector->audio == RADEON_AUDIO_AUTO)) + return ATOM_ENCODER_MODE_HDMI; + else if (radeon_connector->use_digital) + return ATOM_ENCODER_MODE_DVI; + else + return ATOM_ENCODER_MODE_CRT; + } else if (radeon_connector->use_digital) { return ATOM_ENCODER_MODE_DVI; - else + } else { return ATOM_ENCODER_MODE_CRT; + } break; case DRM_MODE_CONNECTOR_DVID: case DRM_MODE_CONNECTOR_HDMIA: default: - if ((radeon_connector->audio == RADEON_AUDIO_ENABLE) || - (drm_detect_hdmi_monitor(radeon_connector->edid) && - (radeon_connector->audio == RADEON_AUDIO_AUTO))) - return ATOM_ENCODER_MODE_HDMI; - else + if (radeon_audio != 0) { + if (radeon_connector->audio == RADEON_AUDIO_ENABLE) + return ATOM_ENCODER_MODE_HDMI; + else if (drm_detect_hdmi_monitor(radeon_connector->edid) && + (radeon_connector->audio == RADEON_AUDIO_AUTO)) + return ATOM_ENCODER_MODE_HDMI; + else + return ATOM_ENCODER_MODE_DVI; + } else { return ATOM_ENCODER_MODE_DVI; + } break; case DRM_MODE_CONNECTOR_LVDS: return ATOM_ENCODER_MODE_LVDS; @@ -732,14 +745,19 @@ atombios_get_encoder_mode(struct drm_encoder *encoder) case DRM_MODE_CONNECTOR_DisplayPort: dig_connector = radeon_connector->con_priv; if ((dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_DISPLAYPORT) || - (dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_eDP)) + (dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_eDP)) { return ATOM_ENCODER_MODE_DP; - else if ((radeon_connector->audio == RADEON_AUDIO_ENABLE) || - (drm_detect_hdmi_monitor(radeon_connector->edid) && - (radeon_connector->audio == RADEON_AUDIO_AUTO))) - return ATOM_ENCODER_MODE_HDMI; - else + } else if (radeon_audio != 0) { + if (radeon_connector->audio == RADEON_AUDIO_ENABLE) + return ATOM_ENCODER_MODE_HDMI; + else if (drm_detect_hdmi_monitor(radeon_connector->edid) && + (radeon_connector->audio == RADEON_AUDIO_AUTO)) + return ATOM_ENCODER_MODE_HDMI; + else + return ATOM_ENCODER_MODE_DVI; + } else { return ATOM_ENCODER_MODE_DVI; + } break; case DRM_MODE_CONNECTOR_eDP: return ATOM_ENCODER_MODE_DP; @@ -1655,7 +1673,7 @@ radeon_atom_encoder_dpms_dig(struct drm_encoder *encoder, int mode) * does the same thing and more. */ if ((rdev->family != CHIP_RV710) && (rdev->family != CHIP_RV730) && - (rdev->family != CHIP_RS880)) + (rdev->family != CHIP_RS780) && (rdev->family != CHIP_RS880)) atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE_OUTPUT, 0, 0); } if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(encoder)) && connector) { diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c index b874ccdf52f7..9cd2bc989ac7 100644 --- a/drivers/gpu/drm/radeon/cik.c +++ b/drivers/gpu/drm/radeon/cik.c @@ -1694,6 +1694,7 @@ static int cik_init_microcode(struct radeon_device *rdev) fw_name); release_firmware(rdev->smc_fw); rdev->smc_fw = NULL; + err = 0; } else if (rdev->smc_fw->size != smc_req_size) { printk(KERN_ERR "cik_smc: Bogus length %zu in firmware \"%s\"\n", @@ -3182,6 +3183,7 @@ int cik_ib_test(struct radeon_device *rdev, struct radeon_ring *ring) r = radeon_ib_get(rdev, ring->idx, &ib, NULL, 256); if (r) { DRM_ERROR("radeon: failed to get ib (%d).\n", r); + radeon_scratch_free(rdev, scratch); return r; } ib.ptr[0] = PACKET3(PACKET3_SET_UCONFIG_REG, 1); @@ -3198,6 +3200,8 @@ int cik_ib_test(struct radeon_device *rdev, struct radeon_ring *ring) r = radeon_fence_wait(ib.fence, false); if (r) { DRM_ERROR("radeon: fence wait failed (%d).\n", r); + radeon_scratch_free(rdev, scratch); + radeon_ib_free(rdev, &ib); return r; } for (i = 0; i < rdev->usec_timeout; i++) { diff --git a/drivers/gpu/drm/radeon/dce6_afmt.c b/drivers/gpu/drm/radeon/dce6_afmt.c index 85a69d2ea3d2..9fcd338c0fcf 100644 --- a/drivers/gpu/drm/radeon/dce6_afmt.c +++ b/drivers/gpu/drm/radeon/dce6_afmt.c @@ -113,6 +113,9 @@ void dce6_afmt_write_speaker_allocation(struct drm_encoder *encoder) u8 *sadb; int sad_count; + /* XXX: setting this register causes hangs on some asics */ + return; + if (!dig->afmt->pin) return; diff --git a/drivers/gpu/drm/radeon/evergreen_hdmi.c b/drivers/gpu/drm/radeon/evergreen_hdmi.c index f815c20640bd..57fcc4b16a52 100644 --- a/drivers/gpu/drm/radeon/evergreen_hdmi.c +++ b/drivers/gpu/drm/radeon/evergreen_hdmi.c @@ -67,6 +67,9 @@ static void dce4_afmt_write_speaker_allocation(struct drm_encoder *encoder) u8 *sadb; int sad_count; + /* XXX: setting this register causes hangs on some asics */ + return; + list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) { if (connector->encoder == encoder) radeon_connector = to_radeon_connector(connector); @@ -288,6 +291,7 @@ void evergreen_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode /* fglrx clears sth in AFMT_AUDIO_PACKET_CONTROL2 here */ WREG32(HDMI_ACR_PACKET_CONTROL + offset, + HDMI_ACR_SOURCE | /* select SW CTS value */ HDMI_ACR_AUTO_SEND); /* allow hw to sent ACR packets when required */ evergreen_hdmi_update_ACR(encoder, mode->clock); diff --git a/drivers/gpu/drm/radeon/kv_dpm.c b/drivers/gpu/drm/radeon/kv_dpm.c index 71399065db04..b41905573cd2 100644 --- a/drivers/gpu/drm/radeon/kv_dpm.c +++ b/drivers/gpu/drm/radeon/kv_dpm.c @@ -2635,7 +2635,7 @@ int kv_dpm_init(struct radeon_device *rdev) pi->caps_sclk_ds = true; pi->enable_auto_thermal_throttling = true; pi->disable_nb_ps3_in_battery = false; - pi->bapm_enable = true; + pi->bapm_enable = false; pi->voltage_drop_t = 0; pi->caps_sclk_throttle_low_notification = false; pi->caps_fps = false; /* true? */ diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c index 93c1f9ef5da9..cac2866d79da 100644 --- a/drivers/gpu/drm/radeon/ni.c +++ b/drivers/gpu/drm/radeon/ni.c @@ -804,6 +804,7 @@ int ni_init_microcode(struct radeon_device *rdev) fw_name); release_firmware(rdev->smc_fw); rdev->smc_fw = NULL; + err = 0; } else if (rdev->smc_fw->size != smc_req_size) { printk(KERN_ERR "ni_mc: Bogus length %zu in firmware \"%s\"\n", diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c index 2a1b1876b431..f9be22062df1 100644 --- a/drivers/gpu/drm/radeon/r600.c +++ b/drivers/gpu/drm/radeon/r600.c @@ -2302,6 +2302,7 @@ int r600_init_microcode(struct radeon_device *rdev) fw_name); release_firmware(rdev->smc_fw); rdev->smc_fw = NULL; + err = 0; } else if (rdev->smc_fw->size != smc_req_size) { printk(KERN_ERR "smc: Bogus length %zu in firmware \"%s\"\n", diff --git a/drivers/gpu/drm/radeon/r600_hdmi.c b/drivers/gpu/drm/radeon/r600_hdmi.c index 5b729319f27b..06022e3b9c3b 100644 --- a/drivers/gpu/drm/radeon/r600_hdmi.c +++ b/drivers/gpu/drm/radeon/r600_hdmi.c @@ -309,6 +309,9 @@ static void dce3_2_afmt_write_speaker_allocation(struct drm_encoder *encoder) u8 *sadb; int sad_count; + /* XXX: setting this register causes hangs on some asics */ + return; + list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) { if (connector->encoder == encoder) radeon_connector = to_radeon_connector(connector); diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index a400ac1c4147..24f4960f59ee 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -1272,8 +1272,8 @@ struct radeon_blacklist_clocks struct radeon_clock_and_voltage_limits { u32 sclk; u32 mclk; - u32 vddc; - u32 vddci; + u16 vddc; + u16 vddci; }; struct radeon_clock_array { diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c index 79159b5da05b..64565732cb98 100644 --- a/drivers/gpu/drm/radeon/radeon_connectors.c +++ b/drivers/gpu/drm/radeon/radeon_connectors.c @@ -1658,9 +1658,12 @@ radeon_add_atom_connector(struct drm_device *dev, drm_object_attach_property(&radeon_connector->base.base, rdev->mode_info.underscan_vborder_property, 0); - drm_object_attach_property(&radeon_connector->base.base, - rdev->mode_info.audio_property, - RADEON_AUDIO_DISABLE); + if (radeon_audio != 0) + drm_object_attach_property(&radeon_connector->base.base, + rdev->mode_info.audio_property, + (radeon_audio == 1) ? + RADEON_AUDIO_AUTO : + RADEON_AUDIO_DISABLE); subpixel_order = SubPixelHorizontalRGB; connector->interlace_allowed = true; if (connector_type == DRM_MODE_CONNECTOR_HDMIB) @@ -1754,10 +1757,12 @@ radeon_add_atom_connector(struct drm_device *dev, rdev->mode_info.underscan_vborder_property, 0); } - if (ASIC_IS_DCE2(rdev)) { + if (ASIC_IS_DCE2(rdev) && (radeon_audio != 0)) { drm_object_attach_property(&radeon_connector->base.base, - rdev->mode_info.audio_property, - RADEON_AUDIO_DISABLE); + rdev->mode_info.audio_property, + (radeon_audio == 1) ? + RADEON_AUDIO_AUTO : + RADEON_AUDIO_DISABLE); } if (connector_type == DRM_MODE_CONNECTOR_DVII) { radeon_connector->dac_load_detect = true; @@ -1799,10 +1804,12 @@ radeon_add_atom_connector(struct drm_device *dev, rdev->mode_info.underscan_vborder_property, 0); } - if (ASIC_IS_DCE2(rdev)) { + if (ASIC_IS_DCE2(rdev) && (radeon_audio != 0)) { drm_object_attach_property(&radeon_connector->base.base, - rdev->mode_info.audio_property, - RADEON_AUDIO_DISABLE); + rdev->mode_info.audio_property, + (radeon_audio == 1) ? + RADEON_AUDIO_AUTO : + RADEON_AUDIO_DISABLE); } subpixel_order = SubPixelHorizontalRGB; connector->interlace_allowed = true; @@ -1843,10 +1850,12 @@ radeon_add_atom_connector(struct drm_device *dev, rdev->mode_info.underscan_vborder_property, 0); } - if (ASIC_IS_DCE2(rdev)) { + if (ASIC_IS_DCE2(rdev) && (radeon_audio != 0)) { drm_object_attach_property(&radeon_connector->base.base, - rdev->mode_info.audio_property, - RADEON_AUDIO_DISABLE); + rdev->mode_info.audio_property, + (radeon_audio == 1) ? + RADEON_AUDIO_AUTO : + RADEON_AUDIO_DISABLE); } connector->interlace_allowed = true; /* in theory with a DP to VGA converter... */ diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c index 66c222836631..80285e35bc65 100644 --- a/drivers/gpu/drm/radeon/radeon_cs.c +++ b/drivers/gpu/drm/radeon/radeon_cs.c @@ -85,9 +85,8 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p) VRAM, also but everything into VRAM on AGP cards to avoid image corruptions */ if (p->ring == R600_RING_TYPE_UVD_INDEX && - p->rdev->family < CHIP_PALM && (i == 0 || drm_pci_device_is_agp(p->rdev->ddev))) { - + /* TODO: is this still needed for NI+ ? */ p->relocs[i].lobj.domain = RADEON_GEM_DOMAIN_VRAM; diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c index cdd12dcd988b..9c14a1ba1de4 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.c +++ b/drivers/gpu/drm/radeon/radeon_drv.c @@ -153,7 +153,7 @@ int radeon_benchmarking = 0; int radeon_testing = 0; int radeon_connector_table = 0; int radeon_tv = 1; -int radeon_audio = 1; +int radeon_audio = -1; int radeon_disp_priority = 0; int radeon_hw_i2c = 0; int radeon_pcie_gen2 = -1; @@ -196,7 +196,7 @@ module_param_named(connector_table, radeon_connector_table, int, 0444); MODULE_PARM_DESC(tv, "TV enable (0 = disable)"); module_param_named(tv, radeon_tv, int, 0444); -MODULE_PARM_DESC(audio, "Audio enable (1 = enable)"); +MODULE_PARM_DESC(audio, "Audio enable (-1 = auto, 0 = disable, 1 = enable)"); module_param_named(audio, radeon_audio, int, 0444); MODULE_PARM_DESC(disp_priority, "Display Priority (0 = auto, 1 = normal, 2 = high)"); diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c index 4f2e73f79638..308eff5be1b4 100644 --- a/drivers/gpu/drm/radeon/radeon_uvd.c +++ b/drivers/gpu/drm/radeon/radeon_uvd.c @@ -476,7 +476,8 @@ static int radeon_uvd_cs_reloc(struct radeon_cs_parser *p, return -EINVAL; } - if (p->rdev->family < CHIP_PALM && (cmd == 0 || cmd == 0x3) && + /* TODO: is this still necessary on NI+ ? */ + if ((cmd == 0 || cmd == 0x3) && (start >> 28) != (p->rdev->uvd.gpu_addr >> 28)) { DRM_ERROR("msg/fb buffer %LX-%LX out of 256MB segment!\n", start, end); diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c index d4652af425b8..d96f7cbca0a1 100644 --- a/drivers/gpu/drm/radeon/si.c +++ b/drivers/gpu/drm/radeon/si.c @@ -1681,6 +1681,7 @@ static int si_init_microcode(struct radeon_device *rdev) fw_name); release_firmware(rdev->smc_fw); rdev->smc_fw = NULL; + err = 0; } else if (rdev->smc_fw->size != smc_req_size) { printk(KERN_ERR "si_smc: Bogus length %zu in firmware \"%s\"\n", diff --git a/drivers/gpu/drm/radeon/uvd_v1_0.c b/drivers/gpu/drm/radeon/uvd_v1_0.c index 3100fa9cb52f..7266805d9786 100644 --- a/drivers/gpu/drm/radeon/uvd_v1_0.c +++ b/drivers/gpu/drm/radeon/uvd_v1_0.c @@ -212,8 +212,8 @@ int uvd_v1_0_start(struct radeon_device *rdev) /* enable VCPU clock */ WREG32(UVD_VCPU_CNTL, 1 << 9); - /* enable UMC and NC0 */ - WREG32_P(UVD_LMI_CTRL2, 1 << 13, ~((1 << 8) | (1 << 13))); + /* enable UMC */ + WREG32_P(UVD_LMI_CTRL2, 0, ~(1 << 8)); /* boot up the VCPU */ WREG32(UVD_SOFT_RESET, 0); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 1a90f0a2f7e5..0508f93b9795 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -740,9 +740,17 @@ static void vmw_postclose(struct drm_device *dev, struct vmw_fpriv *vmw_fp; vmw_fp = vmw_fpriv(file_priv); - ttm_object_file_release(&vmw_fp->tfile); - if (vmw_fp->locked_master) + + if (vmw_fp->locked_master) { + struct vmw_master *vmaster = + vmw_master(vmw_fp->locked_master); + + ttm_lock_set_kill(&vmaster->lock, true, SIGTERM); + ttm_vt_unlock(&vmaster->lock); drm_master_put(&vmw_fp->locked_master); + } + + ttm_object_file_release(&vmw_fp->tfile); kfree(vmw_fp); } @@ -925,14 +933,13 @@ static void vmw_master_drop(struct drm_device *dev, vmw_fp->locked_master = drm_master_get(file_priv->master); ret = ttm_vt_lock(&vmaster->lock, false, vmw_fp->tfile); - vmw_execbuf_release_pinned_bo(dev_priv); - if (unlikely((ret != 0))) { DRM_ERROR("Unable to lock TTM at VT switch.\n"); drm_master_put(&vmw_fp->locked_master); } - ttm_lock_set_kill(&vmaster->lock, true, SIGTERM); + ttm_lock_set_kill(&vmaster->lock, false, SIGTERM); + vmw_execbuf_release_pinned_bo(dev_priv); if (!dev_priv->enable_fb) { ret = ttm_bo_evict_mm(&dev_priv->bdev, TTM_PL_VRAM); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c index 0e67cf41065d..37fb4befec82 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c @@ -970,7 +970,7 @@ void vmw_resource_unreserve(struct vmw_resource *res, if (new_backup) res->backup_offset = new_backup_offset; - if (!res->func->may_evict) + if (!res->func->may_evict || res->id == -1) return; write_lock(&dev_priv->resource_lock); diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 5a8c01112a23..e80da62363bc 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -319,7 +319,7 @@ static s32 item_sdata(struct hid_item *item) static int hid_parser_global(struct hid_parser *parser, struct hid_item *item) { - __u32 raw_value; + __s32 raw_value; switch (item->tag) { case HID_GLOBAL_ITEM_TAG_PUSH: @@ -370,10 +370,11 @@ static int hid_parser_global(struct hid_parser *parser, struct hid_item *item) return 0; case HID_GLOBAL_ITEM_TAG_UNIT_EXPONENT: - /* Units exponent negative numbers are given through a - * two's complement. - * See "6.2.2.7 Global Items" for more information. */ - raw_value = item_udata(item); + /* Many devices provide unit exponent as a two's complement + * nibble due to the common misunderstanding of HID + * specification 1.11, 6.2.2.7 Global Items. Attempt to handle + * both this and the standard encoding. */ + raw_value = item_sdata(item); if (!(raw_value & 0xfffffff0)) parser->global.unit_exponent = hid_snto32(raw_value, 4); else @@ -1870,6 +1871,7 @@ static const struct hid_device_id hid_have_special_driver[] = { { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_PRESENTER_8K_BT) }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_NINTENDO, USB_DEVICE_ID_NINTENDO_WIIMOTE) }, + { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_NINTENDO2, USB_DEVICE_ID_NINTENDO_WIIMOTE) }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_NINTENDO, USB_DEVICE_ID_NINTENDO_WIIMOTE2) }, { } }; diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 9cbc7ab07dfa..f0296a50be5f 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -633,6 +633,7 @@ #define USB_DEVICE_ID_NEXTWINDOW_TOUCHSCREEN 0x0003 #define USB_VENDOR_ID_NINTENDO 0x057e +#define USB_VENDOR_ID_NINTENDO2 0x054c #define USB_DEVICE_ID_NINTENDO_WIIMOTE 0x0306 #define USB_DEVICE_ID_NINTENDO_WIIMOTE2 0x0330 @@ -792,6 +793,8 @@ #define USB_DEVICE_ID_SYNAPTICS_COMP_TP 0x0009 #define USB_DEVICE_ID_SYNAPTICS_WTP 0x0010 #define USB_DEVICE_ID_SYNAPTICS_DPAD 0x0013 +#define USB_DEVICE_ID_SYNAPTICS_LTS1 0x0af8 +#define USB_DEVICE_ID_SYNAPTICS_LTS2 0x1d10 #define USB_VENDOR_ID_THINGM 0x27b8 #define USB_DEVICE_ID_BLINK1 0x01ed @@ -919,4 +922,7 @@ #define USB_VENDOR_ID_PRIMAX 0x0461 #define USB_DEVICE_ID_PRIMAX_KEYBOARD 0x4e05 +#define USB_VENDOR_ID_SIS 0x0457 +#define USB_DEVICE_ID_SIS_TS 0x1013 + #endif diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index 8741d953dcc8..d97f2323af57 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -192,6 +192,7 @@ static int hidinput_setkeycode(struct input_dev *dev, return -EINVAL; } + /** * hidinput_calc_abs_res - calculate an absolute axis resolution * @field: the HID report field to calculate resolution for @@ -234,23 +235,17 @@ __s32 hidinput_calc_abs_res(const struct hid_field *field, __u16 code) case ABS_MT_TOOL_Y: case ABS_MT_TOUCH_MAJOR: case ABS_MT_TOUCH_MINOR: - if (field->unit & 0xffffff00) /* Not a length */ - return 0; - unit_exponent += hid_snto32(field->unit >> 4, 4) - 1; - switch (field->unit & 0xf) { - case 0x1: /* If centimeters */ + if (field->unit == 0x11) { /* If centimeters */ /* Convert to millimeters */ unit_exponent += 1; - break; - case 0x3: /* If inches */ + } else if (field->unit == 0x13) { /* If inches */ /* Convert to millimeters */ prev = physical_extents; physical_extents *= 254; if (physical_extents < prev) return 0; unit_exponent -= 1; - break; - default: + } else { return 0; } break; diff --git a/drivers/hid/hid-wiimote-core.c b/drivers/hid/hid-wiimote-core.c index abb20db2b443..1446f526ee8b 100644 --- a/drivers/hid/hid-wiimote-core.c +++ b/drivers/hid/hid-wiimote-core.c @@ -834,7 +834,8 @@ static void wiimote_init_set_type(struct wiimote_data *wdata, goto done; } - if (vendor == USB_VENDOR_ID_NINTENDO) { + if (vendor == USB_VENDOR_ID_NINTENDO || + vendor == USB_VENDOR_ID_NINTENDO2) { if (product == USB_DEVICE_ID_NINTENDO_WIIMOTE) { devtype = WIIMOTE_DEV_GEN10; goto done; @@ -1855,6 +1856,8 @@ static void wiimote_hid_remove(struct hid_device *hdev) static const struct hid_device_id wiimote_hid_devices[] = { { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_NINTENDO, USB_DEVICE_ID_NINTENDO_WIIMOTE) }, + { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_NINTENDO2, + USB_DEVICE_ID_NINTENDO_WIIMOTE) }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_NINTENDO, USB_DEVICE_ID_NINTENDO_WIIMOTE2) }, { } diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c index 07345521f421..3fca3be08337 100644 --- a/drivers/hid/usbhid/hid-quirks.c +++ b/drivers/hid/usbhid/hid-quirks.c @@ -110,6 +110,9 @@ static const struct hid_blacklist { { USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X, HID_QUIRK_MULTI_INPUT }, { USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M610X, HID_QUIRK_MULTI_INPUT }, { USB_VENDOR_ID_NTRIG, USB_DEVICE_ID_NTRIG_DUOSENSE, HID_QUIRK_NO_INIT_REPORTS }, + { USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_LTS1, HID_QUIRK_NO_INIT_REPORTS }, + { USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_LTS2, HID_QUIRK_NO_INIT_REPORTS }, + { USB_VENDOR_ID_SIS, USB_DEVICE_ID_SIS_TS, HID_QUIRK_NO_INIT_REPORTS }, { 0, 0 } }; diff --git a/drivers/iio/frequency/adf4350.c b/drivers/iio/frequency/adf4350.c index a7b30be86ae0..52605c0ea3a6 100644 --- a/drivers/iio/frequency/adf4350.c +++ b/drivers/iio/frequency/adf4350.c @@ -525,8 +525,10 @@ static int adf4350_probe(struct spi_device *spi) } indio_dev = devm_iio_device_alloc(&spi->dev, sizeof(*st)); - if (indio_dev == NULL) - return -ENOMEM; + if (indio_dev == NULL) { + ret = -ENOMEM; + goto error_disable_clk; + } st = iio_priv(indio_dev); diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c index 2710f7245c3b..2db7dcd826b9 100644 --- a/drivers/iio/industrialio-buffer.c +++ b/drivers/iio/industrialio-buffer.c @@ -477,6 +477,9 @@ void iio_disable_all_buffers(struct iio_dev *indio_dev) indio_dev->currentmode = INDIO_DIRECT_MODE; if (indio_dev->setup_ops->postdisable) indio_dev->setup_ops->postdisable(indio_dev); + + if (indio_dev->available_scan_masks == NULL) + kfree(indio_dev->active_scan_mask); } int iio_update_buffers(struct iio_dev *indio_dev, diff --git a/drivers/infiniband/Kconfig b/drivers/infiniband/Kconfig index 5ceda710f516..b84791f03a27 100644 --- a/drivers/infiniband/Kconfig +++ b/drivers/infiniband/Kconfig @@ -31,6 +31,17 @@ config INFINIBAND_USER_ACCESS libibverbs, libibcm and a hardware driver library from <http://www.openfabrics.org/git/>. +config INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING + bool "Experimental and unstable ABI for userspace access to flow steering verbs" + depends on INFINIBAND_USER_ACCESS + depends on STAGING + ---help--- + The final ABI for userspace access to flow steering verbs + has not been defined. To use the current ABI, *WHICH WILL + CHANGE IN THE FUTURE*, say Y here. + + If unsure, say N. + config INFINIBAND_USER_MEM bool depends on INFINIBAND_USER_ACCESS != n diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h index d040b877475f..d8f9c6c272d7 100644 --- a/drivers/infiniband/core/uverbs.h +++ b/drivers/infiniband/core/uverbs.h @@ -217,7 +217,9 @@ IB_UVERBS_DECLARE_CMD(destroy_srq); IB_UVERBS_DECLARE_CMD(create_xsrq); IB_UVERBS_DECLARE_CMD(open_xrcd); IB_UVERBS_DECLARE_CMD(close_xrcd); +#ifdef CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING IB_UVERBS_DECLARE_CMD(create_flow); IB_UVERBS_DECLARE_CMD(destroy_flow); +#endif /* CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING */ #endif /* UVERBS_H */ diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index f2b81b9ee0d6..2f0f01b70e3b 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -54,7 +54,9 @@ static struct uverbs_lock_class qp_lock_class = { .name = "QP-uobj" }; static struct uverbs_lock_class ah_lock_class = { .name = "AH-uobj" }; static struct uverbs_lock_class srq_lock_class = { .name = "SRQ-uobj" }; static struct uverbs_lock_class xrcd_lock_class = { .name = "XRCD-uobj" }; +#ifdef CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING static struct uverbs_lock_class rule_lock_class = { .name = "RULE-uobj" }; +#endif /* CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING */ #define INIT_UDATA(udata, ibuf, obuf, ilen, olen) \ do { \ @@ -2599,6 +2601,7 @@ out_put: return ret ? ret : in_len; } +#ifdef CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING static int kern_spec_to_ib_spec(struct ib_kern_spec *kern_spec, union ib_flow_spec *ib_spec) { @@ -2824,6 +2827,7 @@ ssize_t ib_uverbs_destroy_flow(struct ib_uverbs_file *file, return ret ? ret : in_len; } +#endif /* CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING */ static int __uverbs_create_xsrq(struct ib_uverbs_file *file, struct ib_uverbs_create_xsrq *cmd, diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 75ad86c4abf8..2df31f68ea09 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -115,8 +115,10 @@ static ssize_t (*uverbs_cmd_table[])(struct ib_uverbs_file *file, [IB_USER_VERBS_CMD_CLOSE_XRCD] = ib_uverbs_close_xrcd, [IB_USER_VERBS_CMD_CREATE_XSRQ] = ib_uverbs_create_xsrq, [IB_USER_VERBS_CMD_OPEN_QP] = ib_uverbs_open_qp, +#ifdef CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING [IB_USER_VERBS_CMD_CREATE_FLOW] = ib_uverbs_create_flow, [IB_USER_VERBS_CMD_DESTROY_FLOW] = ib_uverbs_destroy_flow +#endif /* CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING */ }; static void ib_uverbs_add_one(struct ib_device *device); @@ -605,6 +607,7 @@ static ssize_t ib_uverbs_write(struct file *filp, const char __user *buf, if (!(file->device->ib_dev->uverbs_cmd_mask & (1ull << hdr.command))) return -ENOSYS; +#ifdef CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING if (hdr.command >= IB_USER_VERBS_CMD_THRESHOLD) { struct ib_uverbs_cmd_hdr_ex hdr_ex; @@ -621,6 +624,7 @@ static ssize_t ib_uverbs_write(struct file *filp, const char __user *buf, (hdr_ex.out_words + hdr_ex.provider_out_words) * 4); } else { +#endif /* CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING */ if (hdr.in_words * 4 != count) return -EINVAL; @@ -628,7 +632,9 @@ static ssize_t ib_uverbs_write(struct file *filp, const char __user *buf, buf + sizeof(hdr), hdr.in_words * 4, hdr.out_words * 4); +#ifdef CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING } +#endif /* CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING */ } static int ib_uverbs_mmap(struct file *filp, struct vm_area_struct *vma) diff --git a/drivers/infiniband/hw/amso1100/c2_ae.c b/drivers/infiniband/hw/amso1100/c2_ae.c index d5d1929753e4..cedda25232be 100644 --- a/drivers/infiniband/hw/amso1100/c2_ae.c +++ b/drivers/infiniband/hw/amso1100/c2_ae.c @@ -141,7 +141,7 @@ static const char *to_qp_state_str(int state) return "C2_QP_STATE_ERROR"; default: return "<invalid QP state>"; - }; + } } void c2_ae_event(struct c2_dev *c2dev, u32 mq_index) diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index d6c5a73becf4..f0612645de99 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -1691,9 +1691,11 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) ibdev->ib_dev.create_flow = mlx4_ib_create_flow; ibdev->ib_dev.destroy_flow = mlx4_ib_destroy_flow; +#ifdef CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING ibdev->ib_dev.uverbs_cmd_mask |= (1ull << IB_USER_VERBS_CMD_CREATE_FLOW) | (1ull << IB_USER_VERBS_CMD_DESTROY_FLOW); +#endif /* CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING */ } mlx4_ib_alloc_eqs(dev, ibdev); diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 3f831de9a4d8..b1a6cb3a2809 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -164,6 +164,7 @@ int mlx5_vector2eqn(struct mlx5_ib_dev *dev, int vector, int *eqn, int *irqn) static int alloc_comp_eqs(struct mlx5_ib_dev *dev) { struct mlx5_eq_table *table = &dev->mdev.priv.eq_table; + char name[MLX5_MAX_EQ_NAME]; struct mlx5_eq *eq, *n; int ncomp_vec; int nent; @@ -180,11 +181,10 @@ static int alloc_comp_eqs(struct mlx5_ib_dev *dev) goto clean; } - snprintf(eq->name, MLX5_MAX_EQ_NAME, "mlx5_comp%d", i); + snprintf(name, MLX5_MAX_EQ_NAME, "mlx5_comp%d", i); err = mlx5_create_map_eq(&dev->mdev, eq, i + MLX5_EQ_VEC_COMP_BASE, nent, 0, - eq->name, - &dev->mdev.priv.uuari.uars[0]); + name, &dev->mdev.priv.uuari.uars[0]); if (err) { kfree(eq); goto clean; @@ -301,9 +301,8 @@ static int mlx5_ib_query_device(struct ib_device *ibdev, props->max_srq_sge = max_rq_sg - 1; props->max_fast_reg_page_list_len = (unsigned int)-1; props->local_ca_ack_delay = dev->mdev.caps.local_ca_ack_delay; - props->atomic_cap = dev->mdev.caps.flags & MLX5_DEV_CAP_FLAG_ATOMIC ? - IB_ATOMIC_HCA : IB_ATOMIC_NONE; - props->masked_atomic_cap = IB_ATOMIC_HCA; + props->atomic_cap = IB_ATOMIC_NONE; + props->masked_atomic_cap = IB_ATOMIC_NONE; props->max_pkeys = be16_to_cpup((__be16 *)(out_mad->data + 28)); props->max_mcast_grp = 1 << dev->mdev.caps.log_max_mcg; props->max_mcast_qp_attach = dev->mdev.caps.max_qp_mcg; @@ -1006,6 +1005,11 @@ static void mlx5_ib_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event, ibev.device = &ibdev->ib_dev; ibev.element.port_num = port; + if (port < 1 || port > ibdev->num_ports) { + mlx5_ib_warn(ibdev, "warning: event on port %d\n", port); + return; + } + if (ibdev->ib_active) ib_dispatch_event(&ibev); } diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index bd41df95b6f0..3453580b1eb2 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -42,6 +42,10 @@ enum { DEF_CACHE_SIZE = 10, }; +enum { + MLX5_UMR_ALIGN = 2048 +}; + static __be64 *mr_align(__be64 *ptr, int align) { unsigned long mask = align - 1; @@ -61,13 +65,11 @@ static int order2idx(struct mlx5_ib_dev *dev, int order) static int add_keys(struct mlx5_ib_dev *dev, int c, int num) { - struct device *ddev = dev->ib_dev.dma_device; struct mlx5_mr_cache *cache = &dev->cache; struct mlx5_cache_ent *ent = &cache->ent[c]; struct mlx5_create_mkey_mbox_in *in; struct mlx5_ib_mr *mr; int npages = 1 << ent->order; - int size = sizeof(u64) * npages; int err = 0; int i; @@ -83,21 +85,6 @@ static int add_keys(struct mlx5_ib_dev *dev, int c, int num) } mr->order = ent->order; mr->umred = 1; - mr->pas = kmalloc(size + 0x3f, GFP_KERNEL); - if (!mr->pas) { - kfree(mr); - err = -ENOMEM; - goto out; - } - mr->dma = dma_map_single(ddev, mr_align(mr->pas, 0x40), size, - DMA_TO_DEVICE); - if (dma_mapping_error(ddev, mr->dma)) { - kfree(mr->pas); - kfree(mr); - err = -ENOMEM; - goto out; - } - in->seg.status = 1 << 6; in->seg.xlt_oct_size = cpu_to_be32((npages + 1) / 2); in->seg.qpn_mkey7_0 = cpu_to_be32(0xffffff << 8); @@ -108,8 +95,6 @@ static int add_keys(struct mlx5_ib_dev *dev, int c, int num) sizeof(*in)); if (err) { mlx5_ib_warn(dev, "create mkey failed %d\n", err); - dma_unmap_single(ddev, mr->dma, size, DMA_TO_DEVICE); - kfree(mr->pas); kfree(mr); goto out; } @@ -129,11 +114,9 @@ out: static void remove_keys(struct mlx5_ib_dev *dev, int c, int num) { - struct device *ddev = dev->ib_dev.dma_device; struct mlx5_mr_cache *cache = &dev->cache; struct mlx5_cache_ent *ent = &cache->ent[c]; struct mlx5_ib_mr *mr; - int size; int err; int i; @@ -149,14 +132,10 @@ static void remove_keys(struct mlx5_ib_dev *dev, int c, int num) ent->size--; spin_unlock(&ent->lock); err = mlx5_core_destroy_mkey(&dev->mdev, &mr->mmr); - if (err) { + if (err) mlx5_ib_warn(dev, "failed destroy mkey\n"); - } else { - size = ALIGN(sizeof(u64) * (1 << mr->order), 0x40); - dma_unmap_single(ddev, mr->dma, size, DMA_TO_DEVICE); - kfree(mr->pas); + else kfree(mr); - } } } @@ -408,13 +387,12 @@ static void free_cached_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) static void clean_keys(struct mlx5_ib_dev *dev, int c) { - struct device *ddev = dev->ib_dev.dma_device; struct mlx5_mr_cache *cache = &dev->cache; struct mlx5_cache_ent *ent = &cache->ent[c]; struct mlx5_ib_mr *mr; - int size; int err; + cancel_delayed_work(&ent->dwork); while (1) { spin_lock(&ent->lock); if (list_empty(&ent->head)) { @@ -427,14 +405,10 @@ static void clean_keys(struct mlx5_ib_dev *dev, int c) ent->size--; spin_unlock(&ent->lock); err = mlx5_core_destroy_mkey(&dev->mdev, &mr->mmr); - if (err) { + if (err) mlx5_ib_warn(dev, "failed destroy mkey\n"); - } else { - size = ALIGN(sizeof(u64) * (1 << mr->order), 0x40); - dma_unmap_single(ddev, mr->dma, size, DMA_TO_DEVICE); - kfree(mr->pas); + else kfree(mr); - } } } @@ -540,13 +514,15 @@ int mlx5_mr_cache_cleanup(struct mlx5_ib_dev *dev) int i; dev->cache.stopped = 1; - destroy_workqueue(dev->cache.wq); + flush_workqueue(dev->cache.wq); mlx5_mr_cache_debugfs_cleanup(dev); for (i = 0; i < MAX_MR_CACHE_ENTRIES; i++) clean_keys(dev, i); + destroy_workqueue(dev->cache.wq); + return 0; } @@ -675,10 +651,12 @@ static struct mlx5_ib_mr *reg_umr(struct ib_pd *pd, struct ib_umem *umem, int page_shift, int order, int access_flags) { struct mlx5_ib_dev *dev = to_mdev(pd->device); + struct device *ddev = dev->ib_dev.dma_device; struct umr_common *umrc = &dev->umrc; struct ib_send_wr wr, *bad; struct mlx5_ib_mr *mr; struct ib_sge sg; + int size = sizeof(u64) * npages; int err; int i; @@ -697,7 +675,22 @@ static struct mlx5_ib_mr *reg_umr(struct ib_pd *pd, struct ib_umem *umem, if (!mr) return ERR_PTR(-EAGAIN); - mlx5_ib_populate_pas(dev, umem, page_shift, mr_align(mr->pas, 0x40), 1); + mr->pas = kmalloc(size + MLX5_UMR_ALIGN - 1, GFP_KERNEL); + if (!mr->pas) { + err = -ENOMEM; + goto error; + } + + mlx5_ib_populate_pas(dev, umem, page_shift, + mr_align(mr->pas, MLX5_UMR_ALIGN), 1); + + mr->dma = dma_map_single(ddev, mr_align(mr->pas, MLX5_UMR_ALIGN), size, + DMA_TO_DEVICE); + if (dma_mapping_error(ddev, mr->dma)) { + kfree(mr->pas); + err = -ENOMEM; + goto error; + } memset(&wr, 0, sizeof(wr)); wr.wr_id = (u64)(unsigned long)mr; @@ -718,6 +711,9 @@ static struct mlx5_ib_mr *reg_umr(struct ib_pd *pd, struct ib_umem *umem, wait_for_completion(&mr->done); up(&umrc->sem); + dma_unmap_single(ddev, mr->dma, size, DMA_TO_DEVICE); + kfree(mr->pas); + if (mr->status != IB_WC_SUCCESS) { mlx5_ib_warn(dev, "reg umr failed\n"); err = -EFAULT; diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 045f8cdbd303..5659ea880741 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -203,7 +203,7 @@ static int sq_overhead(enum ib_qp_type qp_type) switch (qp_type) { case IB_QPT_XRC_INI: - size = sizeof(struct mlx5_wqe_xrc_seg); + size += sizeof(struct mlx5_wqe_xrc_seg); /* fall through */ case IB_QPT_RC: size += sizeof(struct mlx5_wqe_ctrl_seg) + @@ -211,20 +211,23 @@ static int sq_overhead(enum ib_qp_type qp_type) sizeof(struct mlx5_wqe_raddr_seg); break; + case IB_QPT_XRC_TGT: + return 0; + case IB_QPT_UC: - size = sizeof(struct mlx5_wqe_ctrl_seg) + + size += sizeof(struct mlx5_wqe_ctrl_seg) + sizeof(struct mlx5_wqe_raddr_seg); break; case IB_QPT_UD: case IB_QPT_SMI: case IB_QPT_GSI: - size = sizeof(struct mlx5_wqe_ctrl_seg) + + size += sizeof(struct mlx5_wqe_ctrl_seg) + sizeof(struct mlx5_wqe_datagram_seg); break; case MLX5_IB_QPT_REG_UMR: - size = sizeof(struct mlx5_wqe_ctrl_seg) + + size += sizeof(struct mlx5_wqe_ctrl_seg) + sizeof(struct mlx5_wqe_umr_ctrl_seg) + sizeof(struct mlx5_mkey_seg); break; @@ -270,7 +273,8 @@ static int calc_sq_size(struct mlx5_ib_dev *dev, struct ib_qp_init_attr *attr, return wqe_size; if (wqe_size > dev->mdev.caps.max_sq_desc_sz) { - mlx5_ib_dbg(dev, "\n"); + mlx5_ib_dbg(dev, "wqe_size(%d) > max_sq_desc_sz(%d)\n", + wqe_size, dev->mdev.caps.max_sq_desc_sz); return -EINVAL; } @@ -280,9 +284,15 @@ static int calc_sq_size(struct mlx5_ib_dev *dev, struct ib_qp_init_attr *attr, wq_size = roundup_pow_of_two(attr->cap.max_send_wr * wqe_size); qp->sq.wqe_cnt = wq_size / MLX5_SEND_WQE_BB; + if (qp->sq.wqe_cnt > dev->mdev.caps.max_wqes) { + mlx5_ib_dbg(dev, "wqe count(%d) exceeds limits(%d)\n", + qp->sq.wqe_cnt, dev->mdev.caps.max_wqes); + return -ENOMEM; + } qp->sq.wqe_shift = ilog2(MLX5_SEND_WQE_BB); qp->sq.max_gs = attr->cap.max_send_sge; - qp->sq.max_post = 1 << ilog2(wq_size / wqe_size); + qp->sq.max_post = wq_size / wqe_size; + attr->cap.max_send_wr = qp->sq.max_post; return wq_size; } @@ -1280,6 +1290,11 @@ static enum mlx5_qp_optpar opt_mask[MLX5_QP_NUM_STATE][MLX5_QP_NUM_STATE][MLX5_Q MLX5_QP_OPTPAR_Q_KEY, [MLX5_QP_ST_MLX] = MLX5_QP_OPTPAR_PKEY_INDEX | MLX5_QP_OPTPAR_Q_KEY, + [MLX5_QP_ST_XRC] = MLX5_QP_OPTPAR_ALT_ADDR_PATH | + MLX5_QP_OPTPAR_RRE | + MLX5_QP_OPTPAR_RAE | + MLX5_QP_OPTPAR_RWE | + MLX5_QP_OPTPAR_PKEY_INDEX, }, }, [MLX5_QP_STATE_RTR] = { @@ -1314,6 +1329,11 @@ static enum mlx5_qp_optpar opt_mask[MLX5_QP_NUM_STATE][MLX5_QP_NUM_STATE][MLX5_Q [MLX5_QP_STATE_RTS] = { [MLX5_QP_ST_UD] = MLX5_QP_OPTPAR_Q_KEY, [MLX5_QP_ST_MLX] = MLX5_QP_OPTPAR_Q_KEY, + [MLX5_QP_ST_UC] = MLX5_QP_OPTPAR_RWE, + [MLX5_QP_ST_RC] = MLX5_QP_OPTPAR_RNR_TIMEOUT | + MLX5_QP_OPTPAR_RWE | + MLX5_QP_OPTPAR_RAE | + MLX5_QP_OPTPAR_RRE, }, }, }; @@ -1651,29 +1671,6 @@ static __always_inline void set_raddr_seg(struct mlx5_wqe_raddr_seg *rseg, rseg->reserved = 0; } -static void set_atomic_seg(struct mlx5_wqe_atomic_seg *aseg, struct ib_send_wr *wr) -{ - if (wr->opcode == IB_WR_ATOMIC_CMP_AND_SWP) { - aseg->swap_add = cpu_to_be64(wr->wr.atomic.swap); - aseg->compare = cpu_to_be64(wr->wr.atomic.compare_add); - } else if (wr->opcode == IB_WR_MASKED_ATOMIC_FETCH_AND_ADD) { - aseg->swap_add = cpu_to_be64(wr->wr.atomic.compare_add); - aseg->compare = cpu_to_be64(wr->wr.atomic.compare_add_mask); - } else { - aseg->swap_add = cpu_to_be64(wr->wr.atomic.compare_add); - aseg->compare = 0; - } -} - -static void set_masked_atomic_seg(struct mlx5_wqe_masked_atomic_seg *aseg, - struct ib_send_wr *wr) -{ - aseg->swap_add = cpu_to_be64(wr->wr.atomic.swap); - aseg->swap_add_mask = cpu_to_be64(wr->wr.atomic.swap_mask); - aseg->compare = cpu_to_be64(wr->wr.atomic.compare_add); - aseg->compare_mask = cpu_to_be64(wr->wr.atomic.compare_add_mask); -} - static void set_datagram_seg(struct mlx5_wqe_datagram_seg *dseg, struct ib_send_wr *wr) { @@ -2063,28 +2060,11 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, case IB_WR_ATOMIC_CMP_AND_SWP: case IB_WR_ATOMIC_FETCH_AND_ADD: - set_raddr_seg(seg, wr->wr.atomic.remote_addr, - wr->wr.atomic.rkey); - seg += sizeof(struct mlx5_wqe_raddr_seg); - - set_atomic_seg(seg, wr); - seg += sizeof(struct mlx5_wqe_atomic_seg); - - size += (sizeof(struct mlx5_wqe_raddr_seg) + - sizeof(struct mlx5_wqe_atomic_seg)) / 16; - break; - case IB_WR_MASKED_ATOMIC_CMP_AND_SWP: - set_raddr_seg(seg, wr->wr.atomic.remote_addr, - wr->wr.atomic.rkey); - seg += sizeof(struct mlx5_wqe_raddr_seg); - - set_masked_atomic_seg(seg, wr); - seg += sizeof(struct mlx5_wqe_masked_atomic_seg); - - size += (sizeof(struct mlx5_wqe_raddr_seg) + - sizeof(struct mlx5_wqe_masked_atomic_seg)) / 16; - break; + mlx5_ib_warn(dev, "Atomic operations are not supported yet\n"); + err = -ENOSYS; + *bad_wr = wr; + goto out; case IB_WR_LOCAL_INV: next_fence = MLX5_FENCE_MODE_INITIATOR_SMALL; diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c index 84d297afd6a9..0aa478bc291a 100644 --- a/drivers/infiniband/hw/mlx5/srq.c +++ b/drivers/infiniband/hw/mlx5/srq.c @@ -295,7 +295,7 @@ struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd, mlx5_vfree(in); if (err) { mlx5_ib_dbg(dev, "create SRQ failed, err %d\n", err); - goto err_srq; + goto err_usr_kern_srq; } mlx5_ib_dbg(dev, "create SRQ with srqn 0x%x\n", srq->msrq.srqn); @@ -316,6 +316,8 @@ struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd, err_core: mlx5_core_destroy_srq(&dev->mdev, &srq->msrq); + +err_usr_kern_srq: if (pd->uobject) destroy_srq_user(pd, srq); else diff --git a/drivers/infiniband/hw/mthca/mthca_eq.c b/drivers/infiniband/hw/mthca/mthca_eq.c index 7c9d35f39d75..690201738993 100644 --- a/drivers/infiniband/hw/mthca/mthca_eq.c +++ b/drivers/infiniband/hw/mthca/mthca_eq.c @@ -357,7 +357,7 @@ static int mthca_eq_int(struct mthca_dev *dev, struct mthca_eq *eq) mthca_warn(dev, "Unhandled event %02x(%02x) on EQ %d\n", eqe->type, eqe->subtype, eq->eqn); break; - }; + } set_eqe_hw(eqe); ++eq->cons_index; diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c index 4ed8235d2d36..50219ab2279d 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c @@ -150,7 +150,7 @@ enum ib_qp_state get_ibqp_state(enum ocrdma_qp_state qps) return IB_QPS_SQE; case OCRDMA_QPS_ERR: return IB_QPS_ERR; - }; + } return IB_QPS_ERR; } @@ -171,7 +171,7 @@ static enum ocrdma_qp_state get_ocrdma_qp_state(enum ib_qp_state qps) return OCRDMA_QPS_SQE; case IB_QPS_ERR: return OCRDMA_QPS_ERR; - }; + } return OCRDMA_QPS_ERR; } @@ -1982,7 +1982,7 @@ int ocrdma_mbx_create_qp(struct ocrdma_qp *qp, struct ib_qp_init_attr *attrs, break; default: return -EINVAL; - }; + } cmd = ocrdma_init_emb_mqe(OCRDMA_CMD_CREATE_QP, sizeof(*cmd)); if (!cmd) diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c index 56e004940f18..0ce7674621ea 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_main.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c @@ -531,7 +531,7 @@ static void ocrdma_event_handler(struct ocrdma_dev *dev, u32 event) case BE_DEV_DOWN: ocrdma_close(dev); break; - }; + } } static struct ocrdma_driver ocrdma_drv = { diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c index 6e982bb43c31..69f1d1221a6b 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c @@ -141,7 +141,7 @@ static inline void get_link_speed_and_width(struct ocrdma_dev *dev, /* Unsupported */ *ib_speed = IB_SPEED_SDR; *ib_width = IB_WIDTH_1X; - }; + } } @@ -2331,7 +2331,7 @@ static enum ib_wc_status ocrdma_to_ibwc_err(u16 status) default: ibwc_status = IB_WC_GENERAL_ERR; break; - }; + } return ibwc_status; } @@ -2370,7 +2370,7 @@ static void ocrdma_update_wc(struct ocrdma_qp *qp, struct ib_wc *ibwc, pr_err("%s() invalid opcode received = 0x%x\n", __func__, hdr->cw & OCRDMA_WQE_OPCODE_MASK); break; - }; + } } static void ocrdma_set_cqe_status_flushed(struct ocrdma_qp *qp, diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index 3591855cc5b5..6df23502059a 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -594,7 +594,7 @@ isert_connect_release(struct isert_conn *isert_conn) pr_debug("Entering isert_connect_release(): >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\n"); - if (device->use_frwr) + if (device && device->use_frwr) isert_conn_free_frwr_pool(isert_conn); if (isert_conn->conn_qp) { diff --git a/drivers/input/input.c b/drivers/input/input.c index c04469928925..e75d015024a1 100644 --- a/drivers/input/input.c +++ b/drivers/input/input.c @@ -1734,6 +1734,7 @@ EXPORT_SYMBOL_GPL(input_class); */ struct input_dev *input_allocate_device(void) { + static atomic_t input_no = ATOMIC_INIT(0); struct input_dev *dev; dev = kzalloc(sizeof(struct input_dev), GFP_KERNEL); @@ -1743,9 +1744,13 @@ struct input_dev *input_allocate_device(void) device_initialize(&dev->dev); mutex_init(&dev->mutex); spin_lock_init(&dev->event_lock); + init_timer(&dev->timer); INIT_LIST_HEAD(&dev->h_list); INIT_LIST_HEAD(&dev->node); + dev_set_name(&dev->dev, "input%ld", + (unsigned long) atomic_inc_return(&input_no) - 1); + __module_get(THIS_MODULE); } @@ -2019,7 +2024,6 @@ static void devm_input_device_unregister(struct device *dev, void *res) */ int input_register_device(struct input_dev *dev) { - static atomic_t input_no = ATOMIC_INIT(0); struct input_devres *devres = NULL; struct input_handler *handler; unsigned int packet_size; @@ -2059,7 +2063,6 @@ int input_register_device(struct input_dev *dev) * If delay and period are pre-set by the driver, then autorepeating * is handled by the driver itself and we don't do it in input.c. */ - init_timer(&dev->timer); if (!dev->rep[REP_DELAY] && !dev->rep[REP_PERIOD]) { dev->timer.data = (long) dev; dev->timer.function = input_repeat_key; @@ -2073,9 +2076,6 @@ int input_register_device(struct input_dev *dev) if (!dev->setkeycode) dev->setkeycode = input_default_setkeycode; - dev_set_name(&dev->dev, "input%ld", - (unsigned long) atomic_inc_return(&input_no) - 1); - error = device_add(&dev->dev); if (error) goto err_free_vals; diff --git a/drivers/input/keyboard/pxa27x_keypad.c b/drivers/input/keyboard/pxa27x_keypad.c index 134c3b404a54..a2e758d27584 100644 --- a/drivers/input/keyboard/pxa27x_keypad.c +++ b/drivers/input/keyboard/pxa27x_keypad.c @@ -786,10 +786,17 @@ static int pxa27x_keypad_probe(struct platform_device *pdev) input_dev->evbit[0] = BIT_MASK(EV_KEY) | BIT_MASK(EV_REP); input_set_capability(input_dev, EV_MSC, MSC_SCAN); - if (pdata) + if (pdata) { error = pxa27x_keypad_build_keycode(keypad); - else + } else { error = pxa27x_keypad_build_keycode_from_dt(keypad); + /* + * Data that we get from DT resides in dynamically + * allocated memory so we need to update our pdata + * pointer. + */ + pdata = keypad->pdata; + } if (error) { dev_err(&pdev->dev, "failed to build keycode\n"); goto failed_put_clk; diff --git a/drivers/input/misc/cm109.c b/drivers/input/misc/cm109.c index 082684e7f390..9365535ba7f1 100644 --- a/drivers/input/misc/cm109.c +++ b/drivers/input/misc/cm109.c @@ -351,7 +351,9 @@ static void cm109_urb_irq_callback(struct urb *urb) if (status) { if (status == -ESHUTDOWN) return; - dev_err(&dev->intf->dev, "%s: urb status %d\n", __func__, status); + dev_err_ratelimited(&dev->intf->dev, "%s: urb status %d\n", + __func__, status); + goto out; } /* Special keys */ @@ -418,8 +420,12 @@ static void cm109_urb_ctl_callback(struct urb *urb) dev->ctl_data->byte[2], dev->ctl_data->byte[3]); - if (status) - dev_err(&dev->intf->dev, "%s: urb status %d\n", __func__, status); + if (status) { + if (status == -ESHUTDOWN) + return; + dev_err_ratelimited(&dev->intf->dev, "%s: urb status %d\n", + __func__, status); + } spin_lock(&dev->ctl_submit_lock); @@ -427,7 +433,7 @@ static void cm109_urb_ctl_callback(struct urb *urb) if (likely(!dev->shutdown)) { - if (dev->buzzer_pending) { + if (dev->buzzer_pending || status) { dev->buzzer_pending = 0; dev->ctl_urb_pending = 1; cm109_submit_buzz_toggle(dev); diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c index 7c5d72a6a26a..83658472ad25 100644 --- a/drivers/input/mouse/alps.c +++ b/drivers/input/mouse/alps.c @@ -103,6 +103,7 @@ static const struct alps_model_info alps_model_data[] = { /* Dell Latitude E5500, E6400, E6500, Precision M4400 */ { { 0x62, 0x02, 0x14 }, 0x00, ALPS_PROTO_V2, 0xcf, 0xcf, ALPS_PASS | ALPS_DUALPOINT | ALPS_PS2_INTERLEAVED }, + { { 0x73, 0x00, 0x14 }, 0x00, ALPS_PROTO_V2, 0xcf, 0xcf, ALPS_DUALPOINT }, /* Dell XT2 */ { { 0x73, 0x02, 0x50 }, 0x00, ALPS_PROTO_V2, 0xcf, 0xcf, ALPS_FOUR_BUTTONS }, /* Dell Vostro 1400 */ { { 0x52, 0x01, 0x14 }, 0x00, ALPS_PROTO_V2, 0xff, 0xff, ALPS_PASS | ALPS_DUALPOINT | ALPS_PS2_INTERLEAVED }, /* Toshiba Tecra A11-11L */ diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c index 78e4de42efaa..52c9ebf94729 100644 --- a/drivers/input/serio/i8042.c +++ b/drivers/input/serio/i8042.c @@ -223,21 +223,26 @@ static int i8042_flush(void) { unsigned long flags; unsigned char data, str; - int i = 0; + int count = 0; + int retval = 0; spin_lock_irqsave(&i8042_lock, flags); - while (((str = i8042_read_status()) & I8042_STR_OBF) && (i < I8042_BUFFER_SIZE)) { - udelay(50); - data = i8042_read_data(); - i++; - dbg("%02x <- i8042 (flush, %s)\n", - data, str & I8042_STR_AUXDATA ? "aux" : "kbd"); + while ((str = i8042_read_status()) & I8042_STR_OBF) { + if (count++ < I8042_BUFFER_SIZE) { + udelay(50); + data = i8042_read_data(); + dbg("%02x <- i8042 (flush, %s)\n", + data, str & I8042_STR_AUXDATA ? "aux" : "kbd"); + } else { + retval = -EIO; + break; + } } spin_unlock_irqrestore(&i8042_lock, flags); - return i; + return retval; } /* @@ -849,7 +854,7 @@ static int __init i8042_check_aux(void) static int i8042_controller_check(void) { - if (i8042_flush() == I8042_BUFFER_SIZE) { + if (i8042_flush()) { pr_err("No controller found\n"); return -ENODEV; } diff --git a/drivers/input/tablet/wacom_sys.c b/drivers/input/tablet/wacom_sys.c index 79b69ea47f74..e53416a4d7f3 100644 --- a/drivers/input/tablet/wacom_sys.c +++ b/drivers/input/tablet/wacom_sys.c @@ -1031,6 +1031,7 @@ static void wacom_destroy_leds(struct wacom *wacom) } static enum power_supply_property wacom_battery_props[] = { + POWER_SUPPLY_PROP_SCOPE, POWER_SUPPLY_PROP_CAPACITY }; @@ -1042,6 +1043,9 @@ static int wacom_battery_get_property(struct power_supply *psy, int ret = 0; switch (psp) { + case POWER_SUPPLY_PROP_SCOPE: + val->intval = POWER_SUPPLY_SCOPE_DEVICE; + break; case POWER_SUPPLY_PROP_CAPACITY: val->intval = wacom->wacom_wac.battery_capacity * 100 / 31; diff --git a/drivers/input/tablet/wacom_wac.c b/drivers/input/tablet/wacom_wac.c index b2aa503c16b1..c59b797eeafa 100644 --- a/drivers/input/tablet/wacom_wac.c +++ b/drivers/input/tablet/wacom_wac.c @@ -2054,6 +2054,12 @@ static const struct wacom_features wacom_features_0x101 = static const struct wacom_features wacom_features_0x10D = { "Wacom ISDv4 10D", WACOM_PKGLEN_MTTPC, 26202, 16325, 255, 0, MTTPC, WACOM_INTUOS_RES, WACOM_INTUOS_RES }; +static const struct wacom_features wacom_features_0x10E = + { "Wacom ISDv4 10E", WACOM_PKGLEN_MTTPC, 27760, 15694, 255, + 0, MTTPC, WACOM_INTUOS_RES, WACOM_INTUOS_RES }; +static const struct wacom_features wacom_features_0x10F = + { "Wacom ISDv4 10F", WACOM_PKGLEN_MTTPC, 27760, 15694, 255, + 0, MTTPC, WACOM_INTUOS_RES, WACOM_INTUOS_RES }; static const struct wacom_features wacom_features_0x4001 = { "Wacom ISDv4 4001", WACOM_PKGLEN_MTTPC, 26202, 16325, 255, 0, MTTPC, WACOM_INTUOS_RES, WACOM_INTUOS_RES }; @@ -2248,6 +2254,8 @@ const struct usb_device_id wacom_ids[] = { { USB_DEVICE_WACOM(0x100) }, { USB_DEVICE_WACOM(0x101) }, { USB_DEVICE_WACOM(0x10D) }, + { USB_DEVICE_WACOM(0x10E) }, + { USB_DEVICE_WACOM(0x10F) }, { USB_DEVICE_WACOM(0x300) }, { USB_DEVICE_WACOM(0x301) }, { USB_DEVICE_WACOM(0x304) }, diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c index d0e948084eaf..9031171c141b 100644 --- a/drivers/irqchip/irq-gic.c +++ b/drivers/irqchip/irq-gic.c @@ -253,10 +253,9 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val, if (cpu >= NR_GIC_CPU_IF || cpu >= nr_cpu_ids) return -EINVAL; + raw_spin_lock(&irq_controller_lock); mask = 0xff << shift; bit = gic_cpu_map[cpu] << shift; - - raw_spin_lock(&irq_controller_lock); val = readl_relaxed(reg) & ~mask; writel_relaxed(val | bit, reg); raw_spin_unlock(&irq_controller_lock); @@ -652,7 +651,9 @@ static void __init gic_pm_init(struct gic_chip_data *gic) void gic_raise_softirq(const struct cpumask *mask, unsigned int irq) { int cpu; - unsigned long map = 0; + unsigned long flags, map = 0; + + raw_spin_lock_irqsave(&irq_controller_lock, flags); /* Convert our logical CPU mask into a physical one. */ for_each_cpu(cpu, mask) @@ -666,7 +667,149 @@ void gic_raise_softirq(const struct cpumask *mask, unsigned int irq) /* this always happens on GIC0 */ writel_relaxed(map << 16 | irq, gic_data_dist_base(&gic_data[0]) + GIC_DIST_SOFTINT); + + raw_spin_unlock_irqrestore(&irq_controller_lock, flags); +} +#endif + +#ifdef CONFIG_BL_SWITCHER +/* + * gic_send_sgi - send a SGI directly to given CPU interface number + * + * cpu_id: the ID for the destination CPU interface + * irq: the IPI number to send a SGI for + */ +void gic_send_sgi(unsigned int cpu_id, unsigned int irq) +{ + BUG_ON(cpu_id >= NR_GIC_CPU_IF); + cpu_id = 1 << cpu_id; + /* this always happens on GIC0 */ + writel_relaxed((cpu_id << 16) | irq, gic_data_dist_base(&gic_data[0]) + GIC_DIST_SOFTINT); +} + +/* + * gic_get_cpu_id - get the CPU interface ID for the specified CPU + * + * @cpu: the logical CPU number to get the GIC ID for. + * + * Return the CPU interface ID for the given logical CPU number, + * or -1 if the CPU number is too large or the interface ID is + * unknown (more than one bit set). + */ +int gic_get_cpu_id(unsigned int cpu) +{ + unsigned int cpu_bit; + + if (cpu >= NR_GIC_CPU_IF) + return -1; + cpu_bit = gic_cpu_map[cpu]; + if (cpu_bit & (cpu_bit - 1)) + return -1; + return __ffs(cpu_bit); } + +/* + * gic_migrate_target - migrate IRQs to another CPU interface + * + * @new_cpu_id: the CPU target ID to migrate IRQs to + * + * Migrate all peripheral interrupts with a target matching the current CPU + * to the interface corresponding to @new_cpu_id. The CPU interface mapping + * is also updated. Targets to other CPU interfaces are unchanged. + * This must be called with IRQs locally disabled. + */ +void gic_migrate_target(unsigned int new_cpu_id) +{ + unsigned int cur_cpu_id, gic_irqs, gic_nr = 0; + void __iomem *dist_base; + int i, ror_val, cpu = smp_processor_id(); + u32 val, cur_target_mask, active_mask; + + if (gic_nr >= MAX_GIC_NR) + BUG(); + + dist_base = gic_data_dist_base(&gic_data[gic_nr]); + if (!dist_base) + return; + gic_irqs = gic_data[gic_nr].gic_irqs; + + cur_cpu_id = __ffs(gic_cpu_map[cpu]); + cur_target_mask = 0x01010101 << cur_cpu_id; + ror_val = (cur_cpu_id - new_cpu_id) & 31; + + raw_spin_lock(&irq_controller_lock); + + /* Update the target interface for this logical CPU */ + gic_cpu_map[cpu] = 1 << new_cpu_id; + + /* + * Find all the peripheral interrupts targetting the current + * CPU interface and migrate them to the new CPU interface. + * We skip DIST_TARGET 0 to 7 as they are read-only. + */ + for (i = 8; i < DIV_ROUND_UP(gic_irqs, 4); i++) { + val = readl_relaxed(dist_base + GIC_DIST_TARGET + i * 4); + active_mask = val & cur_target_mask; + if (active_mask) { + val &= ~active_mask; + val |= ror32(active_mask, ror_val); + writel_relaxed(val, dist_base + GIC_DIST_TARGET + i*4); + } + } + + raw_spin_unlock(&irq_controller_lock); + + /* + * Now let's migrate and clear any potential SGIs that might be + * pending for us (cur_cpu_id). Since GIC_DIST_SGI_PENDING_SET + * is a banked register, we can only forward the SGI using + * GIC_DIST_SOFTINT. The original SGI source is lost but Linux + * doesn't use that information anyway. + * + * For the same reason we do not adjust SGI source information + * for previously sent SGIs by us to other CPUs either. + */ + for (i = 0; i < 16; i += 4) { + int j; + val = readl_relaxed(dist_base + GIC_DIST_SGI_PENDING_SET + i); + if (!val) + continue; + writel_relaxed(val, dist_base + GIC_DIST_SGI_PENDING_CLEAR + i); + for (j = i; j < i + 4; j++) { + if (val & 0xff) + writel_relaxed((1 << (new_cpu_id + 16)) | j, + dist_base + GIC_DIST_SOFTINT); + val >>= 8; + } + } +} + +/* + * gic_get_sgir_physaddr - get the physical address for the SGI register + * + * REturn the physical address of the SGI register to be used + * by some early assembly code when the kernel is not yet available. + */ +static unsigned long gic_dist_physaddr; + +unsigned long gic_get_sgir_physaddr(void) +{ + if (!gic_dist_physaddr) + return 0; + return gic_dist_physaddr + GIC_DIST_SOFTINT; +} + +void __init gic_init_physaddr(struct device_node *node) +{ + struct resource res; + if (of_address_to_resource(node, 0, &res) == 0) { + gic_dist_physaddr = res.start; + pr_info("GIC physical location is %#lx\n", gic_dist_physaddr); + } +} + +#else +#define gic_init_physaddr(node) do { } while (0) #endif static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq, @@ -850,6 +993,8 @@ int __init gic_of_init(struct device_node *node, struct device_node *parent) percpu_offset = 0; gic_init_bases(gic_cnt, -1, dist_base, cpu_base, percpu_offset, node); + if (!gic_cnt) + gic_init_physaddr(node); if (parent) { irq = irq_of_parse_and_map(node, 0); diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index b6a74bcbb08f..2a7f0dd6abab 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -1000,7 +1000,7 @@ static void request_write(struct cached_dev *dc, struct search *s) if (bio->bi_rw & REQ_FLUSH) { /* Also need to send a flush to the backing device */ - struct bio *flush = bio_alloc_bioset(0, GFP_NOIO, + struct bio *flush = bio_alloc_bioset(GFP_NOIO, 0, dc->disk.bio_split); flush->bi_rw = WRITE_FLUSH; diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c index 4caa8e6d59d7..2d2b1b7588d7 100644 --- a/drivers/md/dm-snap-persistent.c +++ b/drivers/md/dm-snap-persistent.c @@ -269,6 +269,14 @@ static chunk_t area_location(struct pstore *ps, chunk_t area) return NUM_SNAPSHOT_HDR_CHUNKS + ((ps->exceptions_per_area + 1) * area); } +static void skip_metadata(struct pstore *ps) +{ + uint32_t stride = ps->exceptions_per_area + 1; + chunk_t next_free = ps->next_free; + if (sector_div(next_free, stride) == NUM_SNAPSHOT_HDR_CHUNKS) + ps->next_free++; +} + /* * Read or write a metadata area. Remembering to skip the first * chunk which holds the header. @@ -502,6 +510,8 @@ static int read_exceptions(struct pstore *ps, ps->current_area--; + skip_metadata(ps); + return 0; } @@ -616,8 +626,6 @@ static int persistent_prepare_exception(struct dm_exception_store *store, struct dm_exception *e) { struct pstore *ps = get_info(store); - uint32_t stride; - chunk_t next_free; sector_t size = get_dev_size(dm_snap_cow(store->snap)->bdev); /* Is there enough room ? */ @@ -630,10 +638,8 @@ static int persistent_prepare_exception(struct dm_exception_store *store, * Move onto the next free pending, making sure to take * into account the location of the metadata chunks. */ - stride = (ps->exceptions_per_area + 1); - next_free = ++ps->next_free; - if (sector_div(next_free, stride) == 1) - ps->next_free++; + ps->next_free++; + skip_metadata(ps); atomic_inc(&ps->pending_count); return 0; diff --git a/drivers/md/md.c b/drivers/md/md.c index adf4d7e1d5e1..561a65f82e26 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -8111,6 +8111,7 @@ static int md_set_badblocks(struct badblocks *bb, sector_t s, int sectors, u64 *p; int lo, hi; int rv = 1; + unsigned long flags; if (bb->shift < 0) /* badblocks are disabled */ @@ -8125,7 +8126,7 @@ static int md_set_badblocks(struct badblocks *bb, sector_t s, int sectors, sectors = next - s; } - write_seqlock_irq(&bb->lock); + write_seqlock_irqsave(&bb->lock, flags); p = bb->page; lo = 0; @@ -8241,7 +8242,7 @@ static int md_set_badblocks(struct badblocks *bb, sector_t s, int sectors, bb->changed = 1; if (!acknowledged) bb->unacked_exist = 1; - write_sequnlock_irq(&bb->lock); + write_sequnlock_irqrestore(&bb->lock, flags); return rv; } diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index d60412c7f995..aacf6bf352d8 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1479,6 +1479,7 @@ static int raid1_spare_active(struct mddev *mddev) } } if (rdev + && rdev->recovery_offset == MaxSector && !test_bit(Faulty, &rdev->flags) && !test_and_set_bit(In_sync, &rdev->flags)) { count++; diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index df7b0a06b0ea..73dc8a377522 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1782,6 +1782,7 @@ static int raid10_spare_active(struct mddev *mddev) } sysfs_notify_dirent_safe(tmp->replacement->sysfs_state); } else if (tmp->rdev + && tmp->rdev->recovery_offset == MaxSector && !test_bit(Faulty, &tmp->rdev->flags) && !test_and_set_bit(In_sync, &tmp->rdev->flags)) { count++; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 7ff4f252ca1a..f8b906843926 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -778,6 +778,12 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) bi->bi_io_vec[0].bv_len = STRIPE_SIZE; bi->bi_io_vec[0].bv_offset = 0; bi->bi_size = STRIPE_SIZE; + /* + * If this is discard request, set bi_vcnt 0. We don't + * want to confuse SCSI because SCSI will replace payload + */ + if (rw & REQ_DISCARD) + bi->bi_vcnt = 0; if (rrdev) set_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags); @@ -816,6 +822,12 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) rbi->bi_io_vec[0].bv_len = STRIPE_SIZE; rbi->bi_io_vec[0].bv_offset = 0; rbi->bi_size = STRIPE_SIZE; + /* + * If this is discard request, set bi_vcnt 0. We don't + * want to confuse SCSI because SCSI will replace payload + */ + if (rw & REQ_DISCARD) + rbi->bi_vcnt = 0; if (conf->mddev->gendisk) trace_block_bio_remap(bdev_get_queue(rbi->bi_bdev), rbi, disk_devt(conf->mddev->gendisk), @@ -2910,6 +2922,14 @@ static void handle_stripe_clean_event(struct r5conf *conf, } /* now that discard is done we can proceed with any sync */ clear_bit(STRIPE_DISCARD, &sh->state); + /* + * SCSI discard will change some bio fields and the stripe has + * no updated data, so remove it from hash list and the stripe + * will be reinitialized + */ + spin_lock_irq(&conf->device_lock); + remove_hash(sh); + spin_unlock_irq(&conf->device_lock); if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state)) set_bit(STRIPE_HANDLE, &sh->state); diff --git a/drivers/media/dvb-frontends/tda10071.c b/drivers/media/dvb-frontends/tda10071.c index 2521f7e23018..e79749cfec81 100644 --- a/drivers/media/dvb-frontends/tda10071.c +++ b/drivers/media/dvb-frontends/tda10071.c @@ -912,14 +912,8 @@ static int tda10071_init(struct dvb_frontend *fe) { 0xd5, 0x03, 0x03 }, }; - /* firmware status */ - ret = tda10071_rd_reg(priv, 0x51, &tmp); - if (ret) - goto error; - - if (!tmp) { + if (priv->warm) { /* warm state - wake up device from sleep */ - priv->warm = 1; for (i = 0; i < ARRAY_SIZE(tab); i++) { ret = tda10071_wr_reg_mask(priv, tab[i].reg, @@ -937,7 +931,6 @@ static int tda10071_init(struct dvb_frontend *fe) goto error; } else { /* cold state - try to download firmware */ - priv->warm = 0; /* request the firmware, this will block and timeout */ ret = request_firmware(&fw, fw_file, priv->i2c->dev.parent); diff --git a/drivers/media/i2c/ad9389b.c b/drivers/media/i2c/ad9389b.c index bb0c99d7a4f1..b06a7e54ee0d 100644 --- a/drivers/media/i2c/ad9389b.c +++ b/drivers/media/i2c/ad9389b.c @@ -628,16 +628,13 @@ static int ad9389b_s_stream(struct v4l2_subdev *sd, int enable) static const struct v4l2_dv_timings_cap ad9389b_timings_cap = { .type = V4L2_DV_BT_656_1120, - .bt = { - .max_width = 1920, - .max_height = 1200, - .min_pixelclock = 25000000, - .max_pixelclock = 170000000, - .standards = V4L2_DV_BT_STD_CEA861 | V4L2_DV_BT_STD_DMT | + /* keep this initialization for compatibility with GCC < 4.4.6 */ + .reserved = { 0 }, + V4L2_INIT_BT_TIMINGS(0, 1920, 0, 1200, 25000000, 170000000, + V4L2_DV_BT_STD_CEA861 | V4L2_DV_BT_STD_DMT | V4L2_DV_BT_STD_GTF | V4L2_DV_BT_STD_CVT, - .capabilities = V4L2_DV_BT_CAP_PROGRESSIVE | - V4L2_DV_BT_CAP_REDUCED_BLANKING | V4L2_DV_BT_CAP_CUSTOM, - }, + V4L2_DV_BT_CAP_PROGRESSIVE | V4L2_DV_BT_CAP_REDUCED_BLANKING | + V4L2_DV_BT_CAP_CUSTOM) }; static int ad9389b_s_dv_timings(struct v4l2_subdev *sd, diff --git a/drivers/media/i2c/adv7511.c b/drivers/media/i2c/adv7511.c index 7a576097471f..7c8d971f1f61 100644 --- a/drivers/media/i2c/adv7511.c +++ b/drivers/media/i2c/adv7511.c @@ -119,16 +119,14 @@ static int adv7511_s_clock_freq(struct v4l2_subdev *sd, u32 freq); static const struct v4l2_dv_timings_cap adv7511_timings_cap = { .type = V4L2_DV_BT_656_1120, - .bt = { - .max_width = ADV7511_MAX_WIDTH, - .max_height = ADV7511_MAX_HEIGHT, - .min_pixelclock = ADV7511_MIN_PIXELCLOCK, - .max_pixelclock = ADV7511_MAX_PIXELCLOCK, - .standards = V4L2_DV_BT_STD_CEA861 | V4L2_DV_BT_STD_DMT | + /* keep this initialization for compatibility with GCC < 4.4.6 */ + .reserved = { 0 }, + V4L2_INIT_BT_TIMINGS(0, ADV7511_MAX_WIDTH, 0, ADV7511_MAX_HEIGHT, + ADV7511_MIN_PIXELCLOCK, ADV7511_MAX_PIXELCLOCK, + V4L2_DV_BT_STD_CEA861 | V4L2_DV_BT_STD_DMT | V4L2_DV_BT_STD_GTF | V4L2_DV_BT_STD_CVT, - .capabilities = V4L2_DV_BT_CAP_PROGRESSIVE | - V4L2_DV_BT_CAP_REDUCED_BLANKING | V4L2_DV_BT_CAP_CUSTOM, - }, + V4L2_DV_BT_CAP_PROGRESSIVE | V4L2_DV_BT_CAP_REDUCED_BLANKING | + V4L2_DV_BT_CAP_CUSTOM) }; static inline struct adv7511_state *get_adv7511_state(struct v4l2_subdev *sd) @@ -1126,6 +1124,7 @@ static int adv7511_probe(struct i2c_client *client, const struct i2c_device_id * state->i2c_edid = i2c_new_dummy(client->adapter, state->i2c_edid_addr >> 1); if (state->i2c_edid == NULL) { v4l2_err(sd, "failed to register edid i2c client\n"); + err = -ENOMEM; goto err_entity; } @@ -1133,6 +1132,7 @@ static int adv7511_probe(struct i2c_client *client, const struct i2c_device_id * state->work_queue = create_singlethread_workqueue(sd->name); if (state->work_queue == NULL) { v4l2_err(sd, "could not create workqueue\n"); + err = -ENOMEM; goto err_unreg_cec; } diff --git a/drivers/media/i2c/adv7842.c b/drivers/media/i2c/adv7842.c index d1748901337c..22f729d66a96 100644 --- a/drivers/media/i2c/adv7842.c +++ b/drivers/media/i2c/adv7842.c @@ -546,30 +546,24 @@ static inline bool is_digital_input(struct v4l2_subdev *sd) static const struct v4l2_dv_timings_cap adv7842_timings_cap_analog = { .type = V4L2_DV_BT_656_1120, - .bt = { - .max_width = 1920, - .max_height = 1200, - .min_pixelclock = 25000000, - .max_pixelclock = 170000000, - .standards = V4L2_DV_BT_STD_CEA861 | V4L2_DV_BT_STD_DMT | + /* keep this initialization for compatibility with GCC < 4.4.6 */ + .reserved = { 0 }, + V4L2_INIT_BT_TIMINGS(0, 1920, 0, 1200, 25000000, 170000000, + V4L2_DV_BT_STD_CEA861 | V4L2_DV_BT_STD_DMT | V4L2_DV_BT_STD_GTF | V4L2_DV_BT_STD_CVT, - .capabilities = V4L2_DV_BT_CAP_PROGRESSIVE | - V4L2_DV_BT_CAP_REDUCED_BLANKING | V4L2_DV_BT_CAP_CUSTOM, - }, + V4L2_DV_BT_CAP_PROGRESSIVE | V4L2_DV_BT_CAP_REDUCED_BLANKING | + V4L2_DV_BT_CAP_CUSTOM) }; static const struct v4l2_dv_timings_cap adv7842_timings_cap_digital = { .type = V4L2_DV_BT_656_1120, - .bt = { - .max_width = 1920, - .max_height = 1200, - .min_pixelclock = 25000000, - .max_pixelclock = 225000000, - .standards = V4L2_DV_BT_STD_CEA861 | V4L2_DV_BT_STD_DMT | + /* keep this initialization for compatibility with GCC < 4.4.6 */ + .reserved = { 0 }, + V4L2_INIT_BT_TIMINGS(0, 1920, 0, 1200, 25000000, 225000000, + V4L2_DV_BT_STD_CEA861 | V4L2_DV_BT_STD_DMT | V4L2_DV_BT_STD_GTF | V4L2_DV_BT_STD_CVT, - .capabilities = V4L2_DV_BT_CAP_PROGRESSIVE | - V4L2_DV_BT_CAP_REDUCED_BLANKING | V4L2_DV_BT_CAP_CUSTOM, - }, + V4L2_DV_BT_CAP_PROGRESSIVE | V4L2_DV_BT_CAP_REDUCED_BLANKING | + V4L2_DV_BT_CAP_CUSTOM) }; static inline const struct v4l2_dv_timings_cap * diff --git a/drivers/media/i2c/ths8200.c b/drivers/media/i2c/ths8200.c index a58a8f663ffb..d9f65d7e3e58 100644 --- a/drivers/media/i2c/ths8200.c +++ b/drivers/media/i2c/ths8200.c @@ -46,14 +46,10 @@ struct ths8200_state { static const struct v4l2_dv_timings_cap ths8200_timings_cap = { .type = V4L2_DV_BT_656_1120, - .bt = { - .max_width = 1920, - .max_height = 1080, - .min_pixelclock = 25000000, - .max_pixelclock = 148500000, - .standards = V4L2_DV_BT_STD_CEA861, - .capabilities = V4L2_DV_BT_CAP_PROGRESSIVE, - }, + /* keep this initialization for compatibility with GCC < 4.4.6 */ + .reserved = { 0 }, + V4L2_INIT_BT_TIMINGS(0, 1920, 0, 1080, 25000000, 148500000, + V4L2_DV_BT_STD_CEA861, V4L2_DV_BT_CAP_PROGRESSIVE) }; static inline struct ths8200_state *to_state(struct v4l2_subdev *sd) diff --git a/drivers/media/pci/saa7134/saa7134-video.c b/drivers/media/pci/saa7134/saa7134-video.c index e12bbd8c3f0b..fb60da85bc2c 100644 --- a/drivers/media/pci/saa7134/saa7134-video.c +++ b/drivers/media/pci/saa7134/saa7134-video.c @@ -1455,6 +1455,7 @@ static int video_release(struct file *file) /* stop video capture */ if (res_check(fh, RESOURCE_VIDEO)) { + pm_qos_remove_request(&dev->qos_request); videobuf_streamoff(&fh->cap); res_free(dev,fh,RESOURCE_VIDEO); } diff --git a/drivers/media/platform/omap3isp/isp.c b/drivers/media/platform/omap3isp/isp.c index df3a0ec7fd2c..1c3608039663 100644 --- a/drivers/media/platform/omap3isp/isp.c +++ b/drivers/media/platform/omap3isp/isp.c @@ -2182,9 +2182,9 @@ static int isp_probe(struct platform_device *pdev) isp->pdata = pdata; isp->ref_count = 0; - isp->raw_dmamask = DMA_BIT_MASK(32); - isp->dev->dma_mask = &isp->raw_dmamask; - isp->dev->coherent_dma_mask = DMA_BIT_MASK(32); + ret = dma_coerce_mask_and_coherent(isp->dev, DMA_BIT_MASK(32)); + if (ret) + return ret; platform_set_drvdata(pdev, isp); diff --git a/drivers/media/platform/omap3isp/isp.h b/drivers/media/platform/omap3isp/isp.h index cd3eff45ae7d..ce65d3ae1aa7 100644 --- a/drivers/media/platform/omap3isp/isp.h +++ b/drivers/media/platform/omap3isp/isp.h @@ -152,7 +152,6 @@ struct isp_xclk { * @mmio_base_phys: Array with physical L4 bus addresses for ISP register * regions. * @mmio_size: Array with ISP register regions size in bytes. - * @raw_dmamask: Raw DMA mask * @stat_lock: Spinlock for handling statistics * @isp_mutex: Mutex for serializing requests to ISP. * @crashed: Bitmask of crashed entities (indexed by entity ID) @@ -190,8 +189,6 @@ struct isp_device { unsigned long mmio_base_phys[OMAP3_ISP_IOMEM_LAST]; resource_size_t mmio_size[OMAP3_ISP_IOMEM_LAST]; - u64 raw_dmamask; - /* ISP Obj */ spinlock_t stat_lock; /* common lock for statistic drivers */ struct mutex isp_mutex; /* For handling ref_count field */ diff --git a/drivers/media/platform/s5p-jpeg/jpeg-core.c b/drivers/media/platform/s5p-jpeg/jpeg-core.c index 15d23968d1de..9b88a4601007 100644 --- a/drivers/media/platform/s5p-jpeg/jpeg-core.c +++ b/drivers/media/platform/s5p-jpeg/jpeg-core.c @@ -1423,6 +1423,7 @@ static int s5p_jpeg_probe(struct platform_device *pdev) jpeg->vfd_decoder->release = video_device_release; jpeg->vfd_decoder->lock = &jpeg->lock; jpeg->vfd_decoder->v4l2_dev = &jpeg->v4l2_dev; + jpeg->vfd_decoder->vfl_dir = VFL_DIR_M2M; ret = video_register_device(jpeg->vfd_decoder, VFL_TYPE_GRABBER, -1); if (ret) { diff --git a/drivers/media/platform/sh_vou.c b/drivers/media/platform/sh_vou.c index 7a9c5e9329f2..4f30341dc2ab 100644 --- a/drivers/media/platform/sh_vou.c +++ b/drivers/media/platform/sh_vou.c @@ -776,7 +776,7 @@ static int sh_vou_try_fmt_vid_out(struct file *file, void *priv, v4l_bound_align_image(&pix->width, 0, VOU_MAX_IMAGE_WIDTH, 1, &pix->height, 0, VOU_MAX_IMAGE_HEIGHT, 1, 0); - for (i = 0; ARRAY_SIZE(vou_fmt); i++) + for (i = 0; i < ARRAY_SIZE(vou_fmt); i++) if (vou_fmt[i].pfmt == pix->pixelformat) return 0; diff --git a/drivers/media/platform/soc_camera/mx3_camera.c b/drivers/media/platform/soc_camera/mx3_camera.c index 8f9f6211c52e..f975b7008692 100644 --- a/drivers/media/platform/soc_camera/mx3_camera.c +++ b/drivers/media/platform/soc_camera/mx3_camera.c @@ -266,7 +266,6 @@ static void mx3_videobuf_queue(struct vb2_buffer *vb) struct idmac_channel *ichan = mx3_cam->idmac_channel[0]; struct idmac_video_param *video = &ichan->params.video; const struct soc_mbus_pixelfmt *host_fmt = icd->current_fmt->host_fmt; - unsigned long flags; dma_cookie_t cookie; size_t new_size; @@ -328,7 +327,7 @@ static void mx3_videobuf_queue(struct vb2_buffer *vb) memset(vb2_plane_vaddr(vb, 0), 0xaa, vb2_get_plane_payload(vb, 0)); #endif - spin_lock_irqsave(&mx3_cam->lock, flags); + spin_lock_irq(&mx3_cam->lock); list_add_tail(&buf->queue, &mx3_cam->capture); if (!mx3_cam->active) @@ -351,7 +350,7 @@ static void mx3_videobuf_queue(struct vb2_buffer *vb) if (mx3_cam->active == buf) mx3_cam->active = NULL; - spin_unlock_irqrestore(&mx3_cam->lock, flags); + spin_unlock_irq(&mx3_cam->lock); error: vb2_buffer_done(vb, VB2_BUF_STATE_ERROR); } diff --git a/drivers/media/tuners/e4000.c b/drivers/media/tuners/e4000.c index ad9309da4a91..6c96e4898777 100644 --- a/drivers/media/tuners/e4000.c +++ b/drivers/media/tuners/e4000.c @@ -19,6 +19,7 @@ */ #include "e4000_priv.h" +#include <linux/math64.h> /* write multiple registers */ static int e4000_wr_regs(struct e4000_priv *priv, u8 reg, u8 *val, int len) @@ -233,7 +234,7 @@ static int e4000_set_params(struct dvb_frontend *fe) * or more. */ f_vco = c->frequency * e4000_pll_lut[i].mul; - sigma_delta = 0x10000UL * (f_vco % priv->cfg->clock) / priv->cfg->clock; + sigma_delta = div_u64(0x10000ULL * (f_vco % priv->cfg->clock), priv->cfg->clock); buf[0] = f_vco / priv->cfg->clock; buf[1] = (sigma_delta >> 0) & 0xff; buf[2] = (sigma_delta >> 8) & 0xff; diff --git a/drivers/media/usb/stkwebcam/stk-webcam.c b/drivers/media/usb/stkwebcam/stk-webcam.c index c43c8d32be40..be77482c3070 100644 --- a/drivers/media/usb/stkwebcam/stk-webcam.c +++ b/drivers/media/usb/stkwebcam/stk-webcam.c @@ -111,6 +111,13 @@ static const struct dmi_system_id stk_upside_down_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "F3JC") } }, + { + .ident = "T12Rg-H", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "HCL Infosystems Limited"), + DMI_MATCH(DMI_PRODUCT_NAME, "T12Rg-H") + } + }, {} }; diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c index 81695d48c13e..c3bb2502225b 100644 --- a/drivers/media/usb/uvc/uvc_driver.c +++ b/drivers/media/usb/uvc/uvc_driver.c @@ -2090,6 +2090,15 @@ static struct usb_device_id uvc_ids[] = { .bInterfaceSubClass = 1, .bInterfaceProtocol = 0, .driver_info = UVC_QUIRK_PROBE_MINMAX }, + /* Microsoft Lifecam NX-3000 */ + { .match_flags = USB_DEVICE_ID_MATCH_DEVICE + | USB_DEVICE_ID_MATCH_INT_INFO, + .idVendor = 0x045e, + .idProduct = 0x0721, + .bInterfaceClass = USB_CLASS_VIDEO, + .bInterfaceSubClass = 1, + .bInterfaceProtocol = 0, + .driver_info = UVC_QUIRK_PROBE_DEF }, /* Microsoft Lifecam VX-7000 */ { .match_flags = USB_DEVICE_ID_MATCH_DEVICE | USB_DEVICE_ID_MATCH_INT_INFO, @@ -2174,6 +2183,15 @@ static struct usb_device_id uvc_ids[] = { .bInterfaceSubClass = 1, .bInterfaceProtocol = 0, .driver_info = UVC_QUIRK_PROBE_DEF }, + /* Dell SP2008WFP Monitor */ + { .match_flags = USB_DEVICE_ID_MATCH_DEVICE + | USB_DEVICE_ID_MATCH_INT_INFO, + .idVendor = 0x05a9, + .idProduct = 0x2641, + .bInterfaceClass = USB_CLASS_VIDEO, + .bInterfaceSubClass = 1, + .bInterfaceProtocol = 0, + .driver_info = UVC_QUIRK_PROBE_DEF }, /* Dell Alienware X51 */ { .match_flags = USB_DEVICE_ID_MATCH_DEVICE | USB_DEVICE_ID_MATCH_INT_INFO, diff --git a/drivers/media/v4l2-core/videobuf2-core.c b/drivers/media/v4l2-core/videobuf2-core.c index 594c75eab5a5..de0e87f0b2c3 100644 --- a/drivers/media/v4l2-core/videobuf2-core.c +++ b/drivers/media/v4l2-core/videobuf2-core.c @@ -353,7 +353,9 @@ static int __verify_length(struct vb2_buffer *vb, const struct v4l2_buffer *b) if (b->m.planes[plane].bytesused > length) return -EINVAL; - if (b->m.planes[plane].data_offset >= + + if (b->m.planes[plane].data_offset > 0 && + b->m.planes[plane].data_offset >= b->m.planes[plane].bytesused) return -EINVAL; } diff --git a/drivers/media/v4l2-core/videobuf2-dma-contig.c b/drivers/media/v4l2-core/videobuf2-dma-contig.c index fd56f2563201..646f08f4f504 100644 --- a/drivers/media/v4l2-core/videobuf2-dma-contig.c +++ b/drivers/media/v4l2-core/videobuf2-dma-contig.c @@ -423,6 +423,39 @@ static inline int vma_is_io(struct vm_area_struct *vma) return !!(vma->vm_flags & (VM_IO | VM_PFNMAP)); } +static int vb2_dc_get_user_pfn(unsigned long start, int n_pages, + struct vm_area_struct *vma, unsigned long *res) +{ + unsigned long pfn, start_pfn, prev_pfn; + unsigned int i; + int ret; + + if (!vma_is_io(vma)) + return -EFAULT; + + ret = follow_pfn(vma, start, &pfn); + if (ret) + return ret; + + start_pfn = pfn; + start += PAGE_SIZE; + + for (i = 1; i < n_pages; ++i, start += PAGE_SIZE) { + prev_pfn = pfn; + ret = follow_pfn(vma, start, &pfn); + + if (ret) { + pr_err("no page for address %lu\n", start); + return ret; + } + if (pfn != prev_pfn + 1) + return -EINVAL; + } + + *res = start_pfn; + return 0; +} + static int vb2_dc_get_user_pages(unsigned long start, struct page **pages, int n_pages, struct vm_area_struct *vma, int write) { @@ -433,6 +466,9 @@ static int vb2_dc_get_user_pages(unsigned long start, struct page **pages, unsigned long pfn; int ret = follow_pfn(vma, start, &pfn); + if (!pfn_valid(pfn)) + return -EINVAL; + if (ret) { pr_err("no page for address %lu\n", start); return ret; @@ -468,16 +504,49 @@ static void vb2_dc_put_userptr(void *buf_priv) struct vb2_dc_buf *buf = buf_priv; struct sg_table *sgt = buf->dma_sgt; - dma_unmap_sg(buf->dev, sgt->sgl, sgt->orig_nents, buf->dma_dir); - if (!vma_is_io(buf->vma)) - vb2_dc_sgt_foreach_page(sgt, vb2_dc_put_dirty_page); + if (sgt) { + dma_unmap_sg(buf->dev, sgt->sgl, sgt->orig_nents, buf->dma_dir); + if (!vma_is_io(buf->vma)) + vb2_dc_sgt_foreach_page(sgt, vb2_dc_put_dirty_page); - sg_free_table(sgt); - kfree(sgt); + sg_free_table(sgt); + kfree(sgt); + } vb2_put_vma(buf->vma); kfree(buf); } +/* + * For some kind of reserved memory there might be no struct page available, + * so all that can be done to support such 'pages' is to try to convert + * pfn to dma address or at the last resort just assume that + * dma address == physical address (like it has been assumed in earlier version + * of videobuf2-dma-contig + */ + +#ifdef __arch_pfn_to_dma +static inline dma_addr_t vb2_dc_pfn_to_dma(struct device *dev, unsigned long pfn) +{ + return (dma_addr_t)__arch_pfn_to_dma(dev, pfn); +} +#elif defined(__pfn_to_bus) +static inline dma_addr_t vb2_dc_pfn_to_dma(struct device *dev, unsigned long pfn) +{ + return (dma_addr_t)__pfn_to_bus(pfn); +} +#elif defined(__pfn_to_phys) +static inline dma_addr_t vb2_dc_pfn_to_dma(struct device *dev, unsigned long pfn) +{ + return (dma_addr_t)__pfn_to_phys(pfn); +} +#else +static inline dma_addr_t vb2_dc_pfn_to_dma(struct device *dev, unsigned long pfn) +{ + /* really, we cannot do anything better at this point */ + return (dma_addr_t)(pfn) << PAGE_SHIFT; +} +#endif + static void *vb2_dc_get_userptr(void *alloc_ctx, unsigned long vaddr, unsigned long size, int write) { @@ -548,6 +617,14 @@ static void *vb2_dc_get_userptr(void *alloc_ctx, unsigned long vaddr, /* extract page list from userspace mapping */ ret = vb2_dc_get_user_pages(start, pages, n_pages, vma, write); if (ret) { + unsigned long pfn; + if (vb2_dc_get_user_pfn(start, n_pages, vma, &pfn) == 0) { + buf->dma_addr = vb2_dc_pfn_to_dma(buf->dev, pfn); + buf->size = size; + kfree(pages); + return buf; + } + pr_err("failed to get user pages\n"); goto fail_vma; } diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c index fa9632eb63f1..357bbc54fe4b 100644 --- a/drivers/mmc/card/queue.c +++ b/drivers/mmc/card/queue.c @@ -15,6 +15,7 @@ #include <linux/freezer.h> #include <linux/kthread.h> #include <linux/scatterlist.h> +#include <linux/dma-mapping.h> #include <linux/mmc/card.h> #include <linux/mmc/host.h> @@ -196,7 +197,7 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, struct mmc_queue_req *mqrq_prev = &mq->mqrq[1]; if (mmc_dev(host)->dma_mask && *mmc_dev(host)->dma_mask) - limit = *mmc_dev(host)->dma_mask; + limit = dma_max_pfn(mmc_dev(host)) << PAGE_SHIFT; mq->card = card; mq->queue = blk_init_queue(mmc_request_fn, lock); diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c index c3785edc0e92..d135c76c4855 100644 --- a/drivers/mmc/host/mmci.c +++ b/drivers/mmc/host/mmci.c @@ -62,6 +62,7 @@ static unsigned int fmax = 515633; * @signal_direction: input/out direction of bus signals can be indicated * @pwrreg_clkgate: MMCIPOWER register must be used to gate the clock * @busy_detect: true if busy detection on dat0 is supported + * @pwrreg_nopower: bits in MMCIPOWER don't controls ext. power supply */ struct variant_data { unsigned int clkreg; @@ -76,6 +77,7 @@ struct variant_data { bool signal_direction; bool pwrreg_clkgate; bool busy_detect; + bool pwrreg_nopower; }; static struct variant_data variant_arm = { @@ -109,6 +111,7 @@ static struct variant_data variant_u300 = { .pwrreg_powerup = MCI_PWR_ON, .signal_direction = true, .pwrreg_clkgate = true, + .pwrreg_nopower = true, }; static struct variant_data variant_nomadik = { @@ -121,6 +124,7 @@ static struct variant_data variant_nomadik = { .pwrreg_powerup = MCI_PWR_ON, .signal_direction = true, .pwrreg_clkgate = true, + .pwrreg_nopower = true, }; static struct variant_data variant_ux500 = { @@ -135,6 +139,7 @@ static struct variant_data variant_ux500 = { .signal_direction = true, .pwrreg_clkgate = true, .busy_detect = true, + .pwrreg_nopower = true, }; static struct variant_data variant_ux500v2 = { @@ -150,6 +155,7 @@ static struct variant_data variant_ux500v2 = { .signal_direction = true, .pwrreg_clkgate = true, .busy_detect = true, + .pwrreg_nopower = true, }; static int mmci_card_busy(struct mmc_host *mmc) @@ -189,6 +195,21 @@ static int mmci_validate_data(struct mmci_host *host, return 0; } +static void mmci_reg_delay(struct mmci_host *host) +{ + /* + * According to the spec, at least three feedback clock cycles + * of max 52 MHz must pass between two writes to the MMCICLOCK reg. + * Three MCLK clock cycles must pass between two MMCIPOWER reg writes. + * Worst delay time during card init is at 100 kHz => 30 us. + * Worst delay time when up and running is at 25 MHz => 120 ns. + */ + if (host->cclk < 25000000) + udelay(30); + else + ndelay(120); +} + /* * This must be called with host->lock held */ @@ -1264,6 +1285,7 @@ static void mmci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) mmci_set_clkreg(host, ios->clock); mmci_write_pwrreg(host, pwr); + mmci_reg_delay(host); spin_unlock_irqrestore(&host->lock, flags); @@ -1510,23 +1532,6 @@ static int mmci_probe(struct amba_device *dev, mmc->f_max = min(host->mclk, fmax); dev_dbg(mmc_dev(mmc), "clocking block at %u Hz\n", mmc->f_max); - host->pinctrl = devm_pinctrl_get(&dev->dev); - if (IS_ERR(host->pinctrl)) { - ret = PTR_ERR(host->pinctrl); - goto clk_disable; - } - - host->pins_default = pinctrl_lookup_state(host->pinctrl, - PINCTRL_STATE_DEFAULT); - - /* enable pins to be muxed in and configured */ - if (!IS_ERR(host->pins_default)) { - ret = pinctrl_select_state(host->pinctrl, host->pins_default); - if (ret) - dev_warn(&dev->dev, "could not set default pins\n"); - } else - dev_warn(&dev->dev, "could not get default pinstate\n"); - /* Get regulators and the supported OCR mask */ mmc_regulator_get_supply(mmc); if (!mmc->ocr_avail) @@ -1760,6 +1765,41 @@ static int mmci_resume(struct device *dev) #endif #ifdef CONFIG_PM_RUNTIME +static void mmci_save(struct mmci_host *host) +{ + unsigned long flags; + + if (host->variant->pwrreg_nopower) { + spin_lock_irqsave(&host->lock, flags); + + writel(0, host->base + MMCIMASK0); + writel(0, host->base + MMCIDATACTRL); + writel(0, host->base + MMCIPOWER); + writel(0, host->base + MMCICLOCK); + mmci_reg_delay(host); + + spin_unlock_irqrestore(&host->lock, flags); + } + +} + +static void mmci_restore(struct mmci_host *host) +{ + unsigned long flags; + + if (host->variant->pwrreg_nopower) { + spin_lock_irqsave(&host->lock, flags); + + writel(host->clk_reg, host->base + MMCICLOCK); + writel(host->datactrl_reg, host->base + MMCIDATACTRL); + writel(host->pwr_reg, host->base + MMCIPOWER); + writel(MCI_IRQENABLE, host->base + MMCIMASK0); + mmci_reg_delay(host); + + spin_unlock_irqrestore(&host->lock, flags); + } +} + static int mmci_runtime_suspend(struct device *dev) { struct amba_device *adev = to_amba_device(dev); @@ -1767,6 +1807,8 @@ static int mmci_runtime_suspend(struct device *dev) if (mmc) { struct mmci_host *host = mmc_priv(mmc); + pinctrl_pm_select_sleep_state(dev); + mmci_save(host); clk_disable_unprepare(host->clk); } @@ -1781,6 +1823,8 @@ static int mmci_runtime_resume(struct device *dev) if (mmc) { struct mmci_host *host = mmc_priv(mmc); clk_prepare_enable(host->clk); + mmci_restore(host); + pinctrl_pm_select_default_state(dev); } return 0; diff --git a/drivers/mmc/host/mmci.h b/drivers/mmc/host/mmci.h index 69080fab6375..168bc72f7a94 100644 --- a/drivers/mmc/host/mmci.h +++ b/drivers/mmc/host/mmci.h @@ -200,10 +200,6 @@ struct mmci_host { struct sg_mapping_iter sg_miter; unsigned int size; - /* pinctrl handles */ - struct pinctrl *pinctrl; - struct pinctrl_state *pins_default; - #ifdef CONFIG_DMA_ENGINE /* DMA stuff */ struct dma_chan *dma_current; diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c index cdd4ce0d7c90..ef19874fcd1f 100644 --- a/drivers/mmc/host/sdhci-acpi.c +++ b/drivers/mmc/host/sdhci-acpi.c @@ -310,8 +310,9 @@ static int sdhci_acpi_probe(struct platform_device *pdev) dma_mask = DMA_BIT_MASK(32); } - dev->dma_mask = &dev->coherent_dma_mask; - dev->coherent_dma_mask = dma_mask; + err = dma_coerce_mask_and_coherent(dev, dma_mask); + if (err) + goto err_free; } if (c->slot) { diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c index 59ab0692f0b9..a9830ff8e3f3 100644 --- a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c +++ b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c @@ -349,7 +349,7 @@ static int legacy_set_geometry(struct gpmi_nand_data *this) int common_nfc_set_geometry(struct gpmi_nand_data *this) { - return set_geometry_by_ecc_info(this) ? 0 : legacy_set_geometry(this); + return legacy_set_geometry(this); } struct dma_chan *get_dma_chan(struct gpmi_nand_data *this) diff --git a/drivers/mtd/nand/pxa3xx_nand.c b/drivers/mtd/nand/pxa3xx_nand.c index dd03dfdfb0d6..c28d4e29af1a 100644 --- a/drivers/mtd/nand/pxa3xx_nand.c +++ b/drivers/mtd/nand/pxa3xx_nand.c @@ -1320,7 +1320,12 @@ static int pxa3xx_nand_probe(struct platform_device *pdev) for (cs = 0; cs < pdata->num_cs; cs++) { struct mtd_info *mtd = info->host[cs]->mtd; - mtd->name = pdev->name; + /* + * The mtd name matches the one used in 'mtdparts' kernel + * parameter. This name cannot be changed or otherwise + * user's mtd partitions configuration would get broken. + */ + mtd->name = "pxa3xx_nand-0"; info->cs = cs; ret = pxa3xx_nand_scan(mtd); if (ret) { diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c index 3b1ff6148702..693d8ffe4653 100644 --- a/drivers/net/can/at91_can.c +++ b/drivers/net/can/at91_can.c @@ -1405,10 +1405,10 @@ static int at91_can_remove(struct platform_device *pdev) static const struct platform_device_id at91_can_id_table[] = { { - .name = "at91_can", + .name = "at91sam9x5_can", .driver_data = (kernel_ulong_t)&at91_at91sam9x5_data, }, { - .name = "at91sam9x5_can", + .name = "at91_can", .driver_data = (kernel_ulong_t)&at91_at91sam9263_data, }, { /* sentinel */ diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c index a668cd491cb3..e3fc07cf2f62 100644 --- a/drivers/net/can/c_can/c_can.c +++ b/drivers/net/can/c_can/c_can.c @@ -814,9 +814,6 @@ static int c_can_do_rx_poll(struct net_device *dev, int quota) msg_ctrl_save = priv->read_reg(priv, C_CAN_IFACE(MSGCTRL_REG, 0)); - if (msg_ctrl_save & IF_MCONT_EOB) - return num_rx_pkts; - if (msg_ctrl_save & IF_MCONT_MSGLST) { c_can_handle_lost_msg_obj(dev, 0, msg_obj); num_rx_pkts++; @@ -824,6 +821,9 @@ static int c_can_do_rx_poll(struct net_device *dev, int quota) continue; } + if (msg_ctrl_save & IF_MCONT_EOB) + return num_rx_pkts; + if (!(msg_ctrl_save & IF_MCONT_NEWDAT)) continue; diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c index f9cba4123c66..1870c4731a57 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -705,14 +705,14 @@ static size_t can_get_size(const struct net_device *dev) size_t size; size = nla_total_size(sizeof(u32)); /* IFLA_CAN_STATE */ - size += sizeof(struct can_ctrlmode); /* IFLA_CAN_CTRLMODE */ + size += nla_total_size(sizeof(struct can_ctrlmode)); /* IFLA_CAN_CTRLMODE */ size += nla_total_size(sizeof(u32)); /* IFLA_CAN_RESTART_MS */ - size += sizeof(struct can_bittiming); /* IFLA_CAN_BITTIMING */ - size += sizeof(struct can_clock); /* IFLA_CAN_CLOCK */ + size += nla_total_size(sizeof(struct can_bittiming)); /* IFLA_CAN_BITTIMING */ + size += nla_total_size(sizeof(struct can_clock)); /* IFLA_CAN_CLOCK */ if (priv->do_get_berr_counter) /* IFLA_CAN_BERR_COUNTER */ - size += sizeof(struct can_berr_counter); + size += nla_total_size(sizeof(struct can_berr_counter)); if (priv->bittiming_const) /* IFLA_CAN_BITTIMING_CONST */ - size += sizeof(struct can_bittiming_const); + size += nla_total_size(sizeof(struct can_bittiming_const)); return size; } diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index 3f21142138b7..8f5ce747feb5 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -62,7 +62,7 @@ #define FLEXCAN_MCR_BCC BIT(16) #define FLEXCAN_MCR_LPRIO_EN BIT(13) #define FLEXCAN_MCR_AEN BIT(12) -#define FLEXCAN_MCR_MAXMB(x) ((x) & 0xf) +#define FLEXCAN_MCR_MAXMB(x) ((x) & 0x1f) #define FLEXCAN_MCR_IDAM_A (0 << 8) #define FLEXCAN_MCR_IDAM_B (1 << 8) #define FLEXCAN_MCR_IDAM_C (2 << 8) @@ -735,9 +735,11 @@ static int flexcan_chip_start(struct net_device *dev) * */ reg_mcr = flexcan_read(®s->mcr); + reg_mcr &= ~FLEXCAN_MCR_MAXMB(0xff); reg_mcr |= FLEXCAN_MCR_FRZ | FLEXCAN_MCR_FEN | FLEXCAN_MCR_HALT | FLEXCAN_MCR_SUPV | FLEXCAN_MCR_WRN_EN | - FLEXCAN_MCR_IDAM_C | FLEXCAN_MCR_SRX_DIS; + FLEXCAN_MCR_IDAM_C | FLEXCAN_MCR_SRX_DIS | + FLEXCAN_MCR_MAXMB(FLEXCAN_TX_BUF_ID); netdev_dbg(dev, "%s: writing mcr=0x%08x", __func__, reg_mcr); flexcan_write(reg_mcr, ®s->mcr); @@ -771,6 +773,10 @@ static int flexcan_chip_start(struct net_device *dev) netdev_dbg(dev, "%s: writing ctrl=0x%08x", __func__, reg_ctrl); flexcan_write(reg_ctrl, ®s->ctrl); + /* Abort any pending TX, mark Mailbox as INACTIVE */ + flexcan_write(FLEXCAN_MB_CNT_CODE(0x4), + ®s->cantxfg[FLEXCAN_TX_BUF_ID].can_ctrl); + /* acceptance mask/acceptance code (accept everything) */ flexcan_write(0x0, ®s->rxgmask); flexcan_write(0x0, ®s->rx14mask); @@ -979,9 +985,9 @@ static void unregister_flexcandev(struct net_device *dev) } static const struct of_device_id flexcan_of_match[] = { - { .compatible = "fsl,p1010-flexcan", .data = &fsl_p1010_devtype_data, }, - { .compatible = "fsl,imx28-flexcan", .data = &fsl_imx28_devtype_data, }, { .compatible = "fsl,imx6q-flexcan", .data = &fsl_imx6q_devtype_data, }, + { .compatible = "fsl,imx28-flexcan", .data = &fsl_imx28_devtype_data, }, + { .compatible = "fsl,p1010-flexcan", .data = &fsl_p1010_devtype_data, }, { /* sentinel */ }, }; MODULE_DEVICE_TABLE(of, flexcan_of_match); diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c index 3b9546588240..4b2d5ed62b11 100644 --- a/drivers/net/can/usb/kvaser_usb.c +++ b/drivers/net/can/usb/kvaser_usb.c @@ -1544,9 +1544,9 @@ static int kvaser_usb_init_one(struct usb_interface *intf, return 0; } -static void kvaser_usb_get_endpoints(const struct usb_interface *intf, - struct usb_endpoint_descriptor **in, - struct usb_endpoint_descriptor **out) +static int kvaser_usb_get_endpoints(const struct usb_interface *intf, + struct usb_endpoint_descriptor **in, + struct usb_endpoint_descriptor **out) { const struct usb_host_interface *iface_desc; struct usb_endpoint_descriptor *endpoint; @@ -1557,12 +1557,18 @@ static void kvaser_usb_get_endpoints(const struct usb_interface *intf, for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i) { endpoint = &iface_desc->endpoint[i].desc; - if (usb_endpoint_is_bulk_in(endpoint)) + if (!*in && usb_endpoint_is_bulk_in(endpoint)) *in = endpoint; - if (usb_endpoint_is_bulk_out(endpoint)) + if (!*out && usb_endpoint_is_bulk_out(endpoint)) *out = endpoint; + + /* use first bulk endpoint for in and out */ + if (*in && *out) + return 0; } + + return -ENODEV; } static int kvaser_usb_probe(struct usb_interface *intf, @@ -1576,8 +1582,8 @@ static int kvaser_usb_probe(struct usb_interface *intf, if (!dev) return -ENOMEM; - kvaser_usb_get_endpoints(intf, &dev->bulk_in, &dev->bulk_out); - if (!dev->bulk_in || !dev->bulk_out) { + err = kvaser_usb_get_endpoints(intf, &dev->bulk_in, &dev->bulk_out); + if (err) { dev_err(&intf->dev, "Cannot get usb endpoint(s)"); return err; } diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c index 9b017d9c58e9..b4d20182549b 100644 --- a/drivers/net/ethernet/broadcom/b44.c +++ b/drivers/net/ethernet/broadcom/b44.c @@ -2183,8 +2183,7 @@ static int b44_init_one(struct ssb_device *sdev, goto err_out_free_dev; } - if (dma_set_mask(sdev->dma_dev, DMA_BIT_MASK(30)) || - dma_set_coherent_mask(sdev->dma_dev, DMA_BIT_MASK(30))) { + if (dma_set_mask_and_coherent(sdev->dma_dev, DMA_BIT_MASK(30))) { dev_err(sdev->dev, "Required 30BIT DMA mask unsupported by the system\n"); goto err_out_powerdown; diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index 249468f95365..9e8a3e024e01 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -244,25 +244,33 @@ static int bgmac_dma_rx_skb_for_slot(struct bgmac *bgmac, struct bgmac_slot_info *slot) { struct device *dma_dev = bgmac->core->dma_dev; + struct sk_buff *skb; + dma_addr_t dma_addr; struct bgmac_rx_header *rx; /* Alloc skb */ - slot->skb = netdev_alloc_skb(bgmac->net_dev, BGMAC_RX_BUF_SIZE); - if (!slot->skb) + skb = netdev_alloc_skb(bgmac->net_dev, BGMAC_RX_BUF_SIZE); + if (!skb) return -ENOMEM; /* Poison - if everything goes fine, hardware will overwrite it */ - rx = (struct bgmac_rx_header *)slot->skb->data; + rx = (struct bgmac_rx_header *)skb->data; rx->len = cpu_to_le16(0xdead); rx->flags = cpu_to_le16(0xbeef); /* Map skb for the DMA */ - slot->dma_addr = dma_map_single(dma_dev, slot->skb->data, - BGMAC_RX_BUF_SIZE, DMA_FROM_DEVICE); - if (dma_mapping_error(dma_dev, slot->dma_addr)) { + dma_addr = dma_map_single(dma_dev, skb->data, + BGMAC_RX_BUF_SIZE, DMA_FROM_DEVICE); + if (dma_mapping_error(dma_dev, dma_addr)) { bgmac_err(bgmac, "DMA mapping error\n"); + dev_kfree_skb(skb); return -ENOMEM; } + + /* Update the slot */ + slot->skb = skb; + slot->dma_addr = dma_addr; + if (slot->dma_addr & 0xC0000000) bgmac_warn(bgmac, "DMA address using 0xC0000000 bit(s), it may need translation trick\n"); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h index 97b3d32a98bd..c5e375ddd6c0 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h @@ -1197,8 +1197,9 @@ union cdu_context { /* TM (timers) host DB constants */ #define TM_ILT_PAGE_SZ_HW 0 #define TM_ILT_PAGE_SZ (4096 << TM_ILT_PAGE_SZ_HW) /* 4K */ -/* #define TM_CONN_NUM (CNIC_STARTING_CID+CNIC_ISCSI_CXT_MAX) */ -#define TM_CONN_NUM 1024 +#define TM_CONN_NUM (BNX2X_FIRST_VF_CID + \ + BNX2X_VF_CIDS + \ + CNIC_ISCSI_CID_MAX) #define TM_ILT_SZ (8 * TM_CONN_NUM) #define TM_ILT_LINES DIV_ROUND_UP(TM_ILT_SZ, TM_ILT_PAGE_SZ) @@ -1527,7 +1528,6 @@ struct bnx2x { #define PCI_32BIT_FLAG (1 << 1) #define ONE_PORT_FLAG (1 << 2) #define NO_WOL_FLAG (1 << 3) -#define USING_DAC_FLAG (1 << 4) #define USING_MSIX_FLAG (1 << 5) #define USING_MSI_FLAG (1 << 6) #define DISABLE_MSI_FLAG (1 << 7) @@ -1621,7 +1621,7 @@ struct bnx2x { u16 rx_ticks_int; u16 rx_ticks; /* Maximal coalescing timeout in us */ -#define BNX2X_MAX_COALESCE_TOUT (0xf0*12) +#define BNX2X_MAX_COALESCE_TOUT (0xff*BNX2X_BTR) u32 lin_cnt; @@ -2072,7 +2072,8 @@ u32 bnx2x_dmae_opcode(struct bnx2x *bp, u8 src_type, u8 dst_type, void bnx2x_prep_dmae_with_comp(struct bnx2x *bp, struct dmae_command *dmae, u8 src_type, u8 dst_type); -int bnx2x_issue_dmae_with_comp(struct bnx2x *bp, struct dmae_command *dmae); +int bnx2x_issue_dmae_with_comp(struct bnx2x *bp, struct dmae_command *dmae, + u32 *comp); /* FLR related routines */ u32 bnx2x_flr_clnup_poll_count(struct bnx2x *bp); @@ -2498,4 +2499,8 @@ enum bnx2x_pci_bus_speed { }; void bnx2x_set_local_cmng(struct bnx2x *bp); + +#define MCPR_SCRATCH_BASE(bp) \ + (CHIP_IS_E1x(bp) ? MCP_REG_MCPR_SCRATCH : MCP_A_REG_MCPR_SCRATCH) + #endif /* bnx2x.h */ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index e66beff2704d..74d6486fccfd 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -681,6 +681,7 @@ static void bnx2x_gro_receive(struct bnx2x *bp, struct bnx2x_fastpath *fp, } } #endif + skb_record_rx_queue(skb, fp->rx_queue); napi_gro_receive(&fp->napi, skb); } @@ -2544,10 +2545,6 @@ int bnx2x_nic_load(struct bnx2x *bp, int load_mode) } } - /* Allocated memory for FW statistics */ - if (bnx2x_alloc_fw_stats_mem(bp)) - LOAD_ERROR_EXIT(bp, load_error0); - /* need to be done after alloc mem, since it's self adjusting to amount * of memory available for RSS queues */ @@ -2557,6 +2554,10 @@ int bnx2x_nic_load(struct bnx2x *bp, int load_mode) LOAD_ERROR_EXIT(bp, load_error0); } + /* Allocated memory for FW statistics */ + if (bnx2x_alloc_fw_stats_mem(bp)) + LOAD_ERROR_EXIT(bp, load_error0); + /* request pf to initialize status blocks */ if (IS_VF(bp)) { rc = bnx2x_vfpf_init(bp); @@ -2811,8 +2812,8 @@ load_error1: if (IS_PF(bp)) bnx2x_clear_pf_load(bp); load_error0: - bnx2x_free_fp_mem(bp); bnx2x_free_fw_stats_mem(bp); + bnx2x_free_fp_mem(bp); bnx2x_free_mem(bp); return rc; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c index 324de5f05332..e8efa1c93ffe 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c @@ -891,17 +891,8 @@ static void bnx2x_get_regs(struct net_device *dev, * will re-enable parity attentions right after the dump. */ - /* Disable parity on path 0 */ - bnx2x_pretend_func(bp, 0); bnx2x_disable_blocks_parity(bp); - /* Disable parity on path 1 */ - bnx2x_pretend_func(bp, 1); - bnx2x_disable_blocks_parity(bp); - - /* Return to current function */ - bnx2x_pretend_func(bp, BP_ABS_FUNC(bp)); - dump_hdr.header_size = (sizeof(struct dump_header) / 4) - 1; dump_hdr.preset = DUMP_ALL_PRESETS; dump_hdr.version = BNX2X_DUMP_VERSION; @@ -928,18 +919,9 @@ static void bnx2x_get_regs(struct net_device *dev, /* Actually read the registers */ __bnx2x_get_regs(bp, p); - /* Re-enable parity attentions on path 0 */ - bnx2x_pretend_func(bp, 0); + /* Re-enable parity attentions */ bnx2x_clear_blocks_parity(bp); bnx2x_enable_blocks_parity(bp); - - /* Re-enable parity attentions on path 1 */ - bnx2x_pretend_func(bp, 1); - bnx2x_clear_blocks_parity(bp); - bnx2x_enable_blocks_parity(bp); - - /* Return to current function */ - bnx2x_pretend_func(bp, BP_ABS_FUNC(bp)); } static int bnx2x_get_preset_regs_len(struct net_device *dev, u32 preset) @@ -993,17 +975,8 @@ static int bnx2x_get_dump_data(struct net_device *dev, * will re-enable parity attentions right after the dump. */ - /* Disable parity on path 0 */ - bnx2x_pretend_func(bp, 0); bnx2x_disable_blocks_parity(bp); - /* Disable parity on path 1 */ - bnx2x_pretend_func(bp, 1); - bnx2x_disable_blocks_parity(bp); - - /* Return to current function */ - bnx2x_pretend_func(bp, BP_ABS_FUNC(bp)); - dump_hdr.header_size = (sizeof(struct dump_header) / 4) - 1; dump_hdr.preset = bp->dump_preset_idx; dump_hdr.version = BNX2X_DUMP_VERSION; @@ -1032,19 +1005,10 @@ static int bnx2x_get_dump_data(struct net_device *dev, /* Actually read the registers */ __bnx2x_get_preset_regs(bp, p, dump_hdr.preset); - /* Re-enable parity attentions on path 0 */ - bnx2x_pretend_func(bp, 0); + /* Re-enable parity attentions */ bnx2x_clear_blocks_parity(bp); bnx2x_enable_blocks_parity(bp); - /* Re-enable parity attentions on path 1 */ - bnx2x_pretend_func(bp, 1); - bnx2x_clear_blocks_parity(bp); - bnx2x_enable_blocks_parity(bp); - - /* Return to current function */ - bnx2x_pretend_func(bp, BP_ABS_FUNC(bp)); - return 0; } diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h index 76df015f486a..c2dfea7968f4 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h @@ -640,23 +640,35 @@ static const struct { * [30] MCP Latched ump_tx_parity * [31] MCP Latched scpad_parity */ -#define MISC_AEU_ENABLE_MCP_PRTY_BITS \ +#define MISC_AEU_ENABLE_MCP_PRTY_SUB_BITS \ (AEU_INPUTS_ATTN_BITS_MCP_LATCHED_ROM_PARITY | \ AEU_INPUTS_ATTN_BITS_MCP_LATCHED_UMP_RX_PARITY | \ - AEU_INPUTS_ATTN_BITS_MCP_LATCHED_UMP_TX_PARITY | \ + AEU_INPUTS_ATTN_BITS_MCP_LATCHED_UMP_TX_PARITY) + +#define MISC_AEU_ENABLE_MCP_PRTY_BITS \ + (MISC_AEU_ENABLE_MCP_PRTY_SUB_BITS | \ AEU_INPUTS_ATTN_BITS_MCP_LATCHED_SCPAD_PARITY) /* Below registers control the MCP parity attention output. When * MISC_AEU_ENABLE_MCP_PRTY_BITS are set - attentions are * enabled, when cleared - disabled. */ -static const u32 mcp_attn_ctl_regs[] = { - MISC_REG_AEU_ENABLE4_FUNC_0_OUT_0, - MISC_REG_AEU_ENABLE4_NIG_0, - MISC_REG_AEU_ENABLE4_PXP_0, - MISC_REG_AEU_ENABLE4_FUNC_1_OUT_0, - MISC_REG_AEU_ENABLE4_NIG_1, - MISC_REG_AEU_ENABLE4_PXP_1 +static const struct { + u32 addr; + u32 bits; +} mcp_attn_ctl_regs[] = { + { MISC_REG_AEU_ENABLE4_FUNC_0_OUT_0, + MISC_AEU_ENABLE_MCP_PRTY_BITS }, + { MISC_REG_AEU_ENABLE4_NIG_0, + MISC_AEU_ENABLE_MCP_PRTY_SUB_BITS }, + { MISC_REG_AEU_ENABLE4_PXP_0, + MISC_AEU_ENABLE_MCP_PRTY_SUB_BITS }, + { MISC_REG_AEU_ENABLE4_FUNC_1_OUT_0, + MISC_AEU_ENABLE_MCP_PRTY_BITS }, + { MISC_REG_AEU_ENABLE4_NIG_1, + MISC_AEU_ENABLE_MCP_PRTY_SUB_BITS }, + { MISC_REG_AEU_ENABLE4_PXP_1, + MISC_AEU_ENABLE_MCP_PRTY_SUB_BITS } }; static inline void bnx2x_set_mcp_parity(struct bnx2x *bp, u8 enable) @@ -665,14 +677,14 @@ static inline void bnx2x_set_mcp_parity(struct bnx2x *bp, u8 enable) u32 reg_val; for (i = 0; i < ARRAY_SIZE(mcp_attn_ctl_regs); i++) { - reg_val = REG_RD(bp, mcp_attn_ctl_regs[i]); + reg_val = REG_RD(bp, mcp_attn_ctl_regs[i].addr); if (enable) - reg_val |= MISC_AEU_ENABLE_MCP_PRTY_BITS; + reg_val |= mcp_attn_ctl_regs[i].bits; else - reg_val &= ~MISC_AEU_ENABLE_MCP_PRTY_BITS; + reg_val &= ~mcp_attn_ctl_regs[i].bits; - REG_WR(bp, mcp_attn_ctl_regs[i], reg_val); + REG_WR(bp, mcp_attn_ctl_regs[i].addr, reg_val); } } diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 82b658d8c04c..767aafb50406 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -503,9 +503,9 @@ void bnx2x_prep_dmae_with_comp(struct bnx2x *bp, } /* issue a dmae command over the init-channel and wait for completion */ -int bnx2x_issue_dmae_with_comp(struct bnx2x *bp, struct dmae_command *dmae) +int bnx2x_issue_dmae_with_comp(struct bnx2x *bp, struct dmae_command *dmae, + u32 *comp) { - u32 *wb_comp = bnx2x_sp(bp, wb_comp); int cnt = CHIP_REV_IS_SLOW(bp) ? (400000) : 4000; int rc = 0; @@ -518,14 +518,14 @@ int bnx2x_issue_dmae_with_comp(struct bnx2x *bp, struct dmae_command *dmae) spin_lock_bh(&bp->dmae_lock); /* reset completion */ - *wb_comp = 0; + *comp = 0; /* post the command on the channel used for initializations */ bnx2x_post_dmae(bp, dmae, INIT_DMAE_C(bp)); /* wait for completion */ udelay(5); - while ((*wb_comp & ~DMAE_PCI_ERR_FLAG) != DMAE_COMP_VAL) { + while ((*comp & ~DMAE_PCI_ERR_FLAG) != DMAE_COMP_VAL) { if (!cnt || (bp->recovery_state != BNX2X_RECOVERY_DONE && @@ -537,7 +537,7 @@ int bnx2x_issue_dmae_with_comp(struct bnx2x *bp, struct dmae_command *dmae) cnt--; udelay(50); } - if (*wb_comp & DMAE_PCI_ERR_FLAG) { + if (*comp & DMAE_PCI_ERR_FLAG) { BNX2X_ERR("DMAE PCI error!\n"); rc = DMAE_PCI_ERROR; } @@ -574,7 +574,7 @@ void bnx2x_write_dmae(struct bnx2x *bp, dma_addr_t dma_addr, u32 dst_addr, dmae.len = len32; /* issue the command and wait for completion */ - rc = bnx2x_issue_dmae_with_comp(bp, &dmae); + rc = bnx2x_issue_dmae_with_comp(bp, &dmae, bnx2x_sp(bp, wb_comp)); if (rc) { BNX2X_ERR("DMAE returned failure %d\n", rc); bnx2x_panic(); @@ -611,7 +611,7 @@ void bnx2x_read_dmae(struct bnx2x *bp, u32 src_addr, u32 len32) dmae.len = len32; /* issue the command and wait for completion */ - rc = bnx2x_issue_dmae_with_comp(bp, &dmae); + rc = bnx2x_issue_dmae_with_comp(bp, &dmae, bnx2x_sp(bp, wb_comp)); if (rc) { BNX2X_ERR("DMAE returned failure %d\n", rc); bnx2x_panic(); @@ -751,6 +751,10 @@ static int bnx2x_mc_assert(struct bnx2x *bp) return rc; } +#define MCPR_TRACE_BUFFER_SIZE (0x800) +#define SCRATCH_BUFFER_SIZE(bp) \ + (CHIP_IS_E1(bp) ? 0x10000 : (CHIP_IS_E1H(bp) ? 0x20000 : 0x28000)) + void bnx2x_fw_dump_lvl(struct bnx2x *bp, const char *lvl) { u32 addr, val; @@ -775,7 +779,17 @@ void bnx2x_fw_dump_lvl(struct bnx2x *bp, const char *lvl) trace_shmem_base = bp->common.shmem_base; else trace_shmem_base = SHMEM2_RD(bp, other_shmem_base_addr); - addr = trace_shmem_base - 0x800; + + /* sanity */ + if (trace_shmem_base < MCPR_SCRATCH_BASE(bp) + MCPR_TRACE_BUFFER_SIZE || + trace_shmem_base >= MCPR_SCRATCH_BASE(bp) + + SCRATCH_BUFFER_SIZE(bp)) { + BNX2X_ERR("Unable to dump trace buffer (mark %x)\n", + trace_shmem_base); + return; + } + + addr = trace_shmem_base - MCPR_TRACE_BUFFER_SIZE; /* validate TRCB signature */ mark = REG_RD(bp, addr); @@ -787,14 +801,17 @@ void bnx2x_fw_dump_lvl(struct bnx2x *bp, const char *lvl) /* read cyclic buffer pointer */ addr += 4; mark = REG_RD(bp, addr); - mark = (CHIP_IS_E1x(bp) ? MCP_REG_MCPR_SCRATCH : MCP_A_REG_MCPR_SCRATCH) - + ((mark + 0x3) & ~0x3) - 0x08000000; + mark = MCPR_SCRATCH_BASE(bp) + ((mark + 0x3) & ~0x3) - 0x08000000; + if (mark >= trace_shmem_base || mark < addr + 4) { + BNX2X_ERR("Mark doesn't fall inside Trace Buffer\n"); + return; + } printk("%s" "begin fw dump (mark 0x%x)\n", lvl, mark); printk("%s", lvl); /* dump buffer after the mark */ - for (offset = mark; offset <= trace_shmem_base; offset += 0x8*4) { + for (offset = mark; offset < trace_shmem_base; offset += 0x8*4) { for (word = 0; word < 8; word++) data[word] = htonl(REG_RD(bp, offset + 4*word)); data[8] = 0x0; @@ -4280,65 +4297,60 @@ static void _print_next_block(int idx, const char *blk) pr_cont("%s%s", idx ? ", " : "", blk); } -static int bnx2x_check_blocks_with_parity0(struct bnx2x *bp, u32 sig, - int par_num, bool print) +static bool bnx2x_check_blocks_with_parity0(struct bnx2x *bp, u32 sig, + int *par_num, bool print) { - int i = 0; - u32 cur_bit = 0; + u32 cur_bit; + bool res; + int i; + + res = false; + for (i = 0; sig; i++) { - cur_bit = ((u32)0x1 << i); + cur_bit = (0x1UL << i); if (sig & cur_bit) { - switch (cur_bit) { - case AEU_INPUTS_ATTN_BITS_BRB_PARITY_ERROR: - if (print) { - _print_next_block(par_num++, "BRB"); + res |= true; /* Each bit is real error! */ + + if (print) { + switch (cur_bit) { + case AEU_INPUTS_ATTN_BITS_BRB_PARITY_ERROR: + _print_next_block((*par_num)++, "BRB"); _print_parity(bp, BRB1_REG_BRB1_PRTY_STS); - } - break; - case AEU_INPUTS_ATTN_BITS_PARSER_PARITY_ERROR: - if (print) { - _print_next_block(par_num++, "PARSER"); + break; + case AEU_INPUTS_ATTN_BITS_PARSER_PARITY_ERROR: + _print_next_block((*par_num)++, + "PARSER"); _print_parity(bp, PRS_REG_PRS_PRTY_STS); - } - break; - case AEU_INPUTS_ATTN_BITS_TSDM_PARITY_ERROR: - if (print) { - _print_next_block(par_num++, "TSDM"); + break; + case AEU_INPUTS_ATTN_BITS_TSDM_PARITY_ERROR: + _print_next_block((*par_num)++, "TSDM"); _print_parity(bp, TSDM_REG_TSDM_PRTY_STS); - } - break; - case AEU_INPUTS_ATTN_BITS_SEARCHER_PARITY_ERROR: - if (print) { - _print_next_block(par_num++, + break; + case AEU_INPUTS_ATTN_BITS_SEARCHER_PARITY_ERROR: + _print_next_block((*par_num)++, "SEARCHER"); _print_parity(bp, SRC_REG_SRC_PRTY_STS); - } - break; - case AEU_INPUTS_ATTN_BITS_TCM_PARITY_ERROR: - if (print) { - _print_next_block(par_num++, "TCM"); - _print_parity(bp, - TCM_REG_TCM_PRTY_STS); - } - break; - case AEU_INPUTS_ATTN_BITS_TSEMI_PARITY_ERROR: - if (print) { - _print_next_block(par_num++, "TSEMI"); + break; + case AEU_INPUTS_ATTN_BITS_TCM_PARITY_ERROR: + _print_next_block((*par_num)++, "TCM"); + _print_parity(bp, TCM_REG_TCM_PRTY_STS); + break; + case AEU_INPUTS_ATTN_BITS_TSEMI_PARITY_ERROR: + _print_next_block((*par_num)++, + "TSEMI"); _print_parity(bp, TSEM_REG_TSEM_PRTY_STS_0); _print_parity(bp, TSEM_REG_TSEM_PRTY_STS_1); - } - break; - case AEU_INPUTS_ATTN_BITS_PBCLIENT_PARITY_ERROR: - if (print) { - _print_next_block(par_num++, "XPB"); + break; + case AEU_INPUTS_ATTN_BITS_PBCLIENT_PARITY_ERROR: + _print_next_block((*par_num)++, "XPB"); _print_parity(bp, GRCBASE_XPB + PB_REG_PB_PRTY_STS); + break; } - break; } /* Clear the bit */ @@ -4346,53 +4358,59 @@ static int bnx2x_check_blocks_with_parity0(struct bnx2x *bp, u32 sig, } } - return par_num; + return res; } -static int bnx2x_check_blocks_with_parity1(struct bnx2x *bp, u32 sig, - int par_num, bool *global, +static bool bnx2x_check_blocks_with_parity1(struct bnx2x *bp, u32 sig, + int *par_num, bool *global, bool print) { - int i = 0; - u32 cur_bit = 0; + u32 cur_bit; + bool res; + int i; + + res = false; + for (i = 0; sig; i++) { - cur_bit = ((u32)0x1 << i); + cur_bit = (0x1UL << i); if (sig & cur_bit) { + res |= true; /* Each bit is real error! */ switch (cur_bit) { case AEU_INPUTS_ATTN_BITS_PBF_PARITY_ERROR: if (print) { - _print_next_block(par_num++, "PBF"); + _print_next_block((*par_num)++, "PBF"); _print_parity(bp, PBF_REG_PBF_PRTY_STS); } break; case AEU_INPUTS_ATTN_BITS_QM_PARITY_ERROR: if (print) { - _print_next_block(par_num++, "QM"); + _print_next_block((*par_num)++, "QM"); _print_parity(bp, QM_REG_QM_PRTY_STS); } break; case AEU_INPUTS_ATTN_BITS_TIMERS_PARITY_ERROR: if (print) { - _print_next_block(par_num++, "TM"); + _print_next_block((*par_num)++, "TM"); _print_parity(bp, TM_REG_TM_PRTY_STS); } break; case AEU_INPUTS_ATTN_BITS_XSDM_PARITY_ERROR: if (print) { - _print_next_block(par_num++, "XSDM"); + _print_next_block((*par_num)++, "XSDM"); _print_parity(bp, XSDM_REG_XSDM_PRTY_STS); } break; case AEU_INPUTS_ATTN_BITS_XCM_PARITY_ERROR: if (print) { - _print_next_block(par_num++, "XCM"); + _print_next_block((*par_num)++, "XCM"); _print_parity(bp, XCM_REG_XCM_PRTY_STS); } break; case AEU_INPUTS_ATTN_BITS_XSEMI_PARITY_ERROR: if (print) { - _print_next_block(par_num++, "XSEMI"); + _print_next_block((*par_num)++, + "XSEMI"); _print_parity(bp, XSEM_REG_XSEM_PRTY_STS_0); _print_parity(bp, @@ -4401,7 +4419,7 @@ static int bnx2x_check_blocks_with_parity1(struct bnx2x *bp, u32 sig, break; case AEU_INPUTS_ATTN_BITS_DOORBELLQ_PARITY_ERROR: if (print) { - _print_next_block(par_num++, + _print_next_block((*par_num)++, "DOORBELLQ"); _print_parity(bp, DORQ_REG_DORQ_PRTY_STS); @@ -4409,7 +4427,7 @@ static int bnx2x_check_blocks_with_parity1(struct bnx2x *bp, u32 sig, break; case AEU_INPUTS_ATTN_BITS_NIG_PARITY_ERROR: if (print) { - _print_next_block(par_num++, "NIG"); + _print_next_block((*par_num)++, "NIG"); if (CHIP_IS_E1x(bp)) { _print_parity(bp, NIG_REG_NIG_PRTY_STS); @@ -4423,32 +4441,34 @@ static int bnx2x_check_blocks_with_parity1(struct bnx2x *bp, u32 sig, break; case AEU_INPUTS_ATTN_BITS_VAUX_PCI_CORE_PARITY_ERROR: if (print) - _print_next_block(par_num++, + _print_next_block((*par_num)++, "VAUX PCI CORE"); *global = true; break; case AEU_INPUTS_ATTN_BITS_DEBUG_PARITY_ERROR: if (print) { - _print_next_block(par_num++, "DEBUG"); + _print_next_block((*par_num)++, + "DEBUG"); _print_parity(bp, DBG_REG_DBG_PRTY_STS); } break; case AEU_INPUTS_ATTN_BITS_USDM_PARITY_ERROR: if (print) { - _print_next_block(par_num++, "USDM"); + _print_next_block((*par_num)++, "USDM"); _print_parity(bp, USDM_REG_USDM_PRTY_STS); } break; case AEU_INPUTS_ATTN_BITS_UCM_PARITY_ERROR: if (print) { - _print_next_block(par_num++, "UCM"); + _print_next_block((*par_num)++, "UCM"); _print_parity(bp, UCM_REG_UCM_PRTY_STS); } break; case AEU_INPUTS_ATTN_BITS_USEMI_PARITY_ERROR: if (print) { - _print_next_block(par_num++, "USEMI"); + _print_next_block((*par_num)++, + "USEMI"); _print_parity(bp, USEM_REG_USEM_PRTY_STS_0); _print_parity(bp, @@ -4457,21 +4477,21 @@ static int bnx2x_check_blocks_with_parity1(struct bnx2x *bp, u32 sig, break; case AEU_INPUTS_ATTN_BITS_UPB_PARITY_ERROR: if (print) { - _print_next_block(par_num++, "UPB"); + _print_next_block((*par_num)++, "UPB"); _print_parity(bp, GRCBASE_UPB + PB_REG_PB_PRTY_STS); } break; case AEU_INPUTS_ATTN_BITS_CSDM_PARITY_ERROR: if (print) { - _print_next_block(par_num++, "CSDM"); + _print_next_block((*par_num)++, "CSDM"); _print_parity(bp, CSDM_REG_CSDM_PRTY_STS); } break; case AEU_INPUTS_ATTN_BITS_CCM_PARITY_ERROR: if (print) { - _print_next_block(par_num++, "CCM"); + _print_next_block((*par_num)++, "CCM"); _print_parity(bp, CCM_REG_CCM_PRTY_STS); } break; @@ -4482,80 +4502,73 @@ static int bnx2x_check_blocks_with_parity1(struct bnx2x *bp, u32 sig, } } - return par_num; + return res; } -static int bnx2x_check_blocks_with_parity2(struct bnx2x *bp, u32 sig, - int par_num, bool print) +static bool bnx2x_check_blocks_with_parity2(struct bnx2x *bp, u32 sig, + int *par_num, bool print) { - int i = 0; - u32 cur_bit = 0; + u32 cur_bit; + bool res; + int i; + + res = false; + for (i = 0; sig; i++) { - cur_bit = ((u32)0x1 << i); + cur_bit = (0x1UL << i); if (sig & cur_bit) { - switch (cur_bit) { - case AEU_INPUTS_ATTN_BITS_CSEMI_PARITY_ERROR: - if (print) { - _print_next_block(par_num++, "CSEMI"); + res |= true; /* Each bit is real error! */ + if (print) { + switch (cur_bit) { + case AEU_INPUTS_ATTN_BITS_CSEMI_PARITY_ERROR: + _print_next_block((*par_num)++, + "CSEMI"); _print_parity(bp, CSEM_REG_CSEM_PRTY_STS_0); _print_parity(bp, CSEM_REG_CSEM_PRTY_STS_1); - } - break; - case AEU_INPUTS_ATTN_BITS_PXP_PARITY_ERROR: - if (print) { - _print_next_block(par_num++, "PXP"); + break; + case AEU_INPUTS_ATTN_BITS_PXP_PARITY_ERROR: + _print_next_block((*par_num)++, "PXP"); _print_parity(bp, PXP_REG_PXP_PRTY_STS); _print_parity(bp, PXP2_REG_PXP2_PRTY_STS_0); _print_parity(bp, PXP2_REG_PXP2_PRTY_STS_1); - } - break; - case AEU_IN_ATTN_BITS_PXPPCICLOCKCLIENT_PARITY_ERROR: - if (print) - _print_next_block(par_num++, - "PXPPCICLOCKCLIENT"); - break; - case AEU_INPUTS_ATTN_BITS_CFC_PARITY_ERROR: - if (print) { - _print_next_block(par_num++, "CFC"); + break; + case AEU_IN_ATTN_BITS_PXPPCICLOCKCLIENT_PARITY_ERROR: + _print_next_block((*par_num)++, + "PXPPCICLOCKCLIENT"); + break; + case AEU_INPUTS_ATTN_BITS_CFC_PARITY_ERROR: + _print_next_block((*par_num)++, "CFC"); _print_parity(bp, CFC_REG_CFC_PRTY_STS); - } - break; - case AEU_INPUTS_ATTN_BITS_CDU_PARITY_ERROR: - if (print) { - _print_next_block(par_num++, "CDU"); + break; + case AEU_INPUTS_ATTN_BITS_CDU_PARITY_ERROR: + _print_next_block((*par_num)++, "CDU"); _print_parity(bp, CDU_REG_CDU_PRTY_STS); - } - break; - case AEU_INPUTS_ATTN_BITS_DMAE_PARITY_ERROR: - if (print) { - _print_next_block(par_num++, "DMAE"); + break; + case AEU_INPUTS_ATTN_BITS_DMAE_PARITY_ERROR: + _print_next_block((*par_num)++, "DMAE"); _print_parity(bp, DMAE_REG_DMAE_PRTY_STS); - } - break; - case AEU_INPUTS_ATTN_BITS_IGU_PARITY_ERROR: - if (print) { - _print_next_block(par_num++, "IGU"); + break; + case AEU_INPUTS_ATTN_BITS_IGU_PARITY_ERROR: + _print_next_block((*par_num)++, "IGU"); if (CHIP_IS_E1x(bp)) _print_parity(bp, HC_REG_HC_PRTY_STS); else _print_parity(bp, IGU_REG_IGU_PRTY_STS); - } - break; - case AEU_INPUTS_ATTN_BITS_MISC_PARITY_ERROR: - if (print) { - _print_next_block(par_num++, "MISC"); + break; + case AEU_INPUTS_ATTN_BITS_MISC_PARITY_ERROR: + _print_next_block((*par_num)++, "MISC"); _print_parity(bp, MISC_REG_MISC_PRTY_STS); + break; } - break; } /* Clear the bit */ @@ -4563,40 +4576,49 @@ static int bnx2x_check_blocks_with_parity2(struct bnx2x *bp, u32 sig, } } - return par_num; + return res; } -static int bnx2x_check_blocks_with_parity3(u32 sig, int par_num, - bool *global, bool print) +static bool bnx2x_check_blocks_with_parity3(struct bnx2x *bp, u32 sig, + int *par_num, bool *global, + bool print) { - int i = 0; - u32 cur_bit = 0; + bool res = false; + u32 cur_bit; + int i; + for (i = 0; sig; i++) { - cur_bit = ((u32)0x1 << i); + cur_bit = (0x1UL << i); if (sig & cur_bit) { switch (cur_bit) { case AEU_INPUTS_ATTN_BITS_MCP_LATCHED_ROM_PARITY: if (print) - _print_next_block(par_num++, "MCP ROM"); + _print_next_block((*par_num)++, + "MCP ROM"); *global = true; + res |= true; break; case AEU_INPUTS_ATTN_BITS_MCP_LATCHED_UMP_RX_PARITY: if (print) - _print_next_block(par_num++, + _print_next_block((*par_num)++, "MCP UMP RX"); *global = true; + res |= true; break; case AEU_INPUTS_ATTN_BITS_MCP_LATCHED_UMP_TX_PARITY: if (print) - _print_next_block(par_num++, + _print_next_block((*par_num)++, "MCP UMP TX"); *global = true; + res |= true; break; case AEU_INPUTS_ATTN_BITS_MCP_LATCHED_SCPAD_PARITY: if (print) - _print_next_block(par_num++, + _print_next_block((*par_num)++, "MCP SCPAD"); - *global = true; + /* clear latched SCPAD PATIRY from MCP */ + REG_WR(bp, MISC_REG_AEU_CLR_LATCH_SIGNAL, + 1UL << 10); break; } @@ -4605,45 +4627,50 @@ static int bnx2x_check_blocks_with_parity3(u32 sig, int par_num, } } - return par_num; + return res; } -static int bnx2x_check_blocks_with_parity4(struct bnx2x *bp, u32 sig, - int par_num, bool print) +static bool bnx2x_check_blocks_with_parity4(struct bnx2x *bp, u32 sig, + int *par_num, bool print) { - int i = 0; - u32 cur_bit = 0; + u32 cur_bit; + bool res; + int i; + + res = false; + for (i = 0; sig; i++) { - cur_bit = ((u32)0x1 << i); + cur_bit = (0x1UL << i); if (sig & cur_bit) { - switch (cur_bit) { - case AEU_INPUTS_ATTN_BITS_PGLUE_PARITY_ERROR: - if (print) { - _print_next_block(par_num++, "PGLUE_B"); + res |= true; /* Each bit is real error! */ + if (print) { + switch (cur_bit) { + case AEU_INPUTS_ATTN_BITS_PGLUE_PARITY_ERROR: + _print_next_block((*par_num)++, + "PGLUE_B"); _print_parity(bp, - PGLUE_B_REG_PGLUE_B_PRTY_STS); - } - break; - case AEU_INPUTS_ATTN_BITS_ATC_PARITY_ERROR: - if (print) { - _print_next_block(par_num++, "ATC"); + PGLUE_B_REG_PGLUE_B_PRTY_STS); + break; + case AEU_INPUTS_ATTN_BITS_ATC_PARITY_ERROR: + _print_next_block((*par_num)++, "ATC"); _print_parity(bp, ATC_REG_ATC_PRTY_STS); + break; } - break; } - /* Clear the bit */ sig &= ~cur_bit; } } - return par_num; + return res; } static bool bnx2x_parity_attn(struct bnx2x *bp, bool *global, bool print, u32 *sig) { + bool res = false; + if ((sig[0] & HW_PRTY_ASSERT_SET_0) || (sig[1] & HW_PRTY_ASSERT_SET_1) || (sig[2] & HW_PRTY_ASSERT_SET_2) || @@ -4660,23 +4687,22 @@ static bool bnx2x_parity_attn(struct bnx2x *bp, bool *global, bool print, if (print) netdev_err(bp->dev, "Parity errors detected in blocks: "); - par_num = bnx2x_check_blocks_with_parity0(bp, - sig[0] & HW_PRTY_ASSERT_SET_0, par_num, print); - par_num = bnx2x_check_blocks_with_parity1(bp, - sig[1] & HW_PRTY_ASSERT_SET_1, par_num, global, print); - par_num = bnx2x_check_blocks_with_parity2(bp, - sig[2] & HW_PRTY_ASSERT_SET_2, par_num, print); - par_num = bnx2x_check_blocks_with_parity3( - sig[3] & HW_PRTY_ASSERT_SET_3, par_num, global, print); - par_num = bnx2x_check_blocks_with_parity4(bp, - sig[4] & HW_PRTY_ASSERT_SET_4, par_num, print); + res |= bnx2x_check_blocks_with_parity0(bp, + sig[0] & HW_PRTY_ASSERT_SET_0, &par_num, print); + res |= bnx2x_check_blocks_with_parity1(bp, + sig[1] & HW_PRTY_ASSERT_SET_1, &par_num, global, print); + res |= bnx2x_check_blocks_with_parity2(bp, + sig[2] & HW_PRTY_ASSERT_SET_2, &par_num, print); + res |= bnx2x_check_blocks_with_parity3(bp, + sig[3] & HW_PRTY_ASSERT_SET_3, &par_num, global, print); + res |= bnx2x_check_blocks_with_parity4(bp, + sig[4] & HW_PRTY_ASSERT_SET_4, &par_num, print); if (print) pr_cont("\n"); + } - return true; - } else - return false; + return res; } /** @@ -7126,7 +7152,7 @@ static int bnx2x_init_hw_port(struct bnx2x *bp) int port = BP_PORT(bp); int init_phase = port ? PHASE_PORT1 : PHASE_PORT0; u32 low, high; - u32 val; + u32 val, reg; DP(NETIF_MSG_HW, "starting port init port %d\n", port); @@ -7271,6 +7297,17 @@ static int bnx2x_init_hw_port(struct bnx2x *bp) val |= CHIP_IS_E1(bp) ? 0 : 0x10; REG_WR(bp, MISC_REG_AEU_MASK_ATTN_FUNC_0 + port*4, val); + /* SCPAD_PARITY should NOT trigger close the gates */ + reg = port ? MISC_REG_AEU_ENABLE4_NIG_1 : MISC_REG_AEU_ENABLE4_NIG_0; + REG_WR(bp, reg, + REG_RD(bp, reg) & + ~AEU_INPUTS_ATTN_BITS_MCP_LATCHED_SCPAD_PARITY); + + reg = port ? MISC_REG_AEU_ENABLE4_PXP_1 : MISC_REG_AEU_ENABLE4_PXP_0; + REG_WR(bp, reg, + REG_RD(bp, reg) & + ~AEU_INPUTS_ATTN_BITS_MCP_LATCHED_SCPAD_PARITY); + bnx2x_init_block(bp, BLOCK_NIG, init_phase); if (!CHIP_IS_E1x(bp)) { @@ -11685,9 +11722,6 @@ static int bnx2x_init_bp(struct bnx2x *bp) static int bnx2x_open(struct net_device *dev) { struct bnx2x *bp = netdev_priv(dev); - bool global = false; - int other_engine = BP_PATH(bp) ? 0 : 1; - bool other_load_status, load_status; int rc; bp->stats_init = true; @@ -11703,6 +11737,10 @@ static int bnx2x_open(struct net_device *dev) * Parity recovery is only relevant for PF driver. */ if (IS_PF(bp)) { + int other_engine = BP_PATH(bp) ? 0 : 1; + bool other_load_status, load_status; + bool global = false; + other_load_status = bnx2x_get_load_status(bp, other_engine); load_status = bnx2x_get_load_status(bp, BP_PATH(bp)); if (!bnx2x_reset_is_done(bp, BP_PATH(bp)) || @@ -12079,13 +12117,8 @@ static int bnx2x_set_coherency_mask(struct bnx2x *bp) { struct device *dev = &bp->pdev->dev; - if (dma_set_mask(dev, DMA_BIT_MASK(64)) == 0) { - bp->flags |= USING_DAC_FLAG; - if (dma_set_coherent_mask(dev, DMA_BIT_MASK(64)) != 0) { - dev_err(dev, "dma_set_coherent_mask failed, aborting\n"); - return -EIO; - } - } else if (dma_set_mask(dev, DMA_BIT_MASK(32)) != 0) { + if (dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)) != 0 && + dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32)) != 0) { dev_err(dev, "System does not support DMA, aborting\n"); return -EIO; } @@ -12248,8 +12281,7 @@ static int bnx2x_init_dev(struct bnx2x *bp, struct pci_dev *pdev, NETIF_F_TSO | NETIF_F_TSO_ECN | NETIF_F_TSO6 | NETIF_F_HIGHDMA; dev->features |= dev->hw_features | NETIF_F_HW_VLAN_CTAG_RX; - if (bp->flags & USING_DAC_FLAG) - dev->features |= NETIF_F_HIGHDMA; + dev->features |= NETIF_F_HIGHDMA; /* Add Loopback capability to the device */ dev->hw_features |= NETIF_F_LOOPBACK; @@ -12612,24 +12644,24 @@ static int set_max_cos_est(int chip_id) return BNX2X_MULTI_TX_COS_E1X; case BCM57712: case BCM57712_MF: - case BCM57712_VF: return BNX2X_MULTI_TX_COS_E2_E3A0; case BCM57800: case BCM57800_MF: - case BCM57800_VF: case BCM57810: case BCM57810_MF: case BCM57840_4_10: case BCM57840_2_20: case BCM57840_O: case BCM57840_MFO: - case BCM57810_VF: case BCM57840_MF: - case BCM57840_VF: case BCM57811: case BCM57811_MF: - case BCM57811_VF: return BNX2X_MULTI_TX_COS_E3B0; + case BCM57712_VF: + case BCM57800_VF: + case BCM57810_VF: + case BCM57840_VF: + case BCM57811_VF: return 1; default: pr_err("Unknown board_type (%d), aborting\n", chip_id); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c index 9ad012bdd915..5e07efb6ec13 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c @@ -470,10 +470,10 @@ static int bnx2x_vfop_qdtor_cmd(struct bnx2x *bp, bnx2x_vfop_qdtor, cmd->done); return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_qdtor, cmd->block); + } else { + BNX2X_ERR("VF[%d] failed to add a vfop\n", vf->abs_vfid); + return -ENOMEM; } - DP(BNX2X_MSG_IOV, "VF[%d] failed to add a vfop. rc %d\n", - vf->abs_vfid, vfop->rc); - return -ENOMEM; } static void @@ -2018,6 +2018,8 @@ failed: void bnx2x_iov_remove_one(struct bnx2x *bp) { + int vf_idx; + /* if SRIOV is not enabled there's nothing to do */ if (!IS_SRIOV(bp)) return; @@ -2026,6 +2028,18 @@ void bnx2x_iov_remove_one(struct bnx2x *bp) pci_disable_sriov(bp->pdev); DP(BNX2X_MSG_IOV, "sriov disabled\n"); + /* disable access to all VFs */ + for (vf_idx = 0; vf_idx < bp->vfdb->sriov.total; vf_idx++) { + bnx2x_pretend_func(bp, + HW_VF_HANDLE(bp, + bp->vfdb->sriov.first_vf_in_pf + + vf_idx)); + DP(BNX2X_MSG_IOV, "disabling internal access for vf %d\n", + bp->vfdb->sriov.first_vf_in_pf + vf_idx); + bnx2x_vf_enable_internal(bp, 0); + bnx2x_pretend_func(bp, BP_ABS_FUNC(bp)); + } + /* free vf database */ __bnx2x_iov_free_vfdb(bp); } @@ -3197,7 +3211,7 @@ int bnx2x_enable_sriov(struct bnx2x *bp) * the "acquire" messages to appear on the VF PF channel. */ DP(BNX2X_MSG_IOV, "about to call enable sriov\n"); - pci_disable_sriov(bp->pdev); + bnx2x_disable_sriov(bp); rc = pci_enable_sriov(bp->pdev, req_vfs); if (rc) { BNX2X_ERR("pci_enable_sriov failed with %d\n", rc); @@ -3390,14 +3404,16 @@ int bnx2x_set_vf_mac(struct net_device *dev, int vfidx, u8 *mac) rc = bnx2x_del_all_macs(bp, mac_obj, BNX2X_ETH_MAC, true); if (rc) { BNX2X_ERR("failed to delete eth macs\n"); - return -EINVAL; + rc = -EINVAL; + goto out; } /* remove existing uc list macs */ rc = bnx2x_del_all_macs(bp, mac_obj, BNX2X_UC_LIST_MAC, true); if (rc) { BNX2X_ERR("failed to delete uc_list macs\n"); - return -EINVAL; + rc = -EINVAL; + goto out; } /* configure the new mac to device */ @@ -3405,6 +3421,7 @@ int bnx2x_set_vf_mac(struct net_device *dev, int vfidx, u8 *mac) bnx2x_set_mac_one(bp, (u8 *)&bulletin->mac, mac_obj, true, BNX2X_ETH_MAC, &ramrod_flags); +out: bnx2x_unlock_vf_pf_channel(bp, vf, CHANNEL_TLV_PF_SET_MAC); } @@ -3467,7 +3484,8 @@ int bnx2x_set_vf_vlan(struct net_device *dev, int vfidx, u16 vlan, u8 qos) &ramrod_flags); if (rc) { BNX2X_ERR("failed to delete vlans\n"); - return -EINVAL; + rc = -EINVAL; + goto out; } /* send queue update ramrod to configure default vlan and silent @@ -3501,7 +3519,8 @@ int bnx2x_set_vf_vlan(struct net_device *dev, int vfidx, u16 vlan, u8 qos) rc = bnx2x_config_vlan_mac(bp, &ramrod_param); if (rc) { BNX2X_ERR("failed to configure vlan\n"); - return -EINVAL; + rc = -EINVAL; + goto out; } /* configure default vlan to vf queue and set silent @@ -3519,18 +3538,18 @@ int bnx2x_set_vf_vlan(struct net_device *dev, int vfidx, u16 vlan, u8 qos) rc = bnx2x_queue_state_change(bp, &q_params); if (rc) { BNX2X_ERR("Failed to configure default VLAN\n"); - return rc; + goto out; } /* clear the flag indicating that this VF needs its vlan - * (will only be set if the HV configured th Vlan before vf was - * and we were called because the VF came up later + * (will only be set if the HV configured the Vlan before vf was + * up and we were called because the VF came up later */ +out: vf->cfg_flags &= ~VF_CFG_VLAN; - bnx2x_unlock_vf_pf_channel(bp, vf, CHANNEL_TLV_PF_SET_VLAN); } - return 0; + return rc; } /* crc is the first field in the bulletin board. Compute the crc over the diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c index 86436c77af03..3b75070411aa 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c @@ -196,7 +196,7 @@ static void bnx2x_hw_stats_post(struct bnx2x *bp) } else if (bp->func_stx) { *stats_comp = 0; - bnx2x_post_dmae(bp, dmae, INIT_DMAE_C(bp)); + bnx2x_issue_dmae_with_comp(bp, dmae, stats_comp); } } diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c index da16953eb2ec..28757dfacf0d 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c @@ -980,7 +980,7 @@ static int bnx2x_copy32_vf_dmae(struct bnx2x *bp, u8 from_vf, dmae.len = len32; /* issue the command and wait for completion */ - return bnx2x_issue_dmae_with_comp(bp, &dmae); + return bnx2x_issue_dmae_with_comp(bp, &dmae, bnx2x_sp(bp, wb_comp)); } static void bnx2x_vf_mbx_resp(struct bnx2x *bp, struct bnx2x_virtf *vf) diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c index b78e69e0e52a..45ce6e2214b3 100644 --- a/drivers/net/ethernet/brocade/bna/bnad.c +++ b/drivers/net/ethernet/brocade/bna/bnad.c @@ -3300,17 +3300,12 @@ bnad_pci_init(struct bnad *bnad, err = pci_request_regions(pdev, BNAD_NAME); if (err) goto disable_device; - if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)) && - !dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64))) { + if (!dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64))) { *using_dac = true; } else { - err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); - if (err) { - err = dma_set_coherent_mask(&pdev->dev, - DMA_BIT_MASK(32)); - if (err) - goto release_regions; - } + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (err) + goto release_regions; *using_dac = false; } pci_set_master(pdev); diff --git a/drivers/net/ethernet/calxeda/xgmac.c b/drivers/net/ethernet/calxeda/xgmac.c index 78d6d6b970e1..48f52882a22b 100644 --- a/drivers/net/ethernet/calxeda/xgmac.c +++ b/drivers/net/ethernet/calxeda/xgmac.c @@ -106,7 +106,6 @@ #define XGMAC_DMA_HW_FEATURE 0x00000f58 /* Enabled Hardware Features */ #define XGMAC_ADDR_AE 0x80000000 -#define XGMAC_MAX_FILTER_ADDR 31 /* PMT Control and Status */ #define XGMAC_PMT_POINTER_RESET 0x80000000 @@ -384,6 +383,7 @@ struct xgmac_priv { struct device *device; struct napi_struct napi; + int max_macs; struct xgmac_extra_stats xstats; spinlock_t stats_lock; @@ -1291,14 +1291,12 @@ static void xgmac_set_rx_mode(struct net_device *dev) netdev_dbg(priv->dev, "# mcasts %d, # unicast %d\n", netdev_mc_count(dev), netdev_uc_count(dev)); - if (dev->flags & IFF_PROMISC) { - writel(XGMAC_FRAME_FILTER_PR, ioaddr + XGMAC_FRAME_FILTER); - return; - } + if (dev->flags & IFF_PROMISC) + value |= XGMAC_FRAME_FILTER_PR; memset(hash_filter, 0, sizeof(hash_filter)); - if (netdev_uc_count(dev) > XGMAC_MAX_FILTER_ADDR) { + if (netdev_uc_count(dev) > priv->max_macs) { use_hash = true; value |= XGMAC_FRAME_FILTER_HUC | XGMAC_FRAME_FILTER_HPF; } @@ -1321,7 +1319,7 @@ static void xgmac_set_rx_mode(struct net_device *dev) goto out; } - if ((netdev_mc_count(dev) + reg - 1) > XGMAC_MAX_FILTER_ADDR) { + if ((netdev_mc_count(dev) + reg - 1) > priv->max_macs) { use_hash = true; value |= XGMAC_FRAME_FILTER_HMC | XGMAC_FRAME_FILTER_HPF; } else { @@ -1342,8 +1340,8 @@ static void xgmac_set_rx_mode(struct net_device *dev) } out: - for (i = reg; i < XGMAC_MAX_FILTER_ADDR; i++) - xgmac_set_mac_addr(ioaddr, NULL, reg); + for (i = reg; i <= priv->max_macs; i++) + xgmac_set_mac_addr(ioaddr, NULL, i); for (i = 0; i < XGMAC_NUM_HASH; i++) writel(hash_filter[i], ioaddr + XGMAC_HASH(i)); @@ -1761,6 +1759,13 @@ static int xgmac_probe(struct platform_device *pdev) uid = readl(priv->base + XGMAC_VERSION); netdev_info(ndev, "h/w version is 0x%x\n", uid); + /* Figure out how many valid mac address filter registers we have */ + writel(1, priv->base + XGMAC_ADDR_HIGH(31)); + if (readl(priv->base + XGMAC_ADDR_HIGH(31)) == 1) + priv->max_macs = 31; + else + priv->max_macs = 7; + writel(0, priv->base + XGMAC_DMA_INTR_ENA); ndev->irq = platform_get_irq(pdev, 0); if (ndev->irq == -ENXIO) { diff --git a/drivers/net/ethernet/chelsio/cxgb3/sge.c b/drivers/net/ethernet/chelsio/cxgb3/sge.c index 9c89dc8fe105..632b318eb38a 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb3/sge.c @@ -1599,7 +1599,8 @@ static void write_ofld_wr(struct adapter *adap, struct sk_buff *skb, flits = skb_transport_offset(skb) / 8; sgp = ndesc == 1 ? (struct sg_ent *)&d->flit[flits] : sgl; sgl_flits = make_sgl(skb, sgp, skb_transport_header(skb), - skb->tail - skb->transport_header, + skb_tail_pointer(skb) - + skb_transport_header(skb), adap->pdev); if (need_skb_unmap()) { setup_deferred_unmapping(skb, adap->pdev, sgp, sgl_flits); diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c index 5f5896e522d2..a7a941b1a655 100644 --- a/drivers/net/ethernet/davicom/dm9000.c +++ b/drivers/net/ethernet/davicom/dm9000.c @@ -158,18 +158,6 @@ static inline board_info_t *to_dm9000_board(struct net_device *dev) /* DM9000 network board routine ---------------------------- */ -static void -dm9000_reset(board_info_t * db) -{ - dev_dbg(db->dev, "resetting device\n"); - - /* RESET device */ - writeb(DM9000_NCR, db->io_addr); - udelay(200); - writeb(NCR_RST, db->io_data); - udelay(200); -} - /* * Read a byte from I/O port */ @@ -191,6 +179,27 @@ iow(board_info_t * db, int reg, int value) writeb(value, db->io_data); } +static void +dm9000_reset(board_info_t *db) +{ + dev_dbg(db->dev, "resetting device\n"); + + /* Reset DM9000, see DM9000 Application Notes V1.22 Jun 11, 2004 page 29 + * The essential point is that we have to do a double reset, and the + * instruction is to set LBK into MAC internal loopback mode. + */ + iow(db, DM9000_NCR, 0x03); + udelay(100); /* Application note says at least 20 us */ + if (ior(db, DM9000_NCR) & 1) + dev_err(db->dev, "dm9000 did not respond to first reset\n"); + + iow(db, DM9000_NCR, 0); + iow(db, DM9000_NCR, 0x03); + udelay(100); + if (ior(db, DM9000_NCR) & 1) + dev_err(db->dev, "dm9000 did not respond to second reset\n"); +} + /* routines for sending block to chip */ static void dm9000_outblk_8bit(void __iomem *reg, void *data, int count) @@ -744,15 +753,20 @@ static const struct ethtool_ops dm9000_ethtool_ops = { static void dm9000_show_carrier(board_info_t *db, unsigned carrier, unsigned nsr) { + int lpa; struct net_device *ndev = db->ndev; + struct mii_if_info *mii = &db->mii; unsigned ncr = dm9000_read_locked(db, DM9000_NCR); - if (carrier) - dev_info(db->dev, "%s: link up, %dMbps, %s-duplex, no LPA\n", + if (carrier) { + lpa = mii->mdio_read(mii->dev, mii->phy_id, MII_LPA); + dev_info(db->dev, + "%s: link up, %dMbps, %s-duplex, lpa 0x%04X\n", ndev->name, (nsr & NSR_SPEED) ? 10 : 100, - (ncr & NCR_FDX) ? "full" : "half"); - else + (ncr & NCR_FDX) ? "full" : "half", lpa); + } else { dev_info(db->dev, "%s: link down\n", ndev->name); + } } static void @@ -890,9 +904,15 @@ dm9000_init_dm9000(struct net_device *dev) (dev->features & NETIF_F_RXCSUM) ? RCSR_CSUM : 0); iow(db, DM9000_GPCR, GPCR_GEP_CNTL); /* Let GPIO0 output */ + iow(db, DM9000_GPR, 0); - dm9000_phy_write(dev, 0, MII_BMCR, BMCR_RESET); /* PHY RESET */ - dm9000_phy_write(dev, 0, MII_DM_DSPCR, DSPCR_INIT_PARAM); /* Init */ + /* If we are dealing with DM9000B, some extra steps are required: a + * manual phy reset, and setting init params. + */ + if (db->type == TYPE_DM9000B) { + dm9000_phy_write(dev, 0, MII_BMCR, BMCR_RESET); + dm9000_phy_write(dev, 0, MII_DM_DSPCR, DSPCR_INIT_PARAM); + } ncr = (db->flags & DM9000_PLATF_EXT_PHY) ? NCR_EXT_PHY : 0; diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h index db020230bd0b..c99dac6a9ddf 100644 --- a/drivers/net/ethernet/emulex/benet/be.h +++ b/drivers/net/ethernet/emulex/benet/be.h @@ -696,6 +696,15 @@ static inline int qnq_async_evt_rcvd(struct be_adapter *adapter) return adapter->flags & BE_FLAGS_QNQ_ASYNC_EVT_RCVD; } +static inline int fw_major_num(const char *fw_ver) +{ + int fw_major = 0; + + sscanf(fw_ver, "%d.", &fw_major); + + return fw_major; +} + extern void be_cq_notify(struct be_adapter *adapter, u16 qid, bool arm, u16 num_popped); extern void be_link_status_update(struct be_adapter *adapter, u8 link_status); diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index bd0e0c0bbcd8..c08fd32bb8e5 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -1198,7 +1198,6 @@ int be_cmd_txq_create(struct be_adapter *adapter, struct be_tx_obj *txo) if (lancer_chip(adapter)) { req->hdr.version = 1; - req->if_id = cpu_to_le16(adapter->if_handle); } else if (BEx_chip(adapter)) { if (adapter->function_caps & BE_FUNCTION_CAPS_SUPER_NIC) req->hdr.version = 2; @@ -1206,6 +1205,8 @@ int be_cmd_txq_create(struct be_adapter *adapter, struct be_tx_obj *txo) req->hdr.version = 2; } + if (req->hdr.version > 0) + req->if_id = cpu_to_le16(adapter->if_handle); req->num_pages = PAGES_4K_SPANNED(q_mem->va, q_mem->size); req->ulp_num = BE_ULP1_NUM; req->type = BE_ETH_TX_RING_TYPE_STANDARD; diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 2c38cc402119..f15ccf03c273 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -3247,6 +3247,12 @@ static int be_setup(struct be_adapter *adapter) be_cmd_get_fw_ver(adapter, adapter->fw_ver, adapter->fw_on_flash); + if (BE2_chip(adapter) && fw_major_num(adapter->fw_ver) < 4) { + dev_err(dev, "Firmware on card is old(%s), IRQs may not work.", + adapter->fw_ver); + dev_err(dev, "Please upgrade firmware to version >= 4.0\n"); + } + if (adapter->vlans_added) be_vid_config(adapter); @@ -4351,19 +4357,11 @@ static int be_probe(struct pci_dev *pdev, const struct pci_device_id *pdev_id) adapter->netdev = netdev; SET_NETDEV_DEV(netdev, &pdev->dev); - status = dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)); + status = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); if (!status) { - status = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64)); - if (status < 0) { - dev_err(&pdev->dev, "dma_set_coherent_mask failed\n"); - goto free_netdev; - } netdev->features |= NETIF_F_HIGHDMA; } else { - status = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); - if (!status) - status = dma_set_coherent_mask(&pdev->dev, - DMA_BIT_MASK(32)); + status = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); if (status) { dev_err(&pdev->dev, "Could not set PCI DMA Mask\n"); goto free_netdev; diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index c4eaadeb572f..9fbe4dda7a0e 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -88,6 +88,7 @@ #include <asm/io.h> #include <asm/reg.h> +#include <asm/mpc85xx.h> #include <asm/irq.h> #include <asm/uaccess.h> #include <linux/module.h> @@ -939,9 +940,8 @@ static void gfar_init_filer_table(struct gfar_private *priv) } } -static void gfar_detect_errata(struct gfar_private *priv) +static void __gfar_detect_errata_83xx(struct gfar_private *priv) { - struct device *dev = &priv->ofdev->dev; unsigned int pvr = mfspr(SPRN_PVR); unsigned int svr = mfspr(SPRN_SVR); unsigned int mod = (svr >> 16) & 0xfff6; /* w/o E suffix */ @@ -957,15 +957,33 @@ static void gfar_detect_errata(struct gfar_private *priv) (pvr == 0x80861010 && (mod & 0xfff9) == 0x80c0)) priv->errata |= GFAR_ERRATA_76; - /* MPC8313 and MPC837x all rev */ - if ((pvr == 0x80850010 && mod == 0x80b0) || - (pvr == 0x80861010 && (mod & 0xfff9) == 0x80c0)) - priv->errata |= GFAR_ERRATA_A002; + /* MPC8313 Rev < 2.0 */ + if (pvr == 0x80850010 && mod == 0x80b0 && rev < 0x0020) + priv->errata |= GFAR_ERRATA_12; +} - /* MPC8313 Rev < 2.0, MPC8548 rev 2.0 */ - if ((pvr == 0x80850010 && mod == 0x80b0 && rev < 0x0020) || - (pvr == 0x80210020 && mod == 0x8030 && rev == 0x0020)) +static void __gfar_detect_errata_85xx(struct gfar_private *priv) +{ + unsigned int svr = mfspr(SPRN_SVR); + + if ((SVR_SOC_VER(svr) == SVR_8548) && (SVR_REV(svr) == 0x20)) priv->errata |= GFAR_ERRATA_12; + if (((SVR_SOC_VER(svr) == SVR_P2020) && (SVR_REV(svr) < 0x20)) || + ((SVR_SOC_VER(svr) == SVR_P2010) && (SVR_REV(svr) < 0x20))) + priv->errata |= GFAR_ERRATA_76; /* aka eTSEC 20 */ +} + +static void gfar_detect_errata(struct gfar_private *priv) +{ + struct device *dev = &priv->ofdev->dev; + + /* no plans to fix */ + priv->errata |= GFAR_ERRATA_A002; + + if (pvr_version_is(PVR_VER_E500V1) || pvr_version_is(PVR_VER_E500V2)) + __gfar_detect_errata_85xx(priv); + else /* non-mpc85xx parts, i.e. e300 core based */ + __gfar_detect_errata_83xx(priv); if (priv->errata) dev_info(dev, "enabled errata workarounds, flags: 0x%x\n", @@ -1599,7 +1617,7 @@ static int __gfar_is_rx_idle(struct gfar_private *priv) /* Normaly TSEC should not hang on GRS commands, so we should * actually wait for IEVENT_GRSC flag. */ - if (likely(!gfar_has_errata(priv, GFAR_ERRATA_A002))) + if (!gfar_has_errata(priv, GFAR_ERRATA_A002)) return 0; /* Read the eTSEC register at offset 0xD1C. If bits 7-14 are diff --git a/drivers/net/ethernet/ibm/emac/mal.c b/drivers/net/ethernet/ibm/emac/mal.c index dac564c25440..e7847510eda2 100644 --- a/drivers/net/ethernet/ibm/emac/mal.c +++ b/drivers/net/ethernet/ibm/emac/mal.c @@ -263,7 +263,9 @@ static inline void mal_schedule_poll(struct mal_instance *mal) { if (likely(napi_schedule_prep(&mal->napi))) { MAL_DBG2(mal, "schedule_poll" NL); + spin_lock(&mal->lock); mal_disable_eob_irq(mal); + spin_unlock(&mal->lock); __napi_schedule(&mal->napi); } else MAL_DBG2(mal, "already in poll" NL); @@ -442,15 +444,13 @@ static int mal_poll(struct napi_struct *napi, int budget) if (unlikely(mc->ops->peek_rx(mc->dev) || test_bit(MAL_COMMAC_RX_STOPPED, &mc->flags))) { MAL_DBG2(mal, "rotting packet" NL); - if (napi_reschedule(napi)) - mal_disable_eob_irq(mal); - else - MAL_DBG2(mal, "already in poll list" NL); - - if (budget > 0) - goto again; - else + if (!napi_reschedule(napi)) goto more_work; + + spin_lock_irqsave(&mal->lock, flags); + mal_disable_eob_irq(mal); + spin_unlock_irqrestore(&mal->lock, flags); + goto again; } mc->ops->poll_tx(mc->dev); } diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index 59ad007dd5aa..34672f87726c 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -1018,19 +1018,14 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) */ pci_using_dac = 0; if ((hw->bus_type == e1000_bus_type_pcix) && - !dma_set_mask(&pdev->dev, DMA_BIT_MASK(64))) { - /* according to DMA-API-HOWTO, coherent calls will always - * succeed if the set call did - */ - dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64)); + !dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64))) { pci_using_dac = 1; } else { - err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); if (err) { pr_err("No usable DMA config, aborting\n"); goto err_dma; } - dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)); } netdev->netdev_ops = &e1000_netdev_ops; diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 4ef786775acb..aedd5736a87d 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -6553,21 +6553,15 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) return err; pci_using_dac = 0; - err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)); + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); if (!err) { - err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64)); - if (!err) - pci_using_dac = 1; + pci_using_dac = 1; } else { - err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); if (err) { - err = dma_set_coherent_mask(&pdev->dev, - DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, - "No usable DMA configuration, aborting\n"); - goto err_dma; - } + dev_err(&pdev->dev, + "No usable DMA configuration, aborting\n"); + goto err_dma; } } diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index 86d51429a189..151e00cad113 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -2655,6 +2655,8 @@ static int igb_set_eee(struct net_device *netdev, (hw->phy.media_type != e1000_media_type_copper)) return -EOPNOTSUPP; + memset(&eee_curr, 0, sizeof(struct ethtool_eee)); + ret_val = igb_get_eee(netdev, &eee_curr); if (ret_val) return ret_val; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 8cf44f2a8ccd..7579383c584d 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -2034,21 +2034,15 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) return err; pci_using_dac = 0; - err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)); + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); if (!err) { - err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64)); - if (!err) - pci_using_dac = 1; + pci_using_dac = 1; } else { - err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); if (err) { - err = dma_set_coherent_mask(&pdev->dev, - DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, - "No usable DMA configuration, aborting\n"); - goto err_dma; - } + dev_err(&pdev->dev, + "No usable DMA configuration, aborting\n"); + goto err_dma; } } diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index 93eb7ee06d3e..4e6b02fbe652 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -2638,21 +2638,15 @@ static int igbvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) return err; pci_using_dac = 0; - err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)); + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); if (!err) { - err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64)); - if (!err) - pci_using_dac = 1; + pci_using_dac = 1; } else { - err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); if (err) { - err = dma_set_coherent_mask(&pdev->dev, - DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, "No usable DMA " - "configuration, aborting\n"); - goto err_dma; - } + dev_err(&pdev->dev, "No usable DMA " + "configuration, aborting\n"); + goto err_dma; } } diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c index 9f6b236828e6..57e390cbe6d0 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c @@ -408,20 +408,14 @@ ixgb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) return err; pci_using_dac = 0; - err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)); + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); if (!err) { - err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64)); - if (!err) - pci_using_dac = 1; + pci_using_dac = 1; } else { - err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); if (err) { - err = dma_set_coherent_mask(&pdev->dev, - DMA_BIT_MASK(32)); - if (err) { - pr_err("No usable DMA configuration, aborting\n"); - goto err_dma_mask; - } + pr_err("No usable DMA configuration, aborting\n"); + goto err_dma_mask; } } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 0ade0cd5ef53..bf046e14ceb5 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -7490,19 +7490,14 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) return err; - if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)) && - !dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64))) { + if (!dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64))) { pci_using_dac = 1; } else { - err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); if (err) { - err = dma_set_coherent_mask(&pdev->dev, - DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, - "No usable DMA configuration, aborting\n"); - goto err_dma; - } + dev_err(&pdev->dev, + "No usable DMA configuration, aborting\n"); + goto err_dma; } pci_using_dac = 0; } diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 59a62bbfb371..e34c2daac6a0 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -3326,19 +3326,14 @@ static int ixgbevf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) return err; - if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)) && - !dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64))) { + if (!dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64))) { pci_using_dac = 1; } else { - err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); if (err) { - err = dma_set_coherent_mask(&pdev->dev, - DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, "No usable DMA " - "configuration, aborting\n"); - goto err_dma; - } + dev_err(&pdev->dev, "No usable DMA " + "configuration, aborting\n"); + goto err_dma; } pci_using_dac = 0; } diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 7fb5677451f9..2c210ec35d59 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -1131,15 +1131,13 @@ static void mib_counters_update(struct mv643xx_eth_private *mp) p->rx_discard += rdlp(mp, RX_DISCARD_FRAME_CNT); p->rx_overrun += rdlp(mp, RX_OVERRUN_FRAME_CNT); spin_unlock_bh(&mp->mib_counters_lock); - - mod_timer(&mp->mib_counters_timer, jiffies + 30 * HZ); } static void mib_counters_timer_wrapper(unsigned long _mp) { struct mv643xx_eth_private *mp = (void *)_mp; - mib_counters_update(mp); + mod_timer(&mp->mib_counters_timer, jiffies + 30 * HZ); } @@ -2237,6 +2235,7 @@ static int mv643xx_eth_open(struct net_device *dev) mp->int_mask |= INT_TX_END_0 << i; } + add_timer(&mp->mib_counters_timer); port_start(mp); wrlp(mp, INT_MASK_EXT, INT_EXT_LINK_PHY | INT_EXT_TX); @@ -2534,6 +2533,7 @@ static int mv643xx_eth_shared_of_add_port(struct platform_device *pdev, if (!ppdev) return -ENOMEM; ppdev->dev.coherent_dma_mask = DMA_BIT_MASK(32); + ppdev->dev.of_node = pnp; ret = platform_device_add_resources(ppdev, &res, 1); if (ret) @@ -2916,7 +2916,6 @@ static int mv643xx_eth_probe(struct platform_device *pdev) mp->mib_counters_timer.data = (unsigned long)mp; mp->mib_counters_timer.function = mib_counters_timer_wrapper; mp->mib_counters_timer.expires = jiffies + 30 * HZ; - add_timer(&mp->mib_counters_timer); spin_lock_init(&mp->mib_counters_lock); diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index ea20182c6969..bb11624a1f39 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -1691,7 +1691,7 @@ static void mlx4_master_deactivate_admin_state(struct mlx4_priv *priv, int slave vp_oper->vlan_idx = NO_INDX; } if (NO_INDX != vp_oper->mac_idx) { - __mlx4_unregister_mac(&priv->dev, port, vp_oper->mac_idx); + __mlx4_unregister_mac(&priv->dev, port, vp_oper->state.mac); vp_oper->mac_idx = NO_INDX; } } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index dec455c8f627..afe2efa69c86 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -70,14 +70,15 @@ static int mlx4_alloc_pages(struct mlx4_en_priv *priv, put_page(page); return -ENOMEM; } - page_alloc->size = PAGE_SIZE << order; + page_alloc->page_size = PAGE_SIZE << order; page_alloc->page = page; page_alloc->dma = dma; - page_alloc->offset = frag_info->frag_align; + page_alloc->page_offset = frag_info->frag_align; /* Not doing get_page() for each frag is a big win * on asymetric workloads. */ - atomic_set(&page->_count, page_alloc->size / frag_info->frag_stride); + atomic_set(&page->_count, + page_alloc->page_size / frag_info->frag_stride); return 0; } @@ -96,16 +97,19 @@ static int mlx4_en_alloc_frags(struct mlx4_en_priv *priv, for (i = 0; i < priv->num_frags; i++) { frag_info = &priv->frag_info[i]; page_alloc[i] = ring_alloc[i]; - page_alloc[i].offset += frag_info->frag_stride; - if (page_alloc[i].offset + frag_info->frag_stride <= ring_alloc[i].size) + page_alloc[i].page_offset += frag_info->frag_stride; + + if (page_alloc[i].page_offset + frag_info->frag_stride <= + ring_alloc[i].page_size) continue; + if (mlx4_alloc_pages(priv, &page_alloc[i], frag_info, gfp)) goto out; } for (i = 0; i < priv->num_frags; i++) { frags[i] = ring_alloc[i]; - dma = ring_alloc[i].dma + ring_alloc[i].offset; + dma = ring_alloc[i].dma + ring_alloc[i].page_offset; ring_alloc[i] = page_alloc[i]; rx_desc->data[i].addr = cpu_to_be64(dma); } @@ -117,7 +121,7 @@ out: frag_info = &priv->frag_info[i]; if (page_alloc[i].page != ring_alloc[i].page) { dma_unmap_page(priv->ddev, page_alloc[i].dma, - page_alloc[i].size, PCI_DMA_FROMDEVICE); + page_alloc[i].page_size, PCI_DMA_FROMDEVICE); page = page_alloc[i].page; atomic_set(&page->_count, 1); put_page(page); @@ -131,10 +135,12 @@ static void mlx4_en_free_frag(struct mlx4_en_priv *priv, int i) { const struct mlx4_en_frag_info *frag_info = &priv->frag_info[i]; + u32 next_frag_end = frags[i].page_offset + 2 * frag_info->frag_stride; + - if (frags[i].offset + frag_info->frag_stride > frags[i].size) - dma_unmap_page(priv->ddev, frags[i].dma, frags[i].size, - PCI_DMA_FROMDEVICE); + if (next_frag_end > frags[i].page_size) + dma_unmap_page(priv->ddev, frags[i].dma, frags[i].page_size, + PCI_DMA_FROMDEVICE); if (frags[i].page) put_page(frags[i].page); @@ -161,7 +167,7 @@ out: page_alloc = &ring->page_alloc[i]; dma_unmap_page(priv->ddev, page_alloc->dma, - page_alloc->size, PCI_DMA_FROMDEVICE); + page_alloc->page_size, PCI_DMA_FROMDEVICE); page = page_alloc->page; atomic_set(&page->_count, 1); put_page(page); @@ -184,10 +190,11 @@ static void mlx4_en_destroy_allocator(struct mlx4_en_priv *priv, i, page_count(page_alloc->page)); dma_unmap_page(priv->ddev, page_alloc->dma, - page_alloc->size, PCI_DMA_FROMDEVICE); - while (page_alloc->offset + frag_info->frag_stride < page_alloc->size) { + page_alloc->page_size, PCI_DMA_FROMDEVICE); + while (page_alloc->page_offset + frag_info->frag_stride < + page_alloc->page_size) { put_page(page_alloc->page); - page_alloc->offset += frag_info->frag_stride; + page_alloc->page_offset += frag_info->frag_stride; } page_alloc->page = NULL; } @@ -478,7 +485,7 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv, /* Save page reference in skb */ __skb_frag_set_page(&skb_frags_rx[nr], frags[nr].page); skb_frag_size_set(&skb_frags_rx[nr], frag_info->frag_size); - skb_frags_rx[nr].page_offset = frags[nr].offset; + skb_frags_rx[nr].page_offset = frags[nr].page_offset; skb->truesize += frag_info->frag_stride; frags[nr].page = NULL; } @@ -517,7 +524,7 @@ static struct sk_buff *mlx4_en_rx_skb(struct mlx4_en_priv *priv, /* Get pointer to first fragment so we could copy the headers into the * (linear part of the) skb */ - va = page_address(frags[0].page) + frags[0].offset; + va = page_address(frags[0].page) + frags[0].page_offset; if (length <= SMALL_PACKET_SIZE) { /* We are copying all relevant data to the skb - temporarily @@ -645,7 +652,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud dma_sync_single_for_cpu(priv->ddev, dma, sizeof(*ethh), DMA_FROM_DEVICE); ethh = (struct ethhdr *)(page_address(frags[0].page) + - frags[0].offset); + frags[0].page_offset); if (is_multicast_ether_addr(ethh->h_dest)) { struct mlx4_mac_entry *entry; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 5e0aa569306a..bf06e3610d27 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -237,8 +237,8 @@ struct mlx4_en_tx_desc { struct mlx4_en_rx_alloc { struct page *page; dma_addr_t dma; - u32 offset; - u32 size; + u32 page_offset; + u32 page_size; }; struct mlx4_en_tx_ring { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 5472cbd34028..6ca30739625f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -180,28 +180,32 @@ static int verify_block_sig(struct mlx5_cmd_prot_block *block) return 0; } -static void calc_block_sig(struct mlx5_cmd_prot_block *block, u8 token) +static void calc_block_sig(struct mlx5_cmd_prot_block *block, u8 token, + int csum) { block->token = token; - block->ctrl_sig = ~xor8_buf(block->rsvd0, sizeof(*block) - sizeof(block->data) - 2); - block->sig = ~xor8_buf(block, sizeof(*block) - 1); + if (csum) { + block->ctrl_sig = ~xor8_buf(block->rsvd0, sizeof(*block) - + sizeof(block->data) - 2); + block->sig = ~xor8_buf(block, sizeof(*block) - 1); + } } -static void calc_chain_sig(struct mlx5_cmd_msg *msg, u8 token) +static void calc_chain_sig(struct mlx5_cmd_msg *msg, u8 token, int csum) { struct mlx5_cmd_mailbox *next = msg->next; while (next) { - calc_block_sig(next->buf, token); + calc_block_sig(next->buf, token, csum); next = next->next; } } -static void set_signature(struct mlx5_cmd_work_ent *ent) +static void set_signature(struct mlx5_cmd_work_ent *ent, int csum) { ent->lay->sig = ~xor8_buf(ent->lay, sizeof(*ent->lay)); - calc_chain_sig(ent->in, ent->token); - calc_chain_sig(ent->out, ent->token); + calc_chain_sig(ent->in, ent->token, csum); + calc_chain_sig(ent->out, ent->token, csum); } static void poll_timeout(struct mlx5_cmd_work_ent *ent) @@ -539,8 +543,7 @@ static void cmd_work_handler(struct work_struct *work) lay->type = MLX5_PCI_CMD_XPORT; lay->token = ent->token; lay->status_own = CMD_OWNER_HW; - if (!cmd->checksum_disabled) - set_signature(ent); + set_signature(ent, !cmd->checksum_disabled); dump_command(dev, ent, 1); ktime_get_ts(&ent->ts1); @@ -773,8 +776,6 @@ static int mlx5_copy_from_msg(void *to, struct mlx5_cmd_msg *from, int size) copy = min_t(int, size, MLX5_CMD_DATA_BLOCK_SIZE); block = next->buf; - if (xor8_buf(block, sizeof(*block)) != 0xff) - return -EINVAL; memcpy(to, block->data, copy); to += copy; @@ -1361,6 +1362,7 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev) goto err_map; } + cmd->checksum_disabled = 1; cmd->max_reg_cmds = (1 << cmd->log_sz) - 1; cmd->bitmask = (1 << cmd->max_reg_cmds) - 1; @@ -1510,7 +1512,7 @@ int mlx5_cmd_status_to_err(struct mlx5_outbox_hdr *hdr) case MLX5_CMD_STAT_BAD_SYS_STATE_ERR: return -EIO; case MLX5_CMD_STAT_BAD_RES_ERR: return -EINVAL; case MLX5_CMD_STAT_RES_BUSY: return -EBUSY; - case MLX5_CMD_STAT_LIM_ERR: return -EINVAL; + case MLX5_CMD_STAT_LIM_ERR: return -ENOMEM; case MLX5_CMD_STAT_BAD_RES_STATE_ERR: return -EINVAL; case MLX5_CMD_STAT_IX_ERR: return -EINVAL; case MLX5_CMD_STAT_NO_RES_ERR: return -EAGAIN; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 443cc4d7b024..2231d93cc7ad 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -366,9 +366,11 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx, goto err_in; } + snprintf(eq->name, MLX5_MAX_EQ_NAME, "%s@pci:%s", + name, pci_name(dev->pdev)); eq->eqn = out.eq_number; err = request_irq(table->msix_arr[vecidx].vector, mlx5_msix_handler, 0, - name, eq); + eq->name, eq); if (err) goto err_eq; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index b47739b0b5f6..bc0f5fb66e24 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -165,9 +165,7 @@ static int handle_hca_cap(struct mlx5_core_dev *dev) struct mlx5_cmd_set_hca_cap_mbox_in *set_ctx = NULL; struct mlx5_cmd_query_hca_cap_mbox_in query_ctx; struct mlx5_cmd_set_hca_cap_mbox_out set_out; - struct mlx5_profile *prof = dev->profile; u64 flags; - int csum = 1; int err; memset(&query_ctx, 0, sizeof(query_ctx)); @@ -197,20 +195,14 @@ static int handle_hca_cap(struct mlx5_core_dev *dev) memcpy(&set_ctx->hca_cap, &query_out->hca_cap, sizeof(set_ctx->hca_cap)); - if (prof->mask & MLX5_PROF_MASK_CMDIF_CSUM) { - csum = !!prof->cmdif_csum; - flags = be64_to_cpu(set_ctx->hca_cap.flags); - if (csum) - flags |= MLX5_DEV_CAP_FLAG_CMDIF_CSUM; - else - flags &= ~MLX5_DEV_CAP_FLAG_CMDIF_CSUM; - - set_ctx->hca_cap.flags = cpu_to_be64(flags); - } - if (dev->profile->mask & MLX5_PROF_MASK_QP_SIZE) set_ctx->hca_cap.log_max_qp = dev->profile->log_max_qp; + flags = be64_to_cpu(query_out->hca_cap.flags); + /* disable checksum */ + flags &= ~MLX5_DEV_CAP_FLAG_CMDIF_CSUM; + + set_ctx->hca_cap.flags = cpu_to_be64(flags); memset(&set_out, 0, sizeof(set_out)); set_ctx->hca_cap.log_uar_page_sz = cpu_to_be16(PAGE_SHIFT - 12); set_ctx->hdr.opcode = cpu_to_be16(MLX5_CMD_OP_SET_HCA_CAP); @@ -225,9 +217,6 @@ static int handle_hca_cap(struct mlx5_core_dev *dev) if (err) goto query_ex; - if (!csum) - dev->cmd.checksum_disabled = 1; - query_ex: kfree(query_out); kfree(set_ctx); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index 3a2408d44820..7b12acf210f8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -90,6 +90,10 @@ struct mlx5_manage_pages_outbox { __be64 pas[0]; }; +enum { + MAX_RECLAIM_TIME_MSECS = 5000, +}; + static int insert_page(struct mlx5_core_dev *dev, u64 addr, struct page *page, u16 func_id) { struct rb_root *root = &dev->priv.page_root; @@ -279,6 +283,9 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages, int err; int i; + if (nclaimed) + *nclaimed = 0; + memset(&in, 0, sizeof(in)); outlen = sizeof(*out) + npages * sizeof(out->pas[0]); out = mlx5_vzalloc(outlen); @@ -388,20 +395,25 @@ static int optimal_reclaimed_pages(void) int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev) { - unsigned long end = jiffies + msecs_to_jiffies(5000); + unsigned long end = jiffies + msecs_to_jiffies(MAX_RECLAIM_TIME_MSECS); struct fw_page *fwp; struct rb_node *p; + int nclaimed = 0; int err; do { p = rb_first(&dev->priv.page_root); if (p) { fwp = rb_entry(p, struct fw_page, rb_node); - err = reclaim_pages(dev, fwp->func_id, optimal_reclaimed_pages(), NULL); + err = reclaim_pages(dev, fwp->func_id, + optimal_reclaimed_pages(), + &nclaimed); if (err) { mlx5_core_warn(dev, "failed reclaiming pages (%d)\n", err); return err; } + if (nclaimed) + end = jiffies + msecs_to_jiffies(MAX_RECLAIM_TIME_MSECS); } if (time_after(jiffies, end)) { mlx5_core_warn(dev, "FW did not return all pages. giving up...\n"); diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c index bd1a2d2bc2ae..ea54d95e5b9f 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.c +++ b/drivers/net/ethernet/moxa/moxart_ether.c @@ -448,7 +448,8 @@ static int moxart_mac_probe(struct platform_device *pdev) irq = irq_of_parse_and_map(node, 0); if (irq <= 0) { netdev_err(ndev, "irq_of_parse_and_map failed\n"); - return -EINVAL; + ret = -EINVAL; + goto irq_map_fail; } priv = netdev_priv(ndev); @@ -472,24 +473,32 @@ static int moxart_mac_probe(struct platform_device *pdev) priv->tx_desc_base = dma_alloc_coherent(NULL, TX_REG_DESC_SIZE * TX_DESC_NUM, &priv->tx_base, GFP_DMA | GFP_KERNEL); - if (priv->tx_desc_base == NULL) + if (priv->tx_desc_base == NULL) { + ret = -ENOMEM; goto init_fail; + } priv->rx_desc_base = dma_alloc_coherent(NULL, RX_REG_DESC_SIZE * RX_DESC_NUM, &priv->rx_base, GFP_DMA | GFP_KERNEL); - if (priv->rx_desc_base == NULL) + if (priv->rx_desc_base == NULL) { + ret = -ENOMEM; goto init_fail; + } priv->tx_buf_base = kmalloc(priv->tx_buf_size * TX_DESC_NUM, GFP_ATOMIC); - if (!priv->tx_buf_base) + if (!priv->tx_buf_base) { + ret = -ENOMEM; goto init_fail; + } priv->rx_buf_base = kmalloc(priv->rx_buf_size * RX_DESC_NUM, GFP_ATOMIC); - if (!priv->rx_buf_base) + if (!priv->rx_buf_base) { + ret = -ENOMEM; goto init_fail; + } platform_set_drvdata(pdev, ndev); @@ -522,7 +531,8 @@ static int moxart_mac_probe(struct platform_device *pdev) init_fail: netdev_err(ndev, "init failed\n"); moxart_mac_free_memory(ndev); - +irq_map_fail: + free_netdev(ndev); return ret; } diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c index a061b93efe66..ba3ca18611f7 100644 --- a/drivers/net/ethernet/nxp/lpc_eth.c +++ b/drivers/net/ethernet/nxp/lpc_eth.c @@ -1399,8 +1399,10 @@ static int lpc_eth_drv_probe(struct platform_device *pdev) } if (pldat->dma_buff_base_v == 0) { - pldat->pdev->dev.coherent_dma_mask = 0xFFFFFFFF; - pldat->pdev->dev.dma_mask = &pldat->pdev->dev.coherent_dma_mask; + ret = dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (ret) + goto err_out_free_irq; + pldat->dma_buff_size = PAGE_ALIGN(pldat->dma_buff_size); /* Allocate a chunk of memory for the DMA ethernet buffers diff --git a/drivers/net/ethernet/octeon/octeon_mgmt.c b/drivers/net/ethernet/octeon/octeon_mgmt.c index 622aa75904c4..2006a0700482 100644 --- a/drivers/net/ethernet/octeon/octeon_mgmt.c +++ b/drivers/net/ethernet/octeon/octeon_mgmt.c @@ -1552,8 +1552,9 @@ static int octeon_mgmt_probe(struct platform_device *pdev) p->phy_np = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0); - pdev->dev.coherent_dma_mask = DMA_BIT_MASK(64); - pdev->dev.dma_mask = &pdev->dev.coherent_dma_mask; + result = dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + if (result) + goto err; netif_carrier_off(netdev); result = register_netdev(netdev); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c index 3ca00e05f23d..ace217c447dd 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c @@ -2276,9 +2276,9 @@ int qlcnic_83xx_get_nic_info(struct qlcnic_adapter *adapter, temp = (cmd.rsp.arg[8] & 0x7FFE0000) >> 17; npar_info->max_linkspeed_reg_offset = temp; } - if (npar_info->capabilities & QLCNIC_FW_CAPABILITY_MORE_CAPS) - memcpy(ahw->extra_capability, &cmd.rsp.arg[16], - sizeof(ahw->extra_capability)); + + memcpy(ahw->extra_capability, &cmd.rsp.arg[16], + sizeof(ahw->extra_capability)); out: qlcnic_free_mbx_args(&cmd); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c index ebe4c86e5230..ff83a9fcd4c5 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c @@ -665,7 +665,7 @@ static int qlcnic_set_channels(struct net_device *dev, return err; } - if (channel->tx_count) { + if (qlcnic_82xx_check(adapter) && channel->tx_count) { err = qlcnic_validate_max_tx_rings(adapter, channel->tx_count); if (err) return err; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c index f8adc7b01f1f..b64e2bef9428 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c @@ -785,8 +785,6 @@ void qlcnic_82xx_config_intr_coalesce(struct qlcnic_adapter *adapter) #define QLCNIC_ENABLE_IPV4_LRO 1 #define QLCNIC_ENABLE_IPV6_LRO 2 -#define QLCNIC_NO_DEST_IPV4_CHECK (1 << 8) -#define QLCNIC_NO_DEST_IPV6_CHECK (2 << 8) int qlcnic_82xx_config_hw_lro(struct qlcnic_adapter *adapter, int enable) { @@ -806,11 +804,10 @@ int qlcnic_82xx_config_hw_lro(struct qlcnic_adapter *adapter, int enable) word = 0; if (enable) { - word = QLCNIC_ENABLE_IPV4_LRO | QLCNIC_NO_DEST_IPV4_CHECK; + word = QLCNIC_ENABLE_IPV4_LRO; if (adapter->ahw->extra_capability[0] & QLCNIC_FW_CAP2_HW_LRO_IPV6) - word |= QLCNIC_ENABLE_IPV6_LRO | - QLCNIC_NO_DEST_IPV6_CHECK; + word |= QLCNIC_ENABLE_IPV6_LRO; } req.words[0] = cpu_to_le64(word); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c index 21d00a0449a1..d8f4897e9e82 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c @@ -1131,7 +1131,10 @@ qlcnic_initialize_nic(struct qlcnic_adapter *adapter) if (err == -EIO) return err; adapter->ahw->extra_capability[0] = temp; + } else { + adapter->ahw->extra_capability[0] = 0; } + adapter->ahw->max_mac_filters = nic_info.max_mac_filters; adapter->ahw->max_mtu = nic_info.max_mtu; @@ -2159,8 +2162,7 @@ void qlcnic_set_drv_version(struct qlcnic_adapter *adapter) else if (qlcnic_83xx_check(adapter)) fw_cmd = QLCNIC_CMD_83XX_SET_DRV_VER; - if ((ahw->capabilities & QLCNIC_FW_CAPABILITY_MORE_CAPS) && - (ahw->extra_capability[0] & QLCNIC_FW_CAPABILITY_SET_DRV_VER)) + if (ahw->extra_capability[0] & QLCNIC_FW_CAPABILITY_SET_DRV_VER) qlcnic_fw_cmd_set_drv_version(adapter, fw_cmd); } @@ -2257,7 +2259,7 @@ qlcnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err = qlcnic_alloc_adapter_resources(adapter); if (err) - goto err_out_free_netdev; + goto err_out_free_wq; adapter->dev_rst_time = jiffies; adapter->ahw->revision_id = pdev->revision; @@ -2396,6 +2398,9 @@ err_out_disable_msi: err_out_free_hw: qlcnic_free_adapter_resources(adapter); +err_out_free_wq: + destroy_workqueue(adapter->qlcnic_wq); + err_out_free_netdev: free_netdev(netdev); @@ -3648,11 +3653,6 @@ int qlcnic_validate_max_tx_rings(struct qlcnic_adapter *adapter, u32 txq) u8 max_hw = QLCNIC_MAX_TX_RINGS; u32 max_allowed; - if (!qlcnic_82xx_check(adapter)) { - netdev_err(netdev, "No Multi TX-Q support\n"); - return -EINVAL; - } - if (!qlcnic_use_msi_x && !qlcnic_use_msi) { netdev_err(netdev, "No Multi TX-Q support in INT-x mode\n"); return -EINVAL; @@ -3692,8 +3692,7 @@ int qlcnic_validate_max_rss(struct qlcnic_adapter *adapter, u8 max_hw = adapter->ahw->max_rx_ques; u32 max_allowed; - if (qlcnic_82xx_check(adapter) && !qlcnic_use_msi_x && - !qlcnic_use_msi) { + if (!qlcnic_use_msi_x && !qlcnic_use_msi) { netdev_err(netdev, "No RSS support in INT-x mode\n"); return -EINVAL; } diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 5cd831ebfa83..b57c278d3b46 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -688,12 +688,16 @@ static struct sh_eth_cpu_data r8a7740_data = { .eesr_err_check = EESR_TWB1 | EESR_TWB | EESR_TABT | EESR_RABT | EESR_RFE | EESR_RDE | EESR_RFRMER | EESR_TFE | EESR_TDE | EESR_ECI, + .fdr_value = 0x0000070f, + .rmcr_value = 0x00000001, .apr = 1, .mpr = 1, .tpauser = 1, .bculr = 1, .hw_swap = 1, + .rpadir = 1, + .rpadir_value = 2 << 16, .no_trimd = 1, .no_ade = 1, .tsu = 1, diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index 9f18ae984f9e..21f9ad6392e9 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -444,6 +444,18 @@ static const struct efx_hw_stat_desc efx_ef10_stat_desc[EF10_STAT_COUNT] = { EF10_DMA_STAT(rx_align_error, RX_ALIGN_ERROR_PKTS), EF10_DMA_STAT(rx_length_error, RX_LENGTH_ERROR_PKTS), EF10_DMA_STAT(rx_nodesc_drops, RX_NODESC_DROPS), + EF10_DMA_STAT(rx_pm_trunc_bb_overflow, PM_TRUNC_BB_OVERFLOW), + EF10_DMA_STAT(rx_pm_discard_bb_overflow, PM_DISCARD_BB_OVERFLOW), + EF10_DMA_STAT(rx_pm_trunc_vfifo_full, PM_TRUNC_VFIFO_FULL), + EF10_DMA_STAT(rx_pm_discard_vfifo_full, PM_DISCARD_VFIFO_FULL), + EF10_DMA_STAT(rx_pm_trunc_qbb, PM_TRUNC_QBB), + EF10_DMA_STAT(rx_pm_discard_qbb, PM_DISCARD_QBB), + EF10_DMA_STAT(rx_pm_discard_mapping, PM_DISCARD_MAPPING), + EF10_DMA_STAT(rx_dp_q_disabled_packets, RXDP_Q_DISABLED_PKTS), + EF10_DMA_STAT(rx_dp_di_dropped_packets, RXDP_DI_DROPPED_PKTS), + EF10_DMA_STAT(rx_dp_streaming_packets, RXDP_STREAMING_PKTS), + EF10_DMA_STAT(rx_dp_emerg_fetch, RXDP_EMERGENCY_FETCH_CONDITIONS), + EF10_DMA_STAT(rx_dp_emerg_wait, RXDP_EMERGENCY_WAIT_CONDITIONS), }; #define HUNT_COMMON_STAT_MASK ((1ULL << EF10_STAT_tx_bytes) | \ @@ -498,44 +510,72 @@ static const struct efx_hw_stat_desc efx_ef10_stat_desc[EF10_STAT_COUNT] = { #define HUNT_40G_EXTRA_STAT_MASK ((1ULL << EF10_STAT_rx_align_error) | \ (1ULL << EF10_STAT_rx_length_error)) -#if BITS_PER_LONG == 64 -#define STAT_MASK_BITMAP(bits) (bits) -#else -#define STAT_MASK_BITMAP(bits) (bits) & 0xffffffff, (bits) >> 32 -#endif - -static const unsigned long *efx_ef10_stat_mask(struct efx_nic *efx) -{ - static const unsigned long hunt_40g_stat_mask[] = { - STAT_MASK_BITMAP(HUNT_COMMON_STAT_MASK | - HUNT_40G_EXTRA_STAT_MASK) - }; - static const unsigned long hunt_10g_only_stat_mask[] = { - STAT_MASK_BITMAP(HUNT_COMMON_STAT_MASK | - HUNT_10G_ONLY_STAT_MASK) - }; +/* These statistics are only provided if the firmware supports the + * capability PM_AND_RXDP_COUNTERS. + */ +#define HUNT_PM_AND_RXDP_STAT_MASK ( \ + (1ULL << EF10_STAT_rx_pm_trunc_bb_overflow) | \ + (1ULL << EF10_STAT_rx_pm_discard_bb_overflow) | \ + (1ULL << EF10_STAT_rx_pm_trunc_vfifo_full) | \ + (1ULL << EF10_STAT_rx_pm_discard_vfifo_full) | \ + (1ULL << EF10_STAT_rx_pm_trunc_qbb) | \ + (1ULL << EF10_STAT_rx_pm_discard_qbb) | \ + (1ULL << EF10_STAT_rx_pm_discard_mapping) | \ + (1ULL << EF10_STAT_rx_dp_q_disabled_packets) | \ + (1ULL << EF10_STAT_rx_dp_di_dropped_packets) | \ + (1ULL << EF10_STAT_rx_dp_streaming_packets) | \ + (1ULL << EF10_STAT_rx_dp_emerg_fetch) | \ + (1ULL << EF10_STAT_rx_dp_emerg_wait)) + +static u64 efx_ef10_raw_stat_mask(struct efx_nic *efx) +{ + u64 raw_mask = HUNT_COMMON_STAT_MASK; u32 port_caps = efx_mcdi_phy_get_caps(efx); + struct efx_ef10_nic_data *nic_data = efx->nic_data; if (port_caps & (1 << MC_CMD_PHY_CAP_40000FDX_LBN)) - return hunt_40g_stat_mask; + raw_mask |= HUNT_40G_EXTRA_STAT_MASK; else - return hunt_10g_only_stat_mask; + raw_mask |= HUNT_10G_ONLY_STAT_MASK; + + if (nic_data->datapath_caps & + (1 << MC_CMD_GET_CAPABILITIES_OUT_PM_AND_RXDP_COUNTERS_LBN)) + raw_mask |= HUNT_PM_AND_RXDP_STAT_MASK; + + return raw_mask; +} + +static void efx_ef10_get_stat_mask(struct efx_nic *efx, unsigned long *mask) +{ + u64 raw_mask = efx_ef10_raw_stat_mask(efx); + +#if BITS_PER_LONG == 64 + mask[0] = raw_mask; +#else + mask[0] = raw_mask & 0xffffffff; + mask[1] = raw_mask >> 32; +#endif } static size_t efx_ef10_describe_stats(struct efx_nic *efx, u8 *names) { + DECLARE_BITMAP(mask, EF10_STAT_COUNT); + + efx_ef10_get_stat_mask(efx, mask); return efx_nic_describe_stats(efx_ef10_stat_desc, EF10_STAT_COUNT, - efx_ef10_stat_mask(efx), names); + mask, names); } static int efx_ef10_try_update_nic_stats(struct efx_nic *efx) { struct efx_ef10_nic_data *nic_data = efx->nic_data; - const unsigned long *stats_mask = efx_ef10_stat_mask(efx); + DECLARE_BITMAP(mask, EF10_STAT_COUNT); __le64 generation_start, generation_end; u64 *stats = nic_data->stats; __le64 *dma_stats; + efx_ef10_get_stat_mask(efx, mask); + dma_stats = efx->stats_buffer.addr; nic_data = efx->nic_data; @@ -543,8 +583,9 @@ static int efx_ef10_try_update_nic_stats(struct efx_nic *efx) if (generation_end == EFX_MC_STATS_GENERATION_INVALID) return 0; rmb(); - efx_nic_update_stats(efx_ef10_stat_desc, EF10_STAT_COUNT, stats_mask, + efx_nic_update_stats(efx_ef10_stat_desc, EF10_STAT_COUNT, mask, stats, efx->stats_buffer.addr, false); + rmb(); generation_start = dma_stats[MC_CMD_MAC_GENERATION_START]; if (generation_end != generation_start) return -EAGAIN; @@ -563,12 +604,14 @@ static int efx_ef10_try_update_nic_stats(struct efx_nic *efx) static size_t efx_ef10_update_stats(struct efx_nic *efx, u64 *full_stats, struct rtnl_link_stats64 *core_stats) { - const unsigned long *mask = efx_ef10_stat_mask(efx); + DECLARE_BITMAP(mask, EF10_STAT_COUNT); struct efx_ef10_nic_data *nic_data = efx->nic_data; u64 *stats = nic_data->stats; size_t stats_count = 0, index; int retry; + efx_ef10_get_stat_mask(efx, mask); + /* If we're unlucky enough to read statistics during the DMA, wait * up to 10ms for it to finish (typically takes <500us) */ diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 07c9bc4c61bc..2e27837ce6a2 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -1121,7 +1121,7 @@ static int efx_init_io(struct efx_nic *efx) */ while (dma_mask > 0x7fffffffUL) { if (dma_supported(&pci_dev->dev, dma_mask)) { - rc = dma_set_mask(&pci_dev->dev, dma_mask); + rc = dma_set_mask_and_coherent(&pci_dev->dev, dma_mask); if (rc == 0) break; } @@ -1134,16 +1134,6 @@ static int efx_init_io(struct efx_nic *efx) } netif_dbg(efx, probe, efx->net_dev, "using DMA mask %llx\n", (unsigned long long) dma_mask); - rc = dma_set_coherent_mask(&pci_dev->dev, dma_mask); - if (rc) { - /* dma_set_coherent_mask() is not *allowed* to - * fail with a mask that dma_set_mask() accepted, - * but just in case... - */ - netif_err(efx, probe, efx->net_dev, - "failed to set consistent DMA mask\n"); - goto fail2; - } efx->membase_phys = pci_resource_start(efx->pci_dev, EFX_MEM_BAR); rc = pci_request_region(pci_dev, EFX_MEM_BAR, "sfc"); diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c index c082562dbf4e..366c8e3e3784 100644 --- a/drivers/net/ethernet/sfc/mcdi.c +++ b/drivers/net/ethernet/sfc/mcdi.c @@ -963,7 +963,7 @@ static int efx_mcdi_drv_attach(struct efx_nic *efx, bool driver_operating, bool *was_attached) { MCDI_DECLARE_BUF(inbuf, MC_CMD_DRV_ATTACH_IN_LEN); - MCDI_DECLARE_BUF(outbuf, MC_CMD_DRV_ATTACH_OUT_LEN); + MCDI_DECLARE_BUF(outbuf, MC_CMD_DRV_ATTACH_EXT_OUT_LEN); size_t outlen; int rc; @@ -981,6 +981,22 @@ static int efx_mcdi_drv_attach(struct efx_nic *efx, bool driver_operating, goto fail; } + /* We currently assume we have control of the external link + * and are completely trusted by firmware. Abort probing + * if that's not true for this function. + */ + if (driver_operating && + outlen >= MC_CMD_DRV_ATTACH_EXT_OUT_LEN && + (MCDI_DWORD(outbuf, DRV_ATTACH_EXT_OUT_FUNC_FLAGS) & + (1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_LINKCTRL | + 1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_TRUSTED)) != + (1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_LINKCTRL | + 1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_TRUSTED)) { + netif_err(efx, probe, efx->net_dev, + "This driver version only supports one function per port\n"); + return -ENODEV; + } + if (was_attached != NULL) *was_attached = MCDI_DWORD(outbuf, DRV_ATTACH_OUT_OLD_STATE); return 0; diff --git a/drivers/net/ethernet/sfc/mcdi_pcol.h b/drivers/net/ethernet/sfc/mcdi_pcol.h index b5cf62492f8e..e0a63ddb7a6c 100644 --- a/drivers/net/ethernet/sfc/mcdi_pcol.h +++ b/drivers/net/ethernet/sfc/mcdi_pcol.h @@ -2574,8 +2574,58 @@ #define MC_CMD_MAC_RX_LANES01_DISP_ERR 0x39 /* enum */ #define MC_CMD_MAC_RX_LANES23_DISP_ERR 0x3a /* enum */ #define MC_CMD_MAC_RX_MATCH_FAULT 0x3b /* enum */ -#define MC_CMD_GMAC_DMABUF_START 0x40 /* enum */ -#define MC_CMD_GMAC_DMABUF_END 0x5f /* enum */ +/* enum: PM trunc_bb_overflow counter. Valid for EF10 with PM_AND_RXDP_COUNTERS + * capability only. + */ +#define MC_CMD_MAC_PM_TRUNC_BB_OVERFLOW 0x3c +/* enum: PM discard_bb_overflow counter. Valid for EF10 with + * PM_AND_RXDP_COUNTERS capability only. + */ +#define MC_CMD_MAC_PM_DISCARD_BB_OVERFLOW 0x3d +/* enum: PM trunc_vfifo_full counter. Valid for EF10 with PM_AND_RXDP_COUNTERS + * capability only. + */ +#define MC_CMD_MAC_PM_TRUNC_VFIFO_FULL 0x3e +/* enum: PM discard_vfifo_full counter. Valid for EF10 with + * PM_AND_RXDP_COUNTERS capability only. + */ +#define MC_CMD_MAC_PM_DISCARD_VFIFO_FULL 0x3f +/* enum: PM trunc_qbb counter. Valid for EF10 with PM_AND_RXDP_COUNTERS + * capability only. + */ +#define MC_CMD_MAC_PM_TRUNC_QBB 0x40 +/* enum: PM discard_qbb counter. Valid for EF10 with PM_AND_RXDP_COUNTERS + * capability only. + */ +#define MC_CMD_MAC_PM_DISCARD_QBB 0x41 +/* enum: PM discard_mapping counter. Valid for EF10 with PM_AND_RXDP_COUNTERS + * capability only. + */ +#define MC_CMD_MAC_PM_DISCARD_MAPPING 0x42 +/* enum: RXDP counter: Number of packets dropped due to the queue being + * disabled. Valid for EF10 with PM_AND_RXDP_COUNTERS capability only. + */ +#define MC_CMD_MAC_RXDP_Q_DISABLED_PKTS 0x43 +/* enum: RXDP counter: Number of packets dropped by the DICPU. Valid for EF10 + * with PM_AND_RXDP_COUNTERS capability only. + */ +#define MC_CMD_MAC_RXDP_DI_DROPPED_PKTS 0x45 +/* enum: RXDP counter: Number of non-host packets. Valid for EF10 with + * PM_AND_RXDP_COUNTERS capability only. + */ +#define MC_CMD_MAC_RXDP_STREAMING_PKTS 0x46 +/* enum: RXDP counter: Number of times an emergency descriptor fetch was + * performed. Valid for EF10 with PM_AND_RXDP_COUNTERS capability only. + */ +#define MC_CMD_MAC_RXDP_EMERGENCY_FETCH_CONDITIONS 0x47 +/* enum: RXDP counter: Number of times the DPCPU waited for an existing + * descriptor fetch. Valid for EF10 with PM_AND_RXDP_COUNTERS capability only. + */ +#define MC_CMD_MAC_RXDP_EMERGENCY_WAIT_CONDITIONS 0x48 +/* enum: Start of GMAC stats buffer space, for Siena only. */ +#define MC_CMD_GMAC_DMABUF_START 0x40 +/* enum: End of GMAC stats buffer space, for Siena only. */ +#define MC_CMD_GMAC_DMABUF_END 0x5f #define MC_CMD_MAC_GENERATION_END 0x60 /* enum */ #define MC_CMD_MAC_NSTATS 0x61 /* enum */ @@ -5065,6 +5115,8 @@ #define MC_CMD_GET_CAPABILITIES_OUT_RX_BATCHING_WIDTH 1 #define MC_CMD_GET_CAPABILITIES_OUT_MCAST_FILTER_CHAINING_LBN 26 #define MC_CMD_GET_CAPABILITIES_OUT_MCAST_FILTER_CHAINING_WIDTH 1 +#define MC_CMD_GET_CAPABILITIES_OUT_PM_AND_RXDP_COUNTERS_LBN 27 +#define MC_CMD_GET_CAPABILITIES_OUT_PM_AND_RXDP_COUNTERS_WIDTH 1 /* RxDPCPU firmware id. */ #define MC_CMD_GET_CAPABILITIES_OUT_RX_DPCPU_FW_ID_OFST 4 #define MC_CMD_GET_CAPABILITIES_OUT_RX_DPCPU_FW_ID_LEN 2 diff --git a/drivers/net/ethernet/sfc/nic.c b/drivers/net/ethernet/sfc/nic.c index e7dbd2dd202e..9826594c8a48 100644 --- a/drivers/net/ethernet/sfc/nic.c +++ b/drivers/net/ethernet/sfc/nic.c @@ -469,8 +469,7 @@ size_t efx_nic_describe_stats(const struct efx_hw_stat_desc *desc, size_t count, * @count: Length of the @desc array * @mask: Bitmask of which elements of @desc are enabled * @stats: Buffer to update with the converted statistics. The length - * of this array must be at least the number of set bits in the - * first @count bits of @mask. + * of this array must be at least @count. * @dma_buf: DMA buffer containing hardware statistics * @accumulate: If set, the converted values will be added rather than * directly stored to the corresponding elements of @stats @@ -503,11 +502,9 @@ void efx_nic_update_stats(const struct efx_hw_stat_desc *desc, size_t count, } if (accumulate) - *stats += val; + stats[index] += val; else - *stats = val; + stats[index] = val; } - - ++stats; } } diff --git a/drivers/net/ethernet/sfc/nic.h b/drivers/net/ethernet/sfc/nic.h index fda29d39032f..890bbbe8320e 100644 --- a/drivers/net/ethernet/sfc/nic.h +++ b/drivers/net/ethernet/sfc/nic.h @@ -386,6 +386,18 @@ enum { EF10_STAT_rx_align_error, EF10_STAT_rx_length_error, EF10_STAT_rx_nodesc_drops, + EF10_STAT_rx_pm_trunc_bb_overflow, + EF10_STAT_rx_pm_discard_bb_overflow, + EF10_STAT_rx_pm_trunc_vfifo_full, + EF10_STAT_rx_pm_discard_vfifo_full, + EF10_STAT_rx_pm_trunc_qbb, + EF10_STAT_rx_pm_discard_qbb, + EF10_STAT_rx_pm_discard_mapping, + EF10_STAT_rx_dp_q_disabled_packets, + EF10_STAT_rx_dp_di_dropped_packets, + EF10_STAT_rx_dp_streaming_packets, + EF10_STAT_rx_dp_emerg_fetch, + EF10_STAT_rx_dp_emerg_wait, EF10_STAT_COUNT }; diff --git a/drivers/net/ethernet/smsc/smc91x.h b/drivers/net/ethernet/smsc/smc91x.h index 5730fe2445a6..98eedb90cdc3 100644 --- a/drivers/net/ethernet/smsc/smc91x.h +++ b/drivers/net/ethernet/smsc/smc91x.h @@ -1124,8 +1124,7 @@ static const char * chip_ids[ 16 ] = { void __iomem *__ioaddr = ioaddr; \ if (__len >= 2 && (unsigned long)__ptr & 2) { \ __len -= 2; \ - SMC_outw(*(u16 *)__ptr, ioaddr, \ - DATA_REG(lp)); \ + SMC_outsw(ioaddr, DATA_REG(lp), __ptr, 1); \ __ptr += 2; \ } \ if (SMC_CAN_USE_DATACS && lp->datacs) \ @@ -1133,8 +1132,7 @@ static const char * chip_ids[ 16 ] = { SMC_outsl(__ioaddr, DATA_REG(lp), __ptr, __len>>2); \ if (__len & 2) { \ __ptr += (__len & ~3); \ - SMC_outw(*((u16 *)__ptr), ioaddr, \ - DATA_REG(lp)); \ + SMC_outsw(ioaddr, DATA_REG(lp), __ptr, 1); \ } \ } else if (SMC_16BIT(lp)) \ SMC_outsw(ioaddr, DATA_REG(lp), p, (l) >> 1); \ diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 79974e31187a..cc3ce557e4aa 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -639,13 +639,6 @@ void cpsw_rx_handler(void *token, int len, int status) static irqreturn_t cpsw_interrupt(int irq, void *dev_id) { struct cpsw_priv *priv = dev_id; - u32 rx, tx, rx_thresh; - - rx_thresh = __raw_readl(&priv->wr_regs->rx_thresh_stat); - rx = __raw_readl(&priv->wr_regs->rx_stat); - tx = __raw_readl(&priv->wr_regs->tx_stat); - if (!rx_thresh && !rx && !tx) - return IRQ_NONE; cpsw_intr_disable(priv); if (priv->irq_enabled == true) { @@ -1169,9 +1162,9 @@ static int cpsw_ndo_open(struct net_device *ndev) } } + napi_enable(&priv->napi); cpdma_ctlr_start(priv->dma); cpsw_intr_enable(priv); - napi_enable(&priv->napi); cpdma_ctlr_eoi(priv->dma, CPDMA_EOI_RX); cpdma_ctlr_eoi(priv->dma, CPDMA_EOI_TX); @@ -1771,8 +1764,8 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data, } data->mac_control = prop; - if (!of_property_read_u32(node, "dual_emac", &prop)) - data->dual_emac = prop; + if (of_property_read_bool(node, "dual_emac")) + data->dual_emac = 1; /* * Populate all the child nodes here... @@ -1782,7 +1775,7 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data, if (ret) pr_warn("Doesn't have any child node\n"); - for_each_node_by_name(slave_node, "slave") { + for_each_child_of_node(node, slave_node) { struct cpsw_slave_data *slave_data = data->slave_data + i; const void *mac_addr = NULL; u32 phyid; @@ -1791,6 +1784,10 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data, struct device_node *mdio_node; struct platform_device *mdio; + /* This is no slave child node, continue */ + if (strcmp(slave_node->name, "slave")) + continue; + parp = of_get_property(slave_node, "phy_id", &lenp); if ((parp == NULL) || (lenp != (sizeof(void *) * 2))) { pr_err("Missing slave[%d] phy_id property\n", i); diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c index 67df09ea9d04..6a32ef9d63ae 100644 --- a/drivers/net/ethernet/ti/davinci_emac.c +++ b/drivers/net/ethernet/ti/davinci_emac.c @@ -876,8 +876,7 @@ static void emac_dev_mcast_set(struct net_device *ndev) netdev_mc_count(ndev) > EMAC_DEF_MAX_MULTICAST_ADDRESSES) { mbp_enable = (mbp_enable | EMAC_MBP_RXMCAST); emac_add_mcast(priv, EMAC_ALL_MULTI_SET, NULL); - } - if (!netdev_mc_empty(ndev)) { + } else if (!netdev_mc_empty(ndev)) { struct netdev_hw_addr *ha; mbp_enable = (mbp_enable | EMAC_MBP_RXMCAST); diff --git a/drivers/net/hamradio/yam.c b/drivers/net/hamradio/yam.c index 0721e72f9299..5af1c3e5032a 100644 --- a/drivers/net/hamradio/yam.c +++ b/drivers/net/hamradio/yam.c @@ -975,7 +975,6 @@ static int yam_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return -EINVAL; /* Cannot change this parameter when up */ if ((ym = kmalloc(sizeof(struct yamdrv_ioctl_mcs), GFP_KERNEL)) == NULL) return -ENOBUFS; - ym->bitrate = 9600; if (copy_from_user(ym, ifr->ifr_data, sizeof(struct yamdrv_ioctl_mcs))) { kfree(ym); return -EFAULT; diff --git a/drivers/net/ieee802154/mrf24j40.c b/drivers/net/ieee802154/mrf24j40.c index 42e6deee6db5..0632d34905c7 100644 --- a/drivers/net/ieee802154/mrf24j40.c +++ b/drivers/net/ieee802154/mrf24j40.c @@ -82,7 +82,6 @@ struct mrf24j40 { struct mutex buffer_mutex; /* only used to protect buf */ struct completion tx_complete; - struct work_struct irqwork; u8 *buf; /* 3 bytes. Used for SPI single-register transfers. */ }; @@ -344,6 +343,8 @@ static int mrf24j40_tx(struct ieee802154_dev *dev, struct sk_buff *skb) if (ret) goto err; + INIT_COMPLETION(devrec->tx_complete); + /* Set TXNTRIG bit of TXNCON to send packet */ ret = read_short_reg(devrec, REG_TXNCON, &val); if (ret) @@ -354,8 +355,6 @@ static int mrf24j40_tx(struct ieee802154_dev *dev, struct sk_buff *skb) val |= 0x4; write_short_reg(devrec, REG_TXNCON, val); - INIT_COMPLETION(devrec->tx_complete); - /* Wait for the device to send the TX complete interrupt. */ ret = wait_for_completion_interruptible_timeout( &devrec->tx_complete, @@ -590,17 +589,6 @@ static struct ieee802154_ops mrf24j40_ops = { static irqreturn_t mrf24j40_isr(int irq, void *data) { struct mrf24j40 *devrec = data; - - disable_irq_nosync(irq); - - schedule_work(&devrec->irqwork); - - return IRQ_HANDLED; -} - -static void mrf24j40_isrwork(struct work_struct *work) -{ - struct mrf24j40 *devrec = container_of(work, struct mrf24j40, irqwork); u8 intstat; int ret; @@ -618,7 +606,7 @@ static void mrf24j40_isrwork(struct work_struct *work) mrf24j40_handle_rx(devrec); out: - enable_irq(devrec->spi->irq); + return IRQ_HANDLED; } static int mrf24j40_probe(struct spi_device *spi) @@ -642,7 +630,6 @@ static int mrf24j40_probe(struct spi_device *spi) mutex_init(&devrec->buffer_mutex); init_completion(&devrec->tx_complete); - INIT_WORK(&devrec->irqwork, mrf24j40_isrwork); devrec->spi = spi; spi_set_drvdata(spi, devrec); @@ -688,11 +675,12 @@ static int mrf24j40_probe(struct spi_device *spi) val &= ~0x3; /* Clear RX mode (normal) */ write_short_reg(devrec, REG_RXMCR, val); - ret = request_irq(spi->irq, - mrf24j40_isr, - IRQF_TRIGGER_FALLING, - dev_name(&spi->dev), - devrec); + ret = request_threaded_irq(spi->irq, + NULL, + mrf24j40_isr, + IRQF_TRIGGER_LOW|IRQF_ONESHOT, + dev_name(&spi->dev), + devrec); if (ret) { dev_err(printdev(devrec), "Unable to get IRQ"); @@ -721,7 +709,6 @@ static int mrf24j40_remove(struct spi_device *spi) dev_dbg(printdev(devrec), "remove\n"); free_irq(spi->irq, devrec); - flush_work(&devrec->irqwork); /* TODO: Is this the right call? */ ieee802154_unregister_device(devrec->dev); ieee802154_free_device(devrec->dev); /* TODO: Will ieee802154_free_device() wait until ->xmit() is diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index adeee615dd19..c9a15925a1f7 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -310,6 +310,7 @@ static ssize_t store_enabled(struct netconsole_target *nt, const char *buf, size_t count) { + unsigned long flags; int enabled; int err; @@ -324,9 +325,7 @@ static ssize_t store_enabled(struct netconsole_target *nt, return -EINVAL; } - mutex_lock(&nt->mutex); if (enabled) { /* 1 */ - /* * Skip netpoll_parse_options() -- all the attributes are * already configured via configfs. Just print them out. @@ -334,19 +333,22 @@ static ssize_t store_enabled(struct netconsole_target *nt, netpoll_print_options(&nt->np); err = netpoll_setup(&nt->np); - if (err) { - mutex_unlock(&nt->mutex); + if (err) return err; - } printk(KERN_INFO "netconsole: network logging started\n"); - } else { /* 0 */ + /* We need to disable the netconsole before cleaning it up + * otherwise we might end up in write_msg() with + * nt->np.dev == NULL and nt->enabled == 1 + */ + spin_lock_irqsave(&target_list_lock, flags); + nt->enabled = 0; + spin_unlock_irqrestore(&target_list_lock, flags); netpoll_cleanup(&nt->np); } nt->enabled = enabled; - mutex_unlock(&nt->mutex); return strnlen(buf, count); } @@ -563,8 +565,10 @@ static ssize_t netconsole_target_attr_store(struct config_item *item, struct netconsole_target_attr *na = container_of(attr, struct netconsole_target_attr, attr); + mutex_lock(&nt->mutex); if (na->store) ret = na->store(nt, buf, count); + mutex_unlock(&nt->mutex); return ret; } diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 807815fc9968..7cb105c103fe 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1293,7 +1293,8 @@ static ssize_t tun_do_read(struct tun_struct *tun, struct tun_file *tfile, if (unlikely(!noblock)) add_wait_queue(&tfile->wq.wait, &wait); while (len) { - current->state = TASK_INTERRUPTIBLE; + if (unlikely(!noblock)) + current->state = TASK_INTERRUPTIBLE; /* Read frames from the queue */ if (!(skb = skb_dequeue(&tfile->socket.sk->sk_receive_queue))) { @@ -1320,9 +1321,10 @@ static ssize_t tun_do_read(struct tun_struct *tun, struct tun_file *tfile, break; } - current->state = TASK_RUNNING; - if (unlikely(!noblock)) + if (unlikely(!noblock)) { + current->state = TASK_RUNNING; remove_wait_queue(&tfile->wq.wait, &wait); + } return ret; } diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index 3569293df872..8e8d0fcd4979 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -36,8 +36,8 @@ #define AX_RXHDR_L4_TYPE_TCP 16 #define AX_RXHDR_L3CSUM_ERR 2 #define AX_RXHDR_L4CSUM_ERR 1 -#define AX_RXHDR_CRC_ERR ((u32)BIT(31)) -#define AX_RXHDR_DROP_ERR ((u32)BIT(30)) +#define AX_RXHDR_CRC_ERR ((u32)BIT(29)) +#define AX_RXHDR_DROP_ERR ((u32)BIT(31)) #define AX_ACCESS_MAC 0x01 #define AX_ACCESS_PHY 0x02 #define AX_ACCESS_EEPROM 0x04 @@ -78,7 +78,6 @@ #define AX_MEDIUM_STATUS_MODE 0x22 #define AX_MEDIUM_GIGAMODE 0x01 #define AX_MEDIUM_FULL_DUPLEX 0x02 - #define AX_MEDIUM_ALWAYS_ONE 0x04 #define AX_MEDIUM_EN_125MHZ 0x08 #define AX_MEDIUM_RXFLOW_CTRLEN 0x10 #define AX_MEDIUM_TXFLOW_CTRLEN 0x20 @@ -1065,8 +1064,8 @@ static int ax88179_bind(struct usbnet *dev, struct usb_interface *intf) /* Configure default medium type => giga */ *tmp16 = AX_MEDIUM_RECEIVE_EN | AX_MEDIUM_TXFLOW_CTRLEN | - AX_MEDIUM_RXFLOW_CTRLEN | AX_MEDIUM_ALWAYS_ONE | - AX_MEDIUM_FULL_DUPLEX | AX_MEDIUM_GIGAMODE; + AX_MEDIUM_RXFLOW_CTRLEN | AX_MEDIUM_FULL_DUPLEX | + AX_MEDIUM_GIGAMODE; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_MEDIUM_STATUS_MODE, 2, 2, tmp16); @@ -1225,7 +1224,7 @@ static int ax88179_link_reset(struct usbnet *dev) } mode = AX_MEDIUM_RECEIVE_EN | AX_MEDIUM_TXFLOW_CTRLEN | - AX_MEDIUM_RXFLOW_CTRLEN | AX_MEDIUM_ALWAYS_ONE; + AX_MEDIUM_RXFLOW_CTRLEN; ax88179_read_cmd(dev, AX_ACCESS_MAC, PHYSICAL_LINK_STATUS, 1, 1, &link_sts); @@ -1339,8 +1338,8 @@ static int ax88179_reset(struct usbnet *dev) /* Configure default medium type => giga */ *tmp16 = AX_MEDIUM_RECEIVE_EN | AX_MEDIUM_TXFLOW_CTRLEN | - AX_MEDIUM_RXFLOW_CTRLEN | AX_MEDIUM_ALWAYS_ONE | - AX_MEDIUM_FULL_DUPLEX | AX_MEDIUM_GIGAMODE; + AX_MEDIUM_RXFLOW_CTRLEN | AX_MEDIUM_FULL_DUPLEX | + AX_MEDIUM_GIGAMODE; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_MEDIUM_STATUS_MODE, 2, 2, tmp16); @@ -1406,6 +1405,19 @@ static const struct driver_info sitecom_info = { .tx_fixup = ax88179_tx_fixup, }; +static const struct driver_info samsung_info = { + .description = "Samsung USB Ethernet Adapter", + .bind = ax88179_bind, + .unbind = ax88179_unbind, + .status = ax88179_status, + .link_reset = ax88179_link_reset, + .reset = ax88179_reset, + .stop = ax88179_stop, + .flags = FLAG_ETHER | FLAG_FRAMING_AX, + .rx_fixup = ax88179_rx_fixup, + .tx_fixup = ax88179_tx_fixup, +}; + static const struct usb_device_id products[] = { { /* ASIX AX88179 10/100/1000 */ @@ -1418,7 +1430,11 @@ static const struct usb_device_id products[] = { }, { /* Sitecom USB 3.0 to Gigabit Adapter */ USB_DEVICE(0x0df6, 0x0072), - .driver_info = (unsigned long) &sitecom_info, + .driver_info = (unsigned long)&sitecom_info, +}, { + /* Samsung USB Ethernet Adapter */ + USB_DEVICE(0x04e8, 0xa100), + .driver_info = (unsigned long)&samsung_info, }, { }, }; diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 3d6aaf79d8b2..818ce90185b5 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -714,6 +714,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */ {QMI_FIXED_INTF(0x2357, 0x9000, 4)}, /* TP-LINK MA260 */ {QMI_FIXED_INTF(0x1bc7, 0x1200, 5)}, /* Telit LE920 */ + {QMI_FIXED_INTF(0x0b3c, 0xc005, 6)}, /* Olivetti Olicard 200 */ {QMI_FIXED_INTF(0x1e2d, 0x0060, 4)}, /* Cinterion PLxx */ /* 4. Gobi 1000 devices */ diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index bf94e10a37c8..90a429b7ebad 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1688,8 +1688,10 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) if (dev->can_dma_sg && !(info->flags & FLAG_SEND_ZLP) && !(info->flags & FLAG_MULTI_PACKET)) { dev->padding_pkt = kzalloc(1, GFP_KERNEL); - if (!dev->padding_pkt) + if (!dev->padding_pkt) { + status = -ENOMEM; goto out4; + } } status = register_netdev (net); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index defec2b3c5a4..bbc9cb84ec1f 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -938,7 +938,9 @@ static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs) return -EINVAL; } else { vi->curr_queue_pairs = queue_pairs; - schedule_delayed_work(&vi->refill, 0); + /* virtnet_open() will refill when device is going to up. */ + if (dev->flags & IFF_UP) + schedule_delayed_work(&vi->refill, 0); } return 0; @@ -1128,6 +1130,7 @@ static int virtnet_cpu_callback(struct notifier_block *nfb, default: break; } + return NOTIFY_OK; } @@ -1689,6 +1692,8 @@ static int virtnet_freeze(struct virtio_device *vdev) struct virtnet_info *vi = vdev->priv; int i; + unregister_hotcpu_notifier(&vi->nb); + /* Prevent config work handler from accessing the device */ mutex_lock(&vi->config_lock); vi->config_enable = false; @@ -1733,7 +1738,13 @@ static int virtnet_restore(struct virtio_device *vdev) vi->config_enable = true; mutex_unlock(&vi->config_lock); + rtnl_lock(); virtnet_set_queues(vi, vi->curr_queue_pairs); + rtnl_unlock(); + + err = register_hotcpu_notifier(&vi->nb); + if (err) + return err; return 0; } diff --git a/drivers/net/wan/farsync.c b/drivers/net/wan/farsync.c index 3f0c4f268751..bcfff0d62de4 100644 --- a/drivers/net/wan/farsync.c +++ b/drivers/net/wan/farsync.c @@ -1972,6 +1972,7 @@ fst_get_iface(struct fst_card_info *card, struct fst_port_info *port, } i = port->index; + memset(&sync, 0, sizeof(sync)); sync.clock_rate = FST_RDL(card, portConfig[i].lineSpeed); /* Lucky card and linux use same encoding here */ sync.clock_type = FST_RDB(card, portConfig[i].internalClock) == diff --git a/drivers/net/wan/sbni.c b/drivers/net/wan/sbni.c index 5bbcb5e3ee0c..388ddf60a66d 100644 --- a/drivers/net/wan/sbni.c +++ b/drivers/net/wan/sbni.c @@ -148,10 +148,6 @@ static int enslave( struct net_device *, struct net_device * ); static int emancipate( struct net_device * ); #endif -#ifdef __i386__ -#define ASM_CRC 1 -#endif - static const char version[] = "Granch SBNI12 driver ver 5.0.1 Jun 22 2001 Denis I.Timofeev.\n"; @@ -1551,88 +1547,6 @@ __setup( "sbni=", sbni_setup ); /* -------------------------------------------------------------------------- */ -#ifdef ASM_CRC - -static u32 -calc_crc32( u32 crc, u8 *p, u32 len ) -{ - register u32 _crc; - _crc = crc; - - __asm__ __volatile__ ( - "xorl %%ebx, %%ebx\n" - "movl %2, %%esi\n" - "movl %3, %%ecx\n" - "movl $crc32tab, %%edi\n" - "shrl $2, %%ecx\n" - "jz 1f\n" - - ".align 4\n" - "0:\n" - "movb %%al, %%bl\n" - "movl (%%esi), %%edx\n" - "shrl $8, %%eax\n" - "xorb %%dl, %%bl\n" - "shrl $8, %%edx\n" - "xorl (%%edi,%%ebx,4), %%eax\n" - - "movb %%al, %%bl\n" - "shrl $8, %%eax\n" - "xorb %%dl, %%bl\n" - "shrl $8, %%edx\n" - "xorl (%%edi,%%ebx,4), %%eax\n" - - "movb %%al, %%bl\n" - "shrl $8, %%eax\n" - "xorb %%dl, %%bl\n" - "movb %%dh, %%dl\n" - "xorl (%%edi,%%ebx,4), %%eax\n" - - "movb %%al, %%bl\n" - "shrl $8, %%eax\n" - "xorb %%dl, %%bl\n" - "addl $4, %%esi\n" - "xorl (%%edi,%%ebx,4), %%eax\n" - - "decl %%ecx\n" - "jnz 0b\n" - - "1:\n" - "movl %3, %%ecx\n" - "andl $3, %%ecx\n" - "jz 2f\n" - - "movb %%al, %%bl\n" - "shrl $8, %%eax\n" - "xorb (%%esi), %%bl\n" - "xorl (%%edi,%%ebx,4), %%eax\n" - - "decl %%ecx\n" - "jz 2f\n" - - "movb %%al, %%bl\n" - "shrl $8, %%eax\n" - "xorb 1(%%esi), %%bl\n" - "xorl (%%edi,%%ebx,4), %%eax\n" - - "decl %%ecx\n" - "jz 2f\n" - - "movb %%al, %%bl\n" - "shrl $8, %%eax\n" - "xorb 2(%%esi), %%bl\n" - "xorl (%%edi,%%ebx,4), %%eax\n" - "2:\n" - : "=a" (_crc) - : "0" (_crc), "g" (p), "g" (len) - : "bx", "cx", "dx", "si", "di" - ); - - return _crc; -} - -#else /* ASM_CRC */ - static u32 calc_crc32( u32 crc, u8 *p, u32 len ) { @@ -1642,9 +1556,6 @@ calc_crc32( u32 crc, u8 *p, u32 len ) return crc; } -#endif /* ASM_CRC */ - - static u32 crc32tab[] __attribute__ ((aligned(8))) = { 0xD202EF8D, 0xA505DF1B, 0x3C0C8EA1, 0x4B0BBE37, 0xD56F2B94, 0xA2681B02, 0x3B614AB8, 0x4C667A2E, diff --git a/drivers/net/wan/wanxl.c b/drivers/net/wan/wanxl.c index 6a24a5a70cc7..4c0a69779b89 100644 --- a/drivers/net/wan/wanxl.c +++ b/drivers/net/wan/wanxl.c @@ -355,6 +355,7 @@ static int wanxl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) ifr->ifr_settings.size = size; /* data size wanted */ return -ENOBUFS; } + memset(&line, 0, sizeof(line)); line.clock_type = get_status(port)->clocking; line.clock_rate = 0; line.loopback = 0; diff --git a/drivers/net/wireless/ath/ath5k/base.c b/drivers/net/wireless/ath/ath5k/base.c index 48161edec8de..69f58b073e85 100644 --- a/drivers/net/wireless/ath/ath5k/base.c +++ b/drivers/net/wireless/ath/ath5k/base.c @@ -1663,15 +1663,15 @@ ath5k_tx_frame_completed(struct ath5k_hw *ah, struct sk_buff *skb, ah->stats.tx_bytes_count += skb->len; info = IEEE80211_SKB_CB(skb); + size = min_t(int, sizeof(info->status.rates), sizeof(bf->rates)); + memcpy(info->status.rates, bf->rates, size); + tries[0] = info->status.rates[0].count; tries[1] = info->status.rates[1].count; tries[2] = info->status.rates[2].count; ieee80211_tx_info_clear_status(info); - size = min_t(int, sizeof(info->status.rates), sizeof(bf->rates)); - memcpy(info->status.rates, bf->rates, size); - for (i = 0; i < ts->ts_final_idx; i++) { struct ieee80211_tx_rate *r = &info->status.rates[i]; diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c index e4f65900132d..709301f88dcd 100644 --- a/drivers/net/wireless/ath/ath9k/main.c +++ b/drivers/net/wireless/ath/ath9k/main.c @@ -208,6 +208,7 @@ static bool ath_complete_reset(struct ath_softc *sc, bool start) struct ath_hw *ah = sc->sc_ah; struct ath_common *common = ath9k_hw_common(ah); unsigned long flags; + int i; if (ath_startrecv(sc) != 0) { ath_err(common, "Unable to restart recv logic\n"); @@ -235,6 +236,15 @@ static bool ath_complete_reset(struct ath_softc *sc, bool start) } work: ath_restart_work(sc); + + for (i = 0; i < ATH9K_NUM_TX_QUEUES; i++) { + if (!ATH_TXQ_SETUP(sc, i)) + continue; + + spin_lock_bh(&sc->tx.txq[i].axq_lock); + ath_txq_schedule(sc, &sc->tx.txq[i]); + spin_unlock_bh(&sc->tx.txq[i].axq_lock); + } } ieee80211_wake_queues(sc->hw); @@ -539,21 +549,10 @@ chip_reset: static int ath_reset(struct ath_softc *sc) { - int i, r; + int r; ath9k_ps_wakeup(sc); - r = ath_reset_internal(sc, NULL); - - for (i = 0; i < ATH9K_NUM_TX_QUEUES; i++) { - if (!ATH_TXQ_SETUP(sc, i)) - continue; - - spin_lock_bh(&sc->tx.txq[i].axq_lock); - ath_txq_schedule(sc, &sc->tx.txq[i]); - spin_unlock_bh(&sc->tx.txq[i].axq_lock); - } - ath9k_ps_restore(sc); return r; diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c index 5ac713d2ff5d..dd30452df966 100644 --- a/drivers/net/wireless/ath/ath9k/xmit.c +++ b/drivers/net/wireless/ath/ath9k/xmit.c @@ -1969,15 +1969,18 @@ static void ath_tx_txqaddbuf(struct ath_softc *sc, struct ath_txq *txq, static void ath_tx_send_normal(struct ath_softc *sc, struct ath_txq *txq, struct ath_atx_tid *tid, struct sk_buff *skb) { + struct ieee80211_tx_info *tx_info = IEEE80211_SKB_CB(skb); struct ath_frame_info *fi = get_frame_info(skb); struct list_head bf_head; - struct ath_buf *bf; - - bf = fi->bf; + struct ath_buf *bf = fi->bf; INIT_LIST_HEAD(&bf_head); list_add_tail(&bf->list, &bf_head); bf->bf_state.bf_type = 0; + if (tid && (tx_info->flags & IEEE80211_TX_CTL_AMPDU)) { + bf->bf_state.bf_type = BUF_AMPDU; + ath_tx_addto_baw(sc, tid, bf); + } bf->bf_next = NULL; bf->bf_lastbf = bf; diff --git a/drivers/net/wireless/b43/dma.c b/drivers/net/wireless/b43/dma.c index c51d2dc489e4..1d7982afc0ad 100644 --- a/drivers/net/wireless/b43/dma.c +++ b/drivers/net/wireless/b43/dma.c @@ -1065,12 +1065,9 @@ static int b43_dma_set_mask(struct b43_wldev *dev, u64 mask) /* Try to set the DMA mask. If it fails, try falling back to a * lower mask, as we can always also support a lower one. */ while (1) { - err = dma_set_mask(dev->dev->dma_dev, mask); - if (!err) { - err = dma_set_coherent_mask(dev->dev->dma_dev, mask); - if (!err) - break; - } + err = dma_set_mask_and_coherent(dev->dev->dma_dev, mask); + if (!err) + break; if (mask == DMA_BIT_MASK(64)) { mask = DMA_BIT_MASK(32); fallback = true; diff --git a/drivers/net/wireless/b43/phy_n.c b/drivers/net/wireless/b43/phy_n.c index 7c970d3ae358..05ee7f10cc8f 100644 --- a/drivers/net/wireless/b43/phy_n.c +++ b/drivers/net/wireless/b43/phy_n.c @@ -164,7 +164,8 @@ static void b43_nphy_rf_ctl_override_rev7(struct b43_wldev *dev, u16 field, } en_addr = en_addrs[override][i]; - val_addr = (i == 0) ? e->val_addr_core0 : e->val_addr_core1; + if (e) + val_addr = (i == 0) ? e->val_addr_core0 : e->val_addr_core1; if (off) { b43_phy_mask(dev, en_addr, ~en_mask); diff --git a/drivers/net/wireless/b43legacy/dma.c b/drivers/net/wireless/b43legacy/dma.c index 42eb26c99e11..b2ed1795130b 100644 --- a/drivers/net/wireless/b43legacy/dma.c +++ b/drivers/net/wireless/b43legacy/dma.c @@ -806,12 +806,9 @@ static int b43legacy_dma_set_mask(struct b43legacy_wldev *dev, u64 mask) /* Try to set the DMA mask. If it fails, try falling back to a * lower mask, as we can always also support a lower one. */ while (1) { - err = dma_set_mask(dev->dev->dma_dev, mask); - if (!err) { - err = dma_set_coherent_mask(dev->dev->dma_dev, mask); - if (!err) - break; - } + err = dma_set_mask_and_coherent(dev->dev->dma_dev, mask); + if (!err) + break; if (mask == DMA_BIT_MASK(64)) { mask = DMA_BIT_MASK(32); fallback = true; diff --git a/drivers/net/wireless/cw1200/cw1200_spi.c b/drivers/net/wireless/cw1200/cw1200_spi.c index 899cad34ccd3..755a0c8edfe1 100644 --- a/drivers/net/wireless/cw1200/cw1200_spi.c +++ b/drivers/net/wireless/cw1200/cw1200_spi.c @@ -237,7 +237,9 @@ static irqreturn_t cw1200_spi_irq_handler(int irq, void *dev_id) struct hwbus_priv *self = dev_id; if (self->core) { + cw1200_spi_lock(self); cw1200_irq_handler(self->core); + cw1200_spi_unlock(self); return IRQ_HANDLED; } else { return IRQ_NONE; diff --git a/drivers/net/wireless/iwlwifi/dvm/tx.c b/drivers/net/wireless/iwlwifi/dvm/tx.c index da442b81370a..1fef5240e6ad 100644 --- a/drivers/net/wireless/iwlwifi/dvm/tx.c +++ b/drivers/net/wireless/iwlwifi/dvm/tx.c @@ -433,27 +433,19 @@ int iwlagn_tx_skb(struct iwl_priv *priv, /* Copy MAC header from skb into command buffer */ memcpy(tx_cmd->hdr, hdr, hdr_len); + txq_id = info->hw_queue; + if (is_agg) txq_id = priv->tid_data[sta_id][tid].agg.txq_id; else if (info->flags & IEEE80211_TX_CTL_SEND_AFTER_DTIM) { /* - * Send this frame after DTIM -- there's a special queue - * reserved for this for contexts that support AP mode. - */ - txq_id = ctx->mcast_queue; - - /* * The microcode will clear the more data * bit in the last frame it transmits. */ hdr->frame_control |= cpu_to_le16(IEEE80211_FCTL_MOREDATA); - } else if (info->flags & IEEE80211_TX_CTL_TX_OFFCHAN) - txq_id = IWL_AUX_QUEUE; - else - txq_id = ctx->ac_to_queue[skb_get_queue_mapping(skb)]; + } - WARN_ON_ONCE(!is_agg && txq_id != info->hw_queue); WARN_ON_ONCE(is_agg && priv->queue_to_mac80211[txq_id] != info->hw_queue); diff --git a/drivers/net/wireless/iwlwifi/iwl-6000.c b/drivers/net/wireless/iwlwifi/iwl-6000.c index 30d45e2fc193..8ac305be68f4 100644 --- a/drivers/net/wireless/iwlwifi/iwl-6000.c +++ b/drivers/net/wireless/iwlwifi/iwl-6000.c @@ -240,6 +240,12 @@ const struct iwl_cfg iwl6035_2agn_cfg = { .ht_params = &iwl6000_ht_params, }; +const struct iwl_cfg iwl6035_2agn_sff_cfg = { + .name = "Intel(R) Centrino(R) Ultimate-N 6235 AGN", + IWL_DEVICE_6035, + .ht_params = &iwl6000_ht_params, +}; + const struct iwl_cfg iwl1030_bgn_cfg = { .name = "Intel(R) Centrino(R) Wireless-N 1030 BGN", IWL_DEVICE_6030, diff --git a/drivers/net/wireless/iwlwifi/iwl-config.h b/drivers/net/wireless/iwlwifi/iwl-config.h index e4d370bff306..b03c25e14903 100644 --- a/drivers/net/wireless/iwlwifi/iwl-config.h +++ b/drivers/net/wireless/iwlwifi/iwl-config.h @@ -280,6 +280,7 @@ extern const struct iwl_cfg iwl2000_2bgn_cfg; extern const struct iwl_cfg iwl2000_2bgn_d_cfg; extern const struct iwl_cfg iwl2030_2bgn_cfg; extern const struct iwl_cfg iwl6035_2agn_cfg; +extern const struct iwl_cfg iwl6035_2agn_sff_cfg; extern const struct iwl_cfg iwl105_bgn_cfg; extern const struct iwl_cfg iwl105_bgn_d_cfg; extern const struct iwl_cfg iwl135_bgn_cfg; diff --git a/drivers/net/wireless/iwlwifi/iwl-trans.h b/drivers/net/wireless/iwlwifi/iwl-trans.h index dd57a36ecb10..c6bac7c90b00 100644 --- a/drivers/net/wireless/iwlwifi/iwl-trans.h +++ b/drivers/net/wireless/iwlwifi/iwl-trans.h @@ -601,8 +601,10 @@ static inline int iwl_trans_send_cmd(struct iwl_trans *trans, { int ret; - WARN_ONCE(trans->state != IWL_TRANS_FW_ALIVE, - "%s bad state = %d", __func__, trans->state); + if (unlikely(trans->state != IWL_TRANS_FW_ALIVE)) { + IWL_ERR(trans, "%s bad state = %d", __func__, trans->state); + return -EIO; + } if (!(cmd->flags & CMD_ASYNC)) lock_map_acquire_read(&trans->sync_cmd_lockdep_map); @@ -638,8 +640,8 @@ static inline void iwl_trans_free_tx_cmd(struct iwl_trans *trans, static inline int iwl_trans_tx(struct iwl_trans *trans, struct sk_buff *skb, struct iwl_device_cmd *dev_cmd, int queue) { - WARN_ONCE(trans->state != IWL_TRANS_FW_ALIVE, - "%s bad state = %d", __func__, trans->state); + if (unlikely(trans->state != IWL_TRANS_FW_ALIVE)) + IWL_ERR(trans, "%s bad state = %d", __func__, trans->state); return trans->ops->tx(trans, skb, dev_cmd, queue); } @@ -647,16 +649,16 @@ static inline int iwl_trans_tx(struct iwl_trans *trans, struct sk_buff *skb, static inline void iwl_trans_reclaim(struct iwl_trans *trans, int queue, int ssn, struct sk_buff_head *skbs) { - WARN_ONCE(trans->state != IWL_TRANS_FW_ALIVE, - "%s bad state = %d", __func__, trans->state); + if (unlikely(trans->state != IWL_TRANS_FW_ALIVE)) + IWL_ERR(trans, "%s bad state = %d", __func__, trans->state); trans->ops->reclaim(trans, queue, ssn, skbs); } static inline void iwl_trans_txq_disable(struct iwl_trans *trans, int queue) { - WARN_ONCE(trans->state != IWL_TRANS_FW_ALIVE, - "%s bad state = %d", __func__, trans->state); + if (unlikely(trans->state != IWL_TRANS_FW_ALIVE)) + IWL_ERR(trans, "%s bad state = %d", __func__, trans->state); trans->ops->txq_disable(trans, queue); } @@ -667,8 +669,8 @@ static inline void iwl_trans_txq_enable(struct iwl_trans *trans, int queue, { might_sleep(); - WARN_ONCE(trans->state != IWL_TRANS_FW_ALIVE, - "%s bad state = %d", __func__, trans->state); + if (unlikely((trans->state != IWL_TRANS_FW_ALIVE))) + IWL_ERR(trans, "%s bad state = %d", __func__, trans->state); trans->ops->txq_enable(trans, queue, fifo, sta_id, tid, frame_limit, ssn); @@ -683,8 +685,8 @@ static inline void iwl_trans_ac_txq_enable(struct iwl_trans *trans, int queue, static inline int iwl_trans_wait_tx_queue_empty(struct iwl_trans *trans) { - WARN_ONCE(trans->state != IWL_TRANS_FW_ALIVE, - "%s bad state = %d", __func__, trans->state); + if (unlikely(trans->state != IWL_TRANS_FW_ALIVE)) + IWL_ERR(trans, "%s bad state = %d", __func__, trans->state); return trans->ops->wait_tx_queue_empty(trans); } diff --git a/drivers/net/wireless/iwlwifi/mvm/power.c b/drivers/net/wireless/iwlwifi/mvm/power.c index 21407a353a3b..d58e393324ef 100644 --- a/drivers/net/wireless/iwlwifi/mvm/power.c +++ b/drivers/net/wireless/iwlwifi/mvm/power.c @@ -273,7 +273,10 @@ static void iwl_mvm_power_build_cmd(struct iwl_mvm *mvm, if (!mvmvif->queue_params[ac].uapsd) continue; - cmd->flags |= cpu_to_le16(POWER_FLAGS_ADVANCE_PM_ENA_MSK); + if (mvm->cur_ucode != IWL_UCODE_WOWLAN) + cmd->flags |= + cpu_to_le16(POWER_FLAGS_ADVANCE_PM_ENA_MSK); + cmd->uapsd_ac_flags |= BIT(ac); /* QNDP TID - the highest TID with no admission control */ diff --git a/drivers/net/wireless/iwlwifi/mvm/scan.c b/drivers/net/wireless/iwlwifi/mvm/scan.c index 9a7ab8495300..3a06832e8e90 100644 --- a/drivers/net/wireless/iwlwifi/mvm/scan.c +++ b/drivers/net/wireless/iwlwifi/mvm/scan.c @@ -93,10 +93,10 @@ static inline __le32 iwl_mvm_scan_max_out_time(struct ieee80211_vif *vif) static inline __le32 iwl_mvm_scan_suspend_time(struct ieee80211_vif *vif) { - if (vif->bss_conf.assoc) - return cpu_to_le32(vif->bss_conf.beacon_int); - else + if (!vif->bss_conf.assoc) return 0; + + return cpu_to_le32(ieee80211_tu_to_usec(vif->bss_conf.beacon_int)); } static inline __le32 @@ -394,6 +394,11 @@ static bool iwl_mvm_scan_abort_notif(struct iwl_notif_wait_data *notif_wait, return false; } + /* + * If scan cannot be aborted, it means that we had a + * SCAN_COMPLETE_NOTIFICATION in the pipe and it called + * ieee80211_scan_completed already. + */ IWL_DEBUG_SCAN(mvm, "Scan cannot be aborted, exit now: %d\n", *resp); return true; @@ -417,14 +422,19 @@ void iwl_mvm_cancel_scan(struct iwl_mvm *mvm) SCAN_COMPLETE_NOTIFICATION }; int ret; + if (mvm->scan_status == IWL_MVM_SCAN_NONE) + return; + iwl_init_notification_wait(&mvm->notif_wait, &wait_scan_abort, scan_abort_notif, ARRAY_SIZE(scan_abort_notif), iwl_mvm_scan_abort_notif, NULL); - ret = iwl_mvm_send_cmd_pdu(mvm, SCAN_ABORT_CMD, CMD_SYNC, 0, NULL); + ret = iwl_mvm_send_cmd_pdu(mvm, SCAN_ABORT_CMD, + CMD_SYNC | CMD_SEND_IN_RFKILL, 0, NULL); if (ret) { IWL_ERR(mvm, "Couldn't send SCAN_ABORT_CMD: %d\n", ret); + /* mac80211's state will be cleaned in the fw_restart flow */ goto out_remove_notif; } diff --git a/drivers/net/wireless/iwlwifi/pcie/drv.c b/drivers/net/wireless/iwlwifi/pcie/drv.c index dc02cb9792af..26108a1a29fa 100644 --- a/drivers/net/wireless/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/iwlwifi/pcie/drv.c @@ -139,13 +139,16 @@ static DEFINE_PCI_DEVICE_TABLE(iwl_hw_card_ids) = { /* 6x00 Series */ {IWL_PCI_DEVICE(0x422B, 0x1101, iwl6000_3agn_cfg)}, + {IWL_PCI_DEVICE(0x422B, 0x1108, iwl6000_3agn_cfg)}, {IWL_PCI_DEVICE(0x422B, 0x1121, iwl6000_3agn_cfg)}, + {IWL_PCI_DEVICE(0x422B, 0x1128, iwl6000_3agn_cfg)}, {IWL_PCI_DEVICE(0x422C, 0x1301, iwl6000i_2agn_cfg)}, {IWL_PCI_DEVICE(0x422C, 0x1306, iwl6000i_2abg_cfg)}, {IWL_PCI_DEVICE(0x422C, 0x1307, iwl6000i_2bg_cfg)}, {IWL_PCI_DEVICE(0x422C, 0x1321, iwl6000i_2agn_cfg)}, {IWL_PCI_DEVICE(0x422C, 0x1326, iwl6000i_2abg_cfg)}, {IWL_PCI_DEVICE(0x4238, 0x1111, iwl6000_3agn_cfg)}, + {IWL_PCI_DEVICE(0x4238, 0x1118, iwl6000_3agn_cfg)}, {IWL_PCI_DEVICE(0x4239, 0x1311, iwl6000i_2agn_cfg)}, {IWL_PCI_DEVICE(0x4239, 0x1316, iwl6000i_2abg_cfg)}, @@ -153,12 +156,16 @@ static DEFINE_PCI_DEVICE_TABLE(iwl_hw_card_ids) = { {IWL_PCI_DEVICE(0x0082, 0x1301, iwl6005_2agn_cfg)}, {IWL_PCI_DEVICE(0x0082, 0x1306, iwl6005_2abg_cfg)}, {IWL_PCI_DEVICE(0x0082, 0x1307, iwl6005_2bg_cfg)}, + {IWL_PCI_DEVICE(0x0082, 0x1308, iwl6005_2agn_cfg)}, {IWL_PCI_DEVICE(0x0082, 0x1321, iwl6005_2agn_cfg)}, {IWL_PCI_DEVICE(0x0082, 0x1326, iwl6005_2abg_cfg)}, + {IWL_PCI_DEVICE(0x0082, 0x1328, iwl6005_2agn_cfg)}, {IWL_PCI_DEVICE(0x0085, 0x1311, iwl6005_2agn_cfg)}, + {IWL_PCI_DEVICE(0x0085, 0x1318, iwl6005_2agn_cfg)}, {IWL_PCI_DEVICE(0x0085, 0x1316, iwl6005_2abg_cfg)}, {IWL_PCI_DEVICE(0x0082, 0xC020, iwl6005_2agn_sff_cfg)}, {IWL_PCI_DEVICE(0x0085, 0xC220, iwl6005_2agn_sff_cfg)}, + {IWL_PCI_DEVICE(0x0085, 0xC228, iwl6005_2agn_sff_cfg)}, {IWL_PCI_DEVICE(0x0082, 0x4820, iwl6005_2agn_d_cfg)}, {IWL_PCI_DEVICE(0x0082, 0x1304, iwl6005_2agn_mow1_cfg)},/* low 5GHz active */ {IWL_PCI_DEVICE(0x0082, 0x1305, iwl6005_2agn_mow2_cfg)},/* high 5GHz active */ @@ -240,8 +247,11 @@ static DEFINE_PCI_DEVICE_TABLE(iwl_hw_card_ids) = { /* 6x35 Series */ {IWL_PCI_DEVICE(0x088E, 0x4060, iwl6035_2agn_cfg)}, + {IWL_PCI_DEVICE(0x088E, 0x406A, iwl6035_2agn_sff_cfg)}, {IWL_PCI_DEVICE(0x088F, 0x4260, iwl6035_2agn_cfg)}, + {IWL_PCI_DEVICE(0x088F, 0x426A, iwl6035_2agn_sff_cfg)}, {IWL_PCI_DEVICE(0x088E, 0x4460, iwl6035_2agn_cfg)}, + {IWL_PCI_DEVICE(0x088E, 0x446A, iwl6035_2agn_sff_cfg)}, {IWL_PCI_DEVICE(0x088E, 0x4860, iwl6035_2agn_cfg)}, {IWL_PCI_DEVICE(0x088F, 0x5260, iwl6035_2agn_cfg)}, @@ -260,54 +270,86 @@ static DEFINE_PCI_DEVICE_TABLE(iwl_hw_card_ids) = { #if IS_ENABLED(CONFIG_IWLMVM) /* 7000 Series */ {IWL_PCI_DEVICE(0x08B1, 0x4070, iwl7260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x08B1, 0x4072, iwl7260_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0x4170, iwl7260_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0x4060, iwl7260_2n_cfg)}, + {IWL_PCI_DEVICE(0x08B1, 0x406A, iwl7260_2n_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0x4160, iwl7260_2n_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0x4062, iwl7260_n_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0x4162, iwl7260_n_cfg)}, {IWL_PCI_DEVICE(0x08B2, 0x4270, iwl7260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x08B2, 0x4272, iwl7260_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B2, 0x4260, iwl7260_2n_cfg)}, + {IWL_PCI_DEVICE(0x08B2, 0x426A, iwl7260_2n_cfg)}, {IWL_PCI_DEVICE(0x08B2, 0x4262, iwl7260_n_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0x4470, iwl7260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x08B1, 0x4472, iwl7260_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0x4460, iwl7260_2n_cfg)}, + {IWL_PCI_DEVICE(0x08B1, 0x446A, iwl7260_2n_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0x4462, iwl7260_n_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0x4870, iwl7260_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0x486E, iwl7260_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0x4A70, iwl7260_2ac_cfg_high_temp)}, {IWL_PCI_DEVICE(0x08B1, 0x4A6E, iwl7260_2ac_cfg_high_temp)}, {IWL_PCI_DEVICE(0x08B1, 0x4A6C, iwl7260_2ac_cfg_high_temp)}, + {IWL_PCI_DEVICE(0x08B1, 0x4570, iwl7260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x08B1, 0x4560, iwl7260_2n_cfg)}, + {IWL_PCI_DEVICE(0x08B2, 0x4370, iwl7260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x08B2, 0x4360, iwl7260_2n_cfg)}, + {IWL_PCI_DEVICE(0x08B1, 0x5070, iwl7260_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0x4020, iwl7260_2n_cfg)}, + {IWL_PCI_DEVICE(0x08B1, 0x402A, iwl7260_2n_cfg)}, {IWL_PCI_DEVICE(0x08B2, 0x4220, iwl7260_2n_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0x4420, iwl7260_2n_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0xC070, iwl7260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x08B1, 0xC072, iwl7260_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0xC170, iwl7260_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0xC060, iwl7260_2n_cfg)}, + {IWL_PCI_DEVICE(0x08B1, 0xC06A, iwl7260_2n_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0xC160, iwl7260_2n_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0xC062, iwl7260_n_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0xC162, iwl7260_n_cfg)}, + {IWL_PCI_DEVICE(0x08B1, 0xC770, iwl7260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x08B1, 0xC760, iwl7260_2n_cfg)}, {IWL_PCI_DEVICE(0x08B2, 0xC270, iwl7260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x08B2, 0xC272, iwl7260_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B2, 0xC260, iwl7260_2n_cfg)}, + {IWL_PCI_DEVICE(0x08B2, 0xC26A, iwl7260_n_cfg)}, {IWL_PCI_DEVICE(0x08B2, 0xC262, iwl7260_n_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0xC470, iwl7260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x08B1, 0xC472, iwl7260_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0xC460, iwl7260_2n_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0xC462, iwl7260_n_cfg)}, + {IWL_PCI_DEVICE(0x08B1, 0xC570, iwl7260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x08B1, 0xC560, iwl7260_2n_cfg)}, + {IWL_PCI_DEVICE(0x08B2, 0xC370, iwl7260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x08B1, 0xC360, iwl7260_2n_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0xC020, iwl7260_2n_cfg)}, + {IWL_PCI_DEVICE(0x08B1, 0xC02A, iwl7260_2n_cfg)}, {IWL_PCI_DEVICE(0x08B2, 0xC220, iwl7260_2n_cfg)}, {IWL_PCI_DEVICE(0x08B1, 0xC420, iwl7260_2n_cfg)}, /* 3160 Series */ {IWL_PCI_DEVICE(0x08B3, 0x0070, iwl3160_2ac_cfg)}, + {IWL_PCI_DEVICE(0x08B3, 0x0072, iwl3160_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B3, 0x0170, iwl3160_2ac_cfg)}, + {IWL_PCI_DEVICE(0x08B3, 0x0172, iwl3160_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B3, 0x0060, iwl3160_2n_cfg)}, {IWL_PCI_DEVICE(0x08B3, 0x0062, iwl3160_n_cfg)}, {IWL_PCI_DEVICE(0x08B4, 0x0270, iwl3160_2ac_cfg)}, + {IWL_PCI_DEVICE(0x08B4, 0x0272, iwl3160_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B3, 0x0470, iwl3160_2ac_cfg)}, + {IWL_PCI_DEVICE(0x08B3, 0x0472, iwl3160_2ac_cfg)}, + {IWL_PCI_DEVICE(0x08B4, 0x0370, iwl3160_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B3, 0x8070, iwl3160_2ac_cfg)}, + {IWL_PCI_DEVICE(0x08B3, 0x8072, iwl3160_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B3, 0x8170, iwl3160_2ac_cfg)}, + {IWL_PCI_DEVICE(0x08B3, 0x8172, iwl3160_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B3, 0x8060, iwl3160_2n_cfg)}, {IWL_PCI_DEVICE(0x08B3, 0x8062, iwl3160_n_cfg)}, {IWL_PCI_DEVICE(0x08B4, 0x8270, iwl3160_2ac_cfg)}, {IWL_PCI_DEVICE(0x08B3, 0x8470, iwl3160_2ac_cfg)}, + {IWL_PCI_DEVICE(0x08B3, 0x8570, iwl3160_2ac_cfg)}, #endif /* CONFIG_IWLMVM */ {0} diff --git a/drivers/net/wireless/iwlwifi/pcie/trans.c b/drivers/net/wireless/iwlwifi/pcie/trans.c index bad95d28d50d..c3f904d422b0 100644 --- a/drivers/net/wireless/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/iwlwifi/pcie/trans.c @@ -1401,6 +1401,10 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev, spin_lock_init(&trans_pcie->reg_lock); init_waitqueue_head(&trans_pcie->ucode_write_waitq); + err = pci_enable_device(pdev); + if (err) + goto out_no_pci; + if (!cfg->base_params->pcie_l1_allowed) { /* * W/A - seems to solve weird behavior. We need to remove this @@ -1412,10 +1416,6 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev, PCIE_LINK_STATE_CLKPM); } - err = pci_enable_device(pdev); - if (err) - goto out_no_pci; - pci_set_master(pdev); err = pci_set_dma_mask(pdev, DMA_BIT_MASK(36)); diff --git a/drivers/net/wireless/iwlwifi/pcie/tx.c b/drivers/net/wireless/iwlwifi/pcie/tx.c index f45eb29c2ede..80f1956b3be3 100644 --- a/drivers/net/wireless/iwlwifi/pcie/tx.c +++ b/drivers/net/wireless/iwlwifi/pcie/tx.c @@ -1102,6 +1102,8 @@ void iwl_trans_pcie_txq_enable(struct iwl_trans *trans, int txq_id, int fifo, * non-AGG queue. */ iwl_clear_bits_prph(trans, SCD_AGGR_SEL, BIT(txq_id)); + + ssn = trans_pcie->txq[txq_id].q.read_ptr; } /* Place first TFD at index corresponding to start sequence number. @@ -1463,7 +1465,8 @@ void iwl_pcie_hcmd_complete(struct iwl_trans *trans, spin_unlock_bh(&txq->lock); } -#define HOST_COMPLETE_TIMEOUT (2 * HZ) +#define HOST_COMPLETE_TIMEOUT (2 * HZ) +#define COMMAND_POKE_TIMEOUT (HZ / 10) static int iwl_pcie_send_hcmd_async(struct iwl_trans *trans, struct iwl_host_cmd *cmd) @@ -1491,6 +1494,7 @@ static int iwl_pcie_send_hcmd_sync(struct iwl_trans *trans, struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); int cmd_idx; int ret; + int timeout = HOST_COMPLETE_TIMEOUT; IWL_DEBUG_INFO(trans, "Attempting to send sync command %s\n", get_cmd_string(trans_pcie, cmd->id)); @@ -1515,10 +1519,29 @@ static int iwl_pcie_send_hcmd_sync(struct iwl_trans *trans, return ret; } - ret = wait_event_timeout(trans_pcie->wait_command_queue, - !test_bit(STATUS_HCMD_ACTIVE, - &trans_pcie->status), - HOST_COMPLETE_TIMEOUT); + while (timeout > 0) { + unsigned long flags; + + timeout -= COMMAND_POKE_TIMEOUT; + ret = wait_event_timeout(trans_pcie->wait_command_queue, + !test_bit(STATUS_HCMD_ACTIVE, + &trans_pcie->status), + COMMAND_POKE_TIMEOUT); + if (ret) + break; + /* poke the device - it may have lost the command */ + if (iwl_trans_grab_nic_access(trans, true, &flags)) { + iwl_trans_release_nic_access(trans, &flags); + IWL_DEBUG_INFO(trans, + "Tried to wake NIC for command %s\n", + get_cmd_string(trans_pcie, cmd->id)); + } else { + IWL_ERR(trans, "Failed to poke NIC for command %s\n", + get_cmd_string(trans_pcie, cmd->id)); + break; + } + } + if (!ret) { if (test_bit(STATUS_HCMD_ACTIVE, &trans_pcie->status)) { struct iwl_txq *txq = diff --git a/drivers/net/wireless/mwifiex/join.c b/drivers/net/wireless/mwifiex/join.c index 9d7c0e6c4fc7..37f873bb342f 100644 --- a/drivers/net/wireless/mwifiex/join.c +++ b/drivers/net/wireless/mwifiex/join.c @@ -1422,13 +1422,19 @@ static int mwifiex_deauthenticate_infra(struct mwifiex_private *priv, u8 *mac) */ int mwifiex_deauthenticate(struct mwifiex_private *priv, u8 *mac) { + int ret = 0; + if (!priv->media_connected) return 0; switch (priv->bss_mode) { case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_P2P_CLIENT: - return mwifiex_deauthenticate_infra(priv, mac); + ret = mwifiex_deauthenticate_infra(priv, mac); + if (ret) + cfg80211_disconnected(priv->netdev, 0, NULL, 0, + GFP_KERNEL); + break; case NL80211_IFTYPE_ADHOC: return mwifiex_send_cmd_sync(priv, HostCmd_CMD_802_11_AD_HOC_STOP, @@ -1440,7 +1446,7 @@ int mwifiex_deauthenticate(struct mwifiex_private *priv, u8 *mac) break; } - return 0; + return ret; } EXPORT_SYMBOL_GPL(mwifiex_deauthenticate); diff --git a/drivers/net/wireless/mwifiex/main.c b/drivers/net/wireless/mwifiex/main.c index fd778337deee..c2b91f566e05 100644 --- a/drivers/net/wireless/mwifiex/main.c +++ b/drivers/net/wireless/mwifiex/main.c @@ -358,10 +358,12 @@ process_start: } } while (true); - if ((adapter->int_status) || IS_CARD_RX_RCVD(adapter)) + spin_lock_irqsave(&adapter->main_proc_lock, flags); + if ((adapter->int_status) || IS_CARD_RX_RCVD(adapter)) { + spin_unlock_irqrestore(&adapter->main_proc_lock, flags); goto process_start; + } - spin_lock_irqsave(&adapter->main_proc_lock, flags); adapter->mwifiex_processing = false; spin_unlock_irqrestore(&adapter->main_proc_lock, flags); diff --git a/drivers/net/wireless/mwifiex/sta_event.c b/drivers/net/wireless/mwifiex/sta_event.c index 8b057524b252..8c351f71f72f 100644 --- a/drivers/net/wireless/mwifiex/sta_event.c +++ b/drivers/net/wireless/mwifiex/sta_event.c @@ -118,7 +118,8 @@ mwifiex_reset_connect_state(struct mwifiex_private *priv, u16 reason_code) dev_dbg(adapter->dev, "info: successfully disconnected from %pM: reason code %d\n", priv->cfg_bssid, reason_code); - if (priv->bss_mode == NL80211_IFTYPE_STATION) { + if (priv->bss_mode == NL80211_IFTYPE_STATION || + priv->bss_mode == NL80211_IFTYPE_P2P_CLIENT) { cfg80211_disconnected(priv->netdev, reason_code, NULL, 0, GFP_KERNEL); } diff --git a/drivers/net/wireless/rt2x00/rt2400pci.c b/drivers/net/wireless/rt2x00/rt2400pci.c index 3d53a09da5a1..38ed9a3e44c8 100644 --- a/drivers/net/wireless/rt2x00/rt2400pci.c +++ b/drivers/net/wireless/rt2x00/rt2400pci.c @@ -1261,7 +1261,7 @@ static void rt2400pci_fill_rxdone(struct queue_entry *entry, */ rxdesc->timestamp = ((u64)rx_high << 32) | rx_low; rxdesc->signal = rt2x00_get_field32(word2, RXD_W2_SIGNAL) & ~0x08; - rxdesc->rssi = rt2x00_get_field32(word2, RXD_W3_RSSI) - + rxdesc->rssi = rt2x00_get_field32(word3, RXD_W3_RSSI) - entry->queue->rt2x00dev->rssi_offset; rxdesc->size = rt2x00_get_field32(word0, RXD_W0_DATABYTE_COUNT); diff --git a/drivers/net/wireless/rt2x00/rt2800usb.c b/drivers/net/wireless/rt2x00/rt2800usb.c index 96961b9a395c..4feb35aef990 100644 --- a/drivers/net/wireless/rt2x00/rt2800usb.c +++ b/drivers/net/wireless/rt2x00/rt2800usb.c @@ -148,6 +148,8 @@ static bool rt2800usb_txstatus_timeout(struct rt2x00_dev *rt2x00dev) return false; } +#define TXSTATUS_READ_INTERVAL 1000000 + static bool rt2800usb_tx_sta_fifo_read_completed(struct rt2x00_dev *rt2x00dev, int urb_status, u32 tx_status) { @@ -176,8 +178,9 @@ static bool rt2800usb_tx_sta_fifo_read_completed(struct rt2x00_dev *rt2x00dev, queue_work(rt2x00dev->workqueue, &rt2x00dev->txdone_work); if (rt2800usb_txstatus_pending(rt2x00dev)) { - /* Read register after 250 us */ - hrtimer_start(&rt2x00dev->txstatus_timer, ktime_set(0, 250000), + /* Read register after 1 ms */ + hrtimer_start(&rt2x00dev->txstatus_timer, + ktime_set(0, TXSTATUS_READ_INTERVAL), HRTIMER_MODE_REL); return false; } @@ -202,8 +205,9 @@ static void rt2800usb_async_read_tx_status(struct rt2x00_dev *rt2x00dev) if (test_and_set_bit(TX_STATUS_READING, &rt2x00dev->flags)) return; - /* Read TX_STA_FIFO register after 500 us */ - hrtimer_start(&rt2x00dev->txstatus_timer, ktime_set(0, 500000), + /* Read TX_STA_FIFO register after 2 ms */ + hrtimer_start(&rt2x00dev->txstatus_timer, + ktime_set(0, 2*TXSTATUS_READ_INTERVAL), HRTIMER_MODE_REL); } diff --git a/drivers/net/wireless/rt2x00/rt2x00mac.c b/drivers/net/wireless/rt2x00/rt2x00mac.c index f883802f3505..ba1de865c892 100644 --- a/drivers/net/wireless/rt2x00/rt2x00mac.c +++ b/drivers/net/wireless/rt2x00/rt2x00mac.c @@ -754,6 +754,9 @@ void rt2x00mac_flush(struct ieee80211_hw *hw, u32 queues, bool drop) struct rt2x00_dev *rt2x00dev = hw->priv; struct data_queue *queue; + if (!test_bit(DEVICE_STATE_PRESENT, &rt2x00dev->flags)) + return; + tx_queue_for_each(rt2x00dev, queue) rt2x00queue_flush_queue(queue, drop); } diff --git a/drivers/net/wireless/rt2x00/rt2x00pci.c b/drivers/net/wireless/rt2x00/rt2x00pci.c index 76d95deb274b..dc49e525ae5e 100644 --- a/drivers/net/wireless/rt2x00/rt2x00pci.c +++ b/drivers/net/wireless/rt2x00/rt2x00pci.c @@ -105,13 +105,11 @@ int rt2x00pci_probe(struct pci_dev *pci_dev, const struct rt2x00_ops *ops) goto exit_release_regions; } - pci_enable_msi(pci_dev); - hw = ieee80211_alloc_hw(sizeof(struct rt2x00_dev), ops->hw); if (!hw) { rt2x00_probe_err("Failed to allocate hardware\n"); retval = -ENOMEM; - goto exit_disable_msi; + goto exit_release_regions; } pci_set_drvdata(pci_dev, hw); @@ -152,9 +150,6 @@ exit_free_reg: exit_free_device: ieee80211_free_hw(hw); -exit_disable_msi: - pci_disable_msi(pci_dev); - exit_release_regions: pci_release_regions(pci_dev); @@ -179,8 +174,6 @@ void rt2x00pci_remove(struct pci_dev *pci_dev) rt2x00pci_free_reg(rt2x00dev); ieee80211_free_hw(hw); - pci_disable_msi(pci_dev); - /* * Free the PCI device data. */ diff --git a/drivers/net/wireless/rtlwifi/rtl8192cu/trx.c b/drivers/net/wireless/rtlwifi/rtl8192cu/trx.c index 763cf1defab5..5a060e537fbe 100644 --- a/drivers/net/wireless/rtlwifi/rtl8192cu/trx.c +++ b/drivers/net/wireless/rtlwifi/rtl8192cu/trx.c @@ -343,7 +343,8 @@ bool rtl92cu_rx_query_desc(struct ieee80211_hw *hw, (bool)GET_RX_DESC_PAGGR(pdesc)); rx_status->mactime = GET_RX_DESC_TSFL(pdesc); if (phystatus) { - p_drvinfo = (struct rx_fwinfo_92c *)(pdesc + RTL_RX_DESC_SIZE); + p_drvinfo = (struct rx_fwinfo_92c *)(skb->data + + stats->rx_bufshift); rtl92c_translate_rx_signal_stuff(hw, skb, stats, pdesc, p_drvinfo); } diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h index 5715318d6bab..400fea1de080 100644 --- a/drivers/net/xen-netback/common.h +++ b/drivers/net/xen-netback/common.h @@ -163,6 +163,7 @@ struct xenvif { unsigned long credit_usec; unsigned long remaining_credit; struct timer_list credit_timeout; + u64 credit_window_start; /* Statistics */ unsigned long rx_gso_checksum_fixup; diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 01bb854c7f62..459935a6bfae 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -312,8 +312,7 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid, vif->credit_bytes = vif->remaining_credit = ~0UL; vif->credit_usec = 0UL; init_timer(&vif->credit_timeout); - /* Initialize 'expires' now: it's used to track the credit window. */ - vif->credit_timeout.expires = jiffies; + vif->credit_window_start = get_jiffies_64(); dev->netdev_ops = &xenvif_netdev_ops; dev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO; diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index f3e591c611de..900da4b243ad 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -1185,9 +1185,8 @@ out: static bool tx_credit_exceeded(struct xenvif *vif, unsigned size) { - unsigned long now = jiffies; - unsigned long next_credit = - vif->credit_timeout.expires + + u64 now = get_jiffies_64(); + u64 next_credit = vif->credit_window_start + msecs_to_jiffies(vif->credit_usec / 1000); /* Timer could already be pending in rare cases. */ @@ -1195,8 +1194,8 @@ static bool tx_credit_exceeded(struct xenvif *vif, unsigned size) return true; /* Passed the point where we can replenish credit? */ - if (time_after_eq(now, next_credit)) { - vif->credit_timeout.expires = now; + if (time_after_eq64(now, next_credit)) { + vif->credit_window_start = now; tx_add_credit(vif); } @@ -1208,6 +1207,7 @@ static bool tx_credit_exceeded(struct xenvif *vif, unsigned size) tx_credit_callback; mod_timer(&vif->credit_timeout, next_credit); + vif->credit_window_start = next_credit; return true; } diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c index b45bce20ad76..1b08d8798372 100644 --- a/drivers/net/xen-netback/xenbus.c +++ b/drivers/net/xen-netback/xenbus.c @@ -39,11 +39,15 @@ static int connect_rings(struct backend_info *); static void connect(struct backend_info *); static void backend_create_xenvif(struct backend_info *be); static void unregister_hotplug_status_watch(struct backend_info *be); +static void set_backend_state(struct backend_info *be, + enum xenbus_state state); static int netback_remove(struct xenbus_device *dev) { struct backend_info *be = dev_get_drvdata(&dev->dev); + set_backend_state(be, XenbusStateClosed); + unregister_hotplug_status_watch(be); if (be->vif) { kobject_uevent(&dev->dev.kobj, KOBJ_OFFLINE); diff --git a/drivers/of/Kconfig b/drivers/of/Kconfig index 9d2009a9004d..78cc76053328 100644 --- a/drivers/of/Kconfig +++ b/drivers/of/Kconfig @@ -74,10 +74,4 @@ config OF_MTD depends on MTD def_bool y -config OF_RESERVED_MEM - depends on OF_FLATTREE && (DMA_CMA || (HAVE_GENERIC_DMA_COHERENT && HAVE_MEMBLOCK)) - def_bool y - help - Initialization code for DMA reserved memory - endmenu # OF diff --git a/drivers/of/Makefile b/drivers/of/Makefile index ed9660adad77..efd05102c405 100644 --- a/drivers/of/Makefile +++ b/drivers/of/Makefile @@ -9,4 +9,3 @@ obj-$(CONFIG_OF_MDIO) += of_mdio.o obj-$(CONFIG_OF_PCI) += of_pci.o obj-$(CONFIG_OF_PCI_IRQ) += of_pci_irq.o obj-$(CONFIG_OF_MTD) += of_mtd.o -obj-$(CONFIG_OF_RESERVED_MEM) += of_reserved_mem.o diff --git a/drivers/of/base.c b/drivers/of/base.c index 865d3f66c86b..7d4c70f859e3 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -303,10 +303,8 @@ struct device_node *of_get_cpu_node(int cpu, unsigned int *thread) struct device_node *cpun, *cpus; cpus = of_find_node_by_path("/cpus"); - if (!cpus) { - pr_warn("Missing cpus node, bailing out\n"); + if (!cpus) return NULL; - } for_each_child_of_node(cpus, cpun) { if (of_node_cmp(cpun->type, "cpu")) diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index 229dd9d69e18..a4fa9ad31b8f 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -18,7 +18,6 @@ #include <linux/string.h> #include <linux/errno.h> #include <linux/slab.h> -#include <linux/random.h> #include <asm/setup.h> /* for COMMAND_LINE_SIZE */ #ifdef CONFIG_PPC @@ -803,14 +802,3 @@ void __init unflatten_device_tree(void) } #endif /* CONFIG_OF_EARLY_FLATTREE */ - -/* Feed entire flattened device tree into the random pool */ -static int __init add_fdt_randomness(void) -{ - if (initial_boot_params) - add_device_randomness(initial_boot_params, - be32_to_cpu(initial_boot_params->totalsize)); - - return 0; -} -core_initcall(add_fdt_randomness); diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c deleted file mode 100644 index 0fe40c7d6904..000000000000 --- a/drivers/of/of_reserved_mem.c +++ /dev/null @@ -1,173 +0,0 @@ -/* - * Device tree based initialization code for reserved memory. - * - * Copyright (c) 2013 Samsung Electronics Co., Ltd. - * http://www.samsung.com - * Author: Marek Szyprowski <m.szyprowski@samsung.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 of the - * License or (at your optional) any later version of the license. - */ - -#include <linux/memblock.h> -#include <linux/err.h> -#include <linux/of.h> -#include <linux/of_fdt.h> -#include <linux/of_platform.h> -#include <linux/mm.h> -#include <linux/sizes.h> -#include <linux/mm_types.h> -#include <linux/dma-contiguous.h> -#include <linux/dma-mapping.h> -#include <linux/of_reserved_mem.h> - -#define MAX_RESERVED_REGIONS 16 -struct reserved_mem { - phys_addr_t base; - unsigned long size; - struct cma *cma; - char name[32]; -}; -static struct reserved_mem reserved_mem[MAX_RESERVED_REGIONS]; -static int reserved_mem_count; - -static int __init fdt_scan_reserved_mem(unsigned long node, const char *uname, - int depth, void *data) -{ - struct reserved_mem *rmem = &reserved_mem[reserved_mem_count]; - phys_addr_t base, size; - int is_cma, is_reserved; - unsigned long len; - const char *status; - __be32 *prop; - - is_cma = IS_ENABLED(CONFIG_DMA_CMA) && - of_flat_dt_is_compatible(node, "linux,contiguous-memory-region"); - is_reserved = of_flat_dt_is_compatible(node, "reserved-memory-region"); - - if (!is_reserved && !is_cma) { - /* ignore node and scan next one */ - return 0; - } - - status = of_get_flat_dt_prop(node, "status", &len); - if (status && strcmp(status, "okay") != 0) { - /* ignore disabled node nad scan next one */ - return 0; - } - - prop = of_get_flat_dt_prop(node, "reg", &len); - if (!prop || (len < (dt_root_size_cells + dt_root_addr_cells) * - sizeof(__be32))) { - pr_err("Reserved mem: node %s, incorrect \"reg\" property\n", - uname); - /* ignore node and scan next one */ - return 0; - } - base = dt_mem_next_cell(dt_root_addr_cells, &prop); - size = dt_mem_next_cell(dt_root_size_cells, &prop); - - if (!size) { - /* ignore node and scan next one */ - return 0; - } - - pr_info("Reserved mem: found %s, memory base %lx, size %ld MiB\n", - uname, (unsigned long)base, (unsigned long)size / SZ_1M); - - if (reserved_mem_count == ARRAY_SIZE(reserved_mem)) - return -ENOSPC; - - rmem->base = base; - rmem->size = size; - strlcpy(rmem->name, uname, sizeof(rmem->name)); - - if (is_cma) { - struct cma *cma; - if (dma_contiguous_reserve_area(size, base, 0, &cma) == 0) { - rmem->cma = cma; - reserved_mem_count++; - if (of_get_flat_dt_prop(node, - "linux,default-contiguous-region", - NULL)) - dma_contiguous_set_default(cma); - } - } else if (is_reserved) { - if (memblock_remove(base, size) == 0) - reserved_mem_count++; - else - pr_err("Failed to reserve memory for %s\n", uname); - } - - return 0; -} - -static struct reserved_mem *get_dma_memory_region(struct device *dev) -{ - struct device_node *node; - const char *name; - int i; - - node = of_parse_phandle(dev->of_node, "memory-region", 0); - if (!node) - return NULL; - - name = kbasename(node->full_name); - for (i = 0; i < reserved_mem_count; i++) - if (strcmp(name, reserved_mem[i].name) == 0) - return &reserved_mem[i]; - return NULL; -} - -/** - * of_reserved_mem_device_init() - assign reserved memory region to given device - * - * This function assign memory region pointed by "memory-region" device tree - * property to the given device. - */ -void of_reserved_mem_device_init(struct device *dev) -{ - struct reserved_mem *region = get_dma_memory_region(dev); - if (!region) - return; - - if (region->cma) { - dev_set_cma_area(dev, region->cma); - pr_info("Assigned CMA %s to %s device\n", region->name, - dev_name(dev)); - } else { - if (dma_declare_coherent_memory(dev, region->base, region->base, - region->size, DMA_MEMORY_MAP | DMA_MEMORY_EXCLUSIVE) != 0) - pr_info("Declared reserved memory %s to %s device\n", - region->name, dev_name(dev)); - } -} - -/** - * of_reserved_mem_device_release() - release reserved memory device structures - * - * This function releases structures allocated for memory region handling for - * the given device. - */ -void of_reserved_mem_device_release(struct device *dev) -{ - struct reserved_mem *region = get_dma_memory_region(dev); - if (!region && !region->cma) - dma_release_declared_memory(dev); -} - -/** - * early_init_dt_scan_reserved_mem() - create reserved memory regions - * - * This function grabs memory from early allocator for device exclusive use - * defined in device tree structures. It should be called by arch specific code - * once the early allocator (memblock) has been activated and all other - * subsystems have already allocated/reserved memory. - */ -void __init early_init_dt_scan_reserved_mem(void) -{ - of_scan_flat_dt_by_path("/memory/reserved-memory", - fdt_scan_reserved_mem, NULL); -} diff --git a/drivers/of/platform.c b/drivers/of/platform.c index 9b439ac63d8e..049c3d0bddd1 100644 --- a/drivers/of/platform.c +++ b/drivers/of/platform.c @@ -21,7 +21,6 @@ #include <linux/of_device.h> #include <linux/of_irq.h> #include <linux/of_platform.h> -#include <linux/of_reserved_mem.h> #include <linux/platform_device.h> const struct of_device_id of_default_bus_match_table[] = { @@ -219,8 +218,6 @@ static struct platform_device *of_platform_device_create_pdata( dev->dev.bus = &platform_bus_type; dev->dev.platform_data = platform_data; - of_reserved_mem_device_init(&dev->dev); - /* We do not fill the DMA ops for platform devices by default. * This is currently the responsibility of the platform code * to do such, possibly using a device notifier @@ -228,7 +225,6 @@ static struct platform_device *of_platform_device_create_pdata( if (of_device_add(dev) != 0) { platform_device_put(dev); - of_reserved_mem_device_release(&dev->dev); return NULL; } @@ -284,9 +280,6 @@ static struct amba_device *of_amba_device_create(struct device_node *node, else of_device_make_bus_id(&dev->dev); - /* setup amba-specific device info */ - dev->dma_mask = ~0; - /* Allow the HW Peripheral ID to be overridden */ prop = of_get_property(node, "arm,primecell-periphid", NULL); if (prop) diff --git a/drivers/parport/parport_pc.c b/drivers/parport/parport_pc.c index 903e1285fda0..963761526229 100644 --- a/drivers/parport/parport_pc.c +++ b/drivers/parport/parport_pc.c @@ -2004,6 +2004,7 @@ struct parport *parport_pc_probe_port(unsigned long int base, struct resource *ECR_res = NULL; struct resource *EPP_res = NULL; struct platform_device *pdev = NULL; + int ret; if (!dev) { /* We need a physical device to attach to, but none was @@ -2014,8 +2015,11 @@ struct parport *parport_pc_probe_port(unsigned long int base, return NULL; dev = &pdev->dev; - dev->coherent_dma_mask = DMA_BIT_MASK(24); - dev->dma_mask = &dev->coherent_dma_mask; + ret = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(24)); + if (ret) { + dev_err(dev, "Unable to set coherent dma mask: disabling DMA\n"); + dma = PARPORT_DMA_NONE; + } } ops = kmalloc(sizeof(struct parport_operations), GFP_KERNEL); diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index 0b7d23b4ad95..1ea75236a15f 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -552,9 +552,8 @@ static void __ref enable_slot(struct acpiphp_slot *slot) struct acpiphp_func *func; int max, pass; LIST_HEAD(add_list); - int nr_found; - nr_found = acpiphp_rescan_slot(slot); + acpiphp_rescan_slot(slot); max = acpiphp_max_busnr(bus); for (pass = 0; pass < 2; pass++) { list_for_each_entry(dev, &bus->devices, bus_list) { @@ -574,9 +573,6 @@ static void __ref enable_slot(struct acpiphp_slot *slot) } } __pci_bus_assign_resources(bus, &add_list, NULL); - /* Nothing more to do here if there are no new devices on this bus. */ - if (!nr_found && (slot->flags & SLOT_ENABLED)) - return; acpiphp_sanitize_bus(bus); acpiphp_set_hpp_values(bus); @@ -994,14 +990,16 @@ void acpiphp_enumerate_slots(struct pci_bus *bus) /* * This bridge should have been registered as a hotplug function - * under its parent, so the context has to be there. If not, we - * are in deep goo. + * under its parent, so the context should be there, unless the + * parent is going to be handled by pciehp, in which case this + * bridge is not interesting to us either. */ mutex_lock(&acpiphp_context_lock); context = acpiphp_get_context(handle); - if (WARN_ON(!context)) { + if (!context) { mutex_unlock(&acpiphp_context_lock); put_device(&bus->dev); + pci_dev_put(bridge->pci_dev); kfree(bridge); return; } diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index 96d6b2eef4f2..b51a7460cc49 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -504,6 +504,7 @@ config ASUS_WMI depends on BACKLIGHT_CLASS_DEVICE depends on RFKILL || RFKILL = n depends on HOTPLUG_PCI + depends on ACPI_VIDEO || ACPI_VIDEO = n select INPUT_SPARSEKMAP select LEDS_CLASS select NEW_LEDS diff --git a/drivers/platform/x86/sony-laptop.c b/drivers/platform/x86/sony-laptop.c index d3fd52036fd6..13ec195f0ca6 100644 --- a/drivers/platform/x86/sony-laptop.c +++ b/drivers/platform/x86/sony-laptop.c @@ -127,18 +127,17 @@ MODULE_PARM_DESC(minor, "default is -1 (automatic)"); #endif -static int kbd_backlight = 1; +static int kbd_backlight = -1; module_param(kbd_backlight, int, 0444); MODULE_PARM_DESC(kbd_backlight, "set this to 0 to disable keyboard backlight, " - "1 to enable it (default: 0)"); + "1 to enable it (default: no change from current value)"); -static int kbd_backlight_timeout; /* = 0 */ +static int kbd_backlight_timeout = -1; module_param(kbd_backlight_timeout, int, 0444); MODULE_PARM_DESC(kbd_backlight_timeout, - "set this to 0 to set the default 10 seconds timeout, " - "1 for 30 seconds, 2 for 60 seconds and 3 to disable timeout " - "(default: 0)"); + "meaningful values vary from 0 to 3 and their meaning depends " + "on the model (default: no change from current value)"); #ifdef CONFIG_PM_SLEEP static void sony_nc_kbd_backlight_resume(void); @@ -1844,6 +1843,8 @@ static int sony_nc_kbd_backlight_setup(struct platform_device *pd, if (!kbdbl_ctl) return -ENOMEM; + kbdbl_ctl->mode = kbd_backlight; + kbdbl_ctl->timeout = kbd_backlight_timeout; kbdbl_ctl->handle = handle; if (handle == 0x0137) kbdbl_ctl->base = 0x0C00; @@ -1870,8 +1871,8 @@ static int sony_nc_kbd_backlight_setup(struct platform_device *pd, if (ret) goto outmode; - __sony_nc_kbd_backlight_mode_set(kbd_backlight); - __sony_nc_kbd_backlight_timeout_set(kbd_backlight_timeout); + __sony_nc_kbd_backlight_mode_set(kbdbl_ctl->mode); + __sony_nc_kbd_backlight_timeout_set(kbdbl_ctl->timeout); return 0; @@ -1886,17 +1887,8 @@ outkzalloc: static void sony_nc_kbd_backlight_cleanup(struct platform_device *pd) { if (kbdbl_ctl) { - int result; - device_remove_file(&pd->dev, &kbdbl_ctl->mode_attr); device_remove_file(&pd->dev, &kbdbl_ctl->timeout_attr); - - /* restore the default hw behaviour */ - sony_call_snc_handle(kbdbl_ctl->handle, - kbdbl_ctl->base | 0x10000, &result); - sony_call_snc_handle(kbdbl_ctl->handle, - kbdbl_ctl->base + 0x200, &result); - kfree(kbdbl_ctl); kbdbl_ctl = NULL; } diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index 5adb2042e824..cee7e2708a1f 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -2077,6 +2077,7 @@ dasd_eckd_build_format(struct dasd_device *base, int intensity = 0; int r0_perm; int nr_tracks; + int use_prefix; startdev = dasd_alias_get_start_dev(base); if (!startdev) @@ -2106,28 +2107,46 @@ dasd_eckd_build_format(struct dasd_device *base, intensity = fdata->intensity; } + use_prefix = base_priv->features.feature[8] & 0x01; + switch (intensity) { case 0x00: /* Normal format */ case 0x08: /* Normal format, use cdl. */ cplength = 2 + (rpt*nr_tracks); - datasize = sizeof(struct PFX_eckd_data) + - sizeof(struct LO_eckd_data) + - rpt * nr_tracks * sizeof(struct eckd_count); + if (use_prefix) + datasize = sizeof(struct PFX_eckd_data) + + sizeof(struct LO_eckd_data) + + rpt * nr_tracks * sizeof(struct eckd_count); + else + datasize = sizeof(struct DE_eckd_data) + + sizeof(struct LO_eckd_data) + + rpt * nr_tracks * sizeof(struct eckd_count); break; case 0x01: /* Write record zero and format track. */ case 0x09: /* Write record zero and format track, use cdl. */ cplength = 2 + rpt * nr_tracks; - datasize = sizeof(struct PFX_eckd_data) + - sizeof(struct LO_eckd_data) + - sizeof(struct eckd_count) + - rpt * nr_tracks * sizeof(struct eckd_count); + if (use_prefix) + datasize = sizeof(struct PFX_eckd_data) + + sizeof(struct LO_eckd_data) + + sizeof(struct eckd_count) + + rpt * nr_tracks * sizeof(struct eckd_count); + else + datasize = sizeof(struct DE_eckd_data) + + sizeof(struct LO_eckd_data) + + sizeof(struct eckd_count) + + rpt * nr_tracks * sizeof(struct eckd_count); break; case 0x04: /* Invalidate track. */ case 0x0c: /* Invalidate track, use cdl. */ cplength = 3; - datasize = sizeof(struct PFX_eckd_data) + - sizeof(struct LO_eckd_data) + - sizeof(struct eckd_count); + if (use_prefix) + datasize = sizeof(struct PFX_eckd_data) + + sizeof(struct LO_eckd_data) + + sizeof(struct eckd_count); + else + datasize = sizeof(struct DE_eckd_data) + + sizeof(struct LO_eckd_data) + + sizeof(struct eckd_count); break; default: dev_warn(&startdev->cdev->dev, @@ -2147,14 +2166,25 @@ dasd_eckd_build_format(struct dasd_device *base, switch (intensity & ~0x08) { case 0x00: /* Normal format. */ - prefix(ccw++, (struct PFX_eckd_data *) data, - fdata->start_unit, fdata->stop_unit, - DASD_ECKD_CCW_WRITE_CKD, base, startdev); - /* grant subsystem permission to format R0 */ - if (r0_perm) - ((struct PFX_eckd_data *)data) - ->define_extent.ga_extended |= 0x04; - data += sizeof(struct PFX_eckd_data); + if (use_prefix) { + prefix(ccw++, (struct PFX_eckd_data *) data, + fdata->start_unit, fdata->stop_unit, + DASD_ECKD_CCW_WRITE_CKD, base, startdev); + /* grant subsystem permission to format R0 */ + if (r0_perm) + ((struct PFX_eckd_data *)data) + ->define_extent.ga_extended |= 0x04; + data += sizeof(struct PFX_eckd_data); + } else { + define_extent(ccw++, (struct DE_eckd_data *) data, + fdata->start_unit, fdata->stop_unit, + DASD_ECKD_CCW_WRITE_CKD, startdev); + /* grant subsystem permission to format R0 */ + if (r0_perm) + ((struct DE_eckd_data *) data) + ->ga_extended |= 0x04; + data += sizeof(struct DE_eckd_data); + } ccw[-1].flags |= CCW_FLAG_CC; locate_record(ccw++, (struct LO_eckd_data *) data, fdata->start_unit, 0, rpt*nr_tracks, @@ -2163,11 +2193,18 @@ dasd_eckd_build_format(struct dasd_device *base, data += sizeof(struct LO_eckd_data); break; case 0x01: /* Write record zero + format track. */ - prefix(ccw++, (struct PFX_eckd_data *) data, - fdata->start_unit, fdata->stop_unit, - DASD_ECKD_CCW_WRITE_RECORD_ZERO, - base, startdev); - data += sizeof(struct PFX_eckd_data); + if (use_prefix) { + prefix(ccw++, (struct PFX_eckd_data *) data, + fdata->start_unit, fdata->stop_unit, + DASD_ECKD_CCW_WRITE_RECORD_ZERO, + base, startdev); + data += sizeof(struct PFX_eckd_data); + } else { + define_extent(ccw++, (struct DE_eckd_data *) data, + fdata->start_unit, fdata->stop_unit, + DASD_ECKD_CCW_WRITE_RECORD_ZERO, startdev); + data += sizeof(struct DE_eckd_data); + } ccw[-1].flags |= CCW_FLAG_CC; locate_record(ccw++, (struct LO_eckd_data *) data, fdata->start_unit, 0, rpt * nr_tracks + 1, @@ -2176,10 +2213,17 @@ dasd_eckd_build_format(struct dasd_device *base, data += sizeof(struct LO_eckd_data); break; case 0x04: /* Invalidate track. */ - prefix(ccw++, (struct PFX_eckd_data *) data, - fdata->start_unit, fdata->stop_unit, - DASD_ECKD_CCW_WRITE_CKD, base, startdev); - data += sizeof(struct PFX_eckd_data); + if (use_prefix) { + prefix(ccw++, (struct PFX_eckd_data *) data, + fdata->start_unit, fdata->stop_unit, + DASD_ECKD_CCW_WRITE_CKD, base, startdev); + data += sizeof(struct PFX_eckd_data); + } else { + define_extent(ccw++, (struct DE_eckd_data *) data, + fdata->start_unit, fdata->stop_unit, + DASD_ECKD_CCW_WRITE_CKD, startdev); + data += sizeof(struct DE_eckd_data); + } ccw[-1].flags |= CCW_FLAG_CC; locate_record(ccw++, (struct LO_eckd_data *) data, fdata->start_unit, 0, 1, diff --git a/drivers/s390/char/sclp.c b/drivers/s390/char/sclp.c index a3aa374799dc..1fe264379e0d 100644 --- a/drivers/s390/char/sclp.c +++ b/drivers/s390/char/sclp.c @@ -486,7 +486,7 @@ sclp_sync_wait(void) timeout = 0; if (timer_pending(&sclp_request_timer)) { /* Get timeout TOD value */ - timeout = get_tod_clock() + + timeout = get_tod_clock_fast() + sclp_tod_from_jiffies(sclp_request_timer.expires - jiffies); } @@ -508,7 +508,7 @@ sclp_sync_wait(void) while (sclp_running_state != sclp_running_state_idle) { /* Check for expired request timer */ if (timer_pending(&sclp_request_timer) && - get_tod_clock() > timeout && + get_tod_clock_fast() > timeout && del_timer(&sclp_request_timer)) sclp_request_timer.function(sclp_request_timer.data); cpu_relax(); diff --git a/drivers/s390/char/vmlogrdr.c b/drivers/s390/char/vmlogrdr.c index 9b3a24e8d3a0..cf31d3321dab 100644 --- a/drivers/s390/char/vmlogrdr.c +++ b/drivers/s390/char/vmlogrdr.c @@ -313,7 +313,7 @@ static int vmlogrdr_open (struct inode *inode, struct file *filp) int ret; dev_num = iminor(inode); - if (dev_num > MAXMINOR) + if (dev_num >= MAXMINOR) return -ENODEV; logptr = &sys_ser[dev_num]; diff --git a/drivers/s390/cio/cio.c b/drivers/s390/cio/cio.c index d7da67a31c77..88e35d85d205 100644 --- a/drivers/s390/cio/cio.c +++ b/drivers/s390/cio/cio.c @@ -878,9 +878,9 @@ static void css_reset(void) atomic_inc(&chpid_reset_count); } /* Wait for machine check for all channel paths. */ - timeout = get_tod_clock() + (RCHP_TIMEOUT << 12); + timeout = get_tod_clock_fast() + (RCHP_TIMEOUT << 12); while (atomic_read(&chpid_reset_count) != 0) { - if (get_tod_clock() > timeout) + if (get_tod_clock_fast() > timeout) break; cpu_relax(); } diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c index 8ed52aa49122..bbd3e511c771 100644 --- a/drivers/s390/cio/qdio_main.c +++ b/drivers/s390/cio/qdio_main.c @@ -338,10 +338,10 @@ again: retries++; if (!start_time) { - start_time = get_tod_clock(); + start_time = get_tod_clock_fast(); goto again; } - if ((get_tod_clock() - start_time) < QDIO_BUSY_BIT_PATIENCE) + if (get_tod_clock_fast() - start_time < QDIO_BUSY_BIT_PATIENCE) goto again; } if (retries) { @@ -504,7 +504,7 @@ static int get_inbound_buffer_frontier(struct qdio_q *q) int count, stop; unsigned char state = 0; - q->timestamp = get_tod_clock(); + q->timestamp = get_tod_clock_fast(); /* * Don't check 128 buffers, as otherwise qdio_inbound_q_moved @@ -595,7 +595,7 @@ static inline int qdio_inbound_q_done(struct qdio_q *q) * At this point we know, that inbound first_to_check * has (probably) not moved (see qdio_inbound_processing). */ - if (get_tod_clock() > q->u.in.timestamp + QDIO_INPUT_THRESHOLD) { + if (get_tod_clock_fast() > q->u.in.timestamp + QDIO_INPUT_THRESHOLD) { DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "in done:%02x", q->first_to_check); return 1; @@ -728,7 +728,7 @@ static int get_outbound_buffer_frontier(struct qdio_q *q) int count, stop; unsigned char state = 0; - q->timestamp = get_tod_clock(); + q->timestamp = get_tod_clock_fast(); if (need_siga_sync(q)) if (((queue_type(q) != QDIO_IQDIO_QFMT) && diff --git a/drivers/scsi/BusLogic.c b/drivers/scsi/BusLogic.c index feab3a5e50b5..757eb0716d45 100644 --- a/drivers/scsi/BusLogic.c +++ b/drivers/scsi/BusLogic.c @@ -696,7 +696,7 @@ static int __init blogic_init_mm_probeinfo(struct blogic_adapter *adapter) while ((pci_device = pci_get_device(PCI_VENDOR_ID_BUSLOGIC, PCI_DEVICE_ID_BUSLOGIC_MULTIMASTER, pci_device)) != NULL) { - struct blogic_adapter *adapter = adapter; + struct blogic_adapter *host_adapter = adapter; struct blogic_adapter_info adapter_info; enum blogic_isa_ioport mod_ioaddr_req; unsigned char bus; @@ -744,9 +744,9 @@ static int __init blogic_init_mm_probeinfo(struct blogic_adapter *adapter) known and enabled, note that the particular Standard ISA I/O Address should not be probed. */ - adapter->io_addr = io_addr; - blogic_intreset(adapter); - if (blogic_cmd(adapter, BLOGIC_INQ_PCI_INFO, NULL, 0, + host_adapter->io_addr = io_addr; + blogic_intreset(host_adapter); + if (blogic_cmd(host_adapter, BLOGIC_INQ_PCI_INFO, NULL, 0, &adapter_info, sizeof(adapter_info)) == sizeof(adapter_info)) { if (adapter_info.isa_port < 6) @@ -762,7 +762,7 @@ static int __init blogic_init_mm_probeinfo(struct blogic_adapter *adapter) I/O Address assigned at system initialization. */ mod_ioaddr_req = BLOGIC_IO_DISABLE; - blogic_cmd(adapter, BLOGIC_MOD_IOADDR, &mod_ioaddr_req, + blogic_cmd(host_adapter, BLOGIC_MOD_IOADDR, &mod_ioaddr_req, sizeof(mod_ioaddr_req), NULL, 0); /* For the first MultiMaster Host Adapter enumerated, @@ -779,12 +779,12 @@ static int __init blogic_init_mm_probeinfo(struct blogic_adapter *adapter) fetch_localram.offset = BLOGIC_AUTOSCSI_BASE + 45; fetch_localram.count = sizeof(autoscsi_byte45); - blogic_cmd(adapter, BLOGIC_FETCH_LOCALRAM, + blogic_cmd(host_adapter, BLOGIC_FETCH_LOCALRAM, &fetch_localram, sizeof(fetch_localram), &autoscsi_byte45, sizeof(autoscsi_byte45)); - blogic_cmd(adapter, BLOGIC_GET_BOARD_ID, NULL, 0, &id, - sizeof(id)); + blogic_cmd(host_adapter, BLOGIC_GET_BOARD_ID, NULL, 0, + &id, sizeof(id)); if (id.fw_ver_digit1 == '5') force_scan_order = autoscsi_byte45.force_scan_order; diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c index 408a42ef787a..f0d432c139d0 100644 --- a/drivers/scsi/aacraid/linit.c +++ b/drivers/scsi/aacraid/linit.c @@ -771,6 +771,8 @@ static long aac_compat_do_ioctl(struct aac_dev *dev, unsigned cmd, unsigned long static int aac_compat_ioctl(struct scsi_device *sdev, int cmd, void __user *arg) { struct aac_dev *dev = (struct aac_dev *)sdev->host->hostdata; + if (!capable(CAP_SYS_RAWIO)) + return -EPERM; return aac_compat_do_ioctl(dev, cmd, (unsigned long)arg); } diff --git a/drivers/scsi/qla2xxx/qla_dbg.c b/drivers/scsi/qla2xxx/qla_dbg.c index 2ef497ebadc0..ee5c1833eb73 100644 --- a/drivers/scsi/qla2xxx/qla_dbg.c +++ b/drivers/scsi/qla2xxx/qla_dbg.c @@ -20,7 +20,7 @@ * | Device Discovery | 0x2095 | 0x2020-0x2022, | * | | | 0x2011-0x2012, | * | | | 0x2016 | - * | Queue Command and IO tracing | 0x3058 | 0x3006-0x300b | + * | Queue Command and IO tracing | 0x3059 | 0x3006-0x300b | * | | | 0x3027-0x3028 | * | | | 0x303d-0x3041 | * | | | 0x302d,0x3033 | diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index df1b30ba938c..ff9c86b1a0d8 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -1957,6 +1957,15 @@ qla2x00_status_entry(scsi_qla_host_t *vha, struct rsp_que *rsp, void *pkt) que = MSW(sts->handle); req = ha->req_q_map[que]; + /* Check for invalid queue pointer */ + if (req == NULL || + que >= find_first_zero_bit(ha->req_qid_map, ha->max_req_queues)) { + ql_dbg(ql_dbg_io, vha, 0x3059, + "Invalid status handle (0x%x): Bad req pointer. req=%p, " + "que=%u.\n", sts->handle, req, que); + return; + } + /* Validate handle. */ if (handle < req->num_outstanding_cmds) sp = req->outstanding_cmds[handle]; diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index d1549b74e2d1..7bd7f0d5f050 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1684,7 +1684,7 @@ u64 scsi_calculate_bounce_limit(struct Scsi_Host *shost) host_dev = scsi_get_device(shost); if (host_dev && host_dev->dma_mask) - bounce_limit = *host_dev->dma_mask; + bounce_limit = dma_max_pfn(host_dev) << PAGE_SHIFT; return bounce_limit; } diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index e62d17d41d4e..5693f6d7eddb 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -2854,6 +2854,7 @@ static void sd_probe_async(void *data, async_cookie_t cookie) gd->events |= DISK_EVENT_MEDIA_CHANGE; } + blk_pm_runtime_init(sdp->request_queue, dev); add_disk(gd); if (sdkp->capacity) sd_dif_config_host(sdkp); @@ -2862,7 +2863,6 @@ static void sd_probe_async(void *data, async_cookie_t cookie) sd_printk(KERN_NOTICE, sdkp, "Attached SCSI %sdisk\n", sdp->removable ? "removable " : ""); - blk_pm_runtime_init(sdp->request_queue, dev); scsi_autopm_put_device(sdp); put_device(&sdkp->dev); } diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 5cbc4bb1b395..df5e961484e1 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -105,8 +105,11 @@ static int scatter_elem_sz_prev = SG_SCATTER_SZ; static int sg_add(struct device *, struct class_interface *); static void sg_remove(struct device *, struct class_interface *); +static DEFINE_SPINLOCK(sg_open_exclusive_lock); + static DEFINE_IDR(sg_index_idr); -static DEFINE_RWLOCK(sg_index_lock); +static DEFINE_RWLOCK(sg_index_lock); /* Also used to lock + file descriptor list for device */ static struct class_interface sg_interface = { .add_dev = sg_add, @@ -143,7 +146,8 @@ typedef struct sg_request { /* SG_MAX_QUEUE requests outstanding per file */ } Sg_request; typedef struct sg_fd { /* holds the state of a file descriptor */ - struct list_head sfd_siblings; /* protected by sfd_lock of device */ + /* sfd_siblings is protected by sg_index_lock */ + struct list_head sfd_siblings; struct sg_device *parentdp; /* owning device */ wait_queue_head_t read_wait; /* queue read until command done */ rwlock_t rq_list_lock; /* protect access to list in req_arr */ @@ -166,12 +170,13 @@ typedef struct sg_fd { /* holds the state of a file descriptor */ typedef struct sg_device { /* holds the state of each scsi generic device */ struct scsi_device *device; + wait_queue_head_t o_excl_wait; /* queue open() when O_EXCL in use */ int sg_tablesize; /* adapter's max scatter-gather table size */ u32 index; /* device index number */ - spinlock_t sfd_lock; /* protect file descriptor list for device */ + /* sfds is protected by sg_index_lock */ struct list_head sfds; - struct rw_semaphore o_sem; /* exclude open should hold this rwsem */ volatile char detached; /* 0->attached, 1->detached pending removal */ + /* exclude protected by sg_open_exclusive_lock */ char exclude; /* opened for exclusive access */ char sgdebug; /* 0->off, 1->sense, 9->dump dev, 10-> all devs */ struct gendisk *disk; @@ -220,14 +225,35 @@ static int sg_allow_access(struct file *filp, unsigned char *cmd) return blk_verify_command(cmd, filp->f_mode & FMODE_WRITE); } +static int get_exclude(Sg_device *sdp) +{ + unsigned long flags; + int ret; + + spin_lock_irqsave(&sg_open_exclusive_lock, flags); + ret = sdp->exclude; + spin_unlock_irqrestore(&sg_open_exclusive_lock, flags); + return ret; +} + +static int set_exclude(Sg_device *sdp, char val) +{ + unsigned long flags; + + spin_lock_irqsave(&sg_open_exclusive_lock, flags); + sdp->exclude = val; + spin_unlock_irqrestore(&sg_open_exclusive_lock, flags); + return val; +} + static int sfds_list_empty(Sg_device *sdp) { unsigned long flags; int ret; - spin_lock_irqsave(&sdp->sfd_lock, flags); + read_lock_irqsave(&sg_index_lock, flags); ret = list_empty(&sdp->sfds); - spin_unlock_irqrestore(&sdp->sfd_lock, flags); + read_unlock_irqrestore(&sg_index_lock, flags); return ret; } @@ -239,6 +265,7 @@ sg_open(struct inode *inode, struct file *filp) struct request_queue *q; Sg_device *sdp; Sg_fd *sfp; + int res; int retval; nonseekable_open(inode, filp); @@ -267,52 +294,54 @@ sg_open(struct inode *inode, struct file *filp) goto error_out; } - if ((flags & O_EXCL) && (O_RDONLY == (flags & O_ACCMODE))) { - retval = -EPERM; /* Can't lock it with read only access */ - goto error_out; - } - if (flags & O_NONBLOCK) { - if (flags & O_EXCL) { - if (!down_write_trylock(&sdp->o_sem)) { - retval = -EBUSY; - goto error_out; - } - } else { - if (!down_read_trylock(&sdp->o_sem)) { - retval = -EBUSY; - goto error_out; - } + if (flags & O_EXCL) { + if (O_RDONLY == (flags & O_ACCMODE)) { + retval = -EPERM; /* Can't lock it with read only access */ + goto error_out; + } + if (!sfds_list_empty(sdp) && (flags & O_NONBLOCK)) { + retval = -EBUSY; + goto error_out; + } + res = wait_event_interruptible(sdp->o_excl_wait, + ((!sfds_list_empty(sdp) || get_exclude(sdp)) ? 0 : set_exclude(sdp, 1))); + if (res) { + retval = res; /* -ERESTARTSYS because signal hit process */ + goto error_out; + } + } else if (get_exclude(sdp)) { /* some other fd has an exclusive lock on dev */ + if (flags & O_NONBLOCK) { + retval = -EBUSY; + goto error_out; + } + res = wait_event_interruptible(sdp->o_excl_wait, !get_exclude(sdp)); + if (res) { + retval = res; /* -ERESTARTSYS because signal hit process */ + goto error_out; } - } else { - if (flags & O_EXCL) - down_write(&sdp->o_sem); - else - down_read(&sdp->o_sem); } - /* Since write lock is held, no need to check sfd_list */ - if (flags & O_EXCL) - sdp->exclude = 1; /* used by release lock */ - + if (sdp->detached) { + retval = -ENODEV; + goto error_out; + } if (sfds_list_empty(sdp)) { /* no existing opens on this device */ sdp->sgdebug = 0; q = sdp->device->request_queue; sdp->sg_tablesize = queue_max_segments(q); } - sfp = sg_add_sfp(sdp, dev); - if (!IS_ERR(sfp)) + if ((sfp = sg_add_sfp(sdp, dev))) filp->private_data = sfp; - /* retval is already provably zero at this point because of the - * check after retval = scsi_autopm_get_device(sdp->device)) - */ else { - retval = PTR_ERR(sfp); - if (flags & O_EXCL) { - sdp->exclude = 0; /* undo if error */ - up_write(&sdp->o_sem); - } else - up_read(&sdp->o_sem); + set_exclude(sdp, 0); /* undo if error */ + wake_up_interruptible(&sdp->o_excl_wait); + } + retval = -ENOMEM; + goto error_out; + } + retval = 0; error_out: + if (retval) { scsi_autopm_put_device(sdp->device); sdp_put: scsi_device_put(sdp->device); @@ -329,18 +358,13 @@ sg_release(struct inode *inode, struct file *filp) { Sg_device *sdp; Sg_fd *sfp; - int excl; if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp))) return -ENXIO; SCSI_LOG_TIMEOUT(3, printk("sg_release: %s\n", sdp->disk->disk_name)); - excl = sdp->exclude; - sdp->exclude = 0; - if (excl) - up_write(&sdp->o_sem); - else - up_read(&sdp->o_sem); + set_exclude(sdp, 0); + wake_up_interruptible(&sdp->o_excl_wait); scsi_autopm_put_device(sdp->device); kref_put(&sfp->f_ref, sg_remove_sfp); @@ -1391,9 +1415,8 @@ static Sg_device *sg_alloc(struct gendisk *disk, struct scsi_device *scsidp) disk->first_minor = k; sdp->disk = disk; sdp->device = scsidp; - spin_lock_init(&sdp->sfd_lock); INIT_LIST_HEAD(&sdp->sfds); - init_rwsem(&sdp->o_sem); + init_waitqueue_head(&sdp->o_excl_wait); sdp->sg_tablesize = queue_max_segments(q); sdp->index = k; kref_init(&sdp->d_ref); @@ -1526,13 +1549,11 @@ static void sg_remove(struct device *cl_dev, struct class_interface *cl_intf) /* Need a write lock to set sdp->detached. */ write_lock_irqsave(&sg_index_lock, iflags); - spin_lock(&sdp->sfd_lock); sdp->detached = 1; list_for_each_entry(sfp, &sdp->sfds, sfd_siblings) { wake_up_interruptible(&sfp->read_wait); kill_fasync(&sfp->async_qp, SIGPOLL, POLL_HUP); } - spin_unlock(&sdp->sfd_lock); write_unlock_irqrestore(&sg_index_lock, iflags); sysfs_remove_link(&scsidp->sdev_gendev.kobj, "generic"); @@ -2043,7 +2064,7 @@ sg_add_sfp(Sg_device * sdp, int dev) sfp = kzalloc(sizeof(*sfp), GFP_ATOMIC | __GFP_NOWARN); if (!sfp) - return ERR_PTR(-ENOMEM); + return NULL; init_waitqueue_head(&sfp->read_wait); rwlock_init(&sfp->rq_list_lock); @@ -2057,13 +2078,9 @@ sg_add_sfp(Sg_device * sdp, int dev) sfp->cmd_q = SG_DEF_COMMAND_Q; sfp->keep_orphan = SG_DEF_KEEP_ORPHAN; sfp->parentdp = sdp; - spin_lock_irqsave(&sdp->sfd_lock, iflags); - if (sdp->detached) { - spin_unlock_irqrestore(&sdp->sfd_lock, iflags); - return ERR_PTR(-ENODEV); - } + write_lock_irqsave(&sg_index_lock, iflags); list_add_tail(&sfp->sfd_siblings, &sdp->sfds); - spin_unlock_irqrestore(&sdp->sfd_lock, iflags); + write_unlock_irqrestore(&sg_index_lock, iflags); SCSI_LOG_TIMEOUT(3, printk("sg_add_sfp: sfp=0x%p\n", sfp)); if (unlikely(sg_big_buff != def_reserved_size)) sg_big_buff = def_reserved_size; @@ -2113,9 +2130,10 @@ static void sg_remove_sfp(struct kref *kref) struct sg_device *sdp = sfp->parentdp; unsigned long iflags; - spin_lock_irqsave(&sdp->sfd_lock, iflags); + write_lock_irqsave(&sg_index_lock, iflags); list_del(&sfp->sfd_siblings); - spin_unlock_irqrestore(&sdp->sfd_lock, iflags); + write_unlock_irqrestore(&sg_index_lock, iflags); + wake_up_interruptible(&sdp->o_excl_wait); INIT_WORK(&sfp->ew.work, sg_remove_sfp_usercontext); schedule_work(&sfp->ew.work); @@ -2502,7 +2520,7 @@ static int sg_proc_seq_show_devstrs(struct seq_file *s, void *v) return 0; } -/* must be called while holding sg_index_lock and sfd_lock */ +/* must be called while holding sg_index_lock */ static void sg_proc_debug_helper(struct seq_file *s, Sg_device * sdp) { int k, m, new_interface, blen, usg; @@ -2587,26 +2605,22 @@ static int sg_proc_seq_show_debug(struct seq_file *s, void *v) read_lock_irqsave(&sg_index_lock, iflags); sdp = it ? sg_lookup_dev(it->index) : NULL; - if (sdp) { - spin_lock(&sdp->sfd_lock); - if (!list_empty(&sdp->sfds)) { - struct scsi_device *scsidp = sdp->device; + if (sdp && !list_empty(&sdp->sfds)) { + struct scsi_device *scsidp = sdp->device; - seq_printf(s, " >>> device=%s ", sdp->disk->disk_name); - if (sdp->detached) - seq_printf(s, "detached pending close "); - else - seq_printf - (s, "scsi%d chan=%d id=%d lun=%d em=%d", - scsidp->host->host_no, - scsidp->channel, scsidp->id, - scsidp->lun, - scsidp->host->hostt->emulated); - seq_printf(s, " sg_tablesize=%d excl=%d\n", - sdp->sg_tablesize, sdp->exclude); - sg_proc_debug_helper(s, sdp); - } - spin_unlock(&sdp->sfd_lock); + seq_printf(s, " >>> device=%s ", sdp->disk->disk_name); + if (sdp->detached) + seq_printf(s, "detached pending close "); + else + seq_printf + (s, "scsi%d chan=%d id=%d lun=%d em=%d", + scsidp->host->host_no, + scsidp->channel, scsidp->id, + scsidp->lun, + scsidp->host->hostt->emulated); + seq_printf(s, " sg_tablesize=%d excl=%d\n", + sdp->sg_tablesize, get_exclude(sdp)); + sg_proc_debug_helper(s, sdp); } read_unlock_irqrestore(&sg_index_lock, iflags); return 0; diff --git a/drivers/staging/bcm/Bcmchar.c b/drivers/staging/bcm/Bcmchar.c index f91bc1fdd895..639ba96adb36 100644 --- a/drivers/staging/bcm/Bcmchar.c +++ b/drivers/staging/bcm/Bcmchar.c @@ -1960,6 +1960,7 @@ cntrlEnd: BCM_DEBUG_PRINT(Adapter, DBG_TYPE_OTHERS, OSAL_DBG, DBG_LVL_ALL, "Called IOCTL_BCM_GET_DEVICE_DRIVER_INFO\n"); + memset(&DevInfo, 0, sizeof(DevInfo)); DevInfo.MaxRDMBufferSize = BUFFER_4K; DevInfo.u32DSDStartOffset = EEPROM_CALPARAM_START; DevInfo.u32RxAlignmentCorrection = 0; diff --git a/drivers/staging/dwc2/platform.c b/drivers/staging/dwc2/platform.c index 44cce2fa6361..1d68c49afabe 100644 --- a/drivers/staging/dwc2/platform.c +++ b/drivers/staging/dwc2/platform.c @@ -100,8 +100,9 @@ static int dwc2_driver_probe(struct platform_device *dev) */ if (!dev->dev.dma_mask) dev->dev.dma_mask = &dev->dev.coherent_dma_mask; - if (!dev->dev.coherent_dma_mask) - dev->dev.coherent_dma_mask = DMA_BIT_MASK(32); + retval = dma_set_coherent_mask(&dev->dev, DMA_BIT_MASK(32)); + if (retval) + return retval; irq = platform_get_irq(dev, 0); if (irq < 0) { diff --git a/drivers/staging/et131x/et131x.c b/drivers/staging/et131x/et131x.c index f73e58f5ef8d..61da7ee36e45 100644 --- a/drivers/staging/et131x/et131x.c +++ b/drivers/staging/et131x/et131x.c @@ -4797,21 +4797,8 @@ static int et131x_pci_setup(struct pci_dev *pdev, pci_set_master(pdev); /* Check the DMA addressing support of this device */ - if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(64))) { - rc = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64)); - if (rc < 0) { - dev_err(&pdev->dev, - "Unable to obtain 64 bit DMA for consistent allocations\n"); - goto err_release_res; - } - } else if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(32))) { - rc = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)); - if (rc < 0) { - dev_err(&pdev->dev, - "Unable to obtain 32 bit DMA for consistent allocations\n"); - goto err_release_res; - } - } else { + if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)) && + dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32))) { dev_err(&pdev->dev, "No usable DMA addressing method\n"); rc = -EIO; goto err_release_res; diff --git a/drivers/staging/imx-drm/imx-drm-core.c b/drivers/staging/imx-drm/imx-drm-core.c index a2e52a0c53c9..a475b3e07c9c 100644 --- a/drivers/staging/imx-drm/imx-drm-core.c +++ b/drivers/staging/imx-drm/imx-drm-core.c @@ -800,6 +800,12 @@ static struct drm_driver imx_drm_driver = { static int imx_drm_platform_probe(struct platform_device *pdev) { + int ret; + + ret = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)); + if (ret) + return ret; + imx_drm_device->dev = &pdev->dev; return drm_platform_init(&imx_drm_driver, pdev); @@ -842,8 +848,6 @@ static int __init imx_drm_init(void) goto err_pdev; } - imx_drm_pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32), - ret = platform_driver_register(&imx_drm_pdrv); if (ret) goto err_pdrv; diff --git a/drivers/staging/imx-drm/ipuv3-crtc.c b/drivers/staging/imx-drm/ipuv3-crtc.c index 6fd37a7453e9..9e73e8d8c9aa 100644 --- a/drivers/staging/imx-drm/ipuv3-crtc.c +++ b/drivers/staging/imx-drm/ipuv3-crtc.c @@ -523,7 +523,9 @@ static int ipu_drm_probe(struct platform_device *pdev) if (!pdata) return -EINVAL; - pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32); + ret = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)); + if (ret) + return ret; ipu_crtc = devm_kzalloc(&pdev->dev, sizeof(*ipu_crtc), GFP_KERNEL); if (!ipu_crtc) diff --git a/drivers/staging/media/dt3155v4l/dt3155v4l.c b/drivers/staging/media/dt3155v4l/dt3155v4l.c index 90d6ac469355..081407be33ab 100644 --- a/drivers/staging/media/dt3155v4l/dt3155v4l.c +++ b/drivers/staging/media/dt3155v4l/dt3155v4l.c @@ -901,10 +901,7 @@ dt3155_probe(struct pci_dev *pdev, const struct pci_device_id *id) int err; struct dt3155_priv *pd; - err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); - if (err) - return -ENODEV; - err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)); + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); if (err) return -ENODEV; pd = kzalloc(sizeof(*pd), GFP_KERNEL); diff --git a/drivers/staging/media/msi3101/Kconfig b/drivers/staging/media/msi3101/Kconfig index b94a95a597d6..76d5bbd4d93c 100644 --- a/drivers/staging/media/msi3101/Kconfig +++ b/drivers/staging/media/msi3101/Kconfig @@ -1,3 +1,4 @@ config USB_MSI3101 tristate "Mirics MSi3101 SDR Dongle" depends on USB && VIDEO_DEV && VIDEO_V4L2 + select VIDEOBUF2_VMALLOC diff --git a/drivers/staging/media/msi3101/sdr-msi3101.c b/drivers/staging/media/msi3101/sdr-msi3101.c index 24c7b70a6cbf..4c3bf776bb20 100644 --- a/drivers/staging/media/msi3101/sdr-msi3101.c +++ b/drivers/staging/media/msi3101/sdr-msi3101.c @@ -1131,7 +1131,13 @@ static int msi3101_queue_setup(struct vb2_queue *vq, /* Absolute min and max number of buffers available for mmap() */ *nbuffers = 32; *nplanes = 1; - sizes[0] = PAGE_ALIGN(3 * 3072); /* 3 * 768 * 4 */ + /* + * 3, wMaxPacketSize 3x 1024 bytes + * 504, max IQ sample pairs per 1024 frame + * 2, two samples, I and Q + * 4, 32-bit float + */ + sizes[0] = PAGE_ALIGN(3 * 504 * 2 * 4); /* = 12096 */ dev_dbg(&s->udev->dev, "%s: nbuffers=%d sizes[0]=%d\n", __func__, *nbuffers, sizes[0]); return 0; @@ -1657,7 +1663,7 @@ static int vidioc_s_frequency(struct file *file, void *priv, f->frequency * 625UL / 10UL); } -const struct v4l2_ioctl_ops msi3101_ioctl_ops = { +static const struct v4l2_ioctl_ops msi3101_ioctl_ops = { .vidioc_querycap = msi3101_querycap, .vidioc_enum_input = msi3101_enum_input, diff --git a/drivers/staging/ozwpan/ozcdev.c b/drivers/staging/ozwpan/ozcdev.c index 6ccb64fb0786..6ce0af9977d8 100644 --- a/drivers/staging/ozwpan/ozcdev.c +++ b/drivers/staging/ozwpan/ozcdev.c @@ -155,6 +155,9 @@ static ssize_t oz_cdev_write(struct file *filp, const char __user *buf, struct oz_app_hdr *app_hdr; struct oz_serial_ctx *ctx; + if (count > sizeof(ei->data) - sizeof(*elt) - sizeof(*app_hdr)) + return -EINVAL; + spin_lock_bh(&g_cdev.lock); pd = g_cdev.active_pd; if (pd) diff --git a/drivers/staging/sb105x/sb_pci_mp.c b/drivers/staging/sb105x/sb_pci_mp.c index 23db32f07fd5..a10cdb17038b 100644 --- a/drivers/staging/sb105x/sb_pci_mp.c +++ b/drivers/staging/sb105x/sb_pci_mp.c @@ -1063,7 +1063,7 @@ static int mp_wait_modem_status(struct sb_uart_state *state, unsigned long arg) static int mp_get_count(struct sb_uart_state *state, struct serial_icounter_struct *icnt) { - struct serial_icounter_struct icount; + struct serial_icounter_struct icount = {}; struct sb_uart_icount cnow; struct sb_uart_port *port = state->port; diff --git a/drivers/staging/wlags49_h2/wl_priv.c b/drivers/staging/wlags49_h2/wl_priv.c index c97e0e154d28..7e10dcdc3090 100644 --- a/drivers/staging/wlags49_h2/wl_priv.c +++ b/drivers/staging/wlags49_h2/wl_priv.c @@ -570,6 +570,7 @@ int wvlan_uil_put_info(struct uilreq *urq, struct wl_private *lp) ltv_t *pLtv; bool_t ltvAllocated = FALSE; ENCSTRCT sEncryption; + size_t len; #ifdef USE_WDS hcf_16 hcfPort = HCF_PORT_0; @@ -686,7 +687,8 @@ int wvlan_uil_put_info(struct uilreq *urq, struct wl_private *lp) break; case CFG_CNF_OWN_NAME: memset(lp->StationName, 0, sizeof(lp->StationName)); - memcpy((void *)lp->StationName, (void *)&pLtv->u.u8[2], (size_t)pLtv->u.u16[0]); + len = min_t(size_t, pLtv->u.u16[0], sizeof(lp->StationName)); + strlcpy(lp->StationName, &pLtv->u.u8[2], len); pLtv->u.u16[0] = CNV_INT_TO_LITTLE(pLtv->u.u16[0]); break; case CFG_CNF_LOAD_BALANCING: @@ -1783,6 +1785,7 @@ int wvlan_set_station_nickname(struct net_device *dev, { struct wl_private *lp = wl_priv(dev); unsigned long flags; + size_t len; int ret = 0; /*------------------------------------------------------------------------*/ @@ -1793,8 +1796,8 @@ int wvlan_set_station_nickname(struct net_device *dev, wl_lock(lp, &flags); memset(lp->StationName, 0, sizeof(lp->StationName)); - - memcpy(lp->StationName, extra, wrqu->data.length); + len = min_t(size_t, wrqu->data.length, sizeof(lp->StationName)); + strlcpy(lp->StationName, extra, len); /* Commit the adapter parameters */ wl_apply(lp); diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index 551c96ca60ac..0f199f6a0738 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -134,10 +134,10 @@ static int pscsi_pmode_enable_hba(struct se_hba *hba, unsigned long mode_flag) * pSCSI Host ID and enable for phba mode */ sh = scsi_host_lookup(phv->phv_host_id); - if (IS_ERR(sh)) { + if (!sh) { pr_err("pSCSI: Unable to locate SCSI Host for" " phv_host_id: %d\n", phv->phv_host_id); - return PTR_ERR(sh); + return -EINVAL; } phv->phv_lld_host = sh; @@ -515,10 +515,10 @@ static int pscsi_configure_device(struct se_device *dev) sh = phv->phv_lld_host; } else { sh = scsi_host_lookup(pdv->pdv_host_id); - if (IS_ERR(sh)) { + if (!sh) { pr_err("pSCSI: Unable to locate" " pdv_host_id: %d\n", pdv->pdv_host_id); - return PTR_ERR(sh); + return -EINVAL; } } } else { diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c index 4714c6f8da4b..d9b92b2c524d 100644 --- a/drivers/target/target_core_sbc.c +++ b/drivers/target/target_core_sbc.c @@ -263,6 +263,11 @@ sbc_setup_write_same(struct se_cmd *cmd, unsigned char *flags, struct sbc_ops *o sectors, cmd->se_dev->dev_attrib.max_write_same_len); return TCM_INVALID_CDB_FIELD; } + /* We always have ANC_SUP == 0 so setting ANCHOR is always an error */ + if (flags[0] & 0x10) { + pr_warn("WRITE SAME with ANCHOR not supported\n"); + return TCM_INVALID_CDB_FIELD; + } /* * Special case for WRITE_SAME w/ UNMAP=1 that ends up getting * translated into block discard requests within backend code. diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c index 3da4fd10b9f8..474cd44fac14 100644 --- a/drivers/target/target_core_xcopy.c +++ b/drivers/target/target_core_xcopy.c @@ -82,6 +82,9 @@ static int target_xcopy_locate_se_dev_e4(struct se_cmd *se_cmd, struct xcopy_op mutex_lock(&g_device_mutex); list_for_each_entry(se_dev, &g_device_list, g_dev_node) { + if (!se_dev->dev_attrib.emulate_3pc) + continue; + memset(&tmp_dev_wwn[0], 0, XCOPY_NAA_IEEE_REGEX_LEN); target_xcopy_gen_naa_ieee(se_dev, &tmp_dev_wwn[0]); @@ -357,6 +360,7 @@ struct xcopy_pt_cmd { struct se_cmd se_cmd; struct xcopy_op *xcopy_op; struct completion xpt_passthrough_sem; + unsigned char sense_buffer[TRANSPORT_SENSE_BUFFER]; }; static struct se_port xcopy_pt_port; @@ -675,7 +679,8 @@ static int target_xcopy_issue_pt_cmd(struct xcopy_pt_cmd *xpt_cmd) pr_debug("target_xcopy_issue_pt_cmd(): SCSI status: 0x%02x\n", se_cmd->scsi_status); - return 0; + + return (se_cmd->scsi_status) ? -EINVAL : 0; } static int target_xcopy_read_source( @@ -708,7 +713,7 @@ static int target_xcopy_read_source( (unsigned long long)src_lba, src_sectors, length); transport_init_se_cmd(se_cmd, &xcopy_pt_tfo, NULL, length, - DMA_FROM_DEVICE, 0, NULL); + DMA_FROM_DEVICE, 0, &xpt_cmd->sense_buffer[0]); xop->src_pt_cmd = xpt_cmd; rc = target_xcopy_setup_pt_cmd(xpt_cmd, xop, src_dev, &cdb[0], @@ -768,7 +773,7 @@ static int target_xcopy_write_destination( (unsigned long long)dst_lba, dst_sectors, length); transport_init_se_cmd(se_cmd, &xcopy_pt_tfo, NULL, length, - DMA_TO_DEVICE, 0, NULL); + DMA_TO_DEVICE, 0, &xpt_cmd->sense_buffer[0]); xop->dst_pt_cmd = xpt_cmd; rc = target_xcopy_setup_pt_cmd(xpt_cmd, xop, dst_dev, &cdb[0], @@ -884,30 +889,42 @@ out: sense_reason_t target_do_xcopy(struct se_cmd *se_cmd) { + struct se_device *dev = se_cmd->se_dev; struct xcopy_op *xop = NULL; unsigned char *p = NULL, *seg_desc; unsigned int list_id, list_id_usage, sdll, inline_dl, sa; + sense_reason_t ret = TCM_INVALID_PARAMETER_LIST; int rc; unsigned short tdll; + if (!dev->dev_attrib.emulate_3pc) { + pr_err("EXTENDED_COPY operation explicitly disabled\n"); + return TCM_UNSUPPORTED_SCSI_OPCODE; + } + sa = se_cmd->t_task_cdb[1] & 0x1f; if (sa != 0x00) { pr_err("EXTENDED_COPY(LID4) not supported\n"); return TCM_UNSUPPORTED_SCSI_OPCODE; } + xop = kzalloc(sizeof(struct xcopy_op), GFP_KERNEL); + if (!xop) { + pr_err("Unable to allocate xcopy_op\n"); + return TCM_OUT_OF_RESOURCES; + } + xop->xop_se_cmd = se_cmd; + p = transport_kmap_data_sg(se_cmd); if (!p) { pr_err("transport_kmap_data_sg() failed in target_do_xcopy\n"); + kfree(xop); return TCM_OUT_OF_RESOURCES; } list_id = p[0]; - if (list_id != 0x00) { - pr_err("XCOPY with non zero list_id: 0x%02x\n", list_id); - goto out; - } - list_id_usage = (p[1] & 0x18); + list_id_usage = (p[1] & 0x18) >> 3; + /* * Determine TARGET DESCRIPTOR LIST LENGTH + SEGMENT DESCRIPTOR LIST LENGTH */ @@ -920,13 +937,6 @@ sense_reason_t target_do_xcopy(struct se_cmd *se_cmd) goto out; } - xop = kzalloc(sizeof(struct xcopy_op), GFP_KERNEL); - if (!xop) { - pr_err("Unable to allocate xcopy_op\n"); - goto out; - } - xop->xop_se_cmd = se_cmd; - pr_debug("Processing XCOPY with list_id: 0x%02x list_id_usage: 0x%02x" " tdll: %hu sdll: %u inline_dl: %u\n", list_id, list_id_usage, tdll, sdll, inline_dl); @@ -935,6 +945,17 @@ sense_reason_t target_do_xcopy(struct se_cmd *se_cmd) if (rc <= 0) goto out; + if (xop->src_dev->dev_attrib.block_size != + xop->dst_dev->dev_attrib.block_size) { + pr_err("XCOPY: Non matching src_dev block_size: %u + dst_dev" + " block_size: %u currently unsupported\n", + xop->src_dev->dev_attrib.block_size, + xop->dst_dev->dev_attrib.block_size); + xcopy_pt_undepend_remotedev(xop); + ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; + goto out; + } + pr_debug("XCOPY: Processed %d target descriptors, length: %u\n", rc, rc * XCOPY_TARGET_DESC_LEN); seg_desc = &p[16]; @@ -957,7 +978,7 @@ out: if (p) transport_kunmap_data_sg(se_cmd); kfree(xop); - return TCM_INVALID_CDB_FIELD; + return ret; } static sense_reason_t target_rcr_operating_parameters(struct se_cmd *se_cmd) diff --git a/drivers/thermal/samsung/exynos_thermal_common.c b/drivers/thermal/samsung/exynos_thermal_common.c index f10a6ad37c06..c2301da08ac7 100644 --- a/drivers/thermal/samsung/exynos_thermal_common.c +++ b/drivers/thermal/samsung/exynos_thermal_common.c @@ -310,8 +310,6 @@ void exynos_report_trigger(struct thermal_sensor_conf *conf) } th_zone = conf->pzone_data; - if (th_zone->therm_dev) - return; if (th_zone->bind == false) { for (i = 0; i < th_zone->cool_dev_size; i++) { diff --git a/drivers/thermal/samsung/exynos_tmu.c b/drivers/thermal/samsung/exynos_tmu.c index b43afda8acd1..32f38b90c4f6 100644 --- a/drivers/thermal/samsung/exynos_tmu.c +++ b/drivers/thermal/samsung/exynos_tmu.c @@ -317,6 +317,9 @@ static void exynos_tmu_control(struct platform_device *pdev, bool on) con = readl(data->base + reg->tmu_ctrl); + if (pdata->test_mux) + con |= (pdata->test_mux << reg->test_mux_addr_shift); + if (pdata->reference_voltage) { con &= ~(reg->buf_vref_sel_mask << reg->buf_vref_sel_shift); con |= pdata->reference_voltage << reg->buf_vref_sel_shift; @@ -488,7 +491,7 @@ static const struct of_device_id exynos_tmu_match[] = { }, { .compatible = "samsung,exynos4412-tmu", - .data = (void *)EXYNOS5250_TMU_DRV_DATA, + .data = (void *)EXYNOS4412_TMU_DRV_DATA, }, { .compatible = "samsung,exynos5250-tmu", @@ -629,9 +632,10 @@ static int exynos_tmu_probe(struct platform_device *pdev) if (ret) return ret; - if (pdata->type == SOC_ARCH_EXYNOS || - pdata->type == SOC_ARCH_EXYNOS4210 || - pdata->type == SOC_ARCH_EXYNOS5440) + if (pdata->type == SOC_ARCH_EXYNOS4210 || + pdata->type == SOC_ARCH_EXYNOS4412 || + pdata->type == SOC_ARCH_EXYNOS5250 || + pdata->type == SOC_ARCH_EXYNOS5440) data->soc = pdata->type; else { ret = -EINVAL; diff --git a/drivers/thermal/samsung/exynos_tmu.h b/drivers/thermal/samsung/exynos_tmu.h index b364c9eee701..3fb65547e64c 100644 --- a/drivers/thermal/samsung/exynos_tmu.h +++ b/drivers/thermal/samsung/exynos_tmu.h @@ -41,7 +41,8 @@ enum calibration_mode { enum soc_type { SOC_ARCH_EXYNOS4210 = 1, - SOC_ARCH_EXYNOS, + SOC_ARCH_EXYNOS4412, + SOC_ARCH_EXYNOS5250, SOC_ARCH_EXYNOS5440, }; @@ -84,6 +85,7 @@ enum soc_type { * @triminfo_reload_shift: shift of triminfo reload enable bit in triminfo_ctrl reg. * @tmu_ctrl: TMU main controller register. + * @test_mux_addr_shift: shift bits of test mux address. * @buf_vref_sel_shift: shift bits of reference voltage in tmu_ctrl register. * @buf_vref_sel_mask: mask bits of reference voltage in tmu_ctrl register. * @therm_trip_mode_shift: shift bits of tripping mode in tmu_ctrl register. @@ -150,6 +152,7 @@ struct exynos_tmu_registers { u32 triminfo_reload_shift; u32 tmu_ctrl; + u32 test_mux_addr_shift; u32 buf_vref_sel_shift; u32 buf_vref_sel_mask; u32 therm_trip_mode_shift; @@ -257,6 +260,7 @@ struct exynos_tmu_registers { * @first_point_trim: temp value of the first point trimming * @second_point_trim: temp value of the second point trimming * @default_temp_offset: default temperature offset in case of no trimming + * @test_mux; information if SoC supports test MUX * @cal_type: calibration type for temperature * @cal_mode: calibration mode for temperature * @freq_clip_table: Table representing frequency reduction percentage. @@ -286,6 +290,7 @@ struct exynos_tmu_platform_data { u8 first_point_trim; u8 second_point_trim; u8 default_temp_offset; + u8 test_mux; enum calibration_type cal_type; enum calibration_mode cal_mode; diff --git a/drivers/thermal/samsung/exynos_tmu_data.c b/drivers/thermal/samsung/exynos_tmu_data.c index 9002499c1f69..073c292baa53 100644 --- a/drivers/thermal/samsung/exynos_tmu_data.c +++ b/drivers/thermal/samsung/exynos_tmu_data.c @@ -90,14 +90,15 @@ struct exynos_tmu_init_data const exynos4210_default_tmu_data = { }; #endif -#if defined(CONFIG_SOC_EXYNOS5250) || defined(CONFIG_SOC_EXYNOS4412) -static const struct exynos_tmu_registers exynos5250_tmu_registers = { +#if defined(CONFIG_SOC_EXYNOS4412) || defined(CONFIG_SOC_EXYNOS5250) +static const struct exynos_tmu_registers exynos4412_tmu_registers = { .triminfo_data = EXYNOS_TMU_REG_TRIMINFO, .triminfo_25_shift = EXYNOS_TRIMINFO_25_SHIFT, .triminfo_85_shift = EXYNOS_TRIMINFO_85_SHIFT, .triminfo_ctrl = EXYNOS_TMU_TRIMINFO_CON, .triminfo_reload_shift = EXYNOS_TRIMINFO_RELOAD_SHIFT, .tmu_ctrl = EXYNOS_TMU_REG_CONTROL, + .test_mux_addr_shift = EXYNOS4412_MUX_ADDR_SHIFT, .buf_vref_sel_shift = EXYNOS_TMU_REF_VOLTAGE_SHIFT, .buf_vref_sel_mask = EXYNOS_TMU_REF_VOLTAGE_MASK, .therm_trip_mode_shift = EXYNOS_TMU_TRIP_MODE_SHIFT, @@ -128,7 +129,7 @@ static const struct exynos_tmu_registers exynos5250_tmu_registers = { .emul_time_mask = EXYNOS_EMUL_TIME_MASK, }; -#define EXYNOS5250_TMU_DATA \ +#define EXYNOS4412_TMU_DATA \ .threshold_falling = 10, \ .trigger_levels[0] = 85, \ .trigger_levels[1] = 103, \ @@ -162,15 +163,32 @@ static const struct exynos_tmu_registers exynos5250_tmu_registers = { .temp_level = 103, \ }, \ .freq_tab_count = 2, \ - .type = SOC_ARCH_EXYNOS, \ - .registers = &exynos5250_tmu_registers, \ + .registers = &exynos4412_tmu_registers, \ .features = (TMU_SUPPORT_EMULATION | TMU_SUPPORT_TRIM_RELOAD | \ TMU_SUPPORT_FALLING_TRIP | TMU_SUPPORT_READY_STATUS | \ TMU_SUPPORT_EMUL_TIME) +#endif +#if defined(CONFIG_SOC_EXYNOS4412) +struct exynos_tmu_init_data const exynos4412_default_tmu_data = { + .tmu_data = { + { + EXYNOS4412_TMU_DATA, + .type = SOC_ARCH_EXYNOS4412, + .test_mux = EXYNOS4412_MUX_ADDR_VALUE, + }, + }, + .tmu_count = 1, +}; +#endif + +#if defined(CONFIG_SOC_EXYNOS5250) struct exynos_tmu_init_data const exynos5250_default_tmu_data = { .tmu_data = { - { EXYNOS5250_TMU_DATA }, + { + EXYNOS4412_TMU_DATA, + .type = SOC_ARCH_EXYNOS5250, + }, }, .tmu_count = 1, }; diff --git a/drivers/thermal/samsung/exynos_tmu_data.h b/drivers/thermal/samsung/exynos_tmu_data.h index dc7feb51099b..a1ea19d9e0a6 100644 --- a/drivers/thermal/samsung/exynos_tmu_data.h +++ b/drivers/thermal/samsung/exynos_tmu_data.h @@ -95,6 +95,10 @@ #define EXYNOS_MAX_TRIGGER_PER_REG 4 +/* Exynos4412 specific */ +#define EXYNOS4412_MUX_ADDR_VALUE 6 +#define EXYNOS4412_MUX_ADDR_SHIFT 20 + /*exynos5440 specific registers*/ #define EXYNOS5440_TMU_S0_7_TRIM 0x000 #define EXYNOS5440_TMU_S0_7_CTRL 0x020 @@ -138,7 +142,14 @@ extern struct exynos_tmu_init_data const exynos4210_default_tmu_data; #define EXYNOS4210_TMU_DRV_DATA (NULL) #endif -#if (defined(CONFIG_SOC_EXYNOS5250) || defined(CONFIG_SOC_EXYNOS4412)) +#if defined(CONFIG_SOC_EXYNOS4412) +extern struct exynos_tmu_init_data const exynos4412_default_tmu_data; +#define EXYNOS4412_TMU_DRV_DATA (&exynos4412_default_tmu_data) +#else +#define EXYNOS4412_TMU_DRV_DATA (NULL) +#endif + +#if defined(CONFIG_SOC_EXYNOS5250) extern struct exynos_tmu_init_data const exynos5250_default_tmu_data; #define EXYNOS5250_TMU_DRV_DATA (&exynos5250_default_tmu_data) #else diff --git a/drivers/thermal/thermal_hwmon.c b/drivers/thermal/thermal_hwmon.c index eeef0e2498ca..fdb07199d9c2 100644 --- a/drivers/thermal/thermal_hwmon.c +++ b/drivers/thermal/thermal_hwmon.c @@ -159,7 +159,7 @@ int thermal_add_hwmon_sysfs(struct thermal_zone_device *tz) INIT_LIST_HEAD(&hwmon->tz_list); strlcpy(hwmon->type, tz->type, THERMAL_NAME_LENGTH); - hwmon->device = hwmon_device_register(&tz->device); + hwmon->device = hwmon_device_register(NULL); if (IS_ERR(hwmon->device)) { result = PTR_ERR(hwmon->device); goto free_mem; diff --git a/drivers/thermal/ti-soc-thermal/ti-thermal-common.c b/drivers/thermal/ti-soc-thermal/ti-thermal-common.c index 4f8b9af54a5a..5a47cc8c8f85 100644 --- a/drivers/thermal/ti-soc-thermal/ti-thermal-common.c +++ b/drivers/thermal/ti-soc-thermal/ti-thermal-common.c @@ -110,6 +110,7 @@ static inline int ti_thermal_get_temp(struct thermal_zone_device *thermal, } else { dev_err(bgp->dev, "Failed to read PCB state. Using defaults\n"); + ret = 0; } } *temp = ti_thermal_hotspot_temperature(tmp, slope, constant); diff --git a/drivers/thermal/x86_pkg_temp_thermal.c b/drivers/thermal/x86_pkg_temp_thermal.c index f36950e4134f..7722cb9d5a80 100644 --- a/drivers/thermal/x86_pkg_temp_thermal.c +++ b/drivers/thermal/x86_pkg_temp_thermal.c @@ -316,18 +316,19 @@ static void pkg_temp_thermal_threshold_work_fn(struct work_struct *work) int phy_id = topology_physical_package_id(cpu); struct phy_dev_entry *phdev = pkg_temp_thermal_get_phy_entry(cpu); bool notify = false; + unsigned long flags; if (!phdev) return; - spin_lock(&pkg_work_lock); + spin_lock_irqsave(&pkg_work_lock, flags); ++pkg_work_cnt; if (unlikely(phy_id > max_phy_id)) { - spin_unlock(&pkg_work_lock); + spin_unlock_irqrestore(&pkg_work_lock, flags); return; } pkg_work_scheduled[phy_id] = 0; - spin_unlock(&pkg_work_lock); + spin_unlock_irqrestore(&pkg_work_lock, flags); enable_pkg_thres_interrupt(); rdmsrl(MSR_IA32_PACKAGE_THERM_STATUS, msr_val); @@ -397,6 +398,7 @@ static int pkg_temp_thermal_device_add(unsigned int cpu) int thres_count; u32 eax, ebx, ecx, edx; u8 *temp; + unsigned long flags; cpuid(6, &eax, &ebx, &ecx, &edx); thres_count = ebx & 0x07; @@ -420,19 +422,19 @@ static int pkg_temp_thermal_device_add(unsigned int cpu) goto err_ret_unlock; } - spin_lock(&pkg_work_lock); + spin_lock_irqsave(&pkg_work_lock, flags); if (topology_physical_package_id(cpu) > max_phy_id) max_phy_id = topology_physical_package_id(cpu); temp = krealloc(pkg_work_scheduled, (max_phy_id+1) * sizeof(u8), GFP_ATOMIC); if (!temp) { - spin_unlock(&pkg_work_lock); + spin_unlock_irqrestore(&pkg_work_lock, flags); err = -ENOMEM; goto err_ret_free; } pkg_work_scheduled = temp; pkg_work_scheduled[topology_physical_package_id(cpu)] = 0; - spin_unlock(&pkg_work_lock); + spin_unlock_irqrestore(&pkg_work_lock, flags); phy_dev_entry->phys_proc_id = topology_physical_package_id(cpu); phy_dev_entry->first_cpu = cpu; diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c index d067285a2d20..6b0f75eac8a2 100644 --- a/drivers/tty/serial/atmel_serial.c +++ b/drivers/tty/serial/atmel_serial.c @@ -1499,7 +1499,7 @@ static void atmel_set_ops(struct uart_port *port) /* * Get ip name usart or uart */ -static int atmel_get_ip_name(struct uart_port *port) +static void atmel_get_ip_name(struct uart_port *port) { struct atmel_uart_port *atmel_port = to_atmel_uart_port(port); int name = UART_GET_IP_NAME(port); @@ -1518,10 +1518,7 @@ static int atmel_get_ip_name(struct uart_port *port) atmel_port->is_usart = false; } else { dev_err(port->dev, "Not supported ip name, set to uart\n"); - return -EINVAL; } - - return 0; } /* @@ -2405,9 +2402,7 @@ static int atmel_serial_probe(struct platform_device *pdev) /* * Get port name of usart or uart */ - ret = atmel_get_ip_name(&port->uart); - if (ret < 0) - goto err_add_port; + atmel_get_ip_name(&port->uart); return 0; diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index a0ebbc9ce5cd..042aa077b5b3 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -1912,9 +1912,6 @@ static int serial_imx_probe_dt(struct imx_port *sport, sport->devdata = of_id->data; - if (of_device_is_stdout_path(np)) - add_preferred_console(imx_reg.cons->name, sport->port.line, 0); - return 0; } #else diff --git a/drivers/tty/serial/vt8500_serial.c b/drivers/tty/serial/vt8500_serial.c index 93b697a0de65..15ad6fcda88b 100644 --- a/drivers/tty/serial/vt8500_serial.c +++ b/drivers/tty/serial/vt8500_serial.c @@ -561,12 +561,13 @@ static int vt8500_serial_probe(struct platform_device *pdev) if (!mmres || !irqres) return -ENODEV; - if (np) + if (np) { port = of_alias_get_id(np, "serial"); if (port >= VT8500_MAX_PORTS) port = -1; - else + } else { port = -1; + } if (port < 0) { /* calculate the port id */ diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c index ba475632c5fa..0e808cf91d97 100644 --- a/drivers/uio/uio.c +++ b/drivers/uio/uio.c @@ -642,16 +642,29 @@ static int uio_mmap_physical(struct vm_area_struct *vma) { struct uio_device *idev = vma->vm_private_data; int mi = uio_find_mem_index(vma); + struct uio_mem *mem; if (mi < 0) return -EINVAL; + mem = idev->info->mem + mi; - vma->vm_ops = &uio_physical_vm_ops; + if (vma->vm_end - vma->vm_start > mem->size) + return -EINVAL; + vma->vm_ops = &uio_physical_vm_ops; vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); + /* + * We cannot use the vm_iomap_memory() helper here, + * because vma->vm_pgoff is the map index we looked + * up above in uio_find_mem_index(), rather than an + * actual page offset into the mmap. + * + * So we just do the physical mmap without a page + * offset. + */ return remap_pfn_range(vma, vma->vm_start, - idev->info->mem[mi].addr >> PAGE_SHIFT, + mem->addr >> PAGE_SHIFT, vma->vm_end - vma->vm_start, vma->vm_page_prot); } diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c index be822a2c1776..7ad541591c81 100644 --- a/drivers/usb/chipidea/ci_hdrc_imx.c +++ b/drivers/usb/chipidea/ci_hdrc_imx.c @@ -121,10 +121,9 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev) pdata.phy = data->phy; - if (!pdev->dev.dma_mask) - pdev->dev.dma_mask = &pdev->dev.coherent_dma_mask; - if (!pdev->dev.coherent_dma_mask) - pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32); + ret = dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (ret) + goto err_clk; if (data->usbmisc_data) { ret = imx_usbmisc_init(data->usbmisc_data); diff --git a/drivers/usb/chipidea/host.c b/drivers/usb/chipidea/host.c index 6f96795dd20c..64d7a6d9a1ad 100644 --- a/drivers/usb/chipidea/host.c +++ b/drivers/usb/chipidea/host.c @@ -100,8 +100,10 @@ static void host_stop(struct ci_hdrc *ci) { struct usb_hcd *hcd = ci->hcd; - usb_remove_hcd(hcd); - usb_put_hcd(hcd); + if (hcd) { + usb_remove_hcd(hcd); + usb_put_hcd(hcd); + } if (ci->platdata->reg_vbus) regulator_disable(ci->platdata->reg_vbus); } diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 5b44cd47da5b..01fe36273f3b 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -97,6 +97,9 @@ static const struct usb_device_id usb_quirk_list[] = { /* Alcor Micro Corp. Hub */ { USB_DEVICE(0x058f, 0x9254), .driver_info = USB_QUIRK_RESET_RESUME }, + /* MicroTouch Systems touchscreen */ + { USB_DEVICE(0x0596, 0x051e), .driver_info = USB_QUIRK_RESET_RESUME }, + /* appletouch */ { USB_DEVICE(0x05ac, 0x021a), .driver_info = USB_QUIRK_RESET_RESUME }, @@ -130,6 +133,9 @@ static const struct usb_device_id usb_quirk_list[] = { /* Broadcom BCM92035DGROM BT dongle */ { USB_DEVICE(0x0a5c, 0x2021), .driver_info = USB_QUIRK_RESET_RESUME }, + /* MAYA44USB sound device */ + { USB_DEVICE(0x0a92, 0x0091), .driver_info = USB_QUIRK_RESET_RESUME }, + /* Action Semiconductor flash disk */ { USB_DEVICE(0x10d6, 0x2200), .driver_info = USB_QUIRK_STRING_FETCH_255 }, diff --git a/drivers/usb/dwc3/dwc3-exynos.c b/drivers/usb/dwc3/dwc3-exynos.c index 2f2e88a3a11a..8b20c70d91e7 100644 --- a/drivers/usb/dwc3/dwc3-exynos.c +++ b/drivers/usb/dwc3/dwc3-exynos.c @@ -119,10 +119,9 @@ static int dwc3_exynos_probe(struct platform_device *pdev) * Since shared usb code relies on it, set it here for now. * Once we move to full device tree support this will vanish off. */ - if (!dev->dma_mask) - dev->dma_mask = &dev->coherent_dma_mask; - if (!dev->coherent_dma_mask) - dev->coherent_dma_mask = DMA_BIT_MASK(32); + ret = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(32)); + if (ret) + goto err1; platform_set_drvdata(pdev, exynos); diff --git a/drivers/usb/gadget/lpc32xx_udc.c b/drivers/usb/gadget/lpc32xx_udc.c index 67128be1e1b7..6a2a65aa0057 100644 --- a/drivers/usb/gadget/lpc32xx_udc.c +++ b/drivers/usb/gadget/lpc32xx_udc.c @@ -3078,7 +3078,9 @@ static int __init lpc32xx_udc_probe(struct platform_device *pdev) udc->isp1301_i2c_client->addr); pdev->dev.dma_mask = &lpc32xx_usbd_dmamask; - pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32); + retval = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)); + if (retval) + goto resource_fail; udc->board = &lpc32xx_usbddata; diff --git a/drivers/usb/host/bcma-hcd.c b/drivers/usb/host/bcma-hcd.c index df13d425e9c5..205f4a336583 100644 --- a/drivers/usb/host/bcma-hcd.c +++ b/drivers/usb/host/bcma-hcd.c @@ -227,8 +227,7 @@ static int bcma_hcd_probe(struct bcma_device *dev) /* TODO: Probably need checks here; is the core connected? */ - if (dma_set_mask(dev->dma_dev, DMA_BIT_MASK(32)) || - dma_set_coherent_mask(dev->dma_dev, DMA_BIT_MASK(32))) + if (dma_set_mask_and_coherent(dev->dma_dev, DMA_BIT_MASK(32))) return -EOPNOTSUPP; usb_dev = kzalloc(sizeof(struct bcma_hcd_device), GFP_KERNEL); diff --git a/drivers/usb/host/ehci-atmel.c b/drivers/usb/host/ehci-atmel.c index 3b645ff46f7b..8e7323e07f79 100644 --- a/drivers/usb/host/ehci-atmel.c +++ b/drivers/usb/host/ehci-atmel.c @@ -90,10 +90,9 @@ static int ehci_atmel_drv_probe(struct platform_device *pdev) * Since shared usb code relies on it, set it here for now. * Once we have dma capability bindings this can go away. */ - if (!pdev->dev.dma_mask) - pdev->dev.dma_mask = &pdev->dev.coherent_dma_mask; - if (!pdev->dev.coherent_dma_mask) - pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32); + retval = dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (retval) + goto fail_create_hcd; hcd = usb_create_hcd(driver, &pdev->dev, dev_name(&pdev->dev)); if (!hcd) { diff --git a/drivers/usb/host/ehci-octeon.c b/drivers/usb/host/ehci-octeon.c index 45cc00158412..323a02b1a0a6 100644 --- a/drivers/usb/host/ehci-octeon.c +++ b/drivers/usb/host/ehci-octeon.c @@ -116,8 +116,10 @@ static int ehci_octeon_drv_probe(struct platform_device *pdev) * We can DMA from anywhere. But the descriptors must be in * the lower 4GB. */ - pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32); pdev->dev.dma_mask = &ehci_octeon_dma_mask; + ret = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)); + if (ret) + return ret; hcd = usb_create_hcd(&ehci_octeon_hc_driver, &pdev->dev, "octeon"); if (!hcd) diff --git a/drivers/usb/host/ehci-omap.c b/drivers/usb/host/ehci-omap.c index 78b01fa475bb..6fa82d6b7661 100644 --- a/drivers/usb/host/ehci-omap.c +++ b/drivers/usb/host/ehci-omap.c @@ -104,7 +104,7 @@ static int ehci_hcd_omap_probe(struct platform_device *pdev) struct resource *res; struct usb_hcd *hcd; void __iomem *regs; - int ret = -ENODEV; + int ret; int irq; int i; struct omap_hcd *omap; @@ -144,11 +144,11 @@ static int ehci_hcd_omap_probe(struct platform_device *pdev) * Since shared usb code relies on it, set it here for now. * Once we have dma capability bindings this can go away. */ - if (!dev->dma_mask) - dev->dma_mask = &dev->coherent_dma_mask; - if (!dev->coherent_dma_mask) - dev->coherent_dma_mask = DMA_BIT_MASK(32); + ret = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(32)); + if (ret) + return ret; + ret = -ENODEV; hcd = usb_create_hcd(&ehci_omap_hc_driver, dev, dev_name(dev)); if (!hcd) { diff --git a/drivers/usb/host/ehci-orion.c b/drivers/usb/host/ehci-orion.c index d1dfb9db5b42..2ba76730e650 100644 --- a/drivers/usb/host/ehci-orion.c +++ b/drivers/usb/host/ehci-orion.c @@ -180,10 +180,9 @@ static int ehci_orion_drv_probe(struct platform_device *pdev) * set. Since shared usb code relies on it, set it here for * now. Once we have dma capability bindings this can go away. */ - if (!pdev->dev.dma_mask) - pdev->dev.dma_mask = &pdev->dev.coherent_dma_mask; - if (!pdev->dev.coherent_dma_mask) - pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32); + err = dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (err) + goto err1; if (!request_mem_region(res->start, resource_size(res), ehci_orion_hc_driver.description)) { diff --git a/drivers/usb/host/ehci-platform.c b/drivers/usb/host/ehci-platform.c index f6b790ca8cf2..7f30b7168d5a 100644 --- a/drivers/usb/host/ehci-platform.c +++ b/drivers/usb/host/ehci-platform.c @@ -78,7 +78,7 @@ static int ehci_platform_probe(struct platform_device *dev) struct resource *res_mem; struct usb_ehci_pdata *pdata; int irq; - int err = -ENOMEM; + int err; if (usb_disabled()) return -ENODEV; @@ -89,10 +89,10 @@ static int ehci_platform_probe(struct platform_device *dev) */ if (!dev_get_platdata(&dev->dev)) dev->dev.platform_data = &ehci_platform_defaults; - if (!dev->dev.dma_mask) - dev->dev.dma_mask = &dev->dev.coherent_dma_mask; - if (!dev->dev.coherent_dma_mask) - dev->dev.coherent_dma_mask = DMA_BIT_MASK(32); + + err = dma_coerce_mask_and_coherent(&dev->dev, DMA_BIT_MASK(32)); + if (err) + return err; pdata = dev_get_platdata(&dev->dev); diff --git a/drivers/usb/host/ehci-s5p.c b/drivers/usb/host/ehci-s5p.c index 7c3de95c7054..d919ed47bd47 100644 --- a/drivers/usb/host/ehci-s5p.c +++ b/drivers/usb/host/ehci-s5p.c @@ -89,10 +89,9 @@ static int s5p_ehci_probe(struct platform_device *pdev) * Since shared usb code relies on it, set it here for now. * Once we move to full device tree support this will vanish off. */ - if (!pdev->dev.dma_mask) - pdev->dev.dma_mask = &pdev->dev.coherent_dma_mask; - if (!pdev->dev.coherent_dma_mask) - pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32); + err = dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (err) + return err; s5p_setup_vbus_gpio(pdev); diff --git a/drivers/usb/host/ehci-spear.c b/drivers/usb/host/ehci-spear.c index 1cf0adba3fc8..ee6f9ffaa0e7 100644 --- a/drivers/usb/host/ehci-spear.c +++ b/drivers/usb/host/ehci-spear.c @@ -81,10 +81,9 @@ static int spear_ehci_hcd_drv_probe(struct platform_device *pdev) * Since shared usb code relies on it, set it here for now. * Once we have dma capability bindings this can go away. */ - if (!pdev->dev.dma_mask) - pdev->dev.dma_mask = &pdev->dev.coherent_dma_mask; - if (!pdev->dev.coherent_dma_mask) - pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32); + retval = dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (retval) + goto fail; usbh_clk = devm_clk_get(&pdev->dev, NULL); if (IS_ERR(usbh_clk)) { diff --git a/drivers/usb/host/ehci-tegra.c b/drivers/usb/host/ehci-tegra.c index 78fa76da3324..e74aaf3f0164 100644 --- a/drivers/usb/host/ehci-tegra.c +++ b/drivers/usb/host/ehci-tegra.c @@ -362,10 +362,9 @@ static int tegra_ehci_probe(struct platform_device *pdev) * Since shared usb code relies on it, set it here for now. * Once we have dma capability bindings this can go away. */ - if (!pdev->dev.dma_mask) - pdev->dev.dma_mask = &pdev->dev.coherent_dma_mask; - if (!pdev->dev.coherent_dma_mask) - pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32); + err = dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (err) + return err; hcd = usb_create_hcd(&tegra_ehci_hc_driver, &pdev->dev, dev_name(&pdev->dev)); diff --git a/drivers/usb/host/ohci-at91.c b/drivers/usb/host/ohci-at91.c index caa3764a3407..36423db63073 100644 --- a/drivers/usb/host/ohci-at91.c +++ b/drivers/usb/host/ohci-at91.c @@ -524,7 +524,7 @@ MODULE_DEVICE_TABLE(of, at91_ohci_dt_ids); static int ohci_at91_of_init(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; - int i, gpio; + int i, gpio, ret; enum of_gpio_flags flags; struct at91_usbh_data *pdata; u32 ports; @@ -536,10 +536,9 @@ static int ohci_at91_of_init(struct platform_device *pdev) * Since shared usb code relies on it, set it here for now. * Once we have dma capability bindings this can go away. */ - if (!pdev->dev.dma_mask) - pdev->dev.dma_mask = &pdev->dev.coherent_dma_mask; - if (!pdev->dev.coherent_dma_mask) - pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32); + ret = dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (ret) + return ret; pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL); if (!pdata) diff --git a/drivers/usb/host/ohci-exynos.c b/drivers/usb/host/ohci-exynos.c index dc6ee9adacf5..866f2464f9de 100644 --- a/drivers/usb/host/ohci-exynos.c +++ b/drivers/usb/host/ohci-exynos.c @@ -114,10 +114,9 @@ static int exynos_ohci_probe(struct platform_device *pdev) * Since shared usb code relies on it, set it here for now. * Once we move to full device tree support this will vanish off. */ - if (!pdev->dev.dma_mask) - pdev->dev.dma_mask = &pdev->dev.coherent_dma_mask; - if (!pdev->dev.coherent_dma_mask) - pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32); + err = dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (err) + return err; exynos_ohci = devm_kzalloc(&pdev->dev, sizeof(struct exynos_ohci_hcd), GFP_KERNEL); diff --git a/drivers/usb/host/ohci-nxp.c b/drivers/usb/host/ohci-nxp.c index 7d7d507d54e8..df3eb3e0324e 100644 --- a/drivers/usb/host/ohci-nxp.c +++ b/drivers/usb/host/ohci-nxp.c @@ -226,8 +226,9 @@ static int usb_hcd_nxp_probe(struct platform_device *pdev) return -EPROBE_DEFER; } - pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32); - pdev->dev.dma_mask = &pdev->dev.coherent_dma_mask; + ret = dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (ret) + goto fail_disable; dev_dbg(&pdev->dev, "%s: " DRIVER_DESC " (nxp)\n", hcd_name); if (usb_disabled()) { diff --git a/drivers/usb/host/ohci-octeon.c b/drivers/usb/host/ohci-octeon.c index 342dc7e543b8..6c16dcef15c6 100644 --- a/drivers/usb/host/ohci-octeon.c +++ b/drivers/usb/host/ohci-octeon.c @@ -127,8 +127,9 @@ static int ohci_octeon_drv_probe(struct platform_device *pdev) } /* Ohci is a 32-bit device. */ - pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32); - pdev->dev.dma_mask = &pdev->dev.coherent_dma_mask; + ret = dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (ret) + return ret; hcd = usb_create_hcd(&ohci_octeon_hc_driver, &pdev->dev, "octeon"); if (!hcd) diff --git a/drivers/usb/host/ohci-omap3.c b/drivers/usb/host/ohci-omap3.c index a09af26f69ed..db9bd6bc97b9 100644 --- a/drivers/usb/host/ohci-omap3.c +++ b/drivers/usb/host/ohci-omap3.c @@ -132,7 +132,7 @@ static int ohci_hcd_omap3_probe(struct platform_device *pdev) struct usb_hcd *hcd = NULL; void __iomem *regs = NULL; struct resource *res; - int ret = -ENODEV; + int ret; int irq; if (usb_disabled()) @@ -166,11 +166,11 @@ static int ohci_hcd_omap3_probe(struct platform_device *pdev) * Since shared usb code relies on it, set it here for now. * Once we have dma capability bindings this can go away. */ - if (!dev->dma_mask) - dev->dma_mask = &dev->coherent_dma_mask; - if (!dev->coherent_dma_mask) - dev->coherent_dma_mask = DMA_BIT_MASK(32); + ret = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(32)); + if (ret) + goto err_io; + ret = -ENODEV; hcd = usb_create_hcd(&ohci_omap3_hc_driver, dev, dev_name(dev)); if (!hcd) { diff --git a/drivers/usb/host/ohci-pxa27x.c b/drivers/usb/host/ohci-pxa27x.c index 93371a235e82..b64949bc43e2 100644 --- a/drivers/usb/host/ohci-pxa27x.c +++ b/drivers/usb/host/ohci-pxa27x.c @@ -287,6 +287,7 @@ static int ohci_pxa_of_init(struct platform_device *pdev) struct device_node *np = pdev->dev.of_node; struct pxaohci_platform_data *pdata; u32 tmp; + int ret; if (!np) return 0; @@ -295,10 +296,9 @@ static int ohci_pxa_of_init(struct platform_device *pdev) * Since shared usb code relies on it, set it here for now. * Once we have dma capability bindings this can go away. */ - if (!pdev->dev.dma_mask) - pdev->dev.dma_mask = &pdev->dev.coherent_dma_mask; - if (!pdev->dev.coherent_dma_mask) - pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32); + ret = dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (ret) + return ret; pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL); if (!pdata) diff --git a/drivers/usb/host/ohci-sa1111.c b/drivers/usb/host/ohci-sa1111.c index 17b2a7dad77b..aa9e127bbe71 100644 --- a/drivers/usb/host/ohci-sa1111.c +++ b/drivers/usb/host/ohci-sa1111.c @@ -185,6 +185,12 @@ static int ohci_hcd_sa1111_probe(struct sa1111_dev *dev) if (usb_disabled()) return -ENODEV; + /* + * We don't call dma_set_mask_and_coherent() here because the + * DMA mask has already been appropraitely setup by the core + * SA-1111 bus code (which includes bug workarounds.) + */ + hcd = usb_create_hcd(&ohci_sa1111_hc_driver, &dev->dev, "sa1111"); if (!hcd) return -ENOMEM; diff --git a/drivers/usb/host/ohci-spear.c b/drivers/usb/host/ohci-spear.c index cc9dd9e4f05e..075bb5e9b43f 100644 --- a/drivers/usb/host/ohci-spear.c +++ b/drivers/usb/host/ohci-spear.c @@ -111,10 +111,9 @@ static int spear_ohci_hcd_drv_probe(struct platform_device *pdev) * Since shared usb code relies on it, set it here for now. * Once we have dma capability bindings this can go away. */ - if (!pdev->dev.dma_mask) - pdev->dev.dma_mask = &pdev->dev.coherent_dma_mask; - if (!pdev->dev.coherent_dma_mask) - pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32); + retval = dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (retval) + goto fail; usbh_clk = devm_clk_get(&pdev->dev, NULL); if (IS_ERR(usbh_clk)) { diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c index 2c76ef1320ea..08ef2829a7e2 100644 --- a/drivers/usb/host/pci-quirks.c +++ b/drivers/usb/host/pci-quirks.c @@ -799,7 +799,7 @@ void usb_enable_intel_xhci_ports(struct pci_dev *xhci_pdev) * switchable ports. */ pci_write_config_dword(xhci_pdev, USB_INTEL_USB3_PSSEN, - cpu_to_le32(ports_available)); + ports_available); pci_read_config_dword(xhci_pdev, USB_INTEL_USB3_PSSEN, &ports_available); @@ -821,7 +821,7 @@ void usb_enable_intel_xhci_ports(struct pci_dev *xhci_pdev) * host. */ pci_write_config_dword(xhci_pdev, USB_INTEL_XUSB2PR, - cpu_to_le32(ports_available)); + ports_available); pci_read_config_dword(xhci_pdev, USB_INTEL_XUSB2PR, &ports_available); diff --git a/drivers/usb/host/ssb-hcd.c b/drivers/usb/host/ssb-hcd.c index 74af2c6287d2..0196f766df73 100644 --- a/drivers/usb/host/ssb-hcd.c +++ b/drivers/usb/host/ssb-hcd.c @@ -163,8 +163,7 @@ static int ssb_hcd_probe(struct ssb_device *dev, /* TODO: Probably need checks here; is the core connected? */ - if (dma_set_mask(dev->dma_dev, DMA_BIT_MASK(32)) || - dma_set_coherent_mask(dev->dma_dev, DMA_BIT_MASK(32))) + if (dma_set_mask_and_coherent(dev->dma_dev, DMA_BIT_MASK(32))) return -EOPNOTSUPP; usb_dev = kzalloc(sizeof(struct ssb_hcd_device), GFP_KERNEL); diff --git a/drivers/usb/host/uhci-platform.c b/drivers/usb/host/uhci-platform.c index d033a0ec7f0d..f8548b72f708 100644 --- a/drivers/usb/host/uhci-platform.c +++ b/drivers/usb/host/uhci-platform.c @@ -75,10 +75,9 @@ static int uhci_hcd_platform_probe(struct platform_device *pdev) * Since shared usb code relies on it, set it here for now. * Once we have dma capability bindings this can go away. */ - if (!pdev->dev.dma_mask) - pdev->dev.dma_mask = &pdev->dev.coherent_dma_mask; - if (!pdev->dev.coherent_dma_mask) - pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32); + ret = dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (ret) + return ret; hcd = usb_create_hcd(&uhci_platform_hc_driver, &pdev->dev, pdev->name); diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index 773a6b28c4f1..e8b4c56dcf62 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -1157,18 +1157,6 @@ int xhci_bus_suspend(struct usb_hcd *hcd) t1 = xhci_port_state_to_neutral(t1); if (t1 != t2) xhci_writel(xhci, t2, port_array[port_index]); - - if (hcd->speed != HCD_USB3) { - /* enable remote wake up for USB 2.0 */ - __le32 __iomem *addr; - u32 tmp; - - /* Get the port power control register address. */ - addr = port_array[port_index] + PORTPMSC; - tmp = xhci_readl(xhci, addr); - tmp |= PORT_RWE; - xhci_writel(xhci, tmp, addr); - } } hcd->state = HC_STATE_SUSPENDED; bus_state->next_statechange = jiffies + msecs_to_jiffies(10); @@ -1247,20 +1235,6 @@ int xhci_bus_resume(struct usb_hcd *hcd) xhci_ring_device(xhci, slot_id); } else xhci_writel(xhci, temp, port_array[port_index]); - - if (hcd->speed != HCD_USB3) { - /* disable remote wake up for USB 2.0 */ - __le32 __iomem *addr; - u32 tmp; - - /* Add one to the port status register address to get - * the port power control register address. - */ - addr = port_array[port_index] + PORTPMSC; - tmp = xhci_readl(xhci, addr); - tmp &= ~PORT_RWE; - xhci_writel(xhci, tmp, addr); - } } (void) xhci_readl(xhci, &xhci->op_regs->command); diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 236c3aabe940..b8dffd59eb25 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -35,6 +35,9 @@ #define PCI_VENDOR_ID_ETRON 0x1b6f #define PCI_DEVICE_ID_ASROCK_P67 0x7023 +#define PCI_DEVICE_ID_INTEL_LYNXPOINT_XHCI 0x8c31 +#define PCI_DEVICE_ID_INTEL_LYNXPOINT_LP_XHCI 0x9c31 + static const char hcd_name[] = "xhci_hcd"; /* called after powerup, by probe or system-pm "wakeup" */ @@ -69,6 +72,14 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) "QUIRK: Fresco Logic xHC needs configure" " endpoint cmd after reset endpoint"); } + if (pdev->device == PCI_DEVICE_ID_FRESCO_LOGIC_PDK && + pdev->revision == 0x4) { + xhci->quirks |= XHCI_SLOW_SUSPEND; + xhci_dbg_trace(xhci, trace_xhci_dbg_quirks, + "QUIRK: Fresco Logic xHC revision %u" + "must be suspended extra slowly", + pdev->revision); + } /* Fresco Logic confirms: all revisions of this chip do not * support MSI, even though some of them claim to in their PCI * capabilities. @@ -110,6 +121,15 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) xhci->quirks |= XHCI_SPURIOUS_REBOOT; xhci->quirks |= XHCI_AVOID_BEI; } + if (pdev->vendor == PCI_VENDOR_ID_INTEL && + (pdev->device == PCI_DEVICE_ID_INTEL_LYNXPOINT_XHCI || + pdev->device == PCI_DEVICE_ID_INTEL_LYNXPOINT_LP_XHCI)) { + /* Workaround for occasional spurious wakeups from S5 (or + * any other sleep) on Haswell machines with LPT and LPT-LP + * with the new Intel BIOS + */ + xhci->quirks |= XHCI_SPURIOUS_WAKEUP; + } if (pdev->vendor == PCI_VENDOR_ID_ETRON && pdev->device == PCI_DEVICE_ID_ASROCK_P67) { xhci->quirks |= XHCI_RESET_ON_RESUME; @@ -217,6 +237,11 @@ static void xhci_pci_remove(struct pci_dev *dev) usb_put_hcd(xhci->shared_hcd); } usb_hcd_pci_remove(dev); + + /* Workaround for spurious wakeups at shutdown with HSW */ + if (xhci->quirks & XHCI_SPURIOUS_WAKEUP) + pci_set_power_state(dev, PCI_D3hot); + kfree(xhci); } diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 1e36dbb48366..6e0d886bcce5 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -730,6 +730,9 @@ void xhci_shutdown(struct usb_hcd *hcd) spin_lock_irq(&xhci->lock); xhci_halt(xhci); + /* Workaround for spurious wakeups at shutdown with HSW */ + if (xhci->quirks & XHCI_SPURIOUS_WAKEUP) + xhci_reset(xhci); spin_unlock_irq(&xhci->lock); xhci_cleanup_msix(xhci); @@ -737,6 +740,10 @@ void xhci_shutdown(struct usb_hcd *hcd) xhci_dbg_trace(xhci, trace_xhci_dbg_init, "xhci_shutdown completed - status = %x", xhci_readl(xhci, &xhci->op_regs->status)); + + /* Yet another workaround for spurious wakeups at shutdown with HSW */ + if (xhci->quirks & XHCI_SPURIOUS_WAKEUP) + pci_set_power_state(to_pci_dev(hcd->self.controller), PCI_D3hot); } #ifdef CONFIG_PM @@ -839,6 +846,7 @@ static void xhci_clear_command_ring(struct xhci_hcd *xhci) int xhci_suspend(struct xhci_hcd *xhci) { int rc = 0; + unsigned int delay = XHCI_MAX_HALT_USEC; struct usb_hcd *hcd = xhci_to_hcd(xhci); u32 command; @@ -861,8 +869,12 @@ int xhci_suspend(struct xhci_hcd *xhci) command = xhci_readl(xhci, &xhci->op_regs->command); command &= ~CMD_RUN; xhci_writel(xhci, command, &xhci->op_regs->command); + + /* Some chips from Fresco Logic need an extraordinary delay */ + delay *= (xhci->quirks & XHCI_SLOW_SUSPEND) ? 10 : 1; + if (xhci_handshake(xhci, &xhci->op_regs->status, - STS_HALT, STS_HALT, XHCI_MAX_HALT_USEC)) { + STS_HALT, STS_HALT, delay)) { xhci_warn(xhci, "WARN: xHC CMD_RUN timeout\n"); spin_unlock_irq(&xhci->lock); return -ETIMEDOUT; diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 289fbfbae746..941d5f59e4dc 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1548,6 +1548,8 @@ struct xhci_hcd { #define XHCI_COMP_MODE_QUIRK (1 << 14) #define XHCI_AVOID_BEI (1 << 15) #define XHCI_PLAT (1 << 16) +#define XHCI_SLOW_SUSPEND (1 << 17) +#define XHCI_SPURIOUS_WAKEUP (1 << 18) unsigned int num_active_eps; unsigned int limit_active_eps; /* There are two roothubs to keep track of bus suspend info for */ diff --git a/drivers/usb/misc/Kconfig b/drivers/usb/misc/Kconfig index e2b21c1d9c40..ba5f70f92888 100644 --- a/drivers/usb/misc/Kconfig +++ b/drivers/usb/misc/Kconfig @@ -246,6 +246,6 @@ config USB_EZUSB_FX2 config USB_HSIC_USB3503 tristate "USB3503 HSIC to USB20 Driver" depends on I2C - select REGMAP + select REGMAP_I2C help This option enables support for SMSC USB3503 HSIC to USB 2.0 Driver. diff --git a/drivers/usb/musb/am35x.c b/drivers/usb/musb/am35x.c index 5c310c664218..790b22b296b1 100644 --- a/drivers/usb/musb/am35x.c +++ b/drivers/usb/musb/am35x.c @@ -89,7 +89,6 @@ struct am35x_glue { struct clk *phy_clk; struct clk *clk; }; -#define glue_to_musb(g) platform_get_drvdata(g->musb) /* * am35x_musb_enable - enable interrupts @@ -452,14 +451,18 @@ static const struct musb_platform_ops am35x_ops = { .set_vbus = am35x_musb_set_vbus, }; -static u64 am35x_dmamask = DMA_BIT_MASK(32); +static const struct platform_device_info am35x_dev_info = { + .name = "musb-hdrc", + .id = PLATFORM_DEVID_AUTO, + .dma_mask = DMA_BIT_MASK(32), +}; static int am35x_probe(struct platform_device *pdev) { struct musb_hdrc_platform_data *pdata = dev_get_platdata(&pdev->dev); struct platform_device *musb; struct am35x_glue *glue; - + struct platform_device_info pinfo; struct clk *phy_clk; struct clk *clk; @@ -471,12 +474,6 @@ static int am35x_probe(struct platform_device *pdev) goto err0; } - musb = platform_device_alloc("musb-hdrc", PLATFORM_DEVID_AUTO); - if (!musb) { - dev_err(&pdev->dev, "failed to allocate musb device\n"); - goto err1; - } - phy_clk = clk_get(&pdev->dev, "fck"); if (IS_ERR(phy_clk)) { dev_err(&pdev->dev, "failed to get PHY clock\n"); @@ -503,12 +500,7 @@ static int am35x_probe(struct platform_device *pdev) goto err6; } - musb->dev.parent = &pdev->dev; - musb->dev.dma_mask = &am35x_dmamask; - musb->dev.coherent_dma_mask = am35x_dmamask; - glue->dev = &pdev->dev; - glue->musb = musb; glue->phy_clk = phy_clk; glue->clk = clk; @@ -516,22 +508,17 @@ static int am35x_probe(struct platform_device *pdev) platform_set_drvdata(pdev, glue); - ret = platform_device_add_resources(musb, pdev->resource, - pdev->num_resources); - if (ret) { - dev_err(&pdev->dev, "failed to add resources\n"); - goto err7; - } - - ret = platform_device_add_data(musb, pdata, sizeof(*pdata)); - if (ret) { - dev_err(&pdev->dev, "failed to add platform_data\n"); - goto err7; - } - - ret = platform_device_add(musb); - if (ret) { - dev_err(&pdev->dev, "failed to register musb device\n"); + pinfo = am35x_dev_info; + pinfo.parent = &pdev->dev; + pinfo.res = pdev->resource; + pinfo.num_res = pdev->num_resources; + pinfo.data = pdata; + pinfo.size_data = sizeof(*pdata); + + glue->musb = musb = platform_device_register_full(&pinfo); + if (IS_ERR(musb)) { + ret = PTR_ERR(musb); + dev_err(&pdev->dev, "failed to register musb device: %d\n", ret); goto err7; } @@ -550,9 +537,6 @@ err4: clk_put(phy_clk); err3: - platform_device_put(musb); - -err1: kfree(glue); err0: diff --git a/drivers/usb/musb/da8xx.c b/drivers/usb/musb/da8xx.c index d9ddf4122f37..2f2c1cb36421 100644 --- a/drivers/usb/musb/da8xx.c +++ b/drivers/usb/musb/da8xx.c @@ -472,7 +472,11 @@ static const struct musb_platform_ops da8xx_ops = { .set_vbus = da8xx_musb_set_vbus, }; -static u64 da8xx_dmamask = DMA_BIT_MASK(32); +static const struct platform_device_info da8xx_dev_info = { + .name = "musb-hdrc", + .id = PLATFORM_DEVID_AUTO, + .dma_mask = DMA_BIT_MASK(32), +}; static int da8xx_probe(struct platform_device *pdev) { @@ -480,7 +484,7 @@ static int da8xx_probe(struct platform_device *pdev) struct musb_hdrc_platform_data *pdata = dev_get_platdata(&pdev->dev); struct platform_device *musb; struct da8xx_glue *glue; - + struct platform_device_info pinfo; struct clk *clk; int ret = -ENOMEM; @@ -491,12 +495,6 @@ static int da8xx_probe(struct platform_device *pdev) goto err0; } - musb = platform_device_alloc("musb-hdrc", PLATFORM_DEVID_AUTO); - if (!musb) { - dev_err(&pdev->dev, "failed to allocate musb device\n"); - goto err1; - } - clk = clk_get(&pdev->dev, "usb20"); if (IS_ERR(clk)) { dev_err(&pdev->dev, "failed to get clock\n"); @@ -510,12 +508,7 @@ static int da8xx_probe(struct platform_device *pdev) goto err4; } - musb->dev.parent = &pdev->dev; - musb->dev.dma_mask = &da8xx_dmamask; - musb->dev.coherent_dma_mask = da8xx_dmamask; - glue->dev = &pdev->dev; - glue->musb = musb; glue->clk = clk; pdata->platform_ops = &da8xx_ops; @@ -535,22 +528,17 @@ static int da8xx_probe(struct platform_device *pdev) musb_resources[1].end = pdev->resource[1].end; musb_resources[1].flags = pdev->resource[1].flags; - ret = platform_device_add_resources(musb, musb_resources, - ARRAY_SIZE(musb_resources)); - if (ret) { - dev_err(&pdev->dev, "failed to add resources\n"); - goto err5; - } - - ret = platform_device_add_data(musb, pdata, sizeof(*pdata)); - if (ret) { - dev_err(&pdev->dev, "failed to add platform_data\n"); - goto err5; - } - - ret = platform_device_add(musb); - if (ret) { - dev_err(&pdev->dev, "failed to register musb device\n"); + pinfo = da8xx_dev_info; + pinfo.parent = &pdev->dev; + pinfo.res = musb_resources; + pinfo.num_res = ARRAY_SIZE(musb_resources); + pinfo.data = pdata; + pinfo.size_data = sizeof(*pdata); + + glue->musb = musb = platform_device_register_full(&pinfo); + if (IS_ERR(musb)) { + ret = PTR_ERR(musb); + dev_err(&pdev->dev, "failed to register musb device: %d\n", ret); goto err5; } @@ -563,9 +551,6 @@ err4: clk_put(clk); err3: - platform_device_put(musb); - -err1: kfree(glue); err0: diff --git a/drivers/usb/musb/davinci.c b/drivers/usb/musb/davinci.c index ed0834e2b72e..45aae0bbb8df 100644 --- a/drivers/usb/musb/davinci.c +++ b/drivers/usb/musb/davinci.c @@ -505,7 +505,11 @@ static const struct musb_platform_ops davinci_ops = { .set_vbus = davinci_musb_set_vbus, }; -static u64 davinci_dmamask = DMA_BIT_MASK(32); +static const struct platform_device_info davinci_dev_info = { + .name = "musb-hdrc", + .id = PLATFORM_DEVID_AUTO, + .dma_mask = DMA_BIT_MASK(32), +}; static int davinci_probe(struct platform_device *pdev) { @@ -513,6 +517,7 @@ static int davinci_probe(struct platform_device *pdev) struct musb_hdrc_platform_data *pdata = dev_get_platdata(&pdev->dev); struct platform_device *musb; struct davinci_glue *glue; + struct platform_device_info pinfo; struct clk *clk; int ret = -ENOMEM; @@ -523,12 +528,6 @@ static int davinci_probe(struct platform_device *pdev) goto err0; } - musb = platform_device_alloc("musb-hdrc", PLATFORM_DEVID_AUTO); - if (!musb) { - dev_err(&pdev->dev, "failed to allocate musb device\n"); - goto err1; - } - clk = clk_get(&pdev->dev, "usb"); if (IS_ERR(clk)) { dev_err(&pdev->dev, "failed to get clock\n"); @@ -542,12 +541,7 @@ static int davinci_probe(struct platform_device *pdev) goto err4; } - musb->dev.parent = &pdev->dev; - musb->dev.dma_mask = &davinci_dmamask; - musb->dev.coherent_dma_mask = davinci_dmamask; - glue->dev = &pdev->dev; - glue->musb = musb; glue->clk = clk; pdata->platform_ops = &davinci_ops; @@ -567,22 +561,17 @@ static int davinci_probe(struct platform_device *pdev) musb_resources[1].end = pdev->resource[1].end; musb_resources[1].flags = pdev->resource[1].flags; - ret = platform_device_add_resources(musb, musb_resources, - ARRAY_SIZE(musb_resources)); - if (ret) { - dev_err(&pdev->dev, "failed to add resources\n"); - goto err5; - } - - ret = platform_device_add_data(musb, pdata, sizeof(*pdata)); - if (ret) { - dev_err(&pdev->dev, "failed to add platform_data\n"); - goto err5; - } - - ret = platform_device_add(musb); - if (ret) { - dev_err(&pdev->dev, "failed to register musb device\n"); + pinfo = davinci_dev_info; + pinfo.parent = &pdev->dev; + pinfo.res = musb_resources; + pinfo.num_res = ARRAY_SIZE(musb_resources); + pinfo.data = pdata; + pinfo.size_data = sizeof(*pdata); + + glue->musb = musb = platform_device_register_full(&pinfo); + if (IS_ERR(musb)) { + ret = PTR_ERR(musb); + dev_err(&pdev->dev, "failed to register musb device: %d\n", ret); goto err5; } @@ -595,9 +584,6 @@ err4: clk_put(clk); err3: - platform_device_put(musb); - -err1: kfree(glue); err0: diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c index 18e877ffe7b7..cd70cc886171 100644 --- a/drivers/usb/musb/musb_core.c +++ b/drivers/usb/musb/musb_core.c @@ -922,6 +922,52 @@ static void musb_generic_disable(struct musb *musb) } /* + * Program the HDRC to start (enable interrupts, dma, etc.). + */ +void musb_start(struct musb *musb) +{ + void __iomem *regs = musb->mregs; + u8 devctl = musb_readb(regs, MUSB_DEVCTL); + + dev_dbg(musb->controller, "<== devctl %02x\n", devctl); + + /* Set INT enable registers, enable interrupts */ + musb->intrtxe = musb->epmask; + musb_writew(regs, MUSB_INTRTXE, musb->intrtxe); + musb->intrrxe = musb->epmask & 0xfffe; + musb_writew(regs, MUSB_INTRRXE, musb->intrrxe); + musb_writeb(regs, MUSB_INTRUSBE, 0xf7); + + musb_writeb(regs, MUSB_TESTMODE, 0); + + /* put into basic highspeed mode and start session */ + musb_writeb(regs, MUSB_POWER, MUSB_POWER_ISOUPDATE + | MUSB_POWER_HSENAB + /* ENSUSPEND wedges tusb */ + /* | MUSB_POWER_ENSUSPEND */ + ); + + musb->is_active = 0; + devctl = musb_readb(regs, MUSB_DEVCTL); + devctl &= ~MUSB_DEVCTL_SESSION; + + /* session started after: + * (a) ID-grounded irq, host mode; + * (b) vbus present/connect IRQ, peripheral mode; + * (c) peripheral initiates, using SRP + */ + if (musb->port_mode != MUSB_PORT_MODE_HOST && + (devctl & MUSB_DEVCTL_VBUS) == MUSB_DEVCTL_VBUS) { + musb->is_active = 1; + } else { + devctl |= MUSB_DEVCTL_SESSION; + } + + musb_platform_enable(musb); + musb_writeb(regs, MUSB_DEVCTL, devctl); +} + +/* * Make the HDRC stop (disable interrupts, etc.); * reversible by musb_start * called on gadget driver unregister diff --git a/drivers/usb/musb/musb_core.h b/drivers/usb/musb/musb_core.h index 65f3917b4fc5..1c5bf75ee8ff 100644 --- a/drivers/usb/musb/musb_core.h +++ b/drivers/usb/musb/musb_core.h @@ -503,6 +503,7 @@ static inline void musb_configure_ep0(struct musb *musb) extern const char musb_driver_name[]; extern void musb_stop(struct musb *musb); +extern void musb_start(struct musb *musb); extern void musb_write_fifo(struct musb_hw_ep *ep, u16 len, const u8 *src); extern void musb_read_fifo(struct musb_hw_ep *ep, u16 len, u8 *dst); diff --git a/drivers/usb/musb/musb_gadget.c b/drivers/usb/musb/musb_gadget.c index b19ed213ab85..3671898a4535 100644 --- a/drivers/usb/musb/musb_gadget.c +++ b/drivers/usb/musb/musb_gadget.c @@ -1853,11 +1853,14 @@ static int musb_gadget_start(struct usb_gadget *g, musb->gadget_driver = driver; spin_lock_irqsave(&musb->lock, flags); + musb->is_active = 1; otg_set_peripheral(otg, &musb->g); musb->xceiv->state = OTG_STATE_B_IDLE; spin_unlock_irqrestore(&musb->lock, flags); + musb_start(musb); + /* REVISIT: funcall to other code, which also * handles power budgeting ... this way also * ensures HdrcStart is indirectly called. diff --git a/drivers/usb/musb/musb_virthub.c b/drivers/usb/musb/musb_virthub.c index a523950c2b32..d1d6b83aabca 100644 --- a/drivers/usb/musb/musb_virthub.c +++ b/drivers/usb/musb/musb_virthub.c @@ -44,52 +44,6 @@ #include "musb_core.h" -/* -* Program the HDRC to start (enable interrupts, dma, etc.). -*/ -static void musb_start(struct musb *musb) -{ - void __iomem *regs = musb->mregs; - u8 devctl = musb_readb(regs, MUSB_DEVCTL); - - dev_dbg(musb->controller, "<== devctl %02x\n", devctl); - - /* Set INT enable registers, enable interrupts */ - musb->intrtxe = musb->epmask; - musb_writew(regs, MUSB_INTRTXE, musb->intrtxe); - musb->intrrxe = musb->epmask & 0xfffe; - musb_writew(regs, MUSB_INTRRXE, musb->intrrxe); - musb_writeb(regs, MUSB_INTRUSBE, 0xf7); - - musb_writeb(regs, MUSB_TESTMODE, 0); - - /* put into basic highspeed mode and start session */ - musb_writeb(regs, MUSB_POWER, MUSB_POWER_ISOUPDATE - | MUSB_POWER_HSENAB - /* ENSUSPEND wedges tusb */ - /* | MUSB_POWER_ENSUSPEND */ - ); - - musb->is_active = 0; - devctl = musb_readb(regs, MUSB_DEVCTL); - devctl &= ~MUSB_DEVCTL_SESSION; - - /* session started after: - * (a) ID-grounded irq, host mode; - * (b) vbus present/connect IRQ, peripheral mode; - * (c) peripheral initiates, using SRP - */ - if (musb->port_mode != MUSB_PORT_MODE_HOST && - (devctl & MUSB_DEVCTL_VBUS) == MUSB_DEVCTL_VBUS) { - musb->is_active = 1; - } else { - devctl |= MUSB_DEVCTL_SESSION; - } - - musb_platform_enable(musb); - musb_writeb(regs, MUSB_DEVCTL, devctl); -} - static void musb_port_suspend(struct musb *musb, bool do_suspend) { struct usb_otg *otg = musb->xceiv->otg; diff --git a/drivers/usb/musb/tusb6010.c b/drivers/usb/musb/tusb6010.c index b3b3ed723882..4432314d70ee 100644 --- a/drivers/usb/musb/tusb6010.c +++ b/drivers/usb/musb/tusb6010.c @@ -1152,7 +1152,11 @@ static const struct musb_platform_ops tusb_ops = { .set_vbus = tusb_musb_set_vbus, }; -static u64 tusb_dmamask = DMA_BIT_MASK(32); +static const struct platform_device_info tusb_dev_info = { + .name = "musb-hdrc", + .id = PLATFORM_DEVID_AUTO, + .dma_mask = DMA_BIT_MASK(32), +}; static int tusb_probe(struct platform_device *pdev) { @@ -1160,7 +1164,7 @@ static int tusb_probe(struct platform_device *pdev) struct musb_hdrc_platform_data *pdata = dev_get_platdata(&pdev->dev); struct platform_device *musb; struct tusb6010_glue *glue; - + struct platform_device_info pinfo; int ret = -ENOMEM; glue = kzalloc(sizeof(*glue), GFP_KERNEL); @@ -1169,18 +1173,7 @@ static int tusb_probe(struct platform_device *pdev) goto err0; } - musb = platform_device_alloc("musb-hdrc", PLATFORM_DEVID_AUTO); - if (!musb) { - dev_err(&pdev->dev, "failed to allocate musb device\n"); - goto err1; - } - - musb->dev.parent = &pdev->dev; - musb->dev.dma_mask = &tusb_dmamask; - musb->dev.coherent_dma_mask = tusb_dmamask; - glue->dev = &pdev->dev; - glue->musb = musb; pdata->platform_ops = &tusb_ops; @@ -1204,31 +1197,23 @@ static int tusb_probe(struct platform_device *pdev) musb_resources[2].end = pdev->resource[2].end; musb_resources[2].flags = pdev->resource[2].flags; - ret = platform_device_add_resources(musb, musb_resources, - ARRAY_SIZE(musb_resources)); - if (ret) { - dev_err(&pdev->dev, "failed to add resources\n"); - goto err3; - } - - ret = platform_device_add_data(musb, pdata, sizeof(*pdata)); - if (ret) { - dev_err(&pdev->dev, "failed to add platform_data\n"); - goto err3; - } - - ret = platform_device_add(musb); - if (ret) { - dev_err(&pdev->dev, "failed to register musb device\n"); + pinfo = tusb_dev_info; + pinfo.parent = &pdev->dev; + pinfo.res = musb_resources; + pinfo.num_res = ARRAY_SIZE(musb_resources); + pinfo.data = pdata; + pinfo.size_data = sizeof(*pdata); + + glue->musb = musb = platform_device_register_full(&pinfo); + if (IS_ERR(musb)) { + ret = PTR_ERR(musb); + dev_err(&pdev->dev, "failed to register musb device: %d\n", ret); goto err3; } return 0; err3: - platform_device_put(musb); - -err1: kfree(glue); err0: diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index c45f9c0a1b34..b21d553c245b 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -904,6 +904,7 @@ static struct usb_device_id id_table_combined [] = { { USB_DEVICE(FTDI_VID, FTDI_LUMEL_PD12_PID) }, /* Crucible Devices */ { USB_DEVICE(FTDI_VID, FTDI_CT_COMET_PID) }, + { USB_DEVICE(FTDI_VID, FTDI_Z3X_PID) }, { } /* Terminating entry */ }; diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index 1b8af461b522..a7019d1e3058 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -1307,3 +1307,9 @@ * Manufacturer: Crucible Technologies */ #define FTDI_CT_COMET_PID 0x8e08 + +/* + * Product: Z3X Box + * Manufacturer: Smart GSM Team + */ +#define FTDI_Z3X_PID 0x0011 diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 80a7104d5ddb..acaee066b99a 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -451,6 +451,10 @@ static void option_instat_callback(struct urb *urb); #define CHANGHONG_VENDOR_ID 0x2077 #define CHANGHONG_PRODUCT_CH690 0x7001 +/* Inovia */ +#define INOVIA_VENDOR_ID 0x20a6 +#define INOVIA_SEW858 0x1105 + /* some devices interfaces need special handling due to a number of reasons */ enum option_blacklist_reason { OPTION_BLACKLIST_NONE = 0, @@ -689,6 +693,222 @@ static const struct usb_device_id option_ids[] = { { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x7A) }, { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x7B) }, { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x7C) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x01) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x02) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x03) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x04) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x05) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x06) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x0A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x0B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x0D) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x0E) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x0F) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x10) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x12) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x13) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x14) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x15) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x17) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x18) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x19) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x1A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x1B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x1C) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x31) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x32) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x33) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x34) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x35) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x36) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x3A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x3B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x3D) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x3E) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x3F) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x48) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x49) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x4A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x4B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x4C) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x61) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x62) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x63) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x64) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x65) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x66) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x6A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x6B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x6D) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x6E) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x6F) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x78) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x79) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x7A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x7B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x7C) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x01) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x02) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x03) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x04) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x05) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x06) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x0A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x0B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x0D) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x0E) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x0F) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x10) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x12) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x13) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x14) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x15) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x17) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x18) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x19) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x1A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x1B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x1C) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x31) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x32) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x33) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x34) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x35) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x36) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x3A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x3B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x3D) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x3E) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x3F) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x48) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x49) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x4A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x4B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x4C) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x61) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x62) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x63) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x64) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x65) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x66) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x6A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x6B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x6D) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x6E) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x6F) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x78) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x79) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x7A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x7B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x7C) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x01) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x02) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x03) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x04) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x05) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x06) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x0A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x0B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x0D) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x0E) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x0F) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x10) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x12) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x13) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x14) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x15) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x17) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x18) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x19) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x1A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x1B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x1C) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x31) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x32) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x33) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x34) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x35) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x36) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x3A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x3B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x3D) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x3E) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x3F) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x48) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x49) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x4A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x4B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x4C) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x61) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x62) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x63) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x64) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x65) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x66) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x6A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x6B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x6D) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x6E) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x6F) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x78) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x79) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x7A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x7B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x7C) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x01) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x02) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x03) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x04) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x05) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x06) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x0A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x0B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x0D) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x0E) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x0F) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x10) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x12) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x13) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x14) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x15) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x17) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x18) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x19) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x1A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x1B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x1C) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x31) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x32) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x33) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x34) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x35) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x36) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x3A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x3B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x3D) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x3E) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x3F) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x48) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x49) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x4A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x4B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x4C) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x61) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x62) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x63) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x64) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x65) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x66) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x6A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x6B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x6D) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x6E) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x6F) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x78) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x79) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x7A) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x7B) }, + { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x7C) }, { USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_V640) }, @@ -1257,7 +1477,9 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD100) }, { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD145) }, - { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD200) }, + { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD200), + .driver_info = (kernel_ulong_t)&net_intf6_blacklist + }, { USB_DEVICE(CELOT_VENDOR_ID, CELOT_PRODUCT_CT680M) }, /* CT-650 CDMA 450 1xEVDO modem */ { USB_DEVICE_AND_INTERFACE_INFO(SAMSUNG_VENDOR_ID, SAMSUNG_PRODUCT_GT_B3730, USB_CLASS_CDC_DATA, 0x00, 0x00) }, /* Samsung GT-B3730 LTE USB modem.*/ { USB_DEVICE(YUGA_VENDOR_ID, YUGA_PRODUCT_CEM600) }, @@ -1345,6 +1567,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x7d03, 0xff, 0x00, 0x00) }, { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e01, 0xff, 0xff, 0xff) }, /* D-Link DWM-152/C1 */ { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e02, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/C1 */ + { USB_DEVICE(INOVIA_VENDOR_ID, INOVIA_SEW858) }, { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, option_ids); diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c index bedf8e47713b..1e6de4cd079d 100644 --- a/drivers/usb/serial/pl2303.c +++ b/drivers/usb/serial/pl2303.c @@ -4,11 +4,6 @@ * Copyright (C) 2001-2007 Greg Kroah-Hartman (greg@kroah.com) * Copyright (C) 2003 IBM Corp. * - * Copyright (C) 2009, 2013 Frank Schäfer <fschaefer.oss@googlemail.com> - * - fixes, improvements and documentation for the baud rate encoding methods - * Copyright (C) 2013 Reinhard Max <max@suse.de> - * - fixes and improvements for the divisor based baud rate encoding method - * * Original driver for 2.2.x by anonymous * * This program is free software; you can redistribute it and/or @@ -134,18 +129,10 @@ MODULE_DEVICE_TABLE(usb, id_table); enum pl2303_type { - type_0, /* H version ? */ - type_1, /* H version ? */ - HX_TA, /* HX(A) / X(A) / TA version */ /* TODO: improve */ - HXD_EA_RA_SA, /* HXD / EA / RA / SA version */ /* TODO: improve */ - TB, /* TB version */ - HX_CLONE, /* Cheap and less functional clone of the HX chip */ + type_0, /* don't know the difference between type 0 and */ + type_1, /* type 1, until someone from prolific tells us... */ + HX, /* HX version of the pl2303 chip */ }; -/* - * NOTE: don't know the difference between type 0 and type 1, - * until someone from Prolific tells us... - * TODO: distinguish between X/HX, TA and HXD, EA, RA, SA variants - */ struct pl2303_serial_private { enum pl2303_type type; @@ -185,7 +172,6 @@ static int pl2303_startup(struct usb_serial *serial) { struct pl2303_serial_private *spriv; enum pl2303_type type = type_0; - char *type_str = "unknown (treating as type_0)"; unsigned char *buf; spriv = kzalloc(sizeof(*spriv), GFP_KERNEL); @@ -198,53 +184,15 @@ static int pl2303_startup(struct usb_serial *serial) return -ENOMEM; } - if (serial->dev->descriptor.bDeviceClass == 0x02) { + if (serial->dev->descriptor.bDeviceClass == 0x02) type = type_0; - type_str = "type_0"; - } else if (serial->dev->descriptor.bMaxPacketSize0 == 0x40) { - /* - * NOTE: The bcdDevice version is the only difference between - * the device descriptors of the X/HX, HXD, EA, RA, SA, TA, TB - */ - if (le16_to_cpu(serial->dev->descriptor.bcdDevice) == 0x300) { - /* Check if the device is a clone */ - pl2303_vendor_read(0x9494, 0, serial, buf); - /* - * NOTE: Not sure if this read is really needed. - * The HX returns 0x00, the clone 0x02, but the Windows - * driver seems to ignore the value and continues. - */ - pl2303_vendor_write(0x0606, 0xaa, serial); - pl2303_vendor_read(0x8686, 0, serial, buf); - if (buf[0] != 0xaa) { - type = HX_CLONE; - type_str = "X/HX clone (limited functionality)"; - } else { - type = HX_TA; - type_str = "X/HX/TA"; - } - pl2303_vendor_write(0x0606, 0x00, serial); - } else if (le16_to_cpu(serial->dev->descriptor.bcdDevice) - == 0x400) { - type = HXD_EA_RA_SA; - type_str = "HXD/EA/RA/SA"; - } else if (le16_to_cpu(serial->dev->descriptor.bcdDevice) - == 0x500) { - type = TB; - type_str = "TB"; - } else { - dev_info(&serial->interface->dev, - "unknown/unsupported device type\n"); - kfree(spriv); - kfree(buf); - return -ENODEV; - } - } else if (serial->dev->descriptor.bDeviceClass == 0x00 - || serial->dev->descriptor.bDeviceClass == 0xFF) { + else if (serial->dev->descriptor.bMaxPacketSize0 == 0x40) + type = HX; + else if (serial->dev->descriptor.bDeviceClass == 0x00) type = type_1; - type_str = "type_1"; - } - dev_dbg(&serial->interface->dev, "device type: %s\n", type_str); + else if (serial->dev->descriptor.bDeviceClass == 0xFF) + type = type_1; + dev_dbg(&serial->interface->dev, "device type: %d\n", type); spriv->type = type; usb_set_serial_data(serial, spriv); @@ -259,10 +207,10 @@ static int pl2303_startup(struct usb_serial *serial) pl2303_vendor_read(0x8383, 0, serial, buf); pl2303_vendor_write(0, 1, serial); pl2303_vendor_write(1, 0, serial); - if (type == type_0 || type == type_1) - pl2303_vendor_write(2, 0x24, serial); - else + if (type == HX) pl2303_vendor_write(2, 0x44, serial); + else + pl2303_vendor_write(2, 0x24, serial); kfree(buf); return 0; @@ -316,174 +264,65 @@ static int pl2303_set_control_lines(struct usb_serial_port *port, u8 value) return retval; } -static int pl2303_baudrate_encode_direct(int baud, enum pl2303_type type, - u8 buf[4]) +static void pl2303_encode_baudrate(struct tty_struct *tty, + struct usb_serial_port *port, + u8 buf[4]) { - /* - * NOTE: Only the values defined in baud_sup are supported ! - * => if unsupported values are set, the PL2303 uses 9600 baud instead - * => HX clones just don't work at unsupported baud rates < 115200 baud, - * for baud rates > 115200 they run at 115200 baud - */ const int baud_sup[] = { 75, 150, 300, 600, 1200, 1800, 2400, 3600, - 4800, 7200, 9600, 14400, 19200, 28800, 38400, - 57600, 115200, 230400, 460800, 614400, 921600, - 1228800, 2457600, 3000000, 6000000, 12000000 }; + 4800, 7200, 9600, 14400, 19200, 28800, 38400, + 57600, 115200, 230400, 460800, 500000, 614400, + 921600, 1228800, 2457600, 3000000, 6000000 }; + + struct usb_serial *serial = port->serial; + struct pl2303_serial_private *spriv = usb_get_serial_data(serial); + int baud; + int i; + /* - * NOTE: With the exception of type_0/1 devices, the following - * additional baud rates are supported (tested with HX rev. 3A only): - * 110*, 56000*, 128000, 134400, 161280, 201600, 256000*, 268800, - * 403200, 806400. (*: not HX and HX clones) - * - * Maximum values: HXD, TB: 12000000; HX, TA: 6000000; - * type_0+1: 1228800; RA: 921600; HX clones, SA: 115200 - * - * As long as we are not using this encoding method for anything else - * than the type_0+1, HX and HX clone chips, there is no point in - * complicating the code to support them. + * NOTE: Only the values defined in baud_sup are supported! + * => if unsupported values are set, the PL2303 seems to use + * 9600 baud (at least my PL2303X always does) */ - int i; + baud = tty_get_baud_rate(tty); + dev_dbg(&port->dev, "baud requested = %d\n", baud); + if (!baud) + return; /* Set baudrate to nearest supported value */ for (i = 0; i < ARRAY_SIZE(baud_sup); ++i) { if (baud_sup[i] > baud) break; } + if (i == ARRAY_SIZE(baud_sup)) baud = baud_sup[i - 1]; else if (i > 0 && (baud_sup[i] - baud) > (baud - baud_sup[i - 1])) baud = baud_sup[i - 1]; else baud = baud_sup[i]; - /* Respect the chip type specific baud rate limits */ - /* - * FIXME: as long as we don't know how to distinguish between the - * HXD, EA, RA, and SA chip variants, allow the max. value of 12M. - */ - if (type == HX_TA) - baud = min_t(int, baud, 6000000); - else if (type == type_0 || type == type_1) - baud = min_t(int, baud, 1228800); - else if (type == HX_CLONE) - baud = min_t(int, baud, 115200); - /* Direct (standard) baud rate encoding method */ - put_unaligned_le32(baud, buf); - - return baud; -} -static int pl2303_baudrate_encode_divisor(int baud, enum pl2303_type type, - u8 buf[4]) -{ - /* - * Divisor based baud rate encoding method - * - * NOTE: HX clones do NOT support this method. - * It's not clear if the type_0/1 chips support it. - * - * divisor = 12MHz * 32 / baudrate = 2^A * B - * - * with - * - * A = buf[1] & 0x0e - * B = buf[0] + (buf[1] & 0x01) << 8 - * - * Special cases: - * => 8 < B < 16: device seems to work not properly - * => B <= 8: device uses the max. value B = 512 instead - */ - unsigned int A, B; + /* type_0, type_1 only support up to 1228800 baud */ + if (spriv->type != HX) + baud = min_t(int, baud, 1228800); - /* - * NOTE: The Windows driver allows maximum baud rates of 110% of the - * specified maximium value. - * Quick tests with early (2004) HX (rev. A) chips suggest, that even - * higher baud rates (up to the maximum of 24M baud !) are working fine, - * but that should really be tested carefully in "real life" scenarios - * before removing the upper limit completely. - * Baud rates smaller than the specified 75 baud are definitely working - * fine. - */ - if (type == type_0 || type == type_1) - baud = min_t(int, baud, 1228800 * 1.1); - else if (type == HX_TA) - baud = min_t(int, baud, 6000000 * 1.1); - else if (type == HXD_EA_RA_SA) - /* HXD, EA: 12Mbps; RA: 1Mbps; SA: 115200 bps */ - /* - * FIXME: as long as we don't know how to distinguish between - * these chip variants, allow the max. of these values - */ - baud = min_t(int, baud, 12000000 * 1.1); - else if (type == TB) - baud = min_t(int, baud, 12000000 * 1.1); - /* Determine factors A and B */ - A = 0; - B = 12000000 * 32 / baud; /* 12MHz */ - B <<= 1; /* Add one bit for rounding */ - while (B > (512 << 1) && A <= 14) { - A += 2; - B >>= 2; - } - if (A > 14) { /* max. divisor = min. baudrate reached */ - A = 14; - B = 512; - /* => ~45.78 baud */ + if (baud <= 115200) { + put_unaligned_le32(baud, buf); } else { - B = (B + 1) >> 1; /* Round the last bit */ - } - /* Handle special cases */ - if (B == 512) - B = 0; /* also: 1 to 8 */ - else if (B < 16) /* - * NOTE: With the current algorithm this happens - * only for A=0 and means that the min. divisor - * (respectively: the max. baudrate) is reached. + * Apparently the formula for higher speeds is: + * baudrate = 12M * 32 / (2^buf[1]) / buf[0] */ - B = 16; /* => 24 MBaud */ - /* Encode the baud rate */ - buf[3] = 0x80; /* Select divisor encoding method */ - buf[2] = 0; - buf[1] = (A & 0x0e); /* A */ - buf[1] |= ((B & 0x100) >> 8); /* MSB of B */ - buf[0] = B & 0xff; /* 8 LSBs of B */ - /* Calculate the actual/resulting baud rate */ - if (B <= 8) - B = 512; - baud = 12000000 * 32 / ((1 << A) * B); - - return baud; -} - -static void pl2303_encode_baudrate(struct tty_struct *tty, - struct usb_serial_port *port, - enum pl2303_type type, - u8 buf[4]) -{ - int baud; + unsigned tmp = 12000000 * 32 / baud; + buf[3] = 0x80; + buf[2] = 0; + buf[1] = (tmp >= 256); + while (tmp >= 256) { + tmp >>= 2; + buf[1] <<= 1; + } + buf[0] = tmp; + } - baud = tty_get_baud_rate(tty); - dev_dbg(&port->dev, "baud requested = %d\n", baud); - if (!baud) - return; - /* - * There are two methods for setting/encoding the baud rate - * 1) Direct method: encodes the baud rate value directly - * => supported by all chip types - * 2) Divisor based method: encodes a divisor to a base value (12MHz*32) - * => not supported by HX clones (and likely type_0/1 chips) - * - * NOTE: Although the divisor based baud rate encoding method is much - * more flexible, some of the standard baud rate values can not be - * realized exactly. But the difference is very small (max. 0.2%) and - * the device likely uses the same baud rate generator for both methods - * so that there is likley no difference. - */ - if (type == type_0 || type == type_1 || type == HX_CLONE) - baud = pl2303_baudrate_encode_direct(baud, type, buf); - else - baud = pl2303_baudrate_encode_divisor(baud, type, buf); /* Save resulting baud rate */ tty_encode_baud_rate(tty, baud, baud); dev_dbg(&port->dev, "baud set = %d\n", baud); @@ -540,8 +379,8 @@ static void pl2303_set_termios(struct tty_struct *tty, dev_dbg(&port->dev, "data bits = %d\n", buf[6]); } - /* For reference: buf[0]:buf[3] baud rate value */ - pl2303_encode_baudrate(tty, port, spriv->type, buf); + /* For reference buf[0]:buf[3] baud rate value */ + pl2303_encode_baudrate(tty, port, &buf[0]); /* For reference buf[4]=0 is 1 stop bits */ /* For reference buf[4]=1 is 1.5 stop bits */ @@ -618,10 +457,10 @@ static void pl2303_set_termios(struct tty_struct *tty, dev_dbg(&port->dev, "0xa1:0x21:0:0 %d - %7ph\n", i, buf); if (C_CRTSCTS(tty)) { - if (spriv->type == type_0 || spriv->type == type_1) - pl2303_vendor_write(0x0, 0x41, serial); - else + if (spriv->type == HX) pl2303_vendor_write(0x0, 0x61, serial); + else + pl2303_vendor_write(0x0, 0x41, serial); } else { pl2303_vendor_write(0x0, 0x0, serial); } @@ -658,7 +497,7 @@ static int pl2303_open(struct tty_struct *tty, struct usb_serial_port *port) struct pl2303_serial_private *spriv = usb_get_serial_data(serial); int result; - if (spriv->type == type_0 || spriv->type == type_1) { + if (spriv->type != HX) { usb_clear_halt(serial->dev, port->write_urb->pipe); usb_clear_halt(serial->dev, port->read_urb->pipe); } else { @@ -833,7 +672,6 @@ static void pl2303_break_ctl(struct tty_struct *tty, int break_state) result = usb_control_msg(serial->dev, usb_sndctrlpipe(serial->dev, 0), BREAK_REQUEST, BREAK_REQUEST_TYPE, state, 0, NULL, 0, 100); - /* NOTE: HX clones don't support sending breaks, -EPIPE is returned */ if (result) dev_err(&port->dev, "error sending break = %d\n", result); } diff --git a/drivers/usb/serial/ti_usb_3410_5052.c b/drivers/usb/serial/ti_usb_3410_5052.c index 760b78560f67..c9a35697ebe9 100644 --- a/drivers/usb/serial/ti_usb_3410_5052.c +++ b/drivers/usb/serial/ti_usb_3410_5052.c @@ -190,6 +190,7 @@ static struct usb_device_id ti_id_table_combined[] = { { USB_DEVICE(IBM_VENDOR_ID, IBM_454B_PRODUCT_ID) }, { USB_DEVICE(IBM_VENDOR_ID, IBM_454C_PRODUCT_ID) }, { USB_DEVICE(ABBOTT_VENDOR_ID, ABBOTT_PRODUCT_ID) }, + { USB_DEVICE(ABBOTT_VENDOR_ID, ABBOTT_STRIP_PORT_ID) }, { USB_DEVICE(TI_VENDOR_ID, FRI2_PRODUCT_ID) }, { } /* terminator */ }; diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c index 94d75edef77f..18509e6c21ab 100644 --- a/drivers/usb/storage/scsiglue.c +++ b/drivers/usb/storage/scsiglue.c @@ -211,8 +211,11 @@ static int slave_configure(struct scsi_device *sdev) /* * Many devices do not respond properly to READ_CAPACITY_16. * Tell the SCSI layer to try READ_CAPACITY_10 first. + * However some USB 3.0 drive enclosures return capacity + * modulo 2TB. Those must use READ_CAPACITY_16 */ - sdev->try_rc_10_first = 1; + if (!(us->fflags & US_FL_NEEDS_CAP16)) + sdev->try_rc_10_first = 1; /* assume SPC3 or latter devices support sense size > 18 */ if (sdev->scsi_level > SCSI_SPC_2) diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index c015f2c16729..de32cfa5bfa6 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -1925,6 +1925,13 @@ UNUSUAL_DEV( 0x1652, 0x6600, 0x0201, 0x0201, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_IGNORE_RESIDUE ), +/* Reported by Oliver Neukum <oneukum@suse.com> */ +UNUSUAL_DEV( 0x174c, 0x55aa, 0x0100, 0x0100, + "ASMedia", + "AS2105", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_NEEDS_CAP16), + /* Reported by Jesse Feddema <jdfeddema@gmail.com> */ UNUSUAL_DEV( 0x177f, 0x0400, 0x0000, 0x0000, "Yarvik", diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index a9807dea3887..4fb7a8f83c8a 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -545,6 +545,8 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu, long npage; int ret = 0, prot = 0; uint64_t mask; + struct vfio_dma *dma = NULL; + unsigned long pfn; end = map->iova + map->size; @@ -587,8 +589,6 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu, } for (iova = map->iova; iova < end; iova += size, vaddr += size) { - struct vfio_dma *dma = NULL; - unsigned long pfn; long i; /* Pin a contiguous chunk of memory */ @@ -597,16 +597,15 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu, if (npage <= 0) { WARN_ON(!npage); ret = (int)npage; - break; + goto out; } /* Verify pages are not already mapped */ for (i = 0; i < npage; i++) { if (iommu_iova_to_phys(iommu->domain, iova + (i << PAGE_SHIFT))) { - vfio_unpin_pages(pfn, npage, prot, true); ret = -EBUSY; - break; + goto out_unpin; } } @@ -616,8 +615,7 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu, if (ret) { if (ret != -EBUSY || map_try_harder(iommu, iova, pfn, npage, prot)) { - vfio_unpin_pages(pfn, npage, prot, true); - break; + goto out_unpin; } } @@ -672,9 +670,8 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu, dma = kzalloc(sizeof(*dma), GFP_KERNEL); if (!dma) { iommu_unmap(iommu->domain, iova, size); - vfio_unpin_pages(pfn, npage, prot, true); ret = -ENOMEM; - break; + goto out_unpin; } dma->size = size; @@ -685,16 +682,21 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu, } } - if (ret) { - struct vfio_dma *tmp; - iova = map->iova; - size = map->size; - while ((tmp = vfio_find_dma(iommu, iova, size))) { - int r = vfio_remove_dma_overlap(iommu, iova, - &size, tmp); - if (WARN_ON(r || !size)) - break; - } + WARN_ON(ret); + mutex_unlock(&iommu->lock); + return ret; + +out_unpin: + vfio_unpin_pages(pfn, npage, prot, true); + +out: + iova = map->iova; + size = map->size; + while ((dma = vfio_find_dma(iommu, iova, size))) { + int r = vfio_remove_dma_overlap(iommu, iova, + &size, dma); + if (WARN_ON(r || !size)) + break; } mutex_unlock(&iommu->lock); diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index ce5221fa393a..e663921eebb6 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -1056,7 +1056,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) if (data_direction != DMA_NONE) { ret = vhost_scsi_map_iov_to_sgl(cmd, &vq->iov[data_first], data_num, - data_direction == DMA_TO_DEVICE); + data_direction == DMA_FROM_DEVICE); if (unlikely(ret)) { vq_err(vq, "Failed to map iov to sgl\n"); goto err_free; diff --git a/drivers/video/amba-clcd.c b/drivers/video/amba-clcd.c index 0a2cce7285be..afe4702a5528 100644 --- a/drivers/video/amba-clcd.c +++ b/drivers/video/amba-clcd.c @@ -10,6 +10,7 @@ * * ARM PrimeCell PL110 Color LCD Controller */ +#include <linux/dma-mapping.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/errno.h> @@ -551,6 +552,10 @@ static int clcdfb_probe(struct amba_device *dev, const struct amba_id *id) if (!board) return -EINVAL; + ret = dma_set_mask_and_coherent(&dev->dev, DMA_BIT_MASK(32)); + if (ret) + goto out; + ret = amba_request_regions(dev, NULL); if (ret) { printk(KERN_ERR "CLCD: unable to reserve regs region\n"); diff --git a/drivers/video/au1100fb.c b/drivers/video/au1100fb.c index a54ccdc4d661..22ad85242e5b 100644 --- a/drivers/video/au1100fb.c +++ b/drivers/video/au1100fb.c @@ -361,37 +361,13 @@ void au1100fb_fb_rotate(struct fb_info *fbi, int angle) int au1100fb_fb_mmap(struct fb_info *fbi, struct vm_area_struct *vma) { struct au1100fb_device *fbdev; - unsigned int len; - unsigned long start=0, off; fbdev = to_au1100fb_device(fbi); - if (vma->vm_pgoff > (~0UL >> PAGE_SHIFT)) { - return -EINVAL; - } - - start = fbdev->fb_phys & PAGE_MASK; - len = PAGE_ALIGN((start & ~PAGE_MASK) + fbdev->fb_len); - - off = vma->vm_pgoff << PAGE_SHIFT; - - if ((vma->vm_end - vma->vm_start + off) > len) { - return -EINVAL; - } - - off += start; - vma->vm_pgoff = off >> PAGE_SHIFT; - vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); pgprot_val(vma->vm_page_prot) |= (6 << 9); //CCA=6 - if (io_remap_pfn_range(vma, vma->vm_start, off >> PAGE_SHIFT, - vma->vm_end - vma->vm_start, - vma->vm_page_prot)) { - return -EAGAIN; - } - - return 0; + return vm_iomap_memory(vma, fbdev->fb_phys, fbdev->fb_len); } static struct fb_ops au1100fb_ops = diff --git a/drivers/video/au1200fb.c b/drivers/video/au1200fb.c index 301224ecc950..1d02897d17f2 100644 --- a/drivers/video/au1200fb.c +++ b/drivers/video/au1200fb.c @@ -1233,34 +1233,13 @@ static int au1200fb_fb_blank(int blank_mode, struct fb_info *fbi) * method mainly to allow the use of the TLB streaming flag (CCA=6) */ static int au1200fb_fb_mmap(struct fb_info *info, struct vm_area_struct *vma) - { - unsigned int len; - unsigned long start=0, off; struct au1200fb_device *fbdev = info->par; - if (vma->vm_pgoff > (~0UL >> PAGE_SHIFT)) { - return -EINVAL; - } - - start = fbdev->fb_phys & PAGE_MASK; - len = PAGE_ALIGN((start & ~PAGE_MASK) + fbdev->fb_len); - - off = vma->vm_pgoff << PAGE_SHIFT; - - if ((vma->vm_end - vma->vm_start + off) > len) { - return -EINVAL; - } - - off += start; - vma->vm_pgoff = off >> PAGE_SHIFT; - vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); pgprot_val(vma->vm_page_prot) |= _CACHE_MASK; /* CCA=7 */ - return io_remap_pfn_range(vma, vma->vm_start, off >> PAGE_SHIFT, - vma->vm_end - vma->vm_start, - vma->vm_page_prot); + return vm_iomap_memory(vma, fbdev->fb_phys, fbdev->fb_len); } static void set_global(u_int cmd, struct au1200_lcd_global_regs_t *pdata) diff --git a/drivers/w1/w1.c b/drivers/w1/w1.c index c7c64f18773d..fa932c2f7d97 100644 --- a/drivers/w1/w1.c +++ b/drivers/w1/w1.c @@ -613,6 +613,9 @@ static int w1_bus_notify(struct notifier_block *nb, unsigned long action, sl = dev_to_w1_slave(dev); fops = sl->family->fops; + if (!fops) + return 0; + switch (action) { case BUS_NOTIFY_ADD_DEVICE: /* if the family driver needs to initialize something... */ @@ -713,7 +716,10 @@ static int w1_attach_slave_device(struct w1_master *dev, struct w1_reg_num *rn) atomic_set(&sl->refcnt, 0); init_completion(&sl->released); + /* slave modules need to be loaded in a context with unlocked mutex */ + mutex_unlock(&dev->mutex); request_module("w1-family-0x%0x", rn->family); + mutex_lock(&dev->mutex); spin_lock(&w1_flock); f = w1_family_registered(rn->family); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index b0ef7b07b1b3..51e3afa78354 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -6437,6 +6437,7 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, if (btrfs_extent_readonly(root, disk_bytenr)) goto out; + btrfs_release_path(path); /* * look for other files referencing this extent, if we diff --git a/fs/buffer.c b/fs/buffer.c index 4d7433534f5c..6024877335ca 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -1005,9 +1005,19 @@ grow_dev_page(struct block_device *bdev, sector_t block, struct buffer_head *bh; sector_t end_block; int ret = 0; /* Will call free_more_memory() */ + gfp_t gfp_mask; - page = find_or_create_page(inode->i_mapping, index, - (mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS)|__GFP_MOVABLE); + gfp_mask = mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS; + gfp_mask |= __GFP_MOVABLE; + /* + * XXX: __getblk_slow() can not really deal with failure and + * will endlessly loop on improvised global reclaim. Prefer + * looping in the allocator rather than here, at least that + * code knows what it's doing. + */ + gfp_mask |= __GFP_NOFAIL; + + page = find_or_create_page(inode->i_mapping, index, gfp_mask); if (!page) return ret; diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index a16b4e58bcc6..77fc5e181077 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -120,14 +120,16 @@ cifs_read_super(struct super_block *sb) { struct inode *inode; struct cifs_sb_info *cifs_sb; + struct cifs_tcon *tcon; int rc = 0; cifs_sb = CIFS_SB(sb); + tcon = cifs_sb_master_tcon(cifs_sb); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIXACL) sb->s_flags |= MS_POSIXACL; - if (cifs_sb_master_tcon(cifs_sb)->ses->capabilities & CAP_LARGE_FILES) + if (tcon->ses->capabilities & tcon->ses->server->vals->cap_large_files) sb->s_maxbytes = MAX_LFS_FILESIZE; else sb->s_maxbytes = MAX_NON_LFS; @@ -147,7 +149,7 @@ cifs_read_super(struct super_block *sb) goto out_no_root; } - if (cifs_sb_master_tcon(cifs_sb)->nocase) + if (tcon->nocase) sb->s_d_op = &cifs_ci_dentry_ops; else sb->s_d_op = &cifs_dentry_ops; diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h index a630475e421c..08f9dfb1a894 100644 --- a/fs/cifs/cifspdu.h +++ b/fs/cifs/cifspdu.h @@ -1491,15 +1491,30 @@ struct file_notify_information { __u8 FileName[0]; } __attribute__((packed)); -struct reparse_data { - __u32 ReparseTag; - __u16 ReparseDataLength; +/* For IO_REPARSE_TAG_SYMLINK */ +struct reparse_symlink_data { + __le32 ReparseTag; + __le16 ReparseDataLength; __u16 Reserved; - __u16 SubstituteNameOffset; - __u16 SubstituteNameLength; - __u16 PrintNameOffset; - __u16 PrintNameLength; - __u32 Flags; + __le16 SubstituteNameOffset; + __le16 SubstituteNameLength; + __le16 PrintNameOffset; + __le16 PrintNameLength; + __le32 Flags; + char PathBuffer[0]; +} __attribute__((packed)); + +/* For IO_REPARSE_TAG_NFS */ +#define NFS_SPECFILE_LNK 0x00000000014B4E4C +#define NFS_SPECFILE_CHR 0x0000000000524843 +#define NFS_SPECFILE_BLK 0x00000000004B4C42 +#define NFS_SPECFILE_FIFO 0x000000004F464946 +#define NFS_SPECFILE_SOCK 0x000000004B434F53 +struct reparse_posix_data { + __le32 ReparseTag; + __le16 ReparseDataLength; + __u16 Reserved; + __le64 InodeType; /* LNK, FIFO, CHR etc. */ char PathBuffer[0]; } __attribute__((packed)); diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 4baf35949b51..ccd31ab815d4 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -3088,7 +3088,8 @@ CIFSSMBQuerySymLink(const unsigned int xid, struct cifs_tcon *tcon, bool is_unicode; unsigned int sub_len; char *sub_start; - struct reparse_data *reparse_buf; + struct reparse_symlink_data *reparse_buf; + struct reparse_posix_data *posix_buf; __u32 data_offset, data_count; char *end_of_smb; @@ -3137,20 +3138,47 @@ CIFSSMBQuerySymLink(const unsigned int xid, struct cifs_tcon *tcon, goto qreparse_out; } end_of_smb = 2 + get_bcc(&pSMBr->hdr) + (char *)&pSMBr->ByteCount; - reparse_buf = (struct reparse_data *) + reparse_buf = (struct reparse_symlink_data *) ((char *)&pSMBr->hdr.Protocol + data_offset); if ((char *)reparse_buf >= end_of_smb) { rc = -EIO; goto qreparse_out; } - if ((reparse_buf->PathBuffer + reparse_buf->PrintNameOffset + - reparse_buf->PrintNameLength) > end_of_smb) { + if (reparse_buf->ReparseTag == cpu_to_le32(IO_REPARSE_TAG_NFS)) { + cifs_dbg(FYI, "NFS style reparse tag\n"); + posix_buf = (struct reparse_posix_data *)reparse_buf; + + if (posix_buf->InodeType != cpu_to_le64(NFS_SPECFILE_LNK)) { + cifs_dbg(FYI, "unsupported file type 0x%llx\n", + le64_to_cpu(posix_buf->InodeType)); + rc = -EOPNOTSUPP; + goto qreparse_out; + } + is_unicode = true; + sub_len = le16_to_cpu(reparse_buf->ReparseDataLength); + if (posix_buf->PathBuffer + sub_len > end_of_smb) { + cifs_dbg(FYI, "reparse buf beyond SMB\n"); + rc = -EIO; + goto qreparse_out; + } + *symlinkinfo = cifs_strndup_from_utf16(posix_buf->PathBuffer, + sub_len, is_unicode, nls_codepage); + goto qreparse_out; + } else if (reparse_buf->ReparseTag != + cpu_to_le32(IO_REPARSE_TAG_SYMLINK)) { + rc = -EOPNOTSUPP; + goto qreparse_out; + } + + /* Reparse tag is NTFS symlink */ + sub_start = le16_to_cpu(reparse_buf->SubstituteNameOffset) + + reparse_buf->PathBuffer; + sub_len = le16_to_cpu(reparse_buf->SubstituteNameLength); + if (sub_start + sub_len > end_of_smb) { cifs_dbg(FYI, "reparse buf beyond SMB\n"); rc = -EIO; goto qreparse_out; } - sub_start = reparse_buf->SubstituteNameOffset + reparse_buf->PathBuffer; - sub_len = reparse_buf->SubstituteNameLength; if (pSMBr->hdr.Flags2 & SMBFLG2_UNICODE) is_unicode = true; else diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c index af847e1cf1c1..651a5279607b 100644 --- a/fs/cifs/netmisc.c +++ b/fs/cifs/netmisc.c @@ -780,7 +780,9 @@ static const struct { ERRDOS, ERRnoaccess, 0xc0000290}, { ERRDOS, ERRbadfunc, 0xc000029c}, { ERRDOS, ERRsymlink, NT_STATUS_STOPPED_ON_SYMLINK}, { - ERRDOS, ERRinvlevel, 0x007c0001}, }; + ERRDOS, ERRinvlevel, 0x007c0001}, { + 0, 0, 0 } +}; /***************************************************************************** Print an error message from the status code diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index 352358de1d7e..e87387dbf39f 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -500,9 +500,9 @@ select_sectype(struct TCP_Server_Info *server, enum securityEnum requested) return NTLMv2; if (global_secflags & CIFSSEC_MAY_NTLM) return NTLM; - /* Fallthrough */ default: - return Unspecified; + /* Fallthrough to attempt LANMAN authentication next */ + break; } case CIFS_NEGFLAVOR_LANMAN: switch (requested) { diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index eba0efde66d7..edccb5252462 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -687,6 +687,10 @@ SMB2_logoff(const unsigned int xid, struct cifs_ses *ses) else return -EIO; + /* no need to send SMB logoff if uid already closed due to reconnect */ + if (ses->need_reconnect) + goto smb2_session_already_dead; + rc = small_smb2_init(SMB2_LOGOFF, NULL, (void **) &req); if (rc) return rc; @@ -701,6 +705,8 @@ SMB2_logoff(const unsigned int xid, struct cifs_ses *ses) * No tcon so can't do * cifs_stats_inc(&tcon->stats.smb2_stats.smb2_com_fail[SMB2...]); */ + +smb2_session_already_dead: return rc; } diff --git a/fs/cifs/smbfsctl.h b/fs/cifs/smbfsctl.h index d952ee48f4dc..a4b2391fe66e 100644 --- a/fs/cifs/smbfsctl.h +++ b/fs/cifs/smbfsctl.h @@ -97,9 +97,23 @@ #define FSCTL_QUERY_NETWORK_INTERFACE_INFO 0x001401FC /* BB add struct */ #define FSCTL_SRV_READ_HASH 0x001441BB /* BB add struct */ +/* See FSCC 2.1.2.5 */ #define IO_REPARSE_TAG_MOUNT_POINT 0xA0000003 #define IO_REPARSE_TAG_HSM 0xC0000004 #define IO_REPARSE_TAG_SIS 0x80000007 +#define IO_REPARSE_TAG_HSM2 0x80000006 +#define IO_REPARSE_TAG_DRIVER_EXTENDER 0x80000005 +/* Used by the DFS filter. See MS-DFSC */ +#define IO_REPARSE_TAG_DFS 0x8000000A +/* Used by the DFS filter See MS-DFSC */ +#define IO_REPARSE_TAG_DFSR 0x80000012 +#define IO_REPARSE_TAG_FILTER_MANAGER 0x8000000B +/* See section MS-FSCC 2.1.2.4 */ +#define IO_REPARSE_TAG_SYMLINK 0xA000000C +#define IO_REPARSE_TAG_DEDUP 0x80000013 +#define IO_REPARSE_APPXSTREAM 0xC0000014 +/* NFS symlinks, Win 8/SMB3 and later */ +#define IO_REPARSE_TAG_NFS 0x80000014 /* fsctl flags */ /* If Flags is set to this value, the request is an FSCTL not ioctl request */ diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 6fdcb1b4a106..800b938e4061 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -410,8 +410,13 @@ static int wait_for_free_request(struct TCP_Server_Info *server, const int timeout, const int optype) { - return wait_for_free_credits(server, timeout, - server->ops->get_credits_field(server, optype)); + int *val; + + val = server->ops->get_credits_field(server, optype); + /* Since an echo is already inflight, no need to wait to send another */ + if (*val <= 0 && optype == CIFS_ECHO_OP) + return -EAGAIN; + return wait_for_free_credits(server, timeout, val); } static int allocate_mid(struct cifs_ses *ses, struct smb_hdr *in_buf, diff --git a/fs/dcache.c b/fs/dcache.c index 41000305d716..ae6ebb88ceff 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -542,7 +542,7 @@ EXPORT_SYMBOL(d_drop); * If ref is non-zero, then decrement the refcount too. * Returns dentry requiring refcount drop, or NULL if we're done. */ -static inline struct dentry * +static struct dentry * dentry_kill(struct dentry *dentry, int unlock_on_failure) __releases(dentry->d_lock) { @@ -630,7 +630,8 @@ repeat: goto kill_it; } - dentry->d_flags |= DCACHE_REFERENCED; + if (!(dentry->d_flags & DCACHE_REFERENCED)) + dentry->d_flags |= DCACHE_REFERENCED; dentry_lru_add(dentry); dentry->d_lockref.count--; @@ -1331,14 +1332,6 @@ rename_retry: * list is non-empty and continue searching. */ -/** - * have_submounts - check for mounts over a dentry - * @parent: dentry to check. - * - * Return true if the parent or its subdirectories contain - * a mount point - */ - static enum d_walk_ret check_mount(void *data, struct dentry *dentry) { int *ret = data; @@ -1349,6 +1342,13 @@ static enum d_walk_ret check_mount(void *data, struct dentry *dentry) return D_WALK_CONTINUE; } +/** + * have_submounts - check for mounts over a dentry + * @parent: dentry to check. + * + * Return true if the parent or its subdirectories contain + * a mount point + */ int have_submounts(struct dentry *parent) { int ret = 0; diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index c88e355f7635..000eae2782b6 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -408,7 +408,7 @@ static loff_t lower_offset_for_page(struct ecryptfs_crypt_stat *crypt_stat, struct page *page) { return ecryptfs_lower_header_size(crypt_stat) + - (page->index << PAGE_CACHE_SHIFT); + ((loff_t)page->index << PAGE_CACHE_SHIFT); } /** diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c index 7d52806c2119..4725a07f003c 100644 --- a/fs/ecryptfs/keystore.c +++ b/fs/ecryptfs/keystore.c @@ -1149,7 +1149,7 @@ decrypt_pki_encrypted_session_key(struct ecryptfs_auth_tok *auth_tok, struct ecryptfs_msg_ctx *msg_ctx; struct ecryptfs_message *msg = NULL; char *auth_tok_sig; - char *payload; + char *payload = NULL; size_t payload_len = 0; int rc; @@ -1203,6 +1203,7 @@ decrypt_pki_encrypted_session_key(struct ecryptfs_auth_tok *auth_tok, } out: kfree(msg); + kfree(payload); return rc; } diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 473e09da7d02..810c28fb8c3c 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -34,7 +34,6 @@ #include <linux/mutex.h> #include <linux/anon_inodes.h> #include <linux/device.h> -#include <linux/freezer.h> #include <asm/uaccess.h> #include <asm/io.h> #include <asm/mman.h> @@ -1605,8 +1604,7 @@ fetch_events: } spin_unlock_irqrestore(&ep->lock, flags); - if (!freezable_schedule_hrtimeout_range(to, slack, - HRTIMER_MODE_ABS)) + if (!schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS)) timed_out = 1; spin_lock_irqsave(&ep->lock, flags); diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c index 1194b1f0f839..f8cde46de9cd 100644 --- a/fs/ext3/namei.c +++ b/fs/ext3/namei.c @@ -1783,7 +1783,7 @@ retry: d_tmpfile(dentry, inode); err = ext3_orphan_add(handle, inode); if (err) - goto err_drop_inode; + goto err_unlock_inode; mark_inode_dirty(inode); unlock_new_inode(inode); } @@ -1791,10 +1791,9 @@ retry: if (err == -ENOSPC && ext3_should_retry_alloc(dir->i_sb, &retries)) goto retry; return err; -err_drop_inode: +err_unlock_inode: ext3_journal_stop(handle); unlock_new_inode(inode); - iput(inode); return err; } diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 1bec5a5c1e45..5a0408d7b114 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2319,7 +2319,7 @@ retry: d_tmpfile(dentry, inode); err = ext4_orphan_add(handle, inode); if (err) - goto err_drop_inode; + goto err_unlock_inode; mark_inode_dirty(inode); unlock_new_inode(inode); } @@ -2328,10 +2328,9 @@ retry: if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries)) goto retry; return err; -err_drop_inode: +err_unlock_inode: ext4_journal_stop(handle); unlock_new_inode(inode); - iput(inode); return err; } diff --git a/fs/file_table.c b/fs/file_table.c index abdd15ad13c9..e900ca518635 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -297,7 +297,7 @@ void flush_delayed_fput(void) delayed_fput(NULL); } -static DECLARE_WORK(delayed_fput_work, delayed_fput); +static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput); void fput(struct file *file) { @@ -317,7 +317,7 @@ void fput(struct file *file) } if (llist_add(&file->f_u.fu_llist, &delayed_fput_list)) - schedule_work(&delayed_fput_work); + schedule_delayed_work(&delayed_fput_work, 1); } } diff --git a/fs/jfs/jfs_inode.c b/fs/jfs/jfs_inode.c index c1a3e603279c..7f464c513ba0 100644 --- a/fs/jfs/jfs_inode.c +++ b/fs/jfs/jfs_inode.c @@ -95,7 +95,7 @@ struct inode *ialloc(struct inode *parent, umode_t mode) if (insert_inode_locked(inode) < 0) { rc = -EINVAL; - goto fail_unlock; + goto fail_put; } inode_init_owner(inode, parent, mode); @@ -156,7 +156,6 @@ struct inode *ialloc(struct inode *parent, umode_t mode) fail_drop: dquot_drop(inode); inode->i_flags |= S_NOQUOTA; -fail_unlock: clear_nlink(inode); unlock_new_inode(inode); fail_put: diff --git a/fs/namei.c b/fs/namei.c index 645268f23eb6..caa28051e197 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2294,10 +2294,11 @@ out: * path_mountpoint - look up a path to be umounted * @dfd: directory file descriptor to start walk from * @name: full pathname to walk + * @path: pointer to container for result * @flags: lookup flags * * Look up the given name, but don't attempt to revalidate the last component. - * Returns 0 and "path" will be valid on success; Retuns error otherwise. + * Returns 0 and "path" will be valid on success; Returns error otherwise. */ static int path_mountpoint(int dfd, const char *name, struct path *path, unsigned int flags) diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 9f8ef9b7674d..8eaa1ba793fc 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -288,10 +288,14 @@ static int proc_reg_mmap(struct file *file, struct vm_area_struct *vma) static unsigned long proc_reg_get_unmapped_area(struct file *file, unsigned long orig_addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct proc_dir_entry *pde = PDE(file_inode(file)); - int rv = -EIO; - unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); + unsigned long rv = -EIO; + unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long) = NULL; if (use_pde(pde)) { - get_unmapped_area = pde->proc_fops->get_unmapped_area; +#ifdef CONFIG_MMU + get_unmapped_area = current->mm->get_unmapped_area; +#endif + if (pde->proc_fops->get_unmapped_area) + get_unmapped_area = pde->proc_fops->get_unmapped_area; if (get_unmapped_area) rv = get_unmapped_area(file, orig_addr, len, pgoff, flags); unuse_pde(pde); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 7366e9d63cee..390bdab01c3c 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -941,6 +941,8 @@ static void pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm, frame = pte_pfn(pte); flags = PM_PRESENT; page = vm_normal_page(vma, addr, pte); + if (pte_soft_dirty(pte)) + flags2 |= __PM_SOFT_DIRTY; } else if (is_swap_pte(pte)) { swp_entry_t entry; if (pte_swp_soft_dirty(pte)) @@ -960,7 +962,7 @@ static void pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm, if (page && !PageAnon(page)) flags |= PM_FILE; - if ((vma->vm_flags & VM_SOFTDIRTY) || pte_soft_dirty(pte)) + if ((vma->vm_flags & VM_SOFTDIRTY)) flags2 |= __PM_SOFT_DIRTY; *pme = make_pme(PM_PFRAME(frame) | PM_STATUS2(pm->v2, flags2) | flags); diff --git a/fs/select.c b/fs/select.c index 35d4adc749d9..dfd5cb18c012 100644 --- a/fs/select.c +++ b/fs/select.c @@ -238,8 +238,7 @@ int poll_schedule_timeout(struct poll_wqueues *pwq, int state, set_current_state(state); if (!pwq->triggered) - rc = freezable_schedule_hrtimeout_range(expires, slack, - HRTIMER_MODE_ABS); + rc = schedule_hrtimeout_range(expires, slack, HRTIMER_MODE_ABS); __set_current_state(TASK_RUNNING); /* diff --git a/fs/seq_file.c b/fs/seq_file.c index 3135c2525c76..a290157265ef 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -328,6 +328,8 @@ loff_t seq_lseek(struct file *file, loff_t offset, int whence) m->read_pos = offset; retval = file->f_pos = offset; } + } else { + file->f_pos = offset; } } file->f_version = m->version; diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 02e113bb8b7d..d9019821aa60 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -311,7 +311,6 @@ struct acpi_device { unsigned int physical_node_count; struct list_head physical_node_list; struct mutex physical_node_lock; - struct list_head power_dependent; void (*remove)(struct acpi_device *); }; @@ -456,8 +455,6 @@ acpi_status acpi_add_pm_notifier(struct acpi_device *adev, acpi_status acpi_remove_pm_notifier(struct acpi_device *adev, acpi_notify_handler handler); int acpi_pm_device_sleep_state(struct device *, int *, int); -void acpi_dev_pm_add_dependent(acpi_handle handle, struct device *depdev); -void acpi_dev_pm_remove_dependent(acpi_handle handle, struct device *depdev); #else static inline acpi_status acpi_add_pm_notifier(struct acpi_device *adev, acpi_notify_handler handler, @@ -478,10 +475,6 @@ static inline int acpi_pm_device_sleep_state(struct device *d, int *p, int m) return (m >= ACPI_STATE_D0 && m <= ACPI_STATE_D3_COLD) ? m : ACPI_STATE_D0; } -static inline void acpi_dev_pm_add_dependent(acpi_handle handle, - struct device *depdev) {} -static inline void acpi_dev_pm_remove_dependent(acpi_handle handle, - struct device *depdev) {} #endif #ifdef CONFIG_PM_RUNTIME diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h index 43ec7e247a80..682df0e1954a 100644 --- a/include/linux/amba/bus.h +++ b/include/linux/amba/bus.h @@ -30,7 +30,6 @@ struct amba_device { struct device dev; struct resource res; struct clk *pclk; - u64 dma_mask; unsigned int periphid; unsigned int irq[AMBA_NR_IRQS]; }; @@ -131,7 +130,6 @@ struct amba_device name##_device = { \ struct amba_device name##_device = { \ .dev = __AMBA_DEV(busid, data, ~0ULL), \ .res = DEFINE_RES_MEM(base, SZ_4K), \ - .dma_mask = ~0ULL, \ .irq = irqs, \ .periphid = id, \ } diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 3a8d0a2af607..fd4aee29ad10 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -97,6 +97,30 @@ static inline int dma_set_coherent_mask(struct device *dev, u64 mask) } #endif +/* + * Set both the DMA mask and the coherent DMA mask to the same thing. + * Note that we don't check the return value from dma_set_coherent_mask() + * as the DMA API guarantees that the coherent DMA mask can be set to + * the same or smaller than the streaming DMA mask. + */ +static inline int dma_set_mask_and_coherent(struct device *dev, u64 mask) +{ + int rc = dma_set_mask(dev, mask); + if (rc == 0) + dma_set_coherent_mask(dev, mask); + return rc; +} + +/* + * Similar to the above, except it deals with the case where the device + * does not have dev->dma_mask appropriately setup. + */ +static inline int dma_coerce_mask_and_coherent(struct device *dev, u64 mask) +{ + dev->dma_mask = &dev->coherent_dma_mask; + return dma_set_mask_and_coherent(dev, mask); +} + extern u64 dma_get_required_mask(struct device *dev); static inline unsigned int dma_get_max_seg_size(struct device *dev) @@ -129,6 +153,13 @@ static inline int dma_set_seg_boundary(struct device *dev, unsigned long mask) return -EIO; } +#ifndef dma_max_pfn +static inline unsigned long dma_max_pfn(struct device *dev) +{ + return *dev->dma_mask >> PAGE_SHIFT; +} +#endif + static inline void *dma_zalloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag) { diff --git a/include/linux/filter.h b/include/linux/filter.h index a6ac84871d6d..ff4e40cd45b1 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -6,6 +6,7 @@ #include <linux/atomic.h> #include <linux/compat.h> +#include <linux/workqueue.h> #include <uapi/linux/filter.h> #ifdef CONFIG_COMPAT @@ -25,15 +26,19 @@ struct sk_filter { atomic_t refcnt; unsigned int len; /* Number of filter blocks */ + struct rcu_head rcu; unsigned int (*bpf_func)(const struct sk_buff *skb, const struct sock_filter *filter); - struct rcu_head rcu; - struct sock_filter insns[0]; + union { + struct sock_filter insns[0]; + struct work_struct work; + }; }; -static inline unsigned int sk_filter_len(const struct sk_filter *fp) +static inline unsigned int sk_filter_size(unsigned int proglen) { - return fp->len * sizeof(struct sock_filter) + sizeof(*fp); + return max(sizeof(struct sk_filter), + offsetof(struct sk_filter, insns[proglen])); } extern int sk_filter(struct sock *sk, struct sk_buff *skb); @@ -67,11 +72,13 @@ static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen, } #define SK_RUN_FILTER(FILTER, SKB) (*FILTER->bpf_func)(SKB, FILTER->insns) #else +#include <linux/slab.h> static inline void bpf_jit_compile(struct sk_filter *fp) { } static inline void bpf_jit_free(struct sk_filter *fp) { + kfree(fp); } #define SK_RUN_FILTER(FILTER, SKB) sk_run_filter(SKB, FILTER->insns) #endif diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index 19c19a5eee29..f6c82de12541 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -34,9 +34,9 @@ struct ipc_namespace { int sem_ctls[4]; int used_sems; - int msg_ctlmax; - int msg_ctlmnb; - int msg_ctlmni; + unsigned int msg_ctlmax; + unsigned int msg_ctlmnb; + unsigned int msg_ctlmni; atomic_t msg_bytes; atomic_t msg_hdrs; int auto_msgmni; diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h index 0e5d9ecdb2b6..cac496b1e279 100644 --- a/include/linux/irqchip/arm-gic.h +++ b/include/linux/irqchip/arm-gic.h @@ -31,6 +31,8 @@ #define GIC_DIST_TARGET 0x800 #define GIC_DIST_CONFIG 0xc00 #define GIC_DIST_SOFTINT 0xf00 +#define GIC_DIST_SGI_PENDING_CLEAR 0xf10 +#define GIC_DIST_SGI_PENDING_SET 0xf20 #define GICH_HCR 0x0 #define GICH_VTR 0x4 @@ -74,6 +76,11 @@ static inline void gic_init(unsigned int nr, int start, gic_init_bases(nr, start, dist, cpu, 0, NULL); } +void gic_send_sgi(unsigned int cpu_id, unsigned int irq); +int gic_get_cpu_id(unsigned int cpu); +void gic_migrate_target(unsigned int new_cpu_id); +unsigned long gic_get_sgir_physaddr(void); + #endif /* __ASSEMBLY */ #endif diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index ecc82b37c4cc..b3e7a667e03c 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -137,47 +137,24 @@ extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, extern void mem_cgroup_replace_page_cache(struct page *oldpage, struct page *newpage); -/** - * mem_cgroup_toggle_oom - toggle the memcg OOM killer for the current task - * @new: true to enable, false to disable - * - * Toggle whether a failed memcg charge should invoke the OOM killer - * or just return -ENOMEM. Returns the previous toggle state. - * - * NOTE: Any path that enables the OOM killer before charging must - * call mem_cgroup_oom_synchronize() afterward to finalize the - * OOM handling and clean up. - */ -static inline bool mem_cgroup_toggle_oom(bool new) +static inline void mem_cgroup_oom_enable(void) { - bool old; - - old = current->memcg_oom.may_oom; - current->memcg_oom.may_oom = new; - - return old; + WARN_ON(current->memcg_oom.may_oom); + current->memcg_oom.may_oom = 1; } -static inline void mem_cgroup_enable_oom(void) +static inline void mem_cgroup_oom_disable(void) { - bool old = mem_cgroup_toggle_oom(true); - - WARN_ON(old == true); -} - -static inline void mem_cgroup_disable_oom(void) -{ - bool old = mem_cgroup_toggle_oom(false); - - WARN_ON(old == false); + WARN_ON(!current->memcg_oom.may_oom); + current->memcg_oom.may_oom = 0; } static inline bool task_in_memcg_oom(struct task_struct *p) { - return p->memcg_oom.in_memcg_oom; + return p->memcg_oom.memcg; } -bool mem_cgroup_oom_synchronize(void); +bool mem_cgroup_oom_synchronize(bool wait); #ifdef CONFIG_MEMCG_SWAP extern int do_swap_account; @@ -402,16 +379,11 @@ static inline void mem_cgroup_end_update_page_stat(struct page *page, { } -static inline bool mem_cgroup_toggle_oom(bool new) -{ - return false; -} - -static inline void mem_cgroup_enable_oom(void) +static inline void mem_cgroup_oom_enable(void) { } -static inline void mem_cgroup_disable_oom(void) +static inline void mem_cgroup_oom_disable(void) { } @@ -420,7 +392,7 @@ static inline bool task_in_memcg_oom(struct task_struct *p) return false; } -static inline bool mem_cgroup_oom_synchronize(void) +static inline bool mem_cgroup_oom_synchronize(bool wait) { return false; } diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 68029b30c3dc..5eb4e31af22b 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -181,7 +181,7 @@ enum { MLX5_DEV_CAP_FLAG_TLP_HINTS = 1LL << 39, MLX5_DEV_CAP_FLAG_SIG_HAND_OVER = 1LL << 40, MLX5_DEV_CAP_FLAG_DCT = 1LL << 41, - MLX5_DEV_CAP_FLAG_CMDIF_CSUM = 1LL << 46, + MLX5_DEV_CAP_FLAG_CMDIF_CSUM = 3LL << 46, }; enum { @@ -417,7 +417,7 @@ struct mlx5_init_seg { struct health_buffer health; __be32 rsvd2[884]; __be32 health_counter; - __be32 rsvd3[1023]; + __be32 rsvd3[1019]; __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 8888381fc150..6b8c496572c8 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -82,7 +82,7 @@ enum { }; enum { - MLX5_MAX_EQ_NAME = 20 + MLX5_MAX_EQ_NAME = 32 }; enum { @@ -747,8 +747,7 @@ static inline u32 mlx5_idx_to_mkey(u32 mkey_idx) enum { MLX5_PROF_MASK_QP_SIZE = (u64)1 << 0, - MLX5_PROF_MASK_CMDIF_CSUM = (u64)1 << 1, - MLX5_PROF_MASK_MR_CACHE = (u64)1 << 2, + MLX5_PROF_MASK_MR_CACHE = (u64)1 << 1, }; enum { @@ -758,7 +757,6 @@ enum { struct mlx5_profile { u64 mask; u32 log_max_qp; - int cmdif_csum; struct { int size; int limit; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3de49aca4519..25f5d2d11e7c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2264,11 +2264,12 @@ static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index) } #ifdef CONFIG_XPS -extern int netif_set_xps_queue(struct net_device *dev, struct cpumask *mask, +extern int netif_set_xps_queue(struct net_device *dev, + const struct cpumask *mask, u16 index); #else static inline int netif_set_xps_queue(struct net_device *dev, - struct cpumask *mask, + const struct cpumask *mask, u16 index) { return 0; diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index f3c7c24bec1c..fbfdb9d8d3a7 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -24,7 +24,8 @@ struct netpoll { struct net_device *dev; char dev_name[IFNAMSIZ]; const char *name; - void (*rx_hook)(struct netpoll *, int, char *, int); + void (*rx_skb_hook)(struct netpoll *np, int source, struct sk_buff *skb, + int offset, int len); union inet_addr local_ip, remote_ip; bool ipv6; @@ -41,7 +42,7 @@ struct netpoll_info { unsigned long rx_flags; spinlock_t rx_lock; struct semaphore dev_lock; - struct list_head rx_np; /* netpolls that registered an rx_hook */ + struct list_head rx_np; /* netpolls that registered an rx_skb_hook */ struct sk_buff_head neigh_tx; /* list of neigh requests to reply to */ struct sk_buff_head txq; diff --git a/include/linux/of_reserved_mem.h b/include/linux/of_reserved_mem.h deleted file mode 100644 index c84128255814..000000000000 --- a/include/linux/of_reserved_mem.h +++ /dev/null @@ -1,14 +0,0 @@ -#ifndef __OF_RESERVED_MEM_H -#define __OF_RESERVED_MEM_H - -#ifdef CONFIG_OF_RESERVED_MEM -void of_reserved_mem_device_init(struct device *dev); -void of_reserved_mem_device_release(struct device *dev); -void early_init_dt_scan_reserved_mem(void); -#else -static inline void of_reserved_mem_device_init(struct device *dev) { } -static inline void of_reserved_mem_device_release(struct device *dev) { } -static inline void early_init_dt_scan_reserved_mem(void) { } -#endif - -#endif /* __OF_RESERVED_MEM_H */ diff --git a/include/linux/percpu.h b/include/linux/percpu.h index cc88172c7d9a..c74088ab103b 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -332,7 +332,7 @@ do { \ #endif #ifndef this_cpu_sub -# define this_cpu_sub(pcp, val) this_cpu_add((pcp), -(val)) +# define this_cpu_sub(pcp, val) this_cpu_add((pcp), -(typeof(pcp))(val)) #endif #ifndef this_cpu_inc @@ -418,7 +418,7 @@ do { \ # define this_cpu_add_return(pcp, val) __pcpu_size_call_return2(this_cpu_add_return_, pcp, val) #endif -#define this_cpu_sub_return(pcp, val) this_cpu_add_return(pcp, -(val)) +#define this_cpu_sub_return(pcp, val) this_cpu_add_return(pcp, -(typeof(pcp))(val)) #define this_cpu_inc_return(pcp) this_cpu_add_return(pcp, 1) #define this_cpu_dec_return(pcp) this_cpu_add_return(pcp, -1) @@ -586,7 +586,7 @@ do { \ #endif #ifndef __this_cpu_sub -# define __this_cpu_sub(pcp, val) __this_cpu_add((pcp), -(val)) +# define __this_cpu_sub(pcp, val) __this_cpu_add((pcp), -(typeof(pcp))(val)) #endif #ifndef __this_cpu_inc @@ -668,7 +668,7 @@ do { \ __pcpu_size_call_return2(__this_cpu_add_return_, pcp, val) #endif -#define __this_cpu_sub_return(pcp, val) __this_cpu_add_return(pcp, -(val)) +#define __this_cpu_sub_return(pcp, val) __this_cpu_add_return(pcp, -(typeof(pcp))(val)) #define __this_cpu_inc_return(pcp) __this_cpu_add_return(pcp, 1) #define __this_cpu_dec_return(pcp) __this_cpu_add_return(pcp, -1) diff --git a/include/linux/sched.h b/include/linux/sched.h index 6682da36b293..e27baeeda3f4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1394,11 +1394,10 @@ struct task_struct { } memcg_batch; unsigned int memcg_kmem_skip_account; struct memcg_oom_info { + struct mem_cgroup *memcg; + gfp_t gfp_mask; + int order; unsigned int may_oom:1; - unsigned int in_memcg_oom:1; - unsigned int oom_locked:1; - int wakeups; - struct mem_cgroup *wait_on_memcg; } memcg_oom; #endif #ifdef CONFIG_UPROBES diff --git a/include/linux/usb/usb_phy_gen_xceiv.h b/include/linux/usb/usb_phy_gen_xceiv.h index f9a7e7bc925b..11d85b9c1b08 100644 --- a/include/linux/usb/usb_phy_gen_xceiv.h +++ b/include/linux/usb/usb_phy_gen_xceiv.h @@ -12,7 +12,7 @@ struct usb_phy_gen_xceiv_platform_data { unsigned int needs_reset:1; }; -#if IS_ENABLED(CONFIG_NOP_USB_XCEIV) +#if defined(CONFIG_NOP_USB_XCEIV) || (defined(CONFIG_NOP_USB_XCEIV_MODULE) && defined(MODULE)) /* sometimes transceivers are accessed only through e.g. ULPI */ extern void usb_nop_xceiv_register(void); extern void usb_nop_xceiv_unregister(void); diff --git a/include/linux/usb_usual.h b/include/linux/usb_usual.h index bf99cd01be20..630356866030 100644 --- a/include/linux/usb_usual.h +++ b/include/linux/usb_usual.h @@ -66,7 +66,9 @@ US_FLAG(INITIAL_READ10, 0x00100000) \ /* Initial READ(10) (and others) must be retried */ \ US_FLAG(WRITE_CACHE, 0x00200000) \ - /* Write Cache status is not available */ + /* Write Cache status is not available */ \ + US_FLAG(NEEDS_CAP16, 0x00400000) + /* cannot handle READ_CAPACITY_10 */ #define US_FLAG(name, value) US_FL_##name = value , enum { US_DO_ALL_FLAGS }; diff --git a/include/linux/yam.h b/include/linux/yam.h index 7fe28228b274..512cdc2fb80f 100644 --- a/include/linux/yam.h +++ b/include/linux/yam.h @@ -77,6 +77,6 @@ struct yamdrv_ioctl_cfg { struct yamdrv_ioctl_mcs { int cmd; - int bitrate; + unsigned int bitrate; unsigned char bits[YAM_FPGA_SIZE]; }; diff --git a/include/net/cipso_ipv4.h b/include/net/cipso_ipv4.h index a7a683e30b64..a8c2ef6d3b93 100644 --- a/include/net/cipso_ipv4.h +++ b/include/net/cipso_ipv4.h @@ -290,6 +290,7 @@ static inline int cipso_v4_validate(const struct sk_buff *skb, unsigned char err_offset = 0; u8 opt_len = opt[1]; u8 opt_iter; + u8 tag_len; if (opt_len < 8) { err_offset = 1; @@ -302,11 +303,12 @@ static inline int cipso_v4_validate(const struct sk_buff *skb, } for (opt_iter = 6; opt_iter < opt_len;) { - if (opt[opt_iter + 1] > (opt_len - opt_iter)) { + tag_len = opt[opt_iter + 1]; + if ((tag_len == 0) || (opt[opt_iter + 1] > (opt_len - opt_iter))) { err_offset = opt_iter + 1; goto out; } - opt_iter += opt[opt_iter + 1]; + opt_iter += tag_len; } out: diff --git a/include/net/dst.h b/include/net/dst.h index 3bc4865f8267..3c4c944096c9 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -479,10 +479,22 @@ static inline struct dst_entry *xfrm_lookup(struct net *net, { return dst_orig; } + +static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst) +{ + return NULL; +} + #else extern struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, struct sock *sk, int flags); + +/* skb attached with this dst needs transformation if dst->xfrm is valid */ +static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst) +{ + return dst->xfrm; +} #endif #endif /* _NET_DST_H */ diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 48ec25a7fcb6..5e661a979694 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -165,6 +165,7 @@ static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst) static inline void rt6_clean_expires(struct rt6_info *rt) { rt->rt6i_flags &= ~RTF_EXPIRES; + rt->dst.expires = 0; } static inline void rt6_set_expires(struct rt6_info *rt, unsigned long expires) diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index f525e7038cca..2b786b7e3585 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -194,11 +194,9 @@ static inline int ip6_skb_dst_mtu(struct sk_buff *skb) skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb)); } -static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt, struct in6_addr *dest) +static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt) { - if (rt->rt6i_flags & RTF_GATEWAY) - return &rt->rt6i_gateway; - return dest; + return &rt->rt6i_gateway; } #endif diff --git a/include/net/mac802154.h b/include/net/mac802154.h index d0d11df9cba1..807d6b7a943f 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -133,7 +133,7 @@ struct ieee802154_ops { /* Basic interface to register ieee802154 device */ struct ieee802154_dev * -ieee802154_alloc_device(size_t priv_data_lex, struct ieee802154_ops *ops); +ieee802154_alloc_device(size_t priv_data_len, struct ieee802154_ops *ops); void ieee802154_free_device(struct ieee802154_dev *dev); int ieee802154_register_device(struct ieee802154_dev *dev); void ieee802154_unregister_device(struct ieee802154_dev *dev); diff --git a/include/net/sock.h b/include/net/sock.h index 1d37a8086bed..808cbc2ec6c1 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1630,16 +1630,14 @@ static inline void sk_filter_release(struct sk_filter *fp) static inline void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp) { - unsigned int size = sk_filter_len(fp); - - atomic_sub(size, &sk->sk_omem_alloc); + atomic_sub(sk_filter_size(fp->len), &sk->sk_omem_alloc); sk_filter_release(fp); } static inline void sk_filter_charge(struct sock *sk, struct sk_filter *fp) { atomic_inc(&fp->refcnt); - atomic_add(sk_filter_len(fp), &sk->sk_omem_alloc); + atomic_add(sk_filter_size(fp->len), &sk->sk_omem_alloc); } /* diff --git a/include/sound/rcar_snd.h b/include/sound/rcar_snd.h index fe66533e9b7a..fb0a312bcb81 100644 --- a/include/sound/rcar_snd.h +++ b/include/sound/rcar_snd.h @@ -68,6 +68,7 @@ struct rsnd_scu_platform_info { * * A : generation */ +#define RSND_GEN_MASK (0xF << 0) #define RSND_GEN1 (1 << 0) /* fixme */ #define RSND_GEN2 (2 << 0) /* fixme */ diff --git a/include/trace/events/power_cpu_migrate.h b/include/trace/events/power_cpu_migrate.h new file mode 100644 index 000000000000..f76dd4de625e --- /dev/null +++ b/include/trace/events/power_cpu_migrate.h @@ -0,0 +1,67 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM power + +#if !defined(_TRACE_POWER_CPU_MIGRATE_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_POWER_CPU_MIGRATE_H + +#include <linux/tracepoint.h> + +#define __cpu_migrate_proto \ + TP_PROTO(u64 timestamp, \ + u32 cpu_hwid) +#define __cpu_migrate_args \ + TP_ARGS(timestamp, \ + cpu_hwid) + +DECLARE_EVENT_CLASS(cpu_migrate, + + __cpu_migrate_proto, + __cpu_migrate_args, + + TP_STRUCT__entry( + __field(u64, timestamp ) + __field(u32, cpu_hwid ) + ), + + TP_fast_assign( + __entry->timestamp = timestamp; + __entry->cpu_hwid = cpu_hwid; + ), + + TP_printk("timestamp=%llu cpu_hwid=0x%08lX", + (unsigned long long)__entry->timestamp, + (unsigned long)__entry->cpu_hwid + ) +); + +#define __define_cpu_migrate_event(name) \ + DEFINE_EVENT(cpu_migrate, cpu_migrate_##name, \ + __cpu_migrate_proto, \ + __cpu_migrate_args \ + ) + +__define_cpu_migrate_event(begin); +__define_cpu_migrate_event(finish); +__define_cpu_migrate_event(current); + +#undef __define_cpu_migrate +#undef __cpu_migrate_proto +#undef __cpu_migrate_args + +/* This file can get included multiple times, TRACE_HEADER_MULTI_READ at top */ +#ifndef _PWR_CPU_MIGRATE_EVENT_AVOID_DOUBLE_DEFINING +#define _PWR_CPU_MIGRATE_EVENT_AVOID_DOUBLE_DEFINING + +/* + * Set from_phys_cpu and to_phys_cpu to CPU_MIGRATE_ALL_CPUS to indicate + * a whole-cluster migration: + */ +#define CPU_MIGRATE_ALL_CPUS 0x80000000U +#endif + +#endif /* _TRACE_POWER_CPU_MIGRATE_H */ + +/* This part must be outside protection */ +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE power_cpu_migrate +#include <trace/define_trace.h> diff --git a/include/trace/events/target.h b/include/trace/events/target.h index aef8fc354025..da9cc0f05c93 100644 --- a/include/trace/events/target.h +++ b/include/trace/events/target.h @@ -144,7 +144,7 @@ TRACE_EVENT(target_sequencer_start, ), TP_fast_assign( - __entry->unpacked_lun = cmd->se_lun->unpacked_lun; + __entry->unpacked_lun = cmd->orig_fe_lun; __entry->opcode = cmd->t_task_cdb[0]; __entry->data_length = cmd->data_length; __entry->task_attribute = cmd->sam_task_attr; @@ -182,7 +182,7 @@ TRACE_EVENT(target_cmd_complete, ), TP_fast_assign( - __entry->unpacked_lun = cmd->se_lun->unpacked_lun; + __entry->unpacked_lun = cmd->orig_fe_lun; __entry->opcode = cmd->t_task_cdb[0]; __entry->data_length = cmd->data_length; __entry->task_attribute = cmd->sam_task_attr; diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h index 550811712f78..28acbaf4a81e 100644 --- a/include/uapi/drm/drm_mode.h +++ b/include/uapi/drm/drm_mode.h @@ -223,6 +223,8 @@ struct drm_mode_get_connector { __u32 connection; __u32 mm_width, mm_height; /**< HxW in millimeters */ __u32 subpixel; + + __u32 pad; }; #define DRM_MODE_PROP_PENDING (1<<0) diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 009a655a5d35..2fc1602e23bb 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -456,13 +456,15 @@ struct perf_event_mmap_page { /* * Control data for the mmap() data buffer. * - * User-space reading the @data_head value should issue an rmb(), on - * SMP capable platforms, after reading this value -- see - * perf_event_wakeup(). + * User-space reading the @data_head value should issue an smp_rmb(), + * after reading this value. * * When the mapping is PROT_WRITE the @data_tail value should be - * written by userspace to reflect the last read data. In this case - * the kernel will not over-write unread data. + * written by userspace to reflect the last read data, after issueing + * an smp_mb() to separate the data read from the ->data_tail store. + * In this case the kernel will not over-write unread data. + * + * See perf_output_put_handle() for the data ordering. */ __u64 data_head; /* head in the data section */ __u64 data_tail; /* user-space written tail */ diff --git a/include/uapi/linux/tc_act/Kbuild b/include/uapi/linux/tc_act/Kbuild index 0623ec4e728f..56f121605c99 100644 --- a/include/uapi/linux/tc_act/Kbuild +++ b/include/uapi/linux/tc_act/Kbuild @@ -1,5 +1,6 @@ # UAPI Header export list header-y += tc_csum.h +header-y += tc_defact.h header-y += tc_gact.h header-y += tc_ipt.h header-y += tc_mirred.h diff --git a/include/linux/tc_act/tc_defact.h b/include/uapi/linux/tc_act/tc_defact.h index 6f65d07c7ce2..17dddb40f740 100644 --- a/include/linux/tc_act/tc_defact.h +++ b/include/uapi/linux/tc_act/tc_defact.h @@ -6,7 +6,7 @@ struct tc_defact { tc_gen; }; - + enum { TCA_DEF_UNSPEC, TCA_DEF_TM, diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h index 0b233c56b0e4..e3ddd86c90a6 100644 --- a/include/uapi/rdma/ib_user_verbs.h +++ b/include/uapi/rdma/ib_user_verbs.h @@ -87,8 +87,10 @@ enum { IB_USER_VERBS_CMD_CLOSE_XRCD, IB_USER_VERBS_CMD_CREATE_XSRQ, IB_USER_VERBS_CMD_OPEN_QP, +#ifdef CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING IB_USER_VERBS_CMD_CREATE_FLOW = IB_USER_VERBS_CMD_THRESHOLD, IB_USER_VERBS_CMD_DESTROY_FLOW +#endif /* CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING */ }; /* @@ -126,6 +128,7 @@ struct ib_uverbs_cmd_hdr { __u16 out_words; }; +#ifdef CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING struct ib_uverbs_cmd_hdr_ex { __u32 command; __u16 in_words; @@ -134,6 +137,7 @@ struct ib_uverbs_cmd_hdr_ex { __u16 provider_out_words; __u32 cmd_hdr_reserved; }; +#endif /* CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING */ struct ib_uverbs_get_context { __u64 response; @@ -696,6 +700,7 @@ struct ib_uverbs_detach_mcast { __u64 driver_data[0]; }; +#ifdef CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING struct ib_kern_eth_filter { __u8 dst_mac[6]; __u8 src_mac[6]; @@ -780,6 +785,7 @@ struct ib_uverbs_destroy_flow { __u32 comp_mask; __u32 flow_handle; }; +#endif /* CONFIG_INFINIBAND_EXPERIMENTAL_UVERBS_FLOW_STEERING */ struct ib_uverbs_create_srq { __u64 response; diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c index 130dfece27ac..b0e99deb6d05 100644 --- a/ipc/ipc_sysctl.c +++ b/ipc/ipc_sysctl.c @@ -62,7 +62,7 @@ static int proc_ipc_dointvec_minmax_orphans(ctl_table *table, int write, return err; } -static int proc_ipc_callback_dointvec(ctl_table *table, int write, +static int proc_ipc_callback_dointvec_minmax(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table ipc_table; @@ -72,7 +72,7 @@ static int proc_ipc_callback_dointvec(ctl_table *table, int write, memcpy(&ipc_table, table, sizeof(ipc_table)); ipc_table.data = get_ipc(table); - rc = proc_dointvec(&ipc_table, write, buffer, lenp, ppos); + rc = proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos); if (write && !rc && lenp_bef == *lenp) /* @@ -152,15 +152,13 @@ static int proc_ipcauto_dointvec_minmax(ctl_table *table, int write, #define proc_ipc_dointvec NULL #define proc_ipc_dointvec_minmax NULL #define proc_ipc_dointvec_minmax_orphans NULL -#define proc_ipc_callback_dointvec NULL +#define proc_ipc_callback_dointvec_minmax NULL #define proc_ipcauto_dointvec_minmax NULL #endif static int zero; static int one = 1; -#ifdef CONFIG_CHECKPOINT_RESTORE static int int_max = INT_MAX; -#endif static struct ctl_table ipc_kern_table[] = { { @@ -198,21 +196,27 @@ static struct ctl_table ipc_kern_table[] = { .data = &init_ipc_ns.msg_ctlmax, .maxlen = sizeof (init_ipc_ns.msg_ctlmax), .mode = 0644, - .proc_handler = proc_ipc_dointvec, + .proc_handler = proc_ipc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &int_max, }, { .procname = "msgmni", .data = &init_ipc_ns.msg_ctlmni, .maxlen = sizeof (init_ipc_ns.msg_ctlmni), .mode = 0644, - .proc_handler = proc_ipc_callback_dointvec, + .proc_handler = proc_ipc_callback_dointvec_minmax, + .extra1 = &zero, + .extra2 = &int_max, }, { .procname = "msgmnb", .data = &init_ipc_ns.msg_ctlmnb, .maxlen = sizeof (init_ipc_ns.msg_ctlmnb), .mode = 0644, - .proc_handler = proc_ipc_dointvec, + .proc_handler = proc_ipc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &int_max, }, { .procname = "sem", diff --git a/ipc/sem.c b/ipc/sem.c index 8c4f59b0204a..db9d241af133 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -1282,6 +1282,12 @@ static int semctl_setval(struct ipc_namespace *ns, int semid, int semnum, sem_lock(sma, NULL, -1); + if (sma->sem_perm.deleted) { + sem_unlock(sma, -1); + rcu_read_unlock(); + return -EIDRM; + } + curr = &sma->sem_base[semnum]; ipc_assert_locked_object(&sma->sem_perm); @@ -1336,12 +1342,14 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, int i; sem_lock(sma, NULL, -1); + if (sma->sem_perm.deleted) { + err = -EIDRM; + goto out_unlock; + } if(nsems > SEMMSL_FAST) { if (!ipc_rcu_getref(sma)) { - sem_unlock(sma, -1); - rcu_read_unlock(); err = -EIDRM; - goto out_free; + goto out_unlock; } sem_unlock(sma, -1); rcu_read_unlock(); @@ -1354,10 +1362,8 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, rcu_read_lock(); sem_lock_and_putref(sma); if (sma->sem_perm.deleted) { - sem_unlock(sma, -1); - rcu_read_unlock(); err = -EIDRM; - goto out_free; + goto out_unlock; } } for (i = 0; i < sma->sem_nsems; i++) @@ -1375,8 +1381,8 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, struct sem_undo *un; if (!ipc_rcu_getref(sma)) { - rcu_read_unlock(); - return -EIDRM; + err = -EIDRM; + goto out_rcu_wakeup; } rcu_read_unlock(); @@ -1404,10 +1410,8 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, rcu_read_lock(); sem_lock_and_putref(sma); if (sma->sem_perm.deleted) { - sem_unlock(sma, -1); - rcu_read_unlock(); err = -EIDRM; - goto out_free; + goto out_unlock; } for (i = 0; i < nsems; i++) @@ -1431,6 +1435,10 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, goto out_rcu_wakeup; sem_lock(sma, NULL, -1); + if (sma->sem_perm.deleted) { + err = -EIDRM; + goto out_unlock; + } curr = &sma->sem_base[semnum]; switch (cmd) { @@ -1836,6 +1844,10 @@ SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops, if (error) goto out_rcu_wakeup; + error = -EIDRM; + locknum = sem_lock(sma, sops, nsops); + if (sma->sem_perm.deleted) + goto out_unlock_free; /* * semid identifiers are not unique - find_alloc_undo may have * allocated an undo structure, it was invalidated by an RMID @@ -1843,8 +1855,6 @@ SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops, * This case can be detected checking un->semid. The existence of * "un" itself is guaranteed by rcu. */ - error = -EIDRM; - locknum = sem_lock(sma, sops, nsops); if (un && un->semid == -1) goto out_unlock_free; @@ -2057,6 +2067,12 @@ void exit_sem(struct task_struct *tsk) } sem_lock(sma, NULL, -1); + /* exit_sem raced with IPC_RMID, nothing to do */ + if (sma->sem_perm.deleted) { + sem_unlock(sma, -1); + rcu_read_unlock(); + continue; + } un = __lookup_undo(ulp, semid); if (un == NULL) { /* exit_sem raced with IPC_RMID+semget() that created diff --git a/ipc/util.c b/ipc/util.c index fdb8ae740775..7684f41bce76 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -17,12 +17,27 @@ * Pavel Emelianov <xemul@openvz.org> * * General sysv ipc locking scheme: - * when doing ipc id lookups, take the ids->rwsem - * rcu_read_lock() - * obtain the ipc object (kern_ipc_perm) - * perform security, capabilities, auditing and permission checks, etc. - * acquire the ipc lock (kern_ipc_perm.lock) throught ipc_lock_object() - * perform data updates (ie: SET, RMID, LOCK/UNLOCK commands) + * rcu_read_lock() + * obtain the ipc object (kern_ipc_perm) by looking up the id in an idr + * tree. + * - perform initial checks (capabilities, auditing and permission, + * etc). + * - perform read-only operations, such as STAT, INFO commands. + * acquire the ipc lock (kern_ipc_perm.lock) through + * ipc_lock_object() + * - perform data updates, such as SET, RMID commands and + * mechanism-specific operations (semop/semtimedop, + * msgsnd/msgrcv, shmat/shmdt). + * drop the ipc lock, through ipc_unlock_object(). + * rcu_read_unlock() + * + * The ids->rwsem must be taken when: + * - creating, removing and iterating the existing entries in ipc + * identifier sets. + * - iterating through files under /proc/sysvipc/ + * + * Note that sems have a special fast path that avoids kern_ipc_perm.lock - + * see sem_lock(). */ #include <linux/mm.h> diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 2418b6e71a85..8bd9cfdc70d7 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2039,7 +2039,7 @@ static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk, /* @tsk either already exited or can't exit until the end */ if (tsk->flags & PF_EXITING) - continue; + goto next; /* as per above, nr_threads may decrease, but not increase. */ BUG_ON(i >= group_size); @@ -2047,7 +2047,7 @@ static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk, ent.cgrp = task_cgroup_from_root(tsk, root); /* nothing to do if this task is already in the cgroup */ if (ent.cgrp == cgrp) - continue; + goto next; /* * saying GFP_ATOMIC has no effect here because we did prealloc * earlier, but it's good form to communicate our expectations. @@ -2055,7 +2055,7 @@ static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk, retval = flex_array_put(group, i, &ent, GFP_ATOMIC); BUG_ON(retval != 0); i++; - + next: if (!threadgroup) break; } while_each_thread(leader, tsk); @@ -3188,11 +3188,9 @@ css_next_descendant_post(struct cgroup_subsys_state *pos, WARN_ON_ONCE(!rcu_read_lock_held()); - /* if first iteration, visit the leftmost descendant */ - if (!pos) { - next = css_leftmost_descendant(root); - return next != root ? next : NULL; - } + /* if first iteration, visit leftmost descendant which may be @root */ + if (!pos) + return css_leftmost_descendant(root); /* if we visited @root, we're done */ if (pos == root) diff --git a/kernel/events/core.c b/kernel/events/core.c index d49a9d29334c..953c14348375 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6767,6 +6767,10 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr, if (ret) return -EFAULT; + /* disabled for now */ + if (attr->mmap2) + return -EINVAL; + if (attr->__reserved_1) return -EINVAL; diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index cd55144270b5..9c2ddfbf4525 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -87,10 +87,31 @@ again: goto out; /* - * Publish the known good head. Rely on the full barrier implied - * by atomic_dec_and_test() order the rb->head read and this - * write. + * Since the mmap() consumer (userspace) can run on a different CPU: + * + * kernel user + * + * READ ->data_tail READ ->data_head + * smp_mb() (A) smp_rmb() (C) + * WRITE $data READ $data + * smp_wmb() (B) smp_mb() (D) + * STORE ->data_head WRITE ->data_tail + * + * Where A pairs with D, and B pairs with C. + * + * I don't think A needs to be a full barrier because we won't in fact + * write data until we see the store from userspace. So we simply don't + * issue the data WRITE until we observe it. Be conservative for now. + * + * OTOH, D needs to be a full barrier since it separates the data READ + * from the tail WRITE. + * + * For B a WMB is sufficient since it separates two WRITEs, and for C + * an RMB is sufficient since it separates two READs. + * + * See perf_output_begin(). */ + smp_wmb(); rb->user_page->data_head = head; /* @@ -154,9 +175,11 @@ int perf_output_begin(struct perf_output_handle *handle, * Userspace could choose to issue a mb() before updating the * tail pointer. So that all reads will be completed before the * write is issued. + * + * See perf_output_put_handle(). */ tail = ACCESS_ONCE(rb->user_page->data_tail); - smp_rmb(); + smp_mb(); offset = head = local_read(&rb->head); head += size; if (unlikely(!perf_output_space(rb, tail, offset, head))) diff --git a/kernel/mutex.c b/kernel/mutex.c index 6d647aedffea..d24105b1b794 100644 --- a/kernel/mutex.c +++ b/kernel/mutex.c @@ -410,7 +410,7 @@ ww_mutex_set_context_fastpath(struct ww_mutex *lock, static __always_inline int __sched __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, struct lockdep_map *nest_lock, unsigned long ip, - struct ww_acquire_ctx *ww_ctx) + struct ww_acquire_ctx *ww_ctx, const bool use_ww_ctx) { struct task_struct *task = current; struct mutex_waiter waiter; @@ -450,7 +450,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, struct task_struct *owner; struct mspin_node node; - if (!__builtin_constant_p(ww_ctx == NULL) && ww_ctx->acquired > 0) { + if (use_ww_ctx && ww_ctx->acquired > 0) { struct ww_mutex *ww; ww = container_of(lock, struct ww_mutex, base); @@ -480,7 +480,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, if ((atomic_read(&lock->count) == 1) && (atomic_cmpxchg(&lock->count, 1, 0) == 1)) { lock_acquired(&lock->dep_map, ip); - if (!__builtin_constant_p(ww_ctx == NULL)) { + if (use_ww_ctx) { struct ww_mutex *ww; ww = container_of(lock, struct ww_mutex, base); @@ -551,7 +551,7 @@ slowpath: goto err; } - if (!__builtin_constant_p(ww_ctx == NULL) && ww_ctx->acquired > 0) { + if (use_ww_ctx && ww_ctx->acquired > 0) { ret = __mutex_lock_check_stamp(lock, ww_ctx); if (ret) goto err; @@ -575,7 +575,7 @@ skip_wait: lock_acquired(&lock->dep_map, ip); mutex_set_owner(lock); - if (!__builtin_constant_p(ww_ctx == NULL)) { + if (use_ww_ctx) { struct ww_mutex *ww = container_of(lock, struct ww_mutex, base); struct mutex_waiter *cur; @@ -615,7 +615,7 @@ mutex_lock_nested(struct mutex *lock, unsigned int subclass) { might_sleep(); __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, - subclass, NULL, _RET_IP_, NULL); + subclass, NULL, _RET_IP_, NULL, 0); } EXPORT_SYMBOL_GPL(mutex_lock_nested); @@ -625,7 +625,7 @@ _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest) { might_sleep(); __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, - 0, nest, _RET_IP_, NULL); + 0, nest, _RET_IP_, NULL, 0); } EXPORT_SYMBOL_GPL(_mutex_lock_nest_lock); @@ -635,7 +635,7 @@ mutex_lock_killable_nested(struct mutex *lock, unsigned int subclass) { might_sleep(); return __mutex_lock_common(lock, TASK_KILLABLE, - subclass, NULL, _RET_IP_, NULL); + subclass, NULL, _RET_IP_, NULL, 0); } EXPORT_SYMBOL_GPL(mutex_lock_killable_nested); @@ -644,7 +644,7 @@ mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass) { might_sleep(); return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, - subclass, NULL, _RET_IP_, NULL); + subclass, NULL, _RET_IP_, NULL, 0); } EXPORT_SYMBOL_GPL(mutex_lock_interruptible_nested); @@ -682,7 +682,7 @@ __ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) might_sleep(); ret = __mutex_lock_common(&lock->base, TASK_UNINTERRUPTIBLE, - 0, &ctx->dep_map, _RET_IP_, ctx); + 0, &ctx->dep_map, _RET_IP_, ctx, 1); if (!ret && ctx->acquired > 1) return ww_mutex_deadlock_injection(lock, ctx); @@ -697,7 +697,7 @@ __ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) might_sleep(); ret = __mutex_lock_common(&lock->base, TASK_INTERRUPTIBLE, - 0, &ctx->dep_map, _RET_IP_, ctx); + 0, &ctx->dep_map, _RET_IP_, ctx, 1); if (!ret && ctx->acquired > 1) return ww_mutex_deadlock_injection(lock, ctx); @@ -809,28 +809,28 @@ __mutex_lock_slowpath(atomic_t *lock_count) struct mutex *lock = container_of(lock_count, struct mutex, count); __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0, - NULL, _RET_IP_, NULL); + NULL, _RET_IP_, NULL, 0); } static noinline int __sched __mutex_lock_killable_slowpath(struct mutex *lock) { return __mutex_lock_common(lock, TASK_KILLABLE, 0, - NULL, _RET_IP_, NULL); + NULL, _RET_IP_, NULL, 0); } static noinline int __sched __mutex_lock_interruptible_slowpath(struct mutex *lock) { return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, 0, - NULL, _RET_IP_, NULL); + NULL, _RET_IP_, NULL, 0); } static noinline int __sched __ww_mutex_lock_slowpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) { return __mutex_lock_common(&lock->base, TASK_UNINTERRUPTIBLE, 0, - NULL, _RET_IP_, ctx); + NULL, _RET_IP_, ctx, 1); } static noinline int __sched @@ -838,7 +838,7 @@ __ww_mutex_lock_interruptible_slowpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) { return __mutex_lock_common(&lock->base, TASK_INTERRUPTIBLE, 0, - NULL, _RET_IP_, ctx); + NULL, _RET_IP_, ctx, 1); } #endif diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index c9c759d5a15c..0121dab83f43 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -846,7 +846,7 @@ static int software_resume(void) goto Finish; } -late_initcall(software_resume); +late_initcall_sync(software_resume); static const char * const hibernation_modes[] = { diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 38959c866789..662c5798a685 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -33,29 +33,64 @@ struct ce_unbind { int res; }; -/** - * clockevents_delta2ns - Convert a latch value (device ticks) to nanoseconds - * @latch: value to convert - * @evt: pointer to clock event device descriptor - * - * Math helper, returns latch value converted to nanoseconds (bound checked) - */ -u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *evt) +static u64 cev_delta2ns(unsigned long latch, struct clock_event_device *evt, + bool ismax) { u64 clc = (u64) latch << evt->shift; + u64 rnd; if (unlikely(!evt->mult)) { evt->mult = 1; WARN_ON(1); } + rnd = (u64) evt->mult - 1; + + /* + * Upper bound sanity check. If the backwards conversion is + * not equal latch, we know that the above shift overflowed. + */ + if ((clc >> evt->shift) != (u64)latch) + clc = ~0ULL; + + /* + * Scaled math oddities: + * + * For mult <= (1 << shift) we can safely add mult - 1 to + * prevent integer rounding loss. So the backwards conversion + * from nsec to device ticks will be correct. + * + * For mult > (1 << shift), i.e. device frequency is > 1GHz we + * need to be careful. Adding mult - 1 will result in a value + * which when converted back to device ticks can be larger + * than latch by up to (mult - 1) >> shift. For the min_delta + * calculation we still want to apply this in order to stay + * above the minimum device ticks limit. For the upper limit + * we would end up with a latch value larger than the upper + * limit of the device, so we omit the add to stay below the + * device upper boundary. + * + * Also omit the add if it would overflow the u64 boundary. + */ + if ((~0ULL - clc > rnd) && + (!ismax || evt->mult <= (1U << evt->shift))) + clc += rnd; do_div(clc, evt->mult); - if (clc < 1000) - clc = 1000; - if (clc > KTIME_MAX) - clc = KTIME_MAX; - return clc; + /* Deltas less than 1usec are pointless noise */ + return clc > 1000 ? clc : 1000; +} + +/** + * clockevents_delta2ns - Convert a latch value (device ticks) to nanoseconds + * @latch: value to convert + * @evt: pointer to clock event device descriptor + * + * Math helper, returns latch value converted to nanoseconds (bound checked) + */ +u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *evt) +{ + return cev_delta2ns(latch, evt, false); } EXPORT_SYMBOL_GPL(clockevent_delta2ns); @@ -380,8 +415,8 @@ void clockevents_config(struct clock_event_device *dev, u32 freq) sec = 600; clockevents_calc_mult_shift(dev, freq, sec); - dev->min_delta_ns = clockevent_delta2ns(dev->min_delta_ticks, dev); - dev->max_delta_ns = clockevent_delta2ns(dev->max_delta_ticks, dev); + dev->min_delta_ns = cev_delta2ns(dev->min_delta_ticks, dev, false); + dev->max_delta_ns = cev_delta2ns(dev->max_delta_ticks, dev, true); } /** diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 06344d986eb9..094f3152ec2b 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -983,7 +983,7 @@ config DEBUG_KOBJECT config DEBUG_KOBJECT_RELEASE bool "kobject release debugging" - depends on DEBUG_KERNEL + depends on DEBUG_OBJECTS_TIMERS help kobjects are reference counted objects. This means that their last reference count put is not predictable, and the kobject can diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c index 7deeb6297a48..1a53d497a8c5 100644 --- a/lib/percpu-refcount.c +++ b/lib/percpu-refcount.c @@ -53,6 +53,7 @@ int percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release) ref->release = release; return 0; } +EXPORT_SYMBOL_GPL(percpu_ref_init); /** * percpu_ref_cancel_init - cancel percpu_ref_init() @@ -84,6 +85,7 @@ void percpu_ref_cancel_init(struct percpu_ref *ref) free_percpu(ref->pcpu_count); } } +EXPORT_SYMBOL_GPL(percpu_ref_cancel_init); static void percpu_ref_kill_rcu(struct rcu_head *rcu) { @@ -156,3 +158,4 @@ void percpu_ref_kill_and_confirm(struct percpu_ref *ref, call_rcu_sched(&ref->rcu, percpu_ref_kill_rcu); } +EXPORT_SYMBOL_GPL(percpu_ref_kill_and_confirm); diff --git a/lib/scatterlist.c b/lib/scatterlist.c index a685c8a79578..d16fa295ae1d 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -577,7 +577,8 @@ void sg_miter_stop(struct sg_mapping_iter *miter) miter->__offset += miter->consumed; miter->__remaining -= miter->consumed; - if (miter->__flags & SG_MITER_TO_SG) + if ((miter->__flags & SG_MITER_TO_SG) && + !PageSlab(miter->page)) flush_kernel_dcache_page(miter->page); if (miter->__flags & SG_MITER_ATOMIC) { diff --git a/mm/filemap.c b/mm/filemap.c index 1e6aec4a2d2e..ae4846ff4849 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1616,7 +1616,6 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) struct inode *inode = mapping->host; pgoff_t offset = vmf->pgoff; struct page *page; - bool memcg_oom; pgoff_t size; int ret = 0; @@ -1625,11 +1624,7 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) return VM_FAULT_SIGBUS; /* - * Do we have something in the page cache already? Either - * way, try readahead, but disable the memcg OOM killer for it - * as readahead is optional and no errors are propagated up - * the fault stack. The OOM killer is enabled while trying to - * instantiate the faulting page individually below. + * Do we have something in the page cache already? */ page = find_get_page(mapping, offset); if (likely(page) && !(vmf->flags & FAULT_FLAG_TRIED)) { @@ -1637,14 +1632,10 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) * We found the page, so try async readahead before * waiting for the lock. */ - memcg_oom = mem_cgroup_toggle_oom(false); do_async_mmap_readahead(vma, ra, file, page, offset); - mem_cgroup_toggle_oom(memcg_oom); } else if (!page) { /* No page in the page cache at all */ - memcg_oom = mem_cgroup_toggle_oom(false); do_sync_mmap_readahead(vma, ra, file, offset); - mem_cgroup_toggle_oom(memcg_oom); count_vm_event(PGMAJFAULT); mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT); ret = VM_FAULT_MAJOR; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 7489884682d8..cca80d96e509 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1278,64 +1278,90 @@ out: int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pmd_t pmd, pmd_t *pmdp) { + struct anon_vma *anon_vma = NULL; struct page *page; unsigned long haddr = addr & HPAGE_PMD_MASK; + int page_nid = -1, this_nid = numa_node_id(); int target_nid; - int current_nid = -1; - bool migrated; + bool page_locked; + bool migrated = false; spin_lock(&mm->page_table_lock); if (unlikely(!pmd_same(pmd, *pmdp))) goto out_unlock; page = pmd_page(pmd); - get_page(page); - current_nid = page_to_nid(page); + page_nid = page_to_nid(page); count_vm_numa_event(NUMA_HINT_FAULTS); - if (current_nid == numa_node_id()) + if (page_nid == this_nid) count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL); + /* + * Acquire the page lock to serialise THP migrations but avoid dropping + * page_table_lock if at all possible + */ + page_locked = trylock_page(page); target_nid = mpol_misplaced(page, vma, haddr); if (target_nid == -1) { - put_page(page); - goto clear_pmdnuma; + /* If the page was locked, there are no parallel migrations */ + if (page_locked) + goto clear_pmdnuma; + + /* + * Otherwise wait for potential migrations and retry. We do + * relock and check_same as the page may no longer be mapped. + * As the fault is being retried, do not account for it. + */ + spin_unlock(&mm->page_table_lock); + wait_on_page_locked(page); + page_nid = -1; + goto out; } - /* Acquire the page lock to serialise THP migrations */ + /* Page is misplaced, serialise migrations and parallel THP splits */ + get_page(page); spin_unlock(&mm->page_table_lock); - lock_page(page); + if (!page_locked) + lock_page(page); + anon_vma = page_lock_anon_vma_read(page); /* Confirm the PTE did not while locked */ spin_lock(&mm->page_table_lock); if (unlikely(!pmd_same(pmd, *pmdp))) { unlock_page(page); put_page(page); + page_nid = -1; goto out_unlock; } - spin_unlock(&mm->page_table_lock); - /* Migrate the THP to the requested node */ + /* + * Migrate the THP to the requested node, returns with page unlocked + * and pmd_numa cleared. + */ + spin_unlock(&mm->page_table_lock); migrated = migrate_misplaced_transhuge_page(mm, vma, pmdp, pmd, addr, page, target_nid); - if (!migrated) - goto check_same; + if (migrated) + page_nid = target_nid; - task_numa_fault(target_nid, HPAGE_PMD_NR, true); - return 0; - -check_same: - spin_lock(&mm->page_table_lock); - if (unlikely(!pmd_same(pmd, *pmdp))) - goto out_unlock; + goto out; clear_pmdnuma: + BUG_ON(!PageLocked(page)); pmd = pmd_mknonnuma(pmd); set_pmd_at(mm, haddr, pmdp, pmd); VM_BUG_ON(pmd_numa(*pmdp)); update_mmu_cache_pmd(vma, addr, pmdp); + unlock_page(page); out_unlock: spin_unlock(&mm->page_table_lock); - if (current_nid != -1) - task_numa_fault(current_nid, HPAGE_PMD_NR, false); + +out: + if (anon_vma) + page_unlock_anon_vma_read(anon_vma); + + if (page_nid != -1) + task_numa_fault(page_nid, HPAGE_PMD_NR, migrated); + return 0; } @@ -2697,6 +2723,7 @@ void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address, mmun_start = haddr; mmun_end = haddr + HPAGE_PMD_SIZE; +again: mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); spin_lock(&mm->page_table_lock); if (unlikely(!pmd_trans_huge(*pmd))) { @@ -2719,7 +2746,14 @@ void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address, split_huge_page(page); put_page(page); - BUG_ON(pmd_trans_huge(*pmd)); + + /* + * We don't always have down_write of mmap_sem here: a racing + * do_huge_pmd_wp_page() might have copied-on-write to another + * huge page before our split_huge_page() got the anon_vma lock. + */ + if (unlikely(pmd_trans_huge(*pmd))) + goto again; } void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address, diff --git a/mm/hugetlb.c b/mm/hugetlb.c index b49579c7f2a5..0b7656e804d1 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -653,6 +653,7 @@ static void free_huge_page(struct page *page) BUG_ON(page_count(page)); BUG_ON(page_mapcount(page)); restore_reserve = PagePrivate(page); + ClearPagePrivate(page); spin_lock(&hugetlb_lock); hugetlb_cgroup_uncharge_page(hstate_index(h), @@ -695,8 +696,22 @@ static void prep_compound_gigantic_page(struct page *page, unsigned long order) /* we rely on prep_new_huge_page to set the destructor */ set_compound_order(page, order); __SetPageHead(page); + __ClearPageReserved(page); for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) { __SetPageTail(p); + /* + * For gigantic hugepages allocated through bootmem at + * boot, it's safer to be consistent with the not-gigantic + * hugepages and clear the PG_reserved bit from all tail pages + * too. Otherwse drivers using get_user_pages() to access tail + * pages may get the reference counting wrong if they see + * PG_reserved set on a tail page (despite the head page not + * having PG_reserved set). Enforcing this consistency between + * head and tail pages allows drivers to optimize away a check + * on the head page when they need know if put_page() is needed + * after get_user_pages(). + */ + __ClearPageReserved(p); set_page_count(p, 0); p->first_page = page; } @@ -1329,9 +1344,9 @@ static void __init gather_bootmem_prealloc(void) #else page = virt_to_page(m); #endif - __ClearPageReserved(page); WARN_ON(page_count(page) != 1); prep_compound_huge_page(page, h->order); + WARN_ON(PageReserved(page)); prep_new_huge_page(h, page, page_to_nid(page)); /* * If we had gigantic hugepages allocated at boot time, we need diff --git a/mm/list_lru.c b/mm/list_lru.c index 72467914b856..72f9decb0104 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -81,8 +81,9 @@ restart: * decrement nr_to_walk first so that we don't livelock if we * get stuck on large numbesr of LRU_RETRY items */ - if (--(*nr_to_walk) == 0) + if (!*nr_to_walk) break; + --*nr_to_walk; ret = isolate(item, &nlru->lock, cb_arg); switch (ret) { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 1c52ddbc839b..13b9d0f221b8 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -54,6 +54,7 @@ #include <linux/page_cgroup.h> #include <linux/cpu.h> #include <linux/oom.h> +#include <linux/lockdep.h> #include "internal.h" #include <net/sock.h> #include <net/ip.h> @@ -866,6 +867,7 @@ static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg, unsigned long val = 0; int cpu; + get_online_cpus(); for_each_online_cpu(cpu) val += per_cpu(memcg->stat->events[idx], cpu); #ifdef CONFIG_HOTPLUG_CPU @@ -873,6 +875,7 @@ static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg, val += memcg->nocpu_base.events[idx]; spin_unlock(&memcg->pcp_counter_lock); #endif + put_online_cpus(); return val; } @@ -2044,6 +2047,12 @@ static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg, return total; } +#ifdef CONFIG_LOCKDEP +static struct lockdep_map memcg_oom_lock_dep_map = { + .name = "memcg_oom_lock", +}; +#endif + static DEFINE_SPINLOCK(memcg_oom_lock); /* @@ -2081,7 +2090,8 @@ static bool mem_cgroup_oom_trylock(struct mem_cgroup *memcg) } iter->oom_lock = false; } - } + } else + mutex_acquire(&memcg_oom_lock_dep_map, 0, 1, _RET_IP_); spin_unlock(&memcg_oom_lock); @@ -2093,6 +2103,7 @@ static void mem_cgroup_oom_unlock(struct mem_cgroup *memcg) struct mem_cgroup *iter; spin_lock(&memcg_oom_lock); + mutex_release(&memcg_oom_lock_dep_map, 1, _RET_IP_); for_each_mem_cgroup_tree(iter, memcg) iter->oom_lock = false; spin_unlock(&memcg_oom_lock); @@ -2159,110 +2170,59 @@ static void memcg_oom_recover(struct mem_cgroup *memcg) memcg_wakeup_oom(memcg); } -/* - * try to call OOM killer - */ static void mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order) { - bool locked; - int wakeups; - if (!current->memcg_oom.may_oom) return; - - current->memcg_oom.in_memcg_oom = 1; - /* - * As with any blocking lock, a contender needs to start - * listening for wakeups before attempting the trylock, - * otherwise it can miss the wakeup from the unlock and sleep - * indefinitely. This is just open-coded because our locking - * is so particular to memcg hierarchies. + * We are in the middle of the charge context here, so we + * don't want to block when potentially sitting on a callstack + * that holds all kinds of filesystem and mm locks. + * + * Also, the caller may handle a failed allocation gracefully + * (like optional page cache readahead) and so an OOM killer + * invocation might not even be necessary. + * + * That's why we don't do anything here except remember the + * OOM context and then deal with it at the end of the page + * fault when the stack is unwound, the locks are released, + * and when we know whether the fault was overall successful. */ - wakeups = atomic_read(&memcg->oom_wakeups); - mem_cgroup_mark_under_oom(memcg); - - locked = mem_cgroup_oom_trylock(memcg); - - if (locked) - mem_cgroup_oom_notify(memcg); - - if (locked && !memcg->oom_kill_disable) { - mem_cgroup_unmark_under_oom(memcg); - mem_cgroup_out_of_memory(memcg, mask, order); - mem_cgroup_oom_unlock(memcg); - /* - * There is no guarantee that an OOM-lock contender - * sees the wakeups triggered by the OOM kill - * uncharges. Wake any sleepers explicitely. - */ - memcg_oom_recover(memcg); - } else { - /* - * A system call can just return -ENOMEM, but if this - * is a page fault and somebody else is handling the - * OOM already, we need to sleep on the OOM waitqueue - * for this memcg until the situation is resolved. - * Which can take some time because it might be - * handled by a userspace task. - * - * However, this is the charge context, which means - * that we may sit on a large call stack and hold - * various filesystem locks, the mmap_sem etc. and we - * don't want the OOM handler to deadlock on them - * while we sit here and wait. Store the current OOM - * context in the task_struct, then return -ENOMEM. - * At the end of the page fault handler, with the - * stack unwound, pagefault_out_of_memory() will check - * back with us by calling - * mem_cgroup_oom_synchronize(), possibly putting the - * task to sleep. - */ - current->memcg_oom.oom_locked = locked; - current->memcg_oom.wakeups = wakeups; - css_get(&memcg->css); - current->memcg_oom.wait_on_memcg = memcg; - } + css_get(&memcg->css); + current->memcg_oom.memcg = memcg; + current->memcg_oom.gfp_mask = mask; + current->memcg_oom.order = order; } /** * mem_cgroup_oom_synchronize - complete memcg OOM handling + * @handle: actually kill/wait or just clean up the OOM state * - * This has to be called at the end of a page fault if the the memcg - * OOM handler was enabled and the fault is returning %VM_FAULT_OOM. + * This has to be called at the end of a page fault if the memcg OOM + * handler was enabled. * - * Memcg supports userspace OOM handling, so failed allocations must + * Memcg supports userspace OOM handling where failed allocations must * sleep on a waitqueue until the userspace task resolves the * situation. Sleeping directly in the charge context with all kinds * of locks held is not a good idea, instead we remember an OOM state * in the task and mem_cgroup_oom_synchronize() has to be called at - * the end of the page fault to put the task to sleep and clean up the - * OOM state. + * the end of the page fault to complete the OOM handling. * * Returns %true if an ongoing memcg OOM situation was detected and - * finalized, %false otherwise. + * completed, %false otherwise. */ -bool mem_cgroup_oom_synchronize(void) +bool mem_cgroup_oom_synchronize(bool handle) { + struct mem_cgroup *memcg = current->memcg_oom.memcg; struct oom_wait_info owait; - struct mem_cgroup *memcg; + bool locked; /* OOM is global, do not handle */ - if (!current->memcg_oom.in_memcg_oom) - return false; - - /* - * We invoked the OOM killer but there is a chance that a kill - * did not free up any charges. Everybody else might already - * be sleeping, so restart the fault and keep the rampage - * going until some charges are released. - */ - memcg = current->memcg_oom.wait_on_memcg; if (!memcg) - goto out; + return false; - if (test_thread_flag(TIF_MEMDIE) || fatal_signal_pending(current)) - goto out_memcg; + if (!handle) + goto cleanup; owait.memcg = memcg; owait.wait.flags = 0; @@ -2271,13 +2231,25 @@ bool mem_cgroup_oom_synchronize(void) INIT_LIST_HEAD(&owait.wait.task_list); prepare_to_wait(&memcg_oom_waitq, &owait.wait, TASK_KILLABLE); - /* Only sleep if we didn't miss any wakeups since OOM */ - if (atomic_read(&memcg->oom_wakeups) == current->memcg_oom.wakeups) + mem_cgroup_mark_under_oom(memcg); + + locked = mem_cgroup_oom_trylock(memcg); + + if (locked) + mem_cgroup_oom_notify(memcg); + + if (locked && !memcg->oom_kill_disable) { + mem_cgroup_unmark_under_oom(memcg); + finish_wait(&memcg_oom_waitq, &owait.wait); + mem_cgroup_out_of_memory(memcg, current->memcg_oom.gfp_mask, + current->memcg_oom.order); + } else { schedule(); - finish_wait(&memcg_oom_waitq, &owait.wait); -out_memcg: - mem_cgroup_unmark_under_oom(memcg); - if (current->memcg_oom.oom_locked) { + mem_cgroup_unmark_under_oom(memcg); + finish_wait(&memcg_oom_waitq, &owait.wait); + } + + if (locked) { mem_cgroup_oom_unlock(memcg); /* * There is no guarantee that an OOM-lock contender @@ -2286,10 +2258,9 @@ out_memcg: */ memcg_oom_recover(memcg); } +cleanup: + current->memcg_oom.memcg = NULL; css_put(&memcg->css); - current->memcg_oom.wait_on_memcg = NULL; -out: - current->memcg_oom.in_memcg_oom = 0; return true; } @@ -2703,6 +2674,9 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, || fatal_signal_pending(current))) goto bypass; + if (unlikely(task_in_memcg_oom(current))) + goto bypass; + /* * We always charge the cgroup the mm_struct belongs to. * The mm_struct's mem_cgroup changes on task migration if the @@ -2800,8 +2774,10 @@ done: *ptr = memcg; return 0; nomem: - *ptr = NULL; - return -ENOMEM; + if (!(gfp_mask & __GFP_NOFAIL)) { + *ptr = NULL; + return -ENOMEM; + } bypass: *ptr = root_mem_cgroup; return -EINTR; @@ -3806,8 +3782,7 @@ void mem_cgroup_move_account_page_stat(struct mem_cgroup *from, { /* Update stat data for mem_cgroup */ preempt_disable(); - WARN_ON_ONCE(from->stat->count[idx] < nr_pages); - __this_cpu_add(from->stat->count[idx], -nr_pages); + __this_cpu_sub(from->stat->count[idx], nr_pages); __this_cpu_add(to->stat->count[idx], nr_pages); preempt_enable(); } @@ -4983,31 +4958,18 @@ static void mem_cgroup_reparent_charges(struct mem_cgroup *memcg) } while (usage > 0); } -/* - * This mainly exists for tests during the setting of set of use_hierarchy. - * Since this is the very setting we are changing, the current hierarchy value - * is meaningless - */ -static inline bool __memcg_has_children(struct mem_cgroup *memcg) -{ - struct cgroup_subsys_state *pos; - - /* bounce at first found */ - css_for_each_child(pos, &memcg->css) - return true; - return false; -} - -/* - * Must be called with memcg_create_mutex held, unless the cgroup is guaranteed - * to be already dead (as in mem_cgroup_force_empty, for instance). This is - * from mem_cgroup_count_children(), in the sense that we don't really care how - * many children we have; we only need to know if we have any. It also counts - * any memcg without hierarchy as infertile. - */ static inline bool memcg_has_children(struct mem_cgroup *memcg) { - return memcg->use_hierarchy && __memcg_has_children(memcg); + lockdep_assert_held(&memcg_create_mutex); + /* + * The lock does not prevent addition or deletion to the list + * of children, but it prevents a new child from being + * initialized based on this parent in css_online(), so it's + * enough to decide whether hierarchically inherited + * attributes can still be changed or not. + */ + return memcg->use_hierarchy && + !list_empty(&memcg->css.cgroup->children); } /* @@ -5087,7 +5049,7 @@ static int mem_cgroup_hierarchy_write(struct cgroup_subsys_state *css, */ if ((!parent_memcg || !parent_memcg->use_hierarchy) && (val == 1 || val == 0)) { - if (!__memcg_has_children(memcg)) + if (list_empty(&memcg->css.cgroup->children)) memcg->use_hierarchy = val; else retval = -EBUSY; diff --git a/mm/memory.c b/mm/memory.c index ca0003947115..d176154c243f 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -837,6 +837,8 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, */ make_migration_entry_read(&entry); pte = swp_entry_to_pte(entry); + if (pte_swp_soft_dirty(*src_pte)) + pte = pte_swp_mksoft_dirty(pte); set_pte_at(src_mm, addr, src_pte, pte); } } @@ -3519,12 +3521,12 @@ static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma, } int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, - unsigned long addr, int current_nid) + unsigned long addr, int page_nid) { get_page(page); count_vm_numa_event(NUMA_HINT_FAULTS); - if (current_nid == numa_node_id()) + if (page_nid == numa_node_id()) count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL); return mpol_misplaced(page, vma, addr); @@ -3535,7 +3537,7 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, { struct page *page = NULL; spinlock_t *ptl; - int current_nid = -1; + int page_nid = -1; int target_nid; bool migrated = false; @@ -3565,15 +3567,10 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, return 0; } - current_nid = page_to_nid(page); - target_nid = numa_migrate_prep(page, vma, addr, current_nid); + page_nid = page_to_nid(page); + target_nid = numa_migrate_prep(page, vma, addr, page_nid); pte_unmap_unlock(ptep, ptl); if (target_nid == -1) { - /* - * Account for the fault against the current node if it not - * being replaced regardless of where the page is located. - */ - current_nid = numa_node_id(); put_page(page); goto out; } @@ -3581,11 +3578,11 @@ int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, /* Migrate to the requested node */ migrated = migrate_misplaced_page(page, target_nid); if (migrated) - current_nid = target_nid; + page_nid = target_nid; out: - if (current_nid != -1) - task_numa_fault(current_nid, 1, migrated); + if (page_nid != -1) + task_numa_fault(page_nid, 1, migrated); return 0; } @@ -3600,7 +3597,6 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long offset; spinlock_t *ptl; bool numa = false; - int local_nid = numa_node_id(); spin_lock(&mm->page_table_lock); pmd = *pmdp; @@ -3623,9 +3619,10 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, for (addr = _addr + offset; addr < _addr + PMD_SIZE; pte++, addr += PAGE_SIZE) { pte_t pteval = *pte; struct page *page; - int curr_nid = local_nid; + int page_nid = -1; int target_nid; - bool migrated; + bool migrated = false; + if (!pte_present(pteval)) continue; if (!pte_numa(pteval)) @@ -3647,25 +3644,19 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, if (unlikely(page_mapcount(page) != 1)) continue; - /* - * Note that the NUMA fault is later accounted to either - * the node that is currently running or where the page is - * migrated to. - */ - curr_nid = local_nid; - target_nid = numa_migrate_prep(page, vma, addr, - page_to_nid(page)); - if (target_nid == -1) { + page_nid = page_to_nid(page); + target_nid = numa_migrate_prep(page, vma, addr, page_nid); + pte_unmap_unlock(pte, ptl); + if (target_nid != -1) { + migrated = migrate_misplaced_page(page, target_nid); + if (migrated) + page_nid = target_nid; + } else { put_page(page); - continue; } - /* Migrate to the requested node */ - pte_unmap_unlock(pte, ptl); - migrated = migrate_misplaced_page(page, target_nid); - if (migrated) - curr_nid = target_nid; - task_numa_fault(curr_nid, 1, migrated); + if (page_nid != -1) + task_numa_fault(page_nid, 1, migrated); pte = pte_offset_map_lock(mm, pmdp, addr, &ptl); } @@ -3863,15 +3854,21 @@ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, * space. Kernel faults are handled more gracefully. */ if (flags & FAULT_FLAG_USER) - mem_cgroup_enable_oom(); + mem_cgroup_oom_enable(); ret = __handle_mm_fault(mm, vma, address, flags); - if (flags & FAULT_FLAG_USER) - mem_cgroup_disable_oom(); - - if (WARN_ON(task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM))) - mem_cgroup_oom_synchronize(); + if (flags & FAULT_FLAG_USER) { + mem_cgroup_oom_disable(); + /* + * The task may have entered a memcg OOM situation but + * if the allocation error was handled gracefully (no + * VM_FAULT_OOM), there is no need to kill anything. + * Just clean up the OOM state peacefully. + */ + if (task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM)) + mem_cgroup_oom_synchronize(false); + } return ret; } diff --git a/mm/migrate.c b/mm/migrate.c index a26bccd44ccb..c04692774e88 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -161,6 +161,8 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma, get_page(new); pte = pte_mkold(mk_pte(new, vma->vm_page_prot)); + if (pte_swp_soft_dirty(*ptep)) + pte = pte_mksoft_dirty(pte); if (is_write_migration_entry(entry)) pte = pte_mkwrite(pte); #ifdef CONFIG_HUGETLB_PAGE @@ -1713,12 +1715,12 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, unlock_page(new_page); put_page(new_page); /* Free it */ - unlock_page(page); + /* Retake the callers reference and putback on LRU */ + get_page(page); putback_lru_page(page); - - count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR); - isolated = 0; - goto out; + mod_zone_page_state(page_zone(page), + NR_ISOLATED_ANON + page_lru, -HPAGE_PMD_NR); + goto out_fail; } /* @@ -1735,9 +1737,9 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); entry = pmd_mkhuge(entry); - page_add_new_anon_rmap(new_page, vma, haddr); - + pmdp_clear_flush(vma, haddr, pmd); set_pmd_at(mm, haddr, pmd, entry); + page_add_new_anon_rmap(new_page, vma, haddr); update_mmu_cache_pmd(vma, address, &entry); page_remove_rmap(page); /* @@ -1756,7 +1758,6 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, count_vm_events(PGMIGRATE_SUCCESS, HPAGE_PMD_NR); count_vm_numa_events(NUMA_PAGE_MIGRATE, HPAGE_PMD_NR); -out: mod_zone_page_state(page_zone(page), NR_ISOLATED_ANON + page_lru, -HPAGE_PMD_NR); @@ -1765,6 +1766,10 @@ out: out_fail: count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR); out_dropref: + entry = pmd_mknonnuma(entry); + set_pmd_at(mm, haddr, pmd, entry); + update_mmu_cache_pmd(vma, address, &entry); + unlock_page(page); put_page(page); return 0; diff --git a/mm/mprotect.c b/mm/mprotect.c index 94722a4d6b43..412ba2b7326a 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -94,13 +94,16 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, swp_entry_t entry = pte_to_swp_entry(oldpte); if (is_write_migration_entry(entry)) { + pte_t newpte; /* * A protection check is difficult so * just be safe and disable write */ make_migration_entry_read(&entry); - set_pte_at(mm, addr, pte, - swp_entry_to_pte(entry)); + newpte = swp_entry_to_pte(entry); + if (pte_swp_soft_dirty(oldpte)) + newpte = pte_swp_mksoft_dirty(newpte); + set_pte_at(mm, addr, pte, newpte); } pages++; } @@ -145,7 +148,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, split_huge_page_pmd(vma, addr, pmd); else if (change_huge_pmd(vma, pmd, addr, newprot, prot_numa)) { - pages += HPAGE_PMD_NR; + pages++; continue; } /* fall through */ diff --git a/mm/mremap.c b/mm/mremap.c index 91b13d6a16d4..0843feb66f3d 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -25,7 +25,6 @@ #include <asm/uaccess.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> -#include <asm/pgalloc.h> #include "internal.h" @@ -63,10 +62,8 @@ static pmd_t *alloc_new_pmd(struct mm_struct *mm, struct vm_area_struct *vma, return NULL; pmd = pmd_alloc(mm, pud, addr); - if (!pmd) { - pud_free(mm, pud); + if (!pmd) return NULL; - } VM_BUG_ON(pmd_trans_huge(*pmd)); diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 314e9d274381..6738c47f1f72 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -680,7 +680,7 @@ void pagefault_out_of_memory(void) { struct zonelist *zonelist; - if (mem_cgroup_oom_synchronize()) + if (mem_cgroup_oom_synchronize(true)) return; zonelist = node_zonelist(first_online_node, GFP_KERNEL); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index f5236f804aa6..63807583d8e8 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1210,11 +1210,11 @@ static unsigned long dirty_poll_interval(unsigned long dirty, return 1; } -static long bdi_max_pause(struct backing_dev_info *bdi, - unsigned long bdi_dirty) +static unsigned long bdi_max_pause(struct backing_dev_info *bdi, + unsigned long bdi_dirty) { - long bw = bdi->avg_write_bandwidth; - long t; + unsigned long bw = bdi->avg_write_bandwidth; + unsigned long t; /* * Limit pause time for small memory systems. If sleeping for too long @@ -1226,7 +1226,7 @@ static long bdi_max_pause(struct backing_dev_info *bdi, t = bdi_dirty / (1 + bw / roundup_pow_of_two(1 + HZ / 8)); t++; - return min_t(long, t, MAX_PAUSE); + return min_t(unsigned long, t, MAX_PAUSE); } static long bdi_min_pause(struct backing_dev_info *bdi, diff --git a/mm/pagewalk.c b/mm/pagewalk.c index 5da2cbcfdbb5..2beeabf502c5 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -242,7 +242,7 @@ int walk_page_range(unsigned long addr, unsigned long end, if (err) break; pgd++; - } while (addr = next, addr != end); + } while (addr = next, addr < end); return err; } diff --git a/mm/slab_common.c b/mm/slab_common.c index a3443278ce3a..e2e98af703ea 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -56,6 +56,7 @@ static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name, continue; } +#if !defined(CONFIG_SLUB) || !defined(CONFIG_SLUB_DEBUG_ON) /* * For simplicity, we won't check this in the list of memcg * caches. We have control over memcg naming, and if there @@ -69,6 +70,7 @@ static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name, s = NULL; return -EINVAL; } +#endif } WARN_ON(strchr(name, ' ')); /* It confuses parsers */ diff --git a/mm/swapfile.c b/mm/swapfile.c index 3963fc24fcc1..de7c904e52e5 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1824,6 +1824,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) struct filename *pathname; int i, type, prev; int err; + unsigned int old_block_size; if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -1914,6 +1915,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) } swap_file = p->swap_file; + old_block_size = p->old_block_size; p->swap_file = NULL; p->max = 0; swap_map = p->swap_map; @@ -1938,7 +1940,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) inode = mapping->host; if (S_ISBLK(inode->i_mode)) { struct block_device *bdev = I_BDEV(inode); - set_blocksize(bdev, p->old_block_size); + set_blocksize(bdev, old_block_size); blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); } else { mutex_lock(&inode->i_mutex); diff --git a/mm/vmscan.c b/mm/vmscan.c index 53f2f82f83ae..eea668d9cff6 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -211,6 +211,7 @@ void unregister_shrinker(struct shrinker *shrinker) down_write(&shrinker_rwsem); list_del(&shrinker->list); up_write(&shrinker_rwsem); + kfree(shrinker->nr_deferred); } EXPORT_SYMBOL(unregister_shrinker); diff --git a/mm/zswap.c b/mm/zswap.c index 841e35f1db22..d93510c6aa2d 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -804,6 +804,10 @@ static void zswap_frontswap_invalidate_area(unsigned type) } tree->rbroot = RB_ROOT; spin_unlock(&tree->lock); + + zbud_destroy_pool(tree->pool); + kfree(tree); + zswap_trees[type] = NULL; } static struct zbud_ops zswap_zbud_ops = { diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index 309129732285..c7e634af8516 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -171,7 +171,7 @@ static size_t vlan_get_size(const struct net_device *dev) return nla_total_size(2) + /* IFLA_VLAN_PROTOCOL */ nla_total_size(2) + /* IFLA_VLAN_ID */ - sizeof(struct ifla_vlan_flags) + /* IFLA_VLAN_FLAGS */ + nla_total_size(sizeof(struct ifla_vlan_flags)) + /* IFLA_VLAN_FLAGS */ vlan_qos_map_size(vlan->nr_ingress_mappings) + vlan_qos_map_size(vlan->nr_egress_mappings); } diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index c72d1bcdcf49..1356af660b5b 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -65,6 +65,7 @@ static int __init batadv_init(void) batadv_recv_handler_init(); batadv_iv_init(); + batadv_nc_init(); batadv_event_workqueue = create_singlethread_workqueue("bat_events"); @@ -142,7 +143,7 @@ int batadv_mesh_init(struct net_device *soft_iface) if (ret < 0) goto err; - ret = batadv_nc_init(bat_priv); + ret = batadv_nc_mesh_init(bat_priv); if (ret < 0) goto err; @@ -167,7 +168,7 @@ void batadv_mesh_free(struct net_device *soft_iface) batadv_vis_quit(bat_priv); batadv_gw_node_purge(bat_priv); - batadv_nc_free(bat_priv); + batadv_nc_mesh_free(bat_priv); batadv_dat_free(bat_priv); batadv_bla_free(bat_priv); diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index a487d46e0aec..4ecc0b6bf8ab 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -35,6 +35,20 @@ static int batadv_nc_recv_coded_packet(struct sk_buff *skb, struct batadv_hard_iface *recv_if); /** + * batadv_nc_init - one-time initialization for network coding + */ +int __init batadv_nc_init(void) +{ + int ret; + + /* Register our packet type */ + ret = batadv_recv_handler_register(BATADV_CODED, + batadv_nc_recv_coded_packet); + + return ret; +} + +/** * batadv_nc_start_timer - initialise the nc periodic worker * @bat_priv: the bat priv with all the soft interface information */ @@ -45,10 +59,10 @@ static void batadv_nc_start_timer(struct batadv_priv *bat_priv) } /** - * batadv_nc_init - initialise coding hash table and start house keeping + * batadv_nc_mesh_init - initialise coding hash table and start house keeping * @bat_priv: the bat priv with all the soft interface information */ -int batadv_nc_init(struct batadv_priv *bat_priv) +int batadv_nc_mesh_init(struct batadv_priv *bat_priv) { bat_priv->nc.timestamp_fwd_flush = jiffies; bat_priv->nc.timestamp_sniffed_purge = jiffies; @@ -70,11 +84,6 @@ int batadv_nc_init(struct batadv_priv *bat_priv) batadv_hash_set_lock_class(bat_priv->nc.coding_hash, &batadv_nc_decoding_hash_lock_class_key); - /* Register our packet type */ - if (batadv_recv_handler_register(BATADV_CODED, - batadv_nc_recv_coded_packet) < 0) - goto err; - INIT_DELAYED_WORK(&bat_priv->nc.work, batadv_nc_worker); batadv_nc_start_timer(bat_priv); @@ -1721,12 +1730,11 @@ free_nc_packet: } /** - * batadv_nc_free - clean up network coding memory + * batadv_nc_mesh_free - clean up network coding memory * @bat_priv: the bat priv with all the soft interface information */ -void batadv_nc_free(struct batadv_priv *bat_priv) +void batadv_nc_mesh_free(struct batadv_priv *bat_priv) { - batadv_recv_handler_unregister(BATADV_CODED); cancel_delayed_work_sync(&bat_priv->nc.work); batadv_nc_purge_paths(bat_priv, bat_priv->nc.coding_hash, NULL); diff --git a/net/batman-adv/network-coding.h b/net/batman-adv/network-coding.h index 85a4ec81ad50..ddfa618e80bf 100644 --- a/net/batman-adv/network-coding.h +++ b/net/batman-adv/network-coding.h @@ -22,8 +22,9 @@ #ifdef CONFIG_BATMAN_ADV_NC -int batadv_nc_init(struct batadv_priv *bat_priv); -void batadv_nc_free(struct batadv_priv *bat_priv); +int batadv_nc_init(void); +int batadv_nc_mesh_init(struct batadv_priv *bat_priv); +void batadv_nc_mesh_free(struct batadv_priv *bat_priv); void batadv_nc_update_nc_node(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, struct batadv_orig_node *orig_neigh_node, @@ -46,12 +47,17 @@ int batadv_nc_init_debugfs(struct batadv_priv *bat_priv); #else /* ifdef CONFIG_BATMAN_ADV_NC */ -static inline int batadv_nc_init(struct batadv_priv *bat_priv) +static inline int batadv_nc_init(void) { return 0; } -static inline void batadv_nc_free(struct batadv_priv *bat_priv) +static inline int batadv_nc_mesh_init(struct batadv_priv *bat_priv) +{ + return 0; +} + +static inline void batadv_nc_mesh_free(struct batadv_priv *bat_priv) { return; } diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index ca04163635da..e6b7fecb3af1 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -64,7 +64,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) br_flood_deliver(br, skb, false); goto out; } - if (br_multicast_rcv(br, NULL, skb)) { + if (br_multicast_rcv(br, NULL, skb, vid)) { kfree_skb(skb); goto out; } diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index ffd5874f2592..33e8f23acddd 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -700,7 +700,7 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], vid = nla_get_u16(tb[NDA_VLAN]); - if (vid >= VLAN_N_VID) { + if (!vid || vid >= VLAN_VID_MASK) { pr_info("bridge: RTM_NEWNEIGH with invalid vlan id %d\n", vid); return -EINVAL; @@ -794,7 +794,7 @@ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], vid = nla_get_u16(tb[NDA_VLAN]); - if (vid >= VLAN_N_VID) { + if (!vid || vid >= VLAN_VID_MASK) { pr_info("bridge: RTM_NEWNEIGH with invalid vlan id %d\n", vid); return -EINVAL; diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index a2fd37ec35f7..7e73c32e205d 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -80,7 +80,7 @@ int br_handle_frame_finish(struct sk_buff *skb) br_fdb_update(br, p, eth_hdr(skb)->h_source, vid); if (!is_broadcast_ether_addr(dest) && is_multicast_ether_addr(dest) && - br_multicast_rcv(br, p, skb)) + br_multicast_rcv(br, p, skb, vid)) goto drop; if (p->state == BR_STATE_LEARNING) diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 85a09bb5ca51..b7b1914dfa25 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -453,7 +453,7 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry) call_rcu_bh(&p->rcu, br_multicast_free_pg); err = 0; - if (!mp->ports && !mp->mglist && mp->timer_armed && + if (!mp->ports && !mp->mglist && netif_running(br->dev)) mod_timer(&mp->timer, jiffies); break; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index d1c578630678..686284ff3d6a 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -272,7 +272,7 @@ static void br_multicast_del_pg(struct net_bridge *br, del_timer(&p->timer); call_rcu_bh(&p->rcu, br_multicast_free_pg); - if (!mp->ports && !mp->mglist && mp->timer_armed && + if (!mp->ports && !mp->mglist && netif_running(br->dev)) mod_timer(&mp->timer, jiffies); @@ -620,7 +620,6 @@ rehash: mp->br = br; mp->addr = *group; - setup_timer(&mp->timer, br_multicast_group_expired, (unsigned long)mp); @@ -660,6 +659,7 @@ static int br_multicast_add_group(struct net_bridge *br, struct net_bridge_mdb_entry *mp; struct net_bridge_port_group *p; struct net_bridge_port_group __rcu **pp; + unsigned long now = jiffies; int err; spin_lock(&br->multicast_lock); @@ -674,6 +674,7 @@ static int br_multicast_add_group(struct net_bridge *br, if (!port) { mp->mglist = true; + mod_timer(&mp->timer, now + br->multicast_membership_interval); goto out; } @@ -681,7 +682,7 @@ static int br_multicast_add_group(struct net_bridge *br, (p = mlock_dereference(*pp, br)) != NULL; pp = &p->next) { if (p->port == port) - goto out; + goto found; if ((unsigned long)p->port < (unsigned long)port) break; } @@ -692,6 +693,8 @@ static int br_multicast_add_group(struct net_bridge *br, rcu_assign_pointer(*pp, p); br_mdb_notify(br->dev, port, group, RTM_NEWMDB); +found: + mod_timer(&p->timer, now + br->multicast_membership_interval); out: err = 0; @@ -944,7 +947,8 @@ void br_multicast_disable_port(struct net_bridge_port *port) static int br_ip4_multicast_igmp3_report(struct net_bridge *br, struct net_bridge_port *port, - struct sk_buff *skb) + struct sk_buff *skb, + u16 vid) { struct igmpv3_report *ih; struct igmpv3_grec *grec; @@ -954,12 +958,10 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br, int type; int err = 0; __be32 group; - u16 vid = 0; if (!pskb_may_pull(skb, sizeof(*ih))) return -EINVAL; - br_vlan_get_tag(skb, &vid); ih = igmpv3_report_hdr(skb); num = ntohs(ih->ngrec); len = sizeof(*ih); @@ -1002,7 +1004,8 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br, #if IS_ENABLED(CONFIG_IPV6) static int br_ip6_multicast_mld2_report(struct net_bridge *br, struct net_bridge_port *port, - struct sk_buff *skb) + struct sk_buff *skb, + u16 vid) { struct icmp6hdr *icmp6h; struct mld2_grec *grec; @@ -1010,12 +1013,10 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, int len; int num; int err = 0; - u16 vid = 0; if (!pskb_may_pull(skb, sizeof(*icmp6h))) return -EINVAL; - br_vlan_get_tag(skb, &vid); icmp6h = icmp6_hdr(skb); num = ntohs(icmp6h->icmp6_dataun.un_data16[1]); len = sizeof(*icmp6h); @@ -1138,7 +1139,8 @@ static void br_multicast_query_received(struct net_bridge *br, static int br_ip4_multicast_query(struct net_bridge *br, struct net_bridge_port *port, - struct sk_buff *skb) + struct sk_buff *skb, + u16 vid) { const struct iphdr *iph = ip_hdr(skb); struct igmphdr *ih = igmp_hdr(skb); @@ -1150,7 +1152,6 @@ static int br_ip4_multicast_query(struct net_bridge *br, unsigned long now = jiffies; __be32 group; int err = 0; - u16 vid = 0; spin_lock(&br->multicast_lock); if (!netif_running(br->dev) || @@ -1186,14 +1187,10 @@ static int br_ip4_multicast_query(struct net_bridge *br, if (!group) goto out; - br_vlan_get_tag(skb, &vid); mp = br_mdb_ip4_get(mlock_dereference(br->mdb, br), group, vid); if (!mp) goto out; - mod_timer(&mp->timer, now + br->multicast_membership_interval); - mp->timer_armed = true; - max_delay *= br->multicast_last_member_count; if (mp->mglist && @@ -1219,7 +1216,8 @@ out: #if IS_ENABLED(CONFIG_IPV6) static int br_ip6_multicast_query(struct net_bridge *br, struct net_bridge_port *port, - struct sk_buff *skb) + struct sk_buff *skb, + u16 vid) { const struct ipv6hdr *ip6h = ipv6_hdr(skb); struct mld_msg *mld; @@ -1231,7 +1229,6 @@ static int br_ip6_multicast_query(struct net_bridge *br, unsigned long now = jiffies; const struct in6_addr *group = NULL; int err = 0; - u16 vid = 0; spin_lock(&br->multicast_lock); if (!netif_running(br->dev) || @@ -1265,14 +1262,10 @@ static int br_ip6_multicast_query(struct net_bridge *br, if (!group) goto out; - br_vlan_get_tag(skb, &vid); mp = br_mdb_ip6_get(mlock_dereference(br->mdb, br), group, vid); if (!mp) goto out; - mod_timer(&mp->timer, now + br->multicast_membership_interval); - mp->timer_armed = true; - max_delay *= br->multicast_last_member_count; if (mp->mglist && (timer_pending(&mp->timer) ? @@ -1358,7 +1351,7 @@ static void br_multicast_leave_group(struct net_bridge *br, call_rcu_bh(&p->rcu, br_multicast_free_pg); br_mdb_notify(br->dev, port, group, RTM_DELMDB); - if (!mp->ports && !mp->mglist && mp->timer_armed && + if (!mp->ports && !mp->mglist && netif_running(br->dev)) mod_timer(&mp->timer, jiffies); } @@ -1370,12 +1363,30 @@ static void br_multicast_leave_group(struct net_bridge *br, br->multicast_last_member_interval; if (!port) { - if (mp->mglist && mp->timer_armed && + if (mp->mglist && (timer_pending(&mp->timer) ? time_after(mp->timer.expires, time) : try_to_del_timer_sync(&mp->timer) >= 0)) { mod_timer(&mp->timer, time); } + + goto out; + } + + for (p = mlock_dereference(mp->ports, br); + p != NULL; + p = mlock_dereference(p->next, br)) { + if (p->port != port) + continue; + + if (!hlist_unhashed(&p->mglist) && + (timer_pending(&p->timer) ? + time_after(p->timer.expires, time) : + try_to_del_timer_sync(&p->timer) >= 0)) { + mod_timer(&p->timer, time); + } + + break; } out: spin_unlock(&br->multicast_lock); @@ -1424,7 +1435,8 @@ static void br_ip6_multicast_leave_group(struct net_bridge *br, static int br_multicast_ipv4_rcv(struct net_bridge *br, struct net_bridge_port *port, - struct sk_buff *skb) + struct sk_buff *skb, + u16 vid) { struct sk_buff *skb2 = skb; const struct iphdr *iph; @@ -1432,7 +1444,6 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, unsigned int len; unsigned int offset; int err; - u16 vid = 0; /* We treat OOM as packet loss for now. */ if (!pskb_may_pull(skb, sizeof(*iph))) @@ -1493,7 +1504,6 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, err = 0; - br_vlan_get_tag(skb2, &vid); BR_INPUT_SKB_CB(skb)->igmp = 1; ih = igmp_hdr(skb2); @@ -1504,10 +1514,10 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, err = br_ip4_multicast_add_group(br, port, ih->group, vid); break; case IGMPV3_HOST_MEMBERSHIP_REPORT: - err = br_ip4_multicast_igmp3_report(br, port, skb2); + err = br_ip4_multicast_igmp3_report(br, port, skb2, vid); break; case IGMP_HOST_MEMBERSHIP_QUERY: - err = br_ip4_multicast_query(br, port, skb2); + err = br_ip4_multicast_query(br, port, skb2, vid); break; case IGMP_HOST_LEAVE_MESSAGE: br_ip4_multicast_leave_group(br, port, ih->group, vid); @@ -1525,7 +1535,8 @@ err_out: #if IS_ENABLED(CONFIG_IPV6) static int br_multicast_ipv6_rcv(struct net_bridge *br, struct net_bridge_port *port, - struct sk_buff *skb) + struct sk_buff *skb, + u16 vid) { struct sk_buff *skb2; const struct ipv6hdr *ip6h; @@ -1535,7 +1546,6 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, unsigned int len; int offset; int err; - u16 vid = 0; if (!pskb_may_pull(skb, sizeof(*ip6h))) return -EINVAL; @@ -1625,7 +1635,6 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, err = 0; - br_vlan_get_tag(skb, &vid); BR_INPUT_SKB_CB(skb)->igmp = 1; switch (icmp6_type) { @@ -1642,10 +1651,10 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, break; } case ICMPV6_MLD2_REPORT: - err = br_ip6_multicast_mld2_report(br, port, skb2); + err = br_ip6_multicast_mld2_report(br, port, skb2, vid); break; case ICMPV6_MGM_QUERY: - err = br_ip6_multicast_query(br, port, skb2); + err = br_ip6_multicast_query(br, port, skb2, vid); break; case ICMPV6_MGM_REDUCTION: { @@ -1666,7 +1675,7 @@ out: #endif int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port, - struct sk_buff *skb) + struct sk_buff *skb, u16 vid) { BR_INPUT_SKB_CB(skb)->igmp = 0; BR_INPUT_SKB_CB(skb)->mrouters_only = 0; @@ -1676,10 +1685,10 @@ int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port, switch (skb->protocol) { case htons(ETH_P_IP): - return br_multicast_ipv4_rcv(br, port, skb); + return br_multicast_ipv4_rcv(br, port, skb, vid); #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): - return br_multicast_ipv6_rcv(br, port, skb); + return br_multicast_ipv6_rcv(br, port, skb, vid); #endif } @@ -1798,7 +1807,6 @@ void br_multicast_stop(struct net_bridge *br) hlist_for_each_entry_safe(mp, n, &mdb->mhash[i], hlist[ver]) { del_timer(&mp->timer); - mp->timer_armed = false; call_rcu_bh(&mp->rcu, br_multicast_free_group); } } diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index e74ddc1c29a8..f75d92e4f96b 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -243,7 +243,7 @@ static int br_afspec(struct net_bridge *br, vinfo = nla_data(tb[IFLA_BRIDGE_VLAN_INFO]); - if (vinfo->vid >= VLAN_N_VID) + if (!vinfo->vid || vinfo->vid >= VLAN_VID_MASK) return -EINVAL; switch (cmd) { diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index efb57d911569..2e8244efb262 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -126,7 +126,6 @@ struct net_bridge_mdb_entry struct timer_list timer; struct br_ip addr; bool mglist; - bool timer_armed; }; struct net_bridge_mdb_htable @@ -452,7 +451,8 @@ extern int br_ioctl_deviceless_stub(struct net *net, unsigned int cmd, void __us extern unsigned int br_mdb_rehash_seq; extern int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port, - struct sk_buff *skb); + struct sk_buff *skb, + u16 vid); extern struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br, struct sk_buff *skb, u16 vid); extern void br_multicast_add_port(struct net_bridge_port *port); @@ -523,7 +523,8 @@ static inline bool br_multicast_querier_exists(struct net_bridge *br, #else static inline int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port, - struct sk_buff *skb) + struct sk_buff *skb, + u16 vid) { return 0; } @@ -643,9 +644,7 @@ static inline u16 br_get_pvid(const struct net_port_vlans *v) * vid wasn't set */ smp_rmb(); - return (v->pvid & VLAN_TAG_PRESENT) ? - (v->pvid & ~VLAN_TAG_PRESENT) : - VLAN_N_VID; + return v->pvid ?: VLAN_N_VID; } #else diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index 108084a04671..656a6f3e40de 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -134,7 +134,7 @@ static void br_stp_start(struct net_bridge *br) if (br->bridge_forward_delay < BR_MIN_FORWARD_DELAY) __br_set_forward_delay(br, BR_MIN_FORWARD_DELAY); - else if (br->bridge_forward_delay < BR_MAX_FORWARD_DELAY) + else if (br->bridge_forward_delay > BR_MAX_FORWARD_DELAY) __br_set_forward_delay(br, BR_MAX_FORWARD_DELAY); if (r == 0) { diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 9a9ffe7e4019..53f0990eab58 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -45,37 +45,34 @@ static int __vlan_add(struct net_port_vlans *v, u16 vid, u16 flags) return 0; } - if (vid) { - if (v->port_idx) { - p = v->parent.port; - br = p->br; - dev = p->dev; - } else { - br = v->parent.br; - dev = br->dev; - } - ops = dev->netdev_ops; - - if (p && (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) { - /* Add VLAN to the device filter if it is supported. - * Stricly speaking, this is not necessary now, since - * devices are made promiscuous by the bridge, but if - * that ever changes this code will allow tagged - * traffic to enter the bridge. - */ - err = ops->ndo_vlan_rx_add_vid(dev, htons(ETH_P_8021Q), - vid); - if (err) - return err; - } - - err = br_fdb_insert(br, p, dev->dev_addr, vid); - if (err) { - br_err(br, "failed insert local address into bridge " - "forwarding table\n"); - goto out_filt; - } + if (v->port_idx) { + p = v->parent.port; + br = p->br; + dev = p->dev; + } else { + br = v->parent.br; + dev = br->dev; + } + ops = dev->netdev_ops; + + if (p && (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) { + /* Add VLAN to the device filter if it is supported. + * Stricly speaking, this is not necessary now, since + * devices are made promiscuous by the bridge, but if + * that ever changes this code will allow tagged + * traffic to enter the bridge. + */ + err = ops->ndo_vlan_rx_add_vid(dev, htons(ETH_P_8021Q), + vid); + if (err) + return err; + } + err = br_fdb_insert(br, p, dev->dev_addr, vid); + if (err) { + br_err(br, "failed insert local address into bridge " + "forwarding table\n"); + goto out_filt; } set_bit(vid, v->vlan_bitmap); @@ -98,7 +95,7 @@ static int __vlan_del(struct net_port_vlans *v, u16 vid) __vlan_delete_pvid(v, vid); clear_bit(vid, v->untagged_bitmap); - if (v->port_idx && vid) { + if (v->port_idx) { struct net_device *dev = v->parent.port->dev; const struct net_device_ops *ops = dev->netdev_ops; @@ -192,6 +189,8 @@ out: bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, struct sk_buff *skb, u16 *vid) { + int err; + /* If VLAN filtering is disabled on the bridge, all packets are * permitted. */ @@ -204,20 +203,32 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, if (!v) return false; - if (br_vlan_get_tag(skb, vid)) { + err = br_vlan_get_tag(skb, vid); + if (!*vid) { u16 pvid = br_get_pvid(v); - /* Frame did not have a tag. See if pvid is set - * on this port. That tells us which vlan untagged - * traffic belongs to. + /* Frame had a tag with VID 0 or did not have a tag. + * See if pvid is set on this port. That tells us which + * vlan untagged or priority-tagged traffic belongs to. */ if (pvid == VLAN_N_VID) return false; - /* PVID is set on this port. Any untagged ingress - * frame is considered to belong to this vlan. + /* PVID is set on this port. Any untagged or priority-tagged + * ingress frame is considered to belong to this vlan. */ - __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), pvid); + *vid = pvid; + if (likely(err)) + /* Untagged Frame. */ + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), pvid); + else + /* Priority-tagged Frame. + * At this point, We know that skb->vlan_tci had + * VLAN_TAG_PRESENT bit and its VID field was 0x000. + * We update only VID field and preserve PCP field. + */ + skb->vlan_tci |= pvid; + return true; } @@ -248,7 +259,9 @@ bool br_allowed_egress(struct net_bridge *br, return false; } -/* Must be protected by RTNL */ +/* Must be protected by RTNL. + * Must be called with vid in range from 1 to 4094 inclusive. + */ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags) { struct net_port_vlans *pv = NULL; @@ -278,7 +291,9 @@ out: return err; } -/* Must be protected by RTNL */ +/* Must be protected by RTNL. + * Must be called with vid in range from 1 to 4094 inclusive. + */ int br_vlan_delete(struct net_bridge *br, u16 vid) { struct net_port_vlans *pv; @@ -289,14 +304,9 @@ int br_vlan_delete(struct net_bridge *br, u16 vid) if (!pv) return -EINVAL; - if (vid) { - /* If the VID !=0 remove fdb for this vid. VID 0 is special - * in that it's the default and is always there in the fdb. - */ - spin_lock_bh(&br->hash_lock); - fdb_delete_by_addr(br, br->dev->dev_addr, vid); - spin_unlock_bh(&br->hash_lock); - } + spin_lock_bh(&br->hash_lock); + fdb_delete_by_addr(br, br->dev->dev_addr, vid); + spin_unlock_bh(&br->hash_lock); __vlan_del(pv, vid); return 0; @@ -329,7 +339,9 @@ unlock: return 0; } -/* Must be protected by RTNL */ +/* Must be protected by RTNL. + * Must be called with vid in range from 1 to 4094 inclusive. + */ int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags) { struct net_port_vlans *pv = NULL; @@ -363,7 +375,9 @@ clean_up: return err; } -/* Must be protected by RTNL */ +/* Must be protected by RTNL. + * Must be called with vid in range from 1 to 4094 inclusive. + */ int nbp_vlan_delete(struct net_bridge_port *port, u16 vid) { struct net_port_vlans *pv; @@ -374,14 +388,9 @@ int nbp_vlan_delete(struct net_bridge_port *port, u16 vid) if (!pv) return -EINVAL; - if (vid) { - /* If the VID !=0 remove fdb for this vid. VID 0 is special - * in that it's the default and is always there in the fdb. - */ - spin_lock_bh(&port->br->hash_lock); - fdb_delete_by_addr(port->br, port->dev->dev_addr, vid); - spin_unlock_bh(&port->br->hash_lock); - } + spin_lock_bh(&port->br->hash_lock); + fdb_delete_by_addr(port->br, port->dev->dev_addr, vid); + spin_unlock_bh(&port->br->hash_lock); return __vlan_del(pv, vid); } diff --git a/net/bridge/netfilter/ebt_ulog.c b/net/bridge/netfilter/ebt_ulog.c index 518093802d1d..7c470c371e14 100644 --- a/net/bridge/netfilter/ebt_ulog.c +++ b/net/bridge/netfilter/ebt_ulog.c @@ -181,6 +181,7 @@ static void ebt_ulog_packet(struct net *net, unsigned int hooknr, ub->qlen++; pm = nlmsg_data(nlh); + memset(pm, 0, sizeof(*pm)); /* Fill in the ulog data */ pm->version = EBT_ULOG_VERSION; @@ -193,8 +194,6 @@ static void ebt_ulog_packet(struct net *net, unsigned int hooknr, pm->hook = hooknr; if (uloginfo->prefix != NULL) strcpy(pm->prefix, uloginfo->prefix); - else - *(pm->prefix) = '\0'; if (in) { strcpy(pm->physindev, in->name); @@ -204,16 +203,14 @@ static void ebt_ulog_packet(struct net *net, unsigned int hooknr, strcpy(pm->indev, br_port_get_rcu(in)->br->dev->name); else strcpy(pm->indev, in->name); - } else - pm->indev[0] = pm->physindev[0] = '\0'; + } if (out) { /* If out exists, then out is a bridge port */ strcpy(pm->physoutdev, out->name); /* rcu_read_lock()ed by nf_hook_slow */ strcpy(pm->outdev, br_port_get_rcu(out)->br->dev->name); - } else - pm->outdev[0] = pm->physoutdev[0] = '\0'; + } if (skb_copy_bits(skb, -ETH_HLEN, pm->data, copy_len) < 0) BUG(); diff --git a/net/compat.c b/net/compat.c index f0a1ba6c8086..89032580bd1d 100644 --- a/net/compat.c +++ b/net/compat.c @@ -71,6 +71,8 @@ int get_compat_msghdr(struct msghdr *kmsg, struct compat_msghdr __user *umsg) __get_user(kmsg->msg_controllen, &umsg->msg_controllen) || __get_user(kmsg->msg_flags, &umsg->msg_flags)) return -EFAULT; + if (kmsg->msg_namelen > sizeof(struct sockaddr_storage)) + return -EINVAL; kmsg->msg_name = compat_ptr(tmp1); kmsg->msg_iov = compat_ptr(tmp2); kmsg->msg_control = compat_ptr(tmp3); diff --git a/net/core/dev.c b/net/core/dev.c index 65f829cfd928..3430b1ed12e5 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1917,7 +1917,8 @@ static struct xps_map *expand_xps_map(struct xps_map *map, return new_map; } -int netif_set_xps_queue(struct net_device *dev, struct cpumask *mask, u16 index) +int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, + u16 index) { struct xps_dev_maps *dev_maps, *new_dev_maps = NULL; struct xps_map *map, *new_map; diff --git a/net/core/filter.c b/net/core/filter.c index 6438f29ff266..01b780856db2 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -644,7 +644,6 @@ void sk_filter_release_rcu(struct rcu_head *rcu) struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu); bpf_jit_free(fp); - kfree(fp); } EXPORT_SYMBOL(sk_filter_release_rcu); @@ -683,7 +682,7 @@ int sk_unattached_filter_create(struct sk_filter **pfp, if (fprog->filter == NULL) return -EINVAL; - fp = kmalloc(fsize + sizeof(*fp), GFP_KERNEL); + fp = kmalloc(sk_filter_size(fprog->len), GFP_KERNEL); if (!fp) return -ENOMEM; memcpy(fp->insns, fprog->filter, fsize); @@ -723,6 +722,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) { struct sk_filter *fp, *old_fp; unsigned int fsize = sizeof(struct sock_filter) * fprog->len; + unsigned int sk_fsize = sk_filter_size(fprog->len); int err; if (sock_flag(sk, SOCK_FILTER_LOCKED)) @@ -732,11 +732,11 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) if (fprog->filter == NULL) return -EINVAL; - fp = sock_kmalloc(sk, fsize+sizeof(*fp), GFP_KERNEL); + fp = sock_kmalloc(sk, sk_fsize, GFP_KERNEL); if (!fp) return -ENOMEM; if (copy_from_user(fp->insns, fprog->filter, fsize)) { - sock_kfree_s(sk, fp, fsize+sizeof(*fp)); + sock_kfree_s(sk, fp, sk_fsize); return -EFAULT; } diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 8d7d0dd72db2..143b6fdb9647 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -40,7 +40,7 @@ again: struct iphdr _iph; ip: iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph); - if (!iph) + if (!iph || iph->ihl < 5) return false; if (ip_is_fragment(iph)) diff --git a/net/core/netpoll.c b/net/core/netpoll.c index fc75c9e461b8..8f971990677c 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -636,8 +636,9 @@ static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo netpoll_send_skb(np, send_skb); - /* If there are several rx_hooks for the same address, - we're fine by sending a single reply */ + /* If there are several rx_skb_hooks for the same + * address we're fine by sending a single reply + */ break; } spin_unlock_irqrestore(&npinfo->rx_lock, flags); @@ -719,8 +720,9 @@ static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo netpoll_send_skb(np, send_skb); - /* If there are several rx_hooks for the same address, - we're fine by sending a single reply */ + /* If there are several rx_skb_hooks for the same + * address, we're fine by sending a single reply + */ break; } spin_unlock_irqrestore(&npinfo->rx_lock, flags); @@ -756,11 +758,12 @@ static bool pkt_is_ns(struct sk_buff *skb) int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo) { - int proto, len, ulen; - int hits = 0; + int proto, len, ulen, data_len; + int hits = 0, offset; const struct iphdr *iph; struct udphdr *uh; struct netpoll *np, *tmp; + uint16_t source; if (list_empty(&npinfo->rx_np)) goto out; @@ -820,7 +823,10 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo) len -= iph->ihl*4; uh = (struct udphdr *)(((char *)iph) + iph->ihl*4); + offset = (unsigned char *)(uh + 1) - skb->data; ulen = ntohs(uh->len); + data_len = skb->len - offset; + source = ntohs(uh->source); if (ulen != len) goto out; @@ -834,9 +840,7 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo) if (np->local_port && np->local_port != ntohs(uh->dest)) continue; - np->rx_hook(np, ntohs(uh->source), - (char *)(uh+1), - ulen - sizeof(struct udphdr)); + np->rx_skb_hook(np, source, skb, offset, data_len); hits++; } } else { @@ -859,7 +863,10 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo) if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto out; uh = udp_hdr(skb); + offset = (unsigned char *)(uh + 1) - skb->data; ulen = ntohs(uh->len); + data_len = skb->len - offset; + source = ntohs(uh->source); if (ulen != skb->len) goto out; if (udp6_csum_init(skb, uh, IPPROTO_UDP)) @@ -872,9 +879,7 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo) if (np->local_port && np->local_port != ntohs(uh->dest)) continue; - np->rx_hook(np, ntohs(uh->source), - (char *)(uh+1), - ulen - sizeof(struct udphdr)); + np->rx_skb_hook(np, source, skb, offset, data_len); hits++; } #endif @@ -1062,7 +1067,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp) npinfo->netpoll = np; - if (np->rx_hook) { + if (np->rx_skb_hook) { spin_lock_irqsave(&npinfo->rx_lock, flags); npinfo->rx_flags |= NETPOLL_RX_ENABLED; list_add_tail(&np->rx, &npinfo->rx_np); diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index 3f1ec1586ae1..8d9d05edd2eb 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -10,6 +10,7 @@ #include <net/secure_seq.h> +#if IS_ENABLED(CONFIG_IPV6) || IS_ENABLED(CONFIG_INET) #define NET_SECRET_SIZE (MD5_MESSAGE_BYTES / 4) static u32 net_secret[NET_SECRET_SIZE] ____cacheline_aligned; @@ -29,6 +30,7 @@ static void net_secret_init(void) cmpxchg(&net_secret[--i], 0, tmp); } } +#endif #ifdef CONFIG_INET static u32 seq_scale(u32 seq) diff --git a/net/core/sock.c b/net/core/sock.c index 5b6beba494a3..0b39e7ae4383 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2319,6 +2319,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_ll_usec = sysctl_net_busy_read; #endif + sk->sk_pacing_rate = ~0U; /* * Before updating sk_refcnt, we must commit prior changes to memory * (Documentation/RCU/rculist_nulls.txt for details) diff --git a/net/ieee802154/6lowpan.c b/net/ieee802154/6lowpan.c index c85e71e0c7ff..ff41b4d60d30 100644 --- a/net/ieee802154/6lowpan.c +++ b/net/ieee802154/6lowpan.c @@ -1372,6 +1372,8 @@ static int lowpan_newlink(struct net *src_net, struct net_device *dev, real_dev = dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK])); if (!real_dev) return -ENODEV; + if (real_dev->type != ARPHRD_IEEE802154) + return -EINVAL; lowpan_dev_info(dev)->real_dev = real_dev; lowpan_dev_info(dev)->fragment_tag = 0; @@ -1386,6 +1388,9 @@ static int lowpan_newlink(struct net *src_net, struct net_device *dev, entry->ldev = dev; + /* Set the lowpan harware address to the wpan hardware address. */ + memcpy(dev->dev_addr, real_dev->dev_addr, IEEE802154_ADDR_LEN); + mutex_lock(&lowpan_dev_info(dev)->dev_list_mtx); INIT_LIST_HEAD(&entry->list); list_add_tail(&entry->list, &lowpan_devices); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 7bd8983dbfcf..96da9c77deca 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -287,7 +287,7 @@ begintw: if (unlikely(!INET_TW_MATCH(sk, net, acookie, saddr, daddr, ports, dif))) { - sock_put(sk); + inet_twsk_put(inet_twsk(sk)); goto begintw; } goto out; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index a04d872c54f9..3982eabf61e1 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -772,15 +772,20 @@ static inline int ip_ufo_append_data(struct sock *sk, /* initialize protocol header pointer */ skb->transport_header = skb->network_header + fragheaderlen; - skb->ip_summed = CHECKSUM_PARTIAL; skb->csum = 0; - /* specify the length of each IP datagram fragment */ - skb_shinfo(skb)->gso_size = maxfraglen - fragheaderlen; - skb_shinfo(skb)->gso_type = SKB_GSO_UDP; + __skb_queue_tail(queue, skb); + } else if (skb_is_gso(skb)) { + goto append; } + skb->ip_summed = CHECKSUM_PARTIAL; + /* specify the length of each IP datagram fragment */ + skb_shinfo(skb)->gso_size = maxfraglen - fragheaderlen; + skb_shinfo(skb)->gso_type = SKB_GSO_UDP; + +append: return skb_append_datato_frags(sk, skb, getfrag, from, (length - transhdrlen)); } diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index e805e7b3030e..6e87f853d033 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -125,8 +125,17 @@ static int vti_rcv(struct sk_buff *skb) iph->saddr, iph->daddr, 0); if (tunnel != NULL) { struct pcpu_tstats *tstats; + u32 oldmark = skb->mark; + int ret; - if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) + + /* temporarily mark the skb with the tunnel o_key, to + * only match policies with this mark. + */ + skb->mark = be32_to_cpu(tunnel->parms.o_key); + ret = xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb); + skb->mark = oldmark; + if (!ret) return -1; tstats = this_cpu_ptr(tunnel->dev->tstats); @@ -135,7 +144,6 @@ static int vti_rcv(struct sk_buff *skb) tstats->rx_bytes += skb->len; u64_stats_update_end(&tstats->syncp); - skb->mark = 0; secpath_reset(skb); skb->dev = tunnel->dev; return 1; @@ -167,7 +175,7 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) memset(&fl4, 0, sizeof(fl4)); flowi4_init_output(&fl4, tunnel->parms.link, - be32_to_cpu(tunnel->parms.i_key), RT_TOS(tos), + be32_to_cpu(tunnel->parms.o_key), RT_TOS(tos), RT_SCOPE_UNIVERSE, IPPROTO_IPIP, 0, dst, tiph->saddr, 0, 0); diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 85a4f21aac1a..59da7cde0724 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -271,6 +271,11 @@ unsigned int arpt_do_table(struct sk_buff *skb, local_bh_disable(); addend = xt_write_recseq_begin(); private = table->private; + /* + * Ensure we load private-> members after we've fetched the base + * pointer. + */ + smp_read_barrier_depends(); table_base = private->entries[smp_processor_id()]; e = get_entry(table_base, private->hook_entry[hook]); diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index d23118d95ff9..718dfbd30cbe 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -327,6 +327,11 @@ ipt_do_table(struct sk_buff *skb, addend = xt_write_recseq_begin(); private = table->private; cpu = smp_processor_id(); + /* + * Ensure we load private-> members after we've fetched the base + * pointer. + */ + smp_read_barrier_depends(); table_base = private->entries[cpu]; jumpstack = (struct ipt_entry **)private->jumpstack[cpu]; stackptr = per_cpu_ptr(private->stackptr, cpu); diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c index cbc22158af49..9cb993cd224b 100644 --- a/net/ipv4/netfilter/ipt_ULOG.c +++ b/net/ipv4/netfilter/ipt_ULOG.c @@ -220,6 +220,7 @@ static void ipt_ulog_packet(struct net *net, ub->qlen++; pm = nlmsg_data(nlh); + memset(pm, 0, sizeof(*pm)); /* We might not have a timestamp, get one */ if (skb->tstamp.tv64 == 0) @@ -238,8 +239,6 @@ static void ipt_ulog_packet(struct net *net, } else if (loginfo->prefix[0] != '\0') strncpy(pm->prefix, loginfo->prefix, sizeof(pm->prefix)); - else - *(pm->prefix) = '\0'; if (in && in->hard_header_len > 0 && skb->mac_header != skb->network_header && @@ -251,13 +250,9 @@ static void ipt_ulog_packet(struct net *net, if (in) strncpy(pm->indev_name, in->name, sizeof(pm->indev_name)); - else - pm->indev_name[0] = '\0'; if (out) strncpy(pm->outdev_name, out->name, sizeof(pm->outdev_name)); - else - pm->outdev_name[0] = '\0'; /* copy_len <= skb->len, so can't fail. */ if (skb_copy_bits(skb, 0, pm->payload, copy_len) < 0) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 727f4365bcdf..6011615e810d 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2072,7 +2072,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) RT_SCOPE_LINK); goto make_route; } - if (fl4->saddr) { + if (!fl4->saddr) { if (ipv4_is_multicast(fl4->daddr)) fl4->saddr = inet_select_addr(dev_out, 0, fl4->flowi4_scope); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 25a89eaa669d..068c8fb0d158 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1284,7 +1284,10 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, tp->lost_cnt_hint -= tcp_skb_pcount(prev); } - TCP_SKB_CB(skb)->tcp_flags |= TCP_SKB_CB(prev)->tcp_flags; + TCP_SKB_CB(prev)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags; + if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) + TCP_SKB_CB(prev)->end_seq++; + if (skb == tcp_highest_sack(sk)) tcp_advance_highest_sack(sk, skb); @@ -2853,7 +2856,8 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, * left edge of the send window. * See draft-ietf-tcplw-high-performance-00, section 3.3. */ - if (seq_rtt < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr) + if (seq_rtt < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && + flag & FLAG_ACKED) seq_rtt = tcp_time_stamp - tp->rx_opt.rcv_tsecr; if (seq_rtt < 0) @@ -2868,14 +2872,19 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, } /* Compute time elapsed between (last) SYNACK and the ACK completing 3WHS. */ -static void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req) +static void tcp_synack_rtt_meas(struct sock *sk, const u32 synack_stamp) { struct tcp_sock *tp = tcp_sk(sk); s32 seq_rtt = -1; - if (tp->lsndtime && !tp->total_retrans) - seq_rtt = tcp_time_stamp - tp->lsndtime; - tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, seq_rtt, -1); + if (synack_stamp && !tp->total_retrans) + seq_rtt = tcp_time_stamp - synack_stamp; + + /* If the ACK acks both the SYNACK and the (Fast Open'd) data packets + * sent in SYN_RECV, SYNACK RTT is the smooth RTT computed in tcp_ack() + */ + if (!tp->srtt) + tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, seq_rtt, -1); } static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 in_flight) @@ -2978,6 +2987,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, s32 seq_rtt = -1; s32 ca_seq_rtt = -1; ktime_t last_ackt = net_invalid_timestamp(); + bool rtt_update; while ((skb = tcp_write_queue_head(sk)) && skb != tcp_send_head(sk)) { struct tcp_skb_cb *scb = TCP_SKB_CB(skb); @@ -3054,14 +3064,13 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) flag |= FLAG_SACK_RENEGING; - if (tcp_ack_update_rtt(sk, flag, seq_rtt, sack_rtt) || - (flag & FLAG_ACKED)) - tcp_rearm_rto(sk); + rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt, sack_rtt); if (flag & FLAG_ACKED) { const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops; + tcp_rearm_rto(sk); if (unlikely(icsk->icsk_mtup.probe_size && !after(tp->mtu_probe.probe_seq_end, tp->snd_una))) { tcp_mtup_probe_success(sk); @@ -3100,6 +3109,13 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, ca_ops->pkts_acked(sk, pkts_acked, rtt_us); } + } else if (skb && rtt_update && sack_rtt >= 0 && + sack_rtt > (s32)(now - TCP_SKB_CB(skb)->when)) { + /* Do not re-arm RTO if the sack RTT is measured from data sent + * after when the head was last (re)transmitted. Otherwise the + * timeout may continue to extend in loss recovery. + */ + tcp_rearm_rto(sk); } #if FASTRETRANS_DEBUG > 0 @@ -3288,7 +3304,7 @@ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag) tcp_init_cwnd_reduction(sk, true); tcp_set_ca_state(sk, TCP_CA_CWR); tcp_end_cwnd_reduction(sk); - tcp_set_ca_state(sk, TCP_CA_Open); + tcp_try_keep_open(sk); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSSPROBERECOVERY); } @@ -5584,6 +5600,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, struct request_sock *req; int queued = 0; bool acceptable; + u32 synack_stamp; tp->rx_opt.saw_tstamp = 0; @@ -5666,9 +5683,11 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, * so release it. */ if (req) { + synack_stamp = tcp_rsk(req)->snt_synack; tp->total_retrans = req->num_retrans; reqsk_fastopen_remove(sk, req, false); } else { + synack_stamp = tp->lsndtime; /* Make sure socket is routed, for correct metrics. */ icsk->icsk_af_ops->rebuild_header(sk); tcp_init_congestion_control(sk); @@ -5691,7 +5710,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, tp->snd_una = TCP_SKB_CB(skb)->ack_seq; tp->snd_wnd = ntohs(th->window) << tp->rx_opt.snd_wscale; tcp_init_wl(tp, TCP_SKB_CB(skb)->seq); - tcp_synack_rtt_meas(sk, req); + tcp_synack_rtt_meas(sk, synack_stamp); if (tp->rx_opt.tstamp_ok) tp->advmss -= TCPOLEN_TSTAMP_ALIGNED; @@ -5709,6 +5728,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, } else tcp_init_metrics(sk); + tcp_update_pacing_rate(sk); + /* Prevent spurious tcp_cwnd_restart() on first data packet */ tp->lsndtime = tcp_time_stamp; diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 3a7525e6c086..533c58a5cfb7 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -18,6 +18,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); + unsigned int sum_truesize = 0; struct tcphdr *th; unsigned int thlen; unsigned int seq; @@ -102,13 +103,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb, if (copy_destructor) { skb->destructor = gso_skb->destructor; skb->sk = gso_skb->sk; - /* {tcp|sock}_wfree() use exact truesize accounting : - * sum(skb->truesize) MUST be exactly be gso_skb->truesize - * So we account mss bytes of 'true size' for each segment. - * The last segment will contain the remaining. - */ - skb->truesize = mss; - gso_skb->truesize -= mss; + sum_truesize += skb->truesize; } skb = skb->next; th = tcp_hdr(skb); @@ -125,7 +120,9 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb, if (copy_destructor) { swap(gso_skb->sk, skb->sk); swap(gso_skb->destructor, skb->destructor); - swap(gso_skb->truesize, skb->truesize); + sum_truesize += skb->truesize; + atomic_add(sum_truesize - gso_skb->truesize, + &skb->sk->sk_wmem_alloc); } delta = htonl(oldlen + (skb_tail_pointer(skb) - diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index e6bb8256e59f..d46f2143305c 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -637,6 +637,8 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb unsigned int size = 0; unsigned int eff_sacks; + opts->options = 0; + #ifdef CONFIG_TCP_MD5SIG *md5 = tp->af_specific->md5_lookup(sk, sk); if (unlikely(*md5)) { @@ -984,8 +986,10 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb) static void tcp_set_skb_tso_segs(const struct sock *sk, struct sk_buff *skb, unsigned int mss_now) { - if (skb->len <= mss_now || !sk_can_gso(sk) || - skb->ip_summed == CHECKSUM_NONE) { + /* Make sure we own this skb before messing gso_size/gso_segs */ + WARN_ON_ONCE(skb_cloned(skb)); + + if (skb->len <= mss_now || skb->ip_summed == CHECKSUM_NONE) { /* Avoid the costly divide in the normal * non-TSO case. */ @@ -1065,9 +1069,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, if (nsize < 0) nsize = 0; - if (skb_cloned(skb) && - skb_is_nonlinear(skb) && - pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + if (skb_unclone(skb, GFP_ATOMIC)) return -ENOMEM; /* Get a new skb... force flag on. */ @@ -2342,6 +2344,8 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) int oldpcount = tcp_skb_pcount(skb); if (unlikely(oldpcount > 1)) { + if (skb_unclone(skb, GFP_ATOMIC)) + return -ENOMEM; tcp_init_tso_segs(sk, skb, cur_mss); tcp_adjust_pcount(sk, skb, oldpcount - tcp_skb_pcount(skb)); } diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 9a459be24af7..e1a63930a967 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -104,9 +104,14 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) const struct iphdr *iph = ip_hdr(skb); u8 *xprth = skb_network_header(skb) + iph->ihl * 4; struct flowi4 *fl4 = &fl->u.ip4; + int oif = 0; + + if (skb_dst(skb)) + oif = skb_dst(skb)->dev->ifindex; memset(fl4, 0, sizeof(struct flowi4)); fl4->flowi4_mark = skb->mark; + fl4->flowi4_oif = reverse ? skb->skb_iif : oif; if (!ip_is_fragment(iph)) { switch (iph->protocol) { @@ -235,7 +240,7 @@ static struct dst_ops xfrm4_dst_ops = { .destroy = xfrm4_dst_destroy, .ifdown = xfrm4_dst_ifdown, .local_out = __ip_local_out, - .gc_thresh = 1024, + .gc_thresh = 32768, }; static struct xfrm_policy_afinfo xfrm4_policy_afinfo = { diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 73784c3d4642..82e1da3a40b9 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -618,8 +618,7 @@ static void ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct ip_auth_hdr *ah = (struct ip_auth_hdr*)(skb->data+offset); struct xfrm_state *x; - if (type != ICMPV6_DEST_UNREACH && - type != ICMPV6_PKT_TOOBIG && + if (type != ICMPV6_PKT_TOOBIG && type != NDISC_REDIRECT) return; diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index d3618a78fcac..e67e63f9858d 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -436,8 +436,7 @@ static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct ip_esp_hdr *esph = (struct ip_esp_hdr *)(skb->data + offset); struct xfrm_state *x; - if (type != ICMPV6_DEST_UNREACH && - type != ICMPV6_PKT_TOOBIG && + if (type != ICMPV6_PKT_TOOBIG && type != NDISC_REDIRECT) return; diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 32b4a1675d82..066640e0ba8e 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -116,7 +116,7 @@ begintw: } if (unlikely(!INET6_TW_MATCH(sk, net, saddr, daddr, ports, dif))) { - sock_put(sk); + inet_twsk_put(inet_twsk(sk)); goto begintw; } goto out; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 7bb5446b9d73..bf4a9a084de5 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -976,6 +976,7 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu) if (t->parms.o_flags&GRE_SEQ) addend += 4; } + t->hlen = addend; if (p->flags & IP6_TNL_F_CAP_XMIT) { int strict = (ipv6_addr_type(&p->raddr) & @@ -1002,8 +1003,6 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu) } ip6_rt_put(rt); } - - t->hlen = addend; } static int ip6gre_tnl_change(struct ip6_tnl *t, @@ -1173,9 +1172,8 @@ done: static int ip6gre_tunnel_change_mtu(struct net_device *dev, int new_mtu) { - struct ip6_tnl *tunnel = netdev_priv(dev); if (new_mtu < 68 || - new_mtu > 0xFFF8 - dev->hard_header_len - tunnel->hlen) + new_mtu > 0xFFF8 - dev->hard_header_len) return -EINVAL; dev->mtu = new_mtu; return 0; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index a54c45ce4a48..91fb4e8212f5 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -105,7 +105,7 @@ static int ip6_finish_output2(struct sk_buff *skb) } rcu_read_lock_bh(); - nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr); + nexthop = rt6_nexthop((struct rt6_info *)dst); neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop); if (unlikely(!neigh)) neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false); @@ -874,7 +874,7 @@ static int ip6_dst_lookup_tail(struct sock *sk, */ rt = (struct rt6_info *) *dst; rcu_read_lock_bh(); - n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt, &fl6->daddr)); + n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt)); err = n && !(n->nud_state & NUD_VALID) ? -EINVAL : 0; rcu_read_unlock_bh(); @@ -1008,6 +1008,7 @@ static inline int ip6_ufo_append_data(struct sock *sk, { struct sk_buff *skb; + struct frag_hdr fhdr; int err; /* There is support for UDP large send offload by network @@ -1015,8 +1016,6 @@ static inline int ip6_ufo_append_data(struct sock *sk, * udp datagram */ if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL) { - struct frag_hdr fhdr; - skb = sock_alloc_send_skb(sk, hh_len + fragheaderlen + transhdrlen + 20, (flags & MSG_DONTWAIT), &err); @@ -1036,20 +1035,24 @@ static inline int ip6_ufo_append_data(struct sock *sk, skb->transport_header = skb->network_header + fragheaderlen; skb->protocol = htons(ETH_P_IPV6); - skb->ip_summed = CHECKSUM_PARTIAL; skb->csum = 0; - /* Specify the length of each IPv6 datagram fragment. - * It has to be a multiple of 8. - */ - skb_shinfo(skb)->gso_size = (mtu - fragheaderlen - - sizeof(struct frag_hdr)) & ~7; - skb_shinfo(skb)->gso_type = SKB_GSO_UDP; - ipv6_select_ident(&fhdr, rt); - skb_shinfo(skb)->ip6_frag_id = fhdr.identification; __skb_queue_tail(&sk->sk_write_queue, skb); + } else if (skb_is_gso(skb)) { + goto append; } + skb->ip_summed = CHECKSUM_PARTIAL; + /* Specify the length of each IPv6 datagram fragment. + * It has to be a multiple of 8. + */ + skb_shinfo(skb)->gso_size = (mtu - fragheaderlen - + sizeof(struct frag_hdr)) & ~7; + skb_shinfo(skb)->gso_type = SKB_GSO_UDP; + ipv6_select_ident(&fhdr, rt); + skb_shinfo(skb)->ip6_frag_id = fhdr.identification; + +append: return skb_append_datato_frags(sk, skb, getfrag, from, (length - transhdrlen)); } diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index a791552e0422..583b77e2f69b 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1430,9 +1430,17 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) static int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu) { - if (new_mtu < IPV6_MIN_MTU) { - return -EINVAL; + struct ip6_tnl *tnl = netdev_priv(dev); + + if (tnl->parms.proto == IPPROTO_IPIP) { + if (new_mtu < 68) + return -EINVAL; + } else { + if (new_mtu < IPV6_MIN_MTU) + return -EINVAL; } + if (new_mtu > 0xFFF8 - dev->hard_header_len) + return -EINVAL; dev->mtu = new_mtu; return 0; } diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index 5636a912074a..ce507d9e1c90 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -64,8 +64,7 @@ static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, (struct ip_comp_hdr *)(skb->data + offset); struct xfrm_state *x; - if (type != ICMPV6_DEST_UNREACH && - type != ICMPV6_PKT_TOOBIG && + if (type != ICMPV6_PKT_TOOBIG && type != NDISC_REDIRECT) return; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 44400c216dc6..710238f58aa9 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -349,6 +349,11 @@ ip6t_do_table(struct sk_buff *skb, local_bh_disable(); addend = xt_write_recseq_begin(); private = table->private; + /* + * Ensure we load private-> members after we've fetched the base + * pointer. + */ + smp_read_barrier_depends(); cpu = smp_processor_id(); table_base = private->entries[cpu]; jumpstack = (struct ip6t_entry **)private->jumpstack[cpu]; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index c979dd96d82a..04e17b3309fb 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -476,6 +476,24 @@ out: } #ifdef CONFIG_IPV6_ROUTER_PREF +struct __rt6_probe_work { + struct work_struct work; + struct in6_addr target; + struct net_device *dev; +}; + +static void rt6_probe_deferred(struct work_struct *w) +{ + struct in6_addr mcaddr; + struct __rt6_probe_work *work = + container_of(w, struct __rt6_probe_work, work); + + addrconf_addr_solict_mult(&work->target, &mcaddr); + ndisc_send_ns(work->dev, NULL, &work->target, &mcaddr, NULL); + dev_put(work->dev); + kfree(w); +} + static void rt6_probe(struct rt6_info *rt) { struct neighbour *neigh; @@ -499,17 +517,23 @@ static void rt6_probe(struct rt6_info *rt) if (!neigh || time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) { - struct in6_addr mcaddr; - struct in6_addr *target; + struct __rt6_probe_work *work; + + work = kmalloc(sizeof(*work), GFP_ATOMIC); - if (neigh) { + if (neigh && work) neigh->updated = jiffies; + + if (neigh) write_unlock(&neigh->lock); - } - target = (struct in6_addr *)&rt->rt6i_gateway; - addrconf_addr_solict_mult(target, &mcaddr); - ndisc_send_ns(rt->dst.dev, NULL, target, &mcaddr, NULL); + if (work) { + INIT_WORK(&work->work, rt6_probe_deferred); + work->target = rt->rt6i_gateway; + dev_hold(rt->dst.dev); + work->dev = rt->dst.dev; + schedule_work(&work->work); + } } else { out: write_unlock(&neigh->lock); @@ -851,7 +875,6 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, if (ort->rt6i_dst.plen != 128 && ipv6_addr_equal(&ort->rt6i_dst.addr, daddr)) rt->rt6i_flags |= RTF_ANYCAST; - rt->rt6i_gateway = *daddr; } rt->rt6i_flags |= RTF_CACHE; @@ -1064,10 +1087,13 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) if (rt->rt6i_genid != rt_genid_ipv6(dev_net(rt->dst.dev))) return NULL; - if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) - return dst; + if (!rt->rt6i_node || (rt->rt6i_node->fn_sernum != cookie)) + return NULL; - return NULL; + if (rt6_check_expired(rt)) + return NULL; + + return dst; } static struct dst_entry *ip6_negative_advice(struct dst_entry *dst) @@ -1338,6 +1364,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, rt->dst.flags |= DST_HOST; rt->dst.output = ip6_output; atomic_set(&rt->dst.__refcnt, 1); + rt->rt6i_gateway = fl6->daddr; rt->rt6i_dst.addr = fl6->daddr; rt->rt6i_dst.plen = 128; rt->rt6i_idev = idev; @@ -1873,7 +1900,10 @@ static struct rt6_info *ip6_rt_copy(struct rt6_info *ort, in6_dev_hold(rt->rt6i_idev); rt->dst.lastuse = jiffies; - rt->rt6i_gateway = ort->rt6i_gateway; + if (ort->rt6i_flags & RTF_GATEWAY) + rt->rt6i_gateway = ort->rt6i_gateway; + else + rt->rt6i_gateway = *dest; rt->rt6i_flags = ort->rt6i_flags; if ((ort->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) == (RTF_DEFAULT | RTF_ADDRCONF)) @@ -2160,6 +2190,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, else rt->rt6i_flags |= RTF_LOCAL; + rt->rt6i_gateway = *addr; rt->rt6i_dst.addr = *addr; rt->rt6i_dst.plen = 128; rt->rt6i_table = fib6_get_table(net, RT6_TABLE_LOCAL); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 72b7eaaf3ca0..18786098fd41 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1225,9 +1225,6 @@ do_udp_sendmsg: if (tclass < 0) tclass = np->tclass; - if (dontfrag < 0) - dontfrag = np->dontfrag; - if (msg->msg_flags&MSG_CONFIRM) goto do_confirm; back_from_confirm: @@ -1246,6 +1243,8 @@ back_from_confirm: up->pending = AF_INET6; do_append_data: + if (dontfrag < 0) + dontfrag = np->dontfrag; up->len += ulen; getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; err = ip6_append_data(sk, getfrag, msg->msg_iov, ulen, diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 23ed03d786c8..5f8e128c512d 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -135,9 +135,14 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) struct ipv6_opt_hdr *exthdr; const unsigned char *nh = skb_network_header(skb); u8 nexthdr = nh[IP6CB(skb)->nhoff]; + int oif = 0; + + if (skb_dst(skb)) + oif = skb_dst(skb)->dev->ifindex; memset(fl6, 0, sizeof(struct flowi6)); fl6->flowi6_mark = skb->mark; + fl6->flowi6_oif = reverse ? skb->skb_iif : oif; fl6->daddr = reverse ? hdr->saddr : hdr->daddr; fl6->saddr = reverse ? hdr->daddr : hdr->saddr; @@ -284,7 +289,7 @@ static struct dst_ops xfrm6_dst_ops = { .destroy = xfrm6_dst_destroy, .ifdown = xfrm6_dst_ifdown, .local_out = __ip6_local_out, - .gc_thresh = 1024, + .gc_thresh = 32768, }; static struct xfrm_policy_afinfo xfrm6_policy_afinfo = { diff --git a/net/key/af_key.c b/net/key/af_key.c index 9d585370c5b4..911ef03bf8fb 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1098,7 +1098,8 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net, x->id.proto = proto; x->id.spi = sa->sadb_sa_spi; - x->props.replay_window = sa->sadb_sa_replay; + x->props.replay_window = min_t(unsigned int, sa->sadb_sa_replay, + (sizeof(x->replay.bitmap) * 8)); if (sa->sadb_sa_flags & SADB_SAFLAGS_NOECN) x->props.flags |= XFRM_STATE_NOECN; if (sa->sadb_sa_flags & SADB_SAFLAGS_DECAP_DSCP) diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index feae495a0a30..b076e8309bc2 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -115,6 +115,11 @@ struct l2tp_net { static void l2tp_session_set_header_len(struct l2tp_session *session, int version); static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel); +static inline struct l2tp_tunnel *l2tp_tunnel(struct sock *sk) +{ + return sk->sk_user_data; +} + static inline struct l2tp_net *l2tp_pernet(struct net *net) { BUG_ON(!net); @@ -504,7 +509,7 @@ static inline int l2tp_verify_udp_checksum(struct sock *sk, return 0; #if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == PF_INET6) { + if (sk->sk_family == PF_INET6 && !l2tp_tunnel(sk)->v4mapped) { if (!uh->check) { LIMIT_NETDEBUG(KERN_INFO "L2TP: IPv6: checksum is 0\n"); return 1; @@ -1128,7 +1133,7 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, /* Queue the packet to IP for output */ skb->local_df = 1; #if IS_ENABLED(CONFIG_IPV6) - if (skb->sk->sk_family == PF_INET6) + if (skb->sk->sk_family == PF_INET6 && !tunnel->v4mapped) error = inet6_csk_xmit(skb, NULL); else #endif @@ -1255,7 +1260,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len /* Calculate UDP checksum if configured to do so */ #if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == PF_INET6) + if (sk->sk_family == PF_INET6 && !tunnel->v4mapped) l2tp_xmit_ipv6_csum(sk, skb, udp_len); else #endif @@ -1304,10 +1309,9 @@ EXPORT_SYMBOL_GPL(l2tp_xmit_skb); */ static void l2tp_tunnel_destruct(struct sock *sk) { - struct l2tp_tunnel *tunnel; + struct l2tp_tunnel *tunnel = l2tp_tunnel(sk); struct l2tp_net *pn; - tunnel = sk->sk_user_data; if (tunnel == NULL) goto end; @@ -1675,7 +1679,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 } /* Check if this socket has already been prepped */ - tunnel = (struct l2tp_tunnel *)sk->sk_user_data; + tunnel = l2tp_tunnel(sk); if (tunnel != NULL) { /* This socket has already been prepped */ err = -EBUSY; @@ -1704,6 +1708,24 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 if (cfg != NULL) tunnel->debug = cfg->debug; +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family == PF_INET6) { + struct ipv6_pinfo *np = inet6_sk(sk); + + if (ipv6_addr_v4mapped(&np->saddr) && + ipv6_addr_v4mapped(&np->daddr)) { + struct inet_sock *inet = inet_sk(sk); + + tunnel->v4mapped = true; + inet->inet_saddr = np->saddr.s6_addr32[3]; + inet->inet_rcv_saddr = np->rcv_saddr.s6_addr32[3]; + inet->inet_daddr = np->daddr.s6_addr32[3]; + } else { + tunnel->v4mapped = false; + } + } +#endif + /* Mark socket as an encapsulation socket. See net/ipv4/udp.c */ tunnel->encap = encap; if (encap == L2TP_ENCAPTYPE_UDP) { @@ -1712,7 +1734,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 udp_sk(sk)->encap_rcv = l2tp_udp_encap_recv; udp_sk(sk)->encap_destroy = l2tp_udp_encap_destroy; #if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == PF_INET6) + if (sk->sk_family == PF_INET6 && !tunnel->v4mapped) udpv6_encap_enable(); else #endif diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 66a559b104b6..6f251cbc2ed7 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -194,6 +194,9 @@ struct l2tp_tunnel { struct sock *sock; /* Parent socket */ int fd; /* Parent fd, if tunnel socket * was created by userspace */ +#if IS_ENABLED(CONFIG_IPV6) + bool v4mapped; +#endif struct work_struct del_work; diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 5ebee2ded9e9..8c46b271064a 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -353,7 +353,9 @@ static int pppol2tp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msgh goto error_put_sess_tun; } + local_bh_disable(); l2tp_xmit_skb(session, skb, session->hdr_len); + local_bh_enable(); sock_put(ps->tunnel_sock); sock_put(sk); @@ -422,7 +424,9 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb) skb->data[0] = ppph[0]; skb->data[1] = ppph[1]; + local_bh_disable(); l2tp_xmit_skb(session, skb, session->hdr_len); + local_bh_enable(); sock_put(sk_tun); sock_put(sk); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 2e7855a1b10d..629dee7ec9bf 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -3518,7 +3518,7 @@ static int ieee80211_probe_client(struct wiphy *wiphy, struct net_device *dev, return -EINVAL; } band = chanctx_conf->def.chan->band; - sta = sta_info_get(sdata, peer); + sta = sta_info_get_bss(sdata, peer); if (sta) { qos = test_sta_flag(sta, WLAN_STA_WME); } else { diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index b6186517ec56..076409526bcb 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -335,6 +335,7 @@ enum ieee80211_sta_flags { IEEE80211_STA_DISABLE_VHT = BIT(11), IEEE80211_STA_DISABLE_80P80MHZ = BIT(12), IEEE80211_STA_DISABLE_160MHZ = BIT(13), + IEEE80211_STA_DISABLE_WMM = BIT(14), }; struct ieee80211_mgd_auth_data { @@ -893,6 +894,8 @@ struct tpt_led_trigger { * that the scan completed. * @SCAN_ABORTED: Set for our scan work function when the driver reported * a scan complete for an aborted scan. + * @SCAN_HW_CANCELLED: Set for our scan work function when the scan is being + * cancelled. */ enum { SCAN_SW_SCANNING, @@ -900,6 +903,7 @@ enum { SCAN_ONCHANNEL_SCANNING, SCAN_COMPLETED, SCAN_ABORTED, + SCAN_HW_CANCELLED, }; /** diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 86e4ad56b573..54ebc8155b49 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -2717,7 +2717,7 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, */ ifmgd->wmm_last_param_set = -1; - if (elems.wmm_param) + if (!(ifmgd->flags & IEEE80211_STA_DISABLE_WMM) && elems.wmm_param) ieee80211_sta_wmm_params(local, sdata, elems.wmm_param, elems.wmm_param_len); else @@ -3152,7 +3152,8 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, ieee80211_sta_process_chanswitch(sdata, rx_status->mactime, &elems, true); - if (ieee80211_sta_wmm_params(local, sdata, elems.wmm_param, + if (!(ifmgd->flags & IEEE80211_STA_DISABLE_WMM) && + ieee80211_sta_wmm_params(local, sdata, elems.wmm_param, elems.wmm_param_len)) changed |= BSS_CHANGED_QOS; @@ -4135,6 +4136,44 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata, return err; } +static bool ieee80211_usable_wmm_params(struct ieee80211_sub_if_data *sdata, + const u8 *wmm_param, int len) +{ + const u8 *pos; + size_t left; + + if (len < 8) + return false; + + if (wmm_param[5] != 1 /* version */) + return false; + + pos = wmm_param + 8; + left = len - 8; + + for (; left >= 4; left -= 4, pos += 4) { + u8 aifsn = pos[0] & 0x0f; + u8 ecwmin = pos[1] & 0x0f; + u8 ecwmax = (pos[1] & 0xf0) >> 4; + int aci = (pos[0] >> 5) & 0x03; + + if (aifsn < 2) { + sdata_info(sdata, + "AP has invalid WMM params (AIFSN=%d for ACI %d), disabling WMM\n", + aifsn, aci); + return false; + } + if (ecwmin > ecwmax) { + sdata_info(sdata, + "AP has invalid WMM params (ECWmin/max=%d/%d for ACI %d), disabling WMM\n", + ecwmin, ecwmax, aci); + return false; + } + } + + return true; +} + int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, struct cfg80211_assoc_request *req) { @@ -4192,9 +4231,45 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, } /* prepare assoc data */ - + ifmgd->beacon_crc_valid = false; + assoc_data->wmm = bss->wmm_used && + (local->hw.queues >= IEEE80211_NUM_ACS); + if (assoc_data->wmm) { + /* try to check validity of WMM params IE */ + const struct cfg80211_bss_ies *ies; + const u8 *wp, *start, *end; + + rcu_read_lock(); + ies = rcu_dereference(req->bss->ies); + start = ies->data; + end = start + ies->len; + + while (true) { + wp = cfg80211_find_vendor_ie( + WLAN_OUI_MICROSOFT, + WLAN_OUI_TYPE_MICROSOFT_WMM, + start, end - start); + if (!wp) + break; + start = wp + wp[1] + 2; + /* if this IE is too short, try the next */ + if (wp[1] <= 4) + continue; + /* if this IE is WMM params, we found what we wanted */ + if (wp[6] == 1) + break; + } + + if (!wp || !ieee80211_usable_wmm_params(sdata, wp + 2, + wp[1] - 2)) { + assoc_data->wmm = false; + ifmgd->flags |= IEEE80211_STA_DISABLE_WMM; + } + rcu_read_unlock(); + } + /* * IEEE802.11n does not allow TKIP/WEP as pairwise ciphers in HT mode. * We still associate in non-HT mode (11a/b/g) if any one of these @@ -4224,18 +4299,22 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, /* Also disable HT if we don't support it or the AP doesn't use WMM */ sband = local->hw.wiphy->bands[req->bss->channel->band]; if (!sband->ht_cap.ht_supported || - local->hw.queues < IEEE80211_NUM_ACS || !bss->wmm_used) { + local->hw.queues < IEEE80211_NUM_ACS || !bss->wmm_used || + ifmgd->flags & IEEE80211_STA_DISABLE_WMM) { ifmgd->flags |= IEEE80211_STA_DISABLE_HT; - if (!bss->wmm_used) + if (!bss->wmm_used && + !(ifmgd->flags & IEEE80211_STA_DISABLE_WMM)) netdev_info(sdata->dev, "disabling HT as WMM/QoS is not supported by the AP\n"); } /* disable VHT if we don't support it or the AP doesn't use WMM */ if (!sband->vht_cap.vht_supported || - local->hw.queues < IEEE80211_NUM_ACS || !bss->wmm_used) { + local->hw.queues < IEEE80211_NUM_ACS || !bss->wmm_used || + ifmgd->flags & IEEE80211_STA_DISABLE_WMM) { ifmgd->flags |= IEEE80211_STA_DISABLE_VHT; - if (!bss->wmm_used) + if (!bss->wmm_used && + !(ifmgd->flags & IEEE80211_STA_DISABLE_WMM)) netdev_info(sdata->dev, "disabling VHT as WMM/QoS is not supported by the AP\n"); } @@ -4264,8 +4343,6 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, sdata->smps_mode = ifmgd->req_smps; assoc_data->capability = req->bss->capability; - assoc_data->wmm = bss->wmm_used && - (local->hw.queues >= IEEE80211_NUM_ACS); assoc_data->supp_rates = bss->supp_rates; assoc_data->supp_rates_len = bss->supp_rates_len; diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c index acd1f71adc03..0c2a29484c07 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -394,6 +394,8 @@ void ieee80211_sw_roc_work(struct work_struct *work) if (started) ieee80211_start_next_roc(local); + else if (list_empty(&local->roc_list)) + ieee80211_run_deferred_scan(local); } out_unlock: diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index e126605cec66..22b223f13c9f 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -235,7 +235,8 @@ static void rc_send_low_basicrate(s8 *idx, u32 basic_rates, static void __rate_control_send_low(struct ieee80211_hw *hw, struct ieee80211_supported_band *sband, struct ieee80211_sta *sta, - struct ieee80211_tx_info *info) + struct ieee80211_tx_info *info, + u32 rate_mask) { int i; u32 rate_flags = @@ -247,6 +248,12 @@ static void __rate_control_send_low(struct ieee80211_hw *hw, info->control.rates[0].idx = 0; for (i = 0; i < sband->n_bitrates; i++) { + if (!(rate_mask & BIT(i))) + continue; + + if ((rate_flags & sband->bitrates[i].flags) != rate_flags) + continue; + if (!rate_supported(sta, sband->band, i)) continue; @@ -274,7 +281,8 @@ bool rate_control_send_low(struct ieee80211_sta *pubsta, bool use_basicrate = false; if (!pubsta || !priv_sta || rc_no_data_or_no_ack_use_min(txrc)) { - __rate_control_send_low(txrc->hw, sband, pubsta, info); + __rate_control_send_low(txrc->hw, sband, pubsta, info, + txrc->rate_idx_mask); if (!pubsta && txrc->bss) { mcast_rate = txrc->bss_conf->mcast_rate[sband->band]; @@ -656,7 +664,8 @@ void ieee80211_get_tx_rates(struct ieee80211_vif *vif, rate_control_apply_mask(sdata, sta, sband, info, dest, max_rates); if (dest[0].idx < 0) - __rate_control_send_low(&sdata->local->hw, sband, sta, info); + __rate_control_send_low(&sdata->local->hw, sband, sta, info, + sdata->rc_rateidx_mask[info->band]); if (sta) rate_fixup_ratelist(vif, sband, info, dest, max_rates); diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 54395d7583ba..674eac1f996c 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -3056,6 +3056,9 @@ static int prepare_for_handlers(struct ieee80211_rx_data *rx, case NL80211_IFTYPE_ADHOC: if (!bssid) return 0; + if (ether_addr_equal(sdata->vif.addr, hdr->addr2) || + ether_addr_equal(sdata->u.ibss.bssid, hdr->addr2)) + return 0; if (ieee80211_is_beacon(hdr->frame_control)) { return 1; } else if (!ieee80211_bssid_match(bssid, sdata->u.ibss.bssid)) { diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 08afe74b98f4..d2d17a449224 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -238,6 +238,9 @@ static bool ieee80211_prep_hw_scan(struct ieee80211_local *local) enum ieee80211_band band; int i, ielen, n_chans; + if (test_bit(SCAN_HW_CANCELLED, &local->scanning)) + return false; + do { if (local->hw_scan_band == IEEE80211_NUM_BANDS) return false; @@ -940,7 +943,23 @@ void ieee80211_scan_cancel(struct ieee80211_local *local) if (!local->scan_req) goto out; + /* + * We have a scan running and the driver already reported completion, + * but the worker hasn't run yet or is stuck on the mutex - mark it as + * cancelled. + */ + if (test_bit(SCAN_HW_SCANNING, &local->scanning) && + test_bit(SCAN_COMPLETED, &local->scanning)) { + set_bit(SCAN_HW_CANCELLED, &local->scanning); + goto out; + } + if (test_bit(SCAN_HW_SCANNING, &local->scanning)) { + /* + * Make sure that __ieee80211_scan_completed doesn't trigger a + * scan on another band. + */ + set_bit(SCAN_HW_CANCELLED, &local->scanning); if (local->ops->cancel_hw_scan) drv_cancel_hw_scan(local, rcu_dereference_protected(local->scan_sdata, diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 368837fe3b80..78dc2e99027e 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -180,6 +180,9 @@ static void ieee80211_frame_acked(struct sta_info *sta, struct sk_buff *skb) struct ieee80211_local *local = sta->local; struct ieee80211_sub_if_data *sdata = sta->sdata; + if (local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS) + sta->last_rx = jiffies; + if (ieee80211_is_data_qos(mgmt->frame_control)) { struct ieee80211_hdr *hdr = (void *) skb->data; u8 *qc = ieee80211_get_qos_ctl(hdr); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 3456c0486b48..70b5a05c0a4e 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1120,7 +1120,8 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, tx->sta = rcu_dereference(sdata->u.vlan.sta); if (!tx->sta && sdata->dev->ieee80211_ptr->use_4addr) return TX_DROP; - } else if (info->flags & IEEE80211_TX_CTL_INJECTED || + } else if (info->flags & (IEEE80211_TX_CTL_INJECTED | + IEEE80211_TX_INTFL_NL80211_FRAME_TX) || tx->sdata->control_port_protocol == tx->skb->protocol) { tx->sta = sta_info_get_bss(sdata, hdr->addr1); } diff --git a/net/mac80211/util.c b/net/mac80211/util.c index e1b34a18b243..69e4ef5348a0 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -2103,7 +2103,7 @@ int ieee80211_add_ext_srates_ie(struct ieee80211_sub_if_data *sdata, { struct ieee80211_local *local = sdata->local; struct ieee80211_supported_band *sband; - int rate, skip, shift; + int rate, shift; u8 i, exrates, *pos; u32 basic_rates = sdata->vif.bss_conf.basic_rates; u32 rate_flags; @@ -2131,14 +2131,11 @@ int ieee80211_add_ext_srates_ie(struct ieee80211_sub_if_data *sdata, pos = skb_put(skb, exrates + 2); *pos++ = WLAN_EID_EXT_SUPP_RATES; *pos++ = exrates; - skip = 0; for (i = 8; i < sband->n_bitrates; i++) { u8 basic = 0; if ((rate_flags & sband->bitrates[i].flags) != rate_flags) continue; - if (skip++ < 8) - continue; if (need_basic && basic_rates & BIT(i)) basic = 0x80; rate = DIV_ROUND_UP(sband->bitrates[i].bitrate, @@ -2241,6 +2238,10 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local, } rate = cfg80211_calculate_bitrate(&ri); + if (WARN_ONCE(!rate, + "Invalid bitrate: flags=0x%x, idx=%d, vht_nss=%d\n", + status->flag, status->rate_idx, status->vht_nss)) + return 0; /* rewind from end of MPDU */ if (status->flag & RX_FLAG_MACTIME_END) diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index bdebd03bc8cd..70866d192efc 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -778,8 +778,8 @@ static int callforward_do_filter(const union nf_inet_addr *src, flowi6_to_flowi(&fl1), false)) { if (!afinfo->route(&init_net, (struct dst_entry **)&rt2, flowi6_to_flowi(&fl2), false)) { - if (!memcmp(&rt1->rt6i_gateway, &rt2->rt6i_gateway, - sizeof(rt1->rt6i_gateway)) && + if (ipv6_addr_equal(rt6_nexthop(rt1), + rt6_nexthop(rt2)) && rt1->dst.dev == rt2->dst.dev) ret = 1; dst_release(&rt2->dst); diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 8b03028cca69..227aa11e8409 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -845,8 +845,13 @@ xt_replace_table(struct xt_table *table, return NULL; } - table->private = newinfo; newinfo->initial_entries = private->initial_entries; + /* + * Ensure contents of newinfo are visible before assigning to + * private. + */ + smp_wmb(); + table->private = newinfo; /* * Even though table entries have now been swapped, other CPU's diff --git a/net/netfilter/xt_NFQUEUE.c b/net/netfilter/xt_NFQUEUE.c index 1e2fae32f81b..ed00fef58996 100644 --- a/net/netfilter/xt_NFQUEUE.c +++ b/net/netfilter/xt_NFQUEUE.c @@ -147,6 +147,7 @@ nfqueue_tg_v3(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_NFQ_info_v3 *info = par->targinfo; u32 queue = info->queuenum; + int ret; if (info->queues_total > 1) { if (info->flags & NFQ_FLAG_CPU_FANOUT) { @@ -157,7 +158,11 @@ nfqueue_tg_v3(struct sk_buff *skb, const struct xt_action_param *par) queue = nfqueue_hash(skb, par); } - return NF_QUEUE_NR(queue); + ret = NF_QUEUE_NR(queue); + if (info->flags & NFQ_FLAG_BYPASS) + ret |= NF_VERDICT_FLAG_QUEUE_BYPASS; + + return ret; } static struct xt_target nfqueue_tg_reg[] __read_mostly = { diff --git a/net/openvswitch/dp_notify.c b/net/openvswitch/dp_notify.c index c3235675f359..5c2dab276109 100644 --- a/net/openvswitch/dp_notify.c +++ b/net/openvswitch/dp_notify.c @@ -65,8 +65,7 @@ void ovs_dp_notify_wq(struct work_struct *work) continue; netdev_vport = netdev_vport_priv(vport); - if (netdev_vport->dev->reg_state == NETREG_UNREGISTERED || - netdev_vport->dev->reg_state == NETREG_UNREGISTERING) + if (!(netdev_vport->dev->priv_flags & IFF_OVS_DATAPATH)) dp_detach_port_notify(vport); } } @@ -88,6 +87,10 @@ static int dp_device_event(struct notifier_block *unused, unsigned long event, return NOTIFY_DONE; if (event == NETDEV_UNREGISTER) { + /* upper_dev_unlink and decrement promisc immediately */ + ovs_netdev_detach_dev(vport); + + /* schedule vport destroy, dev_put and genl notification */ ovs_net = net_generic(dev_net(dev), ovs_net_id); queue_work(system_wq, &ovs_net->dp_notify_work); } diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c index 09d93c13cfd6..d21f77d875ba 100644 --- a/net/openvswitch/vport-netdev.c +++ b/net/openvswitch/vport-netdev.c @@ -150,15 +150,25 @@ static void free_port_rcu(struct rcu_head *rcu) ovs_vport_free(vport_from_priv(netdev_vport)); } -static void netdev_destroy(struct vport *vport) +void ovs_netdev_detach_dev(struct vport *vport) { struct netdev_vport *netdev_vport = netdev_vport_priv(vport); - rtnl_lock(); + ASSERT_RTNL(); netdev_vport->dev->priv_flags &= ~IFF_OVS_DATAPATH; netdev_rx_handler_unregister(netdev_vport->dev); - netdev_upper_dev_unlink(netdev_vport->dev, get_dpdev(vport->dp)); + netdev_upper_dev_unlink(netdev_vport->dev, + netdev_master_upper_dev_get(netdev_vport->dev)); dev_set_promiscuity(netdev_vport->dev, -1); +} + +static void netdev_destroy(struct vport *vport) +{ + struct netdev_vport *netdev_vport = netdev_vport_priv(vport); + + rtnl_lock(); + if (netdev_vport->dev->priv_flags & IFF_OVS_DATAPATH) + ovs_netdev_detach_dev(vport); rtnl_unlock(); call_rcu(&netdev_vport->rcu, free_port_rcu); diff --git a/net/openvswitch/vport-netdev.h b/net/openvswitch/vport-netdev.h index dd298b5c5cdb..8df01c1127e5 100644 --- a/net/openvswitch/vport-netdev.h +++ b/net/openvswitch/vport-netdev.h @@ -39,5 +39,6 @@ netdev_vport_priv(const struct vport *vport) } const char *ovs_netdev_get_name(const struct vport *); +void ovs_netdev_detach_dev(struct vport *); #endif /* vport_netdev.h */ diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index a2fef8b10b96..fdc041c57853 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -255,6 +255,7 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) f->socket_hash != sk->sk_hash)) { f->credit = q->initial_quantum; f->socket_hash = sk->sk_hash; + f->time_next_packet = 0ULL; } return f; } @@ -472,20 +473,16 @@ begin: if (f->credit > 0 || !q->rate_enable) goto out; - if (skb->sk && skb->sk->sk_state != TCP_TIME_WAIT) { - rate = skb->sk->sk_pacing_rate ?: q->flow_default_rate; + rate = q->flow_max_rate; + if (skb->sk && skb->sk->sk_state != TCP_TIME_WAIT) + rate = min(skb->sk->sk_pacing_rate, rate); - rate = min(rate, q->flow_max_rate); - } else { - rate = q->flow_max_rate; - if (rate == ~0U) - goto out; - } - if (rate) { + if (rate != ~0U) { u32 plen = max(qdisc_pkt_len(skb), q->quantum); u64 len = (u64)plen * NSEC_PER_SEC; - do_div(len, rate); + if (likely(rate)) + do_div(len, rate); /* Since socket rate can change later, * clamp the delay to 125 ms. * TODO: maybe segment the too big skb, as in commit @@ -656,7 +653,7 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt) q->quantum = nla_get_u32(tb[TCA_FQ_QUANTUM]); if (tb[TCA_FQ_INITIAL_QUANTUM]) - q->quantum = nla_get_u32(tb[TCA_FQ_INITIAL_QUANTUM]); + q->initial_quantum = nla_get_u32(tb[TCA_FQ_INITIAL_QUANTUM]); if (tb[TCA_FQ_FLOW_DEFAULT_RATE]) q->flow_default_rate = nla_get_u32(tb[TCA_FQ_FLOW_DEFAULT_RATE]); @@ -735,12 +732,14 @@ static int fq_dump(struct Qdisc *sch, struct sk_buff *skb) if (opts == NULL) goto nla_put_failure; + /* TCA_FQ_FLOW_DEFAULT_RATE is not used anymore, + * do not bother giving its value + */ if (nla_put_u32(skb, TCA_FQ_PLIMIT, sch->limit) || nla_put_u32(skb, TCA_FQ_FLOW_PLIMIT, q->flow_plimit) || nla_put_u32(skb, TCA_FQ_QUANTUM, q->quantum) || nla_put_u32(skb, TCA_FQ_INITIAL_QUANTUM, q->initial_quantum) || nla_put_u32(skb, TCA_FQ_RATE_ENABLE, q->rate_enable) || - nla_put_u32(skb, TCA_FQ_FLOW_DEFAULT_RATE, q->flow_default_rate) || nla_put_u32(skb, TCA_FQ_FLOW_MAX_RATE, q->flow_max_rate) || nla_put_u32(skb, TCA_FQ_BUCKETS_LOG, q->fq_trees_log)) goto nla_put_failure; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index a6d788d45216..b87e83d07478 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -358,6 +358,21 @@ static psched_time_t packet_len_2_sched_time(unsigned int len, struct netem_sche return PSCHED_NS2TICKS(ticks); } +static void tfifo_reset(struct Qdisc *sch) +{ + struct netem_sched_data *q = qdisc_priv(sch); + struct rb_node *p; + + while ((p = rb_first(&q->t_root))) { + struct sk_buff *skb = netem_rb_to_skb(p); + + rb_erase(p, &q->t_root); + skb->next = NULL; + skb->prev = NULL; + kfree_skb(skb); + } +} + static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); @@ -520,6 +535,7 @@ static unsigned int netem_drop(struct Qdisc *sch) skb->next = NULL; skb->prev = NULL; len = qdisc_pkt_len(skb); + sch->qstats.backlog -= len; kfree_skb(skb); } } @@ -609,6 +625,7 @@ static void netem_reset(struct Qdisc *sch) struct netem_sched_data *q = qdisc_priv(sch); qdisc_reset_queue(sch); + tfifo_reset(sch); if (q->qdisc) qdisc_reset(q->qdisc); qdisc_watchdog_cancel(&q->watchdog); diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index e7b2d4fe2b6a..96a55910262c 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -279,7 +279,9 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, sctp_v6_to_addr(&dst_saddr, &fl6->saddr, htons(bp->port)); rcu_read_lock(); list_for_each_entry_rcu(laddr, &bp->address_list, list) { - if (!laddr->valid || (laddr->state != SCTP_ADDR_SRC)) + if (!laddr->valid || laddr->state == SCTP_ADDR_DEL || + (laddr->state != SCTP_ADDR_SRC && + !asoc->src_out_of_asoc_ok)) continue; /* Do not compare against v4 addrs */ diff --git a/net/sctp/output.c b/net/sctp/output.c index 0ac3a65daccb..319137340d15 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -536,7 +536,8 @@ int sctp_packet_transmit(struct sctp_packet *packet) * by CRC32-C as described in <draft-ietf-tsvwg-sctpcsum-02.txt>. */ if (!sctp_checksum_disable) { - if (!(dst->dev->features & NETIF_F_SCTP_CSUM)) { + if (!(dst->dev->features & NETIF_F_SCTP_CSUM) || + (dst_xfrm(dst) != NULL) || packet->ipfragok) { __u32 crc32 = sctp_start_cksum((__u8 *)sh, cksum_buf_len); /* 3) Put the resultant value into the checksum field in the diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 666c66842799..1a6eef39ab2f 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -860,7 +860,6 @@ static void sctp_cmd_delete_tcb(sctp_cmd_seq_t *cmds, (!asoc->temp) && (sk->sk_shutdown != SHUTDOWN_MASK)) return; - BUG_ON(asoc->peer.primary_path == NULL); sctp_unhash_established(asoc); sctp_association_free(asoc); } diff --git a/net/socket.c b/net/socket.c index ebed4b68f768..c226aceee65b 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1964,6 +1964,16 @@ struct used_address { unsigned int name_len; }; +static int copy_msghdr_from_user(struct msghdr *kmsg, + struct msghdr __user *umsg) +{ + if (copy_from_user(kmsg, umsg, sizeof(struct msghdr))) + return -EFAULT; + if (kmsg->msg_namelen > sizeof(struct sockaddr_storage)) + return -EINVAL; + return 0; +} + static int ___sys_sendmsg(struct socket *sock, struct msghdr __user *msg, struct msghdr *msg_sys, unsigned int flags, struct used_address *used_address) @@ -1982,8 +1992,11 @@ static int ___sys_sendmsg(struct socket *sock, struct msghdr __user *msg, if (MSG_CMSG_COMPAT & flags) { if (get_compat_msghdr(msg_sys, msg_compat)) return -EFAULT; - } else if (copy_from_user(msg_sys, msg, sizeof(struct msghdr))) - return -EFAULT; + } else { + err = copy_msghdr_from_user(msg_sys, msg); + if (err) + return err; + } if (msg_sys->msg_iovlen > UIO_FASTIOV) { err = -EMSGSIZE; @@ -2191,8 +2204,11 @@ static int ___sys_recvmsg(struct socket *sock, struct msghdr __user *msg, if (MSG_CMSG_COMPAT & flags) { if (get_compat_msghdr(msg_sys, msg_compat)) return -EFAULT; - } else if (copy_from_user(msg_sys, msg, sizeof(struct msghdr))) - return -EFAULT; + } else { + err = copy_msghdr_from_user(msg_sys, msg); + if (err) + return err; + } if (msg_sys->msg_iovlen > UIO_FASTIOV) { err = -EMSGSIZE; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 86de99ad2976..c1f403bed683 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1246,6 +1246,15 @@ static int unix_socketpair(struct socket *socka, struct socket *sockb) return 0; } +static void unix_sock_inherit_flags(const struct socket *old, + struct socket *new) +{ + if (test_bit(SOCK_PASSCRED, &old->flags)) + set_bit(SOCK_PASSCRED, &new->flags); + if (test_bit(SOCK_PASSSEC, &old->flags)) + set_bit(SOCK_PASSSEC, &new->flags); +} + static int unix_accept(struct socket *sock, struct socket *newsock, int flags) { struct sock *sk = sock->sk; @@ -1280,6 +1289,7 @@ static int unix_accept(struct socket *sock, struct socket *newsock, int flags) /* attach accepted sock to socket */ unix_state_lock(tsk); newsock->state = SS_CONNECTED; + unix_sock_inherit_flags(sock, newsock); sock_graft(tsk, newsock); unix_state_unlock(tsk); return 0; diff --git a/net/unix/diag.c b/net/unix/diag.c index d591091603bf..86fa0f3b2caf 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -124,6 +124,7 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r rep->udiag_family = AF_UNIX; rep->udiag_type = sk->sk_type; rep->udiag_state = sk->sk_state; + rep->pad = 0; rep->udiag_ino = sk_ino; sock_diag_save_cookie(sk, rep->udiag_cookie); diff --git a/net/wireless/core.c b/net/wireless/core.c index 67153964aad2..aff959e5a1b3 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -566,18 +566,13 @@ int wiphy_register(struct wiphy *wiphy) /* check and set up bitrates */ ieee80211_set_bitrate_flags(wiphy); - + rtnl_lock(); res = device_add(&rdev->wiphy.dev); - if (res) - return res; - - res = rfkill_register(rdev->rfkill); if (res) { - device_del(&rdev->wiphy.dev); + rtnl_unlock(); return res; } - rtnl_lock(); /* set up regulatory info */ wiphy_regulatory_register(wiphy); @@ -606,6 +601,15 @@ int wiphy_register(struct wiphy *wiphy) rdev->wiphy.registered = true; rtnl_unlock(); + + res = rfkill_register(rdev->rfkill); + if (res) { + rfkill_destroy(rdev->rfkill); + rdev->rfkill = NULL; + wiphy_unregister(&rdev->wiphy); + return res; + } + return 0; } EXPORT_SYMBOL(wiphy_register); @@ -640,7 +644,8 @@ void wiphy_unregister(struct wiphy *wiphy) rtnl_unlock(); __count == 0; })); - rfkill_unregister(rdev->rfkill); + if (rdev->rfkill) + rfkill_unregister(rdev->rfkill); rtnl_lock(); rdev->wiphy.registered = false; @@ -953,8 +958,6 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, case NETDEV_PRE_UP: if (!(wdev->wiphy->interface_modes & BIT(wdev->iftype))) return notifier_from_errno(-EOPNOTSUPP); - if (rfkill_blocked(rdev->rfkill)) - return notifier_from_errno(-ERFKILL); ret = cfg80211_can_add_interface(rdev, wdev->iftype); if (ret) return notifier_from_errno(ret); diff --git a/net/wireless/core.h b/net/wireless/core.h index 9ad43c619c54..3159e9c284c5 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -411,6 +411,9 @@ static inline int cfg80211_can_add_interface(struct cfg80211_registered_device *rdev, enum nl80211_iftype iftype) { + if (rfkill_blocked(rdev->rfkill)) + return -ERFKILL; + return cfg80211_can_change_interface(rdev, NULL, iftype); } diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c index 39bff7d36768..403fe29c024d 100644 --- a/net/wireless/ibss.c +++ b/net/wireless/ibss.c @@ -263,6 +263,8 @@ int cfg80211_ibss_wext_join(struct cfg80211_registered_device *rdev, if (chan->flags & IEEE80211_CHAN_DISABLED) continue; wdev->wext.ibss.chandef.chan = chan; + wdev->wext.ibss.chandef.center_freq1 = + chan->center_freq; break; } @@ -347,6 +349,7 @@ int cfg80211_ibss_wext_siwfreq(struct net_device *dev, if (chan) { wdev->wext.ibss.chandef.chan = chan; wdev->wext.ibss.chandef.width = NL80211_CHAN_WIDTH_20_NOHT; + wdev->wext.ibss.chandef.center_freq1 = freq; wdev->wext.ibss.channel_fixed = true; } else { /* cfg80211_ibss_wext_join will pick one if needed */ diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index af8d84a4a5b2..626dc3b5fd8d 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -2421,7 +2421,7 @@ static int nl80211_set_interface(struct sk_buff *skb, struct genl_info *info) change = true; } - if (flags && (*flags & NL80211_MNTR_FLAG_ACTIVE) && + if (flags && (*flags & MONITOR_FLAG_ACTIVE) && !(rdev->wiphy.features & NL80211_FEATURE_ACTIVE_MONITOR)) return -EOPNOTSUPP; @@ -2483,7 +2483,7 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info) info->attrs[NL80211_ATTR_MNTR_FLAGS] : NULL, &flags); - if (!err && (flags & NL80211_MNTR_FLAG_ACTIVE) && + if (!err && (flags & MONITOR_FLAG_ACTIVE) && !(rdev->wiphy.features & NL80211_FEATURE_ACTIVE_MONITOR)) return -EOPNOTSUPP; diff --git a/net/wireless/radiotap.c b/net/wireless/radiotap.c index 7d604c06c3dc..a271c27fac77 100644 --- a/net/wireless/radiotap.c +++ b/net/wireless/radiotap.c @@ -97,6 +97,10 @@ int ieee80211_radiotap_iterator_init( struct ieee80211_radiotap_header *radiotap_header, int max_length, const struct ieee80211_radiotap_vendor_namespaces *vns) { + /* check the radiotap header can actually be present */ + if (max_length < sizeof(struct ieee80211_radiotap_header)) + return -EINVAL; + /* Linux only supports version 0 radiotap format */ if (radiotap_header->it_version) return -EINVAL; @@ -131,7 +135,8 @@ int ieee80211_radiotap_iterator_init( */ if ((unsigned long)iterator->_arg - - (unsigned long)iterator->_rtheader > + (unsigned long)iterator->_rtheader + + sizeof(uint32_t) > (unsigned long)iterator->_max_length) return -EINVAL; } diff --git a/net/x25/Kconfig b/net/x25/Kconfig index c959312c45e3..e2fa133f9fba 100644 --- a/net/x25/Kconfig +++ b/net/x25/Kconfig @@ -16,8 +16,8 @@ config X25 if you want that) and the lower level data link layer protocol LAPB (say Y to "LAPB Data Link Driver" below if you want that). - You can read more about X.25 at <http://www.sangoma.com/x25.htm> and - <http://www.cisco.com/univercd/cc/td/doc/product/software/ios11/cbook/cx25.htm>. + You can read more about X.25 at <http://www.sangoma.com/tutorials/x25/> and + <http://docwiki.cisco.com/wiki/X.25>. Information about X.25 for Linux is contained in the files <file:Documentation/networking/x25.txt> and <file:Documentation/networking/x25-iface.txt>. diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c index 2906d520eea7..3be02b680268 100644 --- a/net/xfrm/xfrm_ipcomp.c +++ b/net/xfrm/xfrm_ipcomp.c @@ -141,14 +141,14 @@ static int ipcomp_compress(struct xfrm_state *x, struct sk_buff *skb) const int plen = skb->len; int dlen = IPCOMP_SCRATCH_SIZE; u8 *start = skb->data; - const int cpu = get_cpu(); - u8 *scratch = *per_cpu_ptr(ipcomp_scratches, cpu); - struct crypto_comp *tfm = *per_cpu_ptr(ipcd->tfms, cpu); + struct crypto_comp *tfm; + u8 *scratch; int err; local_bh_disable(); + scratch = *this_cpu_ptr(ipcomp_scratches); + tfm = *this_cpu_ptr(ipcd->tfms); err = crypto_comp_compress(tfm, start, plen, scratch, &dlen); - local_bh_enable(); if (err) goto out; @@ -158,13 +158,13 @@ static int ipcomp_compress(struct xfrm_state *x, struct sk_buff *skb) } memcpy(start + sizeof(struct ip_comp_hdr), scratch, dlen); - put_cpu(); + local_bh_enable(); pskb_trim(skb, dlen + sizeof(struct ip_comp_hdr)); return 0; out: - put_cpu(); + local_bh_enable(); return err; } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index ed38d5d81f9e..76e1873811d4 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -334,7 +334,8 @@ static void xfrm_policy_kill(struct xfrm_policy *policy) atomic_inc(&policy->genid); - del_timer(&policy->polq.hold_timer); + if (del_timer(&policy->polq.hold_timer)) + xfrm_pol_put(policy); xfrm_queue_purge(&policy->polq.hold_queue); if (del_timer(&policy->timer)) @@ -589,7 +590,8 @@ static void xfrm_policy_requeue(struct xfrm_policy *old, spin_lock_bh(&pq->hold_queue.lock); skb_queue_splice_init(&pq->hold_queue, &list); - del_timer(&pq->hold_timer); + if (del_timer(&pq->hold_timer)) + xfrm_pol_put(old); spin_unlock_bh(&pq->hold_queue.lock); if (skb_queue_empty(&list)) @@ -600,7 +602,8 @@ static void xfrm_policy_requeue(struct xfrm_policy *old, spin_lock_bh(&pq->hold_queue.lock); skb_queue_splice(&list, &pq->hold_queue); pq->timeout = XFRM_QUEUE_TMO_MIN; - mod_timer(&pq->hold_timer, jiffies); + if (!mod_timer(&pq->hold_timer, jiffies)) + xfrm_pol_hold(new); spin_unlock_bh(&pq->hold_queue.lock); } @@ -1769,6 +1772,10 @@ static void xfrm_policy_queue_process(unsigned long arg) spin_lock(&pq->hold_queue.lock); skb = skb_peek(&pq->hold_queue); + if (!skb) { + spin_unlock(&pq->hold_queue.lock); + goto out; + } dst = skb_dst(skb); sk = skb->sk; xfrm_decode_session(skb, &fl, dst->ops->family); @@ -1787,8 +1794,9 @@ static void xfrm_policy_queue_process(unsigned long arg) goto purge_queue; pq->timeout = pq->timeout << 1; - mod_timer(&pq->hold_timer, jiffies + pq->timeout); - return; + if (!mod_timer(&pq->hold_timer, jiffies + pq->timeout)) + xfrm_pol_hold(pol); + goto out; } dst_release(dst); @@ -1819,11 +1827,14 @@ static void xfrm_policy_queue_process(unsigned long arg) err = dst_output(skb); } +out: + xfrm_pol_put(pol); return; purge_queue: pq->timeout = 0; xfrm_queue_purge(&pq->hold_queue); + xfrm_pol_put(pol); } static int xdst_queue_output(struct sk_buff *skb) @@ -1831,7 +1842,8 @@ static int xdst_queue_output(struct sk_buff *skb) unsigned long sched_next; struct dst_entry *dst = skb_dst(skb); struct xfrm_dst *xdst = (struct xfrm_dst *) dst; - struct xfrm_policy_queue *pq = &xdst->pols[0]->polq; + struct xfrm_policy *pol = xdst->pols[0]; + struct xfrm_policy_queue *pq = &pol->polq; if (pq->hold_queue.qlen > XFRM_MAX_QUEUE_LEN) { kfree_skb(skb); @@ -1850,10 +1862,12 @@ static int xdst_queue_output(struct sk_buff *skb) if (del_timer(&pq->hold_timer)) { if (time_before(pq->hold_timer.expires, sched_next)) sched_next = pq->hold_timer.expires; + xfrm_pol_put(pol); } __skb_queue_tail(&pq->hold_queue, skb); - mod_timer(&pq->hold_timer, sched_next); + if (!mod_timer(&pq->hold_timer, sched_next)) + xfrm_pol_hold(pol); spin_unlock_bh(&pq->hold_queue.lock); diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c index 8dafe6d3c6e4..dab57daae408 100644 --- a/net/xfrm/xfrm_replay.c +++ b/net/xfrm/xfrm_replay.c @@ -61,9 +61,9 @@ static void xfrm_replay_notify(struct xfrm_state *x, int event) switch (event) { case XFRM_REPLAY_UPDATE: - if (x->replay_maxdiff && - (x->replay.seq - x->preplay.seq < x->replay_maxdiff) && - (x->replay.oseq - x->preplay.oseq < x->replay_maxdiff)) { + if (!x->replay_maxdiff || + ((x->replay.seq - x->preplay.seq < x->replay_maxdiff) && + (x->replay.oseq - x->preplay.oseq < x->replay_maxdiff))) { if (x->xflags & XFRM_TIME_DEFER) event = XFRM_REPLAY_TIMEOUT; else @@ -129,8 +129,7 @@ static int xfrm_replay_check(struct xfrm_state *x, return 0; diff = x->replay.seq - seq; - if (diff >= min_t(unsigned int, x->props.replay_window, - sizeof(x->replay.bitmap) * 8)) { + if (diff >= x->props.replay_window) { x->stats.replay_window++; goto err; } @@ -302,9 +301,10 @@ static void xfrm_replay_notify_bmp(struct xfrm_state *x, int event) switch (event) { case XFRM_REPLAY_UPDATE: - if (x->replay_maxdiff && - (replay_esn->seq - preplay_esn->seq < x->replay_maxdiff) && - (replay_esn->oseq - preplay_esn->oseq < x->replay_maxdiff)) { + if (!x->replay_maxdiff || + ((replay_esn->seq - preplay_esn->seq < x->replay_maxdiff) && + (replay_esn->oseq - preplay_esn->oseq + < x->replay_maxdiff))) { if (x->xflags & XFRM_TIME_DEFER) event = XFRM_REPLAY_TIMEOUT; else @@ -353,28 +353,30 @@ static void xfrm_replay_notify_esn(struct xfrm_state *x, int event) switch (event) { case XFRM_REPLAY_UPDATE: - if (!x->replay_maxdiff) - break; - - if (replay_esn->seq_hi == preplay_esn->seq_hi) - seq_diff = replay_esn->seq - preplay_esn->seq; - else - seq_diff = ~preplay_esn->seq + replay_esn->seq + 1; - - if (replay_esn->oseq_hi == preplay_esn->oseq_hi) - oseq_diff = replay_esn->oseq - preplay_esn->oseq; - else - oseq_diff = ~preplay_esn->oseq + replay_esn->oseq + 1; - - if (seq_diff < x->replay_maxdiff && - oseq_diff < x->replay_maxdiff) { + if (x->replay_maxdiff) { + if (replay_esn->seq_hi == preplay_esn->seq_hi) + seq_diff = replay_esn->seq - preplay_esn->seq; + else + seq_diff = ~preplay_esn->seq + replay_esn->seq + + 1; - if (x->xflags & XFRM_TIME_DEFER) - event = XFRM_REPLAY_TIMEOUT; + if (replay_esn->oseq_hi == preplay_esn->oseq_hi) + oseq_diff = replay_esn->oseq + - preplay_esn->oseq; else - return; + oseq_diff = ~preplay_esn->oseq + + replay_esn->oseq + 1; + + if (seq_diff >= x->replay_maxdiff || + oseq_diff >= x->replay_maxdiff) + break; } + if (x->xflags & XFRM_TIME_DEFER) + event = XFRM_REPLAY_TIMEOUT; + else + return; + break; case XFRM_REPLAY_TIMEOUT: diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 3f565e495ac6..f964d4c00ffb 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -446,7 +446,8 @@ static void copy_from_user_state(struct xfrm_state *x, struct xfrm_usersa_info * memcpy(&x->sel, &p->sel, sizeof(x->sel)); memcpy(&x->lft, &p->lft, sizeof(x->lft)); x->props.mode = p->mode; - x->props.replay_window = p->replay_window; + x->props.replay_window = min_t(unsigned int, p->replay_window, + sizeof(x->replay.bitmap) * 8); x->props.reqid = p->reqid; x->props.family = p->family; memcpy(&x->props.saddr, &p->saddr, sizeof(x->props.saddr)); @@ -1856,7 +1857,7 @@ static int xfrm_new_ae(struct sk_buff *skb, struct nlmsghdr *nlh, if (x->km.state != XFRM_STATE_VALID) goto out; - err = xfrm_replay_verify_len(x->replay_esn, rp); + err = xfrm_replay_verify_len(x->replay_esn, re); if (err) goto out; diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index 487ac6f37ca2..9a11f9f799f4 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -55,6 +55,7 @@ static struct sym_entry *table; static unsigned int table_size, table_cnt; static int all_symbols = 0; static char symbol_prefix_char = '\0'; +static unsigned long long kernel_start_addr = 0; int token_profit[0x10000]; @@ -65,7 +66,10 @@ unsigned char best_table_len[256]; static void usage(void) { - fprintf(stderr, "Usage: kallsyms [--all-symbols] [--symbol-prefix=<prefix char>] < in.map > out.S\n"); + fprintf(stderr, "Usage: kallsyms [--all-symbols] " + "[--symbol-prefix=<prefix char>] " + "[--page-offset=<CONFIG_PAGE_OFFSET>] " + "< in.map > out.S\n"); exit(1); } @@ -194,6 +198,9 @@ static int symbol_valid(struct sym_entry *s) int i; int offset = 1; + if (s->addr < kernel_start_addr) + return 0; + /* skip prefix char */ if (symbol_prefix_char && *(s->sym + 1) == symbol_prefix_char) offset++; @@ -646,6 +653,9 @@ int main(int argc, char **argv) if ((*p == '"' && *(p+2) == '"') || (*p == '\'' && *(p+2) == '\'')) p++; symbol_prefix_char = *p; + } else if (strncmp(argv[i], "--page-offset=", 14) == 0) { + const char *p = &argv[i][14]; + kernel_start_addr = strtoull(p, NULL, 16); } else usage(); } diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index 014994936b1c..32b10f53d0b4 100644 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -82,6 +82,8 @@ kallsyms() kallsymopt="${kallsymopt} --all-symbols" fi + kallsymopt="${kallsymopt} --page-offset=$CONFIG_PAGE_OFFSET" + local aflags="${KBUILD_AFLAGS} ${KBUILD_AFLAGS_KERNEL} \ ${NOSTDINC_FLAGS} ${LINUXINCLUDE} ${KBUILD_CPPFLAGS}" diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c index 95c2b2689a03..7db9954f1af2 100644 --- a/security/apparmor/apparmorfs.c +++ b/security/apparmor/apparmorfs.c @@ -580,15 +580,13 @@ static struct aa_namespace *__next_namespace(struct aa_namespace *root, /* check if the next ns is a sibling, parent, gp, .. */ parent = ns->parent; - while (parent) { + while (ns != root) { mutex_unlock(&ns->lock); next = list_entry_next(ns, base.list); if (!list_entry_is_head(next, &parent->sub_ns, base.list)) { mutex_lock(&next->lock); return next; } - if (parent == root) - return NULL; ns = parent; parent = parent->parent; } diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c index 345bec07a27d..705c2879d3a9 100644 --- a/security/apparmor/policy.c +++ b/security/apparmor/policy.c @@ -610,6 +610,7 @@ void aa_free_profile(struct aa_profile *profile) aa_put_dfa(profile->policy.dfa); aa_put_replacedby(profile->replacedby); + kzfree(profile->hash); kzfree(profile); } diff --git a/sound/arm/pxa2xx-pcm.c b/sound/arm/pxa2xx-pcm.c index 69a2455b4472..e6c727b317fb 100644 --- a/sound/arm/pxa2xx-pcm.c +++ b/sound/arm/pxa2xx-pcm.c @@ -11,6 +11,7 @@ */ #include <linux/module.h> +#include <linux/dma-mapping.h> #include <linux/dmaengine.h> #include <sound/core.h> @@ -83,8 +84,6 @@ static struct snd_pcm_ops pxa2xx_pcm_ops = { .mmap = pxa2xx_pcm_mmap, }; -static u64 pxa2xx_pcm_dmamask = 0xffffffff; - int pxa2xx_pcm_new(struct snd_card *card, struct pxa2xx_pcm_client *client, struct snd_pcm **rpcm) { @@ -100,10 +99,9 @@ int pxa2xx_pcm_new(struct snd_card *card, struct pxa2xx_pcm_client *client, pcm->private_data = client; pcm->private_free = pxa2xx_pcm_free_dma_buffers; - if (!card->dev->dma_mask) - card->dev->dma_mask = &pxa2xx_pcm_dmamask; - if (!card->dev->coherent_dma_mask) - card->dev->coherent_dma_mask = 0xffffffff; + ret = dma_coerce_mask_and_coherent(card->dev, DMA_BIT_MASK(32)); + if (ret) + goto out; if (play) { int stream = SNDRV_PCM_STREAM_PLAYBACK; diff --git a/sound/core/pcm.c b/sound/core/pcm.c index 17f45e8aa89c..e1e9e0c999fe 100644 --- a/sound/core/pcm.c +++ b/sound/core/pcm.c @@ -49,6 +49,8 @@ static struct snd_pcm *snd_pcm_get(struct snd_card *card, int device) struct snd_pcm *pcm; list_for_each_entry(pcm, &snd_pcm_devices, list) { + if (pcm->internal) + continue; if (pcm->card == card && pcm->device == device) return pcm; } @@ -60,6 +62,8 @@ static int snd_pcm_next(struct snd_card *card, int device) struct snd_pcm *pcm; list_for_each_entry(pcm, &snd_pcm_devices, list) { + if (pcm->internal) + continue; if (pcm->card == card && pcm->device > device) return pcm->device; else if (pcm->card->number > card->number) diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index 5b6c4e3c92ca..748c6a941963 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -4864,8 +4864,8 @@ static void hda_power_work(struct work_struct *work) spin_unlock(&codec->power_lock); state = hda_call_codec_suspend(codec, true); - codec->pm_down_notified = 0; - if (!bus->power_keep_link_on && (state & AC_PWRST_CLK_STOP_OK)) { + if (!codec->pm_down_notified && + !bus->power_keep_link_on && (state & AC_PWRST_CLK_STOP_OK)) { codec->pm_down_notified = 1; hda_call_pm_notify(bus, false); } diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c index ac41e9cdc976..b7c89dff7066 100644 --- a/sound/pci/hda/hda_generic.c +++ b/sound/pci/hda/hda_generic.c @@ -3531,7 +3531,7 @@ static int create_capture_mixers(struct hda_codec *codec) if (!multi) err = create_single_cap_vol_ctl(codec, n, vol, sw, inv_dmic); - else if (!multi_cap_vol) + else if (!multi_cap_vol && !inv_dmic) err = create_bind_cap_vol_ctl(codec, n, vol, sw); else err = create_multi_cap_vol_ctl(codec); @@ -4475,9 +4475,11 @@ int snd_hda_gen_build_controls(struct hda_codec *codec) true, &spec->vmaster_mute.sw_kctl); if (err < 0) return err; - if (spec->vmaster_mute.hook) + if (spec->vmaster_mute.hook) { snd_hda_add_vmaster_hook(codec, &spec->vmaster_mute, spec->vmaster_mute_enum); + snd_hda_sync_vmaster_hook(&spec->vmaster_mute); + } } free_kctls(spec); /* no longer needed */ diff --git a/sound/pci/hda/patch_analog.c b/sound/pci/hda/patch_analog.c index 0cbdd87dde6d..2aa2f579b4d6 100644 --- a/sound/pci/hda/patch_analog.c +++ b/sound/pci/hda/patch_analog.c @@ -968,6 +968,15 @@ static void ad1884_fixup_hp_eapd(struct hda_codec *codec, } } +static void ad1884_fixup_thinkpad(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + struct ad198x_spec *spec = codec->spec; + + if (action == HDA_FIXUP_ACT_PRE_PROBE) + spec->gen.keep_eapd_on = 1; +} + /* set magic COEFs for dmic */ static const struct hda_verb ad1884_dmic_init_verbs[] = { {0x01, AC_VERB_SET_COEF_INDEX, 0x13f7}, @@ -979,6 +988,7 @@ enum { AD1884_FIXUP_AMP_OVERRIDE, AD1884_FIXUP_HP_EAPD, AD1884_FIXUP_DMIC_COEF, + AD1884_FIXUP_THINKPAD, AD1884_FIXUP_HP_TOUCHSMART, }; @@ -997,6 +1007,12 @@ static const struct hda_fixup ad1884_fixups[] = { .type = HDA_FIXUP_VERBS, .v.verbs = ad1884_dmic_init_verbs, }, + [AD1884_FIXUP_THINKPAD] = { + .type = HDA_FIXUP_FUNC, + .v.func = ad1884_fixup_thinkpad, + .chained = true, + .chain_id = AD1884_FIXUP_DMIC_COEF, + }, [AD1884_FIXUP_HP_TOUCHSMART] = { .type = HDA_FIXUP_VERBS, .v.verbs = ad1884_dmic_init_verbs, @@ -1008,7 +1024,7 @@ static const struct hda_fixup ad1884_fixups[] = { static const struct snd_pci_quirk ad1884_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x2a82, "HP Touchsmart", AD1884_FIXUP_HP_TOUCHSMART), SND_PCI_QUIRK_VENDOR(0x103c, "HP", AD1884_FIXUP_HP_EAPD), - SND_PCI_QUIRK_VENDOR(0x17aa, "Lenovo Thinkpad", AD1884_FIXUP_DMIC_COEF), + SND_PCI_QUIRK_VENDOR(0x17aa, "Lenovo Thinkpad", AD1884_FIXUP_THINKPAD), {} }; diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index bf313bea7085..8ad554312b69 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -4623,6 +4623,7 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x05db, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x1632, "HP RP5800", ALC662_FIXUP_HP_RP5800), SND_PCI_QUIRK(0x1043, 0x1477, "ASUS N56VZ", ALC662_FIXUP_ASUS_MODE4), + SND_PCI_QUIRK(0x1043, 0x1bf3, "ASUS N76VZ", ALC662_FIXUP_ASUS_MODE4), SND_PCI_QUIRK(0x1043, 0x8469, "ASUS mobo", ALC662_FIXUP_NO_JACK_DETECT), SND_PCI_QUIRK(0x105b, 0x0cd6, "Foxconn", ALC662_FIXUP_ASUS_MODE2), SND_PCI_QUIRK(0x144d, 0xc051, "Samsung R720", ALC662_FIXUP_IDEAPAD), diff --git a/sound/pci/rme9652/hdsp.c b/sound/pci/rme9652/hdsp.c index 4f255dfee450..f59a321a6d6a 100644 --- a/sound/pci/rme9652/hdsp.c +++ b/sound/pci/rme9652/hdsp.c @@ -4845,6 +4845,7 @@ static int snd_hdsp_hwdep_ioctl(struct snd_hwdep *hw, struct file *file, unsigne if ((err = hdsp_get_iobox_version(hdsp)) < 0) return err; } + memset(&hdsp_version, 0, sizeof(hdsp_version)); hdsp_version.io_type = hdsp->io_type; hdsp_version.firmware_rev = hdsp->firmware_rev; if ((err = copy_to_user(argp, &hdsp_version, sizeof(hdsp_version)))) diff --git a/sound/soc/atmel/atmel-pcm.c b/sound/soc/atmel/atmel-pcm.c index 3109db7b9017..fbb87e3f1019 100644 --- a/sound/soc/atmel/atmel-pcm.c +++ b/sound/soc/atmel/atmel-pcm.c @@ -68,18 +68,15 @@ int atmel_pcm_mmap(struct snd_pcm_substream *substream, } EXPORT_SYMBOL_GPL(atmel_pcm_mmap); -static u64 atmel_pcm_dmamask = DMA_BIT_MASK(32); - int atmel_pcm_new(struct snd_soc_pcm_runtime *rtd) { struct snd_card *card = rtd->card->snd_card; struct snd_pcm *pcm = rtd->pcm; - int ret = 0; + int ret; - if (!card->dev->dma_mask) - card->dev->dma_mask = &atmel_pcm_dmamask; - if (!card->dev->coherent_dma_mask) - card->dev->coherent_dma_mask = DMA_BIT_MASK(32); + ret = dma_coerce_mask_and_coherent(card->dev, DMA_BIT_MASK(32)); + if (ret) + return ret; if (pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream) { pr_debug("atmel-pcm: allocating PCM playback DMA buffer\n"); diff --git a/sound/soc/blackfin/bf5xx-ac97-pcm.c b/sound/soc/blackfin/bf5xx-ac97-pcm.c index 53f84085bf1f..1d4c676eb6cc 100644 --- a/sound/soc/blackfin/bf5xx-ac97-pcm.c +++ b/sound/soc/blackfin/bf5xx-ac97-pcm.c @@ -415,19 +415,16 @@ static void bf5xx_pcm_free_dma_buffers(struct snd_pcm *pcm) } } -static u64 bf5xx_pcm_dmamask = DMA_BIT_MASK(32); - static int bf5xx_pcm_ac97_new(struct snd_soc_pcm_runtime *rtd) { struct snd_card *card = rtd->card->snd_card; struct snd_pcm *pcm = rtd->pcm; - int ret = 0; + int ret; pr_debug("%s enter\n", __func__); - if (!card->dev->dma_mask) - card->dev->dma_mask = &bf5xx_pcm_dmamask; - if (!card->dev->coherent_dma_mask) - card->dev->coherent_dma_mask = DMA_BIT_MASK(32); + ret = dma_coerce_mask_and_coherent(card->dev, DMA_BIT_MASK(32)); + if (ret) + return ret; if (pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream) { ret = bf5xx_pcm_preallocate_dma_buffer(pcm, diff --git a/sound/soc/blackfin/bf5xx-i2s-pcm.c b/sound/soc/blackfin/bf5xx-i2s-pcm.c index 9cb4a80df98e..2a5b43417fd5 100644 --- a/sound/soc/blackfin/bf5xx-i2s-pcm.c +++ b/sound/soc/blackfin/bf5xx-i2s-pcm.c @@ -323,18 +323,16 @@ static struct snd_pcm_ops bf5xx_pcm_i2s_ops = { .silence = bf5xx_pcm_silence, }; -static u64 bf5xx_pcm_dmamask = DMA_BIT_MASK(32); - static int bf5xx_pcm_i2s_new(struct snd_soc_pcm_runtime *rtd) { struct snd_card *card = rtd->card->snd_card; size_t size = bf5xx_pcm_hardware.buffer_bytes_max; + int ret; pr_debug("%s enter\n", __func__); - if (!card->dev->dma_mask) - card->dev->dma_mask = &bf5xx_pcm_dmamask; - if (!card->dev->coherent_dma_mask) - card->dev->coherent_dma_mask = DMA_BIT_MASK(32); + ret = dma_coerce_mask_and_coherent(card->dev, DMA_BIT_MASK(32)); + if (ret) + return ret; return snd_pcm_lib_preallocate_pages_for_all(rtd->pcm, SNDRV_DMA_TYPE_DEV, card->dev, size, size); diff --git a/sound/soc/codecs/pcm1681.c b/sound/soc/codecs/pcm1681.c index 651ce0923675..c91eba504f92 100644 --- a/sound/soc/codecs/pcm1681.c +++ b/sound/soc/codecs/pcm1681.c @@ -270,7 +270,7 @@ MODULE_DEVICE_TABLE(of, pcm1681_dt_ids); static const struct regmap_config pcm1681_regmap = { .reg_bits = 8, .val_bits = 8, - .max_register = ARRAY_SIZE(pcm1681_reg_defaults) + 1, + .max_register = 0x13, .reg_defaults = pcm1681_reg_defaults, .num_reg_defaults = ARRAY_SIZE(pcm1681_reg_defaults), .writeable_reg = pcm1681_writeable_reg, diff --git a/sound/soc/codecs/pcm1792a.c b/sound/soc/codecs/pcm1792a.c index 2a8eccf64c76..7613181123fe 100644 --- a/sound/soc/codecs/pcm1792a.c +++ b/sound/soc/codecs/pcm1792a.c @@ -188,7 +188,7 @@ MODULE_DEVICE_TABLE(of, pcm1792a_of_match); static const struct regmap_config pcm1792a_regmap = { .reg_bits = 8, .val_bits = 8, - .max_register = 24, + .max_register = 23, .reg_defaults = pcm1792a_reg_defaults, .num_reg_defaults = ARRAY_SIZE(pcm1792a_reg_defaults), .writeable_reg = pcm1792a_writeable_reg, diff --git a/sound/soc/codecs/tlv320aic3x.c b/sound/soc/codecs/tlv320aic3x.c index 6e3f269243e0..64ad84d8a306 100644 --- a/sound/soc/codecs/tlv320aic3x.c +++ b/sound/soc/codecs/tlv320aic3x.c @@ -674,6 +674,8 @@ static const struct snd_soc_dapm_route intercon[] = { /* Left Input */ {"Left Line1L Mux", "single-ended", "LINE1L"}, {"Left Line1L Mux", "differential", "LINE1L"}, + {"Left Line1R Mux", "single-ended", "LINE1R"}, + {"Left Line1R Mux", "differential", "LINE1R"}, {"Left Line2L Mux", "single-ended", "LINE2L"}, {"Left Line2L Mux", "differential", "LINE2L"}, @@ -690,6 +692,8 @@ static const struct snd_soc_dapm_route intercon[] = { /* Right Input */ {"Right Line1R Mux", "single-ended", "LINE1R"}, {"Right Line1R Mux", "differential", "LINE1R"}, + {"Right Line1L Mux", "single-ended", "LINE1L"}, + {"Right Line1L Mux", "differential", "LINE1L"}, {"Right Line2R Mux", "single-ended", "LINE2R"}, {"Right Line2R Mux", "differential", "LINE2R"}, diff --git a/sound/soc/codecs/wm_hubs.c b/sound/soc/codecs/wm_hubs.c index 8b50e5958de5..01daf655e20b 100644 --- a/sound/soc/codecs/wm_hubs.c +++ b/sound/soc/codecs/wm_hubs.c @@ -530,6 +530,7 @@ static int hp_supply_event(struct snd_soc_dapm_widget *w, hubs->hp_startup_mode); break; } + break; case SND_SOC_DAPM_PRE_PMD: snd_soc_update_bits(codec, WM8993_CHARGE_PUMP_1, diff --git a/sound/soc/davinci/davinci-pcm.c b/sound/soc/davinci/davinci-pcm.c index 8460edce1c3b..84a63c660ab9 100644 --- a/sound/soc/davinci/davinci-pcm.c +++ b/sound/soc/davinci/davinci-pcm.c @@ -844,18 +844,15 @@ static void davinci_pcm_free(struct snd_pcm *pcm) } } -static u64 davinci_pcm_dmamask = DMA_BIT_MASK(32); - static int davinci_pcm_new(struct snd_soc_pcm_runtime *rtd) { struct snd_card *card = rtd->card->snd_card; struct snd_pcm *pcm = rtd->pcm; int ret; - if (!card->dev->dma_mask) - card->dev->dma_mask = &davinci_pcm_dmamask; - if (!card->dev->coherent_dma_mask) - card->dev->coherent_dma_mask = DMA_BIT_MASK(32); + ret = dma_coerce_mask_and_coherent(card->dev, DMA_BIT_MASK(32)); + if (ret) + return ret; if (pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream) { ret = davinci_pcm_preallocate_dma_buffer(pcm, diff --git a/sound/soc/fsl/fsl_dma.c b/sound/soc/fsl/fsl_dma.c index 9cc5c1f82f09..f73c7eff8b23 100644 --- a/sound/soc/fsl/fsl_dma.c +++ b/sound/soc/fsl/fsl_dma.c @@ -298,14 +298,11 @@ static int fsl_dma_new(struct snd_soc_pcm_runtime *rtd) { struct snd_card *card = rtd->card->snd_card; struct snd_pcm *pcm = rtd->pcm; - static u64 fsl_dma_dmamask = DMA_BIT_MASK(36); int ret; - if (!card->dev->dma_mask) - card->dev->dma_mask = &fsl_dma_dmamask; - - if (!card->dev->coherent_dma_mask) - card->dev->coherent_dma_mask = fsl_dma_dmamask; + ret = dma_coerce_mask_and_coherent(card->dev, DMA_BIT_MASK(36)); + if (ret) + return ret; /* Some codecs have separate DAIs for playback and capture, so we * should allocate a DMA buffer only for the streams that are valid. diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c index c6b743978d5e..6b81d0ce2c44 100644 --- a/sound/soc/fsl/fsl_ssi.c +++ b/sound/soc/fsl/fsl_ssi.c @@ -936,7 +936,7 @@ static int fsl_ssi_probe(struct platform_device *pdev) ssi_private->ssi_phys = res.start; ssi_private->irq = irq_of_parse_and_map(np, 0); - if (ssi_private->irq == NO_IRQ) { + if (ssi_private->irq == 0) { dev_err(&pdev->dev, "no irq for node %s\n", np->full_name); return -ENXIO; } diff --git a/sound/soc/fsl/imx-mc13783.c b/sound/soc/fsl/imx-mc13783.c index a3d60d4bea4c..a2fd7321b5a9 100644 --- a/sound/soc/fsl/imx-mc13783.c +++ b/sound/soc/fsl/imx-mc13783.c @@ -112,7 +112,7 @@ static int imx_mc13783_probe(struct platform_device *pdev) return ret; } - if (machine_is_mx31_3ds()) { + if (machine_is_mx31_3ds() || machine_is_mx31moboard()) { imx_audmux_v2_configure_port(MX31_AUDMUX_PORT4_SSI_PINS_4, IMX_AUDMUX_V2_PTCR_SYN, IMX_AUDMUX_V2_PDCR_RXDSEL(MX31_AUDMUX_PORT1_SSI0) | diff --git a/sound/soc/fsl/imx-pcm-fiq.c b/sound/soc/fsl/imx-pcm-fiq.c index 34043c55f2a6..fd5f2fb955f1 100644 --- a/sound/soc/fsl/imx-pcm-fiq.c +++ b/sound/soc/fsl/imx-pcm-fiq.c @@ -272,18 +272,16 @@ static int imx_pcm_preallocate_dma_buffer(struct snd_pcm *pcm, int stream) return 0; } -static u64 imx_pcm_dmamask = DMA_BIT_MASK(32); - static int imx_pcm_new(struct snd_soc_pcm_runtime *rtd) { struct snd_card *card = rtd->card->snd_card; struct snd_pcm *pcm = rtd->pcm; - int ret = 0; + int ret; + + ret = dma_coerce_mask_and_coherent(card->dev, DMA_BIT_MASK(32)); + if (ret) + return ret; - if (!card->dev->dma_mask) - card->dev->dma_mask = &imx_pcm_dmamask; - if (!card->dev->coherent_dma_mask) - card->dev->coherent_dma_mask = DMA_BIT_MASK(32); if (pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream) { ret = imx_pcm_preallocate_dma_buffer(pcm, SNDRV_PCM_STREAM_PLAYBACK); diff --git a/sound/soc/fsl/imx-ssi.c b/sound/soc/fsl/imx-ssi.c index f58bcd85c07f..57d6941676ff 100644 --- a/sound/soc/fsl/imx-ssi.c +++ b/sound/soc/fsl/imx-ssi.c @@ -600,19 +600,17 @@ static int imx_ssi_probe(struct platform_device *pdev) ssi->fiq_params.dma_params_rx = &ssi->dma_params_rx; ssi->fiq_params.dma_params_tx = &ssi->dma_params_tx; - ret = imx_pcm_fiq_init(pdev, &ssi->fiq_params); - if (ret) - goto failed_pcm_fiq; + ssi->fiq_init = imx_pcm_fiq_init(pdev, &ssi->fiq_params); + ssi->dma_init = imx_pcm_dma_init(pdev); - ret = imx_pcm_dma_init(pdev); - if (ret) - goto failed_pcm_dma; + if (ssi->fiq_init && ssi->dma_init) { + ret = ssi->fiq_init; + goto failed_pcm; + } return 0; -failed_pcm_dma: - imx_pcm_fiq_exit(pdev); -failed_pcm_fiq: +failed_pcm: snd_soc_unregister_component(&pdev->dev); failed_register: release_mem_region(res->start, resource_size(res)); @@ -628,8 +626,11 @@ static int imx_ssi_remove(struct platform_device *pdev) struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0); struct imx_ssi *ssi = platform_get_drvdata(pdev); - imx_pcm_dma_exit(pdev); - imx_pcm_fiq_exit(pdev); + if (!ssi->dma_init) + imx_pcm_dma_exit(pdev); + + if (!ssi->fiq_init) + imx_pcm_fiq_exit(pdev); snd_soc_unregister_component(&pdev->dev); diff --git a/sound/soc/fsl/imx-ssi.h b/sound/soc/fsl/imx-ssi.h index fb1616ba8c59..560c40fc9ebb 100644 --- a/sound/soc/fsl/imx-ssi.h +++ b/sound/soc/fsl/imx-ssi.h @@ -211,6 +211,8 @@ struct imx_ssi { struct imx_dma_data filter_data_rx; struct imx_pcm_fiq_params fiq_params; + int fiq_init; + int dma_init; int enabled; }; diff --git a/sound/soc/fsl/mpc5200_dma.c b/sound/soc/fsl/mpc5200_dma.c index 2a847ca494b5..8fcf22416740 100644 --- a/sound/soc/fsl/mpc5200_dma.c +++ b/sound/soc/fsl/mpc5200_dma.c @@ -299,7 +299,6 @@ static struct snd_pcm_ops psc_dma_ops = { .hw_params = psc_dma_hw_params, }; -static u64 psc_dma_dmamask = DMA_BIT_MASK(32); static int psc_dma_new(struct snd_soc_pcm_runtime *rtd) { struct snd_card *card = rtd->card->snd_card; @@ -307,15 +306,14 @@ static int psc_dma_new(struct snd_soc_pcm_runtime *rtd) struct snd_pcm *pcm = rtd->pcm; struct psc_dma *psc_dma = snd_soc_dai_get_drvdata(rtd->cpu_dai); size_t size = psc_dma_hardware.buffer_bytes_max; - int rc = 0; + int rc; dev_dbg(rtd->platform->dev, "psc_dma_new(card=%p, dai=%p, pcm=%p)\n", card, dai, pcm); - if (!card->dev->dma_mask) - card->dev->dma_mask = &psc_dma_dmamask; - if (!card->dev->coherent_dma_mask) - card->dev->coherent_dma_mask = DMA_BIT_MASK(32); + rc = dma_coerce_mask_and_coherent(card->dev, DMA_BIT_MASK(32)); + if (rc) + return rc; if (pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream) { rc = snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, pcm->card->dev, diff --git a/sound/soc/jz4740/jz4740-pcm.c b/sound/soc/jz4740/jz4740-pcm.c index 710059292318..1d7ef28585e1 100644 --- a/sound/soc/jz4740/jz4740-pcm.c +++ b/sound/soc/jz4740/jz4740-pcm.c @@ -297,19 +297,15 @@ static void jz4740_pcm_free(struct snd_pcm *pcm) } } -static u64 jz4740_pcm_dmamask = DMA_BIT_MASK(32); - static int jz4740_pcm_new(struct snd_soc_pcm_runtime *rtd) { struct snd_card *card = rtd->card->snd_card; struct snd_pcm *pcm = rtd->pcm; - int ret = 0; - - if (!card->dev->dma_mask) - card->dev->dma_mask = &jz4740_pcm_dmamask; + int ret; - if (!card->dev->coherent_dma_mask) - card->dev->coherent_dma_mask = DMA_BIT_MASK(32); + ret = dma_coerce_mask_and_coherent(card->dev, DMA_BIT_MASK(32)); + if (ret) + return ret; if (pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream) { ret = jz4740_pcm_preallocate_dma_buffer(pcm, diff --git a/sound/soc/kirkwood/kirkwood-dma.c b/sound/soc/kirkwood/kirkwood-dma.c index b238434f92b0..3814bb037485 100644 --- a/sound/soc/kirkwood/kirkwood-dma.c +++ b/sound/soc/kirkwood/kirkwood-dma.c @@ -59,8 +59,6 @@ static struct snd_pcm_hardware kirkwood_dma_snd_hw = { .fifo_size = 0, }; -static u64 kirkwood_dma_dmamask = DMA_BIT_MASK(32); - static irqreturn_t kirkwood_dma_irq(int irq, void *dev_id) { struct kirkwood_dma_data *priv = dev_id; @@ -292,10 +290,9 @@ static int kirkwood_dma_new(struct snd_soc_pcm_runtime *rtd) struct snd_pcm *pcm = rtd->pcm; int ret; - if (!card->dev->dma_mask) - card->dev->dma_mask = &kirkwood_dma_dmamask; - if (!card->dev->coherent_dma_mask) - card->dev->coherent_dma_mask = DMA_BIT_MASK(32); + ret = dma_coerce_mask_and_coherent(card->dev, DMA_BIT_MASK(32)); + if (ret) + return ret; if (pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream) { ret = kirkwood_dma_preallocate_dma_buffer(pcm, diff --git a/sound/soc/nuc900/nuc900-pcm.c b/sound/soc/nuc900/nuc900-pcm.c index c894ff0f2580..f588ee45b4fd 100644 --- a/sound/soc/nuc900/nuc900-pcm.c +++ b/sound/soc/nuc900/nuc900-pcm.c @@ -314,16 +314,15 @@ static void nuc900_dma_free_dma_buffers(struct snd_pcm *pcm) snd_pcm_lib_preallocate_free_for_all(pcm); } -static u64 nuc900_pcm_dmamask = DMA_BIT_MASK(32); static int nuc900_dma_new(struct snd_soc_pcm_runtime *rtd) { struct snd_card *card = rtd->card->snd_card; struct snd_pcm *pcm = rtd->pcm; + int ret; - if (!card->dev->dma_mask) - card->dev->dma_mask = &nuc900_pcm_dmamask; - if (!card->dev->coherent_dma_mask) - card->dev->coherent_dma_mask = DMA_BIT_MASK(32); + ret = dma_coerce_mask_and_coherent(card->dev, DMA_BIT_MASK(32)); + if (ret) + return ret; snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV, card->dev, 4 * 1024, (4 * 1024) - 1); diff --git a/sound/soc/omap/Kconfig b/sound/soc/omap/Kconfig index daa78a0095fa..4a07f7179690 100644 --- a/sound/soc/omap/Kconfig +++ b/sound/soc/omap/Kconfig @@ -1,6 +1,6 @@ config SND_OMAP_SOC tristate "SoC Audio for the Texas Instruments OMAP chips" - depends on (ARCH_OMAP && DMA_OMAP) || (ARCH_ARM && COMPILE_TEST) + depends on (ARCH_OMAP && DMA_OMAP) || (ARM && COMPILE_TEST) select SND_DMAENGINE_PCM config SND_OMAP_SOC_DMIC @@ -26,7 +26,7 @@ config SND_OMAP_SOC_N810 config SND_OMAP_SOC_RX51 tristate "SoC Audio support for Nokia RX-51" - depends on SND_OMAP_SOC && ARCH_ARM && (MACH_NOKIA_RX51 || COMPILE_TEST) + depends on SND_OMAP_SOC && ARM && (MACH_NOKIA_RX51 || COMPILE_TEST) select SND_OMAP_SOC_MCBSP select SND_SOC_TLV320AIC3X select SND_SOC_TPA6130A2 diff --git a/sound/soc/omap/omap-pcm.c b/sound/soc/omap/omap-pcm.c index a11405de86e8..b8fa9862e54c 100644 --- a/sound/soc/omap/omap-pcm.c +++ b/sound/soc/omap/omap-pcm.c @@ -156,8 +156,6 @@ static struct snd_pcm_ops omap_pcm_ops = { .mmap = omap_pcm_mmap, }; -static u64 omap_pcm_dmamask = DMA_BIT_MASK(64); - static int omap_pcm_preallocate_dma_buffer(struct snd_pcm *pcm, int stream) { @@ -202,12 +200,11 @@ static int omap_pcm_new(struct snd_soc_pcm_runtime *rtd) { struct snd_card *card = rtd->card->snd_card; struct snd_pcm *pcm = rtd->pcm; - int ret = 0; + int ret; - if (!card->dev->dma_mask) - card->dev->dma_mask = &omap_pcm_dmamask; - if (!card->dev->coherent_dma_mask) - card->dev->coherent_dma_mask = DMA_BIT_MASK(64); + ret = dma_coerce_mask_and_coherent(card->dev, DMA_BIT_MASK(64)); + if (ret) + return ret; if (pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream) { ret = omap_pcm_preallocate_dma_buffer(pcm, diff --git a/sound/soc/pxa/pxa2xx-pcm.c b/sound/soc/pxa/pxa2xx-pcm.c index 806da27b8b67..d58b09f4f7a4 100644 --- a/sound/soc/pxa/pxa2xx-pcm.c +++ b/sound/soc/pxa/pxa2xx-pcm.c @@ -87,18 +87,15 @@ static struct snd_pcm_ops pxa2xx_pcm_ops = { .mmap = pxa2xx_pcm_mmap, }; -static u64 pxa2xx_pcm_dmamask = DMA_BIT_MASK(32); - static int pxa2xx_soc_pcm_new(struct snd_soc_pcm_runtime *rtd) { struct snd_card *card = rtd->card->snd_card; struct snd_pcm *pcm = rtd->pcm; - int ret = 0; + int ret; - if (!card->dev->dma_mask) - card->dev->dma_mask = &pxa2xx_pcm_dmamask; - if (!card->dev->coherent_dma_mask) - card->dev->coherent_dma_mask = DMA_BIT_MASK(32); + ret = dma_coerce_mask_and_coherent(card->dev, DMA_BIT_MASK(32)); + if (ret) + return ret; if (pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream) { ret = pxa2xx_pcm_preallocate_dma_buffer(pcm, diff --git a/sound/soc/s6000/s6000-pcm.c b/sound/soc/s6000/s6000-pcm.c index d0740a762963..283620a97fe7 100644 --- a/sound/soc/s6000/s6000-pcm.c +++ b/sound/soc/s6000/s6000-pcm.c @@ -444,8 +444,6 @@ static void s6000_pcm_free(struct snd_pcm *pcm) snd_pcm_lib_preallocate_free_for_all(pcm); } -static u64 s6000_pcm_dmamask = DMA_BIT_MASK(32); - static int s6000_pcm_new(struct snd_soc_pcm_runtime *runtime) { struct snd_card *card = runtime->card->snd_card; @@ -456,10 +454,9 @@ static int s6000_pcm_new(struct snd_soc_pcm_runtime *runtime) params = snd_soc_dai_get_dma_data(runtime->cpu_dai, pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream); - if (!card->dev->dma_mask) - card->dev->dma_mask = &s6000_pcm_dmamask; - if (!card->dev->coherent_dma_mask) - card->dev->coherent_dma_mask = DMA_BIT_MASK(32); + res = dma_coerce_mask_and_coherent(card->dev, DMA_BIT_MASK(32)); + if (res) + return res; if (params->dma_in) { s6dmac_disable_chan(DMA_MASK_DMAC(params->dma_in), diff --git a/sound/soc/samsung/dma.c b/sound/soc/samsung/dma.c index 9338d11e9216..fe2748b494d4 100644 --- a/sound/soc/samsung/dma.c +++ b/sound/soc/samsung/dma.c @@ -406,20 +406,17 @@ static void dma_free_dma_buffers(struct snd_pcm *pcm) } } -static u64 dma_mask = DMA_BIT_MASK(32); - static int dma_new(struct snd_soc_pcm_runtime *rtd) { struct snd_card *card = rtd->card->snd_card; struct snd_pcm *pcm = rtd->pcm; - int ret = 0; + int ret; pr_debug("Entered %s\n", __func__); - if (!card->dev->dma_mask) - card->dev->dma_mask = &dma_mask; - if (!card->dev->coherent_dma_mask) - card->dev->coherent_dma_mask = DMA_BIT_MASK(32); + ret = dma_coerce_mask_and_coherent(card->dev, DMA_BIT_MASK(32)); + if (ret) + return ret; if (pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream) { ret = preallocate_dma_buffer(pcm, diff --git a/sound/soc/samsung/idma.c b/sound/soc/samsung/idma.c index ce1e1e16f250..e4f318fc2f82 100644 --- a/sound/soc/samsung/idma.c +++ b/sound/soc/samsung/idma.c @@ -383,18 +383,15 @@ static int preallocate_idma_buffer(struct snd_pcm *pcm, int stream) return 0; } -static u64 idma_mask = DMA_BIT_MASK(32); - static int idma_new(struct snd_soc_pcm_runtime *rtd) { struct snd_card *card = rtd->card->snd_card; struct snd_pcm *pcm = rtd->pcm; - int ret = 0; + int ret; - if (!card->dev->dma_mask) - card->dev->dma_mask = &idma_mask; - if (!card->dev->coherent_dma_mask) - card->dev->coherent_dma_mask = DMA_BIT_MASK(32); + ret = dma_coerce_mask_and_coherent(card->dev, DMA_BIT_MASK(32)); + if (ret) + return ret; if (pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream) { ret = preallocate_idma_buffer(pcm, diff --git a/sound/soc/sh/rcar/rsnd.h b/sound/soc/sh/rcar/rsnd.h index 9cc6986a8cfb..5dd87f4c919e 100644 --- a/sound/soc/sh/rcar/rsnd.h +++ b/sound/soc/sh/rcar/rsnd.h @@ -220,8 +220,8 @@ int rsnd_gen_path_exit(struct rsnd_priv *priv, void __iomem *rsnd_gen_reg_get(struct rsnd_priv *priv, struct rsnd_mod *mod, enum rsnd_reg reg); -#define rsnd_is_gen1(s) ((s)->info->flags & RSND_GEN1) -#define rsnd_is_gen2(s) ((s)->info->flags & RSND_GEN2) +#define rsnd_is_gen1(s) (((s)->info->flags & RSND_GEN_MASK) == RSND_GEN1) +#define rsnd_is_gen2(s) (((s)->info->flags & RSND_GEN_MASK) == RSND_GEN2) /* * R-Car ADG diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index c17c14c394df..b2949aed1ac2 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -1949,7 +1949,7 @@ static ssize_t dapm_widget_power_read_file(struct file *file, w->active ? "active" : "inactive"); list_for_each_entry(p, &w->sources, list_sink) { - if (p->connected && !p->connected(w, p->sink)) + if (p->connected && !p->connected(w, p->source)) continue; if (p->connect) @@ -3495,6 +3495,7 @@ int snd_soc_dapm_new_dai_widgets(struct snd_soc_dapm_context *dapm, if (!w) { dev_err(dapm->dev, "ASoC: Failed to create %s widget\n", dai->driver->playback.stream_name); + return -ENOMEM; } w->priv = dai; @@ -3513,6 +3514,7 @@ int snd_soc_dapm_new_dai_widgets(struct snd_soc_dapm_context *dapm, if (!w) { dev_err(dapm->dev, "ASoC: Failed to create %s widget\n", dai->driver->capture.stream_name); + return -ENOMEM; } w->priv = dai; diff --git a/sound/usb/usx2y/us122l.c b/sound/usb/usx2y/us122l.c index d0323a693ba2..999550bbad40 100644 --- a/sound/usb/usx2y/us122l.c +++ b/sound/usb/usx2y/us122l.c @@ -262,7 +262,9 @@ static int usb_stream_hwdep_mmap(struct snd_hwdep *hw, } area->vm_ops = &usb_stream_hwdep_vm_ops; - area->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; + area->vm_flags |= VM_DONTDUMP; + if (!read) + area->vm_flags |= VM_DONTEXPAND; area->vm_private_data = us122l; atomic_inc(&us122l->mmap_count); out: diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index e297b74471b8..ca0d3d9f4bac 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -90,8 +90,20 @@ OPTIONS Number of mmap data pages. Must be a power of two. -g:: + Enables call-graph (stack chain/backtrace) recording. + --call-graph:: - Do call-graph (stack chain/backtrace) recording. + Setup and enable call-graph (stack chain/backtrace) recording, + implies -g. + + Allows specifying "fp" (frame pointer) or "dwarf" + (DWARF's CFI - Call Frame Information) as the method to collect + the information used to show the call graphs. + + In some systems, where binaries are build with gcc + --fomit-frame-pointer, using the "fp" method will produce bogus + call graphs, using "dwarf", if available (perf tools linked to + the libunwind library) should be used instead. -q:: --quiet:: diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index 58d6598a9686..6a118e71d003 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -140,20 +140,12 @@ Default is to monitor all CPUS. --asm-raw:: Show raw instruction encoding of assembly instructions. --G [type,min,order]:: +-G:: + Enables call-graph (stack chain/backtrace) recording. + --call-graph:: - Display call chains using type, min percent threshold and order. - type can be either: - - flat: single column, linear exposure of call chains. - - graph: use a graph tree, displaying absolute overhead rates. - - fractal: like graph, but displays relative rates. Each branch of - the tree is considered as a new profiled object. - - order can be either: - - callee: callee based call graph. - - caller: inverted caller based call graph. - - Default: fractal,0.5,callee. + Setup and enable call-graph (stack chain/backtrace) recording, + implies -G. --ignore-callees=<regex>:: Ignore callees of the function(s) matching the given regex. diff --git a/tools/perf/arch/arm/Makefile b/tools/perf/arch/arm/Makefile index 15130b50dfe3..fe9b61e322a5 100644 --- a/tools/perf/arch/arm/Makefile +++ b/tools/perf/arch/arm/Makefile @@ -2,3 +2,6 @@ ifndef NO_DWARF PERF_HAVE_DWARF_REGS := 1 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o endif +ifndef NO_LIBUNWIND +LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind.o +endif diff --git a/tools/perf/arch/arm/include/perf_regs.h b/tools/perf/arch/arm/include/perf_regs.h new file mode 100644 index 000000000000..2a1cfde66b69 --- /dev/null +++ b/tools/perf/arch/arm/include/perf_regs.h @@ -0,0 +1,54 @@ +#ifndef ARCH_PERF_REGS_H +#define ARCH_PERF_REGS_H + +#include <stdlib.h> +#include "../../util/types.h" +#include <asm/perf_regs.h> + +#define PERF_REGS_MASK ((1ULL << PERF_REG_ARM_MAX) - 1) +#define PERF_REG_IP PERF_REG_ARM_PC +#define PERF_REG_SP PERF_REG_ARM_SP + +static inline const char *perf_reg_name(int id) +{ + switch (id) { + case PERF_REG_ARM_R0: + return "r0"; + case PERF_REG_ARM_R1: + return "r1"; + case PERF_REG_ARM_R2: + return "r2"; + case PERF_REG_ARM_R3: + return "r3"; + case PERF_REG_ARM_R4: + return "r4"; + case PERF_REG_ARM_R5: + return "r5"; + case PERF_REG_ARM_R6: + return "r6"; + case PERF_REG_ARM_R7: + return "r7"; + case PERF_REG_ARM_R8: + return "r8"; + case PERF_REG_ARM_R9: + return "r9"; + case PERF_REG_ARM_R10: + return "r10"; + case PERF_REG_ARM_FP: + return "fp"; + case PERF_REG_ARM_IP: + return "ip"; + case PERF_REG_ARM_SP: + return "sp"; + case PERF_REG_ARM_LR: + return "lr"; + case PERF_REG_ARM_PC: + return "pc"; + default: + return NULL; + } + + return NULL; +} + +#endif /* ARCH_PERF_REGS_H */ diff --git a/tools/perf/arch/arm/util/unwind.c b/tools/perf/arch/arm/util/unwind.c new file mode 100644 index 000000000000..da3dc950550c --- /dev/null +++ b/tools/perf/arch/arm/util/unwind.c @@ -0,0 +1,48 @@ + +#include <errno.h> +#include <libunwind.h> +#include "perf_regs.h" +#include "../../util/unwind.h" + +int unwind__arch_reg_id(int regnum) +{ + switch (regnum) { + case UNW_ARM_R0: + return PERF_REG_ARM_R0; + case UNW_ARM_R1: + return PERF_REG_ARM_R1; + case UNW_ARM_R2: + return PERF_REG_ARM_R2; + case UNW_ARM_R3: + return PERF_REG_ARM_R3; + case UNW_ARM_R4: + return PERF_REG_ARM_R4; + case UNW_ARM_R5: + return PERF_REG_ARM_R5; + case UNW_ARM_R6: + return PERF_REG_ARM_R6; + case UNW_ARM_R7: + return PERF_REG_ARM_R7; + case UNW_ARM_R8: + return PERF_REG_ARM_R8; + case UNW_ARM_R9: + return PERF_REG_ARM_R9; + case UNW_ARM_R10: + return PERF_REG_ARM_R10; + case UNW_ARM_R11: + return PERF_REG_ARM_FP; + case UNW_ARM_R12: + return PERF_REG_ARM_IP; + case UNW_ARM_R13: + return PERF_REG_ARM_SP; + case UNW_ARM_R14: + return PERF_REG_ARM_LR; + case UNW_ARM_R15: + return PERF_REG_ARM_PC; + default: + pr_err("unwind: invalid reg id %d\n", regnum); + return -EINVAL; + } + + return -EINVAL; +} diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 935d52216c89..fbc2888d6495 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -888,11 +888,18 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx, while ((event = perf_evlist__mmap_read(kvm->evlist, idx)) != NULL) { err = perf_evlist__parse_sample(kvm->evlist, event, &sample); if (err) { + perf_evlist__mmap_consume(kvm->evlist, idx); pr_err("Failed to parse sample\n"); return -1; } err = perf_session_queue_event(kvm->session, event, &sample, 0); + /* + * FIXME: Here we can't consume the event, as perf_session_queue_event will + * point to it, and it'll get possibly overwritten by the kernel. + */ + perf_evlist__mmap_consume(kvm->evlist, idx); + if (err) { pr_err("Failed to enqueue sample: %d\n", err); return -1; diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index a41ac41546c9..d04651484640 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -712,21 +712,12 @@ static int get_stack_size(char *str, unsigned long *_size) } #endif /* LIBUNWIND_SUPPORT */ -int record_parse_callchain_opt(const struct option *opt, - const char *arg, int unset) +int record_parse_callchain(const char *arg, struct perf_record_opts *opts) { - struct perf_record_opts *opts = opt->value; char *tok, *name, *saveptr = NULL; char *buf; int ret = -1; - /* --no-call-graph */ - if (unset) - return 0; - - /* We specified default option if none is provided. */ - BUG_ON(!arg); - /* We need buffer that we know we can write to. */ buf = malloc(strlen(arg) + 1); if (!buf) @@ -764,13 +755,9 @@ int record_parse_callchain_opt(const struct option *opt, ret = get_stack_size(tok, &size); opts->stack_dump_size = size; } - - if (!ret) - pr_debug("callchain: stack dump size %d\n", - opts->stack_dump_size); #endif /* LIBUNWIND_SUPPORT */ } else { - pr_err("callchain: Unknown -g option " + pr_err("callchain: Unknown --call-graph option " "value: %s\n", arg); break; } @@ -778,13 +765,52 @@ int record_parse_callchain_opt(const struct option *opt, } while (0); free(buf); + return ret; +} + +static void callchain_debug(struct perf_record_opts *opts) +{ + pr_debug("callchain: type %d\n", opts->call_graph); + if (opts->call_graph == CALLCHAIN_DWARF) + pr_debug("callchain: stack dump size %d\n", + opts->stack_dump_size); +} + +int record_parse_callchain_opt(const struct option *opt, + const char *arg, + int unset) +{ + struct perf_record_opts *opts = opt->value; + int ret; + + /* --no-call-graph */ + if (unset) { + opts->call_graph = CALLCHAIN_NONE; + pr_debug("callchain: disabled\n"); + return 0; + } + + ret = record_parse_callchain(arg, opts); if (!ret) - pr_debug("callchain: type %d\n", opts->call_graph); + callchain_debug(opts); return ret; } +int record_callchain_opt(const struct option *opt, + const char *arg __maybe_unused, + int unset __maybe_unused) +{ + struct perf_record_opts *opts = opt->value; + + if (opts->call_graph == CALLCHAIN_NONE) + opts->call_graph = CALLCHAIN_FP; + + callchain_debug(opts); + return 0; +} + static const char * const record_usage[] = { "perf record [<options>] [<command>]", "perf record [<options>] -- <command> [<options>]", @@ -813,12 +839,12 @@ static struct perf_record record = { }, }; -#define CALLCHAIN_HELP "do call-graph (stack chain/backtrace) recording: " +#define CALLCHAIN_HELP "setup and enables call-graph (stack chain/backtrace) recording: " #ifdef LIBUNWIND_SUPPORT -const char record_callchain_help[] = CALLCHAIN_HELP "[fp] dwarf"; +const char record_callchain_help[] = CALLCHAIN_HELP "fp dwarf"; #else -const char record_callchain_help[] = CALLCHAIN_HELP "[fp]"; +const char record_callchain_help[] = CALLCHAIN_HELP "fp"; #endif /* @@ -858,9 +884,12 @@ const struct option record_options[] = { "number of mmap data pages"), OPT_BOOLEAN(0, "group", &record.opts.group, "put the counters into a counter group"), - OPT_CALLBACK_DEFAULT('g', "call-graph", &record.opts, - "mode[,dump_size]", record_callchain_help, - &record_parse_callchain_opt, "fp"), + OPT_CALLBACK_NOOPT('g', NULL, &record.opts, + NULL, "enables call-graph recording" , + &record_callchain_opt), + OPT_CALLBACK(0, "call-graph", &record.opts, + "mode[,dump_size]", record_callchain_help, + &record_parse_callchain_opt), OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"), OPT_BOOLEAN('q', "quiet", &quiet, "don't print any message"), diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 212214162bb2..5a11f13e56f9 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -810,7 +810,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) ret = perf_evlist__parse_sample(top->evlist, event, &sample); if (ret) { pr_err("Can't parse sample, err = %d\n", ret); - continue; + goto next_event; } evsel = perf_evlist__id2evsel(session->evlist, sample.id); @@ -825,13 +825,13 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) case PERF_RECORD_MISC_USER: ++top->us_samples; if (top->hide_user_symbols) - continue; + goto next_event; machine = &session->machines.host; break; case PERF_RECORD_MISC_KERNEL: ++top->kernel_samples; if (top->hide_kernel_symbols) - continue; + goto next_event; machine = &session->machines.host; break; case PERF_RECORD_MISC_GUEST_KERNEL: @@ -847,7 +847,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) */ /* Fall thru */ default: - continue; + goto next_event; } @@ -859,6 +859,8 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) machine__process_event(machine, event); } else ++session->stats.nr_unknown_events; +next_event: + perf_evlist__mmap_consume(top->evlist, idx); } } @@ -1016,16 +1018,16 @@ out_delete: } static int -parse_callchain_opt(const struct option *opt, const char *arg, int unset) +callchain_opt(const struct option *opt, const char *arg, int unset) { - /* - * --no-call-graph - */ - if (unset) - return 0; - symbol_conf.use_callchain = true; + return record_callchain_opt(opt, arg, unset); +} +static int +parse_callchain_opt(const struct option *opt, const char *arg, int unset) +{ + symbol_conf.use_callchain = true; return record_parse_callchain_opt(opt, arg, unset); } @@ -1106,9 +1108,12 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) "sort by key(s): pid, comm, dso, symbol, parent, weight, local_weight"), OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples, "Show a column with the number of samples"), - OPT_CALLBACK_DEFAULT('G', "call-graph", &top.record_opts, - "mode[,dump_size]", record_callchain_help, - &parse_callchain_opt, "fp"), + OPT_CALLBACK_NOOPT('G', NULL, &top.record_opts, + NULL, "enables call-graph recording", + &callchain_opt), + OPT_CALLBACK(0, "call-graph", &top.record_opts, + "mode[,dump_size]", record_callchain_help, + &parse_callchain_opt), OPT_CALLBACK(0, "ignore-callees", NULL, "regex", "ignore callees of these functions in call graphs", report_parse_ignore_callees_opt), diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 71aa3e35406b..99c8d9ad6729 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -987,7 +987,7 @@ again: err = perf_evlist__parse_sample(evlist, event, &sample); if (err) { fprintf(trace->output, "Can't parse sample, err = %d, skipping...\n", err); - continue; + goto next_event; } if (trace->base_time == 0) @@ -1001,18 +1001,20 @@ again: evsel = perf_evlist__id2evsel(evlist, sample.id); if (evsel == NULL) { fprintf(trace->output, "Unknown tp ID %" PRIu64 ", skipping...\n", sample.id); - continue; + goto next_event; } if (sample.raw_data == NULL) { fprintf(trace->output, "%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n", perf_evsel__name(evsel), sample.tid, sample.cpu, sample.raw_size); - continue; + goto next_event; } handler = evsel->handler.func; handler(trace, evsel, &sample); +next_event: + perf_evlist__mmap_consume(evlist, i); if (done) goto out_unmap_evlist; diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index 5f6f9b3271bb..75b93d7f7860 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -29,6 +29,10 @@ ifeq ($(ARCH),x86_64) NO_PERF_REGS := 0 LIBUNWIND_LIBS = -lunwind -lunwind-x86_64 endif +ifeq ($(ARCH),arm) + NO_PERF_REGS := 0 + LIBUNWIND_LIBS = -lunwind -lunwind-arm +endif ifeq ($(NO_PERF_REGS),0) CFLAGS += -DHAVE_PERF_REGS @@ -208,8 +212,7 @@ ifeq ($(call try-cc,$(SOURCE_ELF_MMAP),$(FLAGS_LIBELF),-DLIBELF_MMAP),y) endif # try-cc endif # NO_LIBELF -# There's only x86 (both 32 and 64) support for CFI unwind so far -ifneq ($(ARCH),x86) +ifeq ($(LIBUNWIND_LIBS),) NO_LIBUNWIND := 1 endif @@ -223,9 +226,13 @@ endif FLAGS_UNWIND=$(LIBUNWIND_CFLAGS) $(CFLAGS) $(LIBUNWIND_LDFLAGS) $(LDFLAGS) $(EXTLIBS) $(LIBUNWIND_LIBS) ifneq ($(call try-cc,$(SOURCE_LIBUNWIND),$(FLAGS_UNWIND),libunwind),y) - msg := $(warning No libunwind found, disabling post unwind support. Please install libunwind-dev[el] >= 0.99); + msg := $(warning No libunwind found, disabling post unwind support. Please install libunwind-dev[el] >= 1.1); NO_LIBUNWIND := 1 endif # Libunwind support +ifneq ($(call try-cc,$(SOURCE_LIBUNWIND_DEBUG_FRAME),$(FLAGS_UNWIND),libunwind debug_frame),y) + msg := $(warning No debug_frame support found in libunwind); +CFLAGS += -DNO_LIBUNWIND_DEBUG_FRAME +endif # debug_frame support in libunwind endif # NO_LIBUNWIND ifndef NO_LIBUNWIND diff --git a/tools/perf/config/feature-tests.mak b/tools/perf/config/feature-tests.mak index f79305739ecc..028fe997d5eb 100644 --- a/tools/perf/config/feature-tests.mak +++ b/tools/perf/config/feature-tests.mak @@ -185,7 +185,6 @@ extern int UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as, unw_proc_info_t *pi, int need_unwind_info, void *arg); - #define dwarf_search_unwind_table UNW_OBJ(dwarf_search_unwind_table) int main(void) @@ -197,6 +196,26 @@ int main(void) return 0; } endef + +define SOURCE_LIBUNWIND_DEBUG_FRAME +#include <libunwind.h> +#include <stdlib.h> + +extern int +UNW_OBJ(dwarf_find_debug_frame) (int found, unw_dyn_info_t *di_debug, + unw_word_t ip, unw_word_t segbase, + const char *obj_name, unw_word_t start, + unw_word_t end); + +#define dwarf_find_debug_frame UNW_OBJ(dwarf_find_debug_frame) + +int main(void) +{ + dwarf_find_debug_frame(0, NULL, 0, 0, NULL, 0, 0); + return 0; +} +endef + endif ifndef NO_BACKTRACE diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 6fb781d5586c..e3fedfa2906e 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -290,6 +290,7 @@ static int process_events(struct machine *machine, struct perf_evlist *evlist, for (i = 0; i < evlist->nr_mmaps; i++) { while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) { ret = process_event(machine, evlist, event, state); + perf_evlist__mmap_consume(evlist, i); if (ret < 0) return ret; } diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c index d444ea2c47d9..376c35608534 100644 --- a/tools/perf/tests/keep-tracking.c +++ b/tools/perf/tests/keep-tracking.c @@ -36,6 +36,7 @@ static int find_comm(struct perf_evlist *evlist, const char *comm) (pid_t)event->comm.tid == getpid() && strcmp(event->comm.comm, comm) == 0) found += 1; + perf_evlist__mmap_consume(evlist, i); } } return found; diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c index c4185b9aeb80..a7232c204eb9 100644 --- a/tools/perf/tests/mmap-basic.c +++ b/tools/perf/tests/mmap-basic.c @@ -122,6 +122,7 @@ int test__basic_mmap(void) goto out_munmap; } nr_events[evsel->idx]++; + perf_evlist__mmap_consume(evlist, 0); } err = 0; diff --git a/tools/perf/tests/open-syscall-tp-fields.c b/tools/perf/tests/open-syscall-tp-fields.c index fc5b9fca8b47..524b221b829b 100644 --- a/tools/perf/tests/open-syscall-tp-fields.c +++ b/tools/perf/tests/open-syscall-tp-fields.c @@ -77,8 +77,10 @@ int test__syscall_open_tp_fields(void) ++nr_events; - if (type != PERF_RECORD_SAMPLE) + if (type != PERF_RECORD_SAMPLE) { + perf_evlist__mmap_consume(evlist, i); continue; + } err = perf_evsel__parse_sample(evsel, event, &sample); if (err) { diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c index b8a7056519ac..7923b06ffc91 100644 --- a/tools/perf/tests/perf-record.c +++ b/tools/perf/tests/perf-record.c @@ -263,6 +263,8 @@ int test__PERF_RECORD(void) type); ++errs; } + + perf_evlist__mmap_consume(evlist, i); } } diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c index 0ab61b1f408e..4ca1b938f6a6 100644 --- a/tools/perf/tests/perf-time-to-tsc.c +++ b/tools/perf/tests/perf-time-to-tsc.c @@ -122,7 +122,7 @@ int test__perf_time_to_tsc(void) if (event->header.type != PERF_RECORD_COMM || (pid_t)event->comm.pid != getpid() || (pid_t)event->comm.tid != getpid()) - continue; + goto next_event; if (strcmp(event->comm.comm, comm1) == 0) { CHECK__(perf_evsel__parse_sample(evsel, event, @@ -134,6 +134,8 @@ int test__perf_time_to_tsc(void) &sample)); comm2_time = sample.time; } +next_event: + perf_evlist__mmap_consume(evlist, i); } } diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c index 2e41e2d32ccc..6e2b44ec0749 100644 --- a/tools/perf/tests/sw-clock.c +++ b/tools/perf/tests/sw-clock.c @@ -78,7 +78,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id) struct perf_sample sample; if (event->header.type != PERF_RECORD_SAMPLE) - continue; + goto next_event; err = perf_evlist__parse_sample(evlist, event, &sample); if (err < 0) { @@ -88,6 +88,8 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id) total_periods += sample.period; nr_samples++; +next_event: + perf_evlist__mmap_consume(evlist, 0); } if ((u64) nr_samples == total_periods) { diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c index 28fe5894b061..a3e64876e940 100644 --- a/tools/perf/tests/task-exit.c +++ b/tools/perf/tests/task-exit.c @@ -96,10 +96,10 @@ int test__task_exit(void) retry: while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) { - if (event->header.type != PERF_RECORD_EXIT) - continue; + if (event->header.type == PERF_RECORD_EXIT) + nr_exit++; - nr_exit++; + perf_evlist__mmap_consume(evlist, 0); } if (!exited || !nr_exit) { diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c index 194e2f42ff5d..6c152686e837 100644 --- a/tools/perf/ui/stdio/hist.c +++ b/tools/perf/ui/stdio/hist.c @@ -315,8 +315,7 @@ static inline void advance_hpp(struct perf_hpp *hpp, int inc) } static int hist_entry__period_snprintf(struct perf_hpp *hpp, - struct hist_entry *he, - bool color) + struct hist_entry *he) { const char *sep = symbol_conf.field_sep; struct perf_hpp_fmt *fmt; @@ -338,7 +337,7 @@ static int hist_entry__period_snprintf(struct perf_hpp *hpp, } else first = false; - if (color && fmt->color) + if (perf_hpp__use_color() && fmt->color) ret = fmt->color(fmt, hpp, he); else ret = fmt->entry(fmt, hpp, he); @@ -358,12 +357,11 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size, .buf = bf, .size = size, }; - bool color = !symbol_conf.field_sep; if (size == 0 || size > bfsz) size = hpp.size = bfsz; - ret = hist_entry__period_snprintf(&hpp, he, color); + ret = hist_entry__period_snprintf(&hpp, he); hist_entry__sort_snprintf(he, bf + ret, size - ret, hists); ret = fprintf(fp, "%s\n", bf); @@ -482,6 +480,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, print_entries: linesz = hists__sort_list_width(hists) + 3 + 1; + linesz += perf_hpp__color_overhead(); line = malloc(linesz); if (line == NULL) { ret = -1; diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 2b585bc308cf..9e99060408ae 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -147,6 +147,9 @@ static inline void callchain_cursor_advance(struct callchain_cursor *cursor) struct option; +int record_parse_callchain(const char *arg, struct perf_record_opts *opts); int record_parse_callchain_opt(const struct option *opt, const char *arg, int unset); +int record_callchain_opt(const struct option *opt, const char *arg, int unset); + extern const char record_callchain_help[]; #endif /* __PERF_CALLCHAIN_H */ diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 9b393e7dca6f..49096ea58a15 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -187,7 +187,7 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool, return -1; } - event->header.type = PERF_RECORD_MMAP2; + event->header.type = PERF_RECORD_MMAP; /* * Just like the kernel, see __perf_event_mmap in kernel/perf_event.c */ @@ -198,7 +198,6 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool, char prot[5]; char execname[PATH_MAX]; char anonstr[] = "//anon"; - unsigned int ino; size_t size; ssize_t n; @@ -209,15 +208,12 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool, strcpy(execname, ""); /* 00400000-0040c000 r-xp 00000000 fd:01 41038 /bin/cat */ - n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %x:%x %u %s\n", - &event->mmap2.start, &event->mmap2.len, prot, - &event->mmap2.pgoff, &event->mmap2.maj, - &event->mmap2.min, - &ino, execname); - - event->mmap2.ino = (u64)ino; + n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %*x:%*x %*u %s\n", + &event->mmap.start, &event->mmap.len, prot, + &event->mmap.pgoff, + execname); - if (n != 8) + if (n != 5) continue; if (prot[2] != 'x') @@ -227,15 +223,15 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool, strcpy(execname, anonstr); size = strlen(execname) + 1; - memcpy(event->mmap2.filename, execname, size); + memcpy(event->mmap.filename, execname, size); size = PERF_ALIGN(size, sizeof(u64)); - event->mmap2.len -= event->mmap.start; - event->mmap2.header.size = (sizeof(event->mmap2) - - (sizeof(event->mmap2.filename) - size)); - memset(event->mmap2.filename + size, 0, machine->id_hdr_size); - event->mmap2.header.size += machine->id_hdr_size; - event->mmap2.pid = tgid; - event->mmap2.tid = pid; + event->mmap.len -= event->mmap.start; + event->mmap.header.size = (sizeof(event->mmap) - + (sizeof(event->mmap.filename) - size)); + memset(event->mmap.filename + size, 0, machine->id_hdr_size); + event->mmap.header.size += machine->id_hdr_size; + event->mmap.pid = tgid; + event->mmap.tid = pid; if (process(tool, event, &synth_sample, machine) != 0) { rc = -1; diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index f9f77bee0b1b..e584cd30b0f2 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -545,12 +545,19 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx) md->prev = old; - if (!evlist->overwrite) - perf_mmap__write_tail(md, old); - return event; } +void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx) +{ + if (!evlist->overwrite) { + struct perf_mmap *md = &evlist->mmap[idx]; + unsigned int old = md->prev; + + perf_mmap__write_tail(md, old); + } +} + static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx) { if (evlist->mmap[idx].base != NULL) { diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 880d7139d2fb..206d09339306 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -89,6 +89,8 @@ struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id); union perf_event *perf_evlist__mmap_read(struct perf_evlist *self, int idx); +void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx); + int perf_evlist__open(struct perf_evlist *evlist); void perf_evlist__close(struct perf_evlist *evlist); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 0ce9febf1ba0..9f1ef9bee2d0 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -678,7 +678,6 @@ void perf_evsel__config(struct perf_evsel *evsel, attr->sample_type |= PERF_SAMPLE_WEIGHT; attr->mmap = track; - attr->mmap2 = track && !perf_missing_features.mmap2; attr->comm = track; /* diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 1329b6b6ffe6..ce8dc61ce2c3 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -5,6 +5,7 @@ #include <pthread.h> #include "callchain.h" #include "header.h" +#include "color.h" extern struct callchain_param callchain_param; @@ -175,6 +176,18 @@ void perf_hpp__init(void); void perf_hpp__column_register(struct perf_hpp_fmt *format); void perf_hpp__column_enable(unsigned col); +static inline size_t perf_hpp__use_color(void) +{ + return !symbol_conf.field_sep; +} + +static inline size_t perf_hpp__color_overhead(void) +{ + return perf_hpp__use_color() ? + (COLOR_MAXLEN + sizeof(PERF_COLOR_RESET)) * PERF_HPP__MAX_INDEX + : 0; +} + struct perf_evlist; struct hist_browser_timer { diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index c09e0a9fdf4c..f0692737ebf1 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -1357,10 +1357,10 @@ int debuginfo__find_probe_point(struct debuginfo *self, unsigned long addr, goto post; } + fname = dwarf_decl_file(&spdie); if (addr == (unsigned long)baseaddr) { /* Function entry - Relative line number is 0 */ lineno = baseline; - fname = dwarf_decl_file(&spdie); goto post; } diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 71b5412bbbb9..2ac4bc92bb1f 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -822,6 +822,8 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist, PyObject *pyevent = pyrf_event__new(event); struct pyrf_event *pevent = (struct pyrf_event *)pyevent; + perf_evlist__mmap_consume(evlist, cpu); + if (pyevent == NULL) return PyErr_NoMemory(); diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index a85e4ae5f3ac..c0c9795c4f02 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -282,7 +282,7 @@ static void perl_process_tracepoint(union perf_event *perf_event __maybe_unused, event = find_cache_event(evsel); if (!event) - die("ug! no event found for type %" PRIu64, evsel->attr.config); + die("ug! no event found for type %" PRIu64, (u64)evsel->attr.config); pid = raw_field_value(event, "common_pid", data); diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index cc75a3cef388..95d91a0b23af 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -56,6 +56,17 @@ static void handler_call_die(const char *handler_name) Py_FatalError("problem in Python trace event handler"); } +/* + * Insert val into into the dictionary and decrement the reference counter. + * This is necessary for dictionaries since PyDict_SetItemString() does not + * steal a reference, as opposed to PyTuple_SetItem(). + */ +static void pydict_set_item_string_decref(PyObject *dict, const char *key, PyObject *val) +{ + PyDict_SetItemString(dict, key, val); + Py_DECREF(val); +} + static void define_value(enum print_arg_type field_type, const char *ev_name, const char *field_name, @@ -279,11 +290,11 @@ static void python_process_tracepoint(union perf_event *perf_event PyTuple_SetItem(t, n++, PyInt_FromLong(pid)); PyTuple_SetItem(t, n++, PyString_FromString(comm)); } else { - PyDict_SetItemString(dict, "common_cpu", PyInt_FromLong(cpu)); - PyDict_SetItemString(dict, "common_s", PyInt_FromLong(s)); - PyDict_SetItemString(dict, "common_ns", PyInt_FromLong(ns)); - PyDict_SetItemString(dict, "common_pid", PyInt_FromLong(pid)); - PyDict_SetItemString(dict, "common_comm", PyString_FromString(comm)); + pydict_set_item_string_decref(dict, "common_cpu", PyInt_FromLong(cpu)); + pydict_set_item_string_decref(dict, "common_s", PyInt_FromLong(s)); + pydict_set_item_string_decref(dict, "common_ns", PyInt_FromLong(ns)); + pydict_set_item_string_decref(dict, "common_pid", PyInt_FromLong(pid)); + pydict_set_item_string_decref(dict, "common_comm", PyString_FromString(comm)); } for (field = event->format.fields; field; field = field->next) { if (field->flags & FIELD_IS_STRING) { @@ -313,7 +324,7 @@ static void python_process_tracepoint(union perf_event *perf_event if (handler) PyTuple_SetItem(t, n++, obj); else - PyDict_SetItemString(dict, field->name, obj); + pydict_set_item_string_decref(dict, field->name, obj); } if (!handler) @@ -370,21 +381,21 @@ static void python_process_general_event(union perf_event *perf_event if (!handler || !PyCallable_Check(handler)) goto exit; - PyDict_SetItemString(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel))); - PyDict_SetItemString(dict, "attr", PyString_FromStringAndSize( + pydict_set_item_string_decref(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel))); + pydict_set_item_string_decref(dict, "attr", PyString_FromStringAndSize( (const char *)&evsel->attr, sizeof(evsel->attr))); - PyDict_SetItemString(dict, "sample", PyString_FromStringAndSize( + pydict_set_item_string_decref(dict, "sample", PyString_FromStringAndSize( (const char *)sample, sizeof(*sample))); - PyDict_SetItemString(dict, "raw_buf", PyString_FromStringAndSize( + pydict_set_item_string_decref(dict, "raw_buf", PyString_FromStringAndSize( (const char *)sample->raw_data, sample->raw_size)); - PyDict_SetItemString(dict, "comm", + pydict_set_item_string_decref(dict, "comm", PyString_FromString(thread->comm)); if (al->map) { - PyDict_SetItemString(dict, "dso", + pydict_set_item_string_decref(dict, "dso", PyString_FromString(al->map->dso->name)); } if (al->sym) { - PyDict_SetItemString(dict, "symbol", + pydict_set_item_string_decref(dict, "symbol", PyString_FromString(al->sym->name)); } diff --git a/tools/perf/util/unwind.c b/tools/perf/util/unwind.c index 2f891f7e70bf..5390d0b8862a 100644 --- a/tools/perf/util/unwind.c +++ b/tools/perf/util/unwind.c @@ -39,6 +39,15 @@ UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as, #define dwarf_search_unwind_table UNW_OBJ(dwarf_search_unwind_table) +extern int +UNW_OBJ(dwarf_find_debug_frame) (int found, unw_dyn_info_t *di_debug, + unw_word_t ip, + unw_word_t segbase, + const char *obj_name, unw_word_t start, + unw_word_t end); + +#define dwarf_find_debug_frame UNW_OBJ(dwarf_find_debug_frame) + #define DW_EH_PE_FORMAT_MASK 0x0f /* format of the encoded value */ #define DW_EH_PE_APPL_MASK 0x70 /* how the value is to be applied */ @@ -245,8 +254,9 @@ static int unwind_spec_ehframe(struct dso *dso, struct machine *machine, return 0; } -static int read_unwind_spec(struct dso *dso, struct machine *machine, - u64 *table_data, u64 *segbase, u64 *fde_count) +static int read_unwind_spec_eh_frame(struct dso *dso, struct machine *machine, + u64 *table_data, u64 *segbase, + u64 *fde_count) { int ret = -EINVAL, fd; u64 offset; @@ -255,6 +265,7 @@ static int read_unwind_spec(struct dso *dso, struct machine *machine, if (fd < 0) return -EINVAL; + /* Check the .eh_frame section for unwinding info */ offset = elf_section_offset(fd, ".eh_frame_hdr"); close(fd); @@ -263,10 +274,29 @@ static int read_unwind_spec(struct dso *dso, struct machine *machine, table_data, segbase, fde_count); - /* TODO .debug_frame check if eh_frame_hdr fails */ return ret; } +#ifndef NO_LIBUNWIND_DEBUG_FRAME +static int read_unwind_spec_debug_frame(struct dso *dso, + struct machine *machine, u64 *offset) +{ + int fd = dso__data_fd(dso, machine); + + if (fd < 0) + return -EINVAL; + + /* Check the .debug_frame section for unwinding info */ + *offset = elf_section_offset(fd, ".debug_frame"); + close(fd); + + if (*offset) + return 0; + + return -EINVAL; +} +#endif + static struct map *find_map(unw_word_t ip, struct unwind_info *ui) { struct addr_location al; @@ -291,20 +321,33 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi, pr_debug("unwind: find_proc_info dso %s\n", map->dso->name); - if (read_unwind_spec(map->dso, ui->machine, - &table_data, &segbase, &fde_count)) - return -EINVAL; + /* Check the .eh_frame section for unwinding info */ + if (!read_unwind_spec_eh_frame(map->dso, ui->machine, + &table_data, &segbase, &fde_count)) { + memset(&di, 0, sizeof(di)); + di.format = UNW_INFO_FORMAT_REMOTE_TABLE; + di.start_ip = map->start; + di.end_ip = map->end; + di.u.rti.segbase = map->start + segbase; + di.u.rti.table_data = map->start + table_data; + di.u.rti.table_len = fde_count * sizeof(struct table_entry) + / sizeof(unw_word_t); + return dwarf_search_unwind_table(as, ip, &di, pi, + need_unwind_info, arg); + } + +#ifndef NO_LIBUNWIND_DEBUG_FRAME + /* Check the .debug_frame section for unwinding info */ + if (!read_unwind_spec_debug_frame(map->dso, ui->machine, &segbase)) { + memset(&di, 0, sizeof(di)); + dwarf_find_debug_frame(0, &di, ip, 0, map->dso->name, + map->start, map->end); + return dwarf_search_unwind_table(as, ip, &di, pi, + need_unwind_info, arg); + } +#endif - memset(&di, 0, sizeof(di)); - di.format = UNW_INFO_FORMAT_REMOTE_TABLE; - di.start_ip = map->start; - di.end_ip = map->end; - di.u.rti.segbase = map->start + segbase; - di.u.rti.table_data = map->start + table_data; - di.u.rti.table_len = fde_count * sizeof(struct table_entry) - / sizeof(unw_word_t); - return dwarf_search_unwind_table(as, ip, &di, pi, - need_unwind_info, arg); + return -EINVAL; } static int access_fpreg(unw_addr_space_t __maybe_unused as, diff --git a/tools/testing/selftests/timers/posix_timers.c b/tools/testing/selftests/timers/posix_timers.c index 4fa655d68a81..41bd85559d4b 100644 --- a/tools/testing/selftests/timers/posix_timers.c +++ b/tools/testing/selftests/timers/posix_timers.c @@ -151,7 +151,7 @@ static int check_timer_create(int which) fflush(stdout); done = 0; - timer_create(which, NULL, &id); + err = timer_create(which, NULL, &id); if (err < 0) { perror("Can't create timer\n"); return -1; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index a9dd682cf5e3..1cf9ccb01013 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3091,7 +3091,7 @@ static const struct file_operations *stat_fops[] = { static int kvm_init_debug(void) { - int r = -EFAULT; + int r = -EEXIST; struct kvm_stats_debugfs_item *p; kvm_debugfs_dir = debugfs_create_dir("kvm", NULL); |